Intelligent integrated operation and maintenance and fault diagnosis system for pumped storage power station

Abstract

The invention provides an intelligent integrated operation and maintenance and fault diagnosis system for a pumped storage power station, and relates to the technical field of energy equipment operation and maintenance, and the system comprises a multi-source data collection and fusion module which is used for collecting and fusing the operation state data of processing equipment; the intelligent fault diagnosis and prediction module is used for carrying out real-time fault diagnosis and prediction on the equipment; the intelligent operation and maintenance decision and management platform is used for carrying out real-time monitoring, operation and maintenance management and decision support on the equipment based on the fault diagnosis and prediction result; and the communication and safety guarantee module is used for guaranteeing communication smoothness and data safety of the system. Multi-source data acquisition and fusion, fault diagnosis and prediction and intelligent operation and maintenance decision and management are innovatively and organically combined, the problems of poor timeliness, data isolation and the like in traditional operation and maintenance are solved, and the diagnosis precision is improved through intelligent operation and maintenance decision closed-loop management and data fusion.

Description

Technical Field

[0001] The present application relates to the technical field of energy equipment operation and maintenance, and particularly to an intelligent integrated operation and maintenance and fault diagnosis system for pumped storage power stations. Background Art

[0002] Currently, there are few patents in the field of intelligent integrated operation and maintenance systems for pumped storage power stations, and existing research mainly focuses on the state prediction, diagnosis, and monitoring of unit equipment in pumped storage power stations.

[0003] In terms of equipment detection, traditional monitoring methods mainly rely on manual inspections and simple sensor monitoring, which have problems such as long manual inspection cycles, low efficiency, and being easily affected by subjective factors, making it difficult to comprehensively and real-time grasp the equipment operation status. In addition, the data of different types of sensors are independent of each other, lacking effective fusion analysis, resulting in inaccurate and incomplete monitoring of the overall health status of the equipment.

[0004] In terms of fault diagnosis, an artificial intelligence-based method is intended to be used to train multi-source data collected by various sensors. Due to the complexity and variability of actual operation data, as well as the limitations of model training data, the model has poor adaptability when facing different working conditions and faults.

[0005] The existing operation and maintenance systems for pumped storage power stations lack intelligent decision-making support, and the system functions are relatively single, unable to meet the requirements of intelligent integrated operation and maintenance for pumped storage, and at the same time, each module is relatively independent. There is a lack of an intelligent integrated operation and maintenance system for pumped storage power stations, and the overall operation and maintenance efficiency of the power station needs to be further improved. Summary of the Invention

[0006] The present application aims to solve at least one of the technical problems in the related technologies to some extent.

[0007] To this end, the first object of the present application is to propose an intelligent integrated operation and maintenance and fault diagnosis system for pumped storage power stations, aiming to solve the deficiencies such as strong subjectivity, poor pertinence, low fault diagnosis accuracy, and poor timeliness in traditional operation and maintenance that rely on manual inspections and regular maintenance.

[0008] The second object of the present application is to propose an intelligent integrated operation and maintenance and fault diagnosis method for pumped storage power stations.

[0009] The third object of the present application is to propose an electronic device.

[0010] The fourth object of the present application is to propose a computer-readable storage medium.

[0011] The fifth object of the present application is to propose a computer program product.

[0012] To achieve the above object, an intelligent integrated operation and maintenance and fault diagnosis system for a pumped-storage power station is proposed in the first aspect embodiment of the present application, including:

[0013] A multi-source data acquisition and fusion module, which is used to collect and fuse the operation status data of equipment, and provide data support for subsequent modules;

[0014] An intelligent fault diagnosis and prediction module, which is used to perform real-time fault diagnosis and prediction on equipment according to the data collected and fused by the multi-source data acquisition and fusion module;

[0015] An intelligent operation and maintenance decision-making and management platform, which is used to perform real-time monitoring, operation and maintenance management and decision-making support on equipment based on the results of fault diagnosis and prediction;

[0016] A communication and security guarantee module, which is used to ensure the smooth communication and data security of the system, and provide basic support for other modules.

[0017] Optionally, the multi-source data acquisition and fusion module includes:

[0018] Multi-type high-precision sensors, which are used to collect the operation status data of equipment, and the operation status data includes vibration, temperature, pressure, flow, gas, acoustics, current, voltage;

[0019] A distributed data acquisition unit, which is used to preprocess the operation status data collected by the multi-type high-precision sensors, and transmit the preprocessed multi-source data to a data fusion processor. The preprocessing steps include data format conversion and preliminary screening of outliers;

[0020] A data fusion processor, which is used to fuse the preprocessed multi-source data by using the Kalman filter and D-S evidence theory algorithms, and judge the operation status of equipment.

[0021] Optionally, the intelligent fault diagnosis and prediction module includes:

[0022] A historical data storage unit, which is used to build a sample library and collect long-term operation data of the power station. The data includes equipment normal operation data, fault data and maintenance records;

[0023] A model training center, which is used to train fault diagnosis and prediction models by using machine learning and deep learning algorithms, and optimize model parameters through cross-validation;

[0024] A real-time diagnosis and prediction unit, which is used to perform fault diagnosis and prediction by using the trained model according to the real-time collected data, and output fault diagnosis results and prediction information. The fault diagnosis results include fault type identification, fault location positioning, and fault degree evaluation. The fault prediction information includes the remaining service life of equipment, fault development trend and maintenance suggestions.

