Equipment maintenance method and device, computer equipment and computer readable storage medium

Abstract

The invention relates to an equipment maintenance method and device, computer equipment and a computer readable storage medium. The method comprises the following steps: performing predictive analysis on original electrical data of electrical equipment at a plurality of historical moments to obtain target electrical data at a plurality of future moments after the current moment; performing fault analysis on the target electrical data at each future moment, and predicting a target fault probability of the electrical equipment at each future moment; according to the target fault probability of each future moment, determining a maintenance strategy of the electrical equipment at each future moment; and performing maintenance management on the electrical equipment according to the maintenance strategy at each future moment. By adopting the method, the probability of failure shutdown of the electrical equipment can be reduced, and the operation stability of a power system is improved.

Description

Technical Field

[0001] The present application relates to the field of power electronics technology, and in particular to a device maintenance method and apparatus, computer equipment, and a computer-readable storage medium. Background Art

[0002] In the power system, the reliable operation of electrical equipment is crucial to ensure the stability of power supply. With the continuous development of smart grid technology, real-time monitoring of the operating data of electrical equipment has become an important means to improve the operation and maintenance efficiency of the power system.

[0003] The traditional operation and maintenance solution for electrical equipment is to generate fault information of electrical equipment failure when the electrical equipment fails in real time, so that technicians can repair the electrical equipment. However, when the electrical equipment stops working due to failure, it will affect the stable operation of the power system. In other words, the traditional operation and maintenance solution for electrical equipment is difficult to adapt to the power system's requirements for reliable operation of electrical equipment. Summary of the invention

[0004] Based on this, it is necessary to provide an equipment maintenance method and device, computer equipment, and computer-readable storage medium that can improve the operating reliability of electrical equipment in response to the above technical problems.

[0005] In a first aspect, the present application provides a device maintenance method, comprising:

[0006] Perform predictive analysis on the original electrical data of electrical equipment at multiple historical moments to obtain target electrical data at multiple future moments after the current moment;

[0007] Perform fault analysis on target electrical data at each future moment and predict target fault probabilities of electrical equipment at each future moment;

[0008] Determine the maintenance strategy of electrical equipment at each future moment according to the target failure probability at each future moment;

[0009] Maintain and manage electrical equipment based on maintenance strategies at each future moment.

[0010] In one embodiment, the electrical equipment is maintained and managed according to the maintenance strategy at each future moment, including:

[0011] The maintenance strategy at each future moment includes reducing the operating power of the electrical equipment to the target operating power at the target future moment if maintenance is required at the target future moment and the maintenance method is to reduce the operating power of the electrical equipment to the target operating power.

[0012] In one embodiment, determining a maintenance strategy for electrical equipment at each future moment according to a target failure probability at each future moment includes:

[0013] Obtaining a specified failure probability of at least one other electrical device other than the electrical device at each future time;

[0014] determining the total operating power of the electrical equipment and at least one other electrical equipment;

[0015] The maintenance strategy of the electrical equipment at each future moment is determined according to the total operating power, the target failure probability at each future moment and the specified failure probability at each future moment.

[0016] In one embodiment, the original electrical data of the electrical equipment at multiple historical moments are predicted and analyzed to obtain target electrical data at multiple future moments after the current moment, including:

[0017] Perform feature analysis on the original electrical data at multiple historical moments to obtain feature data at multiple historical moments;

[0018] The original electrical data at multiple historical moments and the characteristic data at multiple historical moments are correspondingly merged to obtain the relevant data at multiple historical moments;

[0019] Classify the relevant data of multiple historical moments to obtain the relevant data of multiple historical moments in each category;

[0020] Determine target electrical data at multiple historical moments according to relevant data at multiple historical moments under each category;

[0021] The target electrical data at multiple historical moments are predicted and analyzed to obtain the target electrical data at multiple future moments.

[0022] In one embodiment, the target electrical data at multiple historical moments are determined based on the relevant data at multiple historical moments in each category, including:

[0023] Centralize the relevant data of each historical moment in each category of relevant data to obtain the centralized data of each historical moment in each category;

[0024] Determine the eigenvector of the covariance matrix corresponding to the centralized data of each category at each historical moment;

[0025] A preset number of values ​​in the feature vector of each category at each historical moment are determined as target electrical data of each category at each historical moment.

[0026] In one embodiment, a prediction analysis is performed on target electrical data at multiple historical moments to obtain target electrical data at multiple future moments, including:

[0027] Using target electrical data at multiple historical moments, the parameters in the preset prediction model are trained to obtain a trained target prediction model;

[0028] The target electrical data at the i-th moment is processed by using the target prediction model to obtain the target electrical data at the i+1-th moment; wherein i is an integer greater than or equal to 1, and i+1 is less than or equal to the total number of moments at multiple future moments;

[0029] The target electrical data at the i+1th moment obtained each time is determined as the target electrical data at each future moment.

[0030] In one embodiment, the original electrical data of the electrical equipment at multiple historical moments are predicted and analyzed to obtain target electrical data at multiple future moments after the current moment, including:

[0031] Obtain random errors and p weight coefficients; where p is the number of moments in multiple historical moments;

[0032] Using p weight coefficients, weighted fusion is performed on the target electrical data from the tth moment to the t+p-1th moment to obtain the t+pth target data; t is an integer greater than or equal to 1, and t+p is less than or equal to the total number of moments in the future;

[0033] Determine the target electrical data at the t+pth moment according to the t+pth target data and the random error;

[0034] The target electrical data at the t+pth moment obtained each time is determined as the target electrical data at each future moment.

[0035] In a second aspect, the present application provides an equipment maintenance device, the device comprising:

[0036] The prediction analysis module is used to perform prediction analysis on the original electrical data of the electrical equipment at multiple historical moments to obtain the target electrical data at multiple future moments after the current moment;

[0037] A fault analysis module is used to perform fault analysis on target electrical data at each future moment and predict target fault probabilities of electrical equipment at each future moment;

[0038] A strategy determination module, used to determine the maintenance strategy of the electrical equipment at each future moment according to the target failure probability at each future moment;

[0039] The maintenance management module is used to perform maintenance management on electrical equipment according to maintenance strategies at each future moment.

[0040] In a third aspect, the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any of the above methods when executing the computer program.

[0041] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of any of the above methods when the computer program is executed by a processor.

[0042] In an embodiment of the present application, by predicting the target failure probability of electrical equipment at each future moment, determining the maintenance strategy of the electrical equipment at each future moment according to the target failure probability at each future moment, and performing maintenance management on the electrical equipment according to the maintenance strategy at each future moment, it is possible to determine in advance the maintenance plan for maintaining and managing the electrical equipment, and perform maintenance management on the electrical equipment according to the determined maintenance plan, which helps to discover potential problems with the electrical equipment at future moments after the current moment, effectively prevent the occurrence of failures, reduce the probability of electrical equipment failure shutdowns, and improve the operating stability of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A schematic diagram of the structure of a device maintenance system provided in some embodiments;

[0045] Figure 2 A schematic diagram of a process flow of a device maintenance method provided in some embodiments;

[0046] Figure 3 A flowchart of a method for determining a maintenance strategy for electrical equipment at various future moments provided in some embodiments;

[0047] Figure 4 A flowchart of a method for determining target electrical data at multiple future moments provided in some embodiments;

[0048] Figure 5 A flowchart of a method for determining target electrical data at multiple future moments provided for other embodiments;

[0049] Figure 6 A schematic diagram of the structure of an intelligent monitoring system provided in some embodiments;

[0050] Figure 7 A flowchart of a method for acquiring raw electrical data provided in some embodiments;

[0051] Figure 8 A flowchart of a method for determining whether an electrical device is faulty is provided in some embodiments;

