Analysis method, system, medium and equipment adaptive to fault of water-light storage network source system

Abstract

The invention discloses an analysis method, system, medium and equipment adaptive to faults of a water-optical storage network source system, and relates to the technical field of power system fault analysis. The system comprises a multi-source data acquisition and preprocessing module, a fault feature extraction and classification module, a fault positioning module, a fault influence evaluation module and a dynamic updating and self-adaption module; the method comprises the following steps of multi-source data acquisition and preprocessing, fault feature extraction and classification, fault positioning and influence evaluation, and dynamic updating and adaptive adjustment. The invention provides a fault analysis method adaptive to a water-light storage network source power system, various faults in the complex power system can be comprehensively and accurately analyzed, and rapid and accurate fault type identification, fault position positioning and fault influence range evaluation are realized by comprehensively considering the characteristics of each component of the system. Powerful support is provided for timely and effective fault processing, and stable and reliable operation of a power system is guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of power system fault analysis, and in particular to an analysis method, system, medium and equipment adapted to the fault of a water, light, energy storage and network source system. Background Art

[0002] As the global demand for clean energy continues to grow, the integrated power system of hydropower, photovoltaic power generation, energy storage and grid-based energy has emerged as a new type of power system that integrates hydropower, photovoltaic power generation, energy storage system and traditional grid power supply. This system has shown significant advantages in improving energy utilization efficiency and promoting the consumption of renewable energy. However, due to the complexity and diversity of its components and the large differences in characteristics between the components, fault analysis has become extremely challenging.

[0003] Traditional power system fault analysis methods are mainly aimed at power systems with relatively simple or relatively simple structures. In contrast, each component in the hydropower, photovoltaic, storage and grid power system has its own unique properties.

[0004] For example, hydroelectric power generation is affected by intermittent changes in water flow, photovoltaic power generation depends on light intensity and temperature, the charging and discharging state of the energy storage system is also constantly changing, and there are complex interactions between different power sources. These factors together make the fault characteristics in the hydro-photovoltaic-storage-grid power system complex and changeable.

[0005] Existing power system fault analysis methods often fail to fully consider the above factors when facing hydropower, photovoltaic, storage and grid-based power systems. Therefore, these methods have problems of insufficient accuracy and low efficiency in fault type judgment, fault location and fault impact assessment.

[0006] For example, when photovoltaic power generation experiences a sudden power surge and causes a fault due to cloud cover, traditional methods may not be able to accurately determine whether the fault is caused by the photovoltaic equipment itself or a system abnormality caused by changes in the external environment. This ambiguity in judgment may delay fault handling and adversely affect the stable operation of the power system.

[0007] Therefore, in order to solve the above problems, it is necessary to design an analysis method and system that is suitable for the failure of the water-solar-storage-grid source system. Summary of the invention

[0008] The technical problem to be solved by the present invention is to solve the deficiencies in the prior art, design an analysis method and system adapted to the fault of the hydro-photovoltaic storage network source system, including a multi-source data acquisition and preprocessing module responsible for collecting data from each key node of the hydro-photovoltaic storage network source power system and preprocessing the collected data, and a fault feature extraction and classification module that designs a feature extraction algorithm to extract fault features and classifies and trains the extracted fault features, and a fault location module that accurately calculates the fault position, a fault impact assessment module that assesses the scope and degree of influence of the fault on each part of the power system, and a real-time monitoring of the operating parameters and structural changes of the fault analysis system, automatically updating the parameters and algorithms of the fault analysis system, and using online learning technology to allow the model to continuously learn and optimize the dynamic update and adaptive module. Through data acquisition, preprocessing, feature extraction, fault classification, fault location and fault impact assessment, it is possible to comprehensively and accurately analyze various types of faults in the complex power system, and by comprehensively considering the characteristics of each component of the system, it is possible to achieve fast and accurate fault type identification, fault location location and fault impact range assessment, provide strong support for timely and effective fault handling, and ensure the stable and reliable operation of the power system.