[0025] Optionally, the intelligent operation and maintenance decision-making and management platform includes:

[0026] An equipment real-time monitoring module, which is used to visually display the equipment status, uses two-dimensional / three-dimensional visualization technology to display the equipment layout, structure and operation status, supports remote operation and control, and real-time displays the fault diagnosis results and prediction information;

[0027] An operation and maintenance plan management module, which is used to automatically generate an operation and maintenance plan according to the fault diagnosis results and prediction information, equipment maintenance cycle, and power station operation plan. The operation and maintenance plan includes the type, content, time window, required resources and personnel arrangement of maintenance tasks, and can dynamically track and evaluate the execution of the operation and maintenance plan;

[0028] A material management module, which is used to manage the spare parts and materials required for equipment, provide warehousing, outbound and inventory counting of spare parts, and conduct inventory early warning according to the equipment failure rate and maintenance frequency, and optimize the inventory level and replenishment strategy using intelligent algorithms;

[0029] A personnel management module, which is used to manage the basic information, skill qualifications, work arrangements and performance evaluation of operation and maintenance personnel, conduct intelligent scheduling based on task requirements and personnel skills, and optimize the work distribution of operation and maintenance personnel;

[0030] A knowledge base management module, which is used to manage equipment technical data, constructs an equipment technical database using knowledge graph technology, realizes the structured storage of fault cases and maintenance experience, and provides multi-dimensional knowledge retrieval functions, with the ability of automatic update and learning;

[0031] A report generation and analysis module, which is used to automatically generate equipment operation and fault statistics operation and maintenance reports, deeply mine and analyze the report data, and provide data support for management decision-making. The operation and maintenance reports support multiple formats and are customizable.

[0032] Optionally, the communication and security guarantee module includes:

[0033] A communication network unit, which is used to build a redundant network using industrial communication equipment, including a fiber optic Ethernet backbone network and wireless network coverage. The network uses a ring topology structure to improve network reliability, sets redundant links and uses traffic control technology to reasonably allocate network bandwidth to ensure high-speed and stable data transmission;

[0034] A security protection unit, which is used to deploy a firewall, intrusion detection system, intrusion prevention system, and anti-virus software. The security protection unit can encrypt and store and transmit sensitive data, establish a data backup and recovery mechanism to prevent data leakage and malicious attacks;

[0035] The user privilege management unit is used to implement multi-factor identity authentication, assign different privilege levels according to user roles and responsibilities, and record the operation logs of users in detail, facilitating the tracing of security incidents and the determination of responsibilities.

[0036] To achieve the above object, an intelligent integrated operation and maintenance and fault diagnosis method for a pumped storage power station is proposed in the second aspect of the present application, including:

[0037] Collect the operation parameters of the equipment through multi-type high-precision sensors, and preprocess the collected parameter data through a distributed data acquisition unit;

[0038] Input the preprocessed data into a data fusion processor, use the Kalman filter and D-S evidence theory algorithms to fuse multi-source data, and judge the operation state of the equipment;

[0039] Through the intelligent fault diagnosis and prediction module, combine machine learning and deep learning algorithms to match the fault characteristics of the fused data, and output the fault diagnosis and prediction results;

[0040] According to the fault diagnosis and prediction results, generate an operation and maintenance plan based on the intelligent operation and maintenance decision-making and management platform, and dynamically evaluate the plan execution situation to ensure the timely repair of the equipment and the normal operation of the power station.

[0041] To achieve the above object, an electronic device is proposed in the third aspect of the present application, including: a processor, and a memory communicatively connected to the processor;

[0042] The memory stores computer execution instructions;

[0043] The processor executes the computer execution instructions stored in the memory to implement the method described in any one of the second aspect.

[0044] To achieve the above object, a computer-readable storage medium is proposed in the fourth aspect of the present application. The computer-readable storage medium stores computer execution instructions, and when the computer execution instructions are executed by a processor, they are used to implement the method described in any one of the second aspect.

[0045] To achieve the above object, a computer program product is proposed in the fifth aspect of the present application. When the computer program is executed by a processor, it implements the method described in any one of the second aspect.

[0046] The technical solutions provided by the embodiments of the present application at least bring the following beneficial effects:

[0047] Compared with the prior art, the present application innovatively combines multi-source data acquisition and fusion, fault diagnosis and prediction, and intelligent operation and maintenance decision-making and management, constructs an intelligent integrated operation and maintenance and fault diagnosis system for pumped storage power stations, and fills the technical gap in the field of intelligent operation and maintenance of pumped storage power stations. The present application realizes the all-round perception of the equipment operation status through multi-source data fusion, improves the accuracy of fault diagnosis and prediction ability, helps to discover potential equipment faults in advance, optimize maintenance strategies, and extend the service life of equipment. The intelligent operation and maintenance decision-making and management platform integrates functions such as equipment monitoring, operation and maintenance plan, material management, personnel scheduling, and knowledge base management, solves the problems of scattered functions and low management efficiency of traditional operation and maintenance systems, and provides a useful technical reference for the digital and intelligent operation and maintenance of pumped storage power stations.

[0048] Moreover, the present application can be widely applied to the intelligent operation and maintenance management of pumped storage power stations. Through automated and intelligent diagnosis and decision-making, it improves operation and maintenance efficiency, reduces labor costs, and enhances the economic benefits of the power station. At the same time, the system can improve the safety and stability of the operation of power station equipment, provide a strong guarantee for the reliable operation of the power grid, and has wide popularization and application value.

[0049] The additional aspects and advantages of the present application will be partly given in the following description, partly become obvious from the following description, or be understood through the practice of the present application. Brief Description of the Drawings

[0050] The above-mentioned and / or additional aspects and advantages of the present application will become obvious and easy to understand from the following description of the embodiments in conjunction with the drawings, where:

[0051] Figure 1 It is a schematic structural diagram of an intelligent integrated operation and maintenance and fault diagnosis system for a pumped storage power station provided by an embodiment of the present application.

