Multi-modal fusion monitoring system and method for power industry

Abstract

The invention relates to the technical field of power monitoring, and discloses a multi-modal fusion monitoring system and method for the power industry, and the system comprises a data acquisition module, a data association module, a model construction module and a model operation updating module. The method corresponds to the system. According to the application, the data acquisition module provides a data basis for data association, and the data association module determines the association relationship between the data, so that the data basis is provided for constructing a multi-modal fusion monitoring model; a necessary technical means is provided for power industry monitoring based on a real-time multi-modal data set through the model building module, multi-modal fusion monitoring of the power industry is achieved through the model operation updating module, finally, all-directional, real-time and accurate monitoring of power equipment is achieved, potential problems are found in time, and the power industry monitoring efficiency is improved. And safe and stable operation of a power system is ensured.

Description

Technical Field

[0001] The present application relates to the field of power monitoring technology, and specifically to a multimodal fusion monitoring system and method for the power industry. Background Art

[0002] Today's society is highly dependent on electricity, so the stable operation of the power system is crucial. However, it is not difficult to find that traditional power monitoring has many limitations, such as:

[0003] A single monitoring mode, such as relying solely on electrical parameter monitoring, is difficult to fully and accurately reflect the operating status of power equipment. For example, changes in physical parameters such as temperature and vibration of equipment may not be detected in time, resulting in potential faults being ignored;

[0004] Different types of monitoring data are independent of each other and lack effective integration and analysis, which greatly reduces the accuracy and reliability of monitoring results and cannot provide accurate decision-making basis for the maintenance and management of power systems.

[0005] In summary, with the rapid development of the power industry, power equipment is becoming increasingly complex, and the requirements for monitoring are becoming higher and higher. The existing technology urgently needs a technical solution that can integrate multiple monitoring modes. Summary of the invention

[0006] The purpose of this application is to provide a multimodal fusion monitoring system and method for the power industry to solve the technical problems raised in the above background technology.

[0007] To achieve the above objectives, this application discloses the following technical solutions:

[0008] In a first aspect, the present application discloses a multimodal fusion monitoring system for the power industry, the system comprising:

[0009] A data acquisition module, wherein the data acquisition module is configured to acquire a historical power multimodal data set, wherein the multimodal data set is collected by a sensor disposed on the power equipment;

[0010] A data association module, wherein the data association module is configured to associate various data in the multimodal data set to obtain corresponding association relationships;

[0011] A model building module, wherein the model building module is configured to build a multimodal fusion monitoring model based on the association relationship;

[0012] A model operation update module, wherein the model operation module is configured to: input a real-time multimodal data set into the model and output a monitoring result; and recapture the association relationship based on an update cycle and use it to update the model operation module.

[0013] The data acquisition module provides a data basis for data association. The data association module realizes the determination of the correlation relationship between data, which provides a data basis for building a multimodal fusion monitoring model. The model construction module provides the necessary technical means for monitoring the power industry based on real-time multimodal data sets. The model operation and update module realizes multimodal fusion monitoring of the power industry, realizes all-round, real-time and accurate monitoring of power equipment, timely discovers potential problems, and ensures the safe and stable operation of the power system.

[0014] Preferably, the data acquisition module is further configured as follows:

[0015] Preset monitoring period;

[0016] The set sensors collect electrical parameters, equipment status, environmental parameters, insulation performance and image videos based on time series;

[0017] The electrical parameters include voltage, current, power and frequency;

[0018] The device status includes temperature, vibration and sound;

[0019] The insulation performance includes insulation resistance and partial discharge;

[0020] The image video includes the appearance of the device and the working scene.

[0021] Preferably, the data association module is further configured as follows:

[0022] Unifying the collected electrical parameters, the equipment status, the environmental parameters, the insulation performance and the image video on the same time axis based on a time series;

[0023] Derivatives are obtained for the electrical parameters, various data in the device status, and the insulation resistance, and derivatives with the same signs within the same monitoring period are set as a first association relationship; and the first association relationship is output;

[0024] Detect the partial discharge, the appearance equipment and the working scene, capture the electrical parameters, the equipment status and the insulation resistance corresponding to the discharge abnormality, the appearance abnormality and the scene abnormality, and set them as a second association relationship; output the second association relationship.

[0025] Preferably, the model building module is further configured as:

[0026] Acquire the first association relationship and the second association relationship, and store them in the multimodal fusion monitoring model;

[0027] The set sensors are connected to the multimodal fusion monitoring model.

