Fault processing method and device, electronic equipment, storage medium and product

Abstract

The invention provides a fault processing method and device, electronic equipment, a storage medium and a product, and the method comprises the steps: obtaining real-time operation parameters of power station equipment, carrying out the fault prediction of the real-time operation parameters, obtaining a predicted fault type and a predicted fault occurrence time point of the power station equipment, carrying out the multi-dimensional impact evaluation of the predicted fault type, and obtaining a fault prediction result. The method comprises the following steps: acquiring a multi-dimensional influence result on power station equipment, performing dynamic cost analysis on the power station equipment by predicting a fault type and predicting a fault occurrence time point, acquiring predicted repair cost of the power station equipment, and determining a target fault processing decision for the power station equipment according to the multi-dimensional influence result and the predicted repair cost. And in response to the feedback of the user on the target fault processing decision on the preset user interaction page, optimizing the target fault processing decision, thereby reducing the operation and maintenance cost, improving the fault processing efficiency, improving the availability and reliability of the power station, and improving the user satisfaction.

Description

Technical Field

[0001] The present invention belongs to the field of new energy technology, and in particular relates to a fault handling method, device, electronic equipment, storage medium and product. Background Art

[0002] With the widespread application of electrochemical energy storage technology in power grids, the operation and maintenance management of energy storage power stations has become a key issue to ensure their long-term and stable operation. At present, the operation and maintenance management of electrochemical energy storage power stations mainly rely on regular inspections and maintenance to ensure the normal operation of the equipment. Among them, the service life of the power station is usually more than 20 years, but the warranty period is generally only five years. During the warranty period, the operation and maintenance team can use the services provided by the manufacturer to maintain or replace the equipment. After the warranty period, the operation and maintenance team needs to bear the cost of repairing or replacing the equipment. Usually, the operation and maintenance team decides whether to repair or replace the equipment based on experience or simple cost comparison.

[0003] There are several major problems with the existing technology in the operation and maintenance management of electrochemical energy storage power stations. First, the information is not transparent, and the operation and maintenance team does not have enough understanding of the specific causes of equipment failures, repair costs, and replacement costs, resulting in incomplete information when making decisions. Secondly, the lack of a predictive maintenance mechanism makes it impossible to identify potential equipment failures in advance, which increases the passivity of operation and maintenance. In addition, the economic evaluation is inaccurate, and there is a lack of systematic evaluation of the impact of equipment failures on the overall operational safety and economic benefits of the power station, making it difficult to optimize operation and maintenance decisions. The above problems lead to high power station operation and maintenance costs, low efficiency, and poor reliability in safe operation. Summary of the invention

[0004] The present invention provides a fault handling method, device, electronic equipment, storage medium and product to solve the current problems of high power station operation and maintenance cost, low efficiency and poor reliability of safe operation.

[0005] In order to solve the above-mentioned technical problems, the present invention is achieved as follows:

[0006] In a first aspect, the present invention provides a fault handling method, the method comprising:

[0007] Obtain real-time operating parameters of power station equipment;

[0008] Performing fault prediction on the real-time operating parameters to obtain the predicted fault type and predicted fault occurrence time of the power station equipment;

[0009] Performing a multi-dimensional impact assessment on the predicted fault type to obtain a multi-dimensional impact result on the power station equipment;

[0010] Performing a dynamic cost analysis on the power station equipment according to the predicted fault type and the predicted fault occurrence time point to obtain a predicted repair cost of the power station equipment;

[0011] Determining a target fault handling decision for the power plant equipment based on the multi-dimensional impact results and the predicted repair cost;

[0012] In response to feedback from a user on the target fault handling decision on a preset user interaction page, the target fault handling decision is optimized.

[0013] Optionally, the performing fault prediction on the real-time operating parameters to obtain a predicted fault type and a predicted fault occurrence time point of the power station equipment includes:

[0014] Collecting historical data of the power station equipment, the historical data including historical operating parameters of the power station equipment, historical fault occurrence time points and historical fault types;

[0015] Pre-training the autoregressive integrated moving average model and the deep learning model respectively through the historical data;

[0016] Inputting the real-time operating parameters into the pre-trained autoregressive integrated moving average model to obtain a predicted fault occurrence time point for the power station equipment;

[0017] The real-time operating parameters are input into the pre-trained deep learning model to obtain the predicted fault type of the power station equipment.

[0018] Optionally, the performing fault prediction on the real-time operating parameters to obtain a predicted fault type and a predicted fault occurrence time point of the power station equipment includes:

[0019] Performing fault prediction on the real-time operating parameters to obtain a number of predicted operating parameters of the power station equipment within a preset time period;

[0020] If any of the predicted operating parameters is greater than or equal to a preset fault threshold, obtaining the first power station equipment, target parameter type and target time point corresponding to the predicted operating parameter;

[0021] Obtaining a predicted fault type and a predicted fault occurrence time point of the power station equipment through the first power station equipment, the target parameter type and the target time point;

[0022] If some of the predicted operating parameters are less than preset fault thresholds, it is determined that there is no risk of failure of the power station equipment within a preset time period.

[0023] Optionally, performing a multi-dimensional impact assessment on the predicted fault type to obtain a multi-dimensional impact result on the power station equipment includes:

[0024] Predetermining different impact dimensions related to the predicted fault type assessment, the impact dimensions including economic impact dimensions, environmental impact dimensions, and social impact dimensions;

[0025] Set different weights and evaluation indicators for different impact dimensions;

[0026] The single-dimension impact results and the comprehensive-dimension impact results of different impact dimensions on the power station equipment are determined by using the weights and the evaluation indexes.

[0027] Optionally, performing dynamic cost analysis on the power station equipment according to the predicted fault type and the predicted fault occurrence time point to obtain the predicted repair cost of the power station equipment includes:

[0028] Determining a second power station device that needs to be processed from the power station devices according to the predicted fault type;

[0029] Obtaining replacement cost and maintenance cost of the second power station equipment;

[0030] Determining the loss cost caused by the predicted fault type based on the predicted fault occurrence time point;

[0031] The predicted repair costs of different fault repair methods for the power station equipment are obtained through the replacement cost, the maintenance cost and the loss cost, wherein the fault repair method includes replacing the power station equipment or repairing the power station equipment.

[0032] Optionally, the determining a target fault handling decision for the power plant equipment through the multi-dimensional impact results and the predicted repair cost further includes:

[0033] Obtaining a first fault handling decision on the power station equipment through the multi-dimensional impact results;

[0034] Obtaining a second fault handling decision on the power station equipment through the predicted repair cost;

[0035] The first fault handling decision and the second fault handling decision are screened by a preset strategy to determine a target fault handling decision for the power station equipment.

[0036] Optionally, the screening the first fault handling decision and the second fault handling decision by using a preset strategy to determine a target fault handling decision for the power station equipment includes:

[0037] In the case where it is determined that any single-dimensional impact result among the multi-dimensional impact results is greater than a preset value, determining the first fault handling decision as a target fault handling decision for the power station equipment;

[0038] When it is determined that a single-dimensional impact result in the multi-dimensional impact results is less than or equal to a preset value, the second fault handling decision is determined as a target fault handling decision for the power station equipment.

