A cloud-based FTU management system

Through the cloud-based FTU management system, random forests and linear planning algorithms are used to analyze equipment operation data, identify abnormal patterns and failure risks, optimize maintenance and resource configuration, the problem of insufficient fault prediction and resource allocation in traditional systems is solved, and the power is improved System stability and operational efficiency.

CN118760900BActive Publication Date: 2024-11-08WISDOM (RUGAO) HIGH VOLTAGE SWITCH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411255616.3
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-09
Publication Date
2024-11-08
Estimated Expiration
2044-09-09

AI Technical Summary

Technical Problem

Traditional FTU management systems lack effective data analysis tools, making it difficult to identify and prevent potential failures, resulting in increased risk of equipment downtime and maintenance costs, affecting the stable power supply and overall performance of the power grid.

Method used

The cloud-based FTU management system is adopted, including failure mode identification module, maintenance strategy optimization module, health assessment and prediction module, risk management module and life cycle management module. Through the random forest algorithm and linear planning algorithm, the equipment operation data is analyzed and abnormalities are identified. mode, generate maintenance priorities and plans, evaluate failure risk and equipment life, optimize resource allocation and energy efficiency strategies.

Benefits of technology

Improve the accuracy of equipment failure prediction and optimization of resource allocation, reduce unplanned downtime, extend the service life of the equipment, and improve the stability and operational efficiency of the power system.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118760900B_ABST
    Figure CN118760900B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of remote management technology, specifically a cloud-based FTU management system, the system includes a fault mode identification module, a maintenance strategy optimization module, a health assessment and prediction module, a risk management module, a life cycle management module, and an energy efficiency optimization module. The fault mode identification module collects current, voltage, and temperature change information based on the FTU operation data received from the cloud. In the present invention, the random forest algorithm in the health assessment and prediction module makes the analysis of FTU operation data more in-depth and accurate, allows accurate prediction of future performance changes of equipment, directly reduces unplanned downtime, and improves maintenance efficiency. The application of the linear programming algorithm optimizes the maintenance and replacement strategy of the equipment, ensures the reasonable allocation of resources, thereby extending the service life of the equipment, improving the stability of the system, and effectively solving the accuracy of fault prediction and the optimization of resource allocation. The problem has brought a qualitative leap in power system management.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of remote management technology, and in particular to a cloud-based FTU management system. Background Art

[0002] The field of remote management technology focuses on using cloud computing resources and network technology to monitor and control remote equipment. It is widely used in various industrial and commercial environments, especially in situations where remote monitoring, diagnosis and control are required. The development of this technology has promoted the improvement of intelligence and automation, and can manage its operations more effectively, reducing the need for human intervention.

[0003] Among them, the FTU management system is a system that monitors and controls the feeder terminal units in the power system. Its main purpose is to achieve more efficient and reliable management of power supply lines. Through real-time data collection, analysis and remote control functions, it aims to optimize power distribution, reduce power outages, and improve the stability and efficiency of the power grid, thereby increasing the operational efficiency of the entire power system.

[0004] Traditional systems lack effective data analysis tools, making it difficult to identify and prevent potential failures, resulting in increased risk of equipment downtime and maintenance costs. Failures that are not discovered in time will cause unexpected power outages and affect the stable power supply of the power grid. The irrational allocation of resources further aggravates the difficulty of maintenance work and affects overall performance and efficiency. The above shortcomings expose the limitations of traditional systems in intelligent and automated management, and restrict the improvement of the operational efficiency of the power system. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings in the prior art and to propose a cloud-based FTU management system.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a cloud-based FTU management system, the system comprising:

[0007] The fault mode identification module collects current, voltage and temperature change information based on the FTU operation data received from the cloud, analyzes power load fluctuations and voltage abnormality patterns, identifies potential fault sources, and obtains abnormal mode characteristics;

[0008] The maintenance strategy optimization module analyzes the frequency and impact of failures based on the abnormal mode characteristics, evaluates the impact of failure modes on FTU operation, and generates maintenance priorities and plans;