[0052] Fig. 9 A flowchart of a method for determining whether an electrical device is faulty is provided for other embodiments;

[0053] Fig.10 A flowchart of a maintenance management method provided in some embodiments;

[0054] Fig.11 A schematic diagram of the structure of an equipment maintenance device provided in some embodiments;

[0055] Fig.12 A schematic diagram of the structure of a computer device provided for some embodiments. DETAILED DESCRIPTION

[0056] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0057] In the description of the embodiments of the present application, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0058] The equipment maintenance method provided in the embodiment of the present application can be applied to an equipment maintenance system. Figure 1 A schematic diagram of a device maintenance system provided in some embodiments, such as Figure 1As shown, the equipment maintenance system 10 includes: a plurality of electrical devices 101, and a computer device 102 for acquiring the original electrical data of the plurality of electrical devices 101. The electrical device 101 communicates with the computer device 102, and the computer device 102 can display the determined target failure probability at each future moment and / or the maintenance strategy at each future moment. Taking a single electrical device 101 as an example, in some embodiments, the computer device 102 can directly acquire the original electrical data of the electrical device 101; in other embodiments, the computer device 102 can acquire the original electrical data of the electrical device 101 through a sensor or other acquisition device; in still other embodiments, the original electrical data includes a first type of electrical data and a second type of electrical data, and the computer device 102 can directly acquire the first type of electrical data of the electrical device 101, and acquire the second type of electrical data of the electrical device 101 through a sensor or other acquisition device.

[0059] The electrical equipment in the embodiment of the present application may include one of the following: transformer, circuit breaker, motor, capacitor, uninterruptible power supply (UPS) system, etc. Taking the electrical equipment as a transformer as an example, the original electrical data includes at least one of the following: winding temperature, oil temperature, load current, input voltage, output voltage, partial discharge information, vibration signal, etc. Taking the electrical equipment as a circuit breaker as an example, the original electrical data includes at least one of the following: action current, switch state, voltage, current waveform, opening time, closing time, mechanical wear, temperature rise data, etc. Taking the electrical equipment as an engine as an example, the original electrical data includes at least one of the following: operating current, speed, temperature, vibration, power factor, torque, etc. Taking the electrical equipment as a generator as an example, the original electrical data includes at least one of the following: output current, output voltage, frequency, oil pressure, etc. Taking the electrical equipment as a capacitor as an example, the original electrical data includes at least one of the following: current, voltage, temperature, harmonic content, etc. Taking the electrical equipment as a distribution cabinet as an example, the original electrical data includes at least one of the following: current, voltage, temperature, switch state, grounding resistance, leakage current, etc. Taking the electrical equipment as a UPS system as an example, the original electrical data includes at least one of the following: input voltage, output voltage, battery voltage, battery charge and discharge current, inverter temperature, frequency, etc.

[0060] Figure 2 A schematic diagram of a device maintenance method provided in some embodiments, such as Figure 2 As shown, the method is applied to a computer device, and the method includes:

[0061] S201. Predictively analyze the original electrical data of the electrical equipment at multiple historical moments to obtain target electrical data at multiple future moments after the current moment.

[0062] The multiple historical moments may be moments before the current moment or moments that have occurred currently. In some embodiments, the moment may be replaced by one of the following: time step, time series, time period, time point, etc. In some embodiments, the raw electrical data at a moment may be the electrical data collected at the moment, or the raw electrical data at a moment may be the average value, maximum value, minimum value or median value of multiple electrical data collected during the period between the moment and the moment before the moment.

[0063] In some embodiments, the interval between two adjacent moments in the multiple historical moments may be the same as the interval between two adjacent moments in the multiple future moments. In some embodiments, the interval between two adjacent moments in the multiple historical moments may be the same as the interval between the last moment of the multiple historical moments and the first moment of the multiple future moments.

[0064] In some embodiments, among multiple historical moments and / or multiple future moments, the interval between two adjacent moments may be in the range of 1 second to 24 hours. Exemplarily, the interval may be 1 second, 30 seconds, 1 minute, 1 hour, 12 hours or 24 hours, etc.

[0065] In some embodiments, the number of moments in the multiple historical moments may be the same as the number of moments in the multiple future moments, or the number of moments in the multiple historical moments may be greater than or less than the number of moments in the multiple future moments.

[0066] In some embodiments, the parameter types in the target electrical data (e.g., parameter types such as current and voltage) may be the same as the parameter types in the original electrical data. In other embodiments, the parameter types in the target electrical data may be different from the parameter types in the original electrical data. Exemplarily, the parameter types in the target electrical data include the parameter types in the original electrical data and the parameter types corresponding to the feature data obtained by feature extraction of the original electrical data (e.g., parameter types such as current change and voltage change). Also exemplarily, the parameter types in the target electrical data include the parameter types corresponding to the feature data obtained by feature extraction of the original electrical data. Exemplarily, the feature data at each moment can be represented by the feature vector F={f1,f2,…,f m} means, f1,f2,…,f m Indicates the values ​​corresponding to different parameter types.

[0067] In some embodiments, for an electrical parameter type (such as temperature) of an electrical device, when there are multiple collected data (multiple temperature data) at a moment, the multiple collected data can be fused to obtain a fusion result, and the fusion result at that moment can be determined as the original electrical data at that moment.

[0068] Exemplarily, the weight corresponding to each of the multiple collected data can be obtained, the multiple weights are multiplied by the multiple collected data and then added to obtain a first result, the multiple weights are added to obtain a second result, and the ratio of the first result to the second result is determined as the fusion result corresponding to the multiple collected data.

[0069] For example, you can use Fusion of multiple collected data. i is the weight corresponding to each collected data, n is the total number of collected data, x i Indicates each collected data.

[0070] S202: Perform fault analysis on target electrical data at each future moment, and predict target fault probabilities of electrical equipment at each future moment.

[0071] Some implementation methods of S202 are described below:

[0072] In some embodiments, the target electrical data at each future time is input into the fault probability determination model, so that the fault probability determination model outputs the target fault probability of the electrical equipment at each future time.

[0073] In some embodiments, it is possible to use The target electrical data at each future moment is processed to obtain the calculation results at each future moment, wherein Z represents the calculation results at each future moment, X represents the target electrical data at each future moment, μ represents the mean of the target electrical data at each future moment, and σ represents the standard deviation of the target electrical data at each future moment; the target failure probability of the electrical equipment at each future moment is determined according to the comparison result of the calculation results at each future moment with the preset first failure threshold. For example, when the calculation result at a certain future moment is greater than the first failure threshold, or when the calculation results at a certain future moment and a moment after the future moment are both greater than the first failure threshold, the target failure probability of the electrical equipment at the future moment is determined to be 100%.

[0074] For example, for each future moment, the target electrical data e i , when the number of future moments is n, the calculation formula of the average value μ is The calculation formula for standard deviation σ is:

[0075] In some embodiments, μ+k×σ can be used to determine the second fault threshold; μ represents the mean value of the target electrical data at each future moment, k represents the selected multiple, which can be 2 or 3, and σ represents the standard deviation of the target electrical data at each future moment; according to the comparison result of the target electrical data at each future moment and the second fault threshold, the target fault probability of the electrical equipment at each future moment is determined. For example, when the target electrical data at a certain future moment is greater than the second fault threshold, or when the target electrical data at a certain future moment and a moment after the future moment are both greater than the second fault threshold, the target fault probability of the electrical equipment at the future moment is determined to be 100%. Exemplarily, if the computer device obtains that the power consumption of the electrical equipment at a future moment is 75kW, and the average power of the target electrical data obtained at each future moment is 55kW, and the standard deviation is 5kW, then the second fault threshold determined by the selected multiple of 2 is 55+2×5=65kW. Since 75kW is greater than 65kW, the computer device determines that the electrical equipment at the future moment has a fault, and the computer device can issue an early warning to notify the maintenance personnel to check.

