Patent Grant
11594116
Embodiments of this disclosure relate generally to a fiber optic detection system for detecting conditions within a space and, more particularly, to a fiber optic detection system to detect and identify a source location of smoke or other airborne pollutants in a space.
Although conventional smoke detection systems and high sensitivity smoke detection systems utilizing airflow can detect the presence of smoke or other airborne pollutants, delays often occur in the detection of the smoke or other airborne pollutants. Also, the conventional smoke detection systems and high sensitivity smoke detection systems utilizing airflow can identify the presence of smoke at the detector but do not identify the source location of the smoke or other airborne pollutants.
High sensitivity smoke detection systems based on fiber optics can detect the presence of smoke or other airborne pollutants in real-time. These known high sensitivity smoke detection systems with fiber optics typically use a primary detection node for whole area detection and a secondary node, commonly referred to as a localization or collimated node, for localization based on a spatial index relative the density of the smoke or the airborne pollutant. Although the spatial and temporal evolution of the pattern of the smoke or pollutant is a way to detect smoke or the pollutant and identify the source location, improved capabilities are needed to identify the type of fire or pollutant and to eliminate nuisances caused by detection of non-hazardous conditions or other conditions that may be distinguishable from conditions that would be required (e.g. by building code or other regulation) or desirable to trigger an alarm.
According to an embodiment, a detection system for measuring one or more conditions within an area is provided. The detection system includes at least one fiber optic cable for transmitting light, the at least one fiber optic cable defining a plurality of nodes arranged to measure the one or more conditions. The detection system also includes a control system in communication with the at least one fiber optic cable such that scattered light and a time of flight record is transmitted from the at least one fiber optic cable to the control system, wherein the control system includes a detection algorithm operable to identify a portion of the scattered light associated with each of the plurality of nodes, and when determining an alert the control system transmits data associated with a presence and magnitude of the one or more conditions at each of the plurality of nodes to a cloud computing environment and, in return, receives from the cloud computing environment a notification based on the data transmitted to the cloud computing environment.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the detection system may include wherein the status notification from the cloud computing environment comprises a composition.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the detection system may include wherein the status notification from the cloud computing environment includes a source location based on a determination of a composition and based on a determination of a location within the area.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the detection system may include wherein the status notification from the cloud computing environment includes a source location, a composition, and one of the following: an alert; and an alert and an alarm.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the detection system may include wherein the status notification from the cloud computing environment includes one of the following: an alert; and an alert and an alarm.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the detection system may include wherein the control system transmits an accumulated data stream to the cloud computing environment, and wherein the accumulated data stream includes polarization horizontal and vertical laser signals from a primary node and red and green collimating signals from a collimating node.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the detection system may include wherein the area includes a plurality of zones and the status notification received from the cloud computing environment is also based on data associated with a presence and magnitude of one or more conditions at each of a plurality of other nodes.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the detection system may include wherein the plurality of other nodes correspond with another area, and wherein the other area includes a plurality of other zones monitored by the plurality of other nodes.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the detection system may include wherein the data transmitted to the cloud computing environment is an accumulated data stream includes a nuisance discrimination ratio, wherein the nuisance discrimination ratio is determined by dividing a polarization vertical laser signal and a polarization horizontal laser signal, and wherein the polarization vertical laser and horizontal laser signals are from a primary node.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the detection system may include wherein the data transmitted to the cloud computing environment comprises collimating signals from a collimating node, and the detection system further includes an indication of a moving target within the area from the cloud computing environment based on a comparison of sequential pulses from the data from the collimating node to determine a change in light scattering intensity.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the detection system may include wherein the sequential pulses are subtracted from one another in order to determine the change in light scattering intensity and thereby indicate whether or not a target is moving within the area.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the detection system may include a localization spatial index determined by ignoring data associated with the target within the area wherein the localization spatial index identifies a location of a composition within the area, and wherein the target was determined to be moving less than the composition.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the detection system may include a determination of a solid object nuisance within the area based on a comparison where a number of photons in an accumulated peak data stream associated with a red threshold collimating signal is greater than a number of photons in a peak data stream captured in association with a wall in the area.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the detection system may include a determination of a solid object nuisance within the area based on a comparison where a number of photons in an accumulated peak data stream associated with a red threshold collimating signal is greater than a number of photons in a peak data stream captured in association with a wall in the area.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the detection system may include a determination of smoke within the area based on a comparison of a number of photons in a peak data stream captured in association with a wall of the area and a number of photons in a accumulated peak data stream associated with a red collimating signal, wherein the number of photons captured in association with the wall is greater than the number of photons associated with the red collimating signal.
