A digital management method and system for substation-based operation and maintenance

Abstract

The present invention relates to a digital management method and system for operation and maintenance based on a substation, and to the technical field of substations. The method comprises: collecting the operation data of each device of the substation in real time; cleaning and preprocessing the original operation data to obtain the preprocessed data; based on the preprocessed data, evaluating the status of each device through an equipment health evaluation model to obtain the health score of each device; analyzing the historical operation data of each device through a time series analysis method and a machine learning model to predict potential equipment failures and obtain the failure prediction results of each device; generating the operation and maintenance plan and operation and maintenance priority of each device according to the health score and failure prediction results of each device; when the health score or failure probability of any device meets the preset conditions, automatically triggering an alarm and providing corresponding maintenance suggestions and emergency measures for the device that triggered the alarm. The present invention can improve the accuracy and efficiency of substation operation and maintenance.

Description

Technical Field

[0001] The present invention relates to the technical field of substations, and in particular to a substation-based operation and maintenance digital management method, system, electronic equipment and non-transient computer-readable storage medium. Background Art

[0002] Nowadays, the operation and maintenance of substations mainly rely on manual inspections, regular maintenance and fault handling. Operators usually check the operating status of the equipment on site, record parameters and abnormal conditions, and perform equipment maintenance and repairs according to the predetermined maintenance plan. In addition, operation and maintenance personnel rely on experience and intuition to judge the health of the equipment and take emergency measures when the equipment fails. This method ensures the normal operation of the substation to a certain extent, especially when obvious equipment failures occur, they can be handled in time to reduce the risk of power outages.

[0003] However, manual inspection and recording are susceptible to human factors, which may lead to missing or inaccurate data. Secondly, the regular maintenance method is often based on time cycles rather than the actual operating status of the equipment, which may lead to unnecessary maintenance or failure to detect potential faults in a timely manner. In addition, the reliance on experience and intuition is strong and cannot provide accurate data support, which limits the accuracy of fault diagnosis and prediction.

[0004] With the expansion of power grid scale and the increase of complexity, traditional substation operation and maintenance methods can no longer meet the needs of modern substations for efficient, safe and accurate operation and maintenance. There is an urgent need for a management method based on digital technology to improve operation and maintenance efficiency and management level. Summary of the invention

[0005] In view of the technical problems existing in the prior art, the present invention provides a substation-based digital management method, system, electronic device and non-transient computer-readable storage medium for operation and maintenance, which can improve the accuracy and efficiency of substation operation and maintenance.

[0006] The technical solution of the present invention to solve the above technical problems is as follows:

[0007] The present invention provides a digital management method for operation and maintenance based on a substation, the method comprising:

[0008] Collect the operating data of each device in the substation in real time through the sensor network;

[0009] Cleaning and preprocessing the original operation data to obtain preprocessed data;

[0010] Based on the preprocessed data, the status of each device is evaluated through the device health evaluation model to obtain a health score of each device;

[0011] Analyze the historical operation data of each of the devices through time series analysis and machine learning models to predict potential device failures and obtain failure prediction results for each of the devices;

[0012] Generate an operation and maintenance plan and operation and maintenance priority for each of the devices based on the health score and fault prediction result of each of the devices;

[0013] When the health score or failure probability of any device meets the preset conditions, an alarm is automatically triggered and corresponding maintenance suggestions and emergency measures are provided for the device that triggered the alarm.

[0014] Optionally, based on the preprocessed data, the status of each of the devices is evaluated by a device health evaluation model to obtain a health score of each of the devices, including:

[0015] Obtaining the current power, current temperature, vibration intensity and operating acceleration of each of the devices;

[0016] Obtain the rated power, normal operating temperature, maximum allowable temperature, minimum allowable temperature, critical vibration intensity and operating acceleration of each of the equipment;

[0017] Through the equipment health assessment model, based on the rated power, normal operating temperature, maximum allowable temperature, minimum allowable temperature, critical vibration intensity and operating acceleration of each device, the current power, current temperature, vibration intensity and operating acceleration of the device are processed to obtain the processing results of each type of parameters, and the processing results are weighted and summed in combination with the first weight, the second weight, the third weight and the fourth weight to obtain the health score of each device.

[0018] Optionally, the health score of each device is expressed as: ;

[0019] in, is the health score of the ith device, is the current power of the ith device, is the rated power of the device, is the current temperature of the ith device, is the normal operating temperature of the device, is the maximum temperature allowed by the device, is the lowest temperature allowed by the device, is the vibration intensity of the equipment, is the critical vibration intensity of the equipment, is the running acceleration of the device, is the maximum acceleration at which the device operates, They are the first weight, second weight, third weight and fourth weight of the health model respectively.

[0020] Optionally, the historical operation data of each of the devices is analyzed by time series analysis and machine learning models to predict potential device failures, and the failure prediction results of each of the devices are obtained, including:

[0021] Obtaining the time points at which historical failures of the device occurred and the weight of each of the time points;

[0022] Obtaining an influence coefficient of each potential failure mode of the device and a linear expression of each potential failure mode;

[0023] The fault detection result of the device is determined according to the time points at which the historical faults of the device occurred, the weight of each of the time points, the influence coefficient of each of the potential fault modes, and the linear expression of each of the potential fault modes.

[0024] Optionally, the failure probability of the device is expressed as: ;

[0025] in, is the failure probability of the device at the current time t, is the jth time point when the historical failure occurred, is the weight at the jth time point, is the width parameter at the jth time point, M is the number of fault events in the historical data, The influence coefficient of the kth potential failure mode, is the linear expression of the kth potential failure mode, and Y is the number of potential failure modes.

