Intelligent fault diagnosis and recovery system of new energy centralized control system

Abstract

The invention belongs to the technical field of fault diagnosis, and provides a new energy centralized control system intelligent fault diagnosis and recovery system, which comprises a data acquisition module, a fault diagnosis module, a fault recovery module and a self-learning module, and is characterized in that the data acquisition module, the fault diagnosis module, the fault recovery module and the self-learning module are electrically connected in sequence; equipment data are acquired in real time through the data acquisition module, the fault type and position are accurately judged through the fault diagnosis module, the fault recovery module can automatically select and execute a recovery strategy, normal operation of the system is rapidly recovered, meanwhile, the self-learning module continuously learns and optimizes, the accuracy and reliability of the system are improved, and the service life of the system is prolonged. The operation and maintenance cost is integrally reduced, the downtime is shortened, and the flexibility and adaptability of the system are enhanced.

Description

Technical Field

[0001] The present invention belongs to the technical field of fault diagnosis, and in particular to an intelligent fault diagnosis and recovery system for a new energy centralized control system. Background Art

[0002] With the rapid development of new energy technologies, new energy centralized control systems have become a key tool for managing various types of new energy equipment; however, the complexity of new energy centralized control systems is increasing, and their fault diagnosis and recovery work has become particularly difficult; traditional fault diagnosis methods rely on manual experience, which is not only inefficient, but also difficult to accurately determine the type and location of the fault; at the same time, the fault recovery process also lacks intelligent and automated support, and often requires manual intervention, which further increases operation and maintenance costs and downtime.

[0003] In the prior art, although there are some rule-based fault diagnosis systems, these systems can often only handle preset fault types and have poor diagnostic effects on unknown or complex faults. At the same time, the fault recovery strategies are relatively fixed and lack flexibility and adaptability.

[0004] To this end, those skilled in the art have proposed an intelligent fault diagnosis and recovery system for a new energy centralized control system to solve the problems raised by the background technology. Summary of the invention

[0005] In order to solve the above technical problems, the present invention provides an intelligent fault diagnosis and recovery system for a new energy centralized control system, so as to solve the problems that the system in the prior art can only handle preset fault types, and the diagnosis effect for unknown faults or complex faults is poor. At the same time, the fault recovery strategy is relatively fixed, lacking flexibility and adaptability.

[0006] Intelligent fault diagnosis and recovery system for new energy centralized control system, including:

[0007] Data acquisition module, used to collect the operating data of each device in the new energy centralized control system in real time;

[0008] A fault diagnosis module is used to perform fault diagnosis on the system based on the collected operation data using a preset fault diagnosis algorithm and generate a fault diagnosis result;

[0009] The fault recovery module is used to automatically select and execute the corresponding fault recovery strategy according to the fault diagnosis results to restore the normal operation of the system;

[0010] The self-learning module is used to continuously learn new fault modes and recovery strategies during the fault diagnosis and recovery process, and optimize the performance of the fault diagnosis and recovery system.

[0011] Preferably, in the fault diagnosis module, the fault diagnosis algorithm uses a graph neural network (GNN) to perform fault diagnosis to improve the accuracy of diagnosis.

[0012] Preferably, the fault prediction module uses big data technology to conduct in-depth analysis of historical operation data, explore the laws and trends of fault occurrence, and achieve early warning of faults. The big data technology uses time series prediction algorithms to model historical operation data to predict the possibility and trend of future faults.

[0013] Preferably, the fault recovery module includes multiple recovery strategies, including restarting the device, adjusting device parameters, replacing spare devices, etc., and automatically selects the most appropriate recovery strategy according to the severity of the fault diagnosis result.

[0014] Preferably, in the fault recovery module, a reinforcement learning algorithm is introduced to optimize the fault recovery strategy, the recovery process is modeled as a Markov decision process (MDP), and the optimal recovery strategy is found through trial and error learning.

[0015] Preferably, the self-learning module learns each fault diagnosis and recovery process through a machine learning algorithm, continuously updates the weights and parameters of the fault diagnosis model and recovery strategy, and improves the accuracy and reliability of the system.