According to an embodiment, a method of measuring one or more conditions within an area is provided. The method includes receiving at a control system a signal including scattered light and time of flight information associated with a plurality of nodes of a detection system, parsing the time of flight information into zones of the detection system, identifying one or more features within the scattered light signal, and analyzing the one or more features within the scattered light signal to determine a presence of the one or more conditions at the plurality of nodes within the area. The method also includes, in response to analyzing the one or more features within the scattered light signal, determining an alert and transmitting data associated the presence of the one or more conditions at the plurality of nodes within the area to a cloud computing environment. The method also includes receiving from the cloud computing environment a status notification based on the data transmitted to the cloud computing environment.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the method may include wherein transmitting data to the cloud computing environment includes transmitting an accumulated data stream to the cloud computing environment, and wherein the accumulated data stream includes polarization horizontal and vertical laser signals from a primary node and red and green collimating signals from a collimating node.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the method may include wherein transmitting data to the cloud computing environment includes transmitting an accumulated data stream to the cloud computing environment, and wherein the accumulated data stream includes a nuisance discrimination ratio, wherein the nuisance discrimination ratio is determined by dividing a polarization vertical laser signal and a polarization horizontal laser signal, and wherein the polarization vertical laser and horizontal laser signals are from a primary node.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the method may include determining a localization spatial index determined by ignoring data associated with the target within the area wherein the localization spatial index identifies a location of a composition within the area, and wherein the target was determined to be moving less than the composition.
In addition to one or more of the features described herein, or as an alternative, further embodiments of the method may include determining the presence of either a solid object nuisance or smoke within the area based on a comparison between a number of photons in an accumulated peak data stream associated with a red threshold collimating signal and a number of photons in a peak data stream captured in association with a wall in the area, wherein a solid object is present if the number of photons captured in association with the wall is less than the number of photons associated with the red collimating signal, and wherein smoke is present if the number of photons captured in association with the wall is greater than the number of photons associated with the red collimating signal.
The subject matter, which is regarded as the present disclosure, is particularly pointed out and distinctly claimed in the claims at the conclusion of the specification. The foregoing and other features, and advantages of the present disclosure are apparent from the following detailed description taken in conjunction with the accompanying drawings in which:
The detailed description explains embodiments of the present disclosure, together with advantages and features, by way of example with reference to the drawings.
Referring now to the
In addition to smoke or dust, the system 20 may be utilized to monitor or detect pollutants such as volatile organic compounds (VOC's), particle pollutants such as PM2.5 or PM10.0 particles, biological particles, and/or chemicals or gases such as H2, H2S, CO2, CO, NO2, NO3, or the like. Multiple wavelengths may be transmitted by a light source 36 to enable simultaneous detection of smoke, as well as individual pollutant materials. The light emitted by light source 36 for biological detection is a subset of the wavelength range from 280 nm to 550 nm. The light source 36 may emit light at one or more wavelengths between 360 nm and 2000 nm for detection of particulates needed to detect smoke, dust and particle pollutants. In some representative illustrations herein red refers to a wavelength range between 580 nm and 1000 nm and green refers to a wavelength range between 375 nm and 580 nm. The light source 36 may be selected to emit light between 1500 nm and 5000 nm to detect chemicals, gases or VOCs. As an example, a first wavelength may be utilized for detection of smoke, while a second wavelength may be utilized for detection of VOC's. Additional wavelengths may be utilized for detection of additional pollutants, and using multiple wavelength information in aggregate may enhance sensitivity and provide discrimination of gas species from false or nuisance sources. In order to support multiple wavelengths, one or more lasers may be utilized to emit several wavelengths. Alternatively, the control system can provide selectively controlled emission of the light. Utilization of the system 20 for pollutant detection can lead to improved air quality in a space as well as improved safety.
The detection system 20 uses light to evaluate a volume for the presence of a condition. In this specification, the term “light” means coherent or incoherent radiation at any frequency or a combination of frequencies in the electromagnetic spectrum. In an example, the photoelectric system uses light scattering to determine the presence of particles in the ambient atmosphere to indicate the existence of a condition or event. In this specification, the term “scattered light” may include any change to the amplitude/intensity or direction of the incident light, including reflection, refraction, diffraction, absorption, and scattering in any/all directions. In this example, light is emitted into the designated area; when the light encounters an object (a person, smoke particle, or gas molecule for example), the light can be scattered and/or absorbed due to a difference in the refractive index of the object compared to the surrounding medium (air). Depending on the object, the light can be scattered in all different directions. Observing any changes in the incident light, by detecting light scattered by an object for example, can provide information about the designated area including determining the presence of a condition or event.