[0009] The health assessment and prediction module applies the random forest algorithm based on the maintenance priority and plan, combines the collected FTU operation data, analyzes the equipment operation trend, evaluates the current health status of the equipment, predicts future performance changes, and obtains equipment health prediction records;

[0010] The risk management module evaluates the impact of potential failures on the safety of FTU operation based on the equipment health prediction records, analyzes the downtime risk caused by the failure, formulates risk control measures, and obtains the risk level and management strategy;

[0011] The life cycle management module uses a linear programming algorithm based on the risk level and management strategy to evaluate the impact of maintenance measures on the service life of FTU, analyze the effect of maintenance activities on the extension of equipment life, and obtain a life cycle extension plan;

[0012] The energy efficiency optimization module evaluates the current energy efficiency of FTUs based on the life cycle extension plan, analyzes energy consumption patterns, optimizes equipment configuration and load distribution, and establishes energy efficiency optimization strategies.

[0013] The present invention has improvements in that the abnormal mode characteristics include abnormal current modes, abnormal voltage fluctuations, and temperature exceeding standard indicators; the maintenance priority and plan include maintenance urgency, resources required for maintenance, and a scheduled maintenance schedule; the equipment health prediction record includes performance degradation trends, predicted maintenance time points, and potential fault warnings; the life cycle extension plan includes maintenance cycle adjustment, key component replacement strategy, and expected service life extension; the energy efficiency optimization strategy includes energy consumption analysis, equipment configuration adjustment, and load distribution optimization.

[0014] The present invention is improved in that the maintenance strategy optimization module includes:

[0015] The fault assessment submodule analyzes the fault mode based on the abnormal mode characteristics, evaluates the severity of each fault mode according to the impact of the fault on the safety and efficiency of FTU operation, combined with the fault frequency and historical maintenance records, and generates an impact severity record;

[0016] The resource allocation submodule analyzes the availability of the maintenance team and the inventory status of maintenance materials based on the impact severity records, verifies whether resource allocation matches maintenance requirements, optimizes resource utilization efficiency, and establishes a resource allocation plan;

[0017] The priority determination submodule assigns priorities to maintenance activities based on the resource allocation plan, in combination with the degree of fault impact and the degree of resource shortage, and generates a maintenance priority and plan.

[0018] The present invention is improved in that the health assessment and prediction module comprises:

[0019] The trend analysis submodule aggregates FTU operation data through the cloud platform based on the maintenance priority and plan, analyzes the long-term change trend of current, voltage and temperature, identifies normal and abnormal operation modes, and generates operation trend identification records;

[0020] The health assessment submodule applies a random forest algorithm based on the operation trend identification record, evaluates the current health status of the equipment according to the usage history and maintenance records of the FTU, and identifies key health indicators to obtain a health status index;

[0021] The performance prediction submodule predicts the performance of the FTU in the future operation cycle based on the health status index, historical performance degradation trends and maintenance records, determines potential performance degradation points and maintenance requirement time, and obtains equipment health prediction records.

[0022] The present invention improves the random forest algorithm according to the formula:

[0023] ;

[0024] Calculate the health index of the device;

[0025] in, Predict the health status of the equipment. is the number of decision trees, is the weight coefficient of the i-th tree, is the i-th tree pair sample The prediction results, is the standard deviation of the sample data, for The weight coefficient of is the frequency of device use, for The weight coefficient of is the equipment running time, for The weight coefficient of .

[0026] The present invention is improved in that the risk management module comprises:

[0027] The risk assessment submodule analyzes the impact of potential failures on the safety of FTU operation based on the equipment health prediction record, classifies the risk levels with reference to the downtime and maintenance costs caused by the failure, and generates a risk level assessment record;

[0028] The risk control submodule formulates control measures for the level risk based on the risk level assessment record, including preventive measures and emergency response plans, and obtains a risk control measures plan;

[0029] The response process optimization submodule evaluates the efficiency and effectiveness of the existing operation and maintenance response process based on the risk control measures plan, makes process design adjustments, optimizes the fault response and maintenance execution process, and obtains the risk level and management strategy.