[0016] A processor is configured to execute the intelligent fault diagnosis and recovery system of the new energy centralized control system described above.

[0017] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned intelligent fault diagnosis and recovery system for the new energy centralized control system.

[0018] Compared with the prior art, the present invention has the following beneficial effects:

[0019] 1. The present invention collects the operating data of each device in the new energy centralized control system in real time through the data acquisition module, and uses a preset fault diagnosis algorithm (such as the neural network GNN in the figure) for intelligent diagnosis, which can accurately determine the type and location of the fault, greatly improving the accuracy and efficiency of the diagnosis.

[0020] 2. According to the fault diagnosis results, the fault recovery module of the present invention can automatically select and execute corresponding recovery strategies, such as restarting the device, adjusting device parameters, replacing spare equipment, etc., to restore the normal operation of the system; this not only reduces manual intervention and reduces operation and maintenance costs, but also shortens downtime and improves system availability.

[0021] 3. The present invention also introduces a self-learning module, which can continuously learn new fault modes and recovery strategies during the fault diagnosis and recovery process to optimize the performance of the system; this enables the system to adapt to changing fault types and recovery requirements, and improves the flexibility and adaptability of the system.

[0022] 4. The present invention conducts in-depth analysis of historical operation data through a fault prediction module, and uses big data technology (such as time series prediction algorithm) to explore the laws and trends of fault occurrence, thereby achieving early warning of faults; this helps operation and maintenance personnel take measures in advance to avoid the occurrence of faults or reduce the impact of faults. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 This is a framework diagram of the intelligent fault diagnosis and recovery system of the new energy centralized control system of the present invention. DETAILED DESCRIPTION

[0024] The following embodiments of the present invention are described in further detail in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0025] Embodiment: The present invention provides an intelligent fault diagnosis and recovery system for a new energy centralized control system, such as Figure 1 As shown, it includes a data acquisition module, a fault diagnosis module, a fault recovery module and a self-learning module, and the data acquisition module, the fault diagnosis module, the fault recovery module and the self-learning module are electrically connected in sequence:

[0026] Data acquisition module, used to collect the operating data of each device in the new energy centralized control system in real time;

[0027] A fault diagnosis module is used to perform fault diagnosis on the system based on the collected operation data using a preset fault diagnosis algorithm and generate a fault diagnosis result;

[0028] The fault recovery module is used to automatically select and execute the corresponding fault recovery strategy according to the fault diagnosis results to restore the normal operation of the system;

[0029] The self-learning module is used to continuously learn new fault modes and recovery strategies during the fault diagnosis and recovery process, and optimize the performance of the fault diagnosis and recovery system.

[0030] From the above, we can see that the system obtains equipment data in real time through the data acquisition module, uses the fault diagnosis module to accurately determine the fault type and location, and the fault recovery module can automatically select and execute the recovery strategy to quickly restore the normal operation of the system. At the same time, the self-learning module continuously learns and optimizes, which improves the accuracy and reliability of the system, reduces the overall operation and maintenance costs, shortens the downtime, and enhances the flexibility and adaptability of the system.

[0031] Furthermore, in the fault diagnosis module, the fault diagnosis algorithm uses a graph neural network (GNN) to perform fault diagnosis to improve the accuracy of diagnosis. The formula of the graph neural network includes:

[0032]

[0033] in, is the hidden state of node v in the kth layer, N(v) is the set of neighbor nodes of node v, and W (k) and b (k) are the weight and bias of the kth layer respectively, and σ is the activation function.

[0034] From the above, we can see that in the fault diagnosis module, graph neural network (GNN) is used for fault diagnosis. Through an accurate mathematical model (where is the hidden state of the node in the lth layer, comprehensively considering the node's neighbor node set and the weights and biases of each layer, and performing nonlinear transformation through the activation function), the complex relationship between devices is captured, which significantly improves the accuracy of fault diagnosis, enables the system to locate faults more quickly and accurately, and provides strong support for subsequent fault recovery.

