Patent Application
20240359946
The invention concerns in general the technical field of elevators.
Elevators are implemented from a plurality of entities, such as components, which are selected during the designing phase. The entities of an elevator system are selected so that they, either alone or in combination with one or more other entities, generate an effect enabling the elevator system to meet its requirements in its intended use. As a result, a list of materials, or so-called bill-of-materials, BOM, is generated which contains the entities from which the elevator system is built to.
The problem with the above described way of generating the list is that it is prone to errors. This is partly because it may turn out that some listed entities are changed during the construction phase, but such an information is not updated into the list of materials. Moreover, since the elevators are continuously maintained and repaired, and it may occur that some original entities of the elevator, such as one or more components in the elevator shaft, are changed to some other entities, but not to original ones, and such information does not end up to the list of materials. A still further problem is that even if the list of materials exists and it is up-to-date there may occur deviation in the installation of new components so that replaced components are not installed in the same position e.g. in the shaft as the original ones. This, in turn, may cause disturbance, such as vibration experienced by the passengers during the travel.
From a manufacturer's point of view it would be advantageous to keep on track on the entities included to elevator systems during its lifetime and on the installation setup in general. On the other hand, such a task is challenging to realize when there is a vast amount of elevators to follow up. Hence, there is a need to introduce solutions which improve the situation at least in part to keep on track on at least some aspects of an installation of the elevator system during its lifetime, and which solutions may even be configured to generate information for further use.
The following presents a simplified summary in order to provide basic understanding of some aspects of various invention embodiments. The summary is not an extensive overview of the invention. It is neither intended to identify key or critical elements of the invention nor to delineate the scope of the invention. The following summary merely presents some concepts of the invention in a simplified form as a prelude to a more detailed description of exemplifying embodiments of the invention.
An object of the invention is to present a computer-implemented method, an apparatus, a computer program, and a system for detecting an entity of an elevator system.
The objects of the invention are reached by a computer-implemented method, an apparatus, a computer program, and a system as defined by the respective independent claims.
According to a first aspect, a computer-implemented method for detecting an entity of an elevator system based on data in a representation generated from measurement data gathered over a travel of an elevator car is provided, the method comprising:
For example, the number of vibrational fingerprints of the reference data may be formed in at least one of the following manner: by simulating an operation of a number of elevator systems, by identifying the number of vibrational fingerprints of the reference data from representations in a frequency domain generated from history data collected from a number of elevator systems.
The determining if the representation comprises the number of portions corresponding to the reference data may e.g. be performed on a basis of a frequency range and amplitude values of frequencies in the frequency range.
Moreover, the generation of the representation in the frequency domain may be performed based on the measurement data descriptive of a travel of an elevator car at a constant speed.
The measurement data may be received from at least one sensor configured to measure vibration experienced by the elevator car.
Still further, the representation in the frequency domain may be generated in a form of spectrogram.
The method my further comprise:
In some examples, at least the determining if the representation comprises the number of portions corresponding to reference data may be performed with a machine-learning model, the machine-learning model being trained with the reference data to perform the determining.
According to a second aspect, an apparatus for detecting an entity of an elevator system based on data in a representation generated from measurement data gathered over a travel of an elevator car is provided, the apparatus configured to:
The apparatus may be configured to form the number of vibrational fingerprints of the reference data in at least one of the following manner: by simulating an operation of a number of elevator systems, by identifying the number of vibrational fingerprints of the reference data from representations in a frequency domain generated from history data collected from a number of elevator systems.
The apparatus may also be configured to perform the determining if the representation comprises the number of portions corresponding to the reference data on a basis of a frequency range and amplitude values of frequencies in the frequency range.
For example, the apparatus may be configured to perform the generation of the representation in the frequency domain based on the measurement data descriptive of a travel of an elevator car at a constant speed.
Moreover, the apparatus may be configured to receive the measurement data from at least one sensor configured to measure vibration experienced by the elevator car.
The apparatus may be configured to generate the representation in the frequency domain in a form of spectrogram.
The apparatus may further be configured to:
Still further, the apparatus may be configured to perform at least the determining if the representation comprises the number of portions corresponding to reference data with a machine-learning model, the machine-learning model being trained with the reference data to perform the determining.
According to some examples, the apparatus may be implemented with one or more computing devices.
According to a third aspect, a computer program is provided, the computer program comprising computer readable program code configured to cause performing of the method according to the first aspect as defined above when the computer readable program code is run on one or more computing apparatuses.