[0052] Figure 2 A schematic structural diagram of the multi-source data acquisition and fusion module provided by an embodiment of the present application;

[0053] Figure 3 It is a schematic structural diagram of the intelligent fault diagnosis and prediction module provided by an embodiment of the present application;

[0054] Figure 4 It is a schematic structural diagram of the intelligent fault diagnosis and prediction module provided by an embodiment of the present application;

[0055] Figure 5 It is a schematic structural diagram of the communication and security guarantee module provided by an embodiment of the present application. Detailed Description of the Embodiments

[0056] Embodiments of the present application will be described in detail below. Examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to explain the present application, but should not be construed as limiting the present application.

[0057] In view of the problems existing in the prior art, an intelligent integrated operation and maintenance and fault diagnosis system for a pumped-storage power station is provided in an embodiment of the present application. Figure 1 FIG. is a schematic structural diagram of an intelligent integrated operation and maintenance and fault diagnosis system for a pumped-storage power station provided in an embodiment of the present application.

[0058] As Figure 1 shown, the equipment of the pumped-storage power station includes key equipment such as a pump-turbine, a motor-generator, a transformer, a governor, and a ball valve. Various data will be generated during the operation of these equipment, such as vibration data, temperature data, pressure data, flow data, electrical parameter data, etc. These data are the basis for subsequent modules to analyze and process. The system includes a multi-source data acquisition and fusion module 1, an intelligent fault diagnosis and prediction module 2, an intelligent operation and maintenance decision-making and management platform 3, and a communication and security guarantee module 4.

[0059] Among them, the multi-source data acquisition and fusion module 1 is used to collect and fuse the operation status data of the equipment to provide data support for subsequent modules; the intelligent fault diagnosis and prediction module 2 is used to perform real-time fault diagnosis and prediction on the equipment; the intelligent operation and maintenance decision-making and management platform 3 is used to perform real-time monitoring, operation and maintenance management, and decision support on the equipment based on the fault diagnosis and prediction results; the communication and security guarantee module 4, as a basic support, provides network communication and security guarantee services for the other three functional modules through communication networks, security protection, and permission management. Information interaction is realized between the modules through a standardized data interface to ensure the overall coordinated operation of the system. Operation and maintenance personnel can remotely view the equipment status through the intelligent operation and maintenance decision-making and management platform and remotely operate the equipment within the authorized scope, such as remotely starting and stopping the equipment or adjusting the equipment parameters.

[0060] Figure 2 FIG. is a schematic structural diagram of the multi-source data acquisition and fusion module provided in an embodiment of the present application.

[0061] As Figure 2As shown in the figure, the multi-source data acquisition and fusion module 1 includes multi-type high-precision sensors 11, a distributed data acquisition unit 12, and a data fusion processor 13. Among them, the multi-type high-precision sensors 11 are responsible for collecting device operation status data from various high-precision sensors. The distributed data acquisition unit 12 performs preliminary processing on these data and transmits the data to the data fusion processor 13 for further fusion processing, ultimately providing accurate data support for the subsequent fault diagnosis and prediction module.

[0062] In an embodiment of the present application, the multi-type high-precision sensors 11 collect data for key devices such as pump-turbines, generator-motors, transformers, governors, and ball valves. The operation status data of these devices includes multi-dimensional data such as vibration, temperature, pressure, flow rate, electrical parameters, acoustic signals, and gas components. To ensure the accuracy of data acquisition, the present application selects various types of high-precision sensors, specifically including:

[0063] High-precision vibration sensors (accuracy up to ±0.01 mm / s) are used to collect device vibration data, especially at the root of the runner blades and bearing seats of pump-turbines, which are prone to failure.

[0064] High-sensitivity temperature sensors (accuracy up to ±0.1 °C) are used to monitor the temperature changes of key components of the device, such as the windings of generator-motors and the oil temperature of transformers.

[0065] High-resolution pressure sensors (accuracy up to ±0.001 MPa) are used to monitor the pressure in hydraulic systems and cooling systems.

[0066] Flow sensors are used to monitor the flow rate changes of liquids such as water flow and oil flow.

[0067] Displacement sensors are used to monitor the displacement changes of the device, such as the displacement of the shaft or the vibration displacement of components.

[0068] Acoustic sensors are used to capture abnormal sound signals during device operation, such as discharge sounds and friction sounds.

[0069] Current transformers and voltage transformers are used to collect current and voltage signals of electrical equipment.

[0070] Gas sensors are mainly used to detect the concentration of dissolved gases inside transformers, such as hydrogen and acetylene, to judge potential electrical faults.

[0071] These sensors will be reasonably arranged according to the structural characteristics of the device and the parts prone to failure. The present application does not make specific limitations on this. For example, vibration and temperature sensors are installed at the root of the runner blades and bearing seats of pump-turbines, and current transformers and voltage transformers are installed at the incoming and outgoing line ends of electrical equipment to accurately monitor the operation status of the device.

[0072] To improve the real-time performance and reliability of data acquisition, this application adopts a distributed data acquisition unit 12, and each acquisition unit is equipped with an independent microprocessor and data buffer. Each acquisition unit will perform preliminary processing on the data collected by the sensor, including data format conversion, preliminary screening of outliers, etc., and then transmit the data to the data acquisition server through industrial Ethernet or a high-speed wireless network (such as a 5G network). The data acquisition server verifies, organizes, and caches the received data to ensure the integrity and accuracy of the data and provides high-quality input data for data fusion processing.

[0073] The data fusion processor 13 then uses a fusion algorithm based on Kalman filtering and D-S evidence theory for data processing.