[0009] The solution adopted by the present invention to solve the technical problem is:

[0010] An analysis system that adapts to the failure of water, light, storage and grid source systems.

[0011] It is characterized in that

[0012] Include:

[0013] The multi-source data acquisition and preprocessing module is responsible for collecting data from various key nodes of the hydropower, photovoltaic, storage and grid power system and preprocessing the collected data.

[0014] The fault feature extraction and classification module is used to design a feature extraction algorithm to extract fault features and perform classification training on the extracted fault features.

[0015] Fault location module, used to accurately calculate the fault location,

[0016] Fault impact assessment module, used to assess the scope and extent of the impact of the fault on various parts of the power system,

[0017] The dynamic update and adaptive module is used to monitor the operating parameters and structural changes of the fault analysis system in real time, automatically update the parameters and algorithms of the fault analysis system, and use online learning technology to allow the model to continuously learn and optimize.

[0018] As a preferred embodiment of the present invention, the features that need to be extracted when the fault feature extraction and classification module extracts fault features include:

[0019] Harmonic characteristics of electrical quantities extracted for hydropower plant generator failures and mutation characteristics of active power and reactive power of generators;

[0020] Correlation characteristics between light intensity and output power and abnormal temperature variation characteristics of photovoltaic panels extracted for photovoltaic power station failures;

[0021] The slope change of the battery charge and discharge curve and the abnormal fluctuation characteristics of the state of charge extracted for energy storage system failure.

[0022] As a preferred implementation of the present invention, the fault impact assessment module uses a power flow calculation algorithm to assess the impact of the fault on the power system.

[0023] A method for analyzing faults in water-solar-storage-grid source systems.

[0024] It is characterized in that

[0025] The following steps are involved:

[0026] S1. Data collection and preprocessing,

[0027] Collect data from hydropower plants, photovoltaic power stations, energy storage systems, and key nodes of the power grid, and perform preprocessing operations such as noise removal, missing value filling, format conversion, and time alignment on the collected raw data;

[0028] S2, Fault feature extraction and classification,

[0029] According to the fault characteristics of different components of the hydropower, photovoltaic, energy storage and grid power system, a feature extraction algorithm corresponding to the fault is designed to extract the fault characteristics of the hydropower plant generator, photovoltaic power station, energy storage system and power grid, and use the machine learning classification algorithm to classify the extracted fault characteristics and determine the fault type of the collected data.

[0030] S3, Fault location and impact assessment,

[0031] Based on the fault type judgment results, combined with the topological structure and electrical parameters of the power system, the positioning algorithm is used to accurately calculate the fault location, and the scope and degree of the impact of the fault on various parts of the power system are evaluated by establishing a power flow calculation model.

[0032] S4, dynamic update and adaptive adjustment,

[0033] Monitor the operating conditions and structural changes of the power system in real time, automatically update the parameters and algorithms of the fault analysis system, and use online learning technology to feed back new fault cases to the fault analysis system for optimization.

[0034] As a preferred embodiment of the present invention, the feature extraction algorithm in step S2 comprises:

[0035] The harmonic analysis algorithm designed for the fault of the hydropower plant generator uses Fourier transform to perform spectrum analysis on the electrical quantity and extract the amplitude and phase characteristics of specific harmonics; at the same time, it monitors the sudden change of active and reactive power, sets the power change threshold, and extracts the rate and amplitude of power change and related characteristics when the power change exceeds the threshold.

[0036] A mathematical model of light intensity and output power is established for the design of photovoltaic power stations. The fault characteristics are extracted by real-time monitoring of the deviation between light intensity and output power. At the same time, the temperature data of photovoltaic panels is analyzed in real time. When the temperature rises abnormally or fluctuates too much, the gradient, duration and related characteristics of the temperature change are extracted.

