Patent Application
20170180214
The present invention relates to sensor networks and on demand predictive remote monitoring, and, particularly, to equipment analysis and cost forecast.
This section is intended to provide a background or context to the invention disclosed below. The description herein may include concepts that could be pursued, but are not necessarily ones that have been previously conceived, implemented or described. Therefore, unless otherwise explicitly indicated herein, what is described in this section is not prior art to the description in this application and is not admitted to be prior art by inclusion in this section. Abbreviations that may be found in the specification and/or the drawing figures are defined below, after the detailed description section.
Equipment defects, such as failures of electrical motors, have a severe impact in the industrial environment due to the importance and the large deployment of equipment in several different industrial sectors, such as metallurgical, and pulp and cellulose. To minimize the occurrence of equipment defects, a Preventive Maintenance schedule is often put in place, where several components are verified and/or replaced based on a maintenance plan provided, for example, by the manufacturer. The Preventive Maintenance plan of a manufacturer is often based on product development tests designed to ensure product reliability in most common use cases. However, the manufacturer's maintenance plan typically cannot address the specificity of each application or allow a more or less stringent maintenance plan, for example, tailored to a client's particular use and environment.
Recently, a more optimized approach has been adopted in industry, which is called Predictive Maintenance. Under the Predictive Maintenance approach, the equipment is frequently monitored for key variables (e.g., power consumption, vibration patterns, temperature, and humidity). By analyzing this data, it is possible to predict which kind of defect the machine most probably will have, and when this problem will eventually cause a failure. The Predictive Maintenance approach can thus be more efficient in terms of cost and defect detection, because unlike Preventive Maintenance, Predictive Maintenance optimizes the maintenance schedule to tend to minimize unnecessary interruptions in the equipment utilization. On the other hand, Predictive Maintenance relies on an efficient collection and analysis of relevant data to determine when maintenance is required and to determine which parts should be repaired or replaced. Conventionally, such data is collected manually, for example, by a technician with suitable analysis equipment.
After the data has been collected, an expert may analyze the collected information, and obtain predictive insights using the available data and mathematical models. This approach takes time and rely on expert experience and subjective factors. The predictive models vary accordingly with the type of variables being monitored (e.g., temperature, humidity, vibration, electrical power), the type of equipment/device being inspected (e.g., bearing rings, electrical motors), and also on the application scenario (e.g., refrigerators, heating devices, conveying belts, lifters, etc.). Due to this complex scenario, defining the most suitable predictive model to be used and the minimum amount of data to be collected to execute a good failure prediction is a challenging task.
The predictive maintenance approach, although more efficient in terms of cost and defect detection, must rely on a sensor data collection to obtain the necessary information to enable the early defect detection. Sensor deployment can be expensive, time consuming and often demands that the industrial production be halted (at least partially) in order to install the sensors and infrastructure such as cabling for data and power. Therefore, it is required taking into account the financial cost behind sensor deployment. For instance, installing hard wired sensors to obtain data and sending an expert to the field to execute equipment analysis is time consuming and expensive. Furthermore, this approach do not allow a continuous analysis over an extended period of time, and/or cannot be easily repeated in other similar scenarios.
Currently, there is a lack of financial methodology on how and/or when to install sensors and the best balance between cost deployment and expected benefits. Given the recent development of solutions and applications in the field of predictive remote monitoring, so far there are no methods to evaluate key aspects of a financial case to support an adequate decision making process in a on demand way.
To provide a business model based on defect prediction service for equipment, it is required to define sensor types and quantity of sensors, remotely activate and control the sensors, and analyze the produced data under a Sensor as a Service business model. The “as a service” solution provision has been thoroughly spread in many productive areas, like software as a service (SaaS). However, the predictive remote monitoring field is still not covered by this kind of solution in some areas, like sensoring. The selection, installation and use of individual sensors besides the corresponding supporting network provided as an on demand “as a service” approach is still an open issue. We foresee this as a viable alternative.
Additionally, there is a need for a mechanism to collect and aggregate diagnostic data pertaining to the use and health of equipment, and provide that collected data for remote analysis, forecasting and reporting.
This section is intended to include examples and is not intended to be limiting. In accordance with an inventive method, sensor data is detected from at least one sensor selected and installed for detecting operating conditions of at least one equipment. The sensor generates sensor data signal which is transmitted to a network device. This device transforms the sensor data into a format for transmission over a network to a network server. The network server receives the signal and performs analysis, reporting and visualization, dependent on the operating conditions.
In accordance with an inventive apparatus, the apparatus comprises of one or more processors, one or more memories (including computer program code), and at least one sensor selected and installed for detecting operating conditions of at least one equipment. A sensor data signal is generated dependent on the sensor data.
In accordance with an inventive computer program product, a computer readable storage medium is provided having computer-readable code embodied thereon. The computer-readable code is executable by an apparatus and causes the apparatus, in response to execution of the computer-readable code, to detect sensor data from at least one sensor selected and installed for detecting operating conditions of at least one equipment. The sensor data includes an operating condition of at least one equipment. The sensor is selected dependent on indications of a user restriction and a predictive model.
