Power failure risk identification system, method and equipment based on data analysis and medium

Abstract

The invention belongs to the field of power failure risk identification, and particularly relates to a power failure risk identification system, method and equipment based on data analysis and a medium. The system comprises a data acquisition module which comprises an acquisition unit, a data filtering unit and a transmission unit; the acquisition unit acquires monitoring data of the power equipment; the data filtering unit is used for filtering the monitoring data to obtain the filtered monitoring data, and comprises the following steps: calculating the sampling frequency of the monitoring data according to the acquisition time of the monitoring data, determining a filtering algorithm based on the sampling frequency, and filtering the monitoring data based on the filtering algorithm to obtain the filtered monitoring data; the transmission unit is used for transmitting the filtered monitoring data to the communication module; the communication module transmits the monitoring data to the analysis module; and the analysis module identifies the power failure risk of the power equipment based on the monitoring data to obtain an identification result. According to the invention, the filtering algorithm is adaptively selected based on the sampling frequency to filter the latest monitoring data.

Description

Technical Field

[0001] The present invention belongs to the field of power outage risk identification, and particularly relates to a power outage risk identification system, method, device and medium based on data analysis. Background Art

[0002] Power outage risk identification refers to identifying the power outage risk of power equipment based on the monitoring data of power equipment, so as to prepare corresponding emergency plans in advance.

[0003] For various types of monitoring data obtained, the existing technology generally uses a fixed filtering method for filtering, and cannot automatically switch the filtering method. In this way, it is easy that the acquisition frequency of the monitoring data cannot adapt to the filtering method. If an arithmetic mean filtering algorithm is used for data with a high sampling frequency, it is obvious that the processed signal is prone to distortion, and the information such as the change trend of the data cannot be effectively retained, resulting in inaccurate results for identifying the power outage risk of power equipment. Summary of the Invention

[0004] The purpose of the present invention is to provide a power outage risk identification system, method, device and medium based on data analysis to solve the problem that the existing technology uses a fixed filtering method for filtering, which is prone to signal distortion after processing.

[0005] To achieve the above purpose, the present invention adopts the following technical solutions: In the first aspect of the present invention, a power outage risk identification system based on data analysis is provided, including: A data acquisition module, including an acquisition unit, a data filtering unit and a transmission unit; the acquisition unit is used to obtain the monitoring data of power equipment; the data filtering unit is used to filter the monitoring data to obtain the filtered monitoring data, including: calculating the sampling frequency of the monitoring data according to the acquisition time of the monitoring data, determining the filtering algorithm based on the sampling frequency, and filtering the monitoring data based on the filtering algorithm to obtain the filtered monitoring data; the transmission unit is used to transmit the filtered monitoring data to the communication module; A communication module, used to transmit the monitoring data to the analysis module; An analysis module, used to identify the power outage risk of power equipment based on the monitoring data to obtain the identification result.

[0006] Further, the monitoring data includes the amplitude of the power equipment, the temperature on the surface of the power equipment, and the operating voltage of the power equipment.

[0007] Further, determining the filtering algorithm based on the sampling frequency includes: Determine whether the sampling frequency is greater than a preset frequency threshold; if so, use the first filtering algorithm as the filtering algorithm; if not, use the second filtering algorithm as the filtering algorithm.

[0008] Further, the first filtering algorithm includes: For the latest obtained k-th monitoring data of type A , for The formula for filtering is as follows:

[0009] Wherein, represents the (k - 1)-th monitoring data of type A, represents a preset comparison value, represents for The filtered monitoring data of type A obtained after filtering

[0010] Further, the second filtering algorithm includes: For the latest obtained k-th monitoring data of type A , for The process of filtering is as follows: Store the first D monitoring data of type A whose acquisition time is closest to the acquisition time of into the set AU; Use the following formula to filter :

[0011] Wherein, represents the filtered monitoring data of type A obtained after filtering , represents The time length between the acquisition times of represents the first weight, represents the second weight, and i is the monitoring data of type A in AU.

[0012] Further, the analysis module includes a storage unit and an identification unit; The storage unit is used to store the monitoring data and fault records of the power equipment; The identification unit is used to periodically identify the power outage risk of the power equipment based on the monitoring data and fault records stored in the storage unit, and obtain an identification result.

[0013] Further, identifying the power outage risk of the power equipment based on the monitoring data stored in the storage unit and obtaining an identification result includes: The monitoring inputs obtained within a preset time interval are input into a trained prediction model for prediction to obtain an identification result.