[0030] The present invention is improved in that the life cycle management module comprises:

[0031] The maintenance impact analysis submodule applies time series analysis based on the risk level and management strategy, collects and analyzes maintenance activity data, evaluates the impact of differential maintenance measures on the service life of FTU, and analyzes the contribution of multiple maintenance measures to the extension of equipment performance and life, and generates maintenance contribution indicators;

[0032] The equipment update planning submodule uses a linear programming algorithm based on the maintenance contribution index to determine the key stages of equipment performance degradation, evaluate future development trends and equipment upgrade requirements, plan the time nodes and technical paths for equipment updates, and develop an update strategy overview;

[0033] The replacement plan formulation submodule plans the replacement strategy for obsolete equipment based on the update strategy overview, including replacement schedule, budget assessment and supplier selection, and obtains a life cycle extension plan.

[0034] The present invention is improved in that the linear programming algorithm is according to the formula:

[0035] ;

[0036] Calculate total maintenance costs;

[0037] in, is the total maintenance cost, represents the maintenance cost at time t, is the device performance decay rate at time t, For the additional maintenance costs due to performance degradation, is the technological progress adjustment coefficient at time t, is the demand fluctuation coefficient of the equipment at time t, is the environmental impact coefficient, It is an indicator of the stability of the equipment.

[0038] Compared with the prior art, the advantages and positive effects of the present invention are:

[0039] In the present invention, the random forest algorithm in the health assessment and prediction module makes the analysis of FTU operation data more in-depth and accurate, allowing accurate prediction of future performance changes of the equipment, directly reducing unplanned downtime and improving maintenance efficiency. The application of the linear programming algorithm optimizes the maintenance and replacement strategy of the equipment, ensures the rational allocation of resources, thereby extending the service life of the equipment, improving the stability of the system, and effectively solving the accuracy of fault prediction and the optimization of resource allocation, bringing a qualitative leap in power system management. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] Figure 1A module diagram of a cloud-based FTU management system is proposed for the present invention;

[0041] Figure 2 A system framework diagram of a cloud-based FTU management system is proposed for the present invention;

[0042] Figure 3 A flow chart of a fault mode identification module in a cloud-based FTU management system is proposed for the present invention;

[0043] Figure 4 A flow chart of a maintenance strategy optimization module in a cloud-based FTU management system is proposed for the present invention;

[0044] Figure 5 A flow chart of the health assessment and prediction module in a cloud-based FTU management system is proposed for the present invention;

[0045] Figure 6 A flow chart of the risk management module in a cloud-based FTU management system is proposed for the present invention;

[0046] Figure 7 The present invention proposes a flow chart of a life cycle management module in a cloud-based FTU management system;

[0047] Figure 8 The present invention proposes a flow chart of an energy efficiency optimization module in a cloud-based FTU management system. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention 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 invention and are not intended to limit the present invention.

[0049] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", etc., indicating positions or positional relationships, are based on the positions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. Example

[0050] See also Figure 1 The present invention provides a technical solution: a cloud-based FTU management system comprising:

[0051] The fault mode identification module collects current, voltage and temperature change information based on the FTU operation data received from the cloud, analyzes the power load fluctuation and voltage abnormality mode, identifies potential fault sources, and locates the fault-affected area to obtain abnormal mode characteristics;

[0052] The maintenance strategy optimization module analyzes the frequency and impact of failures based on abnormal mode characteristics, evaluates the impact of failure modes on FTU operation, and allocates maintenance activities according to the impact and resources, determines priorities, and generates maintenance priorities and plans;

[0053] The health assessment and prediction module applies the random forest algorithm based on maintenance priorities and plans, combines the collected FTU operation data, analyzes the equipment operation trend, evaluates the current health status of the equipment, and predicts future performance changes, providing data support for preventive maintenance and obtaining equipment health prediction records;

[0054] The risk management module evaluates the impact of potential failures on FTU operation safety based on equipment health prediction records, analyzes the downtime risk caused by failures, formulates risk control measures, and optimizes the operation and maintenance response process to obtain risk levels and management strategies;

[0055] The life cycle management module uses a linear programming algorithm based on risk levels and management strategies to evaluate the impact of maintenance measures on the service life of FTUs, analyze the role of maintenance activities in extending the life of equipment, develop equipment renewal and replacement plans, and obtain life cycle extension plans;

[0056] The energy efficiency optimization module evaluates the current energy efficiency of FTU based on the life cycle extension plan, analyzes energy consumption patterns, optimizes equipment configuration and load distribution, improves the overall energy efficiency of FTU, and establishes an energy efficiency optimization strategy.