[0037] Analyze the slope change of the battery charge and discharge curve for energy storage system design. By calculating the change in battery voltage and current at adjacent moments, the slope characteristics of the charge and discharge curve are obtained. Monitor abnormal fluctuations in the state of charge. When the state of charge changes significantly in a short period of time, extract the characteristics of the change amplitude and frequency of the state of charge.

[0038] As a preferred implementation of the present invention, the positioning algorithm in step S3 includes:

[0039] The double-end traveling wave method for transmission line faults installs traveling wave measuring devices at both ends of the transmission line to accurately record the time when the fault traveling wave reaches both ends. The time data from both ends are transmitted to the fault location calculation center through the communication system. According to the line wave speed and time difference formula, the distance from the fault point to both ends is calculated, thereby locating the fault location.

[0040] The impedance method for internal equipment failures in hydropower plants, photovoltaic power stations, and energy storage systems combines the electrical connection diagram of the equipment and the fault characteristics to locate the specific location of the fault point inside the equipment by measuring the changes in the electrical impedance of the faulty equipment.

[0041] As a preferred implementation of the present invention, the noise removal in step S1 is performed by using a Kalman filter algorithm; the missing values ​​are filled by using a linear interpolation method or by combining the statistical rules of historical data.

[0042] As a preferred implementation of the present invention, the machine learning classification algorithm used in step S2 includes support vector machine and random forest.

[0043] A computer readable storage medium,

[0044] A computer program is stored thereon, and when the computer program is executed by a processor, the above-mentioned analysis method adapted to the failure of a water-photovoltaic-storage-grid source system is implemented.

[0045] A computer device,

[0046] include:

[0047] Processor and memory;

[0048] The memory is used to store computer programs;

[0049] The processor is used to execute the computer program stored in the memory so that the computer device executes the above-mentioned analysis method adapted to the failure of the water-photovoltaic-storage-grid source system.

[0050] Beneficial effects:

[0051] 1. High-precision fault analysis: The system of the present invention significantly improves the accuracy of fault type judgment by comprehensively collecting multi-source data and deeply mining the fault characteristics of each part, combined with advanced machine learning classification algorithms, thereby improving the accuracy of fault analysis compared to traditional methods.

[0052] In terms of fault location, the method of the present invention uses a variety of advanced location algorithms to provide a strong guarantee for rapid repair of faults.

[0053] 2. Efficient and rapid response: The entire fault analysis process has been optimized and designed. Compared with traditional methods, the time taken from the occurrence of a fault to the completion of fault type judgment, location and impact assessment is shorter, which improves the timeliness of fault handling and reduces power outage time and economic losses caused by faults.

[0054] 3. Strong adaptability and scalability: The dynamic update and adaptive adjustment module of the system of the present invention enables the method of the present invention to adapt well to the ever-changing characteristics of the hydro-photovoltaic-storage-grid power system, and can maintain good fault analysis capabilities regardless of system structure adjustment or operating condition changes. At the same time, the method of the present invention is easy to expand and can easily integrate new monitoring equipment and analysis algorithms to meet the needs of future power system development.

[0055] 4. Improve system stability: Accurate fault analysis helps to take effective fault handling measures in a timely manner, reduce the impact of faults on the power system, maintain the voltage and frequency stability of the system, and improve the operating reliability and stability of the entire hydro-solar-storage-grid power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a schematic diagram of the structure of the analysis system for adapting to the failure of the water-solar-storage-grid source system proposed by the present invention;

[0057] Figure 2 This is a schematic diagram of the analysis method proposed by the present invention that is adapted to the failure of the water-solar-storage-grid source system. DETAILED DESCRIPTION

[0058] The specific implementation of the present invention is described below in conjunction with the accompanying drawings and embodiments:

[0059] It should be noted that the structures, colors, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification so that people familiar with this technology can understand and read them, and are not used to limit the conditions under which the present invention can be implemented. Any structural modification, change in proportional relationship or adjustment of size should still fall within the scope of the technical content disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0060] In the present invention, unless otherwise clearly stipulated and limited, the terms such as "installation", "setting", "connection", "fixation" and "screw-on" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral one; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal connection of two elements or the interaction relationship between two elements. Unless otherwise clearly defined, ordinary technicians in this field can understand the specific meanings of the above terms in the present invention according to the specific circumstances.