[0039] Optionally, the optimizing the target fault handling decision in response to feedback from the user on the target fault handling decision on a preset user interaction page further includes:

[0040] Obtain information on the behavior patterns of operation and maintenance personnel;

[0041] Setting a user interaction page based on the behavior pattern information;

[0042] Processing the power station equipment through the target fault processing decision to obtain a processing result;

[0043] The target fault processing decision is optimized based on the feedback of the target fault processing decision on the user interaction page according to the processing result.

[0044] Optionally, after optimizing the target fault handling decision in response to the user's feedback on the target fault handling decision on the preset user interaction page, the method further includes:

[0045] Obtain the actual fault repair cost and actual fault handling method corresponding to the optimized target fault handling decision;

[0046] The real-time operating parameters, the predicted fault type, the predicted fault occurrence time point, the actual fault repair cost and the actual fault handling method are integrated into a central database.

[0047] Optionally, the obtaining of real-time operating parameters of power station equipment includes:

[0048] Deploy several different types of sensors in the power station equipment in advance;

[0049] Different types of real-time operating parameters of the power station equipment are obtained through different types of sensors, wherein the real-time operating parameters include at least one of the voltage, current and temperature of the power station equipment.

[0050] Optionally, after acquiring the real-time operating parameters of the power station equipment, the method further includes:

[0051] transmitting the real-time operating parameters to an edge computing device;

[0052] Performing data cleaning and standardization processing on the real-time operating parameters through the edge computing device;

[0053] Key features are extracted from the processed real-time operating parameters.

[0054] In a second aspect, the present invention provides a fault handling device, the device comprising:

[0055] A first acquisition module is used to acquire real-time operating parameters of power station equipment;

[0056] A second acquisition module is used to perform fault prediction on the real-time operating parameters to obtain the predicted fault type and predicted fault occurrence time of the power station equipment;

[0057] A third acquisition module is used to perform a multi-dimensional impact assessment on the predicted fault type to obtain a multi-dimensional impact result on the power station equipment;

[0058] A fourth acquisition module, configured to perform a dynamic cost analysis on the power station equipment according to the predicted fault type and the predicted fault occurrence time point, to obtain a predicted repair cost of the power station equipment;

[0059] A first determination module is used to determine a target fault handling decision for the power station equipment based on the multi-dimensional impact results and the predicted repair cost;

[0060] The decision optimization module is used to optimize the target fault handling decision in response to the feedback of the user on the target fault handling decision on the preset user interaction page.

[0061] In a third aspect, the present invention provides an electronic device, comprising: a transceiver, a memory, a processor, and a program stored in the memory and executable on the processor;

[0062] The processor is used to read the program in the memory to implement any of the above-mentioned fault handling methods.

[0063] In a fourth aspect, the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, which, when executed on a computer, enable the computer to execute any of the above-mentioned fault handling methods.

[0064] In a fifth aspect, the fifth aspect of an embodiment of the present invention provides a computer program product, including a computer program / instructions, which, when executed by a processor, implement the steps of the fault handling method as described in the first aspect of an embodiment of the present invention.

[0065] In the present invention, by acquiring the real-time operating parameters of the power station equipment; performing fault prediction on the real-time operating parameters, obtaining the predicted fault type and predicted fault occurrence time point of the power station equipment, realizing predictive maintenance, reducing unexpected downtime, and improving the reliability of the power station, performing multi-dimensional impact assessment on the predicted fault type, obtaining the multi-dimensional impact results on the power station equipment, ensuring that all important factors can be comprehensively considered when making decisions, performing dynamic cost analysis on the power station equipment by predicting the fault type and the predicted fault occurrence time point, obtaining the predicted repair cost of the power station equipment, being able to predict and evaluate the economic feasibility of repair and replacement in real time, helping the operation and maintenance team to make a decision with maximum cost-effectiveness, determining the target fault handling decision for the power station equipment through the multi-dimensional impact results and the predicted repair cost, determining the handling decision after comprehensive consideration, improving the efficiency and accuracy of the decision, responding to the user's feedback on the target fault handling decision on the preset user interaction page, optimizing the target fault handling decision, and setting the user interaction page so that the operation and maintenance personnel can quickly obtain the target fault handling decision, simplify the decision-making process, improve the decision-making efficiency, optimize the target fault handling decision through user feedback, and improve the system availability and user satisfaction. In summary, the present invention predicts faults in advance, evaluates the impact of faults from multiple dimensions, combines the evaluation results with the cost-effectiveness of fault handling, determines the target fault handling decision for power station equipment, and then optimizes the target fault handling decision through users, which not only reduces operation and maintenance costs and improves fault handling efficiency, but also improves the availability and reliability of the power station and enhances user satisfaction. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0067] Figure 1 It is a step flow chart of a fault handling method provided by the present invention;

[0068] Figure 2 yes Figure 1 The flowchart of step 102 in a fault handling method provided by the present invention is shown;

[0069] Figure 3 yes Figure 1 The flowchart of step 103 in a fault handling method provided by the present invention is shown;

[0070] Figure 4 yes Figure 1The flowchart of step 104 in a fault handling method provided by the present invention is shown;

[0071] Figure 5 yes Figure 1 A system architecture diagram of a fault handling method provided by the present invention is shown;

[0072] Figure 6 yes Figure 1 A flowchart of a fault handling method provided by the present invention is shown;

[0073] Figure 7 It is a structural diagram of a fault handling device provided by the present invention;

[0074] Figure 8 It is a structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0075] The technical solution of the present invention will be described clearly and completely below in conjunction with the accompanying drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0076] Reference Figure 1 , Figure 1 is a flowchart of the steps of a fault handling method provided by the present invention, such as Figure 1 As shown, the method may include:

[0077] Step 101, obtaining real-time operating parameters of power station equipment.

[0078] The power station equipment in the embodiment of the present invention may include an energy storage battery system, including lithium-ion batteries, lead-acid batteries, flow batteries, sodium-sulfur batteries, solid-state batteries, etc., a battery management system, an energy storage inverter (converting the DC power stored in the battery into AC power, or converting AC power into DC power for storage), a fire protection system, including smoke detectors, gas fire extinguishing systems (such as heptafluoropropane) or water spray systems and other fire extinguishing devices, ventilation systems, transformers, etc.

[0079] In order to obtain the real-time operating parameters of power station equipment, different types of sensors need to be deployed in advance. Then different types of real-time operating parameters can be obtained through different types of sensors. The specific steps include:

[0080] Deploy several different types of sensors in power station equipment in advance;

[0081] Different types of real-time operating parameters of the power station equipment are acquired through different types of sensors, wherein the real-time operating parameters include at least one of the voltage, current and temperature of the power station equipment.

[0082] It should be noted that different types of sensors may include voltage sensors, current sensors, temperature sensors, environmental humidity monitoring sensors, and equipment vibration monitoring sensors. Therefore, in addition to voltage, current, and temperature, real-time operating parameters may also include humidity, pressure, vibration, etc., which are not specifically limited in the present invention.

[0083] Furthermore, after obtaining the real-time operating parameters, the data will be initially processed through edge computing devices, including data cleaning, standardization, and feature extraction. The specific steps include:

[0084] Transmit real-time operating parameters to edge computing devices;

[0085] Use edge computing devices to clean and standardize real-time operating parameters;

[0086] Extract key features from the processed real-time operating parameters.