[0074] Kalman filtering is used to perform real-time estimation and noise elimination on dynamic data (such as vibration frequency, electrical parameter fluctuations, etc.), thereby improving the stability and accuracy of the data. Its specific steps include:

[0075] First, by analyzing the physical characteristics of the device, a dynamic system model is established. It is assumed that the operating state of the device can be described by a linear system model. In this model, the state variables of the device (such as temperature, vibration amplitude, current, etc.) are functions of time variation. Then, Kalman filtering estimates the device state at each moment through time series processing. At each moment, the filter estimates the device state according to the prediction model of the system and uses the current observation data to correct the prediction result to obtain the optimal estimate. Finally, Kalman filtering suppresses noise by dynamically adjusting the covariance matrix of the estimation error. For example, in a vibration signal, the filter can remove noise caused by external interference (such as mechanical vibration, environmental noise, etc.), ensure the smoothness and stability of the vibration data, and thus improve the accuracy of the data.

[0076] The D-S evidence theory is used to fuse data from multiple sensors. Through the belief assignment rule, the evidence information of different sensors is synthesized to judge the operating state of the device. The specific steps include: (1) Preliminary processing of sensor data: The data of each sensor is first smoothed by Kalman filtering. After removing noise, respective evidence is generated. For example, vibration sensors, temperature sensors, and pressure sensors respectively generate evidence information about the health state of the device. (2) Synthesis of evidence: The basic probability assignment (BPA) function in the D-S evidence theory is used to represent the evidence of each sensor's data. Specifically, the BPA function converts the measurement results of each sensor into the assignment of belief degrees. For example, if both temperature and pressure data show anomalies, they may both provide evidence for device failure. According to the D-S theory, these evidences will be synthesized to form a comprehensive judgment representing the health state of the device. (3) Belief degree assignment: In multi-sensor data fusion, the D-S evidence theory assigns weights according to the credibility (or belief degree) of each sensor's data. For example, if the data of the vibration sensor and the temperature sensor are consistent, the belief degree of their evidence is relatively high; conversely, if the two data are inconsistent, the system will reduce the belief degree and require more evidence for verification. (4) Decision rule: According to the fused evidence information, the maximum belief degree rule or the weighted average method is used to make a final judgment on the operating state of the device. The final output is a multi-dimensional judgment result, such as judging whether the pump-turbine is operating normally and whether there are potential fault hazards, etc.

[0077] Taking the pump-turbine as an example, assume that the system simultaneously receives data from vibration sensors, temperature sensors, and pressure sensors: First, Kalman filtering smooths the vibration data to remove interference signals and ensure the stability of the vibration data; then, the D-S evidence theory fuses the evidence of vibration data, temperature data, and pressure data, and judges the device state according to the preset belief degree rule; if both the vibration data and the temperature data indicate anomalies in the device, while the pressure data is relatively normal, the system will assign a higher belief degree to the vibration and temperature data and determine that the device may have a fault; if the data of all three sensors show anomalies, the credibility of the fault diagnosis will be further strengthened, predicting the risk of possible device failure or performance decline.

[0078] Through the above multi-level data acquisition and fusion processing, the multi-source data acquisition and fusion module 1 provides accurate and reliable data support for the subsequent fault diagnosis and prediction module, thereby improving the intelligent level of the system and the reliability of the device.

[0079] Figure 3 It is a schematic structural diagram of the intelligent fault diagnosis and prediction module provided by the embodiment of this application.

[0080] As Figure 3 shown, the intelligent fault diagnosis and prediction module 2 includes a historical data storage unit 21, a model training center 22, and a real-time diagnosis and prediction unit 23. The main function of this module is to train a fault diagnosis and prediction model using historical data, and input the real-time collected device operation data into the trained model to achieve accurate diagnosis and prediction of device faults, thereby improving the operation safety and reliability of power station equipment.

[0081] In an embodiment of the present application, the working process of the intelligent fault diagnosis and prediction module 2 includes the following steps:

[0082] Data preprocessing (S1): The historical data storage unit 21 is responsible for collecting the long-term operation data of the power station, including device normal operation, fault data, and maintenance records, etc. These historical data are the basis for fault diagnosis and prediction. The main task of data preprocessing is to clean and organize the original data to ensure data quality. The preprocessing steps include: removing error or missing data: screening the collected data to eliminate abnormal data or missing values; noise removal: using algorithms such as wavelet filtering to remove noise in the signal to ensure data stability; feature extraction: extracting key information from the original data, such as vibration spectrum, temperature trend, and electrical parameter fluctuations, etc.; data normalization: performing normalization processing on the data to ensure the unity of the data value range, for example, standardizing the data to the [-1, 1] interval for subsequent model processing.

[0083] Feature extraction (S2): After the data preprocessing is completed, the feature extraction step is used to further mine the representative features of the device from the preprocessed data. These features are the core information for fault diagnosis and prediction. Different device types and fault modes require different features to be extracted. For example: for the vibration data of a pump-turbine, extracting time-domain features such as peak factor and kurtosis, etc., these features help to judge whether the operation state of the device is normal; for temperature data, extracting features such as fluctuation amplitude and period, etc., this information can reflect whether the device is within the normal temperature range; for electrical data, extracting features such as phase difference and harmonic content, etc., these features help to identify potential faults of electrical equipment.

[0084] Model Training (S3): In the model training center 22, machine learning and deep learning algorithms are used to train the extracted features. The specific steps are as follows: For the mechanical faults of the pump-turbine, convolutional neural network (CNN) is used to process the vibration spectrum image data. The spatial features of the vibration signal are extracted by CNN, and the model is trained to identify different types of vibration anomalies, so as to judge the operating state of the equipment. For example, the convolutional layer is used to extract the local features in the vibration spectrum image, and then the pooling layer is used to reduce the dimension. Finally, the fully connected layer is used for fault classification. For the electrical faults of the generator-motor, recurrent neural network (RNN), especially long short-term memory network (LSTM), is used to analyze the time series data of current and voltage. LSTM can capture the long-term dependencies in the equipment operation, identify the dynamic changes in the electrical parameters, and accurately predict potential electrical faults. The LSTM network effectively solves the problem of gradient disappearance that traditional RNN may face when dealing with long time series through the gating mechanism, thus improving the accuracy of fault prediction.