According to a fourth aspect, a system comprising an elevator system and a computing system communicatively connected to each other is provided, the computing system comprises an apparatus according to the second aspect as defined above.
Furthermore, the elevator system may comprise at least one sensor configured to generate measurement data descriptive of a vibration of an elevator car experienced during a travel of the elevator car.
The expression “a number of” refers herein to any positive integer starting from one, e.g. to one, two, or three.
The expression “a plurality of” refers herein to any positive integer starting from two, e.g. to two, three, or four.
Various exemplifying and non-limiting embodiments of the invention both as to constructions and to methods of operation, together with additional objects and advantages thereof, will be best understood from the following description of specific exemplifying and non-limiting embodiments when read in connection with the accompanying drawings.
The verbs “to comprise” and “to include” are used in this document as open limitations that neither exclude nor require the existence of unrecited features. The features recited in dependent claims are mutually freely combinable unless otherwise explicitly stated. Furthermore, it is to be understood that the use of “a” or “an”, i.e. a singular form, throughout this document does not exclude a plurality.
The embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings.
The specific examples provided in the description given below should not be construed as limiting the scope and/or the applicability of the appended claims. Lists and groups of examples provided in the description given below are not exhaustive unless otherwise explicitly stated.
An operating principle of the system as schematically illustrated in
The measurement data obtained from the elevator system 110 is advantageously such which represents its operation in a required manner over an operational cycle of the elevator wherein the operational cycle may refer to a travel of the elevator car 120 in the elevator shaft. The travel may correspond to a travel over a whole length of the travel path, i.e. the length of the shaft defined e.g. by the ground floor and the top floor, or any sub-section between the two extreme ends. For the purpose of the present invention the measurement data collected during the travel of the elevator car 120 is advantageously such that it represents vibrations experienced by the elevator car 120 during the travel. The measurement system for collecting the vibrational information of the elevator car 120 may be arranged so that at least one applicable sensor 140 is associated to the elevator car 120, such as by mounting the at least one sensor on a roof of the elevator car 120. The applicable sensor may be an accelerometer 140, or a plurality of accelerometers, or any other type of sensor configured to generate measurement data on the vibration of the elevator car 120. An example of another type of sensor may be a proximity sensor arranged to measure a distance between two entities wherein the distance changes due to the experienced vibration. Advantageously the implementation is such that the sensor 140, or the plurality of sensors 140, enable a measurement of the acceleration, comprising also deceleration, 3-dimensionally so as to generate comprehensive data of the vibration over the travel of the elevator car 120. In other words, the measurement generates data descriptive of the vibration experienced by the elevator car 120 during the entire travel. Due to that the elevator car 120 is accelerated to a constant speed when initiating the travel from a floor and decelerated when approaching to a landing such inputs to the at least one sensor 140 may be filtered out from the measurement data or to arrange that a generation of the measurement data is performed only over the travel at the constant speed. By taking such an approach it may be concluded that the measurement data represents vibration experienced by the elevator car 120 caused by different excitation sources, such as misalignments or shortcuts due to installation accuracy, component malfunctions, worn-out of components and so on. In addition to the measurement of the vibration a position of the elevator car 120 in the shaft is recorded so that the vibration experienced by the elevator car 120 is mapped with a position of the elevator car 120. The position data may be obtained from any known system applied in elevators for generating the positional data of the elevator car 120 in the elevator shaft. For example, it may be based on a determination of the position with a sensor associated to the elevator car 120 and/or to elevator shaft (e.g. switches), or it may be performed on a basis of information obtainable from an encoder configured to generate data descriptive of a rotation of an electric motor of the elevator. Moreover, since the measurement is performed in time domain the measurement values may also be associated with time stamps indicative of an instant of time of a measurement of each value. Now, for preparing the measurement data for the purpose of the present invention a signal processing may be applied in a known manner to the measurement data so as to generate a representation of the vibration in a frequency domain over the time the speed of the elevator car 120 is constant wherein the position of the elevator car 120 is known at each instant of time over the time the speed of the elevator car 120 is constant. The signal processing may be performed by one or more computing units 160 of the computing system 150 which computing unit 160 is provided with an access to all measurement data as described. The access may be provided so that the measurement data, and any other data, is delivered to the computing unit 160 from the elevator system 110, e.g. through the elevator controller 130 either as a raw data, or pre-processed in any manner, or the data is continuously stored in data storage 170 to which the computing unit 160, or computing units 160, involved in the data processing is provided with the access.