[0061] The drawings in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with this technology, and are not used to limit the conditions under which the present invention can be implemented. Any structural modification, change in proportional relationship or adjustment in size should still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0062] like Figure 1 As shown, the present invention proposes an analysis system that adapts to water-photovoltaic-storage-grid source system failures, including a multi-source data acquisition and preprocessing module, a fault feature extraction and classification module, a fault location module, a fault impact assessment module and a dynamic update and adaptation module.

[0063] Multi-source data acquisition and preprocessing module:

[0064] Responsible for collecting data from key nodes of the hydropower, photovoltaic, storage and grid power system and pre-processing the collected data;

[0065] Fault feature extraction and classification module:

[0066] It is used to design feature extraction algorithms for fault feature extraction based on the fault characteristics of different components of the hydro-photovoltaic-storage-grid power system, and to classify and train the extracted fault features;

[0067] Fault location module:

[0068] It is used to accurately calculate the fault location based on the fault type judgment result, and set different positioning algorithms for different parts;

[0069] Failure Impact Assessment Module:

[0070] Used to assess the scope and extent of the impact of faults on various parts of the power system;

[0071] Dynamic update and adaptive module:

[0072] It is used to monitor the operating parameters and structural changes of the fault analysis system in real time, automatically update the parameters and algorithms of the fault analysis system, and use online learning technology to continuously feed back new fault cases and corresponding analysis results to the classification model, so that the classification model can continue to learn and optimize, and improve the analysis capabilities of various complex faults.

[0073] Selection of data acquisition equipment in the multi-source data acquisition and preprocessing module and its installation location in the water-solar-storage-grid source system:

[0074] 1. In hydropower plants, high-precision turbine sensors are selected and installed in key parts of the turbine such as the water inlet pipe, volute, and main shaft to collect parameters such as flow, water pressure, and speed;

[0075] On the generator side, a power quality monitoring device is configured to collect electrical quantities such as voltage, current, and power.

[0076] 2. In the photovoltaic power station, each row of photovoltaic panels is equipped with temperature sensors and light intensity sensors, and the data is transmitted to the centralized processing unit through the data collector;

[0077] Install power monitoring equipment at the output of the PV inverter.

[0078] 3. For energy storage systems, voltage and current sensors are installed on each battery module of the battery pack to monitor the battery status in real time.

[0079] 4. In the power grid, smart meters, phasor measurement units (PMUs) and other equipment are installed at each substation and key nodes of the transmission lines to collect electrical parameters of the power grid.

[0080] The fault feature extraction and classification module collects a large amount of historical fault data and normal operation data of hydropower plants, photovoltaic power stations, energy storage systems and power grids, and divides them into training sets and test sets according to a certain ratio. During feature classification training, a machine learning classification algorithm is selected. According to the dimension and distribution of the fault features, a suitable kernel function (such as the radial basis kernel function) is selected to train the training set data, and the model parameters of the classification model in the fault feature extraction and classification module are adjusted to achieve the best classification performance.

[0081] In actual operation, the fault features extracted in real time are input into the trained classification model to quickly determine the fault type. At the same time, the classification model is regularly updated and trained with new fault data to improve the adaptability and accuracy of the classification model.

[0082] The dynamic update and adaptive module includes a system monitoring program set up in the operation and management center of the power system, which is used to monitor in real time the changes in the operating parameters of hydropower plants, photovoltaic power stations, energy storage systems and power grids, such as the addition and removal of equipment, and the adjustment of the range of changes in power generation.