[0085] During the training process, the embodiments of the present application adopt the following technical means to improve the performance of the model:

[0086] Cross-validation: K-fold cross-validation is used to divide the dataset. The specific method is to divide the dataset into K subsets. Each time, one subset is used as the validation set, and the other K - 1 subsets are used as the training set. K times of training and validation are carried out, and finally the average performance of the model is calculated. This method can effectively avoid overfitting of the model on a certain specific dataset and improve the generalization ability of the model. Usually, the value of K is selected as 5 or 10, and the specific value of K can be adjusted according to the size of the dataset and the complexity of the model.

[0087] Hyperparameter optimization: In order to further improve the prediction accuracy of the model, advanced hyperparameter optimization tools such as Bayesian optimization are adopted. Bayesian optimization constructs a surrogate model (such as Gaussian process regression), predicts the optimal hyperparameter region according to the evaluation results of the current hyperparameters, and reduces the computational cost of traditional grid search and random search methods. In addition, random search can be combined to randomly select hyperparameters in a large range for search, so as to avoid local optimal solutions and comprehensively improve the performance of the model. The present application does not make specific limitations on this.

[0088] Through the above methods, the model can better fit the data, improve the accuracy of fault diagnosis and prediction, and ensure the intelligent operation and maintenance level of power station equipment.

[0089] Fault diagnosis (S4): In the real-time diagnosis and prediction unit 23, the trained model receives the device data collected in real time and conducts fault diagnosis. The fault diagnosis results include fault type identification, fault location positioning, and fault severity assessment. For example, when the current of a generator motor fluctuates abnormally and the temperature rises, the model can diagnose the type of electrical fault, such as judging it as a winding short circuit. At the same time, the model can also locate the fault position and evaluate the severity of the fault, providing timely fault information for the operation and maintenance personnel.

[0090] Prediction results (S5): Finally, the real-time diagnosis and prediction unit 23 can also predict the probability of device fault occurrence and the remaining service life based on the trained model. For example, for a generator motor, the model can predict the fault development trend and the remaining operating time within the next 24 hours, providing a decision-making basis for the operation and maintenance personnel to help them formulate maintenance plans and spare parts management strategies.

[0091] Through the above steps, the intelligent fault diagnosis and prediction module 2 can achieve early warning and accurate diagnosis of device faults, improve the safety and reliability of power station equipment, and reduce unnecessary downtime and maintenance costs.

[0092] Figure 4 It is a schematic structural diagram of the intelligent fault diagnosis and prediction module provided by the embodiment of the present application.

[0093] As Figure 4 shown, the intelligent operation and maintenance decision-making and management platform 3 includes multiple functional modules, namely, the device real-time monitoring module 31, the operation and maintenance plan management module 32, the material management module 33, the personnel management module 34, the knowledge base management module 35, and the report generation and analysis module 36. These modules work together to provide comprehensive intelligent operation and maintenance management, fault diagnosis support, material management, personnel scheduling, knowledge sharing, and decision-making analysis, providing a comprehensive intelligent solution for the equipment management of the power station. Among them:

[0094] The device real-time monitoring module 31 is responsible for real-time monitoring of the status of power station equipment and visually displaying the layout, structure, and operating status of the equipment. This module uses two-dimensional / three-dimensional visualization technology (such as using WebGL technology to implement three-dimensional model display) to intuitively display the operating conditions of power station equipment. Specifically: using dynamic charts (such as real-time updated line charts and bar charts) to display the change trends of key parameters of the equipment (such as temperature, vibration frequency, electrical parameters, etc.), and through color identification (for example, green indicates normal operation, and red flashing indicates a fault warning), to achieve an intuitive display of the equipment operating status.

[0095] Moreover, the operation and maintenance personnel can perform remote start / stop operations on the equipment through this module, and adjust the equipment operation parameters (such as remotely adjusting the opening of the governor or the speed of the pump-turbine) to ensure that the equipment is always in the best working condition.

[0096] The operation and maintenance plan management module 32 automatically generates operation and maintenance plans based on the fault diagnosis results, prediction information, equipment maintenance cycles, and power station operation plans. When equipment failure risks are predicted or the maintenance cycle is reached, this module can determine the types of maintenance tasks (preventive maintenance, emergency repair, etc.), contents (such as replacing parts, system debugging, etc.), time windows (selecting off-peak periods in combination with the power station load situation), required resources (manpower, spare parts, tools, etc.), and personnel arrangements, and can dynamically track and evaluate the implementation of the operation and maintenance plans to ensure that all maintenance tasks are carried out according to the plan and timely adjust the plan to cope with emergencies.

[0097] The material management module 33 is responsible for the full-life cycle management of spare parts and materials required for the equipment. Its main functions include: providing functions for the warehousing, outbound, and inventory counting of spare parts, and real-time displaying material information for the convenience of operation and maintenance personnel to query; setting inventory thresholds according to equipment failure rates, maintenance frequencies, and procurement cycles, and automatically warning when the inventory is lower than the safety inventory or higher than the maximum inventory to avoid inventory shortages or surpluses; docking with the supplier system to automatically create, approve, track, and execute purchase orders to ensure the timely supply of spare parts and materials; optimizing the inventory structure through data analysis (such as time series analysis to predict spare part requirements), regularly conducting inventory counts, and clearing unnecessary inventory to reduce costs and improve turnover.

[0098] The personnel management module 34 is responsible for managing the basic information, skill qualifications, work arrangements, and performance evaluations of operation and maintenance personnel. Specific functions include: generating shift schedules using intelligent algorithms (such as genetic algorithms or simulated annealing algorithms) according to operation and maintenance task requirements and personnel skill status to ensure the reasonable allocation and efficient utilization of operation and maintenance personnel; managing personnel work arrangements and conducting performance evaluations based on task completion situations to further optimize personnel configuration and work distribution.