[0087] Among them, data cleaning can be to remove noise using a filtering algorithm (such as Kalman filtering), and standardization can be to unify the data format using a standardization algorithm (such as a Z-score standardization algorithm). It should be noted that the acquired real-time operating parameters can be regarded as time series data arranged in chronological order.

[0088] It should be noted that after extracting the key features, fault prediction can be performed through the key features.

[0089] Step 102: perform fault prediction on the real-time operating parameters to obtain the predicted fault type and predicted fault occurrence time point of the power station equipment.

[0090] When the embodiment of the present invention predicts faults for real-time operating parameters, an autoregressive integral moving average model and a deep learning model are required. Other models may also be used, such as seasonal autoregressive integral moving average models, exponential smoothing models, support vector machines, etc. The present invention does not make specific limitations here. Taking the autoregressive integral moving average model as an example, it is necessary to pre-train the model before using it. Pre-training requires the collection of historical data of power station equipment. Because the embodiment of the present invention predicts the type and time of the fault to be caused by real-time operating parameters, the collected historical data also needs to include these factors, that is, the historical data includes the historical operating parameters of the power station equipment, the historical fault occurrence time points and the historical fault types. The predicted fault occurrence time points of the power station equipment are obtained by training the autoregressive integral moving average model with historical data, and the predicted fault types of the power station equipment are obtained by training the deep learning model with historical data.

[0091] Among them, when training the autoregressive integrated moving average model, it is necessary to determine the parameters of the model first. The parameters of the model include p (autoregressive order): indicating the number of lag terms used in the model, d (difference order): indicating the number of differences required to stabilize the time series, q (moving average order): indicating the number of moving average terms used in the model. When determining the parameters of the model, the parameters of the model can also be optimized and adjusted (such as recursive least squares method) by calculating the error value between the predicted results and the actual results of the model until the error value meets the requirements. At this time, the model parameters are the expected model parameters. Then, the autoregressive integrated moving average model with the expected model parameters is used to predict the real-time operating parameters to obtain the predicted fault occurrence time point of the power station equipment. The specific steps include:

[0092] Collect historical data of power plant equipment, including historical operating parameters of power plant equipment, historical fault occurrence time points and historical fault types;

[0093] The autoregressive integrated moving average model and the deep learning model are pre-trained using historical data;

[0094] The real-time operating parameters are input into the pre-trained autoregressive integrated moving average model to obtain the predicted fault occurrence time point of the power station equipment;

[0095] The real-time operating parameters are input into the pre-trained deep learning model to obtain the predicted fault type of the power plant equipment.

[0096] It should be noted that the pre-trained autoregressive integrated moving average model and deep learning model will continue to optimize and adjust based on the new data when making new data predictions.

[0097] The real-time operating parameters are predicted by the pre-trained autoregressive integrated moving average model, and the predicted operating parameters in the future period are obtained. It is checked whether the predicted operating parameters exceed the preset fault threshold. If they exceed, the corresponding first power station equipment, parameter type and time point are recorded. According to the first power station equipment, the parameter type and time point exceeding the threshold, the predicted fault type and occurrence time point are determined. If all predicted operating parameters do not exceed the threshold, it is determined that the equipment does not have a fault risk within the preset time period. Specifically, step 102, such as Figure 2 As shown:

[0098] Step 1021 , performing fault prediction on the real-time operating parameters, and obtaining a number of predicted operating parameters of the power station equipment within a preset time period.

[0099] Step 1022: If any predicted operating parameter is greater than or equal to a preset fault threshold, the first power station equipment, target parameter type and target time point corresponding to the predicted operating parameter are obtained.

[0100] Step 1023 , obtaining the predicted fault type and predicted fault occurrence time point of the power station equipment through the first power station equipment, the target parameter type and the target time point.

[0101] Step 1024: If the plurality of predicted operating parameters are less than the preset fault threshold, it is determined that there is no fault risk for the power station equipment within the preset time period.

[0102] For example, assume that the real-time operating parameters of the equipment in an electrochemical energy storage power station are as follows: battery module A has a voltage of 220 V, a current of 10 A, and a temperature of 25 ° C; battery module B has a voltage of 215 V, a current of 12 A, and a temperature of 28 ° C. To predict the operating parameters within the next 24 hours, battery module A has a voltage of [220, 221, 222, ..., 235] V, a current of [10, 11, 12, ..., 15] A, and a temperature of [25, 26, 27, ..., 30] ° C; battery module B has a voltage of [215, 216, 217, ..., 220] V, a current of [12 A, 28 ° C], and a temperature of [25, 26, 27, ..., 30] ° C. [12,13,14,...,18]A, Temperature: [28,29,30,...,35]℃, set the preset fault threshold of voltage to 230V, the preset fault threshold of current to 20A, and the preset fault threshold of temperature to 40℃. Because the voltage of battery module A at the 12th hour is 235V>230V, it is recorded that the first power station equipment is "battery module A", the target parameter type is "voltage", and the target time point is "the 12th hour". According to the historical data of overvoltage, the predicted fault type is determined to be "battery module A battery overvoltage", and the predicted fault occurrence time point is "the 12th hour". Because all the predicted operating parameters of "battery module B" do not exceed the threshold, it is determined that "battery module B" does not have a fault risk. Similarly, if the predicted operating parameters of all power station equipment are less than the preset fault threshold, it is considered that there is no fault in this prediction.

[0103] By analyzing the equipment failure time series in the above way, the accuracy of failure prediction is improved. In addition, by continuously adjusting and optimizing the autoregressive integral moving average model, potential failures can be warned more accurately in advance, reducing unexpected downtime.

[0104] Step 103: Perform a multi-dimensional impact assessment on the predicted fault type to obtain a multi-dimensional impact result on the power station equipment.

[0105] After determining the predicted fault type in the embodiment of the present invention, the impact dimensions that need to be considered when evaluating the fault type will also be clarified to ensure the comprehensiveness and scientificity of the evaluation. The impact dimension can be an economic impact dimension, through which the impact of the fault on the economic benefits of the power station is evaluated, such as maintenance costs, power generation losses, etc. It can also be an environmental impact dimension, through which the impact of the fault on the environment is evaluated, such as energy waste, increased emissions, etc. It can also be a social impact dimension, through which the impact of the fault on society is evaluated, such as power supply reliability, user satisfaction, etc. Based on expert experience, historical data or related research, a weight is assigned to each impact dimension, and specific evaluation indicators are set to ensure the scientificity and operability of the evaluation. According to the weights and evaluation indicators, the single dimension impact results of different impact dimensions are calculated, and the comprehensive dimension impact results are comprehensively obtained. Specifically, step 103, such as Figure 3 As shown:

[0106] Step 1031 , predetermine different impact dimensions related to the evaluation of the predicted fault type.

[0107] Step 1032, setting different weights and different evaluation indicators for different impact dimensions.

[0108] Step 1033, determining the single dimension impact results and comprehensive dimension impact results of different impact dimensions on power station equipment through weights and evaluation indicators.

[0109] Among them, the impact dimensions include economic impact dimension, environmental impact dimension and social impact dimension.

