Condition monitoring

Abstract

A computer-implemented method for monitoring a condition of electrical equipment 104-107 comprises measuring electrical current supplied to the electrical equipment, measuring a response of the electr

Description

Field of the Disclosure The present disclosure relates to monitoring a condition of electrical equipment. Background of the Disclosure Electrical equipment may be susceptible to failure, for example, in result of age-related degradation or inherent equipment faults. An approach to operating electrical equipment is to wait for a failure to occur before effecting a repair operation, or alternatively electrical equipment may conventionally be subjected to pre-emptive time-based maintenance and replacement schedule. In the former case, equipment failure could undesirably cause operational interruption, and in the latter case basic time-based maintenance could present an excessive time and cost burden for the maintainer. Summary of the Disclosure An objective of the present disclosure is to provide a convenient means for condition monitoring of electrical equipment, to thereby facilitate improved detection, or even advance warning, of equipment failure. This may thereby enable the equipment operator to take preemptive actions, such as maintenance, to avoid operational interruption and / or damage to the electrical equipment. This may desirably reduce costs for the operator in addition to providing a more reliable product. A first aspect of the present disclosure provides a computer-implemented method for monitoring a condition of electrical equipment, the method comprising measuring electrical current supplied to the electrical equipment, measuring a response of the electrical equipment to the supplied electrical current, and providing data representing the measured electrical current and the measured response to a trained machine learning model trained to generate an output representative of the condition of the electrical equipment. In implementations, the trained machine learning model is trained to generate an output representative of the condition of the electrical equipment further based on one or more environmental conditions to which the electrical equipment is exposed, the method comprises obtaining data describing one or more environmental conditions to which the electrical equipment is exposed, and the providing data comprises further providing the data describing the one or more environmental conditions to the trained machine learning model. In implementations, the measuring a response of the electrical equipment comprises measuring a physical response of the electrical equipment. In implementations, the electrical equipment comprises one or more of an electric motor and a thermal management device, and the measuring a physical performance of the electrical equipment comprises measuring a corresponding one or more of a motor speed of the electric motor and a temperature of the thermal management device. In implementations, the measuring a response of the electrical equipment comprises measuring an electrical response of the electrical equipment. In implementation, the trained machine learning model is trained generate an alert signal if the condition of the electrical equipment meets an alert condition. In implementations, the measuring electrical current supplied to the electrical equipment and the measuring a response of the electrical equipment to the supplied electrical current are performed periodically. In implementations, the method comprises outputting signals representing the measured electrical current and the measured response via an internet communications system to a processor located remotely of the signal sources, wherein the trained machine learning model is executed by the processor. In implementations, the method comprises generating a human perceptible representation of the condition of the electrical equipment based on the output of the trained machine learning model. In implementations, the electrical equipment is a building electrical distribution system, and the method is for monitoring a condition of the building electrical distribution system. A second aspect of the present disclosure provides a condition monitoring system for monitoring a condition of electrical equipment, the system comprising: at least one processor, and at least one memory' storing machine-readable instructions, wherein the at least one memory' and the machine-readable instructions are configured to, with the at least one processor, cause the condition monitoring system to monitor a condition of electrical equipment by the method of the first aspect of the present disclosure. A third aspect of the present disclosure provides a computer program comprising instructions, which, when executed by a condition monitoring system cause the condition monitoring system to carry out the method of the first aspect of the present disclosure. A fourth aspect of the present disclosure provides a data storage apparatus having stored thereon the computer program of the third aspect of the present disclosure. These and other aspects of the invention will be apparent from the embodiment(s) described below. Brief Description of the Drawings In order that the present invention may be more readily understood, embodiments of the invention will now be described, by way of example, with reference to the accompanying drawings, in which: Figure 1 shows schematically an example of a building electrical distribution system, Figure 2 shows schematically a condition monitoring system for monitoring a condition of the building electrical distribution system, Figure 3 shows schematically a data processing system of the condition monitoring system, Figure 4 shows schematically operations performed by the condition monitoring system to monitor electrical equipment, and Figure 5 shows schematically further operations performed by the condition monitoring system to monitor electrical equipment. Detailed Description of the Disclosure Example embodiments are described below in sufficient detail to enable those of ordinary skill in the art to embody and implement the systems and processes herein described. It is important to