[0099] The knowledge base management module 35 constructs an equipment technical database using knowledge graph technology and manages the operating procedures, fault cases, and maintenance experiences of the equipment. Specific functions include: realizing the structured storage of equipment technical data, fault cases, and maintenance experiences for the convenience of operation and maintenance personnel to quickly consult; providing multi-dimensional knowledge retrieval functions to help operation and maintenance personnel quickly find relevant fault solutions and maintenance experiences.

[0100] In addition, the knowledge base management module 35 also has the ability of automatic update and learning, and can continuously improve the equipment maintenance knowledge base to ensure that operation and maintenance personnel can obtain the latest technical data and experiences at any time.

[0101] The report generation and analysis module 36 is used to automatically generate reports such as equipment operation reports and fault statistics reports, and deeply mine and analyze the report data to provide data support for management decisions. The specific functions include: automatically generating various operation and maintenance reports according to user requirements, such as daily equipment operation reports and monthly fault statistics reports. The reports support multiple formats (such as PDF, Excel, etc.) and are customizable; using data mining algorithms (such as association rule mining, clustering analysis, etc.) to deeply analyze the report data to discover equipment operation rules and potential problems. For example, by analyzing fault data, identify equipment or components with high failure rates.

[0102] Therefore, the report generation and analysis module 36 can provide a decision-making basis for the management level, assist in formulating equipment transformation, maintenance strategies and resource allocation plans, and improve the economy and reliability of equipment operation.

[0103] Through the comprehensive application of these functional modules, the intelligent operation and maintenance decision-making and management platform 3 can achieve comprehensive monitoring of equipment operation, intelligent maintenance decision-making, and efficient management of materials and personnel, thus providing comprehensive support for the stable operation of the power station.

[0104] Figure 5 It is a schematic structural diagram of the communication and security guarantee module provided by the embodiment of the present application.

[0105] As Figure 5 shown, the communication and security guarantee module 4 includes a communication network unit 41, a security protection unit 42, and a user permission management unit 43. The main function of this module is to ensure the safe, stable and efficient data transmission between various modules of the system and between the system and power station equipment, prevent data leakage and malicious attacks, and ensure the normal operation of the system. Among them:

[0106] The core task of the communication network unit 41 is to build a redundant, efficient, and reliable communication network to ensure that data can be stably and quickly transmitted to each module of the system, especially the equipment in the power station. It ensures the stability and reliability of communication through the following aspects: The fiber optic Ethernet backbone network, as the main communication network, provides a high-speed and stable network connection to ensure the instant transmission of critical data, especially for smooth operation in the case of large data volumes and high concurrency; for areas where wiring is inconvenient, wireless network (such as Wi-Fi, 4G / 5G, etc.) technologies are used for supplementary coverage to ensure seamless data transmission in every corner of the system, whether it is in-office monitoring or remote management of remote devices; the ring topology structure is adopted. While ensuring efficient network connection, this structure can also improve the reliability of the network. If the main link fails, the system can automatically switch to the backup link to avoid network disconnection affecting data flow; combined with traffic control technologies (such as the token bucket algorithm) to reasonably allocate network bandwidth to ensure the priority transmission of critical data (such as fault alarms, device operation status information, etc.), thus ensuring the timely delivery of high-priority data.

[0107] To cope with various possible security threats, the security protection unit 42 deploys multiple protection measures to ensure data security, network protection capabilities, and system stability. Its main protection measures include:

[0108] Firewall: By deploying a stateful inspection firewall, according to the preset security policies, it filters the traffic entering and leaving the network to prevent unauthorized access and potential malicious attacks. The firewall can monitor the legality of traffic in real time and effectively intercept illegal access requests;

[0109] Intrusion Detection System (IDS): This system discovers abnormal behaviors, such as port scanning, a large number of abnormal connection requests, etc., by monitoring network traffic in real time, and immediately issues an alarm to provide timely information for security personnel;

[0110] Intrusion Prevention System (IPS): Based on the IDS, the intrusion prevention system can actively take defensive measures to intercept and prevent detected attacks to prevent the attack source from entering the internal network;

[0111] Antivirus software: Regularly update the virus database to provide real-time protection against potential viruses and malware to ensure that the system is not infected by viruses. The antivirus software can also perform a full-system scan regularly to eliminate potential security risks;

[0112] Data Encryption: All sensitive data is encrypted using the AES-256 encryption algorithm during storage and transmission to ensure data confidentiality. AES-256 is currently recognized as a strong encryption standard with a key length of 256 bits, providing higher security. Even if the data is intercepted during transmission, it cannot be illegally accessed or tampered with. All encryption operations use symmetric encryption technology, and key management is strictly controlled to ensure that only authorized personnel can decrypt sensitive information.

[0113] Data Backup and Recovery Mechanism: The system regularly performs data backups and stores the backup data in a multi-copy manner in different locations to ensure data integrity and security. In case of system failures or data loss, normal operation can be quickly restored through the backup data. Multi-copy storage in different locations not only enhances data security but also ensures that even in the event of catastrophic events (such as fires, natural disasters, etc.), the data can still be effectively protected and quickly restored, avoiding the loss of critical data and ensuring business continuity.

[0114] To ensure secure access and management of the system, the user permission management unit 43 adopts a strict identity authentication and permission control mechanism to ensure that only authorized personnel can access sensitive data and system functions.

[0115] Specific functions include:

[0116] Multi-Factor Identity Authentication: An identity authentication mechanism that uses multiple methods such as password + fingerprint recognition, password + dynamic verification code, etc. This makes it impossible to easily crack the system's access control even if the password is stolen.