In its most basic form the detection system 20 includes a single fiber optic cable with at least one fiber optic core. The term fiber optic cable includes any form of optical fiber. As examples, an optical fiber is a length of cable that is composed of one or more optical fiber cores of single-mode, multimode, polarization maintaining, photonic crystal fiber or hollow core. Each cable may have a length of up to 5000 m. A node 34 is located at the termination point of a fiber optic cable and is included in the definition of a fiber optic cable. The detection system 20 can include a plurality of nodes 34. Each node 34 is positioned in communication with the ambient atmosphere. A light source 36, such as a laser diode for example, and a light sensitive device 38, such as a photodiode for example, are coupled to the fiber optic cable. A control system 50 of the detection system 20 including a control unit 52, discussed in further detail below, is utilized to manage the detection system operation and may include control of components, data acquisition, data processing and data analysis.
Rather than having a plurality of individual fiber optic cables separately coupled to the control unit 50, the detection system 20 includes a fiber harness 30 as shown in
Structural rigidity is provided to the fiber harness 30 via the inclusion of one or more fiber harness backbones 31. As shown in the
The light from the light source 36 is transmitted through fiber optic cable and through the node 34 to the surrounding area. The light interacts with one or more particles indicative of a condition and is reflected or transmitted back to the node 34. A comparison of the light provided to the node 34 from the light source 36 and/or changes to the light reflected back to the light sensitive device 38 from the node 34 will indicate whether or not changes in the atmosphere causing the scattering of the light, such as particles for example, are present in the ambient atmosphere adjacent the node 34. The scattered light as described herein is intended to additionally include reflected, transmitted, and absorbed light. Although the detection system 20 is described as using light scattering to determine a condition or event, embodiments where light obscuration, absorption, and fluorescence is used in addition to or in place of light scattering are also within the scope of the disclosure. Upon detection of an event or condition, it will be possible to localize the position of the event because the position of each node 34 within the system 20 is known, as is the time-of-flight for received light, as explained below.
The control system 50 localizes the scattered light, i.e. identifies the scattered light received from each of the plurality of nodes 34, and an analog-to-digital converter (ADC) converts the localized scattered light to processed signals to be received by the control system 50. The control system 50 may use the position of each node 34, specifically the length of the fiber optic cables associated with each node 34 (recorded within control system 50 when the system 20 is installed) and the corresponding time of flight (i.e. the time elapsed between when the light was emitted by the light source 36 and when the scattered light was received by the light sensitive device 38), to associate different portions of the light signal with each of the respective nodes 34 that are connected to that light sensitive device 38. Alternatively, or in addition, the time of flight may include the time elapsed between when the light is emitted from the node 34 and when the scattered light is received back at the node 34. In such embodiments, the time of flight provides information regarding the distance of the object or particle relative to the node 34.
The detection system 20 may be configured to monitor an area, sometimes referred to as a protected space, such as all or part of a room or building, for example. In an embodiment, the detection system 20 is utilized for areas having a crowded environment, such as a data room housing computer servers and/or other equipment. In such embodiments, a separate fiber harness 30 may be aligned with one or more rows of equipment cabinets, and each node 34 therein may be located directly adjacent to one of the equipment towers within the rows. In addition, the nodes 34 may be arranged so as to monitor specific enclosures, electronic devices, or machinery within the crowded environment. Positioning of the nodes 34 in such a manner allows for earlier detection of a condition as well as localization, which may limit the exposure of the other equipment in the room to the same condition. For example, if a hazardous condition such as overheat, smoke and/or fire were to effect one or more specific pieces of equipment in one or more towers, a node 34 physically arranged closest to the tower and/or closest to the equipment may detect the smoke, fire, temperature, and/or flame. Further, since the location of node 34 is known, suppressive or preventative measures may be quickly deployed in the area directly surrounding the node 34, but not in areas where the hazardous condition has not detected. In another application, the detection system 20 may be integrated into an aircraft, such as for monitoring a cargo bay, avionics rack, lavatory, or another confined region of the aircraft that may be susceptible to fires or other events.
The control system 50 of the detection system 20 is utilized to manage the detection system operation and may include control of components, data acquisition, data processing and data analysis. The control system 50, illustrated in
The control unit 52, and in some embodiments, the processor 54, may be coupled to the at least one light source 36 and the at least one light sensitive device 38 via connectors. The light sensitive device 38 is configured to convert the scattered light received from a node 34 into a corresponding signal receivable by the processor 54. In an embodiment, the signal generated by the light sensing device 38 is an electronic signal. The signal output from the light sensing device 38 is then provided to the control unit 52 for processing via the processor 54 using an algorithm 58 to determine whether a predefined condition is present.
