Intelligent photovoltaic power station fault diagnosis system

Abstract

The invention provides an intelligent photovoltaic power station fault diagnosis system, which belongs to the technical field of photovoltaic power generation and comprises a data acquisition module for acquiring key component operation parameters, a quantum processing module for integrating the parameters, a pulse neural network module for performing secondary integration analysis on an integration result to determine a pulse output quantity, and a fault diagnosis module for performing fault diagnosis on the pulse output quantity. The fault diagnosis module decomposes the pulse output quantity to determine a fault state and analyzes the fault state with a diagnosis state to obtain a diagnosis result, and the visual interaction module displays the operation state and the diagnosis result; by adopting the quantum sensor, the pulse neural network and the quantum machine learning algorithm, the measurement precision, the data processing and analysis capability and the fault diagnosis accuracy and reliability can be improved, the existing technical problems are solved, and the stable operation of the photovoltaic power station is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of photovoltaic power generation, and in particular to an intelligent photovoltaic power station fault diagnosis system. Background Art

[0002] As the global demand for clean energy continues to grow, photovoltaic power generation, as an important form of renewable energy, has been widely used and developed; the scale and number of photovoltaic power stations are increasing, and their stable operation is of great significance to energy supply and environmental protection; however, photovoltaic power stations may have various faults during operation, such as photovoltaic component damage, inverter failure, cable aging, etc. These faults will affect the power generation efficiency and reliability of the power station, and may even cause safety accidents; therefore, it is very necessary to diagnose the faults of photovoltaic power stations in a timely and accurate manner;

[0003] In the past few decades, photovoltaic power station fault diagnosis technology has made certain progress; traditional fault diagnosis methods mainly rely on manual inspections and regular maintenance, but this method is inefficient, costly, and difficult to detect potential faults; with the development of sensor technology, data processing technology, and artificial intelligence technology, some intelligent fault diagnosis methods are gradually applied to photovoltaic power stations; for example, the monitoring system based on sensor data can collect the operating parameters of photovoltaic power stations in real time and diagnose faults through data analysis and algorithm processing; the fault diagnosis method based on machine learning can use historical data to train models to improve the accuracy and reliability of fault diagnosis;

[0004] However, there are still some problems in the existing technology; for example, the measurement accuracy of traditional sensors is limited, and it is difficult to detect tiny fault signals; the efficiency and accuracy of data processing and analysis algorithms need to be improved, and it is difficult to meet the real-time diagnosis needs of large-scale photovoltaic power stations; the training of machine learning models requires a large amount of historical data, and may lack adaptability to newly emerging fault types; in addition, the existing technology often lacks comprehensive consideration of the overall operating status of the photovoltaic power station, making it difficult to accurately diagnose and locate faults. Summary of the invention

[0005] The present invention provides an intelligent photovoltaic power station fault diagnosis system, which adopts quantum sensors to improve measurement accuracy, uses pulse neural networks for data processing and analysis, and combines quantum machine learning algorithms for fault diagnosis. It can effectively solve the problems existing in the prior art, improve the accuracy and reliability of photovoltaic power station fault diagnosis, and ensure the stable operation of photovoltaic power stations.

[0006] The present invention provides an intelligent photovoltaic power station fault diagnosis system, comprising:

[0007] A data acquisition module, which is used to obtain the operating parameters of key components of the photovoltaic power station;

[0008] A quantum processing module, which is connected to the data acquisition module and integrates and processes the operating parameters of the same key component through a quantum processing device;

[0009] A pulse neural network module is connected to the quantum processing module and performs secondary integration analysis on the integration result based on the pulse neural network model to determine the pulse output of the photovoltaic power station at this moment;

[0010] A fault diagnosis module, which is connected to the pulse neural network module, is used to pre-set the diagnosis state, and decompose the pulse output according to the operation type inside the power station to determine the fault state at the current moment; analyze the fault state and the diagnosis state to obtain the fault diagnosis result;

[0011] A visual interaction module is connected to the fault diagnosis module and is used to display the operating status of the photovoltaic power station and the fault diagnosis results.