[0026] Optionally, generating an operation and maintenance priority of each device according to the health score and the fault prediction result of each device includes:

[0027] Obtaining a failure probability of the device and a time corresponding to the failure probability;

[0028] According to the time corresponding to the probability and the Lagrangian function, a first-order derivative and a second-order derivative of the Lagrangian function are obtained by processing;

[0029] The operation and maintenance priority of the device is determined according to the health score, the failure probability, and the first-order derivative and the second-order derivative of the Lagrangian function of the device.

[0030] Optionally, the operation and maintenance priority of each of the devices is expressed as: ;

[0031] in, is the maintenance priority of the ith device, is the health score of the ith device, is the failure probability of the device at the current time t, are the first influence coefficient, the second influence coefficient and the third influence coefficient respectively, and L is the Lagrangian function.

[0032] Optionally, when the health score or failure probability of any device meets a preset condition, an alarm is automatically triggered and corresponding maintenance suggestions and emergency measures are provided for the device that triggered the alarm, including:

[0033] Get the health score threshold and failure probability threshold;

[0034] When the health score of any device is less than the health score threshold, or the failure probability is greater than the failure probability threshold, the device meets the preset conditions, triggers an alarm operation for the device, and provides corresponding maintenance suggestions and emergency measures for the device.

[0035] Optionally, the method further includes:

[0036] Obtaining historical data reports and maintenance records of the operating status of the equipment;

[0037] Multiple time periods calculated from historical data reports of the device, and historical health scores corresponding to each of the time periods;

[0038] Calculate an average value of the historical health scores of the device according to the multiple time periods and the historical health scores of each time period;

[0039] The historical health score averages are analyzed to determine alternate maintenance recommendations for the equipment.

[0040] The present invention also provides a substation-based operation and maintenance digital management system, the system comprising:

[0041] The data acquisition module is used to collect the operation data of each device in the substation in real time through the sensor network;

[0042] A data processing module, used for cleaning and preprocessing the original operation data to obtain preprocessed data;

[0043] An equipment scoring module is used to evaluate the status of each of the equipment based on the preprocessed data through an equipment health evaluation model to obtain a health score of each of the equipment;

[0044] A fault prediction module is used to analyze the historical operation data of each of the devices through time series analysis and machine learning models to predict potential device failures and obtain failure prediction results for each of the devices;

[0045] An operation and maintenance plan module, used to generate an operation and maintenance plan and operation and maintenance priority for each of the devices according to the health score and fault prediction result of each of the devices;

[0046] The operation and maintenance execution module is used to automatically trigger an alarm when the health score or failure probability of any device meets the preset conditions and provide corresponding maintenance suggestions and emergency measures for the device that triggered the alarm.

[0047] In addition, to achieve the above objectives, the present invention also proposes an electronic device, comprising: a memory for storing computer software programs; a processor for reading and executing the computer software programs, thereby realizing a substation-based digital operation and maintenance management method as described above.

[0048] In addition, to achieve the above-mentioned purpose, the present invention also proposes a non-transitory computer-readable storage medium, in which a computer software program is stored. When the computer software program is executed by a processor, it implements a substation-based digital operation and maintenance management method as described above.

[0049] The beneficial effects of the present invention are:

[0050] (1) The present invention can dynamically evaluate the health status and failure risk of equipment by comprehensively considering the real-time operation data (such as power, temperature, vibration, acceleration) and historical fault data of the equipment. Based on this, the generated operation and maintenance priority can accurately guide the operation and maintenance personnel to carry out targeted equipment maintenance, reduce unnecessary maintenance work, and improve operation and maintenance efficiency;

[0051] (2) The present invention uses complex mathematical models (such as Gaussian distribution, logistic regression, and Lagrangian optimization) to more accurately predict potential equipment failures. Combined with historical failure data and analysis of potential failure modes, the failure prediction is more comprehensive and reliable, which helps to discover and deal with hidden dangers in advance and avoid downtime or accidents caused by sudden failures.

[0052] (3) The present invention reduces the interference of human factors through digital management and automated analysis, ensures the objectivity of data and the accuracy of judgment, and thus improves the scientific nature of operation and maintenance decisions.

[0053] (4) By introducing the Lagrangian function and its derivatives, the present invention can dynamically adjust the operation and maintenance priority, taking into account the changing trend and acceleration of the system status over time. It is not only suitable for the evaluation of the current status, but also can predict future trends, thereby achieving more flexible and forward-looking operation and maintenance decisions.

[0054] (5) Through accurate operation and maintenance priority assessment, the present invention can reasonably allocate operation and maintenance resources, giving priority to using limited resources for equipment that requires emergency maintenance, thereby avoiding resource waste. At the same time, this optimized configuration helps to extend the service life of the equipment and reduce the overall operation and maintenance costs.

[0055] (6) Through comprehensive monitoring, accurate evaluation and effective prediction, the present invention can timely detect and handle equipment failures, reduce downtime, and ensure the stable operation of the substation. At the same time, preventive maintenance measures can reduce the probability of sudden failures and improve the overall safety of the system.

[0056] In summary, the present invention significantly improves the operation and maintenance efficiency and safety of substations through digital and intelligent operation and maintenance management, reduces costs and risks, and has significant practical value and promotion prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 A structural block diagram of a substation-based digital operation and maintenance management method provided by the present invention;

[0058] Figure 2 A flowchart of a digital management method for operation and maintenance based on a substation provided by the present invention;

[0059] Figure 3 A schematic diagram of the structure of a substation-based operation and maintenance digital management system provided by the present invention;

[0060] Figure 4 A schematic diagram of the hardware structure of a possible electronic device provided by the present invention;

[0061] Figure 5 A schematic diagram of the hardware structure of a possible computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0063] In the description of the present invention, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0064] In the description of the present invention, the term "for example" is used to mean "used as an example, illustration or explanation". Any embodiment described as "for example" in the present invention is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid obscuring the description of the present invention with unnecessary details. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present invention.