[0035] Furthermore, the fault prediction module uses big data technology to conduct in-depth analysis of historical operation data, explore the laws and trends of fault occurrence, and achieve early warning of faults. The big data technology uses a time series prediction algorithm to model historical operation data to predict the possibility and trend of future faults. The formula of the time series prediction algorithm includes:

[0036]

[0037] Among them, y t It is the operation data at a historical point in time. is the predicted value at the future time point t+1, f LSTM is the prediction function of the LSTM network.

[0038] As can be seen from the above, the fault prediction module uses big data technology, especially the time series prediction algorithm (the algorithm models the operation data at historical time points through the LSTM network and accurately predicts the data trend at future time points), conducts in-depth mining of historical operation data, can discover the potential laws and trends of fault occurrence, and achieve early warning of faults. This enables operation and maintenance personnel to take preventive measures before a fault occurs, effectively avoid or reduce the impact of the fault, and further improve the stability and reliability of the system.

[0039] Furthermore, the fault recovery module includes a variety of recovery strategies, including restarting the device, adjusting device parameters, replacing spare devices, etc., and automatically selects the most appropriate recovery strategy according to the severity of the fault diagnosis result.

[0040] From the above, it can be seen that the fault recovery module contains multiple recovery strategies and can intelligently select the most appropriate recovery measures (such as restarting the device, adjusting parameters or replacing spare equipment, etc.) according to the severity of the fault diagnosis results, ensuring that the fault can be handled in a timely and effective manner. It not only improves the efficiency of fault recovery, but also greatly enhances the flexibility and robustness of the system in dealing with various fault scenarios.

[0041] Furthermore, in the fault recovery module, a reinforcement learning algorithm is introduced to optimize the fault recovery strategy, and the recovery process is modeled as a Markov decision process (MDP). The optimal recovery strategy is found through trial and error learning. The formula of the reinforcement learning algorithm includes:

[0042]

[0043] Among them, π * (as) is the optimal strategy, γ is the discount factor, r(s t ,a t ) is in state s t Take action a t Rewards received.

[0044] From the above, we can see that by introducing the reinforcement learning algorithm and modeling the recovery process as a Markov decision process (MDP), the system can continuously learn by trial and error to find the optimal recovery strategy for various fault scenarios. This not only significantly improves the speed and efficiency of fault recovery, but also enables the system to continuously optimize its recovery strategy and better adapt to the ever-changing fault types and recovery requirements.

[0045] Furthermore, the self-learning module learns each fault diagnosis and recovery process through a machine learning algorithm, continuously updates the weights and parameters of the fault diagnosis model and the recovery strategy, and improves the accuracy and reliability of the system. The formula of the machine learning algorithm includes:

[0046]

[0047] Among them, θ t is the model parameter, η is the learning rate, m t is the first-order momentum estimate, is a correction to the second-order momentum estimate, β1 is an exponential weighting factor for the momentum term, and ε is a small constant to prevent division by zero.

[0048] As can be seen from the above, the self-learning module uses an advanced machine learning algorithm (the algorithm continuously updates the model parameter θ, uses the learning rate η to control the update step size, and combines the correction values ​​of the first-order momentum estimation and the second-order momentum estimation to optimize the weight update, while introducing the exponential weighting coefficient β of the momentum term and the small constant ε to prevent division by zero to ensure the stability and accuracy of learning), to conduct in-depth learning of each fault diagnosis and recovery process, and continuously optimize the weights and parameters of the fault diagnosis model and recovery strategy. This enables the system to continuously accumulate experience from actual operation and improve itself, thereby significantly improving the accuracy of fault diagnosis and the reliability of fault recovery, and ensuring the long-term stable operation of the new energy centralized control system.

[0049] Furthermore, the intelligent fault diagnosis and recovery system of the new energy centralized control system of the embodiment is compared with the current traditional fault diagnosis method (comparative example), and the following table is obtained:

[0050]

[0051] It can be seen from the above table that the new energy centralized control system intelligent fault diagnosis and recovery system of this embodiment shows significant advantages over traditional fault diagnosis methods in data acquisition, fault diagnosis accuracy, fault location speed, fault recovery, recovery strategy flexibility, system self-learning ability, fault prediction ability, operation and maintenance costs, and system downtime.