[0014] In a second aspect of the present invention, a power outage risk identification method is provided, including: Obtain monitoring data of power equipment, filter the monitoring data to obtain filtered monitoring data; wherein, filtering the monitoring data includes: calculating the sampling frequency of the monitoring data according to the acquisition time of the monitoring data, determining a filtering algorithm based on the sampling frequency, and filtering the monitoring data based on the filtering algorithm; Identify the power outage risk of the power equipment based on the monitoring data to obtain an identification result; Among them, determining the filtering algorithm based on the sampling frequency includes: judging whether the sampling frequency is greater than a preset frequency threshold; if so, using a first filtering algorithm as the filtering algorithm; if not, using a second filtering algorithm as the filtering algorithm; The first filtering algorithm includes: For the latest obtained kth piece of monitoring data of type A , the formula for filtering is as follows:

[0015] Among them, represents the (k - 1)th piece of monitoring data of type A, represents a preset comparison value, represents after filtering to obtain the filtered monitoring data of type A; The second filtering algorithm includes: For the latest obtained kth piece of monitoring data of type A , the process of filtering is as follows: Store the first D pieces of monitoring data of type A whose acquisition time is the closest to the acquisition time of into the set AU; Use the following formula to filter :

[0016] Among them, represents the filtered monitoring data of type A obtained after filtering , represents the time length between the acquisition times of and i, represents the first weight,

[0017] In a third aspect of the present invention, there is provided an electronic device, including a processor and a memory, where the processor is configured to execute a computer program stored in the memory to implement the power outage risk identification method described above.

[0018] In a fourth aspect of the present invention, there is provided a computer-readable storage medium storing at least one instruction, and when the at least one instruction is executed by a processor, the power outage risk identification method described above is implemented.

[0019] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention can adaptively select a filtering algorithm based on the sampling frequency of the monitoring data of power equipment to filter the latest obtained monitoring data, so that the filtering algorithm can be adapted to the sampling frequency of the monitoring data. In this way, while ensuring the filtering effect, more information can be retained for the data after filtering, enabling the data after filtering to more truly reflect the change trend of the real data, thereby improving the accuracy of the result of identifying the power outage risk of power equipment. A power outage risk identification method, an electronic device, and a computer-readable storage medium based on data analysis provided by the present invention also solve the problems raised in the background art part. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] The accompanying drawings forming a part of this application are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation to the present invention. In the drawings: Figure 1 is a schematic diagram of a power outage risk identification system based on data analysis according to an embodiment of the present invention; Figure 2 is a schematic diagram of a power outage risk identification method based on data analysis according to an embodiment of the present invention; Figure 3 is a structural block diagram of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] The present invention will be described in detail below with reference to the drawings and in conjunction with the embodiments. It should be noted that, without conflict, the embodiments in this application and the features in the embodiments can be combined with each other.

[0022] The following detailed descriptions are all exemplary descriptions, aiming to provide a further detailed description of the present invention. Unless otherwise specified, all technical terms used in the present invention have the same meaning as commonly understood by those of ordinary skill in the art to which this application belongs. The terms used in the present invention are only for the purpose of describing specific embodiments and are not intended to limit the exemplary embodiments according to the present invention.

[0023] Embodiment 1 As Figure 1 shown, the present invention provides a power outage risk identification system based on data analysis, including a data acquisition module, a communication module, and an analysis module; The data acquisition module is used to obtain the monitoring data of power equipment; The data acquisition module includes an acquisition unit, a data filtering unit, and a transmission unit; the acquisition unit is used to obtain the monitoring data of power equipment; the data filtering unit is used to filter the monitoring data to obtain the filtered monitoring data, including: calculating the sampling frequency of the monitoring data according to the acquisition time of the monitoring data, determining the filtering algorithm based on the sampling frequency, and filtering the monitoring data based on the filtering algorithm to obtain the filtered monitoring data; the transmission unit is used to transmit the filtered monitoring data to the communication module; the communication module is used to transmit the monitoring data to the analysis module; The analysis module is used to identify the power outage risk of power equipment based on the monitoring data and obtain the identification result.

[0024] The above power outage risk identification system provided by the present invention can adaptively select a filtering algorithm based on the sampling frequency of the monitoring data of power equipment to filter the latest obtained monitoring data, so that the filtering algorithm can adapt to the sampling frequency of the monitoring data. In this way, while ensuring the filtering effect, more information can be retained for the data after filtering, enabling the data after filtering to more truly reflect the change trend of the real data, thereby improving the accuracy of the result of identifying the power outage risk of power equipment.