[0083] When changes in system structure or operating parameters are detected, the parameter update program in the dynamic update and adaptive module is automatically triggered. The electrical parameters in the fault analysis model, such as the resistance and reactance of the transmission line, the transformation ratio of the transformer, etc., are updated according to the actual equipment changes; the threshold parameters in the fault feature extraction algorithm, such as the power change threshold and the temperature anomaly threshold, are recalculated and adjusted according to the new operating conditions.

[0084] The dynamic update and adaptive module also uses online learning technology to record the results of each fault analysis and the corresponding fault data to form new learning samples. These new samples are regularly input into the machine learning classification model, and the incremental learning algorithm is used to update and train the classification model so that the classification model can learn new fault modes and characteristics. At the same time, the fault location and impact assessment algorithm is optimized, and the algorithm parameters and calculation logic are adjusted according to the problems reported in the actual fault handling process to continuously improve the overall performance of the fault analysis method.

[0085] like Figure 2 As shown, a method for analyzing the failure of a water-solar-storage-grid source system is provided.

[0086] The following steps are involved:

[0087] S1. Data collection and preprocessing,

[0088] Collect relevant data from hydropower plants, photovoltaic power stations, energy storage systems and key nodes of the power grid, and perform preprocessing operations such as noise removal, missing value filling, format conversion and time alignment on the collected raw data;

[0089] The key nodes data collected include:

[0090] 1. The operating parameters of the turbines in the hydropower plant, such as flow, water pressure, and speed;

[0091] 2. Generator electrical quantities, such as voltage, current, and power;

[0092] 3. Photovoltaic panel temperature, light intensity and output power of photovoltaic power station;

[0093] 4. Battery voltage, current and state of charge of the energy storage system;

[0094] 5. Voltage, current, phase and other information at different locations of the power grid.

[0095] In the background data processing server, a data preprocessing program is written, and the Kalman filter algorithm is used to remove noise. According to the dynamic change characteristics of electrical quantities, the state equation and observation equation are established to filter the real-time collected data.

[0096] Temporary data loss due to sensor failure requires missing value filling, which is done using linear interpolation or in combination with the statistical laws of historical data.

[0097] Specifically, according to the time series characteristics of the data, if the data missing time is short, linear interpolation is used to perform interpolation calculations using data from adjacent moments; if the data missing time is long, it is filled in based on the statistical laws of historical data.

[0098] For the format conversion and time alignment of different types of data, a unified data format standard is formulated, such as the relevant standard format of the International Electrotechnical Commission; through timestamp marking and synchronization algorithm, the data collected by different devices are aligned according to a unified time reference.

[0099] S2, Fault feature extraction and classification,

[0100] According to the fault characteristics of different components of the hydropower, photovoltaic, energy storage and grid-based power system, a feature extraction algorithm corresponding to the fault is designed to extract the fault characteristics of the hydropower plant generators, photovoltaic power stations, energy storage systems and power grids. The machine learning classification algorithm is used to classify the extracted fault features and determine the fault type of the collected data.

[0101] The features extracted when extracting fault features include:

[0102] 1. For generator failures in hydropower plants, extract the harmonic characteristics of electrical quantities and the mutation characteristics of active and reactive power;

[0103] 2. For photovoltaic power stations, extract the correlation characteristics between light intensity and output power, and the abnormal temperature change characteristics of photovoltaic panels;

[0104] 3. For energy storage systems, extract characteristics such as the slope change of the battery charging and discharging curve and the abnormal fluctuation characteristics of the state of charge.

[0105] The designed feature extraction algorithm includes:

[0106] 1. The harmonic analysis algorithm designed for the fault of the hydropower plant generator uses Fourier transform to perform spectrum analysis on the electrical quantity and extract the amplitude and phase characteristics of specific harmonics; at the same time, monitor the sudden change of active and reactive power, set the power change threshold, and extract the rate and amplitude of power change and related characteristics when the power change exceeds the threshold.