The word “exemplary” is used herein to mean “serving as an example, instance, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments. All of the embodiments described in this Detailed Description are non-limiting exemplary embodiments provided to enable persons skilled in the art to make or use the invention and not to limit the scope of the invention which is defined by the claims.
As stated above, in accordance with a non-limiting exemplary embodiment, sensor data is detected from at least one sensor selected and installed for detecting operating conditions of at least one equipment. The sensor data includes an operating condition of at least one equipment. The sensor is selected dependent on indications of a user restriction and a predictive model. A sensor data signal is generated dependent on the sensor data. The sensor data signal is transmitted to a network device for collecting the sensor data and transforming the collected sensor data into a formatted transmission signal having a format for transmission over a network to a network server. The network server receives the formatted transmission signal for performing on-demand service of at least one of analysis, reporting and visualization dependent on the operating condition.
The present invention may be a system, a method, and/or a computer program product. The computer program product may include a computer readable storage medium (or media) having computer readable program instructions thereon for causing a processor to carry out aspects of the present invention.
The computer readable storage medium can be a tangible device that can retain and store instructions for use by an instruction execution device. The computer readable storage medium may be, for example, but is not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. A non-exhaustive list of more specific examples of the computer readable storage medium includes the following: a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanically encoded device, such as punch-cards or raised structures in a groove having instructions recorded thereon, and any suitable combination of the foregoing. A computer readable storage medium, as used herein, is not to be construed as being transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission media (e.g., light pulses passing through a fiber-optic cable), or electrical signals transmitted through a wire.
Computer readable program instructions described herein can be downloaded to respective computing/processing devices from a computer readable storage medium or to an external computer or external storage device via a network, for example, the Internet, a local area network, a wide area network and/or a wireless network. The network may comprise copper transmission cables, optical transmission fibers, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. A network adapter card or network interface in each computing/processing device receives computer readable program instructions from the network and forwards the computer readable program instructions for storage in a computer readable storage medium within the respective computing/processing device.
Computer readable program instructions for carrying out operations of the present invention may be assembler instructions, instruction-set-architecture (ISA) instructions, machine instructions, machine dependent instructions, microcode, firmware instructions, state-setting data, or either source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C++ or the like, and conventional procedural programming languages, such as the “C” programming language or similar programming languages. The computer readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet Service Provider). In some embodiments, electronic circuitry including, for example, programmable logic circuitry, field-programmable gate arrays (FPGA), or programmable logic arrays (PLA) may execute the computer readable program instructions by utilizing state information of the computer readable program instructions to personalize the electronic circuitry, in order to perform aspects of the present invention.
Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer readable program instructions.
These computer readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer readable program instructions may also be stored in a computer readable storage medium that can direct a computer, a programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer readable storage medium having instructions stored therein comprises an article of manufacture including instructions which implement aspects of the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device to cause a series of operational steps to be performed on the computer, other programmable apparatus or other device to produce a computer implemented process, such that the instructions which execute on the computer, other programmable apparatus, or other device implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, dependent upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems that perform the specified functions or acts or carry out combinations of special purpose hardware and computer instructions.
An non-limiting exemplary embodiment of the invention relies on a data collection and interpretation platform for predictive maintenance, based on the deployment of a wireless sensor network (WSN) and/or combination of eventual already installed sensors. This sensor network captures, collects and transmits data from the target equipment. The non-limiting exemplary embodiment uses a cloud computing infrastructure that receives the collected data and automatically chooses the most suitable predictive model, based on the analysis scenario and pre-establish criteria, such as monitoring time and predictive costs.
The non-limiting exemplary embodiment provides a method for quick deployment of remote monitoring services for industrial equipment. Sensor data is captured and intelligent analysis executed to obtain equipment health status under a certain period of time or financial restriction. In addition, the exemplary embodiment provides cost forecasts for the service to achieve such constraints.
The sensor network consist of (1) one or more Network Nodes including several sensors that are attached to the monitored equipment, (2) a Gateway, for collecting the data from the Network Nodes and transforming the collected data to a suitable transmission signal, for example, formatted for transmission over an internet-based network, and (3) a Cloud-based Network Server that executes Data Analysis and make the analysis available, for example, for a Maintenance Team in a suitable format. Each module may include, but is not limited to the following components:
1) Network Node: Set of sensors (vibration, temperature, humidity, etc.), including signal pre-processing features and a Wireless Sensor Network interface
2) Gateway: Transform the Wireless Sensor Network data to a suitable format to be forwarded to the conventional IP network
3) Server: Receives the data from the Gateway and executes Analytics, Reports and Visualization. A non-limiting example of Analytics includes processing the sensor data and constructing models pertaining to the normal operation of a particular equipment, and calculating the probability of a new data sample to be considered to be a sample from the normal operation of the machine or a sample indicating a potential failure in the near future. A non-limiting example of Report includes the generation of documents stating the likelihood of a given equipment to fail in given timeframes. A non-limiting example of Visualization includes providing a visual interface where an expert may inspect sensor data remotely and make diagnoses for a particular equipment.