[0065] See also Figure 1 , Figure 1 The structural block diagram of a digital management method for operation and maintenance based on a substation provided by the present invention. Figure 1 As shown, the terminal 10 and the server 20 are connected via a network, such as a wired or wireless network connection. The terminal 10 may include but is not limited to portable terminals such as mobile phones and tablets installed with various network platform applications, as well as fixed terminals such as computers, query machines, and advertising machines. The server 20 provides users with various business services, including a service push server, a user recommendation server, and the like.

[0066] It should be noted that Figure 1 The structural block diagram of the substation-based operation and maintenance digital management method shown is only an example. The terminal 10, server 20 and application scenario described in the embodiment of the present invention are for more clearly illustrating the technical solution of the embodiment of the present invention, and do not generate limitations on the technical solution provided by the embodiment of the present invention. Ordinary technicians in this field can know that with the evolution of the system and the emergence of new business scenarios, the technical solution provided by the embodiment of the present invention is also applicable to similar technical problems.

[0067] The terminal 10 may be used for:

[0068] Collect the operating data of each device in the substation in real time through the sensor network;

[0069] Cleaning and preprocessing the original operation data to obtain preprocessed data;

[0070] Based on the preprocessed data, the status of each device is evaluated through the device health evaluation model to obtain a health score of each device;

[0071] Analyze the historical operation data of each of the devices through time series analysis and machine learning models to predict potential device failures and obtain failure prediction results for each of the devices;

[0072] Generate an operation and maintenance plan and operation and maintenance priority for each of the devices based on the health score and fault prediction result of each of the devices;

[0073] When the health score or failure probability of any device meets the preset conditions, an alarm is automatically triggered and corresponding maintenance suggestions and emergency measures are provided for the device that triggered the alarm.

[0074] See also Figure 2 , provides a flow chart of a substation-based digital management method for operation and maintenance of the present invention, comprising the following steps:

[0075] Step 201: collect the operation data of each device of the substation in real time through the sensor network.

[0076] In some embodiments, various types of sensors are deployed on key equipment in the substation, such as temperature sensors, vibration sensors, current sensors, and acceleration sensors.

[0077] Each sensor is responsible for monitoring a specific device parameter to ensure that it can fully cover the operating status of the device. For example, a temperature sensor is used to monitor the temperature of the device, a vibration sensor monitors the vibration of the mechanical part, and an acceleration sensor is used to detect the movement of the device.

[0078] In some embodiments, the sensor network can continuously and uninterruptedly collect the operating data of the equipment and transmit it to the central system immediately after collection. This real-time performance ensures the timeliness of the data and can reflect the current status of the equipment. The frequency of data collection can be adjusted according to the importance and operating conditions of the equipment. The frequency of data collection for important equipment or key parameters may be higher to ensure that any abnormal changes can be captured in time.

[0079] In some embodiments, the sensor network usually transmits the collected data to the central monitoring system through wired or wireless communication. Common communication technologies include industrial Ethernet, wireless sensor network (WSN) or Internet of Things (IoT) technology. The data in the transmission process should be encrypted and verified to ensure the integrity and security of the data and prevent the data from being interfered or tampered with during the transmission process.

[0080] In some embodiments, after receiving the sensor data, the central monitoring system will process and store it in real time. This data can be used for subsequent health assessment, fault prediction, and operation and maintenance priority calculation. Data storage usually uses database or cloud storage to call and analyze historical data at any time, providing a basis for long-term trend analysis of equipment operation status.

[0081] In some embodiments, through the real-time data collected by the sensor network, the central monitoring system can make timely decisions based on the current status of the equipment, such as triggering alarms, dispatching maintenance personnel, or adjusting operating parameters. These data also provide a basis for health assessment, fault prediction, and operation and maintenance priority calculation in the present invention, ensuring the scientificity and accuracy of decision-making.

[0082] In summary, the main function of real-time data collection is to ensure that the operating status of substation equipment can be continuously monitored and timely grasped, and to support the system to take prompt countermeasures when abnormalities or potential faults are found. This method improves the automation level of equipment management, reduces reliance on manual inspections, and also improves the overall operational safety and reliability of the system.

[0083] Step 202: clean and preprocess the original operation data to obtain preprocessed data.

[0084] In some embodiments, the raw data collected from the sensor network may contain various problems, such as noise, outliers, missing data, or duplicate records. These problems may be caused by sensor failure, environmental interference, network transmission errors, etc. If the raw data is directly used for analysis without being processed, it may lead to inaccurate or even wrong results, so data cleaning and preprocessing are required first.

[0085] In some embodiments, the data can be smoothed to eliminate random noise caused by sensor accuracy limitations or environmental interference. For example, weighted average filtering, moving average, or Kalman filtering can be used to smooth the data to obtain measurements that are closer to the actual situation. Detect and correct outliers, such as values ​​that deviate extremely from the normal range. These outliers may be caused by sensor failure or temporary external interference. Processing methods include replacing them with the average, median, or nearest normal value. Missing values ​​may occur in data collection, which may be caused by temporary sensor failure or communication interruption. Common data completion methods include interpolation methods (such as linear interpolation, spline interpolation) or predictive filling based on historical data.