[0107] 2. A mathematical model of light intensity and output power is established for the design of photovoltaic power stations. The deviation between light intensity and output power is monitored in real time through the mathematical model to extract fault characteristics. At the same time, the temperature data of photovoltaic panels is analyzed in real time. When the temperature rises abnormally or fluctuates too much, the gradient, duration and related characteristics of the temperature change are extracted.

[0108] 3. Analyze the slope change of the battery charge and discharge curve for energy storage system design. By calculating the change in battery voltage and current at adjacent moments, the slope characteristics of the charge and discharge curve are obtained; monitor abnormal fluctuations in the state of charge. When the state of charge changes significantly in a short period of time, extract the characteristics of the change amplitude and frequency of the state of charge.

[0109] After feature extraction is completed, classification algorithms in machine learning, such as support vector machines (SVM) and random forests, are used to classify and train the extracted fault features. A training set is constructed by building a large amount of historical fault data and normal operation data, allowing the classification model to learn the characteristic patterns corresponding to different fault types, thereby achieving rapid and accurate judgment of the fault type of real-time collected data.

[0110] S3, Fault location and impact assessment,

[0111] Based on the fault type judgment results, combined with the topological structure and electrical parameters of the power system, a positioning algorithm is used to accurately calculate the fault location, and the scope and degree of the fault's impact on various parts of the power system are evaluated by establishing a power flow calculation model.

[0112] After determining the fault type, a suitable location algorithm is selected according to the part of the power system where the fault is located. The location algorithms include improved impedance method, traveling wave method and other location algorithms.

[0113] Among them, for transmission line faults, if the double-end traveling wave method is used, traveling wave measurement devices are installed at both ends of the transmission line to accurately record the time when the fault traveling wave reaches both ends. The time data at both ends is transmitted to the fault location calculation center through the communication system, and the distance from the fault point to both ends is calculated based on the line wave speed and time difference formula.

[0114] For internal equipment failures in hydropower plants, photovoltaic power stations, and energy storage systems, an impedance matching-based positioning method is used in combination with the equipment's electrical connection diagram and fault characteristics. The fault point is located at the specific location inside the equipment by measuring the electrical impedance changes of the faulty equipment.

[0115] By establishing a power system flow calculation model, the redistribution of system flow after a fault occurs is simulated, and the impact on the output of each power source, load node voltage, and power transmission of the transmission line is analyzed. At the same time, the regulation role of the energy storage system should be considered to evaluate the contribution of the energy storage system to maintaining system stability in the event of a fault.

[0116] As an important means of regulation, the energy storage system can play a key role in the event of a system failure. Through rapid charging and discharging, the energy storage system can balance the power imbalance caused by the failure and help maintain the stability of the system frequency and voltage. At the same time, the energy storage system can also provide the necessary power support during the fault recovery phase to accelerate the system recovery process.

[0117] The power flow calculation model uses a series of mature power flow calculation algorithms such as the Newton-Raphson method and the fast decomposition method. These algorithms are based on the basic theory of power systems and solve the power flow distribution of the system through mathematical iteration. They can efficiently handle complex calculation problems of large-scale power systems. The topology, electrical parameters, and initial states of each power supply and load of the power system are input during the specific calculation. After a fault occurs, the corresponding parameters in the model are adjusted according to the type and location of the fault, such as setting the impedance of the fault line to infinity to simulate the impact of the fault on the system power flow.

[0118] Through power flow calculation, the output of each power source, the voltage of load nodes and the change of power transmission line after the fault are obtained, and the scope and degree of the impact of the fault on the power system are evaluated. At the same time, the charging and discharging regulation of the energy storage system during the fault is fully considered, and the power injection of the energy storage system in the power flow calculation model is adjusted in real time according to the real-time status and control strategy of the energy storage system, and the contribution of the energy storage system to maintaining system stability is analyzed.

