Operation state monitoring method and device of electrical equipment, equipment, medium and product

Abstract

The invention provides an electrical equipment operation state monitoring method and device, equipment, a medium and a product. The method comprises the following steps: acquiring multiple power production data of to-be-monitored electrical equipment at any moment; importing the plurality of items of power production data into cells below columns of corresponding titles in a pre-created worksheet; respectively acquiring judgment models corresponding to the multiple items of power production data, and inputting each item of power production data into the judgment model; if the monitoring result of any item of power production data is abnormal, changing the cell where any item of power production data is located into an early warning state; and sending all the electric power production data changed into the early warning state to a monitoring platform, so that the monitoring platform displays all the electric power production data in the early warning state according to a preset warning mode. By automatically analyzing and monitoring the power production data, the accuracy and reliability of data analysis are improved, the time and resources required by manual data supervision are reduced, and the efficiency of data anomaly detection is improved.

Description

Technical Field

[0001] The present application relates to the technical field of data monitoring and processing, and in particular to a method, device, equipment, medium and product for monitoring the operating status of electrical equipment. Background Art

[0002] At present, with the rapid expansion of the renewable energy industry, not only the number of electrical equipment continues to increase, but also the power generation technology is becoming more and more diverse. This growth has brought about a huge amount of data. In order to ensure the smooth operation of electrical equipment and improve production efficiency, it is essential to monitor and manage this data in real time.

[0003] In the prior art, data is usually collected manually and manually checked offline to determine the accuracy of the data and whether there are abnormal fluctuations.

[0004] However, in the prior art, since there are many electrical devices that need to be supervised, manual data supervision will lead to inefficiency, and when processing a large number of repetitive tasks, omissions or misjudgments may occur, which will lead to an increase in the error rate. Summary of the invention

[0005] The present application provides a method, device, equipment, medium and product for monitoring the operating status of electrical equipment to solve the problem in the prior art that there is a large number of electrical equipment that needs to be supervised, which leads to inefficiency when performing data supervision manually, and omissions or misjudgments may occur when processing a large number of repetitive tasks, thereby increasing the error rate.

[0006] In a first aspect, the present application provides a method for monitoring the operating status of an electrical device, which is applied to a computer device, comprising:

[0007] Collect multiple power production data of the electrical equipment to be monitored at any time;

[0008] Importing the plurality of power production data into cells under the columns of corresponding titles in a pre-created worksheet;

[0009] respectively obtaining judgment models corresponding to the plurality of power production data;

[0010] Extracting each item of power production data from the worksheet, and inputting each item of power production data into the judgment model to obtain a monitoring result of whether each item of power production data is abnormal;

[0011] If the monitoring result of any power production data is abnormal, the cell where the power production data is located is changed to a warning state;

[0012] All power production data that have been changed to a warning state are sent to the monitoring platform, so that the monitoring platform displays all power production data in a warning state according to a preset alarm method.

[0013] Among them, the judgment model is a trained machine learning model; the training process of the machine learning model is: collecting multiple historical power production data of the electrical equipment to be monitored within any time period; selecting the model to be trained from the model database according to the data characteristics of the multiple historical power production data; cleaning and preprocessing the multiple historical power production data to obtain the processed multiple historical power production data; extracting features of the processed multiple historical power production data according to different dimensions to obtain multi-dimensional feature training data; iteratively training the model to be trained with the multi-dimensional feature training data to obtain a machine learning model.

[0014] Among them, in the process of iteratively training the model to be trained with the multi-dimensional feature training data to obtain a machine learning model, the loss function used is:

[0015]

[0016] Wherein, p is the number of samples, q is the number of elements in the network output layer, x and x′ are the predicted value and the value corresponding to the labeled result output by the model, respectively, MSE is the mean square error, MSE represents the result of the loss function, and i and j are any positive integers.

[0017] Wherein, the judgment model is a judgment function, and the judgment function is:

[0018] CONCATENATE(IFNA(IFS(OR(b1 <A1,A1<c1)AND(E1> 0,D1=0)

[0019] IFNA(IFS(OR(b2 <A2,A2<c2)

[0020] Among them, CONCATENATE(...) is a string concatenation function, IFNA(IFS(...)) is a nested IF function, and OR(...) is a logical OR operation; A1 and A2 represent any power production data value, b1 and b2 represent the maximum value allowed for any power production data value, c1 and c2 represent the minimum value allowed for any power production data value, D1 represents the number of faulty units, and E1 represents the fault time.

[0021] In one possible design, if the monitoring result of any item of power production data is an abnormality, the cell where any item of power production data is located is changed to a warning state, including: if the monitoring result of any item of power production data is an abnormality, the cell where any item of power production data is located in the worksheet is changed to a warning color; accordingly, all power production data changed to a warning state are sent to the monitoring platform so that the monitoring platform displays all power production data in a warning state according to a preset alarm method, including: the worksheet where all the power production data with all cells changed to a warning color is located is sent to the monitoring platform so that the monitoring platform displays the power production data with all cells changed to a warning color in each worksheet.

