Equipment running state report generation method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to an equipment running state report generation method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps of collecting equipment data of power grid equipment; inputting the equipment data into an analysis model for processing to obtain analysis data; inputting the analysis data into a fault diagnosis model for processing to obtain fault degree data of the power grid equipment; inputting the fault degree data into a leakage analysis model for processing to obtain leakage information of fluid in the power grid equipment; inputting at least one of the equipment data, the analysis data, the fault degree data or the leakage information and the environmental parameters of the environment where the power grid equipment is located into a performance prediction model for processing to obtain a performance prediction result of the power grid equipment; and generating an operation state report of the power grid equipment based on the performance prediction result and the analysis data. By adopting the method, the data calculation amount in the operation data analysis process of the power grid equipment can be reduced.

Description

Technical Field

[0001] The present application relates to the field of computer technology, and in particular to a method and apparatus for generating a device operation status report, a computer device, a computer-readable storage medium, and a computer program product. Background Art

[0002] Grid equipment refers to equipment and systems used for power transmission and distribution. They play a vital role in the power system. Among the current grid equipment, there are many heterogeneous devices. Heterogeneous devices refer to grid equipment produced by different manufacturers, running on different protocols, and supporting different functions or applications.

[0003] Analyzing and processing the operating data of heterogeneous power grid equipment is conducive to maintaining the reliability and safety of power grid equipment. At present, the operating data of distributed heterogeneous power grid equipment is obtained in real time, and then the operating status trend or fault condition of the power grid equipment is obtained based on the operating data. However, in this method, the operating status trend analysis and fault condition analysis of the power grid equipment are two independent analysis processes, and the operating data needs to be analyzed and processed separately, which increases the amount of data calculation. Summary of the invention

[0004] Based on this, it is necessary to provide a method, device, computer equipment, computer-readable storage medium and computer program product for generating equipment operation status reports that can reduce the amount of data calculation in the operation data analysis process of power grid equipment in response to the above-mentioned technical problems.

[0005] In a first aspect, the present application provides a method for generating a device operation status report, the method comprising:

[0006] Collect equipment data of power grid equipment;

[0007] Inputting the device data into an analysis model for processing to obtain analysis data;

[0008] Inputting the analysis data into a fault diagnosis model for processing to obtain fault degree data of the power grid equipment;

[0009] Inputting the fault degree data into a leakage analysis model for processing to obtain leakage information of the fluid in the power grid equipment;

[0010] Inputting the device data, the analysis data, the fault degree data or at least one of the leakage information and the environmental parameters of the environment in which the power grid device is located into a performance prediction model for processing to obtain a performance prediction result of the power grid device;

[0011] Based on the performance prediction result and the analysis data, an operation status report of the power grid equipment is generated.

[0012] In one embodiment, before inputting the device data into the analysis model for processing to obtain the analysis data, the method further includes:

[0013] Through a preset communication protocol, the device data is converted into a data format and standardized to obtain processed data.

[0014] In one embodiment, the inputting the device data into the analysis model for processing to obtain analysis data includes:

[0015] The processed data is input into the analysis model, and the processed data is numerically doubled by the analysis model to obtain the analysis data.

[0016] In one embodiment, the inputting the fault degree data into a leakage analysis model for processing to obtain leakage information of the fluid in the power grid device includes:

[0017] Obtain the distance between the leakage source and the fluid sensor, and the signal strength of the leakage signal;

[0018] The distance, the signal strength and the fault degree data are input into a leakage analysis model for processing to obtain leakage information of the fluid in the power grid equipment.

[0019] In one embodiment, the inputting the distance, the signal strength and the fault degree data into a leakage analysis model for processing to obtain leakage information of the fluid in the power grid device includes:

[0020] By using the leakage analysis model, determining whether the fault degree data is greater than a corresponding threshold value, and determining a fluid leakage indication based on the determination result, wherein the fluid leakage indication is used to indicate whether there is fluid leakage in the power grid equipment;

[0021] Determine whether the distance is less than a preset distance threshold, and obtain a distance determination result;

[0022] Determine whether the signal strength is greater than a preset signal strength threshold, and obtain a signal determination result;

[0023] Based on the fluid leakage indication, the distance judgment result and the signal judgment result, leakage information of the fluid in the power grid device is generated.

[0024] In one embodiment, generating an operation status report of the power grid device based on the performance prediction result and the analysis data includes:

[0025] Calculating statistical values ​​of the analysis data;

[0026] comparing the statistical value with the performance value in the performance prediction result;

[0027] Based on the comparison result, the operation status report is generated.