[0086] In some embodiments, in order to eliminate the dimensional differences between different devices or different parameters, the data is standardized or normalized. For example, temperature data can be standardized by subtracting the mean and then dividing by the standard deviation, so that the data distribution is more suitable for subsequent statistical analysis or machine learning models. For time series data with significant trends or periodicity, the data can be preprocessed by detrending or deperiodic methods to make the data easier to capture short-term fluctuations or anomalies. For example, the trend component is removed using a differential method or a wavelet transform. The data can be further smoothed to eliminate high-frequency fluctuations, making the data smoother and more stable. Common methods include weighted moving average, exponential smoothing, etc.

[0087] In some embodiments, the cleaned and preprocessed data is more reliable and accurate, eliminating noise, outliers and other interference factors, and has better continuity and stability. The preprocessed data provides a solid foundation for subsequent health assessment, fault prediction and operation and maintenance priority calculation, ensuring the accuracy of the analysis results and the scientific nature of the decision.

[0088] By cleaning and preprocessing the original operating data, the present invention can ensure the quality of the data, thereby improving the accuracy and reliability of subsequent analysis. The preprocessed data more realistically reflects the operating status of the equipment, helps to accurately assess the health of the equipment, predict failure risks, and reasonably arrange maintenance plans. This process reduces the errors introduced by human or environmental factors in the data, making data-based decisions more credible, and ultimately helping to improve the overall operating efficiency and safety of the system.

[0089] Step 203: Based on the preprocessed data, the status of each device is evaluated by a device health evaluation model to obtain a health score of each device.

[0090] In some embodiments, step 203 may include the following steps:

[0091] Obtaining the current power, current temperature, vibration intensity and operating acceleration of each of the devices;

[0092] Obtain the rated power, normal operating temperature, maximum allowable temperature, minimum allowable temperature, critical vibration intensity and operating acceleration of each of the equipment;

[0093] Through the equipment health assessment model, based on the rated power, normal operating temperature, maximum allowable temperature, minimum allowable temperature, critical vibration intensity and operating acceleration of each device, the current power, current temperature, vibration intensity and operating acceleration of the device are processed to obtain the processing results of each type of parameters, and the processing results are weighted and summed in combination with the first weight, the second weight, the third weight and the fourth weight to obtain the health score of each device.

[0094] In some embodiments, the health score of each of the devices is expressed as: ;

[0095] in, is the health score of the ith device, is the current power of the ith device, is the rated power of the device, is the current temperature of the ith device, is the normal operating temperature of the device, is the maximum temperature allowed by the device, is the lowest temperature allowed by the device, is the vibration intensity of the equipment, is the critical vibration intensity of the equipment, is the running acceleration of the device, is the maximum acceleration at which the device operates, They are the first weight, second weight, third weight and fourth weight of the health model respectively.

[0096] In the specific implementation, Measure the current power of the device Rated power of equipment The impact of the ratio of on the health of the equipment. near When the ratio is close to 1, it means that the equipment is working according to the designed load and the health is good; if Much lower or higher , the ratio will be far away from 1 and the health score will decrease.

[0097] The use of cubic power strengthens the nonlinear effect of power on health, that is, the greater the power deviation, the more significant the negative impact on health. Determines the influence of power factor on health score. The larger the value, the greater the effect of power changes on health.

[0098] Indicates the current temperature of the device Normal operating temperature The impact of the deviation on the health of the equipment. It is the working range of temperature, which standardizes the temperature deviation and makes the temperature characteristics of different devices comparable. The fourth power increases the impact of temperature deviation on health. The more the temperature deviates from the normal value, the greater the impact on health. After controlling the influence of temperature, the effect of temperature on health Increase and strengthen.

[0099] Measuring the vibration intensity of equipment Relative to critical vibration intensity The logarithmic function can alleviate the impact of vibration intensity changes on health and make the changes smoother. The closer the vibration intensity is to or exceeds the critical value, the lower the health score will be. Introduced equipment running acceleration The exponential function makes the negative impact of acceleration appear in a nonlinear form. The greater the acceleration, the more significant the decrease in health score.

[0100] The third weight Used to control the influence of vibration factors on health. The influence of vibration changes Increase and strengthen. Fourth weight Controls the weakening effect of acceleration on health. The larger the value, the more significant the negative impact of acceleration on health.

[0101] This formula calculates The power, temperature, vibration, acceleration and other parameters of the equipment are combined by their respective weights to reflect the different effects of each parameter on the health of the equipment. Deviations in power and temperature, as well as increases in vibration intensity and acceleration, will lead to a decrease in the health score. The setting allows adjusting the contribution of each factor to the final health score, thereby providing a flexible health assessment model for different devices or scenarios.

[0102] Step 204: Analyze the historical operation data of each of the devices through time series analysis and machine learning models to predict potential device failures and obtain failure prediction results for each of the devices.

[0103] In some embodiments, step 204 may include the following steps:

[0104] Obtaining the time points at which historical failures of the device occurred and the weight of each of the time points;

[0105] Obtaining an influence coefficient of each potential failure mode of the device and a linear expression of each potential failure mode;

[0106] The fault detection result of the device is determined according to the time points at which the historical faults of the device occurred, the weight of each of the time points, the influence coefficient of each of the potential fault modes, and the linear expression of each of the potential fault modes.

[0107] In some embodiments, the failure probability of a device can be expressed as: ;

[0108] in, is the failure probability of the device at the current time t, is the jth time point when the historical failure occurred, is the weight at the jth time point, is the width parameter at the jth time point, M is the number of fault events in the historical data, The influence coefficient of the kth potential failure mode, is the linear expression of the kth potential failure mode, and Y is the number of potential failure modes.

