Method and system for monitoring components in GCB control cabinet based on state recognition

Abstract

The invention discloses a method and system for monitoring components in a GCB control cabinet based on state recognition, and relates to the technical field of monitoring and maintenance of an electric power system.The method comprises the steps that state information of the components in the GCB control cabinet is collected, and all the collected state information is transmitted to a server to be stored and preprocessed; based on an abnormal recognition algorithm of the decision-making unit, analyzing components in the GCB control cabinet and an environment state; and based on the abnormal state threshold value and an alarm unit, carrying out abnormal alarm and formulating an adjustment strategy. According to the method, through integrated monitoring, intelligent analysis and automatic response strategies, data cleaning, format conversion and standardized processing, the data quality is improved, a quantitative decision-making basis is provided for a decision-making unit, the intelligent level of decision-making is improved, the operation safety and reliability of the GCB control cabinet are improved, and the GCB control cabinet is suitable for popularization and application. The fault rate is reduced, the maintenance efficiency is improved, and revolutionary progress is brought to the field of industrial automation.

Description

Technical Field

[0001] The present invention relates to the technical field of monitoring and maintenance of electric power systems, and in particular to a method and system for monitoring components in a GCB control cabinet based on state recognition. Background Art

[0002] With the continuous development of power systems and the continuous growth of power demand, the importance of safe operation and efficient maintenance of high-voltage switchgear (GCB) as a key component in the power system has become increasingly prominent. Traditional GCB monitoring and maintenance technology mainly relies on regular manual inspection and maintenance. This method is not only inefficient, but also unable to detect potential fault hazards in time. Therefore, the component monitoring technology in the GCB control cabinet based on state recognition has emerged and has become the development trend of the current power system monitoring and maintenance technology. At present, the component monitoring technology in the GCB control cabinet based on state recognition has made significant progress. These technologies usually include the collection, transmission, storage and preprocessing of state information, as well as abnormal recognition algorithms based on decision-making units. They can monitor and analyze the equipment status in real time, thereby realizing early warning and prevention of faults, providing decision support for equipment maintenance through intelligent analysis, and improving the operating efficiency and reliability of equipment.

[0003] However, although the existing technology has made progress in some aspects, the existing technical methods are insufficient in the collection and transmission of status information, abnormal identification algorithms, and abnormal alarms and processing. Traditional monitoring systems can often only collect limited component status information and cannot fully understand the equipment status in the GCB control cabinet. The existing technology cannot meet the real-time monitoring needs of the equipment status. Traditional abnormal identification algorithms often rely on fixed parameters and thresholds and cannot adapt to changes in equipment status and complex operating environments. Existing algorithms cannot detect potential fault hazards in a timely and accurate manner. Traditional alarm systems often cannot provide accurate fault location and processing suggestions, resulting in the inability to take effective processing measures in time when a fault occurs. Existing processing strategies often rely on manual intervention and cannot achieve automated and intelligent fault processing. Summary of the invention

[0004] In view of the above-mentioned problems, the present invention is proposed.

[0005] Therefore, the technical problem solved by the present invention is: the existing monitoring and maintenance methods based on the state of the power system have poor adaptability to complex operating environments, untimely abnormality identification and inaccurate alarms, as well as the problem of how to comprehensively monitor the status of components in the GCB control cabinet and efficiently handle faults.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: a method for monitoring components in a GCB control cabinet based on state recognition, comprising collecting state information of components in the GCB control cabinet, transmitting all collected state information to a server for storage and preprocessing; analyzing the components and environmental states in the GCB control cabinet based on an abnormality recognition algorithm of a decision unit; and issuing abnormal alarms and formulating adjustment strategies based on abnormal state thresholds and alarm units.

[0007] As a preferred solution of the method for monitoring components in a GCB control cabinet based on state recognition described in the present invention, the state information of the components in the GCB control cabinet is collected, including collecting acoustic signals, visible light images, installation location information, and infrared image data of the components in the cabinet to form multimodal data, and collecting related action state information of the same control loop and related components for different working conditions; different working conditions include normal operating state of the equipment, maintenance state of the equipment, and abnormal state of the equipment.