[0028] In a second aspect, the present application also provides a device for generating a device operation status report, the device comprising:

[0029] A collection module, used to collect equipment data of power grid equipment;

[0030] A first processing module, used for inputting the device data into an analysis model for processing to obtain analysis data;

[0031] A second processing module is used to input the analysis data into a fault diagnosis model for processing to obtain fault degree data of the power grid equipment;

[0032] A third processing module is used to input the fault degree data into a leakage analysis model for processing to obtain leakage information of the fluid in the power grid equipment;

[0033] A fourth processing module, used for inputting the device data, the analysis data, the fault degree data or at least one of the leakage information and the environmental parameters of the environment in which the power grid device is located into a performance prediction model for processing to obtain a performance prediction result of the power grid device;

[0034] A generation module is used to generate an operation status report of the power grid equipment based on the performance prediction result and the analysis data.

[0035] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method of each embodiment when executing the computer program.

[0036] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the steps of the method of each embodiment when executed by a processor.

[0037] In a fifth aspect, the present application also provides a computer program product, including a computer program, which implements the steps of the methods of each embodiment when executed by a processor.

[0038] The above-mentioned equipment operation status report generation method, device, computer equipment, computer-readable storage medium and computer program product, after collecting equipment data of power grid equipment, input the equipment data into the analysis model for processing to obtain analysis data, and then input the analysis data into the fault diagnosis model for processing to obtain the fault degree data of the power grid equipment, thereby realizing the fault diagnosis of the power grid equipment. The fault degree data obtained by the fault diagnosis can be input into the leakage analysis model for processing to obtain the leakage information of the fluid in the power grid equipment. It can be seen that the fault diagnosis result data can be used for fluid leakage analysis, and then the equipment data, analysis data, fault degree data or at least one of the leakage information and the environmental parameters of the environment in which the power grid equipment is located are input into the performance prediction model for processing to obtain the performance prediction result of the power grid equipment. It can be seen that the equipment data, analysis data and the data generated during the fault diagnosis and leakage analysis can be used for the performance prediction result of the power grid equipment. Therefore, the present application forms an interrelated and collaborative progressive algorithm process, which can simultaneously perform analysis processes such as operation status trend analysis, leakage analysis and fault condition analysis of the power grid equipment, and reduce the amount of data calculation in the operation data analysis process of the power grid equipment through the progressive algorithm process. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0040] Figure 1 A schematic diagram of a flow chart of a method for generating a device operation status report in one embodiment;

[0041] Figure 2 A schematic diagram of a scenario of a method for generating a device operation status report in an embodiment;

[0042] Figure 3 A schematic diagram of a scenario of a method for generating a device operation status report in another embodiment;

[0043] Figure 4 A schematic diagram of a scenario of a method for generating a device operation status report in another embodiment;

[0044] Figure 5 It is a structural block diagram of a device for generating a report on equipment operation status in one embodiment;

[0045] Figure 6 This is a structural block diagram of a computer device. DETAILED DESCRIPTION

[0046] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0047] The existing solutions still have the following defects:

[0048] In current power grid equipment, there are differences in communication protocols and interface standards for heterogeneous devices, which results in the inability of devices to communicate and share data normally;

[0049] The existing data collection and transmission methods have problems with data accuracy. In addition, equipment errors and troubleshooting mainly rely on manual inspections and manual troubleshooting, which are inefficient and need to be improved in accuracy.

[0050] In addition, there are difficulties in leak detection and location for equipment involving liquids or gases. Existing methods have limitations in calculating equipment operating conditions and predicting future performance, and the prediction results are not accurate enough.

[0051] The generated results and reports lack intuitive display and decision-making support information, making it difficult for users or managers to understand the operation of the equipment and make reasonable decisions.

[0052] In one embodiment, Figure 1 As shown, a device operation status report generation is provided. This embodiment takes the method applied to a terminal as an example. It can be understood that the method can also be applied to a server, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes the following steps:

[0053] Step 102: Collect equipment data of power grid equipment;

[0054] The data collected from the power grid equipment includes sensor data of the power grid equipment or terminal data collected by the interface and at least one of equipment status, power consumption, humidity, temperature, flow rate, or medium propagation power speed;

[0055] Step 104: input the device data into the analysis model for processing to obtain analysis data;

[0056] The analytical model is used to monitor and analyze the received data in real time.

[0057] Step 106: Input the analysis data into the fault diagnosis model for processing to obtain fault degree data of the power grid equipment;

[0058] The fault diagnosis model is used to determine whether there is a fault in the power grid equipment and the extent of the fault.

[0059] Step 108: Input the fault degree data into the leakage analysis model for processing to obtain leakage information of the fluid in the power grid equipment;

[0060] In this embodiment, the fluid includes gas and / or liquid.

[0061] Step 110: inputting at least one of the equipment data, analysis data, fault degree data or leakage information and environmental parameters of the environment in which the power grid equipment is located into the performance prediction model for processing to obtain a performance prediction result of the power grid equipment;

[0062] Equipment data, analysis data, fault severity data and leakage information are integrated together as historical processing data. At least one of the equipment data, analysis data, fault severity data or leakage information can be selected from the historical processing data, and performance prediction results of the power grid equipment can be obtained based on the at least one selected data and environmental parameters of the environment in which the power grid equipment is located.