[0012] According to an intelligent photovoltaic power station fault diagnosis system provided by the present invention, the data acquisition module includes:

[0013] Multi-mode sensors are arranged at key components of the photovoltaic power station to collect operating parameters of the key components, wherein the operating parameters include a number of physical data;

[0014] A data preprocessing unit is connected to the multi-mode sensor and is used to clean, denoise and normalize the above operating parameters.

[0015] According to an intelligent photovoltaic power station fault diagnosis system provided by the present invention, the quantum processing module includes:

[0016] The quantum sensor is connected to the data preprocessing unit, and summarizes and analyzes the preprocessed operating parameters of each key component based on the quantum integration model to obtain the quantum integration value Q corresponding to each key component at the current time t jt ;

[0017] The quantum integration model is:

[0018]

[0019] Among them, Q jt is the quantum integration value corresponding to the key component j at time t; α is the sensitivity coefficient of the quantum sensor, which is determined based on the calibration experiment of the quantum sensor; ψ i (t) is the quantum state, |ψ i (t)| 2 represents the probability amplitude of the quantum state, which is determined by the quantum physical properties and the measurement environment; P ihis the physical data corresponding to the i-th quantum state of key component j; n is the number of quantum states, that is, the number of physical data contained in the operating parameters;

[0020] A quantum encoding unit is connected to the quantum sensor and is used to encode the quantum integrated value.

[0021] According to an intelligent photovoltaic power station fault diagnosis system provided by the present invention, the pulse neural network module includes:

[0022] The arrangement and sorting unit is connected to the quantum encoding unit and arranges each quantum integration value Q according to the encoding information. jt Arrange and classify;

[0023] The secondary integration unit is connected to the arrangement and sorting unit to convert the quantum integration value V jt Substitute into the pulse neural network model to calculate the pulse output y of the photovoltaic power station at the current time t (t) ;

[0024] The pulse neural network model is:

[0025]

[0026] Among them, y (t) is the pulse output of the photovoltaic power station at the current time t; ω j is the connection weight, obtained based on historical data training; Q jt is the quantum integration value corresponding to the key component j at time t; is the pulse function, τ j is the time delay from the detection of key component j to the secondary integration, which is determined by the structure and training process of the spiking neural network; m is the number of input signals, that is, the number of key components involved in the detection;

[0027] A parameter training unit is used to optimize the parameters in the pulse neural network model according to historical data.

[0028] According to an intelligent photovoltaic power station fault diagnosis system provided by the present invention, the fault diagnosis module includes:

[0029] The output decomposition unit is connected to the secondary integration unit and is used to convert the pulse output y of the photovoltaic power station at the current time t into (t) Decompose y according to the preset power station operation type a(t) for and b(t) , the decomposition process is:

[0030]

[0031] Where a is the first operation type of the power plant, b is the second operation type of the power plant; j∈a represents the key components belonging to the first operation type a, j∈b represents the key components belonging to the second operation type b; W j is the weight of the key component, which is determined according to the importance of the component and the degree of impact on the operation of the power station; Q jt is the quantum integration value corresponding to the key component j at time t; m is the number of key components involved in the detection;

[0032] A fault state generating unit is connected to the output quantity decomposition unit and is used to generate a fault state ψ at the current time t. f(t) , ψ f(t) =(y a(t) ,y b(t) );

[0033] The diagnostic state preset unit determines the diagnostic state ψ based on the normal operation parameters and experience of the photovoltaic power station d , ψ d =(y a0 ,y b0 );

[0034] A diagnosis and analysis unit, connected to the fault state generating unit and the diagnosis state preset unit, analyzes the fault state and the diagnosis state through a fault diagnosis model to obtain a fault diagnosis result F;

[0035] The fault diagnosis model is:

[0036] F=|<ψ f(t) |- d >| 2

[0037] Where F is the fault diagnosis result, |<ψ f(t) |ψ d >| 2 Represents the fault state ψ f(t) With diagnostic state ψ d The square of the modulus of the inner product of .

[0038] According to an intelligent photovoltaic power station fault diagnosis system provided by the present invention, the preset power station operation type is divided according to the function of the power station components, that is, the first operation type a is power generation related components, and the second operation type b is auxiliary system components.