[0076] In some embodiments, an optimal hyperplane can be constructed based on the original electrical data at each historical moment and the corresponding fault category to maximize the interval between categories. The original electrical data at each historical moment can be divided into two categories: normal or faulty. Then, the target electrical data at each future moment can be analyzed for faults based on the optimal hyperplane to predict the target fault probability of the electrical equipment at each future moment. In some embodiments, the computer device can determine the target fault probability of the electrical equipment at each future moment based on the distance of the target electrical data at each future moment relative to the optimal hyperplane. Exemplarily, by optimizing the target The restriction is Determine the optimal hyperplane to classify the raw electrical data into two categories: normal or faulty, where w is the weight vector of the hyperplane, b is the bias, and x i (i ranges from 1 to n) is the sample data, y i (i ranges from 1 to n) is the true label of the sample, Represents for all i.

[0077] In some embodiments, the target matrix can be obtained by subtracting the reconstructed matrix (also called the trained weight matrix) from the matrix formed by the target electrical data at each future moment; when the square of the 2-norm of the target matrix corresponding to a certain future moment is greater than a set threshold, the electrical equipment failure at that future moment is determined. Among them, the reconstructed matrix is ​​obtained by training based on the original electrical data of multiple historical moments. In some embodiments, the computer device can determine the target failure probability of the electrical equipment at each future moment based on the difference between the square of the 2-norm of the target matrix corresponding to each future moment and the set threshold. For example, the calculation formula of the reconstruction error ReconstructionError is: Among them, the matrix X represents the target electrical data at each future moment, is the reconstructed matrix, also called the trained weight matrix, Representation Matrix The squared 2-norm of . It is trained based on raw electrical data from multiple historical moments.

[0078] In some embodiments, when the target electrical data at each future moment includes a current value, a voltage value, and a temperature value, the computer device may obtain a preset current range of [I min ,I max ], voltage range is [V min ,V max ] and the temperature range is [T min ,T max ], the target electrical data at a certain future time meets the condition or or When , it is determined that the electrical equipment has a fault at that moment; wherein I, V and T represent the current value, voltage value and temperature value at a future moment respectively. In some embodiments, the current value and the maximum current value I at each future moment can be obtained. max The first difference between the current value at each future moment and the minimum current value I min The second gap between the voltage value at each future moment and the maximum voltage value V max The third gap between the voltage value at each future moment and the minimum voltage value V min The fourth gap between the temperature value at each future moment and the maximum temperature value T max The fifth difference between the temperature value at each future moment and the minimum temperature value T min The target failure probability of the electrical equipment at each future moment is determined according to the smaller value of the first gap and the second gap, the smaller value of the third gap and the fourth gap, and the smaller value of the fifth gap and the sixth gap.

[0079] In some embodiments, multiple numerical ranges are determined, and different numerical ranges in the multiple numerical ranges correspond to different fault probabilities. For the jth future moment, when the target electrical data at the jth future moment is within the target numerical range, the fault probability corresponding to the target numerical range is determined as the target fault probability at the jth future moment. The target numerical range is a numerical range with the smallest range among at least one numerical range, and at least one numerical range is a numerical range in which the target electrical data at the jth future moment is located.

[0080] In some embodiments, the computer device can also perform fault analysis on the target electrical data at each historical moment to predict the target fault probability of the electrical equipment at each historical moment. The method used for performing fault analysis on the target electrical data at each historical moment is similar to the method used for performing fault analysis on the target electrical data at each future moment, and this embodiment of the application will not be described in detail.

[0081] S203: Determine the maintenance strategy of the electrical equipment at each future moment according to the target failure probability at each future moment.

[0082] Exemplarily, for any future moment in the multiple future moments, the maintenance strategy may include indication information that maintenance is required and a target maintenance level, where the target maintenance level is one of the multiple maintenance levels, or the maintenance strategy includes indication information that maintenance is not required. For example, the maintenance strategy includes 0, indicating that maintenance is not required. For another example, the maintenance strategy includes 1, indicating that maintenance is required and the target maintenance level is level 1. For another example, the maintenance strategy includes 2, indicating that maintenance is required and the target maintenance level is level 2.

[0083] Among multiple maintenance levels, the higher the maintenance level, the lower the probability of failure of the electrical equipment after the electrical equipment is maintained at the maintenance level. Exemplarily, the current operating power of the electrical equipment can be reduced. The more it is reduced, the higher the maintenance level. For example, when the target maintenance level is level 1, the current operating power of the electrical equipment is reduced to the first operating power. When the target maintenance level is level 2, the current operating power of the electrical equipment is reduced to the second operating power. The second operating power is less than the first operating power. Another exemplary method, the maintenance methods corresponding to multiple maintenance levels from low to high can include, in sequence: prompting inspection, reducing the operating power of the electrical equipment, cleaning, lubricating, stopping operation, and replacing the electrical equipment.

[0084] In some embodiments, S203 may include: when the target failure probability at each future moment is less than or equal to the probability threshold, determining that the maintenance strategy of the electrical equipment at each future moment includes indication information that maintenance is not required.

[0085] In some embodiments, S203 may include: when at least one target failure probability of each future moment is greater than a probability threshold, obtaining the maximum failure probability among the target failure probabilities of each future moment, and determining the probability difference between the maximum failure probability and the probability threshold; obtaining the target future moment when the target failure probability of each future moment is greater than the probability threshold for the first time, and determining the time difference between the specific moment corresponding to the maximum failure probability and the target future moment; determining the target maintenance level of the target future moment according to the probability difference and the time difference, and determining the maintenance strategy of each future moment according to the target maintenance level of the target future moment: the maintenance strategy at the target future moment includes the indication information that needs maintenance and the target maintenance level, and the maintenance strategy at other moments other than the target future moment in each future moment includes the indication information that does not need maintenance. In some embodiments, a mapping relationship between the probability difference, the time difference, and the maintenance level may be stored in the computer device, and the computer device may determine the target maintenance level according to the mapping relationship.

[0086] In some embodiments, S203 may include: obtaining a plurality of pre-set maintenance strategies; updating the target failure probability of the electrical equipment at each future moment to a specific failure probability according to the plurality of maintenance strategies; determining the target maintenance strategy from the plurality of maintenance strategies according to the specific failure probability at each future moment, the maintenance cost corresponding to the target maintenance level, and the fault repair cost, so as to obtain the maintenance strategy at each future moment.

[0087] Each of the multiple maintenance strategies corresponds to a future time when maintenance is required.

[0088] In some embodiments, different maintenance strategies represent performing maintenance of different maintenance levels at the same time in multiple future moments, or performing maintenance of the same maintenance level at different times in multiple future moments. For example, different maintenance strategies represent performing maintenance of the first maintenance level at different times in multiple future moments.

[0089] Exemplarily, a target maintenance strategy is determined from multiple maintenance strategies based on specific failure probabilities at each future moment, maintenance costs corresponding to the target maintenance level, and fault repair costs, including: determining multiple cost values ​​corresponding to the multiple maintenance strategies respectively based on specific failure probabilities at each future moment, maintenance costs corresponding to the target maintenance level, and fault repair costs, and determining the maintenance strategy corresponding to the smallest cost value among the multiple cost values ​​as the target maintenance strategy.

[0090] For example, an implementation method for determining the cost value corresponding to each maintenance strategy may include: determining the total probability of specific failure probabilities at multiple future moments corresponding to each maintenance strategy; multiplying the total probability by the failure repair cost to obtain a first cost; multiplying the level value corresponding to the target maintenance level by the failure repair cost to obtain a second cost; and adding the first cost to the second cost to obtain the cost value corresponding to each maintenance strategy.