[0109] In the specific implementation, is the failure probability of the equipment at the current time t. is the jth time point when the historical failure occurred. is the weight of the jth time point, reflecting the importance or impact of the fault event. The larger the weight, the greater the contribution of the event to the fault probability at the current moment. is the width parameter at the jth time point, which determines the impact range of the historical fault. Indicates that the impact of the fault event is wider and the time decay is slower; smaller This means that the impact range is narrower and the time decay is faster. M is the number of fault events in the historical data. The influence coefficient of the kth potential failure mode determines the contribution of this failure mode to the failure probability. The larger the coefficient, the more significant the impact of this mode on the failure probability.

[0110] It is a linear expression of the kth potential failure mode, which describes the comprehensive effect of various input variables (such as equipment parameters, operating status, etc.) on the failure risk under this mode. The general form is: ,in, is the weight of the i-th input variable in the k-th mode; are input variables (e.g. sensor data, environmental conditions, etc.); is the bias term. is the logistic regression function (sigmoid function), which is used to transform the linear expression Converted to a probability value between 0 and 1, reflecting the probability of device failure in this mode. Y is the number of potential failure modes, representing the total number of different failure mechanisms or modes considered in the model.

[0111] Specifically, This part reflects the impact of historical fault events on the current fault probability. Calculated in the form of a Gaussian function, the impact of each historical fault event decays over time. The closer the fault event is to the current time, the greater its impact on the current fault probability.

[0112] This section reflects the impact of the risk assessment based on potential failure modes on the current failure probability. The risk of each potential failure mode is assessed through a logistic regression model and integrated into the total failure probability.

[0113] Failure probability It consists of two main parts:

[0114] Impact of historical fault data: The weighted sum of historical fault data is performed through the Gaussian distribution function to reflect the impact of historical fault events on the current moment's fault risk. This part mainly relies on past experience data and takes into account the time decay effect. The more recent the historical fault, the greater the impact on the current moment.

[0115] Impact of potential failure modes: The potential failure mode risk is evaluated through a logistic regression model, and these modes are combined to correct and supplement the failure probability at the current moment. This part enhances the depth and breadth of prediction through the combined impact of multiple failure modes, and is applicable to different failure mechanisms.

[0116] This formula combines historical data and machine learning models to both leverage past failure experience and predict possible future failures in a data-driven manner, providing a comprehensive failure risk assessment method.

[0117] Step 205: Generate an operation and maintenance plan and operation and maintenance priority for each of the devices based on the health score and fault prediction result of each of the devices.

[0118] In some embodiments, step 205 may include the following steps:

[0119] Obtaining a failure probability of the device and a time corresponding to the failure probability;

[0120] According to the time corresponding to the probability and the Lagrangian function, a first-order derivative and a second-order derivative of the Lagrangian function are obtained by processing;

[0121] The operation and maintenance priority of the device is determined according to the health score, the failure probability, and the first-order derivative and the second-order derivative of the Lagrangian function of the device.

[0122] In some embodiments, the operation and maintenance priority of each of the devices is expressed as: ;

[0123] in, is the maintenance priority of the ith device, is the health score of the ith device, is the failure probability of the device at the current time t, are the first influence coefficient, the second influence coefficient and the third influence coefficient respectively, and L is the Lagrangian function.

[0124] In the specific implementation, is the maintenance priority of the ith device, is the health score of the ith device. The lower the health score (i.e. The smaller), The larger the value, the higher the maintenance priority of the device. is the failure probability of the device at the current time t, are the first influence coefficient, the second influence coefficient and the third influence coefficient respectively. The increase in the probability of failure directly increases the priority of operation and maintenance. L is the Lagrangian function.

[0125] Specifically, This section reflects the impact of equipment health and failure probability on operation and maintenance priorities. Device priority (i.e. poor device status) Higher, and the probability of failure As the number of tasks increases, the priority of operations and maintenance also increases. It takes into account the health status and failure risk of the equipment, ensuring that the priority of operation and maintenance rises rapidly when the equipment health is poor and the probability of failure is high.

[0126] These two parts introduce the first and second order derivatives of the time-related Lagrangian function L, which are used to further adjust the operation and maintenance priority, taking into account the dynamic changes of the system over time. In optimization problems, the Lagrangian function L is usually used to deal with the combination of objective functions and constraints. Here, it can represent comprehensive factors such as the system's operation and maintenance costs and resource allocation.

[0127] First Derivative It represents the rate of change of the Lagrangian function over time, reflecting the immediate change trend of system operation and maintenance costs or resource allocation. is the weight coefficient associated with the rate of change. If it is positive, it means that the system status may deteriorate, so the maintenance priority may need to be increased.

[0128] Second Derivative It represents the acceleration change of the Lagrangian function over time, reflecting the acceleration of the system state change. is the weight coefficient associated with this acceleration. If If it is positive, it means that the system status is deteriorating rapidly, so the maintenance priority may need to be increased more significantly.

[0129] By calculating the operation and maintenance priority of each device It is an indicator for comprehensively evaluating equipment maintenance needs. It takes into account the current status, historical data and future trends of the equipment, and provides a comprehensive and dynamic equipment operation and maintenance priority evaluation method, which helps to optimize the allocation of operation and maintenance resources and ensure the stable operation of the system.

[0130] Step 206: When the health score or failure probability of any device meets the preset conditions, an alarm is automatically triggered and corresponding maintenance suggestions and emergency measures are provided for the device that triggered the alarm.