[0110] For example, the predicted fault type is: battery module A battery overheating, and the related different impact dimensions include economic impact dimension (repair cost 5000 yuan, power generation loss 10000 yuan), environmental impact dimension (energy waste 200kWh, emission increase 100kg CO2) and social impact dimensions (power supply reliability decreased by 10%, user satisfaction decreased by 5%), the weights set are: economic impact dimension: 0.5, environmental impact dimension: 0.3, social impact dimension: 0.2, the economic impact dimensions in the evaluation indicators set are: maintenance cost, power generation loss, environmental impact dimensions are: energy waste, increased emissions, social impact dimensions are: power supply reliability, user satisfaction, the calculated single dimension impact results are: economic impact results: 5000 yuan (maintenance cost) + 10000 yuan (power generation loss) = 15000 yuan, corresponding to 15000 points, environmental impact results: 200kWh (energy waste) + 100kgCO2 (increased emissions) = 300, social impact results: 10% (power supply reliability decreased) + 5% (user satisfaction decreased) = 15, the calculated comprehensive dimension impact results = 15000×0.5+300×0.3+15×0.2=7500+90+3=7593 points.

[0111] By conducting a multi-dimensional impact assessment, not only the economic impact of the failure is taken into account, but also the environmental and social impact of the failure, making the decision more comprehensive and responsible.

[0112] Step 104 , performing dynamic cost analysis on the power station equipment by predicting the fault type and the time point at which the fault will occur, to obtain the predicted repair cost of the power station equipment.

[0113] In addition to performing a multi-dimensional impact assessment on the predicted fault type, the embodiment of the present invention also predicts the fault repair cost. First, according to the predicted fault type, the equipment that needs to be processed (the second power station equipment) is determined, and then the replacement cost and maintenance cost of the second power station equipment are obtained to provide data support for subsequent cost analysis. According to the predicted time point of the fault, the loss cost caused by the fault is calculated, and the replacement cost, maintenance cost and loss cost are combined to calculate the predicted result of the fault repair cost. Specifically, step 104, as shown in Figure 4 As shown:

[0114] Step 1041: Determine a second power station device that needs to be processed from the power station devices by predicting the fault type.

[0115] Step 1042, obtaining the replacement cost and maintenance cost of the second power station equipment.

[0116] Step 1043, by predicting the time point of occurrence of the fault, determine the loss cost caused by the predicted fault type.

[0117] Step 1044, obtaining predicted repair costs for different fault repair methods of power station equipment through replacement cost, maintenance cost and loss cost.

[0118] Among them, the above-mentioned different fault repair methods for power station equipment include replacing power station equipment (second power station equipment) or repairing power station equipment (second power station equipment). The replacement cost may include equipment replacement cost and installation and commissioning cost, the maintenance cost may include equipment maintenance cost and maintenance personnel expenses, and the loss cost may include power generation loss cost and other loss costs. The predicted repair cost includes the predicted repair cost of the replacement method, in which case the predicted repair cost = replacement cost + loss cost, and also includes the predicted repair cost of the maintenance method, in which case the predicted repair cost = maintenance cost + loss cost.

[0119] For example, assuming that the predicted fault type is battery module A overheating, the predicted fault occurrence time is the 12th hour, it is determined that the second power station equipment is battery module A, the replacement cost of battery module A is 20,000 yuan and the repair cost is 5,000 yuan, because the battery overheating leads to reduced power generation, the power generation loss cost is 10,000 yuan, at this time, the predicted repair cost of the replacement method is: 20,000 yuan + 10,000 yuan = 30,000 yuan, and the predicted repair cost of the repair method is: 5,000 yuan + 10,000 yuan = 15,000 yuan.

[0120] The above steps provide a quantitative economic evaluation for repair and replacement, helping operation and maintenance personnel make more economical decisions.

[0121] It should be noted that the above cost forecast can be achieved through the exponential smoothing method. In addition, when forecasting the cost of the maintenance method, the service life of the equipment after maintenance and the service life after replacement can also be considered and discounted into discounted costs to more comprehensively evaluate the economic feasibility of the maintenance method. The steps include:

[0122] Obtain the remaining service life of the second power station equipment after maintenance;

[0123] Obtaining a total service life of the second power station equipment;

[0124] Use the discount rate to discount the benefits over the remaining useful life to the first discounted cost and the benefits over the total useful life to the second discounted cost;

[0125] Obtaining a predicted repair cost under a maintenance mode through the first discounted cost, the loss cost and the maintenance cost;

[0126] The predicted repair cost under the replacement mode is obtained through the second discounted cost, the loss cost and the replacement cost.

[0127] Discounted cost = income from useful life / (1+discount rate)^number of years

[0128] For example, if the service life of battery module A after repair is 2 years, the discount rate is 5%, and the profit after repair for 2 years is 10,000 yuan, the first discounted cost of the service life after repair for 2 years = 10,000 / (1+0.05)^2 = 9,070 yuan, and correspondingly, the predicted repair cost under the maintenance mode = 5,000 yuan (repair cost) + 10,000 yuan (loss cost) - 9,070 yuan (discounted cost) = 5,930 yuan. If the service life of battery module A after replacement is 10 years, the profit is 50,000 yuan, the second discounted cost = 50,000 / (1+0.05)^10 = 30,695 yuan, and the predicted repair cost under the replacement mode = 20,000 yuan + 10,000 yuan - 30,695 yuan = -695 yuan.

[0129] The above methods help the operation and maintenance team avoid unnecessary repairs and premature equipment replacement, thereby reducing long-term operation and maintenance costs.

[0130] Step 105, determining a target fault handling decision for the power plant equipment through multi-dimensional impact results and predicted repair costs.

[0131] In the embodiment of the present invention, an intelligent decision tree based on the CART algorithm is used to comprehensively consider multi-dimensional impact results and predict repair costs, and finally determine the target fault handling decision for power station equipment. The specific steps include:

[0132] Obtain the first fault handling decision on power plant equipment through multi-dimensional impact results;

[0133] Obtain the second fault handling decision on power plant equipment by predicting the repair cost;

[0134] The first fault handling decision and the second fault handling decision are screened by a preset strategy to determine a target fault handling decision for the power station equipment.

[0135] It should be noted that the steps of screening the first fault handling decision and the second fault handling decision by a preset strategy to determine the target fault handling decision for the power station equipment include:

[0136] When it is determined that any single-dimensional impact result among the multi-dimensional impact results is greater than a preset value, determining the first fault handling decision as a target fault handling decision for the power station equipment;

[0137] When it is determined that a single-dimensional impact result in the multi-dimensional impact results is less than or equal to a preset value, the second fault handling decision is determined as a target fault handling decision for the power station equipment.