[0091] For example, the maintenance strategy for each future moment can be determined by a linear programming method, wherein the loss function corresponding to the optimization model of the linear programming method is: Among them, m i represents the maintenance decision at the i-th moment (indicating the target maintenance level that needs maintenance or no maintenance, for example, m i 0 means no maintenance is required at the i-th moment, or m i 1 means the maintenance level at the i-th moment is 1, m i 2 means the maintenance level at the i-th moment is 2), f i represents the specific failure probability at each future moment determined according to the maintenance decision at each moment. For example, when each maintenance decision indicates that maintenance is not required, the specific failure probability at each future moment is the target failure probability, C m represents the maintenance cost corresponding to the target maintenance level indicated by the maintenance decision, C f Represents the failure repair cost.

[0092] S204: Perform maintenance management on the electrical equipment according to the maintenance strategy at each future moment.

[0093] In some embodiments, S204 may include: when the target failure probability at each future moment is less than or equal to the probability threshold, outputting first prompt information according to the maintenance strategy at each future moment, the first prompt information being used to indicate that maintenance of the electrical equipment is not required.

[0094] In some embodiments, S204 may include: when at least one of the target failure probabilities at each future moment is greater than a probability threshold, maintaining the electrical equipment according to the maintenance strategy at each future moment.

[0095] In some embodiments, S204 may include: when at least one target failure probability among the target failure probabilities at each future moment is greater than a probability threshold, outputting second prompt information according to the maintenance strategy at each future moment, the second prompt information being used to indicate that the electrical equipment is to be maintained at a target maintenance level at the target future moment. In this way, relevant personnel may perform maintenance on the electrical equipment at the target future moment according to the second prompt information.

[0096] In an embodiment of the present application, by predicting the target failure probability of electrical equipment at each future moment, determining the maintenance strategy of the electrical equipment at each future moment according to the target failure probability at each future moment, and performing maintenance management on the electrical equipment according to the maintenance strategy at each future moment, it is possible to determine in advance the maintenance plan for maintaining and managing the electrical equipment, and perform maintenance management on the electrical equipment according to the determined maintenance plan, which helps to discover potential problems with the electrical equipment at future moments after the current moment, effectively prevent the occurrence of failures, reduce the probability of electrical equipment failure shutdowns, and improve the operating stability of the power system.

[0097] In some embodiments, maintenance management of electrical equipment is performed according to maintenance strategies at each future moment, which may include: when the maintenance strategy at each future moment includes that maintenance is required at a target future moment and the maintenance method is to reduce the operating power of the electrical equipment to a target operating power, at the target future moment, the operating power of the electrical equipment is reduced to the target operating power.

[0098] Figure 3 A flowchart of a method for determining a maintenance strategy for electrical equipment at each future moment is provided for some embodiments, such as Figure 3 As shown, the method is applied to a computer device, and the method includes:

[0099] S301. Obtain a specified failure probability of at least one other electrical device other than the electrical device at each future moment.

[0100] S302: Determine the total operating power of the electrical device and at least one other electrical device.

[0101] S303: Determine a maintenance strategy for the electrical equipment at each future moment according to the total operating power, the target failure probability at each future moment, and the specified failure probability at each future moment.

[0102] In some embodiments of the present application, the sum of the operating powers of the electrical device and at least one other electrical device should be greater than or equal to the total operating power.

[0103] Taking the electrical equipment as the first electrical equipment and at least one other electrical equipment including the second electrical equipment as an example, if the failure probability of the first electrical equipment at the target future moment is 90%, the operating power of the first electrical equipment at the target future moment is 800W, the failure probability of the second electrical equipment at the target future moment is 0.5%, the operating power of the second electrical equipment at the target future moment is 800W, and the total operating power is 800W, then the maintenance strategy for the first electrical equipment and the second electrical equipment at each future moment is: update the operating power of the first electrical equipment at the target future moment to 0, and keep the operating power of the second electrical equipment at the target future moment unchanged.

[0104] In some embodiments, the operating power of electrical equipment and at least one other electrical equipment can be scheduled by a linear programming method, wherein the optimization model of the linear programming method is to minimize a target value, and the target value is the result of multiplying and adding the cost coefficients of multiple electrical equipment (including the electrical equipment and at least one other electrical equipment) and the operating powers of the multiple electrical equipment accordingly; the restriction conditions of the linear programming method include: the operating power of each device is greater than or equal to the minimum operating power of each device and less than or equal to the maximum operating power of each device; the sum of the operating powers of multiple electrical equipment is equal to the total operating power.

[0105] Exemplarily, the loss function corresponding to the optimization model of the linear programming method is The corresponding constraints are ∑P i =P 最小总 Among them, P i is the power generation of the ith device, c i is the cost coefficient of the ith equipment. i_min is the minimum operating power of the ith device, P i_max is the maximum operating power of the ith device, It means that for any i, P 最小总 is the minimum total operating power.

[0106] Figure 4 A flowchart of a method for determining target electrical data at multiple future moments is provided for some embodiments, such as Figure 4 As shown, the method is applied to a computer device, and the method includes:

[0107] S401. Perform feature analysis on original electrical data at multiple historical moments to obtain feature data at multiple historical moments.

[0108] In some embodiments, the characteristic data includes at least one of the following: current fluctuation frequency data, voltage fluctuation frequency data, voltage jump rate data, temperature change rate data, frequency data of temperature greater than a first temperature threshold, frequency data of temperature less than a second temperature threshold, etc. For example, if the computer device can obtain multiple current data from each historical moment to the last historical moment, the characteristic data of each historical moment includes current fluctuation frequency data. For another example, if the computer device can obtain multiple voltage data from each historical moment to the last historical moment, the characteristic data of each historical moment includes voltage fluctuation frequency data and / or voltage jump rate data. For another example, if the original electrical data of each historical moment includes temperature data, the characteristic data of each historical moment includes temperature change rate data. For another example, if the computer device can obtain multiple temperature data from each historical moment to the last historical moment, the characteristic data of each historical moment includes at least one of the following: frequency data of temperature greater than a first temperature threshold, frequency data of temperature less than a second temperature threshold, etc.

[0109] S402: Merge the original electrical data of multiple historical moments and the characteristic data of multiple historical moments correspondingly to obtain relevant data of multiple historical moments.

[0110] In some embodiments, the characteristic data at each historical moment is merged with the original electrical data at each historical moment to obtain the relevant data at each historical moment.

[0111] S403: Classify the relevant data of multiple historical moments to obtain the relevant data of multiple historical moments in each category.

[0112] The following describes an implementation method for classifying related data at multiple historical moments:

[0113] (1) Initialize 2 or 3 center points. For example, the 2 center points correspond to the following two categories: fault and normal. For example, the 3 center points correspond to the following three categories: fault, warning, and normal.

[0114] (2) Calculate the distance between the relevant data of each historical moment and each center point among the relevant data of multiple historical moments, and assign the relevant data of each historical moment to the center point closest to it.

[0115] (3) Update the position of each center point. The new position of each center point is determined in the following manner: add the corresponding data of multiple historical moments corresponding to each center point to obtain a third result; divide the third result by the length of the vector corresponding to the coordinates of each center point, and divide the third result by the length of the vector to obtain the coordinates of the new position of each center point. For example, the new position of each center point is Among them, ∑xi Indicates the center point c i The corresponding data x for all historical moments i The sum of |c i | represents the length of the vector corresponding to the coordinates of each center point.

[0116] (4) Repeat steps (2) and (3) until the center point no longer changes or the maximum number of iterations is reached.

[0117] S404: Determine target electrical data at multiple historical moments according to relevant data at multiple historical moments in each category.

[0118] In some embodiments, S404 may include: centralizing the relevant data of each historical moment in each category of relevant data to obtain the centralized data of each historical moment in each category; determining the eigenvector of the covariance matrix corresponding to the centralized data of each historical moment in each category; and determining a preset number of values ​​in the eigenvector of each historical moment in each category as the target electrical data of each historical moment in each category.