[0063] Step 122: Generate an operation status report of the power grid equipment based on the performance prediction results and analysis data.

[0064] In this embodiment, after collecting the equipment data of the power grid equipment, the equipment data is input into the analysis model for processing to obtain the analysis data, and then the analysis data is input into the fault diagnosis model for processing to obtain the fault degree data of the power grid equipment, thereby realizing the fault diagnosis of the power grid equipment. The fault degree data obtained by the fault diagnosis can be input into the leakage analysis model for processing to obtain the leakage information of the fluid in the power grid equipment. It can be seen that the fault diagnosis result data can be used for fluid leakage analysis, and then the equipment data, analysis data, fault degree data or at least one of the leakage information and the environmental parameters of the environment in which the power grid equipment is located are input into the performance prediction model for processing to obtain the performance prediction result of the power grid equipment. It can be seen that the equipment data, analysis data and the data generated during the fault diagnosis and leakage analysis can be used for the performance prediction result of the power grid equipment. Therefore, the present application forms an interrelated and collaborative progressive algorithm process, which can simultaneously perform analysis processes such as operation status trend analysis, leakage analysis and fault condition analysis of the power grid equipment, and reduces the amount of data calculation in the operation data analysis process of the power grid equipment through the progressive algorithm process.

[0065] Specifically, the calculation formula used in the above steps is:

[0066] For step 102, Data_in = f(Device)

[0067] Convert the equipment data (input data Data_in) of the power grid equipment into a unified format as input for subsequent steps;

[0068] For step 104, Data_processed = g(Data_in)

[0069] Use the processed data in the previous step (i.e., analysis data Data_processed) as the input of the analysis model to perform data monitoring and analysis;

[0070] For step 106, Model_errors_faults = h(Data_processed)

[0071] Use the data processed in the previous step to input the fault diagnosis model for anomaly detection and fault diagnosis to obtain fault degree data (corresponding to model error fault Model_errors_faults);

[0072] For step 108, Leak_detection_location = i(Model_errors_faults)

[0073] In automatic anomaly detection and fault diagnosis, the fault degree data is input into the leakage analysis model to detect and locate the leakage, and the leakage information is obtained, including the leakage detection location Leak_detection_location;

[0074] For step 110:

[0075] Performance_prediction=j(Historical_data, Environment_parameters)

[0076] Based on the historical processing data (Historical_data) and environmental parameters (Environment_parameters) of the equipment, an accurate performance prediction model is established using the time series analysis method to predict the operating conditions and future performance of the equipment and obtain the performance prediction results (Performance_prediction);

[0077] Corresponding to step 112:

[0078] Decision_support_info=k(Data_processed,Performance_prediction)

[0079] Process and display analytical data and performance prediction results to generate decision support visualization results and reports (decision_support_info);

[0080] The output of each step serves as the input of the next step, forming a progressive algorithmic process that is interconnected and works in coordination;

[0081] The functions or methods used in each step are the process of converting input data into output data. These functions or methods are predefined mathematical models, algorithms, conversion rules and data processing techniques. In a given situation, the letters f, g, h, i, j and k are used to represent the conversion functions in each step.

[0082] The following is a detailed description of the device operation status report generation method of the present application:

[0083] Specifically, in step 104, the device data is input into the analysis model for processing. Before obtaining the analysis data, the method further includes: performing data format conversion and standardization processing on the device data through a preset communication protocol to obtain processed data.

[0084] An adapter or gateway is used to convert the communication protocol of the power grid equipment into a unified preset communication protocol, which may be the message queuing telemetry transport (MQTT) protocol. The adapter or gateway is responsible for receiving data from the power grid equipment and encapsulating and forwarding it according to the specifications of the MQTT protocol.

[0085] The device data is converted into a data format through the preset communication protocol, specifically:

[0086] The calculation formula is: Data_in=f(Device), where Data_in is the input data and f() is the conversion function, which converts the device data into input data in a unified format;

[0087] Data format conversion includes unit conversion. Standardization of device data includes value range adjustment and outlier processing.

[0088] This application utilizes Internet of Things technology and the MQTT protocol to achieve seamless integration and interconnection of heterogeneous devices and unify the data formats of heterogeneous devices.

[0089] The specific implementation process of the above step 104 is as follows:

[0090] In one embodiment, the analysis data is input into a fault diagnosis model for processing to obtain fault degree data of the power grid equipment, specifically including: inputting the processed data into the analysis model, and numerically doubling the processed data through the analysis model to obtain the analysis data.

[0091] The processed data is transmitted through the message queue to ensure the accuracy and stability of data transmission; a data receiving module and a storage module are established in the analysis model, and the data receiving module is used to receive data from the message queue; the storage module is used to receive and store data from the message queue and store data in the analysis model processing process and the processing result data.