[0008] As a preferred solution of the method for monitoring components in a GCB control cabinet based on state recognition described in the present invention, the storage and preprocessing include configuring a WiFi network, building a data transmission channel between a signal acquisition device and a server, setting up an encryption and authentication mechanism for data transmission, and establishing a component feature database, an action model database, and an environment model database on the server side; preprocessing the collected data on the server side, including data cleaning, format conversion, and standardization processing, and the standardized processing of the collected data is expressed as:

[0009]

[0010] in, represents the standardized data of the i-th component at time t, X i (t) represents the original data of the i-th component at time t, and The original data X i (t) The mean and standard deviation of

[0011] As a preferred solution of the method for monitoring components in a GCB control cabinet based on state recognition described in the present invention, the abnormality recognition algorithm includes identifying the state of components in the GCB control cabinet in combination with multimodal data, and constructing an abnormal state recognition model for components in the GCB control cabinet based on a deep belief network, which is expressed as:

[0012]

[0013] Among them, P(v i ) represents the state probability distribution of components in the i-th GCB control cabinet, represents the transposition of the weight matrix of the components in the i-th GCB control cabinet from the hidden layer to the visible layer, represents the transposition of the weight matrix of the components in the i-th GCB control cabinet from the visible layer to the hidden layer, v i Indicates the status of components in the i-th GCB control cabinet, h i represents the hidden layer variables of the components in the i-th GCB control cabinet, Represents the multimodal standardized data of the components in the i-th GCB control cabinet, represents the hidden layer bias term of the components in the i-th GCB control cabinet, Represents the visible layer bias item of the components in the i-th GCB control cabinet.

[0014] As a preferred solution of the method for monitoring components in a GCB control cabinet based on state recognition described in the present invention, the abnormality recognition algorithm also includes the following steps: s (t) and the ambient visible light signal E v (t) Perform standardization processing to obtain a standardized signal and Use the convolution kernel K j The normalized signal is convolved to build an environmental anomaly recognition model, which is expressed as:

[0015]

[0016] Among them, y(t) is the output value at time t, which represents the prediction result of the environmental state, n represents the maximum number of steps of time delay, K j (k) is the weight value of the jth convolution kernel at the kth position, which is used to perform weighted summation of the signal. m represents the size of the convolution kernel, that is, the length of the weight matrix used in the convolution operation. β S is the weight parameter of the ambient acoustic signal, is the ambient acoustic signal at the jth time delay and kth position, β V is the weight parameter of the ambient visible light signal, is the ambient visible light signal at the jth time delay and the kth position.

[0017] As a preferred solution of the method for monitoring components in a GCB control cabinet based on state recognition described in the present invention, wherein: the abnormal alarm includes setting an abnormal state threshold based on the output results of the abnormal state recognition model of the components in the GCB control cabinet and the output results of the environmental abnormality recognition model, and performing an abnormal alarm through the alarm unit; when 0 <P(v i )<0.2, it indicates that there is an abnormality in the components in the GCB control cabinet, and the alarm unit generates an alarm message; when 0.2≤P(v i)<0.8, the state of the components in the GCB control cabinet is in maintenance state. The state of the components is further analyzed, and the real-time state of the components is judged based on the prediction results of the environmental state. If y(t) is greater than or equal to the upper limit threshold θ of the normal state of the environment normal , the component status is judged to be abnormal, and the alarm unit generates an alarm message. If y(t) is less than the upper threshold value θ of the normal state of the environment normal , the state of the component is judged to be normal; when 0.8≤P(v i )<1, it indicates that the components in the GCB control cabinet are in normal status.

[0018] As a preferred solution of the method for monitoring components in a GCB control cabinet based on state identification described in the present invention, the formulation of an adjustment strategy includes immediately triggering an emergency shutdown program when the system receives an alarm message, isolating abnormal components, resetting the components if the abnormal state can be resolved by restarting or resetting, and arranging maintenance personnel to conduct on-site inspections of the abnormal components to eliminate abnormal faults if the abnormal state cannot be resolved by restarting or resetting.

[0019] Another object of the present invention is to provide a component monitoring system in a GCB control cabinet based on state recognition, which can collect status information of components in the GCB control cabinet and transmit all collected status information to a server for storage and preprocessing, thereby solving the problem that the current power system monitoring and maintenance technology has poor adaptability to complex operating environments.