[0131] In some embodiments, step 206 may include the following steps:

[0132] Get the health score threshold and failure probability threshold;

[0133] When the health score of any device is less than the health score threshold, or the failure probability is greater than the failure probability threshold, the device meets the preset conditions, triggers an alarm operation for the device, and provides corresponding maintenance suggestions and emergency measures for the device.

[0134] It can be understood that the health score is a comprehensive score calculated based on the operating parameters of the device (such as power, temperature, vibration, acceleration, etc.), which reflects the current health status of the device. The health score threshold is a pre-set value used to determine whether the device is in normal operating condition. This threshold is usually set based on the historical operating data of the device, the safety standards recommended by the manufacturer, or operation and maintenance experience. When the health score of the device is lower than this threshold, it means that the operating status of the device has deteriorated to an unsafe level and may require immediate maintenance or repair.

[0135] It can also be understood that the failure probability of a device is a numerical value based on the device's historical failure data and potential failure mode predictions, indicating the possibility of a device failure at the current moment. The failure probability threshold is a set critical value that indicates the probability at which a device needs special attention and treatment. This threshold can be determined based on statistical analysis of historical failure data, industry standards, or operation and maintenance strategies. When the failure probability of a device exceeds this threshold, it means that the device may face a high risk of failure and preventive measures need to be taken in advance.

[0136] In some embodiments, when the health score of the device is lower than the health score threshold, or the failure probability exceeds the failure probability threshold, any of the following conditions is met, the device is considered to have potential risks. When the above preset conditions are met, the system will automatically trigger an alarm operation and send a warning signal to the operation and maintenance personnel. This alarm can be in the form of sound, light, SMS notification, email notification, etc., to ensure that the operation and maintenance personnel are aware of the abnormal status of the equipment in a timely manner.

[0137] In some embodiments, when an alarm is triggered, the system can provide corresponding maintenance suggestions based on the specific situation of the equipment. These suggestions may include immediately checking a component, adjusting the operating parameters of the equipment, arranging downtime for maintenance, etc., to help operation and maintenance personnel make correct decisions. When the equipment is at risk of serious failure, the system will also recommend emergency measures, such as reducing the equipment load, switching to backup equipment, temporarily stopping the equipment operation, etc., to prevent the failure from further deteriorating or causing a larger power outage.

[0138] By setting health score thresholds and failure probability thresholds, this solution can monitor the operating status of equipment in real time and issue alerts in a timely manner when potential risks occur. This not only prevents equipment from continuing to operate in a hidden danger state, but also reduces the incidence and severity of equipment failures through early intervention, ensuring the safe and stable operation of the substation. In addition, the maintenance suggestions and emergency measures automatically generated by the system help operation and maintenance personnel respond quickly, effectively reducing downtime and operation and maintenance costs.

[0139] In some embodiments, the method of the present invention may further include:

[0140] Obtaining historical data reports and maintenance records of the operating status of the equipment;

[0141] Multiple time periods calculated from historical data reports of the device, and historical health scores corresponding to each of the time periods;

[0142] Calculate an average value of the historical health scores of the device according to the multiple time periods and the historical health scores of each time period;

[0143] The historical health score averages are analyzed to determine alternate maintenance recommendations for the equipment.

[0144] Among them, the historical data report is a document automatically generated by the system, which records the operating status data of the equipment in the past period of time. These data usually include key parameters such as power, temperature, vibration, acceleration, etc. of the equipment, and are arranged in chronological order. The maintenance record is a record of all maintenance activities taken by the equipment during the past operation and maintenance process. The maintenance record describes in detail the inspection, maintenance, repair or replacement of parts performed by the equipment at various time points, as well as the results of these activities.

[0145] In some embodiments, historical data reports can be divided into multiple time periods (such as monthly, quarterly, and annually) based on the operating characteristics of the device and the frequency of data collection. Each time period represents the operating status of the device during this period. In each time period, the system calculates a historical health score based on the operating data of the device. This score reflects the comprehensive operating status of the device during the time period. The higher the health score, the better the operating status of the device; the lower the score, the possible problem of the device.

[0146] For each device, the system calculates the average of its historical health scores over multiple time periods. This average provides a long-term, comprehensive assessment of the device's health status.

[0147] In some embodiments, by analyzing the average historical health score of the device, the system can identify trend problems that may exist in the long-term operation of the device. For example, if the average health score gradually decreases, it may indicate that the condition of the device is deteriorating and early intervention and maintenance are required.

[0148] Determination of alternate maintenance recommendations: Based on the analysis results of historical health scores, the system will generate alternate maintenance recommendations. These recommendations may include increasing the monitoring frequency of certain components, replacing wearing parts in advance, and arranging more preventive maintenance activities to extend the service life of the equipment and prevent sudden failures.

[0149] In summary, by acquiring and analyzing the historical operating status and maintenance records of the equipment, the present invention can gain an in-depth understanding of the long-term health status of the equipment and identify potential trending problems. The calculated average historical health score provides a quantitative assessment of the overall operating quality of the equipment, helping operation and maintenance personnel to more accurately predict the maintenance needs of the equipment. The backup maintenance recommendations formulated based on these analysis results make the operation and maintenance strategy more proactive and preventive, help reduce the frequency of equipment failures, extend the service life of the equipment, and optimize the allocation of operation and maintenance resources, thereby improving the operational safety and reliability of the substation.

[0150] See also Figure 3 , Figure 3 A structural schematic diagram of a substation-based operation and maintenance digital management system provided by the present invention.