[0092] After receiving the data from the message queue, perform preprocessing such as data cleaning, denoising, and anomaly detection to obtain preprocessed data;

[0093] The preprocessed data is input into the analysis model, and the analysis model performs numerical doubling processing on the preprocessed data to obtain analysis data, wherein the numerical doubling processing refers to doubling the numerical value of the preprocessed data.

[0094] The calculation formula is: Data_processed = g(Data_in), where Data_processed is the analysis data, and g() is the numerical doubling process corresponding to the analysis model, which can double the value of the input data;

[0095] For example, a set of initial input data Data_in is preset, which contains the following sample data:

[0096] Data_in=[10,15,12,18,20]

[0097] Use the formula Data_processed=g(Data_in) for real-time monitoring and analysis. g() is a simple doubling function, which multiplies each value in the input data by 2. Then Data_processed=g(Data_in)=[20,30,24,36,40].

[0098] According to the preset formula and sample data, the analyzed data Data_processed is obtained, which is the result obtained by doubling each value in the initial input data Data_in. During the data analysis process, the initial input data is monitored and processed in real time, and the data is doubled according to the preset processing method in order to achieve the purpose of adjusting the scale of the data or transforming the data form. Data_processed is provided to the fault diagnosis model for fault diagnosis.

[0099] This application monitors and analyzes equipment data to help promptly detect abnormalities or failures in the equipment's operating status and take measures to repair or prevent them, thereby improving the stability and reliability of the equipment.

[0100] The specific implementation of the above step 106 is as follows:

[0101] Use historical equipment data to train machine learning algorithms such as support vector machines or random forests to build fault diagnosis models;

[0102] In the process of training the fault diagnosis model, when selecting historical equipment data, the following conditions need to be met: the historical equipment data is greater than the data quality threshold, the historical equipment data covers a time range of at least 6 months, and the data integrity reaches more than 90%. Data integrity can characterize whether the historical equipment data has missing values, whether the data has errors or abnormal values, and whether the completeness of the data records is recorded;

[0103] The threshold of the fault degree data is set to T; if the fault degree data (i.e., Model_errors_faults)>T, it indicates that there is an abnormality or fault; if the fault degree data<T, it indicates that it is normal;

[0104] At the same time, set the following rules to determine the severity and type of the fault:

[0105] If the fault degree data is less than 0.3, it means it is normal; if 0.3 is less than or equal to the fault degree data less than 0.7, it means there is a slight abnormality; if 0.7 is less than or equal to the fault degree data less than 0.9, it means there is a moderate abnormality; if the fault degree data is greater than or equal to 0.9, it means there is a serious fault.

[0106] One scenario is: the analysis data is [0.6, 0.8, 0.75], these data are substituted into the formula Model_errors_faults=h(Data_processed) for calculation, and the preset calculated Model_errors_faults value is 0.65.

[0107] Classify and judge based on preset thresholds and rules: Verify the quality threshold of historical equipment data: the historical data coverage time range is at least 6 months; the data integrity reaches more than 90%;

[0108] Verify the model output threshold: set the threshold T = 0.7, 0.65 is less than the threshold T, which is considered normal;

[0109] Verify the abnormality and fault type rules: Classify and judge according to the preset rules. Because 0.65 is greater than 0.3 and less than 0.7, it is judged that there is a slight abnormality.

[0110] It should be noted that the specific threshold T and the threshold settings for the severity and type of faults should be adjusted based on the actual data and the definition of the modeling function h();

[0111] Data accuracy is ensured by transmitting data through message queues. This application uses machine learning algorithms to establish fault diagnosis models. With these models, it can respond quickly when equipment abnormalities or failures occur, and take corrective measures to reduce downtime and production losses, thereby improving the efficiency and accuracy of fault diagnosis.

[0112] The specific implementation process of the above step 108 is as follows:

[0113] In one embodiment, the fault degree data is input into the leakage analysis model for processing to obtain the leakage information of the fluid in the power grid equipment, including: obtaining the distance between the leakage source location and the fluid sensor, and the signal strength of the leakage signal; inputting the distance, signal strength and fault degree data into the leakage analysis model for processing to obtain the leakage information of the fluid in the power grid equipment.

[0114] Use machine learning algorithms to train and model sensor data to establish leak detection and positioning models; sensor data includes historically collected gas sensor data and sound sensor data.

[0115] In this embodiment, the equipment data includes gas sensor data and sound sensor data around the power grid equipment obtained by sound sensors and gas sensors. The real-time monitored gas sensor data and sound sensor data are input into the analysis model for processing. After the analysis data is obtained, the analysis data is input into the fault diagnosis model for processing. After the fault degree data is obtained, the fault degree data is input into the leakage analysis model, and the fault degree data is processed according to the following calculation formula:

[0116] Calculation formula: Leak_detection_location=i(Model_errors_faults), Leak_detection_location is the leakage information, and i() is the detection and positioning function.