[0052] Working principle: The data acquisition module collects the operating data of each device in the new energy centralized control system in real time. The fault diagnosis module uses a preset fault diagnosis algorithm (such as the neural network GNN in the figure) to analyze these data and accurately determine the fault type and location; then, the fault recovery module automatically selects and executes the corresponding recovery strategy based on the diagnosis results, such as restarting the device, adjusting parameters or replacing spare equipment, etc., to quickly restore the normal operation of the system; at the same time, the self-learning module continuously learns new fault modes and recovery strategies during the fault diagnosis and recovery process, optimizes model parameters through machine learning algorithms, and improves the accuracy and reliability of the system; in addition, the fault prediction module also uses big data technology to conduct in-depth analysis of historical operating data to achieve early warning of faults, further enhancing the stability and reliability of the system.

[0053] The embodiment of the present application provides an electronic device, which is applicable to the above-mentioned intelligent fault diagnosis and recovery system of the new energy centralized control system, including:

[0054] Memory, used to protect computer programs and data;

[0055] Processor, used to run system programs.

[0056] An embodiment of the present application provides a computer storage medium, which is applicable to the above-mentioned new energy centralized control system intelligent fault diagnosis and recovery system, and performs hierarchical confidentiality management on the above-mentioned system and data in accordance with confidentiality management requirements.

[0057] Those skilled in the art will appreciate that the embodiments of the present application may be provided as a system or a computer program product. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.

[0058] The present application is described with reference to the flowcharts and / or block diagrams of the devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0059] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0060] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0061] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0062] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0063] Computer readable media include permanent and non-permanent, removable and non-removable media, and can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include transitory media such as modulated data signals and carrier waves.

[0064] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, commodity or device including the elements.

[0065] The embodiments of the present invention are provided for the purpose of illustration and description. Although the embodiments of the present invention have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations of the present invention. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. Intelligent fault diagnosis and recovery system for new energy centralized control system, characterized by: include: Data acquisition module, used to collect the operating data of each device in the new energy centralized control system in real time; A fault diagnosis module is used to perform fault diagnosis on the system based on the collected operation data using a preset fault diagnosis algorithm and generate a fault diagnosis result; The fault recovery module is used to automatically select and execute the corresponding fault recovery strategy according to the fault diagnosis results to restore the normal operation of the system; The self-learning module is used to continuously learn new fault modes and recovery strategies during the fault diagnosis and recovery process, and optimize the performance of the fault diagnosis and recovery system.

2. The intelligent fault diagnosis and recovery system for the new energy centralized control system as claimed in claim 1, characterized in that: In the fault diagnosis module, the fault diagnosis algorithm uses a graph neural network to perform fault diagnosis.

3. The intelligent fault diagnosis and recovery system for the new energy centralized control system as claimed in claim 1, characterized in that: The fault prediction module uses big data technology to conduct in-depth analysis of historical operation data, explore the laws and trends of fault occurrence, and achieve early warning of faults. The big data technology uses time series prediction algorithms to model historical operation data.

4. The intelligent fault diagnosis and recovery system for the new energy centralized control system as claimed in claim 1, characterized in that: The fault recovery module includes multiple recovery strategies, including restarting the device, adjusting device parameters, replacing spare devices, and automatically selecting the most appropriate recovery strategy according to the severity of the fault diagnosis result.

5. The intelligent fault diagnosis and recovery system for the new energy centralized control system as claimed in claim 4, characterized in that: In the fault recovery module, a reinforcement learning algorithm is introduced to optimize the fault recovery strategy. The recovery process is modeled as a Markov decision process, and the optimal recovery strategy is found through trial and error learning.

6. The intelligent fault diagnosis and recovery system for the new energy centralized control system as claimed in claim 1, characterized in that: The self-learning module learns each fault diagnosis and recovery process through a machine learning algorithm, and continuously updates the weights and parameters of the fault diagnosis model and the recovery strategy.

7. A processor, characterized in that: The method is configured to execute the intelligent fault diagnosis and recovery system of the new energy centralized control system according to any one of claims 1 to 6.

8. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the intelligent fault diagnosis and recovery system for the new energy centralized control system according to any one of claims 1 to 6 is implemented.

Images