[0138] For example, if the economic impact results in the multi-dimensional impact results are: maintenance cost 5,000 yuan, power generation loss 10,000 yuan, so the score is 15,000 points, environmental impact results: energy waste 200kWh, emission increase 100kg CO2, so the score is 300 points, social impact results: power supply reliability decreases 10%, user satisfaction decreases 5%, so the score is 15 points. The preset values ​​of the economic impact results are set to 15,000, the preset values ​​of the environmental impact results are 300, and the preset values ​​of the social impact results are 20 points. Because all the single-dimensional impact results are less than or equal to the preset values, the target fault handling decision for the power station equipment is determined by predicting the repair cost. Because the predicted repair cost under the maintenance method is: 5,930 yuan, and the predicted repair cost under the replacement method is: -695 yuan, the target fault handling decision for the power station equipment is to replace the second power station equipment that has failed. Suppose the preset value of the economic impact result is set to 15000, the preset value of the environmental impact result is set to 200, and the preset value of the social impact result is set to 20 points. Because the environmental impact result of 300>200, the environmental protection strategy needs to be given priority before considering the cost. Because the environmental pollution caused by replacement is more serious, the maintenance method is preferred, that is, the target fault handling decision for the power station equipment is to repair the second power station equipment that has a fault.

[0139] Through the above method, the operation and maintenance personnel are provided with the optimal maintenance or replacement strategy based on current data and prediction results, which reduces the complexity and uncertainty of decision-making and improves the efficiency and effectiveness of decision-making.

[0140] Step 106 , in response to the user's feedback on the target fault handling decision on the preset user interaction page, optimizing the target fault handling decision.

[0141] In the embodiment of the present invention, K-means clustering is also used to analyze the behavior patterns of operation and maintenance personnel. According to the behavior patterns of operation and maintenance personnel, user interaction pages are designed. For example, operation and maintenance personnel often check the operating status and historical fault records of specific equipment. At this time, the status of these equipment can be automatically placed in a prominent position on the dashboard, or quick links to these equipment can be provided when the user logs in. Or some operation and maintenance personnel may prefer to make decisions based on cost-benefit analysis, while others may pay more attention to the immediate status of the equipment. At this time, customized decision support tools and reports can be provided according to the user's preferences, such as highlighting economic analysis for cost-oriented users and providing real-time monitoring data for status-oriented users. Or users may be accustomed to using specific operating procedures, such as checking alarm information first and then checking the detailed status of related equipment. At this time, an intuitive workflow can be designed to guide users to operate in the way they are accustomed to, or a customizable workflow can be provided to allow users to set the operation order according to their own habits. Or some users may prefer charts and graphics to obtain information, while other users may prefer text reports. At this time, a variety of information display methods can be provided, allowing users to choose charts, graphics or text formats according to their preferences. Or when a fault occurs, some operations and maintenance personnel may need to be notified immediately by the system, while others may not have such strict requirements on the response time for non-emergency situations. In this case, different notification priorities and notification methods can be set according to the user's sensitivity to response time, such as SMS, email, or in-app notification. Or users may follow specific steps when handling faults, such as diagnosing the fault first, then finding spare parts, and finally performing repairs. In this case, a structured fault handling interface can be provided to guide users through each step according to the process they are accustomed to.

[0142] After making a decision on the target fault handling, it is necessary to conduct a comprehensive test in the actual power station environment and record the results of the fault handling, including the handling time, handling cost, equipment status, etc. The accuracy, reliability and user satisfaction of the system are verified based on the handling results, and optimization is carried out based on the feedback. The specific steps include:

[0143] Obtain information on the behavior patterns of operation and maintenance personnel;

[0144] Set up user interaction pages based on behavior pattern information;

[0145] Process the power plant equipment through target fault processing decisions and obtain processing results;

[0146] Based on the processing results, the target fault handling decision is optimized by providing feedback on the target fault handling decision on the user interaction page.

[0147] Among them, the behavior patterns can be divided into two categories: maintenance preference type and replacement preference type. According to the behavior pattern of maintenance preference type operation and maintenance personnel, the maintenance option is highlighted on the page, and according to the behavior pattern of replacement preference type operation and maintenance personnel, the replacement option is highlighted on the page. Users can evaluate and feedback the processing results. The feedback content can be a score for the target fault handling decision, with satisfaction being 10 points and dissatisfaction being 1 point. The target fault handling decision can be further adjusted based on the feedback content. The user interface of the above process can display the status of power plant equipment, the predicted fault type and predicted fault occurrence time point during fault prediction, the impact assessment results of the predicted fault type, and the target fault handling decision for power plant equipment, and provide customized views and interactive tools.

[0148] Analyzing the behavior patterns of operation and maintenance personnel in the above process helps to optimize the user interaction interface and interaction process, improve system availability and user satisfaction, and the testing and feedback loop ensures the long-term stable operation and continuous improvement of the system.

[0149] Furthermore, after obtaining the test results, all the data obtained this time will be integrated into the central database and effectively managed using data warehouse technology. The specific steps include:

[0150] Obtain the actual fault repair cost and actual fault handling method corresponding to the optimized target fault handling decision;

[0151] Integrate real-time operating parameters, predicted fault types, predicted fault occurrence time, actual fault repair costs and actual fault handling methods into the central database.

[0152] By integrating data in the above manner, it is possible to avoid a large amount of time wasted due to information dispersion and improve the efficiency of operation and maintenance management.

[0153] It should be noted that the fault handling method of the embodiment of the present invention can be implemented by the intelligent operation and maintenance management system of the power station, such as Figure 5As shown, the intelligent operation and maintenance management system includes a data acquisition layer, a data processing layer, a decision support layer and a user interaction layer. The data acquisition layer includes setting up a sensor network, and obtaining the real-time operating parameters of the power station equipment through the sensor network. The data processing layer includes a data preprocessing module, which performs data cleaning, standardization and feature extraction operations on the real-time operating parameters, an autoregressive integral sliding average model, a multi-dimensional evaluation model, a cost prediction model and a decision tree algorithm model. The decision support layer analyzes the fault prediction results, the impact evaluation results and the cost-benefit analysis results, and determines the maintenance or replacement strategy, wherein the fault prediction results (including the predicted fault type and the predicted fault occurrence time point) are obtained through the autoregressive integral sliding average model, the impact evaluation results (corresponding to the multi-dimensional impact results) are obtained through the multi-dimensional evaluation model, and the cost-benefit analysis results (corresponding to the predicted repair cost) are obtained through the cost prediction model, and the maintenance or replacement strategy (corresponding to the target fault handling decision) is determined through the decision tree algorithm model. The user interaction layer sets a user interaction interface, and interactive tools (such as shortcut keys) and feedback systems are set on the user interaction interface.

[0154] Specifically, the function implementation process in the intelligent operation and maintenance management system of the power station is as follows: Figure 6 As shown, the functions include: data collection, fault prediction, impact assessment, cost prediction, decision analysis, decision support, data management, user interaction and feedback improvement. Among them, data collection includes sensor data acquisition, data cleaning and feature extraction. Fault prediction analyzes the real-time operating parameters that constitute the time series through an adaptive fault prediction algorithm. The model parameters are first estimated through the autoregressive integral moving average model, and then the model is trained to obtain the expected model parameters. After that, the pre-trained autoregressive integral moving average model is used to predict faults and output the fault prediction results (including the predicted fault type and the predicted fault occurrence time point). Impact assessment is achieved through a multi-dimensional evaluation model. It is necessary to first assign weights to the impact dimensions of the multi-dimensional evaluation model, and then obtain the multi-dimensional impact results through the hierarchical analysis method. Cost prediction is achieved through the cost prediction model To achieve this, the cost is predicted through the exponential smoothing method to obtain the predicted repair cost. The decision analysis is achieved by further evaluating the economic feasibility of maintenance and replacement through the NPV algorithm to obtain the target predicted repair cost. Decision support is determined through intelligent decision trees to determine the maintenance or replacement strategy. Data management refers to data integration and management, which integrates information into a central database and is managed by the central database to facilitate subsequent data query and data retrieval. User interaction refers to user interface and interaction design, which is achieved through the set user interaction interface, which includes interactive tools and feedback systems. Feedback improvement is achieved by conducting actual performance tests on the target fault handling decisions, and then collecting user feedback for optimization and adjustment.