[0117] Permission Assignment: Different permission levels are assigned according to the user's role (such as administrator, operation and maintenance personnel, data analysis personnel, etc.) and responsibilities. Each permission level corresponds to different operation menus and function modules. For example, the administrator has full system permissions and can perform configuration and management operations; operation and maintenance personnel can operate and monitor devices, while data analysis personnel can only view and analyze data.

[0118] Operation Log Recording: To ensure the traceability of security events, all user operations are detailedly recorded, including login time, operation content, operation results, etc. All operation logs will be regularly backed up and archived so that in case of security events, they can be quickly traced and the responsibility can be accurately determined.

[0119] Through the coordinated work of the above three major units, the communication and security guarantee module 4 effectively ensures the security, reliability, and efficiency of the system, can guarantee the stability and security of data transmission under any circumstances, and at the same time ensures that the user's access rights to the system are strictly controlled. This module plays an important role in preventing malicious attacks, data leakage, and other network security risks and is the basic support for ensuring the stable operation of the entire system.

[0120] As can be seen from the above embodiments, the intelligent integrated operation and maintenance and fault diagnosis system of the pumped storage power station of the present application can effectively achieve all-round monitoring, accurate diagnosis and intelligent operation and maintenance of power station equipment in practical applications, improve the safety, reliability and economy of power station operation, and has broad application prospects and popularization value.

[0121] It should be noted that the above embodiments are only partial implementation manners of the present application. Within the scope of knowledge possessed by those of ordinary skill in the art, various changes can be made without departing from the purpose of the present application. For example, according to the equipment configuration and operation requirements of different power stations, optimize and adjust the selection and layout of sensors; try new algorithms or algorithm combinations in the fault diagnosis and prediction model to further improve the diagnosis accuracy and prediction accuracy; expand and customize the function modules of the intelligent operation and maintenance decision-making and management platform to meet the specific management requirements of the power station, etc.

[0122] To implement the above embodiments, the present application also proposes an intelligent integrated operation and maintenance and fault diagnosis method for a pumped storage power station. The method includes:

[0123] Collect the operation parameters of the equipment through multi-type high-precision sensors, and preprocess the collected parameter data through a distributed data acquisition unit;

[0124] Input the preprocessed data into a data fusion processor, use the Kalman filter and D-S evidence theory algorithms to fuse multi-source data, and judge the operation state of the equipment;

[0125] Through the intelligent fault diagnosis and prediction module, combine machine learning and deep learning algorithms to match the fault characteristics of the fused data, and output the fault diagnosis and prediction results;

[0126] According to the fault diagnosis and prediction results, generate an operation and maintenance plan based on the intelligent operation and maintenance decision-making and management platform, and dynamically evaluate the plan execution situation to ensure the timely repair of the equipment and the normal operation of the power station.

[0127] Regarding the method in the above embodiments, the specific ways of performing operations in each step have been described in detail in the embodiments related to the device, and will not be elaborated here.

[0128] To implement the above embodiments, the present application also proposes an electronic device, including: a processor, and a memory communicatively connected to the processor; the memory stores computer execution instructions; the processor executes the computer execution instructions stored in the memory to implement the method provided in the foregoing embodiments.

[0129] To implement the above embodiments, the present application further provides a computer-readable storage medium storing computer-executable instructions, which are used to implement the method provided by the foregoing embodiments when executed by a processor.

[0130] To implement the above embodiments, the present application further provides a computer program product including a computer program, which implements the method provided by the foregoing embodiments when executed by a processor.

[0131] The collection, storage, use, processing, transmission, provision, and disclosure of the user's personal information involved in the present application all comply with the provisions of relevant laws and regulations and do not violate public order and good customs.

[0132] It should be noted that personal information from users should be collected for legal and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after obtaining the informed consent of the user, including but not limited to notifying the user to read the user agreement / user notice and sign an agreement / authorization including authorizing relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others with access to the personal information data comply with their privacy policies and procedures.

[0133] The present application anticipates providing embodiments that allow users to selectively block the use or access of personal information data. That is, the present disclosure anticipates providing hardware and / or software to prevent or block access to such personal information data. Once personal information data is no longer needed, the risk can be minimized by restricting data collection and deleting the data. In addition, when applicable, personal identifiers are removed from such personal information to protect the privacy of the user.

[0134] In the description of the foregoing embodiments, the descriptions referring to terms such as "one embodiment", "some embodiments", "example", "specific example", or "some examples" mean that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, without contradiction, those skilled in the art can combine and combine the different embodiments or examples described in this specification and the features of different embodiments or examples.

[0135] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the technical features indicated. Thus, features defined with "first" and "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "a plurality of" means at least two, such as two, three, etc., unless otherwise specifically defined.

[0136] Any process or method description represented in a flowchart or otherwise described herein can be understood to represent a module, segment, or portion of code including one or more executable instructions for implementing a customized logical function or process. The scope of the preferred embodiments of the present application includes additional implementations, where the functions may be executed in a substantially simultaneous manner or in a reverse order according to the functions involved, rather than in the order shown or discussed. This should be understood by those skilled in the art to which the embodiments of the present application pertain.

[0137] The logic and / or steps represented in a flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing a logical function, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device), or in conjunction with such instruction execution systems, apparatuses, or devices. For the purposes of this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. More specific examples (non-exhaustive list) of computer-readable media include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or other appropriate processing as necessary, and then stored in a computer memory.

[0138] It should be understood that each part of the present application can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits with logic gate circuits for implementing logical functions on data signals, application specific integrated circuits with appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0139] Those of ordinary skill in the art of this technology can understand that all or part of the steps carried by the methods of the above embodiments can be completed by instructing relevant hardware through a program. The said program can be stored in a computer-readable storage medium. When the program is executed, it includes one or a combination of the steps of the method embodiments.