With reference back to
Data representative of the output from each APD sensor 64 in the APD array 66 may be periodically taken by a switch 68, or alternatively, may be collected simultaneously. A data acquisition module 67 collects the electronic signals from the APD and associates the collected signals with data relevant to a determination of location, time, and likelihood of nuisance or of monitored condition; as an example time, frequency, location or node. In an exemplary embodiment, the electronic signals from the APD sensor 64 are synchronized to the laser modulation such that the electrical signals are collected for a period of time that starts when the laser is pulsed to several microseconds after the laser pulse. The data will be collected and processed by the processor 54 to determine whether any of the nodes 34 indicates the existence of a predefined condition or event. In an embodiment, only a portion of the data output by the sensor array 66 is collected, for example the data from a first APD sensor 64 associated with a first fiber harness 30. The switch 68 may therefore be configured to collect information from the various APD sensors 64 of the sensor array 66 sequentially. While the data collected from a first APD sensor 64 is being processed to determine if an event or condition has occurred, the data from a second APD sensor 64 of the sensor array 66 may be collected and provided to the processor 54 for analysis. When a predefined condition or event has been detected from the data collected from one of the APD sensors 64, the switch 68 may be configured to provide additional information from the same APD sensor 64 to the processor 54 so as to track the condition or event at the location and/or under the conditions the condition or event was detected.
In an embodiment, a single control unit 52 can be configured with one or multiple APDs and the corresponding light sensitive devices 38 necessary to support multiple fiber harnesses 30. For example, 16 APDs with corresponding light sensitive devices 38 necessary to support 16 fiber harnesses 30, each fiber harness 30 having up to 30 nodes, resulting in a system with up to 480 nodes that can cover an area being monitored of up to 5000 square meters m2. However, it should be understood that the system can be reconfigured to support more or fewer nodes to cover large buildings with up to a million m2 or small enclosures with 5 m2. The larger coverage area enables reducing or removing fire panels, high sensitivity smoke detectors and/or control panels, which may reduce cost and/or complexity of an installed hazard control system.
The light sensing device 38 generates a signal in response to the scattered light received by each node 34, and provides that signal to the control unit 52 for further processing. Using one or more algorithms 58 executed by the processor 54, each signal representing the scattered light received by each of the corresponding nodes 34 is evaluated to determine whether the light at the node 34 is indicative of a predefined condition, such as smoke, for example. The signal indicative of scattered light is parsed into a plurality of signals based on their respective originating node 34. One or more characteristics or features (pulse features) of the signal may be determined. Examples of such features include, but are not limited to, a peak height, an area under a curve defined by the signal, statistical characteristics such as mean, variance, and/or higher-order moments, correlations in time, frequency, space, and/or combinations thereof, and empirical features as determined, by deep learning, dictionary learning, and/or adaptive learning and the like, to be relevant to or to be added to the predefined set of monitored conditions.
Referring now to
The light scattering information collected from each node 34, may be evaluated individually to determine a status at each the node 34, and initiate an alarm if necessary. Alternatively, or in addition, the data from each node 34 may be analyzed in aggregate, such as via cooperative data fusion for example, to perform a more refined analysis when determining whether to initiate an alarm, sometimes referred to as “object refinement.”
With reference to
In one or more embodiments, as shown in
A user interface on the control unit 52, a laptop or on another device, may display the detection status of one or more of the nodes 34. For example, an alarm may be generated for zone 4 (whole area detection) based on scattered light measured by the primary and secondary nodes. By parsing the time of flight record into zones associated with the one or more corresponding nodes 34, if smoke or another event occurs within a zone, a change in the light scattering will be detected within that zone.
Through application of the data processing, the features may then be further processed by using, for example, smoothing, Fourier transformation or cross correlation. In an embodiment, the processed data is then sent to the detection algorithm to determine whether or not the signal indicates the presence and/or magnitude of a condition or event at a corresponding node 34. This evaluation may be a simple binary comparison that does not identify the magnitude of deviation between the characteristic and a threshold. The evaluation may also be a comparison of a numerical function of the characteristic or characteristics to a threshold. The threshold may be determined a priori or may be determined from the signal. The determination of the threshold from the signal may be called background learning.
Background learning may be accomplished by adaptive filtering, model-based parameter estimation, statistical modeling, and the like. In some embodiments, if one of the identified features does not exceed a threshold, the remainder of the detection algorithm is not applied in order to reduce the total amount of processing performed during the detection algorithm. In the event that the detection algorithm indicates the presence of the condition at one or more nodes 34, an alarm or fire suppression system may, but need not be activated.