[0020] As a preferred solution of the component monitoring system in the GCB control cabinet based on state recognition described in the present invention, it includes: a data acquisition module, a state analysis module, and an abnormal alarm module; the data acquisition module is used to collect the state information of the components in the GCB control cabinet, and transmit all the collected state information to the server for storage and preprocessing; the state analysis module is used to analyze the components and environmental states in the GCB control cabinet based on the abnormal recognition algorithm of the decision unit; the abnormal alarm module is used to issue abnormal alarms and formulate adjustment strategies based on abnormal state thresholds and alarm units.

[0021] A computer device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement a method for monitoring components in a GCB control cabinet based on state identification.

[0022] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of a method for monitoring components in a GCB control cabinet based on state identification.

[0023] Beneficial effects of the present invention: The method for monitoring components in a GCB control cabinet based on state recognition provided by the present invention realizes comprehensive monitoring of the equipment state by collecting the state information of the components in the GCB control cabinet. The multimodal data collection method can provide more abundant equipment state information, thereby improving the accuracy and reliability of monitoring, and can monitor the state of the components in the GCB control cabinet in real time, and timely discover potential hidden faults, thereby ensuring the safe operation of the power system. Through the abnormal recognition algorithm based on the decision-making unit, an in-depth analysis of the components and environmental state in the GCB control cabinet is realized. This algorithm can effectively process the collected multimodal data and realize accurate recognition of the equipment state. By constructing an abnormal state recognition model through a deep belief network, the accuracy and robustness of the algorithm can be further improved. In addition, by combining the ambient acoustic signal and the ambient visible light signal, the influence of environmental factors on the equipment status can be fully considered, thereby improving the accuracy of abnormal identification. By using the abnormal status threshold and the alarm unit to issue an abnormal alarm and formulate an adjustment strategy, the abnormal status of the components in the GCB control cabinet can be discovered in time, and the alarm unit can issue an abnormal alarm and formulate an adjustment strategy in time, which can effectively deal with the abnormal status, ensure the safe operation of the power system, improve the efficiency and accuracy of fault handling, and reduce the impact of faults on the power system. The present invention achieves better results in comprehensive monitoring of the status of components in the GCB control cabinet, abnormal status identification and fault handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0025] Figure 1 An overall flow chart of a method for monitoring components in a GCB control cabinet based on state recognition provided in the first embodiment of the present invention.

[0026] Figure 2 An overall flow chart of a component monitoring system in a GCB control cabinet based on state recognition provided in the third embodiment of the present invention. DETAILED DESCRIPTION

[0027] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0028] Example 1, reference Figure 1 , is an embodiment of the present invention, and provides a method for monitoring components in a GCB control cabinet based on state recognition, comprising:

[0029] S1: Collect the status information of components in the GCB control cabinet and transmit all the collected status information to the server for storage and preprocessing.

[0030] Furthermore, the status information of components in the GCB control cabinet is collected, including the acoustic signals, visible light images, installation location information, and infrared image data of the components in the cabinet to form multimodal data, and the related action status information of the same control loop and related components is collected for different working conditions; different working conditions include normal operation status of equipment, maintenance status of equipment, and abnormal status of equipment.

[0031] It should be noted that storage and preprocessing include configuring the WiFi network, building a data transmission channel between the signal acquisition device and the server, setting up the encryption and authentication mechanism for data transmission, and establishing a component feature database, an action model database, and an environment model database on the server side; preprocessing the collected data on the server side, including data cleaning, format conversion, and standardization. The standardized processing of the collected data is expressed as:

[0032]

[0033] in, represents the standardized data of the i-th component at time t, X i (t) represents the original data of the i-th component at time t, and The original data X i (t) The mean and standard deviation of

[0034] It should also be noted that by collecting the status information of components in the GCB control cabinet, comprehensive monitoring of the equipment status is achieved. This multimodal data collection method can provide richer equipment status information, thereby improving the accuracy and reliability of monitoring. This method can monitor the status of components in the GCB control cabinet in real time, and discover potential fault hazards in time, thereby ensuring the safe operation of the power system.

[0035] S2: Based on the abnormal identification algorithm of the decision-making unit, the components and environmental status in the GCB control cabinet are analyzed.