[0119] In some embodiments, the relevant data of each historical moment in each category of relevant data is centrally processed to obtain the centralized data of each historical moment in each category, which may include: subtracting the average value of the relevant data of multiple historical moments corresponding to each category from the relevant data of each historical moment in each category of relevant data to obtain the centralized data of each historical moment in each category. For example, using X′=X-μ, the relevant data of each historical moment in each category of relevant data is centrally processed to obtain the centralized data of each historical moment in each category. Among them, X represents the relevant data of each historical moment in each category of relevant data, μ represents the average value of the relevant data of each historical moment in each category of relevant data, and X′ represents the centralized data of each historical moment in each category.

[0120] In some embodiments, a predetermined matrix corresponding to the relevant data of each historical moment of each category may be obtained; a covariance matrix corresponding to the relevant data of each historical moment of each category may be determined based on the product of the predetermined matrix and the transpose of the predetermined matrix; then, the eigenvalues ​​and eigenvectors of the covariance matrix may be calculated to obtain the eigenvectors of each historical moment of each category. Determine the covariance matrix corresponding to the centralized data of each historical moment of each category. Wherein, C represents the covariance matrix corresponding to the centralized data of each historical moment of each category; A represents the predetermined matrix corresponding to the relevant data of each historical moment of each category; n represents the number of moments of multiple historical moments corresponding to each category. In this way, when the covariance matrix is ​​obtained, the eigenvalues ​​and eigenvectors of the covariance matrix can be calculated.

[0121] S405 , predict and analyze the target electrical data at multiple historical moments to obtain the target electrical data at multiple future moments.

[0122] In some embodiments, S405 may include: using target electrical data of multiple historical moments to train parameters in a preset prediction model to obtain a trained target prediction model; using the target prediction model to process the target electrical data of the i-th moment to obtain the target electrical data of the i+1-th moment; wherein i is an integer greater than or equal to 1, and i+1 is less than or equal to the total number of moments of multiple future moments; determining the target electrical data of the i+1-th moment obtained each time as the target electrical data of each future moment. Wherein, when i=1, the i-th moment is the last moment of multiple historical moments.

[0123] Exemplarily, the target prediction model is used to process the target electrical data of the last moment of multiple historical moments to obtain the target electrical data of the first future moment, and then the target prediction model is used to process the target electrical data of the first future moment to obtain the target electrical data of the second future moment, and then the target prediction model is used to process the target electrical data of the second future moment to obtain the target electrical data of the third future moment, and so on, to obtain the target electrical data of multiple future moments.

[0124] The following describes an implementation method of using target electrical data at multiple historical moments to train parameters in a preset prediction model to obtain a trained target prediction model:

[0125] The preset prediction model corresponding to the following formulas (1) to (6) and the target electrical data x at the sth historical moment are used: s , predict the target electrical data at the s+1th historical moment

[0126] Forget Gate t :f s =σ(W f ·[h s-1 ,x s ]+b f ) (1);

[0127] Input Gate i t :i s =σ(W i ·[h s-1 ,x s ]+b i ) (2);

[0128] Candidate value

[0129] Update cell status:

[0130] Output gate o t :o s =σ(W o ·[h s-1 ,x s ]+b o )(5);

[0131] Update hidden state:

[0132] In formulas (1) to (6), W f , W i , W C , W o represents the weight, b f , b i , b C , b o represents the bias, σ() is the activation function, and h() is the hyperbolic tangent function.

[0133] The following loss function is used to train the weights and biases in the preset prediction model: Among them, MSE represents the mean square error loss function, represents the target electrical data at the sth historical moment predicted by the preset prediction model, n is the number of parameter categories included in the target electrical data, x s Represents the target electrical data at the real s-th historical moment. Exemplarily, the model parameters can be updated by a back-propagation algorithm to optimize the loss function.

[0134] For example, the historical current data of the electrical equipment is as follows: [10, 11, 12, 13, 14]. The trained target prediction model can predict the trend of the current in the future time step. For example, the predicted result is [15, 16, 17], which means that the current of the equipment will gradually increase in the future operation.

[0135] In this way, the equipment prediction unit can effectively determine the future trends of electrical equipment and promptly detect potential failure risks, thereby achieving more intelligent maintenance management and decision support.

[0136] Figure 5 A flowchart of a method for determining target electrical data at multiple future moments is provided for other embodiments, such as Figure 5 As shown, the method is applied to a computer device, and the method includes:

[0137] S501. Obtain random errors and p weight coefficients; wherein p is the number of moments in multiple historical moments.

[0138] In some embodiments, the random error and the p weight coefficients may be pre-configured in the computer device. In other embodiments, the random error and the p weight coefficients may be trained based on the original electrical data of multiple early moments before multiple historical moments.

[0139] S502 , using p weight coefficients to perform weighted fusion on the target electrical data from the t-th moment to the t+p-1-th moment, respectively, to obtain the t+p-th target data.

[0140] Here, t is an integer greater than or equal to 1, and t+p is less than or equal to the total number of the multiple future moments.

[0141] Among them, when t=1, the tth moment is the first moment of multiple historical moments, and the target electrical data from the tth moment to the t+p-1th moment is the original electrical data.

[0142] S503, determining the target electrical data at the t+pth moment according to the t+pth target data and the random error;

[0143] S504, determining the target electrical data at the t+pth moment obtained each time as the target electrical data at each future moment.

[0144] Using the method of the embodiment of the present application, p weight coefficients are used to perform weighted fusion on the target electrical data from the 1st moment to the pth moment, respectively, to obtain the p+1th target data, and then the p+1th target electrical data (i.e., the target data at the 1st future moment) is determined based on the p+1th target data and random errors. Then, p weight coefficients are used to perform weighted fusion on the target electrical data from the 2nd moment to the p+1th moment, respectively, to obtain the p+2th target data, and then the p+2th target electrical data (i.e., the target data at the 2nd future moment) is determined based on the p+2th target data and random errors. Then, p weight coefficients are used to perform weighted fusion on the target electrical data from the 3rd moment to the p+2th moment, respectively, to obtain the p+3th target data, and then the p+3th target electrical data (i.e., the target data at the 3rd future moment) is determined based on the p+3th target data and random errors. By analogy, target electrical data at multiple future moments can be obtained.

[0145] For example, according to Determine the target electrical data at time t+p, where α represents the bias, β1, β2, and β p represents the first weight coefficient, the second weight coefficient and the pth weight coefficient (all included in the above-mentioned p weight coefficients); Y t , Y t+1 and Y t+p-1Respectively represent the target electrical data at the t-th (i.e., t-th) moment, the target electrical data at the t+1-th (i.e., t+1-th) moment, and the target electrical data at the t+p-1-th (i.e., t+p-1-th) moment; t represents random error; Represents the predicted target electrical data at the t+pth moment. p And t It is trained by using the original electrical data from multiple early moments before multiple historical moments.

[0146] For example, you can Loss Function As well as the original electrical data of multiple early moments before multiple historical moments, α, β1, β2, β p And t Conduct training.

[0147] in, represents the predicted electrical data at the rth early moment, Y r represents the original electrical data at the rth early moment, and N represents the number of parameter categories included in each original electrical data.

[0148] The embodiment of the present application is an intelligent monitoring system for electrical equipment based on artificial intelligence (i.e., the equipment maintenance system mentioned above), which improves the operational safety and maintenance efficiency of electrical equipment through real-time data collection, intelligent analysis, and fault prediction. Using artificial intelligence algorithms, the system can monitor the operating status of equipment in real time, accurately predict future operating trends, and issue early warnings in a timely manner, helping to effectively reduce the equipment failure rate and improve the reliability and safety of equipment operation.