In addition to evaluating the signals generated from each node 34 individually, the processor 54 may additionally be configured to evaluate the plurality of signals or characteristics thereof collectively, such as through a data fusion operation to produce fused signals or fused characteristics. The data fusion operation may provide information related to time and spatial evolution of an event or condition. As a result, a data fusion operation may be useful in detecting a lower level event, insufficient to initiate an alarm at any of the nodes 34 individually. For example, in the event of a slow burning fire, the light signal generated by a small amount of smoke near each of the nodes 34 individually may not be sufficient to initiate an alarm. However, when the signals from the plurality of nodes 34 are reviewed in aggregate, the increase in light returned to the light sensitive device 38 from multiple nodes 34 may indicate the occurrence of an event or the presence of an object not otherwise detected. In an embodiment, the fusion is performed by Bayesian Estimation. Alternatively, linear or non-linear joint estimation techniques may be employed such as maximum likelihood (ML), maximum a priori (MAP), non-linear least squares (NNLS), clustering techniques, support vector machines, decision trees and forests, and the like.
Thus, one or more signals including scattered light and raw time of flight information are received by the control unit 52 from one or more light sensitive devices 38. In response to this information, the control unit 52, parses the time of flight information into information associated with individual zones and/or nodes of the detection system 20. The control unit 52 also processes the scattered light information contained within each signal to identify one or more features within the scattered light. These features can then be used by a detection algorithm to process the information associated with a single node or zone, or alternatively or additionally, data fusion may be performed to analyze the information from several nodes or zones. The output is then used to determine an alarm status and, in instances where the alarm status would prompt initiation of an alarm, e.g., based upon comparison of the alarm status to known or pre-populated conditions within a table (or other suitable data structure), initiate an alarm.
The processing unit 54 of the control unit 52 may include a field-programmable gate array board (FPGA) wherein the FPGA firmware performing the data processing of the control unit 52 of the control system 50. Also, the FPGA firmware may include laser drivers for driving the lasers and a laser firing and data sampler timer for collecting laser firing data associated with the horizontal and vertical polarization lasers of the primary node received at a detector of the control unit 52 and the collimating red and green lasers of the collimating received at another detector of the control unit 52. The laser driver is associated with an analog digital converter (ADC) to correlate the detectors firing and the lasers firing so that the collected data with information regarding the detection at the primary and secondary nodes which is then parsed out to determine where to look for smoke or pollutants. In one or more embodiments, pulsed data is collected at 2000 ns for each channel and 1 pulse of accumulated data contains 4 channels. The FPGA board also preferably includes an Ethernet controller for transmitting, via Ethernet using User Datagram Protocol (UDP) or Transmission Control Protocol (TCP), a data stream to a cloud computing environment for performing cloud-based computing. However, other reliable protocols may instead be used.
As shown in
At 607, the location or composition of the particulates in the environment is determined. The location of particulates may be determined using a localization process as described herein. Composition classification of particulates may be achieved using a polarization node algorithm as described herein. At 609, the change in the environment detected at 605 and 607 is reported, to one or both of a central controller or a cloud commuting environment. At 611, an alarm status to report on the change in the environment is determined. The alarm status may be determined using a decision tree, ensemble, artificial intelligence, Bayesian estimation or parallel decision making approach. Results of the localization and composition from 607 may also be communicated with the alarm decision.
The control unit 52 analyzes a polarization horizontal signal and a polarization vertical signal from the polarization node detector and a green collimating node signal and a red collimating node signal from the collimating node detector (
At 630, one or both of the data stream from the polarization node detector and the collimating node detector is used to detect if a solid object is present. A process to derive a solid object indicator is shown in
The true or false conditions at each of blocks 610, 620 and 630 are combined at 640 to determine if further analysis is warranted. If all of the results of blocks 610, 620 and 630 are true, this indicates that further analysis is needed to detect an event. Otherwise, the process continues monitoring the data streams until the conditions at blocks 610, 620 and 630 are all true.
The process proceeds from block 640 to block 650 and block 660 to classify the light scattering. In block 650, the data from the collimating node detector is analyzed to determine a data localization value of particles using a sub-routine as shown in
In block 660, the data from a polarization node detector is analyzed to determine a polarization ratio using a sub-routine as shown in
At block 670, the results of block 650 and block 660 are analyzed to determine if an alarm condition is present. Block 670 considers whether the data localization value exceeds the threshold at block 650 and whether the polarization ratio is greater than the upper limit or less than the lower limit at block 670. Block 670 may include using a variety of techniques, including a decision tree, ensemble, artificial intelligence, Bayesian estimation or parallel decision making to determine alarm status. If an alarm condition is detected, the results of block 650 and block 660 are passed to the cloud with the alarm decision as shown at 680. An alarm may also be indicated visually on the control unit 52 or transmitted to a personal device, computer or other device capable of indicating the alert and the alarm.