[0022] In one possible design, if the monitoring result of any item of power production data is abnormal, the cell where any item of power production data in the worksheet is located is changed to a warning color, including: obtaining the key information field of any item of power production data whose monitoring result is abnormal, wherein the key information field includes the daily maximum wind speed, the daily minimum wind speed, the daily expected power generation, tomorrow's predicted power generation and the wind / light power prediction accuracy; inputting the daily maximum wind speed, the daily minimum wind speed, the daily expected power generation, tomorrow's predicted power generation and the wind / light power prediction accuracy into a preset grade calculation formula to obtain the abnormal grade; and changing the warning color of the cell where the power production data is located according to the abnormal grade.

[0023] In one possible design, the preset grade calculation formula is as follows:

[0024] Abnormal level = h(V max ,V min ,E ex ,E pre ,Ac)

[0025] Among them, V max The highest wind speed of the day, V min The lowest wind speed of the day, E ex The daily power generation, E pre is the predicted power generation for tomorrow, AC is the wind / solar power prediction accuracy, and h is the level calculation function;

[0026]

[0027] Among them, V max,th is the threshold of the daily maximum wind speed, V min,th is the threshold of the daily minimum wind speed, E ex,th is the threshold of daily power generation, E pre,th is the threshold of tomorrow's predicted power generation, AC th is the threshold of wind / solar power prediction accuracy, and 0, 1, and 2 are abnormal levels.

[0028] In a possible design, after the daily maximum wind speed, daily minimum wind speed, daily expected power generation, tomorrow's predicted power generation and wind / light power prediction accuracy are input into a preset level calculation formula to obtain the abnormal level, it also includes: normalizing the daily maximum wind speed, daily minimum wind speed, daily expected power generation, tomorrow's predicted power generation and wind / light power prediction accuracy to obtain the normalized daily maximum wind speed, daily minimum wind speed, daily expected power generation, tomorrow's predicted power generation and wind / light power prediction accuracy; obtaining multiple operation and maintenance personnel within a preset range of electrical equipment, and obtaining personnel information of each operation and maintenance personnel, and normalizing the personnel information to obtain normalized personnel information; calculating the matching degree corresponding to each operation and maintenance personnel according to the normalized daily maximum wind speed, daily minimum wind speed, daily expected power generation, tomorrow's predicted power generation and wind / light power prediction accuracy and the normalized personnel information; determining the target operation and maintenance personnel according to the matching degree; and sending operation and maintenance instructions to the terminal of the target operation and maintenance personnel.

[0029] In a possible design, the matching degree of each operation and maintenance personnel is calculated based on the normalized daily maximum wind speed, daily minimum wind speed, daily expected power generation, tomorrow's predicted power generation and wind / solar power prediction accuracy, and the normalized personnel information. The calculation formula is:

[0030]

[0031] Among them, A is a vector in the three-dimensional space composed of the normalized daily maximum wind speed, daily minimum wind speed, daily power generation, tomorrow's predicted power generation and wind / solar power prediction accuracy, B is a vector composed of normalized personnel information, and θ is the matching degree corresponding to the operation and maintenance personnel.

[0032] In a possible design, after inputting each item of power production data into the judgment model to obtain the monitoring result of whether each item of power production data has an abnormality, it also includes: performing a secondary verification on the monitoring result using a preset verification rule to screen out the monitoring results with abnormalities and the monitoring results without abnormalities; recording the secondary verification process, the monitoring results with abnormalities and the monitoring results without abnormalities to generate a verification report; and entering the verification report into a preset log file.

[0033] In a second aspect, the present application provides an operating status monitoring device for an electrical device, which is applied to a computer device, comprising:

[0034] Collection module: used to collect multiple power production data of the electrical equipment to be monitored at any time;

[0035] Import module: used for importing the plurality of power production data into cells under the columns of corresponding titles in a pre-created worksheet;

[0036] An acquisition module: used to respectively acquire the judgment models corresponding to the plurality of power production data;

[0037] Output module: used for extracting each item of power production data from the worksheet, and inputting each item of power production data into the judgment model to obtain a monitoring result of whether each item of power production data is abnormal;

[0038] Change module: used for changing the cell where any power production data is located to a warning state if the monitoring result of any power production data is abnormal;

[0039] Sending module: used to send all power production data that have changed to a warning state to the monitoring platform, so that the monitoring platform displays all power production data in a warning state according to a preset alarm method.

[0040] In a third aspect, the present application provides a computer device, comprising: at least one processor and a memory;

[0041] The memory stores computer-executable instructions;

[0042] The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor performs the method for monitoring the operating status of the electrical equipment as described in the first aspect and various possible designs of the first aspect.

[0043] In a fourth aspect, the present application provides a computer storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the method for monitoring the operating status of an electrical device as described in the first aspect and various possible designs of the first aspect is implemented.

[0044] In a fifth aspect, the present application provides a computer program product, including a computer program. When the computer program is executed by a processor, it implements the method for monitoring the operating status of an electrical device as described in the first aspect and various possible designs of the first aspect.