[0036] Furthermore, the anomaly recognition algorithm includes identifying the status of components in the GCB control cabinet by combining multimodal data, and constructing an abnormal status recognition model of components in the GCB control cabinet based on a deep belief network, which is expressed as:

[0037]

[0038] Among them, P(v i ) represents the state probability distribution of components in the i-th GCB control cabinet, represents the transposition of the weight matrix of the components in the i-th GCB control cabinet from the hidden layer to the visible layer, represents the transposition of the weight matrix of the components in the i-th GCB control cabinet from the visible layer to the hidden layer, v i Indicates the status of components in the i-th GCB control cabinet, h i represents the hidden layer variables of the components in the i-th GCB control cabinet, Represents the multimodal standardized data of the components in the i-th GCB control cabinet, represents the hidden layer bias term of the components in the i-th GCB control cabinet, Represents the visible layer bias item of the components in the i-th GCB control cabinet.

[0039] It should be noted that the abnormality recognition algorithm also includes the collected environmental acoustic signal E s (t) and the ambient visible light signal E v (t) Perform standardization processing to obtain a standardized signal and Use the convolution kernel K j The normalized signal is convolved to build an environmental anomaly recognition model, which is expressed as:

[0040]

[0041] Among them, y(t) is the output value at time t, which represents the prediction result of the environmental state, n represents the maximum number of steps of time delay, K j (k) is the weight value of the jth convolution kernel at the kth position, which is used to perform weighted summation of the signal. m represents the size of the convolution kernel, that is, the length of the weight matrix used in the convolution operation. β S is the weight parameter of the ambient acoustic signal, is the ambient acoustic signal at the jth time delay and kth position, β V is the weight parameter of the ambient visible light signal, is the ambient visible light signal at the jth time delay and the kth position.

[0042] It should also be noted that the accuracy and robustness of the algorithm can be further improved by building an abnormal state recognition model through a deep belief network. In addition, by combining environmental acoustic signals and ambient visible light signals, the impact of environmental factors on the device state can be fully considered, thereby improving the accuracy of abnormal recognition.

[0043] S3: Based on the abnormal state threshold and alarm unit, abnormal alarm is issued and adjustment strategy is formulated.

[0044] Furthermore, the abnormal alarm includes setting the abnormal state threshold based on the output results of the abnormal state recognition model of the components in the GCB control cabinet and the output results of the environmental abnormality recognition model, and issuing an abnormal alarm through the alarm unit; when 0 <P(v i )<0.2, it indicates that there is an abnormality in the components in the GCB control cabinet, and the alarm unit generates an alarm message; when 0.2≤P(v i )<0.8, the state of the components in the GCB control cabinet is in maintenance state. The state of the components is further analyzed, and the real-time state of the components is judged based on the prediction results of the environmental state. If y(t) is greater than or equal to the upper limit threshold θ of the normal state of the environment normal , the component status is judged to be abnormal, and the alarm unit generates an alarm message. If y(t) is less than the upper threshold value θ of the normal state of the environment normal , the state of the component is judged to be normal; when 0.8≤P(v i )<1, it indicates that the components in the GCB control cabinet are in normal status.

[0045] It should be noted that the formulation of the adjustment strategy includes immediately triggering the emergency shutdown procedure when the system receives an alarm message, isolating the abnormal components, and resetting the components if the abnormal state can be resolved by restarting or resetting. If the abnormal state cannot be resolved by restarting or resetting, arranging maintenance personnel to conduct on-site inspections of the abnormal components to eliminate abnormal faults.

[0046] It should also be noted that based on the abnormal state threshold and alarm unit, abnormal alarm and adjustment strategy can timely detect the abnormal state of components in the GCB control cabinet, and issue abnormal alarm through the alarm unit, so as to take timely response measures to effectively deal with the abnormal state, ensure the safe operation of the power system, improve the efficiency and accuracy of fault handling, and reduce the impact of faults on the power system.