If the polarization horizontal signal exceeds the background threshold at block 750, the polarization horizontal signal is processed at block 760 where a moving window is used to eliminate transient signals. The moving window applied at block 760 requires multiple successive signals to be present during a period of time, thereby eliminating transient signals. The polarization horizontal signal is then passed to block 770 where the signals are averaged using a moving window. The polarization vertical signal is processed at block 740, where the polarization vertical signal is averaged using a moving window.
At block 780, the vertical polarization signal is divided by the horizontal polarization signal to define the polarization ratio. The polarization ratio of block 780 is then scaled in block 782. In block 784, an upper limit (e.g., 1.4) is utilized to identify the presence of a smoldering fire when the polarization ratio exceeds the upper limit. When the polarization ratio exceeds the upper limit, a smoldering fire is indicated at block 788. In 786, a lower limit (e.g., 0.8) is utilized to identify the presence of a flaming fire when the polarization ratio is less than the lower limit. When the polarization ratio is less than the lower limit, a flaming fire is indicated at block 790. If neither condition in block 786 and block 784 is met, than the output is deemed a nuisance. In addition, the polarization ratio is output.
The polarization ratio output can be utilized remotely to provide additional classification of the fire source. The classification of the light signals from the polarization node enables potential smoke source identification. In data center applications, flaming fire sources tend to be high voltage components such as UPS, power cables and fans. Whereas, smoldering fires come from low voltage components such as communication cables, servers and server racks. Nuisances are often times introduced from stirring up dust or from external to the environment. The additional classification of source is provided based on the output of the algorithm using lookup tables.
If the collimated red signal exceeds the background threshold at block 750, the collimated red signal is processed at block 760 where a moving window is used to eliminate transient signals. The moving window applied at block 760 requires multiple successive signals to be present during a period of time, thereby eliminating transient signals. The collimated red signal is then passed to block 820 where the collimated red signal is normalized. The collimated green signal is processed at block 830, where the collimated green signal is normalized.
At block 840, the normalized collimated red signal and the normalized collimated green signal are subtracted from each other. At block 840, two sequential pulses are subtracted from one another to determine changes in light scattering intensity where the result of the operating indicates whether or not an object, smoke or particulate cloud is moving within a field of view. Because smoke and pollutants are stochastic or random in pattern, the result of the subtraction operation results in a different signal regardless of how fast the pulsing is. For example, a person or a moving hand in the field of view appears as a stationary object compared to smoke when pulsing every 6 microseconds. The output of block 840 is processed by a moving target indication (MTI) filter to remove the effect of stationary objects from the output of block 840. In block 850, the signal from block 840 is amplified to yield the data localization value.
In block 860, the data localization value is compared to a threshold (e.g., 6) and is evaluated to determine if particulates are present. If the data localization value is greater than the threshold, then at block 870 a localization spatial index is reported. The location of particulates is analyzed to using signal analysis approaches, either separately or together, to determine particulate location. Signal analysis approaches include time or spatial analysis using thresholding, derivatives, FFT, correlation or persistence. A decision tree, ensemble, artificial intelligence, Bayesian estimation or parallel decision making is then employed to determine location of the particulates in an area. The data localization value may also be an output of the processing.
From block 920, the accumulated peak data stream and an accumulated shot start is passed to block 944 where a maximum value of the accumulated peak data is captured. A block 948, the process determines if the red collimating node signal is greater than 4 times standard deviation of background threshold. The background threshold can be set using a multiplication factor of the standard deviation added to the mean. If the red collimating node signal is greater than 4 times standard deviation of background signal, block 948 generates variable y=“1.” If the red collimating node signal is not greater than 4 times standard deviation of background signal, block 948 generates variable y=“0.” Arbiter 940 includes arbiter logic where, as shown in
Turning to
One or more aspects or features of the present invention may be implemented using cloud computing. Nonetheless, it is understood in advance that although this disclosure includes a detailed description on cloud computing, implementation of the teachings recited herein are not limited to a cloud computing environment. Rather, embodiments of the present invention are capable of being implemented in conjunction with any other type of computing environment now known or later developed.
Cloud computing is a model of service delivery for enabling convenient, on-demand network access to a shared pool of configurable computing resources (e.g. networks, network bandwidth, servers, processing, memory, storage, applications, virtual machines, and services) that can be rapidly provisioned and released with minimal management effort or interaction with a provider of the service. This cloud model may include at least five characteristics, at least three service models, and at least four deployment models.