[0057] Abnormal mode characteristics include abnormal current patterns, abnormal voltage fluctuations, and temperature exceeding the standard index; maintenance priorities and plans include maintenance urgency, resources required for maintenance, and scheduled maintenance schedules; equipment health prediction records include performance degradation trends, predicted maintenance time points, and potential failure warnings; life cycle extension plans include maintenance cycle adjustments, key component replacement strategies, and expected service life extension; energy efficiency optimization strategies include energy consumption analysis, equipment configuration adjustments, and load distribution optimization.

[0058] See also Figure 2 and Figure 3 ,The fault mode identification module includes a data collection submodule, a fault analysis submodule, and a fault location submodule;

[0059] The data collection submodule automatically collects the current, voltage and temperature information transmitted by the FTU based on the FTU operation data received from the cloud, performs preliminary screening on the data, excludes error data, and obtains the screened data set;

[0060] The fault analysis submodule identifies abnormal fluctuations in the current data based on the filtered data set and the historical data pattern, compares the abnormal data with the normal operating range, identifies the data points that deviate from the normal range, and obtains the fault indicator identification;

[0061] The fault location submodule uses GIS technology based on fault indicator identification and combines the location information of FTU to map the location of the fault and the potential impact area to obtain the abnormal pattern characteristics.

[0062] In the data collection submodule, based on the FTU operation data received from the cloud, an automation script is written in Python, and the Pandas library is used to automatically collect the current, voltage, and temperature information transmitted by the FTU. The data is stored in the DataFrame format, and the dropna method is used to exclude data rows containing null values. The query method is used to filter out data with a current range of 0 to 1000 amperes, a voltage range of 0 to 10,000 volts, and a temperature range of -40 to 150 degrees Celsius to generate a filtered data set.

[0063] In the fault analysis submodule, based on the screened data set, an automated script is written in Python, and the stats module in the SciPy library is used to perform statistical analysis on the data set. The describe method is used to obtain the statistical description of the current, voltage, and temperature, including the mean and standard deviation. The identify_abnormal function is used to identify data points that deviate from the mean by more than 3 standard deviations through the normal distribution fitting test. The data points are used as abnormal data and compared with the normal operating range. The data points that deviate from the normal range are identified to generate a fault indicator identifier.

[0064] In the fault location submodule, based on the fault indicator identification, an automated script is written in Python, and ArcGIS-Python is used to perform spatial analysis on the fault indicator identification. GIS technology is used, combined with the location information of the FTU, and the map_view method is used to draw the FTU location on the map. The buffer_analysis method is used to calculate the potential impact area. By setting the distance parameter to a range of 500 meters around the fault data point, the location of the fault and the potential impact area are mapped to generate abnormal pattern features.

[0065] See also Figure 2 and Figure 4 ,The maintenance strategy optimization module includes a fault assessment submodule, a resource allocation submodule, and a priority determination submodule;

[0066] The fault assessment submodule analyzes the fault mode based on the abnormal mode characteristics, evaluates the severity of each fault mode according to the impact of the fault on the safety and efficiency of FTU operation, combined with the fault frequency and historical maintenance records, and generates an impact severity record;

[0067] The resource allocation submodule analyzes the availability of the maintenance team and the inventory status of maintenance materials based on the impact severity records, verifies whether resource allocation matches maintenance requirements, optimizes resource utilization efficiency, and establishes a resource allocation plan;

[0068] The priority determination submodule assigns priorities to maintenance activities based on the resource allocation plan, combined with the degree of fault impact and resource intensity, and generates maintenance priorities and plans.

[0069] In the fault assessment submodule, based on the abnormal pattern characteristics, the logistic regression algorithm is used to perform fault mode analysis. The Python language and Scikit-learn library are used to quantify the impact of faults on the safety and efficiency of FTU operation. The fault frequency and historical maintenance records are used as input features. The solver parameter of the logistic regression model is set to liblinear, and the penalty parameter is set to l2 for regularization to prevent overfitting. The model is trained using the fit method, and the predict_proba method is used to estimate the severity probability of each fault mode and generate impact severity records.