[0117] Specific:

[0118] Data collection uses sound sensor and gas sensor technology to obtain gas sensor data and sound sensor data of power grid equipment. The sound sensor data includes sound characteristics, and the gas sensor data includes gas concentration.

[0119] Data preprocessing: preprocessing the collected sensor data (sensor data includes gas sensor data and sound sensor data), including denoising, filtering, standardization and other processing;

[0120] During model training, the pre-processed sensor data is trained and modeled using a machine learning algorithm to establish a leakage analysis model, using one or more machine learning algorithms, such as a support vector machine, a random forest, or a neural network;

[0121] When the model is applied, the distance (distance) between the leakage source and the fluid sensor and the signal strength (signal_strength) of the leakage signal are obtained, and the distance, signal strength and fault degree data are input into the leakage analysis model for processing. The corresponding processing formula when the leakage analysis model is processing is Leak_detection_location=i(Model_errors_faults, distance, signal_strength), and the leakage information is obtained.

[0122] In this embodiment, the leakage source refers to the location source where the fluid leakage occurs in the power grid equipment.

[0123] This application combines sound sensor and gas sensor technology to detect and locate leaks in the environment around the equipment, helping to quickly detect leaks and accurately locate the source of leaks. By taking timely measures to repair leaks, safety risks are reduced, resource waste is reduced, and the environment is protected;

[0124] In one of the embodiments, the distance, signal strength and fault degree data are input into a leakage analysis model for processing to obtain leakage information of the fluid in the power grid equipment, including: judging whether the fault degree data is greater than a corresponding threshold through the leakage analysis model, and determining a fluid leakage indication based on the judgment result, the fluid leakage indication is used to indicate whether there is fluid leakage in the power grid equipment; judging whether the distance is less than a preset distance threshold to obtain a distance judgment result; judging whether the signal strength is greater than a preset signal strength threshold to obtain a signal judgment result; and generating leakage information of the fluid in the power grid equipment based on the fluid leakage indication, the distance judgment result and the signal judgment result.

[0125] In this embodiment, the threshold of the fault degree data is set to A, which may be 0.6;

[0126] If the fault degree data is greater than A, it means there is a leak and the next step is carried out; if the fault degree data is less than A, it means there is no leak and the processing flow is terminated;

[0127] Set a minimum distance threshold B, which can be 5 meters. If the distance is less than B, the distance judgment result is that the leak position can be located, otherwise the distance judgment result is that the leak position cannot be located;

[0128] The signal strength threshold is set to C, which may be -50 dBm. If signal_strength is greater than C, the signal judgment result is that there is a leakage signal. Otherwise, the signal judgment result is that there is no leakage signal.

[0129] The specific implementation process of the above step 110 is as follows:

[0130] Collect historical equipment data and environmental parameters of the equipment and use time series analysis methods to establish accurate performance prediction models;

[0131] Input historical processing data and environmental parameters into the performance prediction model for processing, and calculate the operating conditions through the performance prediction model;

[0132] The relevant formula is:

[0133] Performance_prediction=j(Historical_data,Environment_parameters);

[0134] Among them, Performance_prediction is the equipment performance prediction result, j() is the prediction function, which trains and predicts the equipment's operating conditions and future performance based on historical data and environmental parameters;

[0135] Among them, historical processing data includes:

[0136] The output of step 102 is Data_in=[10,15,12,18,20], the output of step 104 is Data_processed=[0.6,0.8,0.75], the output of step 106 is Model_errors_faults, the input of step 108 is distance and signal_strength, and the environmental parameters (the environmental parameters include the ambient temperature and the ambient humidity) and the leakage information.

[0137] Select some data in the historical processing data, for example, select Data_in=[10,15,12,18,20], prepare the environmental parameters, the ambient temperature is 25°C and the ambient humidity is 60%;

[0138] The selected part of the data and environmental parameters are passed into the LSTM model for prediction to obtain the performance prediction results.

[0139] This application uses time series analysis methods to predict the operating conditions and future performance of equipment, develop better maintenance plans and scheduling strategies, improve the accuracy of prediction results, and identify potential problems in advance, reduce equipment failures and downtime, and improve equipment reliability and production efficiency.

[0140] The specific implementation process of the above step 112 is:

[0141] In one embodiment, an operation status report of a power grid device is generated based on performance prediction results and analysis data, including: calculating a statistical value of the analysis data; comparing the average value with the performance value in the performance prediction results; and generating an operation status report based on the comparison result.