understand that embodiments can be provided in many alternate forms and should not be construed as limited to the examples set forth herein. Accordingly, while embodiments can be modified in various ways and take on various alternative forms, specific embodiments thereof are shown in the drawings and described in detail below as examples. There is no intent to limit to the particular forms disclosed. On the contrary, all modifications, equivalents, and alternatives falling within the scope of the appended claims should be included. Elements of the example embodiments are consistently denoted by the same reference numerals throughout the drawings and detailed description where appropriate. The terminology used herein to describe embodiments is not intended to limit the scope. The articles “a,” “an,” and “the” are singular in that they have a single referent, however the use of the singular form in the present document should not preclude the presence of more than one referent. In other words, elements referred to in the singular can number one or more, unless the context clearly indicates otherwise. It will be further understood that the terms “comprises,” “comprising,” “includes,” and / or “including,” when used herein, specify the presence of stated features, items, steps, operations, elements, and / or components, but do not preclude the presence or addition of one or more other features, items, steps, operations, elements, components, and / or groups thereof. Figure 1 depicts schematically an example of a building 101 in which aspects of the present disclosure may be utilised. The building 101 comprises an electrical installation 102 and a condition monitoring system 103 for monitoring a condition of the electrical installation 102. In the example, the building 101 is a factory building. The electrical installation 102 comprises a plurality of items of electrical equipment, for example, electrical machines 104, 105 and electrical devices 106, 107, and electrical conductors 108 for electrically coupling the electrical equipment to a source 109 of alternating current, which may, for example, comprise a mains electricity distribution grid. The electrical machines comprise a thermal management device 104, such as a room heater or cooler, and an electric motor 105 for driving an industrial machine. The electrical devices 106, 107 may comprise power supplies for supplying electrical power to respective electrical sub-systems. The various items of electrical equipment, and the electrical conductors, may be susceptible to failure in use, for example, in result of age-related degradation or inherent equipment faults. Conventionally such failures may be handled by waiting for a failure to occur before effecting a repair operation, or alternatively the electrical equipment could be subjected to pre-emptive time-based maintenance and replacement. In the former case, equipment failure could undesirably cause operational interruption to the electrical installation. For example, in the event that the power supply 106 fails, the electrical subsystem supplied by the power supply may be rendered inoperable. And simple time-based maintenance may present an excessive time and cost burden for the maintainer. Moreover, there may be situations where parts of the electrical installation are degraded only to the extent that their performance and efficiency is reduced, rather than failing completely. Conventional periodic inspection and testing may not reveal the occurrence of such partial failure, hence the failure may go undetected for an extended period of time, potentially impacting operational performance and / or efficiency of tire electrical installation. Ure present disclosure thus employs the condition monitoring system 103 for monitoring the condition of the electrical installation 102, to detect and even predict in advance the occurrence of a fault condition with the electrical installation or a part thereof. In particular, in examples the condition monitoring system is functional to measure the electrical current ‘1’ at various points of the installation, and also to measure the physical performance of the electrical machines. The condition monitoring system 102 is described in further detail with reference to Figures 2 to 5. Referring next to Figure 2, the condition monitoring system 103 comprises data processing system 201, communications network 202, and sensor modules 203a to 203d. The data processing system 201 is configured to obtain measurements of the electrical current at the various points of the electrical installation and the physical performance of the electrical machines 104, 105 by communicating with the sensor modules 203a to 203d. The data processing system is further configured to evaluate the measured data to determine measurements and / or measurement trends indicative of a fault condition having occurred or being likely to occur. As will be described with reference to later figures, the data processing system implements a trained machine learning model to analyse the measured data and predict the occurrence of fault conditions. Sensor modules 203a to 203d are provided for measuring the electrical and physical response of the electrical installation, and the electrical equipment thereof, to electrical current supplied to the electrical installation. Sensor modules 203a and 203a comprise electrical current sensors, for measuring the electrical current at the various nodes depicted in Figure 1. Sensor 203a comprises a temperature sensor for sensing the temperature of the thermal management device 104, and sensor 203d comprises a motor speed sensor for sensing a speed of the motor 105. The communications network 202 is provided for communicating the data processing system 201 with the sensor modules 203a to 203d. In some examples, the data processing system 201 could be located mutually remotely of the sensor modules 203a to 203d, and even remotely of the building 101. For example, the data processing system 201 could be located offsite, and the communications network 202, which may, for example, comprise an internet-based communications network, may communicate sensor data from the sensors 203a to 203d to the data processing