Characteristics are as follows:
On-demand self-service: a cloud consumer can unilaterally provision computing capabilities, such as server time and network storage, as needed automatically without requiring human interaction with the service's provider.
Broad network access: capabilities are available over a network and accessed through standard mechanisms that promote use by heterogeneous thin or thick client platforms (e.g., mobile phones, laptops, and PDAs).
Resource pooling: the provider's computing resources are pooled to serve multiple consumers using a multi-tenant model, with different physical and virtual resources dynamically assigned and reassigned according to demand. There is a sense of location independence in that the consumer generally has no control or knowledge over the exact location of the provided resources but may be able to specify location at a higher level of abstraction (e.g., country, state, or datacenter).
Rapid elasticity: capabilities can be rapidly and elastically provisioned, in some cases automatically, to quickly scale out and rapidly released to quickly scale in. To the consumer, the capabilities available for provisioning often appear to be unlimited and can be purchased in any quantity at any time.
Measured service: cloud systems automatically control and optimize resource use by leveraging a metering capability at some level of abstraction appropriate to the type of service (e.g., storage, processing, bandwidth, and active user accounts). Resource usage can be monitored, controlled, and reported providing transparency for both the provider and consumer of the utilized service.
Software as a Service (SaaS): the capability provided to the consumer is to use the provider's applications running on a cloud infrastructure. The applications are accessible from various client devices through a thin client interface such as a web browser (e.g., web-based e-mail). The consumer does not manage or control the underlying cloud infrastructure including network, servers, operating systems, storage, or even individual application capabilities, with the possible exception of limited user-specific application configuration settings.
Platform as a Service (PaaS): the capability provided to the consumer is to deploy onto the cloud infrastructure consumer-created or acquired applications created using programming languages and tools supported by the provider. The consumer does not manage or control the underlying cloud infrastructure including networks, servers, operating systems, or storage, but has control over the deployed applications and possibly application hosting environment configurations.
Infrastructure as a Service (IaaS): the capability provided to the consumer is to provision processing, storage, networks, and other fundamental computing resources where the consumer is able to deploy and run arbitrary software, which can include operating systems and applications. The consumer does not manage or control the underlying cloud infrastructure but has control over operating systems, storage, deployed applications, and possibly limited control of select networking components (e.g., host firewalls).
Deployment Models are as follows:
Private cloud: the cloud infrastructure is operated solely for an organization. It may be managed by the organization or a third party and may exist on-premises or off-premises.
Community cloud: the cloud infrastructure is shared by several organizations and supports a specific community that has shared concerns (e.g., mission, security requirements, policy, and compliance considerations). It may be managed by the organizations or a third party and may exist on-premises or off-premises.
Public cloud: the cloud infrastructure is made available to the general public or a large industry group and is owned by an organization selling cloud services.
Hybrid cloud: the cloud infrastructure is a composition of two or more clouds (private, community, or public) that remain unique entities but are bound together by standardized or proprietary technology that enables data and application portability (e.g., cloud bursting for load-balancing between clouds).
A cloud computing environment is service oriented with a focus on statelessness, low coupling, modularity, and semantic interoperability. At the heart of cloud computing is an infrastructure comprising a network of interconnected nodes.
Referring now to
Referring now to
Hardware and software layer 1260 includes hardware and software components. Examples of hardware components include: mainframes 1261; RISC (Reduced Instruction Set Computer) architecture based servers 1262; servers 1263; blade servers 1264; storage devices 1265; and networks and networking components 1266. In some embodiments, software components include network application server software 1267 and database software 1268.
Virtualization layer 1270 provides an abstraction layer from which the following examples of virtual entities may be provided: virtual servers 1271; virtual storage 1272; virtual networks 1273; including virtual private networks; virtual applications and operating systems 1274; and virtual clients 1275.