It is now assumed that the collection of the measurement data is performed in a manner that the vibrational data with respect to a position of the elevator car 120 is received by the computing unit 160 and further aspects are now discussed by referring to
In response to a generation of the representation as described, i.e. the spectrogram, the computing unit 160 may be configured to determine 220 if the representation comprises one or more portions corresponding to reference data. The reference data defines a number of vibrational fingerprints each of which are representations descriptive of a vibration generable by an entity of an elevator system. In other words, the vibrational fingerprints may be understood as accurate representation of a vibration of a certain entity, such as a component, of an elevator system. Typically, the vibrational fingerprint is a sub-section of any representation against which the determination may be made. Hence, the determination 220 may be understood as a computer-implemented process in which an attempt is to find a corresponding sub-section from the representation in the frequency domain descriptive of the vibration experienced by the elevator car 120 during the travel of the elevator car 120 as is defined by a number of vibrational fingerprints forming the reference data. For sake of clarity it is worthwhile to mention that the reference data may be generated in a manner as is described in the forthcoming description so that it comprise vibrational fingerprints with respect to the same directions in the 3-dimensional space as the measurement data is generated so as to make the pieces of data comparable so that the determination may be made.
The number of vibrational fingerprints forming the reference data may advantageously be generated by forming a simulation models of a number of elevator systems and simulating an operation of the respective elevator systems, and entities of the elevator systems, so that the reference data may be formed. Furthermore, it is possible to utilize so-called history data obtained from a number of elevator systems operating in various locations and therefrom form the vibrational fingerprints. The forming of the reference data may be performed so that the representations in the frequency domain are formed from the data descriptive of the operation of the elevator system obtained either from the simulation or from the history data. Now, portions of the generated representation may be obtained, or extracted, therefrom to generate the vibrational fingerprints to form the reference data to be used in the method in accordance with the present invention. The portions may be obtained from the representation by extracting known portions from the representation which describe portions generated by known entities of the elevator system at least in terms of a frequency. For sake of clarity, the frequency, or frequencies, and their amplitudes may be used as a definition of the vibrational fingerprint due to that the entities generate an output to the representation, which is characteristic to the respective entities. The frequency aspect may be called as an eigenfrequency of the respective entity, but as said the amplitude aspect may also be taken into account. Such aspects are schematically illustrated in
A further note with respect to the generation of the vibrational fingerprints may be that in an automatic generation of the vibrational fingerprints from the representations generated from the simulation data or the history data a predefined algorithm may be applied to the task. The applied algorithm, i.e. the mathematical method, may e.g. be so-called Finite Element (FE) analysis, which may be configured to identify frequency ranges known to be generated by respective entities in the elevator system. In other words, the sources of excitation, i.e. at least some entities of the elevator system, are known to have impact at known frequencies, or at frequency ranges, in the representation and those are identified in order to generate the reference data.
Now, by reverting back to
In accordance with some example embodiments of the invention the method performed by the computing unit may further comprise a step in which data record associating the entity detected to be present in the elevator system 110 with data indicative of a position of the respective entity is generated. This may correspond to a process in which the entity causing the positive detection result is defined on the basis of the vibrational fingerprint corresponding to the entity and additionally the data indicative of the position in a travel path of the elevator car may be determined from the representation, e.g. by mapping the detected fingerprint to the representation and obtaining therefrom the data indicative of the position in the shaft. The data indicative of the position of the respective entity may also be expressed in terms of time if applicable since the correspondence between the time and the position in the shaft is obtainable from the measurement data, for example. In response to the generation of the data record it may be stored to data storage (170).
The method as described may be a computer-implemented method and preferably in accordance with the present invention it is at least in part implemented by utilizing a machine-learning model in the task. The machine-learning model, ML, may be used in performing the determination 220 e.g. as a predefined type of comparison process as well as in a generation of the output of the determination by setting 230 the detection result as described. This may be arranged by training the machine-learning model with a training data formed from the simulation data and/or from the history data so that the machine-learning model becomes capable of setting 230 the detection result to indicate if at least one entity defined by the training data may be determined from an elevator system based on an analysis of the representation in the frequency domain generated from the measurement data. Hence, it may be considered that the machine-learning model may classify the detections in accordance with the detected entities from the measurement data since the detection brings out the entity causing the detection since the vibrational fingerprints are labeled at least with the entity information wherefrom the entity information may be obtained for the detection of the entity from the representation generated from the measurement data.