[0045] The method, device, equipment, medium and product for monitoring the operating status of electrical equipment provided by the present application first collect the power production data of the electrical equipment, import it into a pre-set worksheet, and use a specific judgment model to analyze the data; if the analysis result is that abnormal data is monitored, the cell where the abnormal data is located is changed to a warning state, and all abnormal data is sent to the monitoring platform. By automatically analyzing and monitoring power production data, human errors are reduced, the accuracy and reliability of data analysis are improved, and the time and resources required for manual supervision of data are reduced, thereby improving the efficiency of data anomaly detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to 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 application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0047] Figure 1 A schematic diagram of an application scenario for monitoring the operating status of electrical equipment provided in an embodiment of the present application;

[0048] Figure 2 A flow chart of a method for monitoring the operating status of an electrical device provided in an embodiment of the present application;

[0049] Figure 3 A schematic diagram of the structure of an operating status monitoring device for electrical equipment provided in an embodiment of the present application;

[0050] Figure 4 A schematic diagram of the hardware structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0052] At present, with the rapid expansion of the renewable energy industry, the world is experiencing a new era of energy transformation, and various innovative technologies are constantly advancing and changing the face of the energy industry. The promotion and application of these technologies have brought about a huge amount of data, and it has become crucial to monitor and effectively manage these data in real time. This can not only ensure the stability of power supply and the efficient operation of electrical equipment, but also optimize maintenance plans through data analysis and prevent potential failures, thereby further improving the reliability and economy of the entire energy system. In the prior art, data is usually collected manually and manually checked offline to determine the accuracy of the data and whether there are abnormal fluctuations. However, in the prior art, due to the large number of electrical equipment that needs to be supervised, manual data supervision will lead to inefficiency, and when dealing with a large number of repetitive tasks, omissions or misjudgments may occur, which will lead to increased error rates.

[0053] In order to solve the above technical problems, the embodiments of the present application propose the following technical concepts: Considering the importance of real-time monitoring of power production data, the inventors have come up with an automated method for monitoring the operating status of electrical equipment. The method first uses a preset worksheet and judgment model to analyze and monitor multiple power production data of electrical equipment, automatically identifies and marks abnormal monitoring results; by changing the cell where the abnormal power production data is located to a warning state and sending it to the monitoring platform, the alarm and display of the operating status of the electrical equipment become rapid and intuitive. The following is a detailed description using a detailed embodiment.

[0054] Figure 1 Schematic diagram of application scenario of operating status monitoring of electrical equipment provided in the embodiment of the present application. Figure 1 As shown, the scenario includes: a computer device 101 and a monitoring platform 102 .

[0055] It is understandable that the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the object identification method. In other feasible implementations of the present application, the above architecture may include more or fewer components than shown in the figure, or combine certain components, or split certain components, or arrange the components differently, which can be determined according to the actual application scenario and is not limited here. Figure 1 The components shown may be implemented in hardware, software, or a combination of software and hardware.

[0056] In a specific implementation process, the computer device 101 can be used to obtain power production data, and analyze and monitor the data to obtain a monitoring result of whether each power production data has an abnormality.

[0057] Monitoring platform 102: can be used to receive monitoring results of whether each power production data sent by computer device 101 has abnormalities, and display them in a preset alarm manner.

[0058] In addition, the network architecture and business scenarios described in the embodiments of the present application are intended to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided in the embodiments of the present application. Ordinary technicians in this field can know that with the evolution of network architecture and the emergence of new business scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0059] based on Figure 1 In the application scenario, the embodiment of the present application provides a method for monitoring the operating status of an electrical device, and the execution subject can be Figure 1 The computer device shown is not particularly limited in this embodiment. Figure 2 A flow chart of a method for monitoring the operating status of an electrical device provided in an embodiment of the present application is shown in FIG. Figure 2 As shown, the method includes:

[0060] S201: Collect multiple power production data of the electrical equipment to be monitored at any time.

[0061] Among them, multiple power production data refer to various data that need to be monitored during the production process of electrical equipment, which may include but are not limited to voltage, current, power, temperature, pressure and / or frequency.

[0062] S202: Import multiple pieces of power production data into cells under columns of corresponding titles in a pre-created worksheet.

[0063] Among them, the pre-created worksheet refers to a pre-set spreadsheet document, which usually has a series of column headers corresponding to different types of electricity production data.

[0064] S203: Obtain judgment models corresponding to a plurality of power production data respectively.

[0065] Among them, the judgment model can be a statistical model, a machine learning model, a threshold model, a state estimation model and / or a trend analysis model.

[0066] When the judgment model is a judgment function, the judgment function is specifically:

[0067] CONCATENATE(IFNA(IFS(OR(b1 <A1,A1<c1)AND(E1> 0,D1=0)

[0068] IFNA(IFS(OR(b2 <A2,A2<c2)

[0069] Among them, CONCATENATE(...) is a string concatenation function, IFNA(IFS(...)) is a nested IF function, and OR(...) is a logical OR operation; A1 and A2 represent any power production data value, b1 and b2 represent the maximum value allowed for any power production data value, c1 and c2 represent the minimum value allowed for any power production data value, D1 represents the number of faulty units, and E1 represents the fault time.