[0025] Preferably, the monitoring data includes the amplitude of the power equipment, the temperature on the surface of the power equipment, and the operating voltage of the power equipment.

[0026] Specifically, the amplitude of the power equipment can be obtained by a vibration sensor arranged inside the power equipment. The temperature on the surface of the power equipment can be obtained by a temperature sensor arranged on the surface of the power equipment. The operating voltage of the power equipment can be obtained by a voltage sensor arranged on the power supply line of the power equipment.

[0027] Preferably, calculating the sampling frequency of the monitoring data according to the acquisition time of the monitoring data includes: Let A represent the type of monitoring data, and use to represent the acquisition time of the latest obtained A-type monitoring data by the acquisition unit. Then the calculation formula for the sampling frequency of A-type monitoring data is:

[0028] where represents the sampling frequency of A-type monitoring data, and N represents the time interval Within it, the total number of monitoring data of type A acquired by the acquisition unit, and T is the preset time length.

[0029] Specifically, by obtaining the quantity of monitoring data of the same type acquired within a fixed time length, the sampling frequency of this type of monitoring data can be updated in real time. Thus, when the sampling frequency of the monitoring data changes, there is no need to manually update the sampling frequency, and the real-time performance of the sampling frequency can be made stronger.

[0030] Preferably, the preset time length is 60 seconds.

[0031] In addition, the preset time length can also be 120 seconds, 240 seconds, etc.

[0032] Preferably, determining the filtering algorithm based on the sampling frequency includes: Judging whether the sampling frequency is greater than the preset frequency threshold. If so, the first filtering algorithm is used as the filtering algorithm; if not, the second filtering algorithm is used as the filtering algorithm.

[0033] Specifically, by setting a frequency threshold to determine the filtering algorithm for the monitoring data, the sampling frequency of the monitoring data can be adapted to the filtering algorithm, avoiding excessive delay of the filtered data and being unable to correctly represent the change trend of the monitoring data.

[0034] Preferably, the preset frequency threshold can be 30 times per minute.

[0035] Preferably, the first filtering algorithm includes: For the latest obtained k-th monitoring data of type A , for The formula for filtering is as follows:

[0036] Wherein, represents the (k - 1)-th monitoring data of type A, represents the preset comparison value, represents for The filtered monitoring data of type A obtained after filtering.

[0037] The above filtering algorithm filters by setting a preset comparison value, and can filter out the mutated data when the monitoring data mutates due to the failure of the acquisition unit, so as to effectively retain the correct data change trend.

[0038] Preferably, the preset comparison value is one-fourth of the upper limit value of the value range of the monitoring data of type A.

[0039] For example, if the value range of the operating voltage is [10, 100], the upper limit value is 100, and the preset comparison value is 25.

[0040] If the filtering algorithm is the second filtering algorithm, the monitoring data is filtered in the following manner: Preferably, the second filtering algorithm includes: For the most recently obtained kth piece of monitoring data of type A , the process of filtering is as follows: Store the first D pieces of monitoring data of type A with the acquisition time closest to the acquisition time of into the set AU; Filter using the following formula:

[0041] where represents the filtered monitoring data of type A obtained after filtering , represents the time length between the acquisition times of represents the first weight, represents the second weight, and i is the monitoring data of type A in AU.

[0042] In the second filtering algorithm proposed in the embodiments of the present invention, the filtering weight of i is determined respectively from the time length between the acquisition times of two pieces of monitoring data i and with different acquisition times and the numerical difference between i and . Thus, when the time length between the acquisition times of i and is smaller and the numerical difference between i and is smaller, the weight of i is made larger. When the time length between the acquisition times of i and is larger and the numerical difference between i and is larger, the weight of i is made smaller. The adaptive change of the weight of i is realized, such that the greater the influence on the change of , the greater the weight of the data with greater reference value, and the smaller the influence on the change of , the smaller the weight of the data with smaller reference value, effectively improving the accuracy of the final filtering result.

[0043] Specifically, the first weight is 0.6 and the second weight is 0.4.

[0044] Preferably, the communication module includes at least one of a 4G communication device, a 5G communication device, and a satellite communication device.

[0045] Specifically, the communication module can be installed on the power equipment to be monitored.

[0046] Preferably, the analysis module includes a storage unit and an identification unit; The storage unit is used to store the monitoring data and fault records of the power equipment; The identification unit is used to periodically identify the power outage risk of the power equipment based on the monitoring data and fault records stored in the storage unit, and obtain an identification result.