[0028] Preferably, the model operation update is further configured as follows:

[0029] Collect the real-time multimodal data set using sensors, and analyze the real-time multimodal data set to obtain corresponding real-time electrical parameters, real-time equipment status, real-time environmental parameters, real-time insulation performance and real-time image video;

[0030] Deriving the real-time electrical parameter, various data in the real-time device status, and the real-time insulation resistance, and using the first association relationship, generating and outputting a first warning signal for a sensor corresponding to the data with an abnormal derivative sign;

[0031] Using the real-time electrical parameters, various data in the real-time device status and the real-time insulation resistance, a real-time similarity calculation is performed in the second association relationship, and when the real-time similarity is greater than or equal to a preset similarity threshold, a second warning signal indicating the presence of discharge abnormality, appearance abnormality and scene abnormality is obtained and output;

[0032] The update cycle is preset, and when the set sensor completes one update cycle, the first association relationship and the second association relationship are rebuilt.

[0033] In a second aspect, the present application discloses a multimodal fusion monitoring method for the power industry, the method comprising:

[0034] S1: Acquire a historical power multimodal data set, where the multimodal data set is collected by sensors installed on power equipment;

[0035] S2: Associating various data in the multimodal data set to obtain corresponding association relationships;

[0036] S3: constructing a multimodal fusion monitoring model based on the association relationship;

[0037] S4: inputting the real-time multimodal data set into the model and outputting the monitoring results; recapturing the association relationship based on the update cycle and using it to update the model operation module.

[0038] Preferably, step S1 further comprises:

[0039] Preset monitoring period;

[0040] The set sensors collect electrical parameters, equipment status, environmental parameters, insulation performance and image videos based on time series;

[0041] The electrical parameters include voltage, current, power and frequency;

[0042] The device status includes temperature, vibration and sound;

[0043] The insulation performance includes insulation resistance and partial discharge;

[0044] The image video includes the appearance of the device and the working scene.

[0045] Preferably, step S2 further comprises:

[0046] Unifying the collected electrical parameters, the equipment status, the environmental parameters, the insulation performance and the image video on the same time axis based on a time series;

[0047] Derivatives are obtained for the electrical parameters, various data in the device status, and the insulation resistance, and derivatives with the same signs within the same monitoring period are set as a first association relationship; and the first association relationship is output;

[0048] Detect the partial discharge, the appearance equipment and the working scene, capture the electrical parameters, the equipment status and the insulation resistance corresponding to the discharge abnormality, the appearance abnormality and the scene abnormality, and set them as a second association relationship; output the second association relationship.

[0049] Preferably, step S3 further comprises:

[0050] Acquire the first association relationship and the second association relationship, and store them in the multimodal fusion monitoring model;

[0051] The set sensors are connected to the multimodal fusion monitoring model.

[0052] Preferably, step S4 further comprises:

[0053] Collect the real-time multimodal data set using sensors, and analyze the real-time multimodal data set to obtain corresponding real-time electrical parameters, real-time equipment status, real-time environmental parameters, real-time insulation performance and real-time image video;

[0054] Deriving the real-time electrical parameter, various data in the real-time device status, and the real-time insulation resistance, and using the first association relationship, generating and outputting a first warning signal for a sensor corresponding to the data with an abnormal derivative sign;

[0055] Using the real-time electrical parameters, various data in the real-time device status and the real-time insulation resistance, a real-time similarity calculation is performed in the second association relationship, and when the real-time similarity is greater than or equal to a preset similarity threshold, a second warning signal indicating the presence of discharge abnormality, appearance abnormality and scene abnormality is obtained and output;

[0056] The update cycle is preset, and when the set sensor completes one update cycle, the first association relationship and the second association relationship are rebuilt.

[0057] Beneficial effects: The multimodal fusion monitoring system and method for the electric power industry of the present application provides a data basis for data association through the data acquisition module, realizes the determination of the correlation relationship between data through the data association module, provides a data basis for building a multimodal fusion monitoring model, and provides the necessary technical means for monitoring the electric power industry based on real-time multimodal data sets through the model construction module. The model operation update module realizes multimodal fusion monitoring of the electric power industry, realizes all-round, real-time and accurate monitoring of power equipment, timely discovers potential problems, and ensures the safe and stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For those skilled in the art, other drawings can be obtained based on these drawings without paying any creative work.

[0059] Figure 1 A schematic block diagram of a multimodal fusion monitoring system for the power industry provided in an embodiment of the present application;

[0060] Figure 2 A flowchart of a multimodal fusion monitoring method for the power industry provided in an embodiment of the present application. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present application are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application.