system 201. The data processing system 201 could, for example, utilise ‘cloud-based’ computing resources. Although in the example the sensor modules 203a to 203d are depicted as forming part of the condition monitoring system 103, in other examples the sensor modules 203a to 203d could instead be integrated with the electrical equipment, and the condition monitoring system 103 may simply receive measured data from the electrical equipment. Data processing system 201 will be described in further detail with reference to Figure 3, and the method implemented by the data processing system for monitoring the condition of the electrical equipment will be described in further detail with reference to Figures 4 and 5. Referring next to Figure 3, in examples the data processing system 201 of the condition monitoring system 103 comprises processor 301, memory 302, input / output device 303, and system bus 304. Processor 301 is configured for execution of instructions of a computer program for monitoring the condition of the electrical installation 102. Memory 302 is configured for non-volatile storage of the computer program, defining machine-readable instructions, for execution by the processor, and for serving as read / write memory for storage of operational data associated with the computer program executed by the processor 301. Display 303 is provided for displaying a graphical user interface associated with the computer program, to enable a user to interact with the computer program, and in particular to enable display of condition-related data in a human comprehensible format. Input / output interface 304 is configured for connection of the data processing system 303 to the communications network 202. The components of the data processing system 103 are in communication via system bus 305. Referring next to Figure 4, in implementations the method for monitoring the condition of the electrical installation may comprise three processes. At process 401, the computer program causes the processor 301 of the data processing system 201 to initiate the monitoring process. Process 401 could, for example, occur in response to a user input to the data processing system, and could involve the data processing system 201 loading a graphical user interface. At process 402, the computer program causes the processor 301 to monitor the electrical installation, and evaluate the measured sensor data to make predictions regarding the condition of the electrical installation. Processes involved in stage 402 will be described in further detail with reference to Figure 5. At process 403, the computer program causes the processor 301 of the data processing system 201 to display via the graphical user interface and the display 303 a visual representation of information pertaining to the condition of the electrical installation. For example, where fault conditions are determined at process 402, process 403 may involve displaying corresponding alert messages to the user, alerting the user of the occurrence of the fault condition. Additionally or alternatively, process 403 could involve the data processing system outputting alert messages to external computing systems. For example process 403 could involve the data processing system outputting alert messages via a wired or wireless communications system to external data processing systems accessible by maintainers charged with maintaining the electrical installation. Referring next to Figure 5, in implementations the method for monitoring the condition of the electrical installation comprises four processes. At process 501, the computer program causes the processor 301 of the data processing system 201 to control the sensor modules 203a to 230d to measure the respective electrical or physical attribute of the electrical installation. Process 501 could, for example, involve all sensors being employed to collect all available measurements. Or alternatively, the computer program may be functional to enable a user to select a subset of the sensors to monitor, in which case process 501 may involve operating only the selected sensors. At process 502, the computer program causes the processor 301 of the data processing system 201 to interrogate the sensor modules 203a to 203d to receive the measured data via the communications network 202. Process 502 could also involve the processor 301 receiving additional data relevant to evaluating the condition of the electrical installation. For example, process 502 could involve the processor 301 receiving environmental condition data describing environmental conditions, such as ambient temperature and / or humidity, to which the electrical installation is exposed. Such additional data could originate, for example, from an external monitoring system. At process 503, the computer program causes the processor 301 of the data processing system 201 to execute a trained machine learning model based on the data received at process 502. In particular, it is proposed that the machine learning model implemented is trained using training data in which the electrical and physical responses of the electrical installation, and the components thereof, is associated with supplied electrical currents. For example, regarding the physical response of the electrical installations, the machine learning model may be trained using training data mapping the electrical current ‘Iheat’ supplied to the thermal management device x to the thermal performance of the device, for example, the temperature gradient achieved by the device, as measured using the temperature sensor 203c, and mapping the electrical current Tmotor’ supplied to the electric motor 105 to the motor speed, as sensed by the speed sensor 203d. This training is based on the principle that there should be an expected performance of electrical equipment for a given electrical current, for example, a temperature of the thermal management device 104 or speed of the motor 105. And in the case of the electrical response, the machine learning model may be trained on the relationship between the electrical currents at the various points of the electrical installation. Hence, the electrical current “IpWr i m" supplied to the power supply 106 may be