[0142] In one scenario, the analysis data is Data_processed=[0.6,0.8,0.75], and the performance prediction result is Performance_prediction=0.85;

[0143] According to the formula Decision_support_info=k(Data_processed,Performance_prediction), the statistical value is compared with the performance value in the performance prediction result, which specifically includes the following steps:

[0144] The values ​​of Data_processed are extracted as 0.6, 0.8, and 0.75; the value of Performance_prediction is extracted as 0.85; the extracted data is further processed and processed, such as associating with other data, calculating indicators, and generating summary statistics;

[0145] The average value of Data_processed is calculated and compared with Performance_prediction to obtain decision support information, thereby generating an operation status report based on the decision support information.

[0146] In this example, the calculation is as follows: (0.6+0.8+0.75) divided by 3 = 0.7167, and 0.7167 is compared with 0.85 to obtain decision support information.

[0147] This application can process and handle data and present decision support information in a visual way, so that managers and operators can intuitively understand the equipment's operating conditions, performance forecasts and related decision support information. With this information, they can make accurate decisions, optimize equipment maintenance and production plans, and improve resource utilization efficiency and economic benefits.

[0148] For fault diagnosis scenarios, leakage analysis scenarios, or device performance prediction scenarios, possible implementation methods of this application are as follows:

[0149] A possible scenario A, in which the present application is implemented in the anomaly detection and fault diagnosis scenario, is as follows:

[0150] Step A1: Collecting equipment data of power grid equipment;

[0151] Collect historical data of the equipment, including operating status, performance indicators, etc. The preset historical data is Data_in=[10,15,12,18,20];

[0152] Step A2: input the equipment data into the analysis model for processing to obtain analysis data;

[0153] Input Data_in to the real-time data processing platform for data monitoring and analysis; Data cleaning and preprocessing: De-noising and filtering steps are performed on Data_in, and the processed data is preset as Data_processed=[0.6,0.8,0.75];

[0154] Step A3: input the analysis data into the fault diagnosis model for processing to obtain the fault degree data of the power grid equipment;

[0155] Step A3: Train the error and failure model using machine learning algorithms;

[0156] Prepare historical data: use Data_processed as input for training data;

[0157] Prepare label data: Prepare label data based on known device abnormality and fault information, for example, [0,1,0] represents normal, abnormal, and normal;

[0158] Train error and failure models: Use machine learning algorithms (such as support vector machines or random forests) to train on Data_processed and labeled data;

[0159] Model output: The default model output is Model_errors_faults=0.63;

[0160] Determine abnormalities and faults based on thresholds:

[0161] Threshold setting: Set the threshold T=0.7 to determine the severity of the abnormality or fault;

[0162] Judgment calculation: compare Model_errors_faults with the threshold T;

[0163] Result: According to the calculation results, if Model_errors_faults is greater than T, it means there is an abnormality or fault; otherwise, it is considered normal;

[0164] Through the above calculations, it is concluded that there is a slight abnormality in the equipment;

[0165] Another possible scenario B, in the scenario of leakage analysis, is implemented as follows:

[0166] Step B1, collecting the spectral data of the environment around the device, including sound characteristics and gas concentration, using sound sensors and gas sensors to obtain data;

[0167] Step B2, inputting the environmental wave spectrum data into the analysis model for data monitoring and analysis;

[0168] Data cleaning and preprocessing: Filter and denoise the collected sound and gas data to remove background noise and extract effective signals;

[0169] The preprocessed data is input into the analysis model for processing to obtain analysis data.

[0170] Step B3: Use sound sensor and gas sensor technology to train and model sensor data to establish a leak detection and positioning model;

[0171] The leak detection and location model is the leak analysis model mentioned above.

[0172] Training data preparation: The preprocessed sound and gas data are used as the input of training data, and the known leakage events are marked as positive examples, and the non-leakage events are marked as negative examples;

[0173] Feature engineering: Extract useful features from sound and gas data, such as spectrum features, time domain features, and energy features, for training models.

[0174] Model training: Use machine learning algorithms (such as support vector machines, random forests, or neural networks) to train and build models on the prepared training data;

[0175] Model application: Input the real-time collected sound and gas data into the trained model for leak detection and location;

[0176] Judgment condition: judge according to the result of model output. For example, set the threshold T=0.5. If the model output is greater than the threshold T, it is considered that there is a leak.

[0177] Specific calculation process:

[0178] The preset sound data collected is sound_data=[0.8,0.9,0.75,0.6];

[0179] The preset collected gas data is gas_data=[0.5,0.6,0.7,0.8];

[0180] Preprocess and extract features of sound data and gas data to obtain the processed feature vector feature_vector=[0.85,0.82];

[0181] Use labeled training data to train the model and obtain a classifier;

[0182] Input the feature vector collected in real time into the trained model and get the model output leak_detection_location=0.65;

[0183] According to the judgment condition, if leak_detection_location is greater than the threshold T=0.5, it is considered that there is a leak;

[0184] Through the above calculation, we can conclude that if the model output leak_detection_location is greater than the threshold T, it means there is a leak. The leak location is determined based on the specific leak_detection_location value.