[0039] According to an intelligent photovoltaic power station fault diagnosis system provided by the present invention, the preset power station operation type is divided according to the impact of the fault type, that is, the first operation type a is an electrical fault related component, and the second operation type b is a physical fault related component.

[0040] According to an intelligent photovoltaic power station fault diagnosis system provided by the present invention, the visual interaction module includes:

[0041] A visualization interface, which is connected to the diagnostic analysis unit and is used to display the real-time operating status, fault diagnosis results and historical data trends of the photovoltaic power station;

[0042] The user interaction unit is used to provide users with the operation authority to perform parameter setting, data analysis and report generation through the interface.

[0043] Compared with the prior art, the present invention has the following beneficial effects:

[0044] 1. Improve measurement accuracy: Using quantum sensors to measure the operating parameters of key components of photovoltaic power plants can achieve ultra-sensitive measurements, improve data accuracy, and thus more accurately detect tiny fault signals;

[0045] 2. Enhance data processing capabilities: Using pulse neural networks to analyze the integrated operating parameters can fully tap the potential information in the data and improve the efficiency and accuracy of data processing and analysis;

[0046] 3. Improve the accuracy of fault diagnosis: Combined with quantum machine learning algorithms, through learning and training of a large amount of historical data, it can diagnose faults more accurately and improve the accuracy and reliability of fault diagnosis;

[0047] 4. Strong real-time and adaptability: It can collect and process data in real time, monitor and diagnose the operation status of photovoltaic power stations in real time, detect faults in time and issue early warnings; at the same time, the system has strong adaptability to new fault types and can improve the accuracy of diagnosis by continuously learning and updating models;

[0048] 5. Comprehensive consideration of the overall operation status of the power station: The present invention comprehensively considers the overall operation status of the photovoltaic power station from data acquisition, quantum processing, pulse neural network analysis to fault diagnosis, and can achieve accurate diagnosis and location of faults, thereby improving the operation stability and reliability of the power station;

[0049] 6. Visual interaction: Through the visual interaction module, users can intuitively understand the operating status and fault diagnosis results of the photovoltaic power station, facilitate parameter setting, data analysis and report generation, and improve user experience and management efficiency.

[0050] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description and the accompanying drawings.

[0051] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0053] Figure 1 It is a structural schematic diagram of an intelligent photovoltaic power station fault diagnosis system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The preferred embodiments of the present invention are described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0055] Embodiment 1:

[0056] This embodiment provides an intelligent photovoltaic power station fault diagnosis system. Figure 1 ,include:

[0057] A data acquisition module, which is used to obtain the operating parameters of key components of the photovoltaic power station;

[0058] The quantum processing module is connected to the data acquisition module and integrates and processes the operating parameters of the same key component through the quantum processing device;

[0059] The pulse neural network module is connected to the quantum processing module, and performs secondary integration analysis on the integration results based on the pulse neural network model to determine the pulse output of the photovoltaic power station at this moment;

[0060] The fault diagnosis module is connected to the pulse neural network module and is used to pre-set the diagnosis state and decompose the pulse output according to the operation type inside the power station to determine the fault state at the current moment; analyze the fault state and the diagnosis state to obtain the fault diagnosis result;

[0061] The visualization interaction module is connected with the fault diagnosis module to display the operation status and fault diagnosis results of the photovoltaic power station.

[0062] The principle of the above embodiment is: the data acquisition module collects the operating parameters of the key components of the photovoltaic power station through a multi-mode sensor and performs preprocessing; the quantum processing module integrates the preprocessed operating parameters using a quantum sensor to obtain a quantum integrated value; the pulse neural network module arranges, classifies and re-integrates the quantum integrated value to calculate the pulse output of the photovoltaic power station; the fault diagnosis module decomposes the pulse output according to the power station operation type, generates a fault state, and analyzes it with the preset diagnosis state to obtain a fault diagnosis result; the visual interaction module displays the operating status and fault diagnosis results of the photovoltaic power station, which is convenient for users to monitor and manage;

[0063] The beneficial effects of the above embodiments are: improving the accuracy and reliability of fault diagnosis, being able to timely discover potential faults of photovoltaic power stations and reduce losses caused by faults; achieving real-time monitoring and intelligent management of photovoltaic power stations and improving the operating efficiency and stability of power stations; through the visual interactive module, users can intuitively understand the operating status and fault diagnosis results of the power station, facilitating decision-making and maintenance; using quantum processing and pulse neural network technology, improving the efficiency and accuracy of data processing, and being able to better meet the fault diagnosis needs of large-scale photovoltaic power stations.