expected to result in a current “Ipwr i out” output by the power supply. Where the current output of the power supply varies from that relationship, it may be inferred that the power supply has failed or is failing. Because the electrical and physical response of the electrical installation and the components thereof to a supplied electrical current may be influenced even in non-fault condition operation by external influences, such as the ambient temperature and / or humidity to which the electrical installation is exposed, the machine learning model may further be trained to predict fault conditions taking into account these influences. At process 504, the computer program causes the processor 301 of the data processing system to generate a condition prediction based on the output of the machine learning model at process 503. Process 504 could, for example, involve generating an alert signal where the condition prediction predicts the current or imminent occurrence of a fault condition. Ure computer program may cause the processor 301 to repeat method steps 501 to 504 periodically. The system and apparatus described above may use dedicated processor systems, micro controllers, programmable logic devices, microprocessors, or any combination thereof, to perform some or all of the operations described herein. Some of the operations described above may be implemented in software and other operations may be implemented in hardware. Any of the operations, processes, and / or methods described herein may be performed by an apparatus, a device, and / or a system substantially similar to those as described herein and with reference to the illustrated figures. References herein to a device, or similar, do not imply a unitary apparatus, and instead include a system of components, which may or may not be colocated. The processor may execute instructions or "code" stored in memory. The memory may store data as well. The processing device may include, but may not be limited to, an analog processor, a digital processor, a microprocessor, a multi-core processor, a processor array, a network processor, or the like. The processing device may be part of an integrated control system or system manager, or may be provided as a portable electronic device configured to interface with a networked system either locally or remotely via wireless transmission. The memory may be integrated together with the processing device, for example RAM or FLASH memory disposed within an integrated circuit microprocessor or the like. In other examples, the memory may comprise an independent device, such as an external disk drive, a storage array, a portable FLASH key fob, or the like. The memory and processing device may be operatively coupled together, or in communication with each other, for example by an I / O port, a network connection, or the like, and the processing device may read a file stored on the memory. Associated memory may be "read only" by design (ROM) by virtue of permission settings, or not. Other examples of memory may include, but may not be limited to, WORM, EPROM, EEPROM, FLASH, or the like, which may be implemented in solid state semiconductor devices. Other memories may comprise moving parts, such as a known rotating disk drive. All such memories may be "machine-readable" and may be readable by a processing device. Operating instructions or commands may be implemented or embodied in tangible forms of stored computer software (also known as "computer program" or "code"). Programs, or code, may be stored in a digital memory and may be read by the processing device. "‘Computer-readable storage medium" (or alternatively, "machine-readable storage medium") may include all of the foregoing ty pes of memory, as well as new technologies of the future, as long as the memory may be capable of storing digital information in the nature of a computer program or other data, at least temporarily, and as long at the stored information may be "read" by an appropriate processing device. Hie term "computer-readable" may not be limited to the historical usage of "computer" to imply a complete mainframe, mini-computer, desktop or even laptop computer. Rather, "computer-readable" may comprise storage medium that may be readable by a processor, a processing device, or any computing system. Such media may be any available media that may be locally and / or remotely accessible by a computer or a processor, and may include volatile and non-volatile media, and removable and non-removable media, or any combination thereof. A program stored in a computer-readable storage medium may comprise a computer program product. For example, a storage medium may be used as a convenient means to store or transport a computer program. For the sake of convenience, the operations may be described as various interconnected or coupled functional blocks or diagrams. However, there may be cases where these functional blocks or diagrams may be equivalently aggregated into a single logic device, program or operation with unclear boundaries. While the application describes specific examples of carrying out embodiments of the invention, those skilled in the art will appreciate that there are numerous variations and permutations of the above described systems and techniques that fall within the spirit and scope of the invention as set forth in the appended claims. For example, while specific terminology has been employed above to refer to electronic design automation processes, it should be appreciated that various examples of the invention may be implemented using any desired combination of electronic design automation processes. 5 One of skill in the art will also recognize that the concepts taught herein can be tailored to a particular application in many other ways. In particular, those skilled in the art will recognize that the illustrated examples are but one of many alternative implementations that will become apparent upon reading this disclosure. 10 Although the specification may refer to “an”, “one”, “another”, or “some” example(s) in several locations, this does not necessarily mean that each such reference is to the same example(s), or that the feature only applies to a single example.