The non-limiting exemplary embodiment enables the quick deployment of a sensor network that allows a service provider or maintenance team to obtain equipment health status during a certain period of time (e.g., one week or another period that provides enough data to execute the diagnosis).
When setting up the sensor network, a mesh network sensor configuration may be deployed to increase reliability. The sensor network may be a multi-agent network for pre-processing sensor data and dynamic load balance between similar equipments (for example, to decrease production load on equipments with detected anomalies).
The Network Node may include a plurality of sensors forming a sensor network, where the sensor network is configured to pre-process the sensor data to identify a defective operating condition. For example, one or more sensors of the sensor network can be configured to pre-process the sensor data received from one or more sensors of the other sensors of the sensor network. For example, the plurality of sensors can be battery powered. A battery status of each sensor of the plurality of sensors can be determined and sensors having a relatively higher battery charge pre-process the sensor data received from sensors having a relatively lower battery charge. The sensor data can be transmitted to the network device via a publish-subscribe based messaging protocol. The sensors can be in direct or in indirect contact with the equipment being monitored. As examples of an indirect contact sensor, at least one sensor may comprise a thermal imaging camera, capacitive and magnetic sensors.
A cloud-based Network Server is set up and may be used to enable quick deployment and scalability. Sensor data is monitored and the data may be pre-processed before being uploaded to the Network Server. In accordance with the non-limiting exemplary embodiment, real-time or near real-time data collection is possible. Data analysis may be done remote from the physical location of the machines being monitored. The sensor data is transmitted, for example, from the Gateway to the Network Server over an Internet connection. The Network Server has capacities to analyze, report and provide visualization of the monitored operating conditions. This provides fast results, for quicker maintenance intervention, instead of waiting the typical several weeks for log analysis provided by traditional maintenance tools. If a problem is detected the Network Server can provide diagnostics and suggested maintenance intervention using analytics/machine learning/cognitive techniques to provide richer and detailed content results as compared to traditional human-based analysis. If a problem is not detected, then Network Server analysis results on no maintenance is required due to the sensed data.
The non-limiting exemplary embodiment can utilize Cognitive Analytics to derive knowledge of normal manufacturing plant behavior from received sensor data (e.g., machine learning) and input models (e.g., physics equations, cost models, production models). An abnormal behavior of a monitored system can be detected (based on knowledge of normal behavior of the system) to assist in the monitoring and prediction of possible machine failures. Future failures can be predicted and addressed, for example, during the machine's scheduled downtime, to reduce the costly possibility of an equipment being unavailable when needed.
The exemplary embodiment can be used to explain and advise human operators to help make the best decisions, for example, to maximize the equipment asset uptime (e.g., advising to increase production or which maintenance plan is better to put in place). The non-limiting exemplary embodiment can be used to integrate the workforce and workforce usage (for example, to allocate a maintenance staff to first correct urgent issues).
In accordance with the non-limiting exemplary embodiment shown, for example, in
Another non-limiting exemplary embodiment is similar to the embodiment shown in
If the Network Server also has access to the Production Schedule, the Network Server may also provide suggestions of the best maintenance schedule (e.g., a maintenance window that minimizes the impact of the maintenance downtime in the production line) and, eventually, auto execute a load balance, so that a more suitable maintenance schedule can be put in place. For instance, usually on a holiday season, we would avoid as much as possible to stop a production line. Using this dynamic load balance, based on the equipment health status, it is possible to avoid it until the holiday season passes, so that it is more convenient.
The sensor data may be integrated with the Production Schedule, and a preventive dynamic load balancing can be deployed, which could postpone the maintenance for a more favorable maintenance window (e.g., after holiday season). The dynamic load balancing may decrease the production load over equipment with a detected problem and may allow the maintenance to be done after an initial forecast. In this case, the sensor network would still execute the health monitoring of the machines, to generate warnings, in case the wearing level becomes too high and the failure chances becomes considerably high. The integration of the sensor data is done in the Maintenance Server, so that, using a suitable predictive model, estimates the machine health status. Using the machine health status, it is possible to order the Production Server to increase the load on the machines that have a better health status, compensating for a lower load on the machines with worse health status.
Another non-limiting exemplary embodiment is similar to the embodiment shown in
In accordance with another embodiment, similar to the last embodiment, data is exchanged with a production forecast, so that the most energy efficient schedule can be implemented. This is done using a power consumption profile obtained by the data monitoring system over several manufacturing cycles and other variables, such as hourly or seasonal energy cost, so that a higher energy consumption is more likely to be required for a production schedule based on knowing when the cost of energy is lower.