[0064] In order to further optimize the above embodiment, the data acquisition module includes:

[0065] Multi-mode sensors are deployed at key components of photovoltaic power plants to collect operating parameters of key components, which include several physical data. For example, current sensors are used to measure current, voltage sensors are used to measure voltage, temperature sensors are used to measure the temperature of key components, and irradiation sensors are used to measure light intensity. These sensors can collect operating parameters of key components of photovoltaic power plants in real time and provide data support for subsequent fault diagnosis.

[0066] The data preprocessing unit is connected to the multi-mode sensor and is used to clean, denoise and normalize the above-mentioned operating parameters. In actual operation, the data collected by the sensor may be affected by noise and interference, resulting in inaccurate data. The data preprocessing unit improves the quality of the data by cleaning the data, removing abnormal data and noise. De-noising can use methods such as filtering to reduce the impact of noise on the data. Normalization converts the data into a unified range to facilitate subsequent data processing and analysis.

[0067] Through the above implementation, the data acquisition module can accurately collect the operating parameters of the key components of the photovoltaic power station, and pre-process the data to improve the quality and reliability of the data, and provide an accurate data basis for subsequent fault diagnosis. Its technical effect is that the pre-processed data can better reflect the actual operating status of the photovoltaic power station, reduce the impact of data errors on fault diagnosis, and improve the accuracy and reliability of fault diagnosis. The principle is to make the data more stable and accurate through cleaning, denoising and normalization, which is convenient for subsequent analysis and processing.

[0068] In order to further optimize the above embodiment, the quantum processing module includes:

[0069] The quantum sensor is connected to the data preprocessing unit, and the preprocessed operating parameters of each key component are summarized and analyzed based on the quantum integration model to obtain the quantum integration value Q corresponding to each key component at the current time t jt ;

[0070] The quantum integration model is:

[0071]

[0072] Among them, Q jt is the quantum integration value corresponding to the key component j at time t; α is the sensitivity coefficient of the quantum sensor, which is determined based on the calibration experiment of the quantum sensor; ψ i (t) is the quantum state, |ψ i (t)| 2 represents the probability amplitude of the quantum state, which is determined by the quantum physical properties and the measurement environment; P ij is the physical data corresponding to the i-th quantum state of key component j; n is the number of quantum states, that is, the number of physical data contained in the operating parameters;

[0073] The quantum encoding unit is connected to the quantum sensor and is used to encode the quantum integrated value.

[0074] It should be noted that the formula of the quantum integration model is based on the principles of quantum physics, and the summary analysis of operating parameters is achieved by combining the probability amplitude of the quantum state with the physical data of key components. The sensitivity coefficient of the quantum sensor is used to adjust the sensitivity of the measurement. The probability amplitude of the quantum state reflects the uncertainty of the quantum state, and P ij is the physical data corresponding to the ith quantum state of key component j. By comprehensive calculation of these parameters, the quantum integration value Q is obtained. jt , thereby achieving high-precision integration of key component operating parameters;

[0075] The high-precision measurement capability of quantum sensors can capture tiny changes in operating parameters, thereby providing more accurate data support for subsequent fault diagnosis, helping to improve the sensitivity and accuracy of fault diagnosis and promptly detect potential fault problems.

[0076] In practical applications, accurate calibration experiments are required for quantum sensors to determine the appropriate sensitivity coefficients and ensure the accuracy of the measurements. At the same time, the probability amplitude of the quantum state will be affected by the quantum physical properties and the measurement environment, so it is necessary to ensure the stability of the measurement environment and reduce the impact of external interference on the measurement results. In addition, the encoding method of the quantum coding unit needs to match the subsequent pulse neural network module to ensure the effective transmission and processing of data.