[0070] S204: extracting each item of power production data from the worksheet, and inputting each item of power production data into the judgment model to obtain a monitoring result of whether each item of power production data has an abnormality.

[0071] The test results include normal and abnormal results. Normal results indicate that the analyzed power production data falls within the expected range, no deviation or abnormal behavior is found, and the production process meets the standards and expectations; abnormal results indicate that the analyzed power production data is significantly different from the expected results, and there may be potential problems, failures or performance degradation.

[0072] Among them, when the "ambient temperature" value A1>b1, or A1<c1 of any electrical equipment, the monitoring result of abnormal "ambient temperature" of any electrical equipment is output; when the "number of faults" value D1=0 of any electrical equipment, and the "fault time" E1>0, the monitoring result of abnormal "number of faults" of any electrical equipment is output; when the "power generation" value A2>b2, or A2<c2 of any electrical equipment, the monitoring result of abnormal "power generation" of any electrical equipment is output.

[0073] S205: If the monitoring result of any item of power production data is abnormal, the cell where the any item of power production data is located is changed to a warning state.

[0074] Among them, S205 specifically includes:

[0075] If the monitoring result of any power production data is abnormal, the cell where any power production data is located in the worksheet will be changed to a warning color.

[0076] Among them, the warning color refers to a specific color used to visually identify abnormal data. Usually, the warning color will be selected from some eye-catching colors, such as red, yellow or orange.

[0077] S206: Send all power production data that have been changed to a warning state to the monitoring platform, so that the monitoring platform displays all power production data in a warning state according to a preset alarm method.

[0078] Among them, S206 specifically includes:

[0079] The worksheets containing the power production data in which all cells are changed to the warning color are sent to the monitoring platform, so that the monitoring platform displays the power production data in which all cells of each worksheet are changed to the warning color.

[0080] In summary, we can first collect the power production data of electrical equipment, import it into a pre-set worksheet, and use a specific judgment model to analyze the data; if the analysis result is abnormal data, the cell where the abnormal data is located is changed to a warning state, and all abnormal data is sent to the monitoring platform. By automatically analyzing and monitoring power production data, human errors are reduced, the accuracy and reliability of data analysis are improved, and the time and resources required for manual data supervision are reduced, which improves the efficiency of data anomaly detection.

[0081] Based on the above embodiment, the model is judged to be a trained machine learning model. This embodiment further describes the training process of the machine learning model, which is described in detail as follows:

[0082] S301: Collect multiple historical power production data of the electrical equipment to be monitored in any time period.

[0083] S302: Select a model to be trained from a model database according to data characteristics of a plurality of historical power production data.

[0084] Among them, data characteristics refer to the characteristics or patterns exhibited by historical electricity production data, such as the fluctuation range, cyclical changes or trends of the data.

[0085] The model database is a library used to store multiple different types of analysis models, each of which can be used to handle specific data analysis tasks. The models in the model database may be pre-developed or customized and trained according to new requirements.

[0086] S303: Cleaning and preprocessing the plurality of historical power production data to obtain the processed plurality of historical power production data.

[0087] Among them, the cleaning operation is to remove or correct missing values ​​or duplicate values ​​in multiple historical power production data.

[0088] The preprocessing operation may include data conversion or data integration processing of multiple historical power production data.

[0089] S304: Extracting features from the processed multiple historical power production data according to different dimensions to obtain multi-dimensional feature training data.

[0090] Among them, feature extraction is to create new features from historical power production data through certain mathematical transformations. These new features can better represent the inherent structure and pattern of historical power production data.

[0091] Multidimensional features refer to features that are obtained when measuring data from different angles or perspectives. In the case of power production data, this may mean creating features by considering multiple dimensions such as time, environmental factors, and equipment performance.

[0092] S305: Iteratively train the model to be trained with the multi-dimensional feature training data to obtain a machine learning model.

[0093] Among them, the loss function used in the process of iteratively training the multi-dimensional feature training data to the training model to obtain the machine learning model is:

[0094]

[0095] Where p is the number of samples, q is the number of elements in the network output layer, x and x′ are the predicted value and the value corresponding to the labeled result of the model output, respectively, MSE is the mean square error, MSE represents the result of the loss function, and i and j are any positive integers.

[0096] In summary, we first collect historical power production data from electrical equipment, and then select a suitable model based on the characteristics of this data; then clean and preprocess the data, extract the characteristics of the historical power production data after cleaning and preprocessing, and use these characteristics to train the machine learning model in an iterative manner. The model to be trained is selected based on data characteristics, which ensures the matching of the model and data, improves the quality of data processing, enhances the accuracy of model prediction, and optimizes the performance of the model through iterative training.

[0097] On the basis of the above embodiment, this embodiment further describes the process of changing the cell where the power production data is located to a warning color when there is an abnormality in the detection result of any power production data, and performing secondary verification on the detection result through a preset verification rule to distinguish between abnormal and non-abnormal detection results and generate a report to be recorded in the log, which is described in detail as follows:

[0098] S401: Obtain key information fields of any power production data with abnormal monitoring results, wherein the key information fields include daily maximum wind speed, daily minimum wind speed, daily power generation, tomorrow's predicted power generation and wind / light power prediction accuracy.