[0151] like Figure 3 As shown, an operation and maintenance digital management system based on a substation proposed in an embodiment of the present invention includes:

[0152] The data acquisition module 301 is used to collect the operation data of each device of the substation in real time through the sensor network;

[0153] The data processing module 302 is used to clean and preprocess the original operation data to obtain preprocessed data;

[0154] The device scoring module 303 is used to evaluate the status of each device through the device health evaluation model based on the preprocessed data to obtain the health score of each device;

[0155] A fault prediction module 304 is used to analyze the historical operation data of each of the devices through time series analysis and machine learning models to predict potential device failures and obtain a fault prediction result for each of the devices;

[0156] The operation and maintenance plan module 305 is used to generate an operation and maintenance plan and an operation and maintenance priority for each of the devices according to the health score and the fault prediction result of each of the devices;

[0157] The operation and maintenance execution module 306 is used to automatically trigger an alarm when the health score or failure probability of any device meets the preset conditions and provide corresponding maintenance suggestions and emergency measures for the device that triggered the alarm.

[0158] See also Figure 4 , Figure 4 Schematic diagram of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, an embodiment of the present invention provides an electronic device 400, including a memory 410, a processor 420, and a computer program 411 stored in the memory 410 and executable on the processor 420. When the processor 420 executes the computer program 411, the following steps are implemented:

[0159] Collect the operating data of each device in the substation in real time through the sensor network;

[0160] Cleaning and preprocessing the original operation data to obtain preprocessed data;

[0161] Based on the preprocessed data, the status of each device is evaluated through the device health evaluation model to obtain a health score of each device;

[0162] Analyze the historical operation data of each of the devices through time series analysis and machine learning models to predict potential device failures and obtain failure prediction results for each of the devices;

[0163] Generate an operation and maintenance plan and operation and maintenance priority for each of the devices based on the health score and fault prediction result of each of the devices;

[0164] When the health score or failure probability of any device meets the preset conditions, an alarm is automatically triggered and corresponding maintenance suggestions and emergency measures are provided for the device that triggered the alarm.

[0165] See also Figure 5 , Figure 5 A schematic diagram of an embodiment of a computer-readable storage medium provided in an embodiment of the present invention. Figure 5 As shown, this embodiment provides a computer-readable storage medium 500, on which a computer program 411 is stored. When the computer program 411 is executed by a processor, the following steps are implemented:

[0166] Collect the operating data of each device in the substation in real time through the sensor network;

[0167] Cleaning and preprocessing the original operation data to obtain preprocessed data;

[0168] Based on the preprocessed data, the status of each device is evaluated through the device health evaluation model to obtain a health score of each device;

[0169] Analyze the historical operation data of each of the devices through time series analysis and machine learning models to predict potential device failures and obtain failure prediction results for each of the devices;

[0170] Generate an operation and maintenance plan and operation and maintenance priority for each of the devices based on the health score and fault prediction result of each of the devices;

[0171] When the health score or failure probability of any device meets the preset conditions, an alarm is automatically triggered and corresponding maintenance suggestions and emergency measures are provided for the device that triggered the alarm.

[0172] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0173] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0174] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A system that specifies the functions of a box or multiple boxes.

[0175] These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing device to work in a specific manner, so that the instructions stored in the computer-readable memory produce a product including an instruction system, which is implemented in the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0176] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0177] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0178] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A digital management method for operation and maintenance based on a substation, characterized in that: The method comprises: Collect the operating data of each device in the substation in real time through the sensor network; Cleaning and preprocessing the original operation data to obtain preprocessed data; Based on the preprocessed data, the status of each device is evaluated through the device health evaluation model to obtain a health score of each device; Analyze the historical operation data of each of the devices through time series analysis and machine learning models to predict potential device failures and obtain failure prediction results for each of the devices; Generate an operation and maintenance plan and operation and maintenance priority for each of the devices based on the health score and fault prediction result of each of the devices; When the health score or failure probability of any device meets the preset conditions, an alarm is automatically triggered and corresponding maintenance suggestions and emergency measures are provided for the device that triggered the alarm; Based on the preprocessed data, the status of each device is evaluated by the device health evaluation model to obtain the health score of each device, including: Obtaining the current power, current temperature, vibration intensity and operating acceleration of each of the devices; Obtain the rated power, normal operating temperature, maximum allowable temperature, minimum allowable temperature, critical vibration intensity and operating acceleration of each of the equipment; Through the equipment health assessment model, based on the rated power, normal operating temperature, maximum allowable temperature, minimum allowable temperature, critical vibration intensity and operating acceleration of each of the equipment, the current power, current temperature, vibration intensity and operating acceleration of the equipment are processed to obtain processing results of each type of parameters, and the processing results are weighted and summed in combination with the first weight, the second weight, the third weight and the fourth weight to obtain a health score of each of the equipment; The historical operation data of each of the above-mentioned equipment is analyzed by time series analysis method and machine learning model to predict potential equipment failures, and the failure prediction results of each of the above-mentioned equipment are obtained, including: Obtaining the time points at which historical failures of the device occurred and the weight of each of the time points; Obtaining an influence coefficient of each potential failure mode of the device and a linear expression of each potential failure mode; Determine a fault detection result of the device according to the time point at which the historical fault of the device occurred, the weight of each of the time points, the influence coefficient of each of the potential fault modes, and the linear expression of each of the potential fault modes; The failure probability of the device is expressed as: Among them, F t is the failure probability of the device at the current time t, t j is the jth time point when the historical failure occurred, ω j is the weight at the jth time point, σ j is the width parameter at the jth time point, M is the number of fault events in the historical data, and λ k The influence coefficient of the kth potential failure mode, z k is the linear expression of the kth potential failure mode, Y is the number of potential failure modes; Generating the operation and maintenance priority of each device according to the health score and fault prediction result of each device includes: Obtaining a failure probability of the device and a time corresponding to the failure probability; According to the time corresponding to the probability and the Lagrangian function, a first-order derivative and a second-order derivative of the Lagrangian function are obtained by processing; Determining the operation and maintenance priority of the device according to the health score, failure probability, and the first-order derivative and second-order derivative of the Lagrangian function of the device; The operation and maintenance priority of each device is expressed as: Among them, U i is the maintenance priority of the ith device, H i is the health score of the ith device, F t is the failure probability of the equipment at the current time t, λ, λ1, λ2 are the first influence coefficient, the second influence coefficient and the third influence coefficient respectively, and L is the Lagrangian function.