[0185] Another possible scenario C, in the scenario of performance prediction, is implemented as follows:

[0186] Step C1: Collect historical equipment data and environmental parameters of the equipment. The historical equipment data includes equipment operation status and performance indicators, and the environmental parameters include temperature and humidity.

[0187] Step C2: inputting historical equipment data and environmental parameters into the performance prediction model to be trained, and training the performance prediction model to predict the performance of the power grid equipment;

[0188] Data preparation: Take device data and environmental parameters as input, where the device data needs to be normalized or standardized;

[0189] Model selection and training: Select appropriate time series analysis methods (such as ARIMA, LSTM), and use training data for model training;

[0190] Model validation and tuning: Use validation data to validate the model and perform tuning based on the validation results to improve the model’s predictive performance;

[0191] Model application and prediction: Input the current equipment operating conditions and environmental parameters into the trained model and use the model to predict equipment performance;

[0192] Judgment conditions: Determine the equipment performance status by comparing the performance prediction value output by the model with the threshold;

[0193] Specific calculation process:

[0194] The preset collected device data is performance_data=[0.75,0.8,0.85,0.9];

[0195] The preset collected environment parameters are environment_data=[25,28,26,27];

[0196] Preprocess and extract features of device data and environmental parameters to obtain the processed feature vector feature_vector=[0.82,26.5];

[0197] Use the training data to train the model and obtain a time series analysis model;

[0198] Input the current equipment data and environmental parameters into the trained model and use the model to predict equipment performance;

[0199] Compare the performance prediction value output by the model with the threshold, for example, set the threshold T=0.8;

[0200] If the model output performance_prediction is greater than the threshold T, the device performance status is considered to be good;

[0201] If the model output performance_prediction is less than or equal to the threshold T, it is considered that the device performance needs to be further improved;

[0202] Through the above calculations, it is concluded that if the performance prediction value output by the model exceeds the preset threshold, it can be judged that the performance status of the equipment is good; otherwise, measures need to be taken to improve the performance of the equipment.

[0203] In summary, this application firstly utilizes the Internet of Things technology and the MQTT protocol to achieve seamless integration and interconnection of heterogeneous devices. Secondly, data collection and transmission utilize a real-time data processing platform to ensure the accuracy and stability of the data. At the same time, error and troubleshooting improvements apply machine learning algorithms to establish models to achieve automatic anomaly detection and fault diagnosis. In addition, leakage analysis combines sensor technology and machine learning algorithms to achieve accurate leak detection and positioning; based on historical processing data and environmental parameters, an accurate performance prediction model is established to predict the operating conditions and future performance of the equipment. Finally, the report and decision support information improvement plan utilizes data visualization tools to generate intuitive results and reports, and provide decision support information. These improvement plans and steps are interrelated, and the accuracy and efficiency of data processing are achieved through predefined conversion functions and algorithms, providing users or managers with intuitive operating status displays and decision support information.

[0204] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0205] Based on the same inventive concept, the embodiment of the present application also provides a standby operation status report generation device for implementing the standby operation status report generation method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more standby operation status report generation device embodiments provided below can refer to the limitations of the standby operation status report generation method above, and will not be repeated here.

[0206] In an exemplary embodiment, Figure 5 As shown, a device 500 for generating a device operation status report is provided, comprising:

[0207] A collection module 501 is used to collect equipment data of power grid equipment;

[0208] A first processing module 502 is used to input the device data into an analysis model for processing to obtain analysis data;

[0209] The second processing module 503 is used to input the analysis data into a fault diagnosis model for processing to obtain fault degree data of the power grid equipment;

[0210] The third processing module 504 is used to input the fault degree data into the leakage analysis model for processing to obtain leakage information of the fluid in the power grid equipment;

[0211] A fourth processing module 505 is used to input the device data, the analysis data, the fault degree data or at least one of the leakage information and the environmental parameters of the environment in which the power grid device is located into the performance prediction model for processing to obtain a performance prediction result of the power grid device;

[0212] The generating module 506 is used to generate an operating status report of the power grid device based on the performance prediction result and the analysis data.

[0213] In one embodiment, the apparatus further comprises a fourth processing module, before the second processing module inputs the device data into the analysis model for processing to obtain analysis data;

[0214] The fourth processing module is used to perform data format conversion and standardization processing on the device data through a preset communication protocol to obtain processed data.

[0215] In one embodiment, the third processing module 504 is used to input the processed data into the analysis model, and perform numerical doubling processing on the processed data through the analysis model to obtain the analysis data.

[0216] In one embodiment, the fourth processing module 505 is used to obtain the distance between the leakage source location and the fluid sensor, and the signal strength of the leakage signal; the distance, the signal strength and the fault degree data are input into the leakage analysis model for processing to obtain the leakage information of the fluid in the power grid equipment.