[0062] In this article, the term "comprising" is intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of more restrictions, the elements defined by the sentence "comprising..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0063] In a first aspect, this embodiment discloses Figure 1A multi-modal fusion monitoring system for the power industry is shown, the system comprising:

[0064] A data acquisition module, the data acquisition module is configured to acquire a historical power multimodal data set, the multimodal data set being collected by a sensor disposed on the power equipment;

[0065] A data association module, the data association module is configured to associate various data in the multimodal data set to obtain corresponding association relationships;

[0066] A model building module, the model building module is configured to build a multimodal fusion monitoring model based on the association relationship;

[0067] The model operation update module is configured as follows: inputting a real-time multimodal data set into the model and outputting monitoring results; recapturing the association relationship based on an update cycle and using it to update the model operation module.

[0068] The data acquisition module provides a data basis for data association. The data association module realizes the determination of the correlation relationship between data, which provides a data basis for building a multimodal fusion monitoring model. The model construction module provides the necessary technical means for monitoring the power industry based on real-time multimodal data sets. The model operation and update module realizes multimodal fusion monitoring of the power industry, realizes all-round, real-time and accurate monitoring of power equipment, timely discovers potential problems, and ensures the safe and stable operation of the power system.

[0069] Specifically, the data acquisition module is further configured as follows:

[0070] Preset monitoring period;

[0071] The set sensors collect electrical parameters, equipment status, environmental parameters, insulation performance and image videos based on time series;

[0072] Electrical parameters include voltage, current, power, and frequency;

[0073] Device status includes temperature, vibration, and sound;

[0074] Insulation performance includes insulation resistance and partial discharge;

[0075] The image video includes the equipment appearance and working scenes.

[0076] Specifically, the data association module is further configured as follows:

[0077] Unify the collected electrical parameters, equipment status, environmental parameters, insulation performance and image videos on the same timeline based on time series;

[0078] Derivatives are obtained for the electrical parameters, various data in the equipment status, and the insulation resistance, and derivatives with the same sign in the same monitoring period are set as a first association relationship; and the first association relationship is output;

[0079] Detect partial discharge, appearance equipment and working scenes, capture the corresponding electrical parameters, equipment status and insulation resistance when discharge abnormality, appearance abnormality and scene abnormality occur, and set them as the second association relationship; output the second association relationship.

[0080] Specifically, the model building module is also configured as:

[0081] Obtaining the first association relationship and the second association relationship, and storing them in a multimodal fusion monitoring model;

[0082] Connect the set sensors to the multimodal fusion monitoring model.

[0083] Specifically, the model operation update is also configured as:

[0084] Use sensors to collect real-time multimodal data sets and analyze them to obtain corresponding real-time electrical parameters, real-time equipment status, real-time environmental parameters, real-time insulation performance, and real-time image and video;

[0085] Deriving the real-time electrical parameters, various data in the real-time device status, and the real-time insulation resistance, and using the first association relationship, generating and outputting a first warning signal for the sensor corresponding to the data with abnormal derivative signs;

[0086] Using the real-time electrical parameters, various data in the real-time device status and the real-time insulation resistance, a real-time similarity calculation is performed in the second association relationship. When the real-time similarity is greater than or equal to a preset similarity threshold, a second warning signal is obtained and outputted when a discharge abnormality, an appearance abnormality and a scene abnormality occur.

[0087] The preset update cycle is such that when the set sensor completes an update cycle, the first association relationship and the second association relationship are rebuilt.

[0088] In a second aspect, this embodiment discloses Figure 2 A multi-modal fusion monitoring method for the power industry is shown, the method comprising:

[0089] S1: Acquire a historical power multimodal dataset, where the multimodal dataset is collected by sensors installed on power equipment;

[0090] S2: Associating various data in the multimodal data set to obtain corresponding association relationships;

[0091] S3: Construct a multimodal fusion monitoring model based on association relationships;

[0092] S4: Input the real-time multimodal data set into the model and output the monitoring results; recapture the association relationship based on the update cycle and use it to update the model operation module.

[0093] Specifically, step S1 also includes:

[0094] Preset monitoring period;

[0095] The set sensors collect electrical parameters, equipment status, environmental parameters, insulation performance and image videos based on time series;

[0096] Electrical parameters include voltage, current, power, and frequency;

[0097] Device status includes temperature, vibration, and sound;

[0098] Insulation performance includes insulation resistance and partial discharge;

[0099] The image video includes the equipment appearance and working scenes.