[0070] In the resource allocation submodule, based on the impact severity record, a linear programming algorithm is used to optimize resource allocation. The Python language and PuLP library are used to define the availability of the maintenance team and the inventory status of maintenance materials as constraints in the linear programming problem. The objective function is set to maximize resource utilization efficiency. By setting the objective of the LpProblem object to LpMaximize, the LpVariable method is used to define the variables of the maintenance team and material resources. The solve method is called to solve the linear programming problem, optimize the matching degree between resource allocation and maintenance requirements, and generate a resource allocation plan.

[0071] In the priority determination submodule, based on the resource allocation plan, a dynamic priority queuing algorithm is adopted. The Python language and NumPy library are used to calculate the priority of each maintenance activity in combination with the fault impact degree and resource intensity. An array is set to store the fault impact degree and resource intensity of each maintenance activity. The sort function is used to sort the maintenance activities according to the priority rules defined by the dynamic priority algorithm. This ensures that the comparison function is dynamically adjusted according to the fault impact degree and resource intensity of the maintenance activity during the sorting process to generate the maintenance priority and plan.

[0072] See also Figure 2 and Figure 5 ,The health assessment and prediction module includes a trend analysis submodule, a health assessment submodule, and a performance prediction submodule;

[0073] The trend analysis submodule aggregates FTU operation data through the cloud platform based on maintenance priorities and plans, analyzes long-term trends in current, voltage, and temperature, identifies normal and abnormal operation modes, and generates operation trend identification records;

[0074] The health assessment submodule uses the random forest algorithm based on the operation trend recognition records to evaluate the current health status of the equipment according to the FTU usage history and maintenance records, and identifies key health indicators to obtain the health status index;

[0075] The performance prediction submodule predicts the performance of the FTU in the future operation cycle based on the health status index, historical performance degradation trends and maintenance records, determines potential performance degradation points and maintenance requirement times, and obtains equipment health prediction records.

[0076] In the trend analysis submodule, based on maintenance priorities and plans, the time series analysis method is adopted, the Python language and the Pandas library are used to summarize the FTU operation data, and the long-term change trends of current, voltage and temperature are analyzed. The DateTimeIndex is used to process the time series data, and the rolling method is used to calculate the moving average to smooth short-term fluctuations. The window parameter is set to 7 days, the mean method is used to calculate the average value, and the standard deviation is calculated by the std method to identify abnormal fluctuations. The calculation results are compared with historical thresholds to identify normal and abnormal operation modes and generate operation trend identification records.

[0077] In the health assessment submodule, the random forest algorithm is used to assess the health status of the equipment based on the operation trend identification records. The Python language and Scikit-learn library are used. According to the usage history and maintenance records of the FTU, the n_estimators parameter of the random forest model is set to 100, indicating that 100 trees are used for decision making. The max_depth parameter is set to None, allowing the tree to grow to the maximum depth. The fit method is used to train the model, and the trained model is applied to the operation trend identification records. The predict method is used to evaluate the current health status of the equipment, and the feature_importances_ attribute is used to identify key health indicators to obtain the health status index.

[0078] Random forest algorithm, according to the formula:

[0079] ;

[0080] Calculate the health index of the device;

[0081] in, Predict the health status of the equipment. is the number of decision trees, is the weight coefficient of the i-th tree, is the i-th tree pair sample The prediction results, is the standard deviation of the sample data, representing the volatility of the input data, for The weight coefficient of is the frequency of device use, for The weight coefficient of is the equipment running time, for The weight coefficient of .

[0082] Execution process:

[0083] First, calculate the probability of each decision tree for the sample The prediction results , and then based on the frequency of use of the device and running time Adjust the prediction results, where the equipment usage frequency and running time are used as additional indicators for health status assessment to increase the accuracy of the prediction. The data volatility in the equipment usage history and maintenance records is adjusted by Reflection, providing an evaluation of the model prediction stability, each parameter , , and The weight coefficients are determined through data analysis. , , and The coefficient value is obtained through correlation analysis and regression testing of historical data to ensure effective adjustment of the model prediction results. Finally, all calculation results are summarized to obtain the health status index. .