[0099] Among them, the daily maximum wind speed refers to the highest wind speed value measured in a certain day; the daily minimum wind speed refers to the lowest wind speed value measured in a certain day; the daily expected power generation refers to the amount of electricity that should be generated theoretically in one day based on the actual situation of wind or solar energy resources; tomorrow's predicted power generation refers to the amount of electricity that may be generated tomorrow based on weather forecasts and historical data; the wind / light power prediction accuracy refers to the degree of match between the predicted wind or solar power generation and the actual power generation, usually expressed as a percentage. The higher the accuracy, the closer the prediction result is to the actual power generation.

[0100] S402: input the daily maximum wind speed, daily minimum wind speed, daily expected power generation, tomorrow's predicted power generation and wind / solar power prediction accuracy into a preset level calculation formula to obtain an abnormality level.

[0101] Among them, the preset level calculation formula is as follows:

[0102] Abnormal level = h(V max ,V min ,E ex ,E pre ,Ac)

[0103] Among them, V max The highest wind speed of the day, V min The lowest wind speed of the day, E ex The daily power generation, E pre is the predicted power generation for tomorrow, AC is the wind / solar power prediction accuracy, and h is the level calculation function.

[0104]

[0105] Among them, V max,th is the threshold of the daily maximum wind speed, V min,th is the threshold of the daily minimum wind speed, E ex,th is the threshold of daily power generation, E pre,th is the threshold of tomorrow's predicted power generation, AC th is the threshold of wind / solar power prediction accuracy, and 0, 1, and 2 are abnormal levels.

[0106] S403: Changing the warning color of the cell where the power production data is located according to the abnormality level.

[0107] Among them, the warning color is a visual identifier used to indicate the abnormal level of power production data. The warning color can be divided into several colors, such as red, yellow and green, representing different abnormal levels.

[0108] S404: Normalize the daily maximum wind speed, daily minimum wind speed, daily expected power generation, tomorrow's predicted power generation and wind / light power prediction accuracy to obtain the normalized daily maximum wind speed, daily minimum wind speed, daily expected power generation, tomorrow's predicted power generation and wind / light power prediction accuracy.

[0109] Among them, normalization is a data preprocessing method that aims to convert data of different dimensions or units into values ​​with the same scale, usually by scaling the data range to [0, 1]. This can eliminate the impact of the dimension and make the data more suitable for comprehensive evaluation or comparison.

[0110] Specifically, the minimum-maximum normalization method can be used for normalization. First, collect the original data of the daily maximum wind speed, daily minimum wind speed, daily power generation, tomorrow's predicted power generation and wind / light power prediction accuracy to form a corresponding data set; find the maximum and minimum values ​​in different data sets; use the normalization formula to transform each data to obtain the normalized data of the daily maximum wind speed, daily minimum wind speed, daily power generation, tomorrow's predicted power generation and wind / light power prediction accuracy.

[0111] Among them, the normalization formula is specifically:

[0112]

[0113] Among them, x norm is the normalized data; x is the original data; x min is the minimum value in the data set; x max is the maximum value in the data set.

[0114] S405: Acquire multiple operation and maintenance personnel within a preset range of the electrical equipment, acquire personnel information of each operation and maintenance personnel, and normalize the personnel information to obtain normalized personnel information.

[0115] S406: Calculate the matching degree of each operation and maintenance personnel according to the normalized daily maximum wind speed, daily minimum wind speed, daily expected power generation, tomorrow's predicted power generation and wind / solar power prediction accuracy, and the normalized personnel information.

[0116] Among them, according to the normalized daily maximum wind speed, daily minimum wind speed, daily power generation, tomorrow's predicted power generation and wind / light power prediction accuracy, and the normalized personnel information, the matching degree corresponding to each operation and maintenance personnel is calculated. The calculation formula is:

[0117]

[0118] Among them, A is a vector in the three-dimensional space composed of the normalized daily maximum wind speed, daily minimum wind speed, daily power generation, tomorrow's predicted power generation and wind / solar power prediction accuracy, B is a vector composed of normalized personnel information, and θ is the matching degree corresponding to the operation and maintenance personnel.

[0119] S407: Determine the target operation and maintenance personnel according to the matching degree.

[0120] Among them, the operation and maintenance personnel whose matching degree exceeds the matching degree threshold can be determined as the target operation and maintenance personnel.

[0121] S408: Sending the operation and maintenance instruction to the terminal of the target operation and maintenance personnel.

[0122] The operation and maintenance instructions may include: detecting the operating status of the electrical equipment and / or replacing damaged parts of the electrical equipment.

[0123] S409: Perform secondary verification on the monitoring results using preset verification rules to screen out abnormal monitoring results and non-abnormal monitoring results.