For sake of completeness, it is worthwhile to mention that the training data may represent any type of an elevator system, but in order to train the machine-learning model efficiently to perform detections towards a certain type of elevator systems, it may be advantageous to arrange that the training dataset is formed based respective elevator systems, or at least close to, as those analyzed by the machine-learning model.
An example of an apparatus suitable for performing a method according to an example embodiment of the invention as the computing unit 160 is schematically illustrated in
The execution of the method, or at least some portions of it, may be achieved by arranging a processing unit 510 comprising at least one processor to execute at least some portion of computer program code 525 stored in at least one memory 520 causing the processor 510, and, thus, the apparatus to implement the method steps as described. In other words, the processing unit 510 may be arranged to access the memory 520 and to retrieve and to store any information therefrom and thereto. Moreover, the processing unit 510 may be configured to control a communication through one or more communication interfaces 530 for accessing the other entities being involved in the operation, such as the data storage 170 in a manner as described in the foregoing description. Hence, the communication interface 530 may be arranged to implement, possibly under control of the processing unit 510, a number of communication protocols, such as an IP or any other communication protocol, for communicating with one or more entities to receive input and to output data as described. The term communication interface 530 shall be understood in a broad manner comprising necessary hardware and software elements for implementing the communication techniques. Further, the apparatus in question comprises one or more input/output devices for inputting and outputting information. In accordance with the present invention such input/output devices forming a user interface may at least comprise a touch screen, but may also comprise further entities, such as a physical keyboard, buttons, display, loudspeaker, microphone camera and so on. In some implementation of the apparatus at least some of the input/output devices may be external to the apparatus and coupled to it either wirelessly or in a wired manner. For sake of clarity, the processing unit 510 herein refers to any unit or a plurality of units suitable for processing information and control the operation of the apparatus in general at least in part, among other tasks. The mentioned operations may e.g. be implemented with a microcontroller solution with embedded software. Similarly, the invention is not limited to a certain type of memory 520, but any memory unit or a plurality of memory units suitable for storing the described pieces of information, such as portions of computer program code and/or parameters, may be applied in the context of the present invention. Moreover, at least the mentioned entities may be arranged to be at least communicatively coupled to each other with an internal data connection, such as with a data bus.
In
Hence, the computing unit 160 as schematically illustrated in
In some examples, the computing unit 160 may be implemented with a distributed computing environment in which a plurality of computing devices is configured to cooperate to cause an execution of the method according to at least one of the examples as described. A non-limiting example of such a distributed computing system may be that a first computing unit 160 is configured to collect the measurement data and e.g. to pre-process it for inputting it to a second computing unit 160. The pre-processing may e.g. comprise a step in which the representation in the frequency domain is generated. The second computing unit 160, in turn, may be configured to perform an extraction of the at least one portion of data from the representation in accordance with a predefined set of rules and e.g. classify them in accordance with the entity identified to generate the respective portions of data in the representation. Finally, the second computing unit 160 may output the portions of the data to a data record.
As derivable from above, some aspects of the present invention may relate to a computer program product which, when executed by at least one processor, cause an apparatus as the computing unit 160 to perform at least some portions of the method as described. For example, the computer program product may comprise at least one computer-readable non-transitory medium having the computer program code 525 stored thereon. The computer-readable non-transitory medium may comprise a memory device or a record medium such as a CD-ROM, a DVD, a Blu-ray disc, or another article of manufacture that tangibly embodies the computer program. As another example, the computer program may be provided as a signal configured to reliably transfer the computer program.
Still further, the computer program code 525 may comprise a proprietary application, such as computer program code for generating the data record in the manner as described.
The computer program code 525 may also be considered to include the definitions and instructions of an execution of the application of the data record in a further use.
For sake of completeness it is worthwhile to mention that the machine learning model applicable to be used for the processing of the data in the described manner may e.g. be a convolutional neural network, CNN, but also other types of neural networks may also be used for.
Still further, the foregoing description provides that the vibrational fingerprints and the spectrogram are digital images, and they are used as such in the comparison. As is known the digital images are images composed of picture elements, also known as pixels, each with finite, discrete quantities of numeric representation, or values, e.g. for its intensity or gray level. Hence, the comparison is made between one or more of these values in any known manner in order to decide their likeliness with an acceptable accuracy.
The specific examples provided in the description given above should not be construed as limiting the applicability and/or the interpretation of the appended claims. Lists and groups of examples provided in the description given above are not exhaustive unless otherwise explicitly stated.
| Number | Date | Country | |
|---|---|---|---|
| Parent | PCT/EP2022/054973 | Mar 2022 | WO |
| Child | 18768305 | US |