[0047] Embodiment 2 is an embodiment of the present invention, which provides a method for monitoring components in a GCB control cabinet based on state recognition. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0048] In this experiment, four components (1, 2, 3, 4) in the GCB control cabinet and their environment (5, 6) were monitored and analyzed in detail. The first step of the experiment was to collect the status information of the components in the GCB control cabinet, including acoustic signals, visible light images, installation location information and infrared image data. High-precision sensors were used to ensure the accuracy of the data, and the data was transmitted to the server for storage and preprocessing through the configured WiFi network. In the data preprocessing stage, data cleaning was first performed to remove invalid and abnormal data points, and then the data was format converted and standardized for subsequent analysis. After analysis, an abnormal state recognition model of components was constructed based on the deep belief network. The ambient acoustic signals and ambient visible light signals were standardized, and convolution kernels were used for convolution operations to construct an environmental anomaly recognition model. In the abnormal alarm stage, the abnormal state threshold was set, and the abnormal alarm was issued through the alarm unit. When the probability of the abnormal state of the component is lower than 0.2, the system will generate an alarm message, and when the probability is between 0.2 and 0.8, the system will further analyze the component state. If the predicted value of the environmental state exceeds the upper threshold of the normal state, an alarm message will also be generated. Refer to Table 1 to record and analyze the experimental data.

[0049] Table 1 Experimental data record table

[0050]

[0051] According to the experimental data, the following results can be observed: the abnormal state probabilities of components 1 and 3 are low (0.1 and 0.15, respectively), indicating that these components operate stably during the experiment; the abnormal state probability of component 2 is 0.3, indicating that it may need maintenance or further monitoring; the abnormal state probability of component 4 is 0.85, which is close to the normal state, but attention should be paid to possible fluctuations; the state prediction values ​​of environments 5 and 6 are both high, especially environment 6, whose prediction value reaches 0.95, indicating that the environmental state is good; the following conclusions can be drawn from the data analysis; the abnormal recognition algorithm proposed in the present invention can effectively identify the different operating states of components; compared with the prior art, the present invention has advantages in early abnormality detection and helps to prevent potential failures; combined with multimodal data and deep learning technology, the present invention performs well in improving recognition accuracy and efficiency; these results verify the effectiveness of the present invention in improving the safety and reliability of GCB control cabinet operation.

[0052] Example 3, reference Figure 2 , which is an embodiment of the present invention, provides a component monitoring system in a GCB control cabinet based on state recognition, including a data acquisition module, a state analysis module, and an abnormal alarm module.

[0053] The data acquisition module is used to collect the status information of components in the GCB control cabinet and transmit all the collected status information to the server for storage and preprocessing; the status analysis module is used to analyze the components and environmental status in the GCB control cabinet based on the abnormal recognition algorithm of the decision unit; the abnormal alarm module is used to issue abnormal alarms and formulate adjustment strategies based on abnormal status thresholds and alarm units.

[0054] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods of each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0055] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0056] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering, or processing in another suitable manner as necessary, and then stored in a computer memory.

[0057] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc. It should be noted that the above embodiments are only used to illustrate the technical solution of the present invention and are not limited. Although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention, which should be included in the scope of the claims of the present invention.

[0058] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A method for monitoring components in a GCB control cabinet based on state recognition, characterized in that: include: Collect the status information of components in the GCB control cabinet and transmit all the collected status information to the server for storage and preprocessing; Analyze the components and environmental status in the GCB control cabinet based on the abnormal identification algorithm of the decision-making unit; Based on abnormal status thresholds and alarm units, abnormal alarms are issued and adjustment strategies are formulated.

2. The method for monitoring components in a GCB control cabinet based on state recognition according to claim 1, characterized in that: The collecting of status information of components in the GCB control cabinet includes collecting acoustic signals, visible light images, installation location information, and infrared image data of components in the cabinet to form multimodal data, and collecting associated action status information of the same control loop and associated components for different working conditions; Different working conditions include normal equipment operation status, equipment maintenance status, and equipment abnormal status.