[0149] Figure 6 A schematic diagram of the structure of an intelligent monitoring system provided in some embodiments, such as Figure 6 As shown, the intelligent monitoring system 600 includes: a data acquisition module 601, an operation monitoring module 602, an electrical data prediction module 603, a fault prediction module 604, a system management module 605, a remote monitoring module 606 and a central monitoring platform 607.

[0150] The data acquisition module 601 is used to collect data information of electrical equipment and obtain the original electrical data of multiple historical moments. The operation monitoring module 602 is used to monitor the original electrical data of electrical equipment at multiple historical moments. The electrical data prediction module 603 predicts and analyzes the original electrical data of electrical equipment at multiple historical moments to obtain the target electrical data at multiple future moments after the current moment. The fault prediction module 604 is used to perform fault analysis on the target electrical data at each future moment, predict the target fault probability of the electrical equipment at each future moment, and perform fault analysis on the original electrical data at each historical moment to predict the target fault probability of the electrical equipment at each historical moment. The system management module 605 is used to determine the maintenance strategy of the electrical equipment at each future moment, and perform maintenance management on the electrical equipment according to the maintenance strategy at each future moment, and to determine the maintenance strategy of the electrical equipment at each historical moment, and perform maintenance management on the electrical equipment according to the maintenance strategy at each historical moment. The remote monitoring module 606 is used to monitor the maintenance management of the electrical equipment. The central monitoring platform 607 is used to obtain the monitoring information of the remote monitoring module 606, and can also obtain the maintenance strategy for each future moment from the system management module 605, and perform maintenance management on the electrical equipment according to the maintenance strategy for each future moment.

[0151] Figure 7 A flowchart of a method for acquiring raw electrical data provided in some embodiments, such as Figure 7 As shown, the method includes:

[0152] S701. A data collector collects original electrical data of electrical equipment.

[0153] In some embodiments, the data collector may include a sensor.

[0154] S702. The data collector transmits the original electrical data to a data storage repository.

[0155] S703. The computer device obtains raw electrical data from the data repository.

[0156] Figure 8 A flowchart of a method for determining whether an electrical device is faulty is provided in some embodiments, such as Figure 8 As shown, the method is applied to a computer device, and the method includes:

[0157] S801. Obtain original electrical data of electrical equipment at multiple historical moments.

[0158] S802: Determine target electrical data at multiple historical moments based on original electrical data at multiple historical moments.

[0159] S803. Determine whether the electrical equipment at each historical moment is faulty based on the target electrical data at each historical moment.

[0160] S804. When an electrical device fails at a specified time among multiple historical times, a fault analysis report is generated.

[0161] Exemplarily, in the event of an electrical device failure at a specified time, the computer device may also output an alarm message.

[0162] S805. When all electrical equipment at each historical moment is not faulty, the original electrical data is continuously monitored.

[0163] By continuously monitoring the raw electrical data, the raw electrical data of the next batch of historical moments can be obtained.

[0164] Fig. 9 A flowchart of a method for determining whether an electrical device is faulty is provided for other embodiments, such as Fig. 9 As shown, the method is applied to a computer device, and the method includes:

[0165] S901. Obtain original electrical data of electrical equipment at multiple historical moments.

[0166] S902: Perform forecast analysis on the original electrical data at multiple historical moments to obtain target electrical data at multiple future moments after the current moment.

[0167] S903: Determine whether the electrical equipment at each future moment is faulty based on the target electrical data at each future moment.

[0168] S904. When an electrical device fails at a target future time among multiple future time points, a failure analysis report is generated.

[0169] Exemplarily, in the event of an electrical device failure at a target future time, the computer device may also output an alarm message.

[0170] S905. When the electrical equipment at each future moment does not fail, the original electrical data is continuously monitored.

[0171] Fig.10 A flowchart of a maintenance management method provided in some embodiments, such as Fig.10 As shown, the method is applied to a computer device, and the method includes:

[0172] S1001. Obtain target failure probability at each future moment.

[0173] S1002. Determine a maintenance strategy for the electrical equipment at each future moment according to the target failure probability at each future moment.

[0174] S1003. Perform maintenance management on electrical equipment according to maintenance strategies at each future moment.

[0175] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, the steps corresponding to at least one optimization model in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0176] The artificial intelligence-based intelligent monitoring system for electrical equipment provided in the embodiment of the present application can provide at least one of the following functions through the collaborative work of multiple units:

[0177] Real-time monitoring: The key parameters of electrical equipment (such as current, voltage, temperature, etc.) are collected in real time through the data acquisition unit. The artificial intelligence algorithm and big data analysis in the equipment operation monitoring unit can detect the operating status and abnormal conditions of the equipment in real time. Real-time data monitoring can issue early warnings in time when electrical equipment is abnormal, preventing potential faults from evolving into serious safety accidents.

[0178] Automatic alarm and fault analysis: When the system detects equipment abnormalities, it will automatically generate an abnormality report through the equipment operation monitoring unit and respond quickly through the abnormal alarm mechanism, effectively reducing the losses caused by equipment failures and ensuring the safety of the electrical system.

[0179] Equipment failure prediction: Using the equipment failure prediction unit and the data trend prediction model, the system can predict the future state changes of electrical equipment in the time dimension based on the historical data and current state of the equipment. Through deep learning and time series prediction models, the system can identify the time point when the equipment may fail, so as to take maintenance measures in advance.

[0180] Preventive maintenance: Through prediction and analysis, the system can not only issue early warnings when equipment is about to fail, but also generate maintenance plans and proactively arrange preventive maintenance for equipment. This data-driven maintenance model is more scientific than the traditional scheduled maintenance model, effectively extending the service life of equipment and reducing economic losses caused by downtime.

[0181] Data fusion and optimized scheduling: The system management unit integrates the equipment operation monitoring and fault prediction results, and optimizes the equipment operation scheduling through data analysis. Using intelligent algorithms and data fusion technology, the system can effectively allocate power resources in power grid load management, reduce energy waste, and ensure that electrical equipment works in the best operating state.

[0182] Remote monitoring and intelligent management: The remote monitoring unit enables the system to realize centralized monitoring and management of distributed electrical equipment. By remotely acquiring equipment operation status data, managers can grasp the operation status of equipment in real time without visiting the site, conduct intelligent scheduling and optimize configuration, and improve the efficiency and accuracy of operation and maintenance.

[0183] Comprehensive monitoring and analysis: Through monitoring, fault analysis, prediction and maintenance management covering the entire life cycle of the equipment, the system can optimize the equipment's full life cycle management strategy. From equipment installation, operation, maintenance, to equipment scrapping, the system can always provide comprehensive data support, effectively improve equipment operating efficiency, extend equipment service life, and reduce equipment operation and maintenance costs throughout the life cycle.

[0184] The embodiment of the present application provides an intelligent monitoring system for electrical equipment based on artificial intelligence, which can perform real-time monitoring, fault analysis, fault prediction, remote management and maintenance scheduling of electrical equipment. The system is mainly composed of a data acquisition unit, an equipment operation monitoring unit, an equipment fault prediction unit, a system management unit and a remote monitoring unit. The following describes some implementation methods of these units.

[0185] Implementation of the data acquisition unit: The data acquisition unit is used to collect the operating status data of the electrical equipment, including but not limited to at least one parameter such as current, voltage, temperature, load rate, power factor, etc. The unit obtains the real-time operating data of the electrical equipment through sensors and data collectors, and transmits the data to the central processing module for analysis. Exemplary implementation steps may include: installing a variety of sensors on the electrical equipment to monitor key operating parameters, including voltage sensors, current sensors, temperature sensors, etc. The data acquisition unit transmits real-time data to the central processing system through the collector, and the system can be connected to the central processing module by wire or wireless means to ensure the real-time nature of data acquisition. All collected data will be stored in the data repository as the basic data for subsequent fault analysis, predictive analysis and remote monitoring.