[0124] Exemplarily, there are three monitoring results as follows: Time point 1: normal wind speed, normal power generation; Time point 2: normal wind speed, abnormal power generation (lower than expected); Time point 3: abnormal wind speed (higher than average), normal power generation; The preset verification rule is: check whether the wind speed and power generation at each time point meet the preset normal range rules. For example, if the wind speed is between 3-25m / s, it is normal, and the power generation is normal within ±10% of the expected value. If the data at time point 1 meets these rules, the result of the secondary verification is that there is no abnormality; if the power generation at time point 2 is lower than 10% of the expected value, the result of the secondary verification is that there is an abnormality; if the wind speed at time point 3 is higher than 25m / s, the result of the secondary verification is that there is an abnormality.

[0125] S410: Record the secondary verification process, the monitoring results with abnormalities, and the monitoring results without abnormalities to generate a verification report.

[0126] S411: Record the verification report into a preset log file.

[0127] In summary, we first obtain the key information fields of the monitoring results with abnormalities, and calculate the abnormality level to change the warning color of the cell where the power production data is located. Then, the power production data is normalized, and the information of multiple operation and maintenance personnel in the preset range of electrical equipment is obtained and normalized. Then, based on these normalized data, the matching degree of each operation and maintenance personnel is calculated and the target operation and maintenance personnel is determined accordingly. Based on the normalized data and matching degree calculation, the operation and maintenance resources are reasonably allocated, and the efficiency is improved.

[0128] In addition, the monitoring results are verified twice to screen out the monitoring results with and without abnormalities, and a verification report is generated and recorded in the log file, ensuring the high accuracy of anomaly detection.

[0129] Figure 3 This is a schematic diagram of the structure of the operating status monitoring device of the electrical equipment provided in the embodiment of the present application. Figure 3 As shown, the operating status monitoring device of the electrical equipment is applied to a computer device, and includes: a collection module 501 , an import module 502 , an acquisition module 503 , an output module 504 , a change module 505 and a sending module 506 .

[0130] Collection module 501: used to collect multiple power production data of the electrical equipment to be monitored at any time.

[0131] Import module 502: used for importing a plurality of power production data into cells under the columns of corresponding titles in a pre-created worksheet.

[0132] The acquisition module 503 is used to respectively acquire the judgment models corresponding to the multiple power production data.

[0133] Output module 504: is used to extract each item of power production data from the worksheet, and input each item of power production data into the judgment model to obtain a monitoring result of whether each item of power production data has an abnormality.

[0134] The changing module 505 is used to change the cell where any power production data is located to a warning state if the monitoring result of any power production data is abnormal.

[0135] The sending module 506 is used to send all the power production data that have been changed to the warning state to the monitoring platform, so that the monitoring platform can display all the power production data in the warning state according to the preset alarm mode.

[0136] Among them, the judgment model is a trained machine learning model; the training process of the machine learning model is: collecting multiple historical power production data of the electrical equipment to be monitored in any time period; selecting the model to be trained from the model database according to the data characteristics of the multiple historical power production data; cleaning and preprocessing the multiple historical power production data to obtain the processed multiple historical power production data; extracting features of the processed multiple historical power production data according to different dimensions to obtain multi-dimensional feature training data; iteratively training the model to be trained with the multi-dimensional feature training data to obtain the machine learning model.

[0137] Among them, the loss function used in the process of iteratively training the multi-dimensional feature training data to the training model to obtain the machine learning model is:

[0138]

[0139] Where p is the number of samples, q is the number of elements in the network output layer, x and x′ are the predicted value and the value corresponding to the labeled result of the model output, respectively, MSE is the mean square error, MSE represents the result of the loss function, and i and j are any positive integers.

[0140] Among them, the judgment model is the judgment function, and the judgment function is:

[0141] CONCATENATE(IFNA(IFS(OR(b1 <A1,A1<c1)AND(E1> 0,D1=0)

[0142] IFNA(IFS(OR(b2 <A2,A2<c2)

[0143] Among them, CONCATENATE(...) is a string concatenation function, IFNA(IFS(...)) is a nested IF function, and OR(...) is a logical OR operation; A1 and A2 represent any power production data value, b1 and b2 represent the maximum value allowed for any power production data value, c1 and c2 represent the minimum value allowed for any power production data value, D1 represents the number of faulty units, and E1 represents the fault time.

[0144] In one possible design, the change module 505 is specifically used to change the cell where any item of power production data in the worksheet is located to a warning color if the monitoring result of any item of power production data is abnormal; accordingly, all power production data changed to a warning state are sent to the monitoring platform, so that the monitoring platform displays all power production data in a warning state according to a preset alarm method, including: sending the worksheet where all the power production data in which all cells are changed to a warning color are located to the monitoring platform, so that the monitoring platform displays the power production data in all cells of each worksheet changed to a warning color.

[0145] The device provided in this embodiment can be used to execute the technical solution of the above method embodiment. Its implementation principle and technical effect are similar, and this embodiment will not be repeated here.

[0146] Figure 4 Schematic diagram of the hardware structure of the computer device provided in the embodiment of the present application. Figure 4 As shown, the computer device includes: at least one processor 601 and a memory 602; the memory stores computer execution instructions; at least one processor executes the computer execution instructions stored in the memory, so that at least one processor executes the above method for monitoring the operating status of the electrical equipment.