[0077] In order to further optimize the above embodiment, the pulse neural network module includes:

[0078] The arrangement and sorting unit is connected to the quantum encoding unit and performs the quantum integration value Q according to the encoding information. jt Arrange and classify;

[0079] The secondary integration unit is connected to the arrangement and sorting unit to convert the quantum integration value Q jt Substitute into the pulse neural network model to calculate the pulse output y of the photovoltaic power station at the current time t (t) ;

[0080] The spiking neural network model is:

[0081]

[0082] Among them, y (t) is the pulse output of the photovoltaic power station at the current time t; ω j is the connection weight, obtained based on historical data training; Q jt is the quantum integration value corresponding to the key component j at time t; is the pulse function, τ j is the time delay from the detection of key component j to the secondary integration, which is determined by the structure and training process of the spiking neural network; m is the number of input signals, that is, the number of key components involved in the detection;

[0083] A parameter training unit is used to optimize the parameters in the pulse neural network model according to historical data.

[0084] It should be noted that the formula of the pulse neural network model is based on the principle of the pulse neural network. The quantum integration value is weighted and summed through the connection weights, and the pulse function and time delay are combined to calculate the pulse output of the photovoltaic power station. The connection weight reflects the contribution of the quantum integration value of different key components to the pulse output, which is obtained through historical data training. The pulse function and time delay take into account the transmission and processing characteristics of the signal in the network.

[0085] The quantum integration value is arranged and classified by the arrangement and sorting unit, and the secondary integration unit calculates the pulse output using the pulse neural network model, which can fully consider the relationship between key components and the signal transmission delay, and more accurately reflect the operating status of the photovoltaic power station. The parameter training unit optimizes the model parameters based on historical data, further improving the calculation accuracy of the pulse output and providing a reliable data basis for fault diagnosis.

[0086] In practical applications, it is necessary to ensure the quality and representativeness of historical data in order to train accurate connection weights. At the same time, the determination of pulse function and time delay needs to be reasonably set according to the actual characteristics of the photovoltaic power station to fully reflect the signal transmission and processing process. In addition, the training and optimization of the model requires a certain amount of computing resources and time, and it is necessary to reasonably arrange computing resources and training time to improve the efficiency of the system.

[0087] In order to further optimize the above embodiment, the fault diagnosis module includes:

[0088] The output decomposition unit is connected to the secondary integration unit and is used to convert the pulse output y of the photovoltaic power station at the current time t (t) Decompose y according to the preset power station operation type a(t) for and b(t) , the decomposition process is:

[0089]

[0090] Where a is the first operation type of the power plant, b is the second operation type of the power plant; j∈a represents the key components belonging to the first operation type a, j∈b represents the key components belonging to the second operation type b; W j is the weight of the key component, which is determined according to the importance of the component and the degree of impact on the operation of the power station; Q jt is the quantum integration value corresponding to the key component j at time t; m is the number of key components involved in the detection;

[0091] The fault state generation unit is connected to the output quantity decomposition unit and is used to generate the fault state ψ at the current time t f(t) , ψ f(t) =(y a(t) ,y b(t) );

[0092] The diagnostic state preset unit determines the diagnostic state ψ based on the normal operation parameters and experience of the photovoltaic power station d , ψ d =(y a0 ,y b0 );

[0093] A diagnosis and analysis unit, which is connected to the fault state generating unit and the diagnosis state preset unit, analyzes the fault state and the diagnosis state through a fault diagnosis model to obtain a fault diagnosis result F;

[0094] The fault diagnosis model is:

[0095] F=|<ψ f(t) |ψ d >| 2

[0096] Where F is the fault diagnosis result, |<ψ f(t) |ψ d >| 2 Represents the fault state ψ f(t) With diagnostic state ψ d The square of the modulus of the inner product of .

[0097] It should be noted that by weighting the quantum integration values ​​of different types of components, calculating the ratio with the total weighted sum, and then multiplying it by the overall pulse output, the fault state components corresponding to each type are obtained; such a decomposition formula can better reflect the characteristics of the functional division of power station components;

[0098] For the calculation of fault diagnosis results, let's take a specific example: Assume that the fault state is ψ f(t) =(0.55,0.75), the diagnostic state is ψ d =(0.5,0.7);

[0099] According to the fault diagnosis model F=|<ψ f(t) |ψ d >| 2 , first calculate the inner product:

[0100] < f(t) |ψ d >=0.55*0.5+0.75*0.7

[0101] =0.275+0.525

[0102] =0.8;

[0103] Then the fault diagnosis result F=0.8 2 =0.64;

[0104] Furthermore, a threshold value may be preset, for example, the threshold value is set to 0.5, then a fault diagnosis result F exceeding 0.5 will be judged as a fault in the power station at the current moment.