Claims

1. A computer-implemented method for monitoring a condition of electrical equipment, the method comprisingmeasuring electrical current supplied to the electrical equipment,measuring a response of the electrical equipment to the supplied electrical current, andproviding data representing the measured electrical current and the measured response to a trained machine learning model to generate an output representative of the condition of the electrical equipment.

2. The computer-implemented method of claim 1, wherein the trained machine learning model is trained to generate an output representative of the condition of the electrical equipment further based on one or more environmental conditions to which the electrical equipment is exposed, the method comprises obtaining data describing one or more environmental conditions to which the electrical equipment is exposed, and the providing data comprises further providing the data describing the one or more environmental conditions to the trained machine learning model.

3. The computer-implemented method of claim 1, wherein the measuring a response of the electrical equipment comprises measuring a physical response of the electrical equipment.

4. The computer-implemented method of claim 3, wherein the electrical equipment comprises at least one of an electric motor and a thennal management device, and the measuring a physical response of the electrical equipment comprises measuring at least one of a speed of the electric motor and a temperature of the thermal management device.

5. The computer-implemented method of claim 1, wherein the measuring a response of the electrical equipment comprises measuring an electrical response of the electrical equipment.

6. The computer-implemented method of claim 1, wherein the trained machine learning model is trained to generate an alert signal if the condition of the electrical equipment meets an alert condition.

7. The computer-implemented method of claim 1, wherein the measuring electrical current supplied to the electrical equipment and the measuring a response of the electrical equipment to the supplied electrical current are performed periodically.

8. The computer-implemented method of claim 1, comprising outputting signals representing the measured electrical current and the measured response via an internet communications system to a processor located remotely of the signal sources, wherein the trained machine learning model is executed by the processor.

9. The computer-implemented method of claim 1, comprising generating a human perceptible representation of the condition of the electrical equipment based on the output of the trained machine learning model.

10. The computer-implemented method of claim 1. wherein the electrical equipment is a building electrical distribution system, and the method is for monitoring a condition of the building electrical distribution system.

11. A condition monitoring system for monitoring a condition of electrical equipment, the system comprising:at least one processor, andat least one memory storing machine-readable instructions,wherein the at least one memory and the machine-readable instructions are configured to, with the at least one processor, cause the condition monitoring system to monitor a condition of electrical equipment by the method of claim I.

12. A computer program comprising instructions, which, when executed by a condition monitoring system cause the condition monitoring system to carry out the method of claim 1.

13. A data storage apparatus having stored thereon the computer program of claim 12.Amendments have been added to the claims as follows :15Claims1. A computer-implemented method for monitoring a condition of electrical equipment, the method comprising5 measuring electrical current supplied to the electrical equipment,measuring a response of the electrical equipment to the supplied electrical current, andproviding data representing the measured electrical current and the measured response to a trained machine learning model to generate an output representative of the condition of the electrical equipment,10 wherein the electrical equipment is a building electrical distribution system, and themethod is for monitoring a condition of the building electrical distribution system.

152. The computer-implemented method of claim 1, wherein the trained machine learning model is trained to generate an output representative of the condition of the electrical equipment further based on one or more environmental conditions to which the electrical equipment is exposed, the method comprises obtaining data describing one or more environmental conditions to which the electrical equipment is exposed, and the providing data comprises further providing the data describing the one or more environmental conditions to the trained machinelearning model.

203. The computer-implemented method of claim 1, wherein the measuring a response of the electrical equipment comprises measuring a physical response of the electrical equipment.

4. The computer-implemented method of claim 3, wherein the electrical equipment25 comprises at least one of an electric motor and a thermal management device, and the measuring a physical response of the electrical equipment comprises measuring at least one of a speed of the electric motor and a temperature of the thennal management device.

5. The computer-implemented method of claim 1, wherein the measuring a response of the30 electrical equipment comprises measuring an electrical response of the electrical equipment.

6. The computer-implemented method of claim 1, wherein the trained machine learning model is trained to generate an alert signal if the condition of the electrical equipment meets an alert condition.5 7. The computer-implemented method of claim 1, wherein the measuring electrical currentsupplied to the electrical equipment and the measuring a response of the electrical equipment to the supplied electrical current are performed periodically.

8. The computer-implemented method of claim 1, comprising outputting signals 10 representing the measured electrical current and the measured response via an internet communications system to a processor located remotely of the signal sources, wherein the trained machine learning model is executed by the processor.LOCM 9. The computer-implemented method of claim 1, comprising generating a human 00 15 perceptible representation of the condition of the electrical equipment based on the output of thetrained machine learning model.1—10. A condition monitoring system for monitoring a condition of electrical equipment, the system comprising:20 at least one processor, andat least one memory storing machine-readable instructions,wherein the at least one memory and tire machine-readable instructions are configured to, with the at least one processor, cause the condition monitoring system to monitor a condition of electrical equipment by the method of claim 1.2511. A computer program comprising instructions, which, when executed by a condition monitoring system cause the condition monitoring system to carry out the method of claim 1.

12. A data storage apparatus having stored thereon the computer program of claim 11.30

Images