[0140] In addition, in each embodiment of the present application, the functional units can be integrated into a processing module, or each unit can exist physically alone, or two or more units can be integrated into one module. The above integrated module can be implemented in the form of hardware or in the form of a software functional module. When the above integrated module is implemented in the form of a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium.

[0141] The above-mentioned storage medium can be a read-only memory, a magnetic disk, an optical disc, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limiting the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.

[0142] It should be understood that various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in the present application can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present application can be achieved. No limitations are imposed herein.

[0143] The above specific embodiments do not constitute a limitation to the protection scope of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present application shall be included within the protection scope of the present application.

Claims

1. An intelligent integrated operation and maintenance and fault diagnosis system for a pumped storage power station, characterized in that: Includes the following modules: Multi-source data acquisition and fusion module, used to collect and fuse the operating status data of the processing equipment to provide data support for subsequent modules; An intelligent fault diagnosis and prediction module, used to perform real-time fault diagnosis and prediction on the equipment based on the data collected and fused by the multi-source data collection and fusion module; Intelligent operation and maintenance decision-making and management platform, used for real-time monitoring, operation and maintenance management and decision support of equipment based on fault diagnosis and prediction results; The communication and security assurance module is used to ensure smooth communication and data security of the system and provide basic support for other modules.

2. The system according to claim 1, characterized in that The multi-source data acquisition and fusion module includes: Multiple types of high-precision sensors are used to collect equipment operating status data, including vibration, temperature, pressure, flow, gas, acoustics, current, and voltage; A distributed data acquisition unit, used for preprocessing the operating status data collected by the multi-type high-precision sensors, and transmitting the preprocessed multi-source data to a data fusion processor, wherein the preprocessing step includes data format conversion and preliminary screening of abnormal values; The data fusion processor is used to fuse the pre-processed multi-source data using Kalman filtering and DS evidence theory algorithm to determine the operating status of the equipment.

3. The system according to claim 2, characterized in that The intelligent fault diagnosis and prediction module comprises: A historical data storage unit, used to build a sample library and collect long-term operation data of the power station, the data including normal operation data of the equipment, fault data and maintenance records; Model Training Center, which uses machine learning and deep learning algorithms to train fault diagnosis and prediction models using historical data and optimize model parameters through cross-validation; The real-time diagnosis and prediction unit is used to perform fault diagnosis and prediction based on the real-time collected data using the trained model, and output the fault diagnosis results and prediction information. The fault diagnosis results include fault type identification, fault location positioning, and fault degree assessment. The fault prediction information includes the remaining service life of the equipment, fault development trend and maintenance suggestions.

4. The system according to claim 3, characterized in that The intelligent operation and maintenance decision-making and management platform includes: The equipment real-time monitoring module is used to visualize the equipment status. It uses 2D / 3D visualization technology to display the equipment layout, structure and operating status, supports remote operation control, and displays fault diagnosis results and prediction information in real time. The operation and maintenance plan management module is used to automatically generate an operation and maintenance plan based on fault diagnosis results and prediction information, equipment maintenance cycle and power plant operation plan. The operation and maintenance plan includes the type, content, time window, required resources and personnel arrangement of the maintenance task, and can dynamically track and evaluate the execution of the operation and maintenance plan; The material management module is used to manage the spare parts and materials required for the equipment, provide storage, delivery and inventory of spare parts, and conduct inventory warnings based on equipment failure rates and maintenance frequencies, and use intelligent algorithms to optimize inventory levels and replenishment strategies; The personnel management module is used to manage the basic information, skill qualifications, work arrangements and performance evaluation of operation and maintenance personnel, conduct intelligent scheduling based on task requirements and personnel skills, and optimize the work allocation of operation and maintenance personnel; The knowledge base management module is used to manage equipment technical data. It uses knowledge graph technology to build an equipment technical database, realizes structured storage of fault cases and maintenance experience, and provides multi-dimensional knowledge retrieval functions with automatic update and learning capabilities. The report generation and analysis module is used to automatically generate equipment operation and fault statistics operation and maintenance reports, and conduct in-depth mining and analysis of report data to provide data support for management decisions. The operation and maintenance reports support multiple formats and support customization.

5. The system according to claim 4, characterized in that The communication and security assurance module comprises: A communication network unit is used to construct a redundant network using industrial-grade communication equipment, including a fiber-optic Ethernet backbone network and wireless network coverage. The network adopts a ring topology to improve network reliability, sets redundant links, and uses flow control technology to reasonably allocate network bandwidth to ensure high-speed and stable data transmission; Security protection unit, used to deploy firewalls, intrusion detection systems, intrusion prevention systems, anti-virus software, the security protection unit can encrypt the storage and transmission of sensitive data, establish a data backup and recovery mechanism to prevent data leakage and malicious attacks; The user rights management unit is used to implement multi-factor identity authentication, assign different rights levels according to user roles and responsibilities, and record user operation logs in detail to facilitate the tracing and responsibility identification of security incidents.

6. A method for intelligent integrated operation and maintenance and fault diagnosis of a pumped storage power station, characterized in that: include: The operating parameters of the equipment are collected through multiple types of high-precision sensors, and the collected parameter data are pre-processed through distributed data acquisition units; The pre-processed data is input into the data fusion processor, and the Kalman filter and DS evidence theory algorithm are used to fuse the multi-source data and judge the operating status of the equipment; Through the intelligent fault diagnosis and prediction module, the fused data is matched with fault features by combining machine learning and deep learning algorithms, and the fault diagnosis and prediction results are output; According to the fault diagnosis and prediction results, an operation and maintenance plan is generated based on the intelligent operation and maintenance decision-making and management platform, and the execution of the plan is dynamically evaluated to ensure timely repair of equipment and normal operation of the power station.

7. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to claim 6.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to claim 6 when executed by a processor.

9. A computer program product, characterized in that The invention comprises a computer program which, when executed by a processor, implements the method as claimed in claim 6.

Images