[0119] S4, dynamic update and adaptive adjustment,

[0120] Monitor the operating conditions and structural changes of the power system in real time, automatically update the parameters and algorithms of the fault analysis system, and use online learning technology to feed back new fault cases to the fault analysis system for optimization.

[0121] As the operating conditions of the power system change and new equipment is connected or old equipment is modified, the system characteristics will change. By real-time monitoring of the operating parameters and structural changes of the fault analysis system, the parameters and algorithms of the fault analysis model are automatically updated. The accuracy and effectiveness of the fault analysis system of the integrated hydropower, photovoltaic, storage and grid power system are ensured. This helps to improve the stability and reliability of the power system and provide strong support for the widespread application of clean energy.

[0122] In addition, it is necessary to continuously improve and optimize the algorithms and models, implementation steps and safeguards of the fault analysis system to adapt to the changing operating conditions and equipment characteristics of the power system. For example, when a photovoltaic power station adds a new photovoltaic panel array, the fault feature extraction algorithm and classification model of the photovoltaic part should be adjusted in time to adapt to the new power generation characteristics.

[0123] At the same time, online learning technology is used to continuously feed back newly emerging fault cases and corresponding analysis results to the fault analysis system, allowing the fault analysis system to continue learning and optimizing, thereby improving its ability to analyze various complex faults.

[0124] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the above-mentioned analysis method for adapting to the failure of a water-photovoltaic-storage-grid source system.

[0125] A person skilled in the art can understand that:

[0126] All or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to the computer program. The aforementioned computer program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

[0127] Computer-readable and writable storage media may include read-only memory, random access memory, EEPROM, CD-ROM or other optical disk storage devices, magnetic disk storage devices or other magnetic storage devices, flash memory, USB flash drives, mobile hard disks, or any other media that can be used to store desired program code in the form of instructions or data structures and can be accessed by a computer.

[0128] A computer device comprises: a processor and a memory; the memory is used to store computer programs; the processor is used to execute the computer programs stored in the memory, so that the computer device executes the above-mentioned analysis method adapted to the failure of the water-photovoltaic-storage-network source system.

[0129] Although the preferred embodiments of the present application have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present application.

[0130] Many other changes and modifications may be made without departing from the concept and scope of the present invention.It should be understood that the present invention is not limited to the specific embodiments, and the scope of the present invention is defined by the appended claims.

Claims

1. An analysis system adapted to the failure of water, light, storage and grid source system, It is characterized in that Include: The multi-source data acquisition and preprocessing module is responsible for collecting data from various key nodes of the hydropower, photovoltaic, storage and grid power system and preprocessing the collected data. The fault feature extraction and classification module is used to design a feature extraction algorithm to extract fault features and perform classification training on the extracted fault features. Fault location module, used to accurately calculate the fault location, Fault impact assessment module, used to assess the scope and extent of the impact of the fault on various parts of the power system, The dynamic update and adaptive module is used to monitor the operating parameters and structural changes of the fault analysis system in real time, automatically update the parameters and algorithms of the fault analysis system, and use online learning technology to allow the model to continuously learn and optimize.

2. The analysis system for adapting to the failure of the water-solar-storage-grid source system as claimed in claim 1, It is characterized in that The features that need to be extracted when the fault feature extraction and classification module extracts fault features include: Harmonic characteristics of electrical quantities extracted for hydropower plant generator failures and mutation characteristics of active power and reactive power of generators; Correlation characteristics between light intensity and output power and abnormal temperature variation characteristics of photovoltaic panels extracted for photovoltaic power station failures; The slope change of the battery charge and discharge curve and the abnormal fluctuation characteristics of the state of charge extracted for energy storage system failure.

3. The analysis system for adapting to the failure of the water-solar-storage-grid source system as claimed in claim 2, It is characterized in that The fault impact assessment module uses a power flow calculation algorithm to assess the impact of a fault on the power system.