[0147] Optionally, the memory 602 may be independent or integrated with the processor 601 .

[0148] When the memory 602 is independently provided, the computer device further includes a bus 603 for connecting the memory 602 and the processor 601 .

[0149] The embodiment of the present application also provides a computer storage medium, in which computer execution instructions are stored. When a processor executes the computer execution instructions, the above-mentioned method for monitoring the operating status of an electrical device is implemented.

[0150] An embodiment of the present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the above method for monitoring the operating status of an electrical device.

[0151] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the above modules is only a logical function division. There may be other division methods in actual implementation, such as multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0152] The modules described above as separate components may or may not be physically separated, and the components shown as modules may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to implement the solution of this embodiment.

[0153] In addition, each functional module in each embodiment of the present application can be integrated into one processing unit, or each module can exist physically separately, or two or more modules can be integrated into one unit. The above-mentioned module-composed unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0154] The above-mentioned integrated module implemented in the form of a software function module can be stored in a computer-readable storage medium. The above-mentioned software function module is stored in a storage medium, including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the above-mentioned method in each embodiment of the present application.

[0155] It should be understood that the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), etc. A general-purpose processor may be a microprocessor or any conventional processor. The steps of the method disclosed in the invention may be directly implemented as being executed by a hardware processor, or may be implemented by a combination of hardware and software modules in the processor.

[0156] The memory may include a high-speed RAM memory, and may also include a non-volatile storage NVM, such as at least one disk memory, and may also be a USB flash drive, a mobile hard disk, a read-only memory, a magnetic disk or an optical disk, etc.

[0157] The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, the bus in the drawings of the present application is not limited to only one bus or one type of bus.

[0158] The above storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), electrically erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk. The storage medium can be any available medium that can be accessed by a general or special computer.

[0159] An exemplary storage medium is coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be a component of the processor. The processor and the storage medium can be located in an application specific integrated circuit (ASIC). Of course, the processor and the storage medium can also exist as discrete components in an electronic device or a main control device.

[0160] Those skilled in the art can understand that all or part of the steps of implementing the above-mentioned method embodiments can be completed by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps of the above-mentioned method embodiments are executed; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk and other media that can store program codes.

[0161] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for monitoring the operating status of an electrical device, characterized in that: Applicable to computer equipment, including: Collect multiple power production data of the electrical equipment to be monitored at any time; Importing the plurality of power production data into cells under the columns of corresponding titles in a pre-created worksheet; respectively obtaining judgment models corresponding to the plurality of power production data; Extracting each item of power production data from the worksheet, and inputting each item of power production data into the judgment model to obtain a monitoring result of whether each item of power production data is abnormal; If the monitoring result of any power production data is abnormal, the cell where the power production data is located is changed to a warning state; All power production data that have been changed to a warning state are sent to the monitoring platform, so that the monitoring platform displays all power production data in a warning state according to a preset alarm method.

2. The method according to claim 1, characterized in that The judgment model is a trained machine learning model; The training process of the machine learning model is: Collecting a plurality of historical power production data of the electrical equipment to be monitored within any time period; Selecting a model to be trained from the model database according to the characteristics of the plurality of historical power production data; Cleaning and preprocessing the plurality of historical power production data to obtain processed plurality of historical power production data; Extracting features from the processed multiple historical power production data according to different dimensions to obtain multi-dimensional feature training data; The multi-dimensional feature training data is used to iteratively train the model to be trained to obtain a machine learning model.

3. The method according to claim 2, characterized in that In the process of iteratively training the model to be trained with the multi-dimensional feature training data to obtain a machine learning model, the loss function used is: Wherein, p is the number of samples, q is the number of elements in the network output layer, x and x′ are the predicted value and the value corresponding to the labeled result output by the model, respectively, MSE is the mean square error, MSE represents the result of the loss function, and i and j are any positive integers.

4. The method according to claim 1, characterized in that: The judgment model is a judgment function, and the judgment function is: CONCATENATE(IFNA(IFS(OR(b1 <A1,A1<c1)AND(E1> 0,D1=0) IFNA(IFS(OR(b2 <A2,A2<c2) Among them, CONCATENATE(...) is a string concatenation function, IFNA(IFS(...)) is a nested IF function, and OR(...) is a logical OR operation; A1 and A2 represent any power production data value, b1 and b2 represent the maximum value allowed for any power production data value, c1 and c2 represent the minimum value allowed for any power production data value, D1 represents the number of faulty units, and E1 represents the fault time.

5. The method according to any one of claims 1 to 4, characterized in that: If the monitoring result of any item of power production data is abnormal, the cell where the any item of power production data is located is changed to a warning state, including: If the monitoring result of any item of power production data is abnormal, the cell where any item of power production data is located in the worksheet is changed to a warning color; Accordingly, all power production data changed to the warning state are sent to the monitoring platform, so that the monitoring platform displays all power production data in the warning state according to the preset alarm mode, including: The worksheets containing the power production data in which all cells are changed to the warning color are sent to the monitoring platform, so that the monitoring platform displays the power production data in which all cells of each worksheet are changed to the warning color.