[0155] In the present invention, by acquiring the real-time operating parameters of the power station equipment; performing fault prediction on the real-time operating parameters, obtaining the predicted fault type and predicted fault occurrence time point of the power station equipment, realizing predictive maintenance, reducing unexpected downtime, and improving the reliability of the power station, performing multi-dimensional impact assessment on the predicted fault type, obtaining the multi-dimensional impact results on the power station equipment, ensuring that all important factors can be comprehensively considered when making decisions, performing dynamic cost analysis on the power station equipment by predicting the fault type and the predicted fault occurrence time point, obtaining the predicted repair cost of the power station equipment, being able to predict and evaluate the economic feasibility of repair and replacement in real time, helping the operation and maintenance team to make a decision with maximum cost-effectiveness, determining the target fault handling decision for the power station equipment through the multi-dimensional impact results and the predicted repair cost, determining the handling decision after comprehensive consideration, improving the efficiency and accuracy of the decision, responding to the user's feedback on the target fault handling decision on the preset user interaction page, optimizing the target fault handling decision, and setting the user interaction page so that the operation and maintenance personnel can quickly obtain the target fault handling decision, simplify the decision-making process, improve the decision-making efficiency, optimize the target fault handling decision through user feedback, and improve the system availability and user satisfaction. In summary, the present invention predicts faults in advance, evaluates the impact of faults from multiple dimensions, combines the evaluation results with the cost-effectiveness of fault handling, determines the target fault handling decision for power station equipment, and then optimizes the target fault handling decision through users, which not only reduces operation and maintenance costs and improves fault handling efficiency, but also improves the availability and reliability of the power station and enhances user satisfaction.

[0156] Figure 7 : is a structural diagram of a fault handling device provided by the present invention, and the device may include:

[0157] The first acquisition module 201 is used to acquire real-time operating parameters of power station equipment.

[0158] The second acquisition module 202 is used to perform fault prediction on the real-time operating parameters and obtain the predicted fault type and predicted fault occurrence time point of the power station equipment.

[0159] The third acquisition module 203 is used to perform a multi-dimensional impact assessment on the predicted fault type and obtain a multi-dimensional impact result on the power station equipment.

[0160] The fourth acquisition module 204 is used to perform dynamic cost analysis on the power station equipment by predicting the fault type and predicting the time point of the fault occurrence, so as to obtain the predicted repair cost of the power station equipment.

[0161] The first determination module 205 is used to determine a target fault handling decision for power station equipment through multi-dimensional impact results and predicted repair costs.

[0162] The decision optimization module 206 is used to optimize the target fault processing decision in response to the user's feedback on the target fault processing decision on the preset user interaction page.

[0163] Optionally, the second acquisition module 202 specifically includes:

[0164] The collection submodule is used to collect historical data of power station equipment, which includes historical operating parameters of power station equipment, historical fault occurrence time points and historical fault types.

[0165] The first determination submodule is used to pre-train the autoregressive integrated moving average model and the deep learning model through historical data to determine the expected model parameters.

[0166] The first acquisition submodule is used to input the real-time operating parameters into the pre-trained autoregressive integral moving average model to obtain the predicted fault occurrence time point of the power station equipment;

[0167] The second acquisition submodule is used to input the real-time operating parameters into the pre-trained deep learning model to obtain the predicted fault type of the power station equipment.

[0168] The third acquisition submodule is used to perform fault prediction on the real-time operating parameters and obtain a number of predicted operating parameters of the power station equipment within a preset time period.

[0169] The fourth acquisition submodule is used to acquire the first power station equipment, target parameter type and target time point corresponding to the predicted operation parameter if any predicted operation parameter is greater than or equal to a preset fault threshold.

[0170] The fifth acquisition submodule is used to acquire the predicted fault type and predicted fault occurrence time point of the power station equipment through the first power station equipment, the target parameter type and the target time point.

[0171] The determination submodule is used to determine that there is no risk of failure of the power station equipment within a preset time period if a number of predicted operating parameters are less than a preset fault threshold.

[0172] Optionally, the third acquisition module 203 specifically includes:

[0173] The second determination submodule is used to predetermine different impact dimensions related to the prediction fault type assessment, and the impact dimensions include economic impact dimension, environmental impact dimension and social impact dimension.

[0174] The first setting submodule is used to set different weights and different evaluation indicators for different impact dimensions.

[0175] The third determination submodule is used to determine the single-dimension impact results and comprehensive-dimension impact results of different impact dimensions on power station equipment through weights and evaluation indicators.

[0176] Optionally, the fourth acquisition module 204 specifically includes:

[0177] The fourth determination submodule is used to determine the second power station equipment that needs to be processed from the power station equipment by predicting the fault type.

[0178] The sixth acquisition submodule is used to acquire the replacement cost and maintenance cost of the second power station equipment.

[0179] The fifth determination submodule is used to determine the loss cost caused by the predicted fault type by predicting the time point of fault occurrence.

[0180] The seventh acquisition submodule is used to obtain the predicted repair costs of different fault repair methods for power station equipment through replacement cost, maintenance cost and loss cost, wherein the fault repair method includes replacing the power station equipment or repairing the power station equipment.

[0181] Optionally, the first determining module 205 specifically includes:

[0182] The eighth acquisition submodule is used to acquire a first fault handling decision on the power station equipment through multi-dimensional impact results.

[0183] The ninth acquisition submodule is used to acquire a second fault handling decision on the power station equipment by predicting the repair cost.

[0184] The sixth determination submodule is used to screen the first fault handling decision and the second fault handling decision through a preset strategy to determine a target fault handling decision for the power station equipment.

[0185] Optionally, the sixth determining submodule specifically includes:

[0186] The first determination unit is used to determine the first fault handling decision as a target fault handling decision for the power station equipment when it is determined that any single-dimensional impact result among the multi-dimensional impact results is greater than a preset value.

[0187] The second determination unit is used to determine the second fault handling decision as a target fault handling decision for the power station equipment when it is determined that a single-dimensional impact result in the multi-dimensional impact results is less than or equal to a preset value.

[0188] Optionally, the decision optimization module 206 specifically includes:

[0189] The tenth acquisition submodule is used to obtain the behavior pattern information of the operation and maintenance personnel.

[0190] The second setting submodule is used to set the user interaction page through the behavior pattern information.

[0191] The eleventh acquisition submodule is used to process the power station equipment through the target fault processing decision and obtain the processing result.

[0192] The decision optimization submodule is used to optimize the target fault processing decision based on the processing results and the feedback on the target fault processing decision on the user interaction page.