4. An analysis method for failures in water, solar, storage and grid systems, Using the analysis system adapted to the failure of the water-photovoltaic-storage-grid source system as claimed in claim 3, It is characterized in that The following steps are involved: S1. Data collection and preprocessing, Collect data from hydropower plants, photovoltaic power stations, energy storage systems, and key nodes of the power grid, and perform preprocessing operations such as noise removal, missing value filling, format conversion, and time alignment on the collected raw data; S2, Fault feature extraction and classification, According to the fault characteristics of different components of the hydropower, photovoltaic, energy storage and power grid power system, a feature extraction algorithm corresponding to the fault is designed to extract the fault characteristics of the hydropower plant generator, photovoltaic power station, energy storage system and power grid, and use the machine learning classification algorithm to classify the extracted fault characteristics and determine the fault type of the collected data; S3, Fault location and impact assessment, Based on the fault type judgment results, combined with the topological structure and electrical parameters of the power system, the positioning algorithm is used to accurately calculate the fault location, and the scope and degree of the impact of the fault on various parts of the power system are evaluated by establishing a power flow calculation model; S4, dynamic update and adaptive adjustment, Monitor the operating conditions and structural changes of the power system in real time, automatically update the parameters and algorithms of the fault analysis system, and use online learning technology to feed back new fault cases to the fault analysis system for optimization.

5. The method for analyzing the failure of the water-solar-storage-grid source system according to claim 4, It is characterized in that The feature extraction algorithm in step S2 comprises: The harmonic analysis algorithm designed for the fault of the hydropower plant generator uses Fourier transform to perform spectrum analysis on the electrical quantity and extract the amplitude and phase characteristics of specific harmonics; at the same time, it monitors the sudden change of active and reactive power, sets the power change threshold, and extracts the rate and amplitude of power change and related characteristics when the power change exceeds the threshold. A mathematical model of light intensity and output power is established for photovoltaic power station design, and fault characteristics are extracted by real-time monitoring of the deviation between the two. At the same time, real-time analysis of photovoltaic panel temperature data is performed. When the temperature rises abnormally or fluctuates too much, the gradient, duration and related characteristics of the temperature change are extracted. Analyze the slope change of the battery charge and discharge curve for energy storage system design. By calculating the change in battery voltage and current at adjacent moments, the slope characteristics of the charge and discharge curve are obtained. Monitor abnormal fluctuations in the state of charge. When the state of charge changes significantly in a short period of time, extract features such as the change amplitude and frequency of the state of charge.

6. The method for analyzing the failure of the water-solar-storage-grid source system according to claim 5, It is characterized in that The positioning algorithm in step S3 includes: The double-end traveling wave method for transmission line faults installs traveling wave measuring devices at both ends of the transmission line to accurately record the time when the fault traveling wave reaches both ends. The time data from both ends are transmitted to the fault location calculation center through the communication system. The distance from the fault point to both ends is calculated based on the line wave speed and time difference formula. The impedance method for internal equipment failures in hydropower plants, photovoltaic power stations, and energy storage systems combines the electrical connection diagram of the equipment and the fault characteristics to locate the specific location of the fault point inside the equipment by measuring the changes in the electrical impedance of the faulty equipment.

7. The method for analyzing the failure of the water-solar-storage-grid source system according to claim 6, It is characterized in that In step S1, the noise removal is performed by using the Kalman filter algorithm; the missing values ​​are filled by using the linear interpolation method or combining the statistical rules of historical data.

8. The method for analyzing the failure of the water-solar-storage-grid source system according to claim 7, It is characterized in that The machine learning classification algorithms used in step S2 include support vector machines and random forests.

9. A computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by the processor, the method for analyzing the failure of the water-photovoltaic-storage-grid source system according to claim 8 is implemented.

10. A computer device, It is characterized in that include: Processor and memory; The memory is used to store computer programs; The processor is used to execute the computer program stored in the memory so that the computer device executes the analysis method for adapting to water-photovoltaic-storage-grid source system failures as described in claim 8.

Images