[0186] Implementation of the equipment operation monitoring unit: The equipment operation monitoring unit uses artificial intelligence algorithms and big data technology to analyze the collected equipment operation data in real time to identify the normal operation status and potential failure risks of electrical equipment. Exemplary implementation steps may include: First, the real-time data collected by the data acquisition unit is combined with historical data to establish a data model for electrical equipment. The model is adaptively adjusted according to different types of electrical equipment to ensure the accuracy of the analysis. The real-time data is classified and processed using big data analysis technology to extract the characteristic values ​​of the equipment operation status. The health status of the equipment is analyzed through the feature extraction algorithm, including normal status, minor abnormalities, serious abnormalities, etc. The abnormal status of the equipment is further analyzed using artificial intelligence algorithms, especially neural network-based classification algorithms. The algorithm can learn based on historical fault data to identify complex equipment abnormalities. When an abnormal state is detected, the operation monitoring unit generates a fault analysis report showing the abnormal type of the equipment, possible causes, and recommended maintenance solutions.

[0187] Implementation of the equipment failure prediction unit: The equipment failure prediction unit uses a deep learning model to predict the future operating status of electrical equipment based on the analysis results of the equipment operation monitoring unit, combined with data trend prediction technology. Exemplary implementation steps may include: First, collect historical data and real-time operation data of electrical equipment, input them into the deep learning model, and use these data to train and optimize the model. Use a deep learning model suitable for time series data to analyze the trend of the state of electrical equipment over time. The model determines the future state of the equipment by predicting the changing trends of key parameters of electrical equipment (such as voltage, current, temperature, etc.) in the future. If the predicted data exceeds the normal operating parameter range of the equipment, the system will generate a fault prediction report in advance and issue an alarm to prevent possible equipment failures in the future.

[0188] Implementation of the system management unit: The system management unit is responsible for managing the results of operation monitoring, fault analysis and fault prediction, and optimizing the maintenance and scheduling of equipment. Exemplary implementation steps may include: The management unit first generates an intelligent maintenance management plan based on the equipment operation status, fault analysis report and fault prediction results. The plan includes regular maintenance time, maintenance steps and parts that may need to be replaced. Based on the data analysis results, the management unit can adjust the scheduling of electrical equipment and optimize the operating efficiency of the equipment. The system automatically generates scheduling data for adjusting the load distribution in the power system. Equipment operation data and maintenance scheduling data are merged to form an electrical equipment database. The database is used to continuously update the equipment operation model and enhance the system's self-learning and optimization capabilities.

[0189] Implementation of the remote monitoring unit: The remote monitoring unit can obtain the operating status data of the electrical equipment in real time, monitor the power consumption of the equipment, and perform remote scheduling through data fusion results. Exemplary implementation steps may include: the remote monitoring unit transmits the power consumption data and operating status data of the electrical equipment to the central monitoring platform in real time through wireless communication technology or Internet connection. The central monitoring platform generates equipment operation reports and power consumption status monitoring results by integrating the historical data, real-time data and predicted data of the equipment. When the operating status of the electrical equipment is abnormal, the system can issue an alarm through the remote platform and automatically generate a fault analysis report. For minor faults, the remote monitoring system can trigger an automated repair program or a remote scheduling task.

[0190] Based on the same inventive concept, the embodiment of the present application also provides an equipment maintenance device for implementing the equipment maintenance method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more equipment maintenance device embodiments provided below can refer to the limitations on the equipment maintenance method above, and will not be repeated here.

[0191] In an exemplary embodiment, Fig.11 A schematic diagram of the structure of the equipment maintenance device provided in some embodiments, such as Fig.11 As shown, the equipment maintenance device 1100 includes:

[0192] The prediction analysis module 1101 is used to perform prediction analysis on the original electrical data of the electrical equipment at multiple historical moments to obtain target electrical data at multiple future moments after the current moment;

[0193] The fault analysis module 1102 is used to perform fault analysis on target electrical data at each future moment and predict target fault probabilities of electrical equipment at each future moment;

[0194] A strategy determination module 1103 is used to determine the maintenance strategy of the electrical equipment at each future moment according to the target failure probability at each future moment;

[0195] The maintenance management module 1104 is used to perform maintenance management on the electrical equipment according to the maintenance strategy at each future moment.

[0196] In some embodiments, the maintenance management module 1104 is also used to reduce the operating power of the electrical equipment to the target operating power at the target future moment in the maintenance strategy for each future moment, including when maintenance is required at the target future moment and the maintenance method is to reduce the operating power of the electrical equipment to the target operating power at the target future moment.

[0197] In some embodiments, the strategy determination module 1103 includes: a failure probability acquisition unit and a maintenance strategy determination unit; wherein the failure probability acquisition unit is used to obtain the specified failure probability of at least one other electrical equipment other than the electrical equipment at each future moment; the maintenance strategy determination unit is used to determine the total operating power of the electrical equipment and at least one other electrical equipment, and to determine the maintenance strategy of the electrical equipment at each future moment based on the total operating power, the target failure probability at each future moment and the specified failure probability at each future moment.

[0198] In some embodiments, the prediction and analysis module 1101 includes an analysis unit, a merging unit, a classification unit, an electrical data determination unit and a prediction unit; wherein the analysis unit is used to perform feature analysis on the original electrical data of multiple historical moments to obtain feature data of multiple historical moments; the merging unit is used to merge the original electrical data of multiple historical moments and the feature data of multiple historical moments correspondingly to obtain relevant data of multiple historical moments; the classification unit is used to classify the relevant data of multiple historical moments to obtain relevant data of multiple historical moments under each category; the electrical data determination unit is used to determine the target electrical data of multiple historical moments based on the relevant data of multiple historical moments under each category; the prediction unit is used to perform predictive analysis on the target electrical data of multiple historical moments to obtain target electrical data of multiple future moments.

[0199] In some embodiments, the electrical data determination unit includes: a centralization processing subunit, a feature vector determination subunit and an electrical data determination subunit; wherein the centralization processing subunit is used to perform centralization processing on the relevant data of each historical moment in each category of relevant data to obtain the centralized data of each historical moment of each category; the feature vector determination subunit is used to determine the feature vector of the covariance matrix corresponding to the centralized data of each historical moment of each category; the electrical data determination subunit is used to determine a preset number of values ​​in the feature vector of each historical moment of each category as the target electrical data of each historical moment of each category.

[0200] In some embodiments, the prediction unit includes a training subunit and an electrical data processing subunit; wherein the training subunit is used to use the target electrical data of multiple historical moments to train the parameters in the preset prediction model to obtain the trained target prediction model; the electrical data processing subunit is used to use the target prediction model to process the target electrical data at the i-th moment to obtain the target electrical data at the i+1-th moment; wherein i is an integer greater than or equal to 1, and i+1 is less than or equal to the total number of moments in the future; the electrical data processing subunit is also used to determine the target electrical data at the i+1-th moment obtained each time as the target electrical data for each future moment.

[0201] In some embodiments, the prediction and analysis module includes a weight coefficient acquisition unit, a fusion unit, and an electrical data determination unit; wherein the weight coefficient acquisition unit is used to obtain random errors and p weight coefficients; wherein p is the number of moments in multiple historical moments; the fusion unit is used to use p weight coefficients to weightedly fuse the target electrical data from the tth moment to the t+p-1th moment, respectively, to obtain the t+pth target data; t is an integer greater than or equal to 1, and t+p is less than or equal to the total number of moments in multiple future moments; the electrical data determination unit is used to determine the target electrical data at the t+pth moment based on the t+pth target data and the random error; the electrical data determination unit is also used to determine the target electrical data at the t+pth moment obtained each time as the target electrical data for each future moment.