[0193] Optionally, the fault handling device further includes:

[0194] The fifth acquisition module is used to obtain the actual fault repair cost and the actual fault handling method corresponding to the optimized target fault handling decision.

[0195] The integration module is used to integrate the real-time operating parameters, predicted fault type, predicted fault occurrence time, actual fault repair cost and actual fault handling method into the central database.

[0196] Optionally, the first acquisition module 201 specifically includes:

[0197] The deployment submodule is used to deploy several different types of sensors in the power station equipment in advance.

[0198] The twelfth acquisition submodule is used to acquire different types of real-time operating parameters of the power station equipment through different types of sensors, wherein the real-time operating parameters include at least one of the voltage, current and temperature of the power station equipment.

[0199] Optionally, the fault handling device further includes:

[0200] The transmission module is used to transmit real-time operating parameters to the edge computing device.

[0201] The data processing module is used to clean and standardize the real-time operating parameters through edge computing devices.

[0202] The feature extraction module is used to extract key features from the processed real-time operation parameters.

[0203] In the present invention, by acquiring the real-time operating parameters of the power station equipment; performing fault prediction on the real-time operating parameters, obtaining the predicted fault type and predicted fault occurrence time point of the power station equipment, realizing predictive maintenance, reducing unexpected downtime, and improving the reliability of the power station, performing multi-dimensional impact assessment on the predicted fault type, obtaining the multi-dimensional impact results on the power station equipment, ensuring that all important factors can be comprehensively considered when making decisions, performing dynamic cost analysis on the power station equipment by predicting the fault type and the predicted fault occurrence time point, obtaining the predicted repair cost of the power station equipment, being able to predict and evaluate the economic feasibility of repair and replacement in real time, helping the operation and maintenance team to make a decision with maximum cost-effectiveness, determining the target fault handling decision for the power station equipment through the multi-dimensional impact results and the predicted repair cost, determining the handling decision after comprehensive consideration, improving the efficiency and accuracy of the decision, responding to the user's feedback on the target fault handling decision on the preset user interaction page, optimizing the target fault handling decision, and setting the user interaction page so that the operation and maintenance personnel can quickly obtain the target fault handling decision, simplify the decision-making process, improve the decision-making efficiency, optimize the target fault handling decision through user feedback, and improve the system availability and user satisfaction. In summary, the present invention predicts faults in advance, evaluates the impact of faults from multiple dimensions, combines the evaluation results with the cost-effectiveness of fault handling, determines the target fault handling decision for power station equipment, and then optimizes the target fault handling decision through users, which not only reduces operation and maintenance costs and improves fault handling efficiency, but also improves the availability and reliability of the power station and enhances user satisfaction.

[0204] The present invention also provides an electronic device, such as Figure 8 As shown, it includes a processor 301, a communication interface 302, a memory 303 and a communication bus 304, wherein the processor 301, the communication interface 302, and the memory 303 communicate with each other through the communication bus 304.

[0205] Memory 303, used for storing computer programs;

[0206] The processor 301 is used to execute the program stored in the memory 303 to implement the following steps:

[0207] Obtain real-time operating parameters of power station equipment;

[0208] Performing fault prediction on the real-time operating parameters to obtain the predicted fault type and predicted fault occurrence time of the power station equipment;

[0209] Performing a multi-dimensional impact assessment on the predicted fault type to obtain a multi-dimensional impact result on the power station equipment;

[0210] Performing a dynamic cost analysis on the power station equipment according to the predicted fault type and the predicted fault occurrence time point to obtain a predicted repair cost of the power station equipment;

[0211] Determining a target fault handling decision for the power plant equipment based on the multi-dimensional impact results and the predicted repair cost;

[0212] In response to feedback from a user on the target fault handling decision on a preset user interaction page, the target fault handling decision is optimized.

[0213] The communication bus mentioned in the above terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into a physical address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is used in the figure, but it does not mean that there is only one bus or one type of bus.

[0214] The communication interface is used for communication between the above terminal and other devices.

[0215] The memory may include a random access memory (RAM) or a non-volatile memory, such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0216] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0217] The present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps in the fault handling method described in any of the above embodiments of the present invention are implemented.

[0218] The present invention further provides a computer program product, comprising a computer program / instruction, wherein when the computer program / instruction is executed by a processor, the steps in the fault handling method as described in any of the above embodiments of the present invention are implemented.

[0219] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0220] The algorithm and display provided herein are not inherently related to any particular computer, virtual system or other equipment. According to the above description, it is obvious that the structure required for constructing such a system is. In addition, the present invention is not directed to any specific programming language either. It should be understood that various programming languages ​​can be utilized to realize the content of the present invention described herein, and the description of the above specific language is for disclosing the best mode of the present invention.

[0221] In the description provided herein, a large number of specific details are described. However, it is understood that embodiments of the present invention can be practiced without these specific details. In some instances, well-known methods, structures and techniques are not shown in detail so as not to obscure the understanding of this description.

[0222] Similarly, it should be understood that in order to streamline the present invention and aid in understanding one or more of the various inventive aspects, in the above description of exemplary embodiments of the present invention, various features of the present invention are sometimes grouped together into a single embodiment, figure, or description thereof. However, this disclosed method should not be interpreted as reflecting the following intention: that the claimed invention requires more features than those expressly recited in each claim. Rather, as reflected in the claims below, inventive aspects lie in less than all of the features of the individual embodiments disclosed above. Therefore, the claims that follow the detailed description are hereby expressly incorporated into the detailed description, with each claim itself serving as a separate embodiment of the present invention.

[0223] Those skilled in the art will appreciate that the modules in the devices in the embodiments may be adaptively changed and arranged in one or more devices different from the embodiments. The modules or units or components in the embodiments may be combined into one module or unit or component, and in addition they may be divided into a plurality of submodules or subunits or subcomponents. Except that at least some of such features and / or processes or units are mutually exclusive, all features disclosed in this specification (including the accompanying claims, abstracts and drawings) and all processes or units of any method or device disclosed in this manner may be combined in any combination. Unless otherwise expressly stated, each feature disclosed in this specification (including the accompanying claims, abstracts and drawings) may be replaced by an alternative feature providing the same, equivalent or similar purpose.

[0224] The various component embodiments of the present invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It should be understood by those skilled in the art that a microprocessor or digital signal processor (DSP) may be used in practice to implement some or all of the functions of some or all of the components in the sorting device according to the present invention. The present invention may also be implemented as a device or apparatus program for executing part or all of the methods described herein. Such a program for implementing the present invention may be stored on a computer-readable medium, or may be in the form of one or more signals. Such a signal may be downloaded from an Internet website, or provided on a carrier signal, or provided in any other form.

[0225] It should be noted that the above embodiments illustrate the present invention rather than limit it, and that those skilled in the art may devise alternative embodiments without departing from the scope of the appended claims. In the claims, any reference symbol between brackets shall not be construed as a limitation on the claims. The word "comprising" does not exclude the presence of elements or steps not listed in the claims. The word "one" or "an" preceding an element does not exclude the presence of a plurality of such elements. The present invention may be implemented by means of hardware comprising a number of different elements and by means of a suitably programmed computer. In a unit claim enumerating a number of devices, several of these devices may be embodied by the same hardware item. The use of the words first, second, and third, etc., does not indicate any order. These words may be interpreted as names.