[0217] In one embodiment, when the fourth processing module 505 inputs the distance, the signal strength and the fault degree data into the leakage analysis model for processing to obtain the leakage information of the fluid in the power grid device, it is specifically used to:

[0218] By using the leakage analysis model, determining whether the fault degree data is greater than a corresponding threshold value, and determining a fluid leakage indication based on the determination result, wherein the fluid leakage indication is used to indicate whether there is fluid leakage in the power grid equipment;

[0219] Determine whether the distance is less than a preset distance threshold, and obtain a distance determination result;

[0220] Determine whether the signal strength is greater than a preset signal strength threshold, and obtain a signal determination result;

[0221] Based on the fluid leakage indication, the distance judgment result and the signal judgment result, leakage information of the fluid in the power grid device is generated.

[0222] In one embodiment, the generation module 506 is specifically used to calculate the statistical value of the analysis data; compare the statistical value with the performance value in the performance prediction result; and generate the operation status report based on the comparison result.

[0223] Each module in the above-mentioned device operation status report generating device can be implemented in whole or in part by software, hardware and their combination. Each of the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0224] In an exemplary embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 6 As shown. The computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected through a system bus, and the communication interface, the display unit and the input device are connected to the system bus through the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and the external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (NearField Communication, NFC) or other technologies. When the computer program is executed by the processor, a method for generating a device operation status report is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0225] Those skilled in the art will understand that Figure 6 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0226] In an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps of the method of each embodiment when executing the computer program.

[0227] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method of each embodiment are implemented.

[0228] In one embodiment, a computer program product is provided, including a computer program, which implements the steps of implementing the methods of various embodiments when executed by a processor.

[0229] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0230] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., but are not limited to this.

[0231] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0232] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for generating a device operation status report, characterized in that: The method comprises: Collect equipment data of power grid equipment; Inputting the device data into an analysis model for processing to obtain analysis data; Inputting the analysis data into a fault diagnosis model for processing to obtain fault degree data of the power grid equipment; Inputting the fault degree data into a leakage analysis model for processing to obtain leakage information of the fluid in the power grid equipment; Inputting the device data, the analysis data, the fault degree data or at least one of the leakage information and the environmental parameters of the power grid device into a performance prediction model for processing to obtain a performance prediction result of the power grid device; Based on the performance prediction result and the analysis data, an operation status report of the power grid equipment is generated.

2. The method according to claim 1, characterized in that Before inputting the device data into the analysis model for processing to obtain the analysis data, the method further includes: Through a preset communication protocol, the device data is converted into a data format and standardized to obtain processed data.

3. The method according to claim 2, characterized in that The inputting the device data into the analysis model for processing to obtain analysis data comprises: The processed data is input into the analysis model, and the processed data is numerically doubled by the analysis model to obtain the analysis data.

4. The method according to any one of claims 1 to 3, characterized in that The step of inputting the fault degree data into a leakage analysis model for processing to obtain leakage information of the fluid in the power grid equipment includes: Obtain the distance between the leakage source and the fluid sensor, and the signal strength of the leakage signal; The distance, the signal strength and the fault degree data are input into a leakage analysis model for processing to obtain leakage information of the fluid in the power grid equipment.

5. The method according to claim 4, characterized in that The step of inputting the distance, the signal strength and the fault degree data into a leakage analysis model for processing to obtain leakage information of the fluid in the power grid device includes: By using the leakage analysis model, determining whether the fault degree data is greater than a corresponding threshold value, and determining a fluid leakage indication based on the determination result, wherein the fluid leakage indication is used to indicate whether there is fluid leakage in the power grid equipment; Determine whether the distance is less than a preset distance threshold, and obtain a distance determination result; Determine whether the signal strength is greater than a preset signal strength threshold, and obtain a signal determination result; Based on the fluid leakage indication, the distance judgment result and the signal judgment result, leakage information of the fluid in the power grid device is generated.

6. The method according to any one of claims 1 to 3, characterized in that The generating the operation status report of the power grid device based on the performance prediction result and the analysis data includes: Calculating statistical values ​​of the analysis data; comparing the statistical value with the performance value in the performance prediction result; Based on the comparison result, the operation status report is generated.

7. A device for generating a report on equipment operation status, characterized in that: The device comprises: A collection module, used to collect equipment data of power grid equipment; A first processing module, used for inputting the device data into an analysis model for processing to obtain analysis data; A second processing module is used to input the analysis data into a fault diagnosis model for processing to obtain fault degree data of the power grid equipment; A third processing module is used to input the fault degree data into a leakage analysis model for processing to obtain leakage information of the fluid in the power grid equipment; A fourth processing module, used for inputting the device data, the analysis data, the fault degree data or at least one of the leakage information and the environmental parameters of the environment in which the power grid device is located into a performance prediction model for processing to obtain a performance prediction result of the power grid device; A generation module is used to generate an operation status report of the power grid equipment based on the performance prediction result and the analysis data.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images