[0105] In general, the fault diagnosis module can accurately diagnose photovoltaic power station faults by decomposing the pulse output, generating fault states, presetting diagnostic states, and conducting diagnostic analysis. In practical applications, it is necessary to set the rationality of each unit formula parameter and the accuracy of the data according to the actual situation to improve the reliability of fault diagnosis.

[0106] In order to further optimize the above embodiment, the preset power station operation types are divided according to the functions of power station components, that is, the first operation type a is power generation related components, and the second operation type b is auxiliary system components.

[0107] It should be noted that the first operation type a is power generation related components, such as photovoltaic modules, inverters, etc. These components are directly involved in the generation and conversion of electric energy, and if a failure occurs, it will directly affect the power generation efficiency of the power station.

[0108] The second operation type b is auxiliary system components, such as combiner boxes, transformers, monitoring systems, etc. These components mainly play the role of assisting power generation and ensuring the normal operation of the power station. If a failure occurs, it may affect the stability and safety of the power station.

[0109] In another implementation method, the preset power station operation types are divided according to the impact of the fault type, that is, the first operation type a is an electrical fault-related component, and the second operation type b is a physical fault-related component.

[0110] It should be noted that the first operation type a is related to electrical faults, such as abnormal voltage, unstable current, excessive power loss, etc. These faults are usually related to the performance of the electrical system and may cause a decrease in the quality of power output from the power station.

[0111] The second operation type b is related to physical faults, such as damaged PV panels, loose connectors, overheated equipment, etc. These faults are often related to the state of the physical components of the power station and may affect the reliability and life of the power station.

[0112] In order to further optimize the above embodiment, the visual interaction module includes:

[0113] A visualization interface, which is connected to the diagnostic analysis unit and is used to display the real-time operating status of the photovoltaic power station, fault diagnosis results and historical data trends;

[0114] The user interaction unit is used to provide users with the operation authority to perform parameter setting, data analysis and report generation through the interface.

[0115] It should be noted that by displaying these data in the form of intuitive charts and graphs, users can clearly understand the operation of the photovoltaic power station. Users can adjust the relevant parameters of the photovoltaic power station according to their needs, conduct in-depth analysis of the data, and generate detailed reports. Through the visual interaction module, users can more intuitively understand the operation of the photovoltaic power station, discover problems in time and deal with them, thereby improving the management efficiency and reliability of the photovoltaic power station.

[0116] Finally, 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 aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. An intelligent photovoltaic power station fault diagnosis system, characterized in that: include: A data acquisition module, which is used to obtain the operating parameters of key components of the photovoltaic power station; A quantum processing module, which is connected to the data acquisition module and integrates and processes the operating parameters of the same key component through a quantum processing device; A pulse neural network module is connected to the quantum processing module and performs secondary integration analysis on the integration result based on the pulse neural network model to determine the pulse output of the photovoltaic power station at this moment; A fault diagnosis module, which is connected to the pulse neural network module, is used to pre-set the diagnosis state, and decompose the pulse output according to the operation type inside the power station to determine the fault state at the current moment; analyze the fault state and the diagnosis state to obtain the fault diagnosis result; A visual interaction module is connected to the fault diagnosis module and is used to display the operating status of the photovoltaic power station and the fault diagnosis results.

2. The intelligent photovoltaic power station fault diagnosis system according to claim 1, characterized in that: The data acquisition module comprises: Multi-mode sensors are arranged at key components of the photovoltaic power station to collect operating parameters of the key components, wherein the operating parameters include a number of physical data; A data preprocessing unit is connected to the multi-mode sensor and is used to clean, denoise and normalize the above operating parameters.