[0100] Specifically, step S2 also includes:

[0101] Unify the collected electrical parameters, equipment status, environmental parameters, insulation performance and image videos on the same timeline based on time series;

[0102] Derivatives are obtained for the electrical parameters, various data in the equipment status, and the insulation resistance, and derivatives with the same sign in the same monitoring period are set as a first association relationship; and the first association relationship is output;

[0103] Detect partial discharge, appearance equipment and working scenes, capture the corresponding electrical parameters, equipment status and insulation resistance when discharge abnormality, appearance abnormality and scene abnormality occur, and set them as the second association relationship; output the second association relationship.

[0104] Specifically, step S3 also includes:

[0105] Obtaining the first association relationship and the second association relationship, and storing them in a multimodal fusion monitoring model;

[0106] Connect the set sensors to the multimodal fusion monitoring model.

[0107] Specifically, step S4 also includes:

[0108] Use sensors to collect real-time multimodal data sets and analyze them to obtain corresponding real-time electrical parameters, real-time equipment status, real-time environmental parameters, real-time insulation performance, and real-time image and video;

[0109] Deriving the real-time electrical parameters, various data in the real-time device status, and the real-time insulation resistance, and using the first association relationship, generating and outputting a first warning signal for the sensor corresponding to the data with abnormal derivative signs;

[0110] Using the real-time electrical parameters, various data in the real-time device status and the real-time insulation resistance, a real-time similarity calculation is performed in the second association relationship. When the real-time similarity is greater than or equal to a preset similarity threshold, a second warning signal is obtained and outputted when a discharge abnormality, an appearance abnormality and a scene abnormality occur.

[0111] The preset update cycle is such that when the set sensor completes an update cycle, the first association relationship and the second association relationship are rebuilt.

[0112] In summary, the multimodal fusion monitoring system and method for the electric power industry of this embodiment provides a data basis for data association through the data acquisition module, realizes the determination of the correlation relationship between data through the data association module, provides a data basis for building a multimodal fusion monitoring model, and provides the necessary technical means for monitoring the electric power industry based on real-time multimodal data sets through the model construction module. The model operation update module realizes multimodal fusion monitoring of the electric power industry, realizes all-round, real-time and accurate monitoring of power equipment, timely discovers potential problems, and ensures the safe and stable operation of the power system.

[0113] In the embodiments provided in the present application, it should be understood that the embodiments described herein can be implemented in hardware, software, firmware, middleware, code or any appropriate combination thereof. For hardware implementation, the processor can be implemented in one or more of the following units: application specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), processor, controller, microcontroller, microprocessor, other electronic units designed to implement the functions described herein or their combination. For software implementation, part or all of the flow of the embodiment can be completed by instructing the relevant hardware through a computer program. When implemented, the above program can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein the communication medium includes any medium that is convenient for transmitting a computer program from one place to another. The storage medium can be any available medium that a computer can access. The computer-readable storage medium can include but is not limited to RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer.

[0114] Finally, it should be noted that the above is only a preferred embodiment of the present application and is not intended to limit the present application. Although the present application has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application shall be included in the protection scope of the present application.

Claims

1. A multi-modal fusion monitoring system for the power industry, characterized in that: The system includes: A data acquisition module, wherein the data acquisition module is configured to acquire a historical power multimodal data set, wherein the multimodal data set is collected by a sensor disposed on the power equipment; A data association module, wherein the data association module is configured to associate various data in the multimodal data set to obtain corresponding association relationships; A model building module, wherein the model building module is configured to build a multimodal fusion monitoring model based on the association relationship; A model operation update module, wherein the model operation module is configured to: input a real-time multimodal data set into the model and output a monitoring result; and recapture the association relationship based on an update cycle and use it to update the model operation module.

2. The multimodal fusion monitoring system for the power industry according to claim 1 is characterized in that: The data acquisition module is also configured as follows: Preset monitoring period; The set sensors collect electrical parameters, equipment status, environmental parameters, insulation performance and image videos based on time series; The electrical parameters include voltage, current, power and frequency; The device status includes temperature, vibration and sound; The insulation performance includes insulation resistance and partial discharge; The image video includes the appearance of the device and the working scene.