2. The method for digital operation and maintenance management based on a substation according to claim 1 is characterized in that: The health score of each of the devices is expressed as: Among them, H i is the health score of the ith device, P i is the current power of the ith device, P nom is the rated power of the device, T i is the current temperature of the ith device, T nom is the normal operating temperature of the device, T max is the maximum temperature allowed by the device, T min is the lowest temperature allowed by the device, V i is the vibration intensity of the equipment, V crit is the critical vibration intensity of the equipment, A i is the running acceleration of the equipment, A max is the maximum acceleration of the equipment operation, and α, β, γ, and δ are the first weight, second weight, third weight, and fourth weight of the health model, respectively.

3. The digital management method for operation and maintenance based on a substation according to claim 1 is characterized in that: When the health score or failure probability of any device meets the preset conditions, an alarm is automatically triggered and corresponding maintenance suggestions and emergency measures are provided for the device that triggered the alarm, including: Get the health score threshold and failure probability threshold; When the health score of any device is less than the health score threshold, or the failure probability is greater than the failure probability threshold, the device meets the preset conditions, triggers an alarm operation for the device, and provides corresponding maintenance suggestions and emergency measures for the device.

4. The method for digital operation and maintenance management based on a substation according to claim 3 is characterized in that: The method further comprises: Obtaining historical data reports and maintenance records of the operating status of the equipment; Multiple time periods calculated from historical data reports of the device, and historical health scores corresponding to each of the time periods; Calculate an average value of the historical health scores of the device according to the multiple time periods and the historical health scores of each time period; The historical health score averages are analyzed to determine alternate maintenance recommendations for the equipment.

5. A digital operation and maintenance management system based on a substation, characterized in that: The system comprises: The data acquisition module is used to collect the operation data of each device in the substation in real time through the sensor network; A data processing module, used for cleaning and preprocessing the original operation data to obtain preprocessed data; An equipment scoring module is used to evaluate the status of each of the equipment based on the preprocessed data through an equipment health evaluation model to obtain a health score of each of the equipment; A fault prediction module is used to analyze the historical operation data of each of the devices through time series analysis and machine learning models to predict potential device failures and obtain failure prediction results for each of the devices; An operation and maintenance plan module, used to generate an operation and maintenance plan and operation and maintenance priority for each of the devices according to the health score and fault prediction result of each of the devices; The operation and maintenance execution module is used to automatically trigger an alarm when the health score or failure probability of any device meets the preset conditions and provide corresponding maintenance suggestions and emergency measures for the device that triggered the alarm; Based on the preprocessed data, the status of each device is evaluated by the device health evaluation model to obtain the health score of each device, including: Obtaining the current power, current temperature, vibration intensity and operating acceleration of each of the devices; Obtain the rated power, normal operating temperature, maximum allowable temperature, minimum allowable temperature, critical vibration intensity and operating acceleration of each of the equipment; Through the equipment health assessment model, based on the rated power, normal operating temperature, maximum allowable temperature, minimum allowable temperature, critical vibration intensity and operating acceleration of each of the equipment, the current power, current temperature, vibration intensity and operating acceleration of the equipment are processed to obtain processing results of each type of parameters, and the processing results are weighted and summed in combination with the first weight, the second weight, the third weight and the fourth weight to obtain a health score of each of the equipment; The historical operation data of each of the above-mentioned equipment is analyzed by time series analysis method and machine learning model to predict potential equipment failures, and the failure prediction results of each of the above-mentioned equipment are obtained, including: Obtaining the time points at which historical failures of the device occurred and the weight of each of the time points; Obtaining an influence coefficient of each potential failure mode of the device and a linear expression of each potential failure mode; Determine a fault detection result of the device according to the time point at which the historical fault of the device occurred, the weight of each of the time points, the influence coefficient of each of the potential fault modes, and the linear expression of each of the potential fault modes; The failure probability of the device is expressed as: Among them, F t is the failure probability of the device at the current time t, t j is the jth time point when the historical failure occurred, ω j is the weight at the jth time point, σ j is the width parameter at the jth time point, M is the number of fault events in the historical data, and λ k The influence coefficient of the kth potential failure mode, z k is the linear expression of the kth potential failure mode, Y is the number of potential failure modes; Generating the operation and maintenance priority of each device according to the health score and fault prediction result of each device includes: Obtaining a failure probability of the device and a time corresponding to the failure probability; According to the time corresponding to the probability and the Lagrangian function, a first-order derivative and a second-order derivative of the Lagrangian function are obtained by processing; Determining the operation and maintenance priority of the device according to the health score, failure probability, and the first-order derivative and second-order derivative of the Lagrangian function of the device; The operation and maintenance priority of each device is expressed as: Among them, U i is the maintenance priority of the ith device, H i is the health score of the ith device, F t is the failure probability of the equipment at the current time t, λ, λ1, λ2 are the first influence coefficient, the second influence coefficient and the third influence coefficient respectively, and L is the Lagrangian function.

Images