[0047] Specifically, the storage unit can store historical monitoring data, which is conducive to providing data support for subsequent prediction processes.

[0048] Preferably, identifying the power outage risk of the power equipment based on the monitoring data stored in the storage unit and obtaining an identification result includes: inputting the monitoring data obtained within a preset time interval into a trained prediction model for prediction to obtain an identification result.

[0049] Specifically, the identification result can be a failure probability.

[0050] Specifically, the training process of the prediction model is as follows: 1. Data cleaning Process the missing values, outliers, and duplicate values of the data stored in the storage unit to make the data complete and consistent. For time series data, align or interpolate the timestamps to make the data time step consistent.

[0051] 2. Data annotation Label definition: For the model predicting faults, determine which data represents the "fault" state and which represents the "normal" state. In this solution, clear labels are set for the fault data (e.g., 1 represents fault and 0 represents normal).

[0052] Label generation: Generate labels according to the fault records, and each historical record corresponds to a label value. If the data volume is large, the time window can be used as the basis for label generation. For example, the data in a period of time before the equipment fails is marked as 1.

[0053] 3. Feature extraction Feature extraction: Extract features useful for fault prediction from the original data. The features can be univariate statistical features (such as mean, standard deviation, extreme values, etc.), time series features (such as autoregressive coefficients, trends, periods, etc.), or composite features (such as the ratio between two variables, etc.).

[0054] Feature selection: Screen out important features through methods such as correlation analysis and principal component analysis (PCA) to avoid the impact of feature redundancy on the model performance.

[0055] 4. Data Segmentation Training set and test set: Divide the data into a training set and a test set to ensure that the model can perform well on unseen data. Time series data can be divided in chronological order to avoid future data leakage to the model.

[0056] Cross-validation: To avoid overfitting, cross-validation methods can be used, especially time series cross-validation (such as rolling window cross-validation).

[0057] 5. Model Selection and Training Select a model: In this solution, according to actual needs, common predictive fault models are selected. For example, common predictive fault probability models include logistic regression, support vector machine (SVM), random forest, gradient boosting trees (such as XGBoost), neural networks (such as LSTM, GRU), etc. This solution can select a suitable model according to actual requirements.

[0058] Model training: Perform model training on the training set. For models of time series data (such as LSTM or GRU), the input data is the data of multiple time steps of the sequence, rather than the data of a single time point.

[0059] 6. Model Evaluation Performance evaluation: Use the test set to evaluate the model. Evaluation metrics can include accuracy, recall, precision, F1 score, AUC (area under the ROC curve), etc.

[0060] Probability prediction: In addition to giving a binary classification result of fault or normal, the model can also output the fault probability. By adjusting the probability threshold, the accuracy and recall of the prediction can be balanced.

[0061] 7. Hyperparameter Tuning and Optimization Hyperparameter tuning: Perform hyperparameter tuning through methods such as grid search, random search, or Bayesian optimization to further improve the model performance.

[0062] In the above solution, the filtering algorithm is dynamically selected according to the sampling frequency of the monitoring data, which can ensure the filtering effect while retaining more information and improving the recognition accuracy. The filtered data can more truly reflect the data change trend, improving the accuracy of power outage risk recognition. At the same time, using the prediction model for risk recognition improves the intelligent level of recognition. The present invention effectively solves the problem of signal distortion in the prior art and improves the accuracy and intelligent level of power outage risk recognition through the adaptive filtering technology and intelligent recognition method.

[0063] Embodiment 2 As Figure 2 shown, based on the same inventive concept as the above embodiment, the present invention also provides a power outage risk recognition method, including: S1. Obtain the monitoring data of the power equipment, filter the monitoring data to obtain the filtered monitoring data; wherein, filtering the monitoring data includes: calculating the sampling frequency of the monitoring data according to the acquisition time of the monitoring data, determining the filtering algorithm based on the sampling frequency, and filtering the monitoring data based on the filtering algorithm; S2. Identify the power outage risk of the power equipment based on the monitoring data to obtain the identification result; Among them, determining the filtering algorithm based on the sampling frequency includes: judging whether the sampling frequency is greater than a preset frequency threshold; if so, using the first filtering algorithm as the filtering algorithm; if not, using the second filtering algorithm as the filtering algorithm; The first filtering algorithm includes: For the latest obtained kth piece of monitoring data of type A , the formula for filtering is as follows:

[0064] Among them, represents the (k - 1)th piece of monitoring data of type A, represents a preset comparison value, represents the filtered monitoring data of type A obtained after filtering The second filtering algorithm includes: For the latest obtained kth piece of monitoring data of type A , the process of filtering is as follows: Store the first D pieces of monitoring data of type A whose acquisition time is the closest to the acquisition time of into the set AU; Use the following formula to filter :

[0065] Among them, represents the filtered monitoring data of type A obtained after filtering , represents the time length between the acquisition times of and i, represents the first weight,

[0066] Example 3 As Figure 3 shown, the present invention also provides an electronic device 100 for implementing the power outage risk identification method in Example 2; The electronic device 100 includes a memory 101, at least one processor 102, a computer program 103 stored in the memory 101 and executable on the at least one processor 102, and at least one communication bus 104.

[0067] The memory 101 can be used to store the computer program 103. The processor 102 realizes the steps of the power outage risk identification method in Embodiment 2 by running or executing the computer program stored in the memory 101 and calling the data stored in the memory 101.

[0068] The memory 101 mainly includes a program storage area and a data storage area. Among them, the program storage area can store an operating system, application programs required for at least one function (such as a sound playback function, an image playback function, etc.); the data storage area can store data created according to the use of the electronic device 100 (such as audio data, etc.). In addition, the memory 101 can include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices.

[0069] The at least one processor 102 can be a Central Processing Unit (CPU), and can also be other general-purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field-Programmable Gate Arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 102 can be a microprocessor or the processor 102 can also be any conventional processor, etc. The processor 102 is the control center of the electronic device 100 and connects various parts of the entire electronic device 100 through various interfaces and lines.

[0070] The memory 101 in the electronic device 100 stores multiple instructions to implement a power outage risk identification method. The processor 102 can execute the multiple instructions to achieve: Obtain the monitoring data of the power equipment, filter the monitoring data to obtain the filtered monitoring data; wherein, filtering the monitoring data includes: calculating the sampling frequency of the monitoring data according to the acquisition time of the monitoring data, determining the filtering algorithm based on the sampling frequency, and filtering the monitoring data based on the filtering algorithm; Identify the power outage risk of power equipment based on monitoring data to obtain the identification result; Among them, determine the filtering algorithm based on the sampling frequency, including: judging whether the sampling frequency is greater than a preset frequency threshold; if so, use the first filtering algorithm as the filtering algorithm; if not, use the second filtering algorithm as the filtering algorithm; The first filtering algorithm includes: For the latest obtained kth piece of monitoring data of type A , for The formula for filtering is as follows:

[0071] Among them, represents the (k - 1)th piece of monitoring data of type A, represents a preset comparison value, represents for The filtered monitoring data of type A obtained after filtering; The second filtering algorithm includes: For the latest obtained kth piece of monitoring data of type A , for The process of filtering is as follows: Store the first D pieces of monitoring data of type A whose acquisition time is the closest to the acquisition time of into the set AU; Use the following formula to filter :

[0072] Among them, represents the filtered monitoring data of type A obtained after filtering , represents The time length between the acquisition time of and i, represents the first weight, represents the second weight, and i is the monitoring data of type A in AU.

[0073] Embodiment 4 If the modules / units integrated in the electronic device 100 are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, to implement all or part of the processes in the above-described embodiment methods of the present invention, it can also be completed by instructing relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above-described method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file, or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disc, computer memory, and read-only memory (ROM, Read-Only Memory).

[0074] Those skilled in the art should understand that the embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention can take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memory, CD-ROM, optical memory, etc.) containing computer-usable program code.

[0075] The present invention is described with reference to the flowcharts and / or block diagrams of methods, apparatuses (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram can be implemented by computer program instructions, and the combination of processes and / or blocks in the flowchart and / or block diagram can also be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing devices generate a device for implementing the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0076] These computer program instructions can also be stored in a computer-readable memory capable of guiding a computer or other programmable data processing devices to work in a specific manner, so that the instructions stored in the computer-readable memory generate a manufactured article including an instruction device, and the instruction device implements the specified functions in Figure 1 one process or multiple processes and / or blocks Figure 1 one block or multiple blocks.

[0077] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus, so that a series of operation steps are performed on the computer or other programmable apparatus to produce a computer-implemented process, thereby providing instructions for implementing the functions specified in one process or a plurality of processes and / or blocks Figure 1 one process or a plurality of processes and / or blocks Figure 1 in the block or blocks.