[0226] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0227] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

[0228] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0229] It should be noted that the various data-related processes in the embodiments of the present invention are all carried out in compliance with the corresponding data protection laws and policies of the country where the device is located and with the authorization given by the corresponding device owner.

Claims

1. A fault handling method, the method comprising: Obtain real-time operating parameters of power station equipment; Performing fault prediction on the real-time operating parameters to obtain the predicted fault type and predicted fault occurrence time of the power station equipment; Performing a multi-dimensional impact assessment on the predicted fault type to obtain a multi-dimensional impact result on the power station equipment; Performing a dynamic cost analysis on the power station equipment according to the predicted fault type and the predicted fault occurrence time point to obtain a predicted repair cost of the power station equipment; Determining a target fault handling decision for the power plant equipment based on the multi-dimensional impact results and the predicted repair cost; In response to feedback from a user on the target fault handling decision on a preset user interaction page, the target fault handling decision is optimized.

2. The method according to claim 1, characterized in that: The performing fault prediction on the real-time operating parameters to obtain the predicted fault type and predicted fault occurrence time of the power station equipment includes: Collecting historical data of the power station equipment, the historical data including historical operating parameters of the power station equipment, historical fault occurrence time points and historical fault types; Pre-training the autoregressive integrated moving average model and the deep learning model respectively through the historical data; Inputting the real-time operating parameters into the pre-trained autoregressive integrated moving average model to obtain a predicted fault occurrence time point for the power station equipment; The real-time operating parameters are input into the pre-trained deep learning model to obtain the predicted fault type of the power station equipment.

3. The method according to claim 1, characterized in that: The performing fault prediction on the real-time operating parameters to obtain the predicted fault type and predicted fault occurrence time of the power station equipment includes: Performing fault prediction on the real-time operating parameters to obtain a number of predicted operating parameters of the power station equipment within a preset time period; If any of the predicted operating parameters is greater than or equal to a preset fault threshold, obtaining the first power station equipment, target parameter type and target time point corresponding to the predicted operating parameter; Obtaining a predicted fault type and a predicted fault occurrence time point of the power station equipment through the first power station equipment, the target parameter type and the target time point; If some of the predicted operating parameters are less than preset fault thresholds, it is determined that there is no risk of failure of the power station equipment within a preset time period.

4. The method according to claim 1, characterized in that: The performing a multi-dimensional impact assessment on the predicted fault type to obtain a multi-dimensional impact result on the power station equipment includes: Predetermining different impact dimensions related to the predicted fault type assessment, the impact dimensions including economic impact dimensions, environmental impact dimensions, and social impact dimensions; Set different weights and evaluation indicators for different impact dimensions; The single-dimension impact results and the comprehensive-dimension impact results of different impact dimensions on the power station equipment are determined by using the weights and the evaluation indexes.

5. The method according to claim 1, characterized in that: The performing dynamic cost analysis on the power station equipment according to the predicted fault type and the predicted fault occurrence time point to obtain the predicted repair cost of the power station equipment includes: Determining a second power station device that needs to be processed from the power station devices according to the predicted fault type; Obtaining replacement cost and maintenance cost of the second power station equipment; Determining the loss cost caused by the predicted fault type based on the predicted fault occurrence time point; The predicted repair costs of different fault repair methods for the power station equipment are obtained through the replacement cost, the maintenance cost and the loss cost, wherein the fault repair method includes replacing the power station equipment or repairing the power station equipment.

6. The method according to claim 1, characterized in that: The determining of a target fault handling decision for the power station equipment by using the multi-dimensional impact results and the predicted repair cost also includes: Obtaining a first fault handling decision on the power station equipment through the multi-dimensional impact results; Obtaining a second fault handling decision on the power station equipment through the predicted repair cost; The first fault handling decision and the second fault handling decision are screened by a preset strategy to determine a target fault handling decision for the power station equipment.

7. The method according to claim 6, characterized in that: The screening of the first fault handling decision and the second fault handling decision by a preset strategy to determine a target fault handling decision for the power station equipment includes: In the case where it is determined that any single-dimensional impact result among the multi-dimensional impact results is greater than a preset value, determining the first fault handling decision as a target fault handling decision for the power station equipment; When it is determined that a single-dimensional impact result in the multi-dimensional impact results is less than or equal to a preset value, the second fault handling decision is determined as a target fault handling decision for the power station equipment.

8. The method according to claim 1, characterized in that: The optimizing the target fault handling decision in response to the user's feedback on the target fault handling decision on a preset user interaction page also includes: Obtain information on the behavior patterns of operation and maintenance personnel; Setting a user interaction page based on the behavior pattern information; Processing the power station equipment through the target fault processing decision to obtain a processing result; The target fault processing decision is optimized based on the feedback of the target fault processing decision on the user interaction page according to the processing result.

9. The method according to claim 1, characterized in that: After optimizing the target fault handling decision in response to the user's feedback on the target fault handling decision on the preset user interaction page, the method further includes: Obtain the actual fault repair cost and actual fault handling method corresponding to the optimized target fault handling decision; The real-time operating parameters, the predicted fault type, the predicted fault occurrence time point, the actual fault repair cost and the actual fault handling method are integrated into a central database.

10. The method according to claim 1, characterized in that: The obtaining of real-time operating parameters of power station equipment includes: Deploy several different types of sensors in the power station equipment in advance; Different types of real-time operating parameters of the power station equipment are obtained through different types of sensors, wherein the real-time operating parameters include at least one of the voltage, current and temperature of the power station equipment.

11. The method according to claim 1, characterized in that: After obtaining the real-time operating parameters of the power station equipment, the method further includes: transmitting the real-time operating parameters to an edge computing device; Performing data cleaning and standardization processing on the real-time operating parameters through the edge computing device; Key features are extracted from the processed real-time operating parameters.

12. A fault handling device, characterized in that: The device comprises: A first acquisition module is used to acquire real-time operating parameters of power station equipment; A second acquisition module is used to perform fault prediction on the real-time operating parameters to obtain the predicted fault type and predicted fault occurrence time of the power station equipment; A third acquisition module is used to perform a multi-dimensional impact assessment on the predicted fault type to obtain a multi-dimensional impact result on the power station equipment; A fourth acquisition module, configured to perform a dynamic cost analysis on the power station equipment according to the predicted fault type and the predicted fault occurrence time point, to obtain a predicted repair cost of the power station equipment; A first determination module is used to determine a target fault handling decision for the power station equipment based on the multi-dimensional impact results and the predicted repair cost; The decision optimization module is used to optimize the target fault handling decision in response to the feedback of the user on the target fault handling decision on the preset user interaction page.

13. An electronic device, characterized in that: include: A transceiver, a memory, a processor, and a program stored on the memory and executable on the processor; The processor is used to read the program in the memory to implement the steps in the fault handling method as described in any one of claims 1-11.

14. A readable storage medium for storing a program, characterized in that: When the stored program is executed by the processor, the steps in the fault handling method as described in any one of claims 1 to 11 are implemented.

15. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps in the fault handling method as described in any one of claims 1-11 are implemented.

Images