3. The intelligent photovoltaic power station fault diagnosis system according to claim 2 is characterized in that: The quantum processing module comprises: The quantum sensor is connected to the data preprocessing unit, and summarizes and analyzes the preprocessed operating parameters of each key component based on the quantum integration model to obtain the quantum integration value Q corresponding to each key component at the current time t jt ; The quantum integration model is: Among them, Q jt is the quantum integration value corresponding to the key component j at time t; α is the sensitivity coefficient of the quantum sensor, which is determined based on the calibration experiment of the quantum sensor; ψ i (t) is the quantum state, |ψ i (t)| 2 represents the probability amplitude of the quantum state, which is determined by the quantum physical properties and the measurement environment; P ij is the physical data corresponding to the i-th quantum state of key component j; n is the number of quantum states, that is, the number of physical data contained in the operating parameters; A quantum encoding unit is connected to the quantum sensor and is used to encode the quantum integrated value.

4. The intelligent photovoltaic power station fault diagnosis system according to claim 3 is characterized in that: The pulse neural network module comprises: The arrangement and sorting unit is connected to the quantum encoding unit and arranges each quantum integration value Q according to the encoding information. jt Arrange and classify; The secondary integration unit is connected to the arrangement and sorting unit to convert the quantum integration value Q jt Substitute into the pulse neural network model to calculate the pulse output y of the photovoltaic power station at the current time t (t) ; The pulse neural network model is: Among them, y (t) is the pulse output of the photovoltaic power station at the current time t; ω j is the connection weight, obtained based on historical data training; Q jt is the quantum integration value corresponding to the key component j at time t; is the pulse function, τ j is the time delay from the detection of key component j to the secondary integration, which is determined by the structure and training process of the spiking neural network; m is the number of input signals, that is, the number of key components involved in the detection; A parameter training unit is used to optimize the parameters in the pulse neural network model according to historical data.

5. The intelligent photovoltaic power station fault diagnosis system according to claim 4 is characterized in that: The fault diagnosis module comprises: The output decomposition unit is connected to the secondary integration unit and is used to convert the pulse output y of the photovoltaic power station at the current time t into (t) Decompose y according to the preset power station operation type a(t) for and b(t) , the decomposition process is: Where a is the first operation type of the power plant, b is the second operation type of the power plant; j∈a represents the key components belonging to the first operation type a, j∈b represents the key components belonging to the second operation type b; W j is the weight of the key component, which is determined according to the importance of the component and the degree of impact on the operation of the power station; Q jt is the quantum integration value corresponding to the key component j at time t; m is the number of key components involved in the detection; A fault state generating unit is connected to the output quantity decomposition unit and is used to generate a fault state ψ at the current time t. f(t) , ψ f(t) =(y a(t) ,y b(t) ); The diagnostic state preset unit determines the diagnostic state ψd based on the normal operation parameters and experience of the photovoltaic power station, ψd = (y a0 ,y b0 ); A diagnosis and analysis unit, connected to the fault state generating unit and the diagnosis state preset unit, analyzes the fault state and the diagnosis state through a fault diagnosis model to obtain a fault diagnosis result F; The fault diagnosis model is: F=|<ψ f(t) |ψ d >| 2 Where F is the fault diagnosis result, |<ψ f(t) |ψ d >| 2 Represents the fault state ψ f(t) The square of the modulus of the inner product with the diagnostic state ψd.

6. The intelligent photovoltaic power station fault diagnosis system according to claim 5, characterized in that: The preset power station operation types are divided according to the functions of power station components, that is, the first operation type a is power generation related components, and the second operation type b is auxiliary system components.

7. The intelligent photovoltaic power station fault diagnosis system according to claim 5, characterized in that: The preset power station operation type is divided according to the impact of the fault type, that is, the first operation type a is an electrical fault related component, and the second operation type b is a physical fault related component.

8. An intelligent photovoltaic power station fault diagnosis system according to claims 1-7, characterized in that: The visual interaction module includes: A visualization interface, which is connected to the diagnostic analysis unit and is used to display the real-time operating status, fault diagnosis results and historical data trends of the photovoltaic power station; The user interaction unit is used to provide users with the operation authority to perform parameter setting, data analysis and report generation through the interface.

Images