In one example, management layer 1280 may provide the functions described below. Resource provisioning 1281 provides dynamic procurement of computing resources and other resources that are utilized to perform tasks within the cloud computing environment. Metering and pricing 1282 provide cost tracking as resources are utilized within the cloud computing environment, and billing or invoicing for consumption of these resources. In one example, these resources may comprise application software licenses. Security provides identity verification for cloud consumers and tasks, as well as protection for data and other resources. User portal 1283 provides access to the cloud computing environment for consumers and system administrators. Service level management 1284 provides cloud computing resource allocation and management such that required service levels are met. Service Level Agreement (SLA) planning and fulfillment 1285 provide pre-arrangement for, and procurement of, cloud computing resources for which a future requirement is anticipated in accordance with an SLA
Workloads layer 1290 provides examples of functionality for which the cloud computing environment may be utilized. Examples of workloads and functions which may be provided from this layer include: mapping and navigation 1291; software development and lifecycle management 1292; virtual classroom education delivery 1293; data analytics processing 1294; transaction processing 1295; and failure diagnostics processing 1296, for performing one or more processes for receiving accumulated data streams from one or more detection systems 20, providing notifications such as status reports back to the one or more detection systems 20, analyzing and generating compositions, which includes localization information, determining types of smoke or pollutants located within a or protected area based on the accumulated data stream and other received information from detection systems, and for performing one or more processes for determining source location and other failure diagnostics. The status notifications may also include alerts or a combination of alerts and alarms.
While the disclosure has been described in detail in connection with only a limited number of embodiments, it should be readily understood that the disclosure is not limited to such disclosed embodiments. Rather, the invention can be modified to incorporate any number of variations, alterations, substitutions or equivalent arrangements not heretofore described, but which are commensurate with the spirit and scope of the disclosure. Additionally, while various embodiments of the disclosure have been described, it is to be understood that aspects of the disclosure may include only some of the described embodiments. Accordingly, the disclosure is not to be seen as limited by the foregoing description, but is only limited by the scope of the appended claims.
This application is a US National Stage of International Application No. PCT/US2020/036642 filed Jun. 8, 2020, which claims the benefit of U.S. Application No. 62/867,550, filed on Jun. 27, 2019, which are incorporated herein by reference in their entirety.
| Filing Document | Filing Date | Country | Kind |
|---|---|---|---|
| PCT/US2020/036642 | 6/8/2020 | WO |
| Publishing Document | Publishing Date | Country | Kind |
|---|---|---|---|
| WO2020/263549 | 12/30/2020 | WO | A |
| Number | Name | Date | Kind |
|---|---|---|---|
| 4839527 | Leitch | Jun 1989 | A |
| 5898377 | Adachi | Apr 1999 | A |
| 7495573 | Tice et al. | Feb 2009 | B2 |
| 7769204 | Privalov | Aug 2010 | B2 |
| 7804522 | Haynes | Sep 2010 | B2 |
| 7805002 | Privalov | Sep 2010 | B2 |
| 8208723 | Yamagishi et al. | Jun 2012 | B2 |
| 8497904 | Jelinek et al. | Jul 2013 | B2 |
| 8983180 | Ko et al. | Mar 2015 | B2 |
| 9530074 | Newton et al. | Dec 2016 | B2 |
| 9805472 | Chou et al. | Oct 2017 | B2 |
| 10593181 | Stadler | Mar 2020 | B2 |
| 20060202847 | Oppelt et al. | Sep 2006 | A1 |
| 20090219389 | Marbach | Sep 2009 | A1 |
| 20150371515 | Zribi et al. | Dec 2015 | A1 |
| 20170032660 | El-Mankabady | Feb 2017 | A1 |
| 20170206764 | Zribi et al. | Jul 2017 | A1 |
| 20180136053 | Birnkrant | May 2018 | A1 |
| Number | Date | Country |
|---|---|---|
| 3321906 | May 2018 | EP |
| 2018089654 | May 2018 | WO |
| Entry |
|---|
| Appana et al.; “A Video-Based Smoke Detection Using Smoke Flow Pattern and Spatial-Temporal Energy Analyses for Alarm Systems”; Information Sciences; vols. 418-419; Dec. 2017; pp. 91-101. |
| Byoungchul et al.; “Wildfire Smoke Detection Using Temporospatial Features and Random Forest Classifiers” Optical Engineering; vol. 51, Issue 1; Jan. 2012; 2 Pages. |
| Habiboglu et al.; “Flame Detection Method in Video Using Covariance Descriptors”; IEEE; May 22-27, 2011; pp. 1817-1820. |
| International Search Report and Written Opinion for International Application No. PCT/US2020/036642; International Filing Date Jun. 8, 2020; dated Sep. 25, 2020 (pp. 1-14). |
| Lee et al.; “Smoke Detection Using Spatial and Temporal Analyses”; International Journal of Innovative Computing, Information and Control; vol. 8, No. 6; Jun. 2012; 23 Pages. |
| Sagar et al. “Smoke Detection in Digital Frames”; International Research Journal of Engineering and Technology; vol. 5, Issue 4; Apr. 2018; 5 Pages. |
| Number | Date | Country | |
|---|---|---|---|
| 20220189272 A1 | Jun 2022 | US |
| Number | Date | Country | |
|---|---|---|---|
| 62867550 | Jun 2019 | US |