[0078] In the description of the present specification, descriptions with reference to the terms "one embodiment", "example", "specific example", etc. mean that the specific features, structures, materials or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0079] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: modifications or equivalent replacements can still be made to the specific embodiments of the present invention. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall be covered by the protection scope of the claims of the present invention.

Claims

1. A power outage risk identification system based on data analysis, characterized in that Comprising: A data acquisition module, including an acquisition unit, a data filtering unit, and a transmission unit; The acquisition unit is used to obtain the monitoring data of the power equipment; The data filtering unit is used to filter the monitoring data to obtain the filtered monitoring data, including: calculating the sampling frequency of the monitoring data according to the acquisition time of the monitoring data, determining the filtering algorithm based on the sampling frequency, and filtering the monitoring data based on the filtering algorithm to obtain the filtered monitoring data; The transmission unit is used to transmit the filtered monitoring data to the communication module; A communication module, used to transmit the monitoring data to the analysis module; An analysis module, used to identify the power outage risk of the power equipment based on the monitoring data to obtain an identification result.

2. The power outage risk identification system according to claim 1, characterized in that The monitoring data includes the amplitude of the power equipment, the temperature on the surface of the power equipment, and the operating voltage of the power equipment.

3. The power outage risk identification system according to claim 1, characterized in that, Determining the filtering algorithm based on the sampling frequency includes: Judging whether the sampling frequency is greater than a preset frequency threshold; if so, using the first filtering algorithm as the filtering algorithm; if not, using the second filtering algorithm as the filtering algorithm.

4. The power outage risk identification system according to claim 3, wherein The first filtering algorithm includes: For the most recently obtained monitoring data of the k-th type A , for , the formula for filtering is as follows: Among them, represents the monitoring data of the (k - 1)-th type A, represents a preset comparison value, represents the filtered monitoring data of type A obtained after filtering [[ ]].

5. The power outage risk identification system according to claim 4, wherein The second filtering algorithm includes: For the most recently obtained monitoring data of the k-th type A , the process of filtering is as follows: Store the acquisition time and the D most recent monitoring data of type A before the acquisition time of into the set AU; Filter using the following formula: in, Express The filtered monitoring data of type A obtained after filtering, express The length of time between the acquisition time of and i, represents the first weight, represents the second weight, and i is the monitoring data of type A in the AU.

6. The power outage risk identification system according to claim 1, wherein, The analysis module includes a storage unit and an identification unit; The storage unit is used to store the monitoring data and fault records of the power equipment; The identification unit is used to periodically identify the power outage risk of the power equipment based on the monitoring data and fault records stored in the storage unit to obtain an identification result.

7. The power outage risk identification system according to claim 6, characterized in that, Identifying the power outage risk of the power equipment based on the monitoring data stored in the storage unit to obtain an identification result, including: Inputting the monitoring data obtained within a preset time interval into a pre-trained prediction model for prediction to obtain an identification result.

8. A power outage risk identification method, characterized in that, Comprising: Obtaining the monitoring data of the power equipment, filtering the monitoring data to obtain the filtered monitoring data; wherein, filtering the monitoring data includes: calculating the sampling frequency of the monitoring data according to the acquisition time of the monitoring data, determining the filtering algorithm based on the sampling frequency, and filtering the monitoring data based on the filtering algorithm; Identifying the power outage risk of the power equipment based on the monitoring data to obtain an identification result; Wherein, determining the filtering algorithm based on the sampling frequency includes: judging whether the sampling frequency is greater than a preset frequency threshold; if so, using the first filtering algorithm as the filtering algorithm; if not, using the second filtering algorithm as the filtering algorithm; The first filtering algorithm includes: For the most recently obtained monitoring data of the k-th A type , for , the filtering formula is as follows: Among them, represents the monitoring data of the (k - 1)-th type A, represents a preset comparison value, represents the filtered monitoring data of type A obtained after filtering ; The second filtering algorithm includes: For the most recently obtained monitoring data of the k-th A type , the process of filtering is as follows: The acquisition time is compared with the D monitoring data of type A with the closest acquisition time before it are stored in the set AU; Filter using the following formula: in, Express The filtered monitoring data of type A obtained after filtering, express The length of time between the acquisition time of and i, represents the first weight, represents the second weight, and i is the monitoring data of type A in the AU.

9. An electronic device, characterized in that, Comprising a processor and a memory, the processor is used to execute the computer program stored in the memory to implement the power outage risk identification method as claimed in claim 8.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores at least one instruction, and when the at least one instruction is executed by the processor, it implements the power outage risk identification method as claimed in claim 8.

Images