3. The method for monitoring components in a GCB control cabinet based on state recognition according to claim 2, characterized in that: The storage and preprocessing include configuring a WiFi network, building a data transmission channel between a signal acquisition device and a server, setting up an encryption and authentication mechanism for data transmission, and establishing a component feature database, an action model database, and an environment model database on the server side; The collected data is preprocessed on the server side, including data cleaning, format conversion and standardization. The standardization of the collected data is expressed as: in, represents the standardized data of the i-th component at time t, X i (t) represents the original data of the i-th component at time t, and The original data X i (t) The mean and standard deviation of 4. The method for monitoring components in a GCB control cabinet based on state recognition according to claim 3 is characterized in that: The abnormality recognition algorithm includes identifying the status of components in the GCB control cabinet by combining multimodal data, and constructing an abnormal status recognition model of components in the GCB control cabinet based on a deep belief network, which is expressed as: Among them, P(v i ) represents the state probability distribution of components in the i-th GCB control cabinet, represents the transposition of the weight matrix of the components in the i-th GCB control cabinet from the hidden layer to the visible layer, represents the transposition of the weight matrix of the components in the i-th GCB control cabinet from the visible layer to the hidden layer, v i Indicates the status of components in the i-th GCB control cabinet, h i represents the hidden layer variables of the components in the i-th GCB control cabinet, Represents the multimodal standardized data of the components in the i-th GCB control cabinet, represents the hidden layer bias term of the components in the i-th GCB control cabinet, Represents the visible layer bias item of the components in the i-th GCB control cabinet.

5. The method for monitoring components in a GCB control cabinet based on state recognition according to claim 4, characterized in that: The abnormality recognition algorithm also includes the collected environmental acoustic signal E s (t) and the ambient visible light signal E v (t) Perform standardization processing to obtain a standardized signal and Use the convolution kernel K j The normalized signal is convolved to build an environmental anomaly recognition model, which is expressed as: Among them, y(t) is the output value at time t, which represents the prediction result of the environmental state, n represents the maximum number of steps of time delay, K j (k) is the weight value of the jth convolution kernel at the kth position, which is used to perform weighted summation of the signal. m represents the size of the convolution kernel, that is, the length of the weight matrix used in the convolution operation. β S is the weight parameter of the ambient acoustic signal, is the ambient acoustic signal at the jth time delay and kth position, β V is the weight parameter of the ambient visible light signal, is the ambient visible light signal at the jth time delay and the kth position.

6. The method for monitoring components in a GCB control cabinet based on state recognition according to claim 5, characterized in that: The abnormal alarm includes setting an abnormal state threshold based on the output results of the abnormal state recognition model of the components in the GCB control cabinet and the output results of the environmental abnormality recognition model, and performing an abnormal alarm through the alarm unit; When 0 <P(v i )<0.2, it indicates that there is an abnormality in the components in the GCB control cabinet, and the alarm unit generates an alarm message; When 0.2≤P(v i )<0.8, the state of the components in the GCB control cabinet is in maintenance state. The state of the components is further analyzed, and the real-time state of the components is judged based on the prediction results of the environmental state. If y(t) is greater than or equal to the upper limit threshold θ of the normal state of the environment normal , the component status is judged to be abnormal, and the alarm unit generates an alarm message. If y(t) is less than the upper threshold value θ of the normal state of the environment normal , then the component status is determined to be normal; When 0.8≤P(v i )<1, it indicates that the components in the GCB control cabinet are in normal status.

7. The method for monitoring components in a GCB control cabinet based on state recognition according to claim 6, characterized in that: The formulation of the adjustment strategy includes immediately triggering an emergency shutdown procedure when the system receives an alarm message, isolating abnormal components, resetting the components if the abnormal state can be resolved by restarting or resetting, and arranging maintenance personnel to conduct on-site inspections of the abnormal components to eliminate abnormal faults if the abnormal state cannot be resolved by restarting or resetting.

8. A system using the method for monitoring components in a GCB control cabinet based on state recognition as claimed in any one of claims 1 to 7, characterized in that: Including data acquisition module, status analysis module, abnormal alarm module; The data acquisition module is used to collect status information of components in the GCB control cabinet and transmit all the collected status information to the server for storage and preprocessing; The state analysis module is used to analyze the components and environmental status in the GCB control cabinet based on the abnormal identification algorithm of the decision unit; The abnormal alarm module is used to issue abnormal alarms and formulate adjustment strategies based on abnormal state thresholds and alarm units.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method for monitoring components in a GCB control cabinet based on state identification as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method for monitoring components in a GCB control cabinet based on state identification according to any one of claims 1 to 7 are implemented.

Images