6. The method according to claim 5, characterized in that If the monitoring result of any power production data is abnormal, the cell where any power production data is located in the worksheet is changed to a warning color, including: Obtaining key information fields of any item of power production data in which the monitoring result is abnormal, wherein the key information fields include daily maximum wind speed, daily minimum wind speed, daily expected power generation, tomorrow's predicted power generation and wind / light power prediction accuracy; The daily maximum wind speed, daily minimum wind speed, daily expected power generation, tomorrow's predicted power generation and wind / light power prediction accuracy are input into a preset level calculation formula to obtain an abnormality level; The warning color of the cell where the power production data is located is changed according to the abnormality level.

7. The method according to claim 6, characterized in that The preset level calculation formula is as follows: Abnormal level = h(V max ,V min ,E ex ,E pre ,Ac) Among them, V max The highest wind speed of the day, V min The lowest wind speed of the day, E ex The daily power generation, E pre is the predicted power generation for tomorrow, AC is the wind / solar power prediction accuracy, and h is the level calculation function; Among them, V max,th is the threshold of the daily maximum wind speed, V min,th is the threshold of the daily minimum wind speed, E ex,th is the threshold of daily power generation, E pre,th is the threshold of tomorrow's predicted power generation, AC th is the threshold of wind / solar power prediction accuracy, and 0, 1, and 2 are abnormal levels.

8. The method according to claim 6, characterized in that After inputting the daily maximum wind speed, daily minimum wind speed, daily expected power generation, tomorrow's predicted power generation and wind / light power prediction accuracy into a preset level calculation formula to obtain the abnormal level, it also includes: The daily maximum wind speed, daily minimum wind speed, daily expected power generation, tomorrow's predicted power generation and wind / light power prediction accuracy are normalized to obtain the normalized daily maximum wind speed, daily minimum wind speed, daily expected power generation, tomorrow's predicted power generation and wind / light power prediction accuracy; Acquire multiple operation and maintenance personnel within a preset range of the electrical equipment, acquire personnel information of each operation and maintenance personnel, and normalize the personnel information to obtain normalized personnel information; According to the normalized daily maximum wind speed, daily minimum wind speed, daily expected power generation, tomorrow's predicted power generation and wind / solar power prediction accuracy, and the normalized personnel information, the matching degree of each operation and maintenance personnel is calculated; Determine the target operation and maintenance personnel based on the matching degree; Sending an operation and maintenance instruction to the terminal of the target operation and maintenance personnel.

9. The method according to claim 6, characterized in that The matching degree corresponding to each operation and maintenance personnel is calculated based on the normalized daily maximum wind speed, daily minimum wind speed, daily power generation, tomorrow's predicted power generation and wind / light power prediction accuracy, and the normalized personnel information. The calculation formula is: Among them, A is a vector in the three-dimensional space composed of the normalized daily maximum wind speed, daily minimum wind speed, daily power generation, tomorrow's predicted power generation and wind / solar power prediction accuracy, B is a vector composed of normalized personnel information, and θ is the matching degree corresponding to the operation and maintenance personnel.

10. The method according to claim 1, characterized in that After inputting each item of power production data into the judgment model to obtain a monitoring result of whether each item of power production data is abnormal, the method further includes: Performing secondary verification on the monitoring results using preset verification rules to screen out monitoring results with abnormalities and monitoring results without abnormalities; Recording the secondary verification process, the monitoring results with abnormalities, and the monitoring results without abnormalities to generate a verification report; The verification report is recorded in a preset log file.

11. A device for monitoring the operating status of an electrical device, characterized in that: Applicable to computer equipment, including: Collection module: used to collect multiple power production data of the electrical equipment to be monitored at any time; Import module: used for importing the plurality of power production data into cells under the columns of corresponding titles in a pre-created worksheet; An acquisition module: used to respectively acquire the judgment models corresponding to the plurality of power production data; Output module: used for extracting each item of power production data from the worksheet, and inputting each item of power production data into the judgment model to obtain a monitoring result of whether each item of power production data is abnormal; Change module: used for changing the cell where any power production data is located to a warning state if the monitoring result of any power production data is abnormal; Sending module: used to send all power production data that have changed to a warning state to the monitoring platform, so that the monitoring platform displays all power production data in a warning state according to a preset alarm method.

12. A computer device, characterized in that: include: at least one processor and memory; The memory stores computer-executable instructions; The at least one processor executes the computer-executable instructions stored in the memory, so that the at least one processor executes the method for monitoring the operating status of an electrical device according to any one of claims 1 to 10.

13. A computer storage medium, characterized in that: The computer storage medium stores computer executable instructions, and when the processor executes the computer executable instructions, the operating status monitoring method of the electrical equipment according to any one of claims 1 to 10 is implemented.

14. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the method for monitoring the operating status of an electrical device as claimed in any one of claims 1 to 10 is implemented.

Images