3. The multimodal fusion monitoring system for the power industry according to claim 2 is characterized in that: The data association module is further configured to: Unifying the collected electrical parameters, the equipment status, the environmental parameters, the insulation performance and the image video on the same time axis based on a time series; Derivatives are obtained for the electrical parameters, various data in the device status, and the insulation resistance, and derivatives with the same signs within the same monitoring period are set as a first association relationship; and the first association relationship is output; Detect the partial discharge, the appearance equipment and the working scene, capture the electrical parameters, the equipment status and the insulation resistance corresponding to the discharge abnormality, the appearance abnormality and the scene abnormality, and set them as a second association relationship; output the second association relationship.

4. The multimodal fusion monitoring system for the power industry according to claim 3 is characterized in that: The model building module is also configured to: Acquire the first association relationship and the second association relationship, and store them in the multimodal fusion monitoring model; The set sensors are connected to the multimodal fusion monitoring model.

5. The multimodal fusion monitoring system for the power industry according to claim 4 is characterized in that: The model run update is also configured as: Collect the real-time multimodal data set using sensors, and analyze the real-time multimodal data set to obtain corresponding real-time electrical parameters, real-time equipment status, real-time environmental parameters, real-time insulation performance and real-time image video; Deriving the real-time electrical parameter, various data in the real-time device status, and the real-time insulation resistance, and using the first association relationship, generating and outputting a first warning signal for a sensor corresponding to the data with an abnormal derivative sign; Using the real-time electrical parameters, various data in the real-time device status and the real-time insulation resistance, a real-time similarity calculation is performed in the second association relationship, and when the real-time similarity is greater than or equal to a preset similarity threshold, a second warning signal indicating the presence of discharge abnormality, appearance abnormality and scene abnormality is obtained and output; The update cycle is preset, and when the set sensor completes one update cycle, the first association relationship and the second association relationship are rebuilt.

6. A multi-modal fusion monitoring method for the power industry, characterized in that: The method includes: S1: Acquire a historical power multimodal data set, where the multimodal data set is collected by sensors installed on power equipment; S2: Associating various data in the multimodal data set to obtain corresponding association relationships; S3: constructing a multimodal fusion monitoring model based on the association relationship; S4: inputting the real-time multimodal data set into the model and outputting the monitoring results; recapturing the association relationship based on the update cycle and using it to update the model operation module.

7. The multimodal fusion monitoring method for the electric power industry according to claim 6 is characterized in that: Step S1 also includes: Preset monitoring period; The set sensors collect electrical parameters, equipment status, environmental parameters, insulation performance and image videos based on time series; The electrical parameters include voltage, current, power and frequency; The device status includes temperature, vibration and sound; The insulation performance includes insulation resistance and partial discharge; The image video includes the appearance of the device and the working scene.

8. The multimodal fusion monitoring method for the electric power industry according to claim 7, characterized in that: Step S2 also includes: Unifying the collected electrical parameters, the equipment status, the environmental parameters, the insulation performance and the image video on the same time axis based on a time series; Derivatives are obtained for the electrical parameters, various data in the device status, and the insulation resistance, and derivatives with the same signs within the same monitoring period are set as a first association relationship; and the first association relationship is output; Detect the partial discharge, the appearance equipment and the working scene, capture the electrical parameters, the equipment status and the insulation resistance corresponding to the discharge abnormality, the appearance abnormality and the scene abnormality, and set them as a second association relationship; output the second association relationship.

9. The multimodal fusion monitoring method for the electric power industry according to claim 8, characterized in that: Step S3 also includes: Acquire the first association relationship and the second association relationship, and store them in the multimodal fusion monitoring model; The set sensors are connected to the multimodal fusion monitoring model.

10. The multi-modal fusion monitoring method for the electric power industry according to claim 9, characterized in that: Step S4 also includes: Collect the real-time multimodal data set using sensors, and analyze the real-time multimodal data set to obtain corresponding real-time electrical parameters, real-time equipment status, real-time environmental parameters, real-time insulation performance and real-time image video; Deriving the real-time electrical parameter, various data in the real-time device status, and the real-time insulation resistance, and using the first association relationship, generating and outputting a first warning signal for a sensor corresponding to the data with an abnormal derivative sign; Using the real-time electrical parameters, various data in the real-time device status and the real-time insulation resistance, a real-time similarity calculation is performed in the second association relationship, and when the real-time similarity is greater than or equal to a preset similarity threshold, a second warning signal indicating the presence of discharge abnormality, appearance abnormality and scene abnormality is obtained and output; The update cycle is preset, and when the set sensor completes one update cycle, the first association relationship and the second association relationship are rebuilt.

Images