[0202] Each module in the above-mentioned equipment maintenance device can be implemented in whole or in part by software, hardware and their combination. Each module can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to each module above.

[0203] In an exemplary embodiment, a computer device is provided. Fig.12 A schematic diagram of the structure of a computer device provided for some embodiments, the computer device includes a processor, a memory, an input / output interface, a communication interface, a display unit and an input device. The processor, the memory and the input / output interface are connected via a system bus, and the communication interface, the display unit and the input device are connected to the system bus via the input / output interface. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, near field communication (Near Field Communication, NFC) or other technologies. When the computer program is executed by the processor, a device maintenance method is implemented. The display unit of the computer device is used to form a visually visible picture, which can be a display screen, a projection device or a virtual reality imaging device. The display screen can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the computer device shell, or an external keyboard, touchpad or mouse.

[0204] Those skilled in the art will understand that Fig.12 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0205] For example, in an exemplary embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the following steps when executing the computer program: performing predictive analysis on original electrical data of electrical equipment at multiple historical moments to obtain target electrical data at multiple future moments after the current moment; performing fault analysis on the target electrical data at each future moment to predict the target failure probability of the electrical equipment at each future moment; determining the maintenance strategy of the electrical equipment at each future moment based on the target failure probability at each future moment; and performing maintenance management on the electrical equipment based on the maintenance strategy at each future moment.

[0206] In one embodiment, a computer-readable storage medium is provided, and when a computer program is executed by a processor, the steps of the method provided in any of the above embodiments are implemented.

[0207] For example, in an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: predictive analysis is performed on the original electrical data of the electrical equipment at multiple historical moments to obtain target electrical data at multiple future moments after the current moment; fault analysis is performed on the target electrical data at each future moment to predict the target failure probability of the electrical equipment at each future moment; based on the target failure probability at each future moment, a maintenance strategy for the electrical equipment at each future moment is determined; and maintenance management is performed on the electrical equipment based on the maintenance strategy at each future moment.

[0208] A person skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods.

[0209] The processor, each functional module or each functional unit in any embodiment of the present application may include any one or more of the following integrations: general-purpose processor, application-specific integrated circuit (ASIC), digital signal processor (DSP), digital signal processing device (DSPD), programmable logic device (PLD), field programmable gate array (FPGA), central processing unit (CPU), graphics processing unit (GPU), embedded neural network processor (neural-network processing units, NPU), controller, microcontroller, microprocessor, programmable logic device, discrete gate or transistor logic device, discrete hardware component, data processing logic based on quantum computing, artificial intelligence (AI) processor, etc. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0210] The memory or computer-readable storage medium in any embodiment of the present application may include at least one of a non-volatile memory and a volatile memory. Non-volatile memory includes the integration of one or more of the following: Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Ferromagnetic Random Access Memory (FRAM), Flash Memory, Magnetic Surface Storage, Optical Disc, Compact Disc Read-Only Memory (CD-ROM), Magnetic Tape, Floppy Disk, Flash Memory, Optical Storage, High-density Embedded Non-volatile Memory, Resistive Random Access Memory (ReRAM), Magnetoresistive Random Access Memory (MRAM), Ferroelectric Random Access Memory (FRAM), Phase Change Memory (PCM), Graphene Memory, Volatile Memory, etc. Volatile memory includes an integration of one or more of the following: Random Access Memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), etc.

[0211] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0212] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for equipment maintenance, characterized in that: The method comprises: Perform predictive analysis on the original electrical data of electrical equipment at multiple historical moments to obtain target electrical data at multiple future moments after the current moment; Performing fault analysis on target electrical data at each of the future moments to predict target fault probabilities of the electrical equipment at each of the future moments; Determining a maintenance strategy for the electrical equipment at each of the future moments according to the target failure probability at each of the future moments; The electrical equipment is maintained and managed according to the maintenance strategy at each future moment.

2. The method according to claim 1, characterized in that The maintenance management of the electrical equipment according to the maintenance strategy at each future moment includes: The maintenance strategy at each of the future moments includes reducing the operating power of the electrical equipment to the target operating power at the target future moment when maintenance is required and the maintenance method is to reduce the operating power of the electrical equipment to the target operating power.

3. The method according to claim 1, characterized in that Determining the maintenance strategy of the electrical equipment at each of the future moments according to the target failure probability at each of the future moments includes: Obtaining a specified failure probability of the electrical equipment at each future moment; determining a total operating power of the electrical device and the at least one other electrical device; A maintenance strategy for the electrical equipment at each of the future moments is determined based on the total operating power, the target failure probability at each of the future moments, and the specified failure probability at each of the future moments.

4. The method according to any one of claims 1 to 3, characterized in that: The method of predicting and analyzing the original electrical data of the electrical equipment at multiple historical moments to obtain target electrical data at multiple future moments after the current moment includes: Performing feature analysis on the original electrical data at the multiple historical moments to obtain feature data at the multiple historical moments; Merging the original electrical data of the multiple historical moments and the characteristic data of the multiple historical moments correspondingly to obtain relevant data of the multiple historical moments; Classifying the relevant data of the multiple historical moments to obtain relevant data of multiple historical moments in each category; Determining target electrical data at the multiple historical moments according to the relevant data at the multiple historical moments under each category; Predictive analysis is performed on the target electrical data at the multiple historical moments to obtain the target electrical data at the multiple future moments.

5. The method according to claim 4, characterized in that Determining target electrical data at the multiple historical moments according to the relevant data at the multiple historical moments in each category includes: Centralize the relevant data of each historical moment in each category of relevant data to obtain the centralized data of each historical moment in each category; Determine the eigenvector of the covariance matrix corresponding to the centralized data of each category at each historical moment; A preset number of values ​​in the feature vector of each historical moment of each category are determined as the target electrical data of each historical moment of each category.

6. The method according to claim 4, characterized in that The predictive analysis of the target electrical data at the multiple historical moments to obtain the target electrical data at the multiple future moments includes: Using the target electrical data at the plurality of historical moments, training the parameters in the preset prediction model to obtain a trained target prediction model; The target electrical data at the i-th moment is processed using the target prediction model to obtain the target electrical data at the i+1-th moment; wherein i is an integer greater than or equal to 1, and i+1 is less than or equal to the total number of the multiple future moments; The target electrical data at the (i+1)th moment obtained each time is determined as the target electrical data at each future moment.

7. The method according to any one of claims 1 to 3, characterized in that: The method of predicting and analyzing the original electrical data of the electrical equipment at multiple historical moments to obtain target electrical data at multiple future moments after the current moment includes: Obtaining a random error and p weight coefficients; wherein p is the number of moments in the plurality of historical moments; The p weight coefficients are used to perform weighted fusion on the target electrical data from the tth moment to the t+p-1th moment, respectively, to obtain the t+pth target data; t is an integer greater than or equal to 1, and t+p is less than or equal to the total number of the multiple future moments; Determining target electrical data at the t+pth moment according to the t+pth target data and the random error; The target electrical data at the t+pth moment obtained each time is determined as the target electrical data at each future moment.

8. An equipment maintenance device, characterized in that: The device comprises: The prediction analysis module is used to perform prediction analysis on the original electrical data of the electrical equipment at multiple historical moments to obtain the target electrical data at multiple future moments after the current moment; A fault analysis module, used to perform fault analysis on the target electrical data at each of the future moments, and predict the target fault probability of the electrical equipment at each of the future moments; A strategy determination module, used to determine the maintenance strategy of the electrical equipment at each of the future moments according to the target failure probability at each of the future moments; The maintenance management module is used to perform maintenance management on the electrical equipment according to the maintenance strategy at each future moment.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images