[0084] In the performance prediction submodule, based on the health status index, a linear regression algorithm is used to predict the future performance of FTU. The Python language and SciPy library are used to set up a linear regression model according to the historical performance degradation trend and maintenance records. The linregress method is used to calculate the slope and intercept of the historical data, which represent the performance degradation rate and the initial performance level. The slope and intercept are used to estimate the performance of FTU in the future operation cycle, determine the potential performance degradation points and maintenance requirement time, and obtain the equipment health prediction record.

[0085] See also Figure 2 and Figure 6,The risk management module includes the risk assessment submodule, the risk control submodule, and the response process optimization submodule;

[0086] The risk assessment submodule analyzes the impact of potential failures on the safety of FTU operation based on the equipment health prediction records, classifies the risk levels according to the downtime and repair costs caused by the failures, and generates risk level assessment records;

[0087] The risk control submodule formulates control measures for the risk level based on the risk level assessment records, including preventive measures and emergency response plans, and obtains a risk control measures plan;

[0088] The response process optimization submodule evaluates the efficiency and effectiveness of the existing operation and maintenance response process based on the risk control measures plan, makes process design adjustments, optimizes the fault response and maintenance execution process, and obtains the risk level and management strategy.

[0089] In the risk assessment submodule, based on the equipment health prediction records, the decision tree classification algorithm is used to analyze the impact of potential faults on the safe operation of FTUs. The Python language and Scikit-learn library are used to take the downtime and maintenance cost caused by the faults as feature inputs. The criterion parameter of the decision tree model is set to gini to measure the segmentation quality, and the max_depth parameter is set to 5 to limit the growth depth of the tree. The fit method is used to train the model, and the predict method is applied to classify the risk levels. According to the different fault types, they are classified into three levels of risk: low, medium and high, and risk level assessment records are generated.

[0090] In the risk control submodule, based on the risk level assessment records, the risk matrix method in the project management principles is used to formulate control measures for risks at all levels. Using Excel VBA scripts, according to the risk levels in the risk level assessment records, an automated script is written to sort risk factors, and conditional formatting is set to highlight high-risk items. For each risk level, corresponding preventive measures and emergency response plans are formulated, such as scheduling preventive maintenance for high-risk faults, setting inspection reminders for medium-risk faults, and performing routine monitoring of low-risk faults, to obtain a risk control measures plan.

[0091] In the response process optimization submodule, based on the risk control measures plan, the process simulation analysis method is used to evaluate the efficiency and effectiveness of the existing operation and maintenance response process. The Python language and SimPy library are used to build a simulation model of the operation and maintenance response process. The environmental parameters are set to the current number of maintenance team members and maintenance resource configuration. The process method is used to define the various stages of fault response and maintenance execution. By running simulation experiments, the completion time of each stage is recorded, the bottleneck links in the process are analyzed, and the process design is adjusted for the identified bottleneck links, such as increasing the manpower of the maintenance team or optimizing the material distribution process, optimizing the fault response and maintenance execution process, and obtaining the risk level and management strategy.

[0092] See also Figure 2 and Figure 7 ,The life cycle management module includes the maintenance impact analysis submodule, the equipment update planning submodule, and the replacement plan formulation submodule;

[0093] The maintenance impact analysis submodule uses time series analysis to collect and analyze maintenance activity data based on risk levels and management strategies, evaluate the impact of differential maintenance measures on the service life of FTUs, and analyze the contribution of multiple maintenance measures to the extension of equipment performance and life, generating maintenance contribution indicators;

[0094] The equipment update planning submodule uses a linear programming algorithm based on maintenance contribution indicators to determine the key stages of equipment performance degradation, evaluate future development trends and equipment upgrade requirements, plan the time nodes and technical paths for equipment updates, and develop an overview of the update strategy;

[0095] The replacement plan formulation submodule plans the replacement strategy for old equipment based on the update strategy overview, including replacement schedule, budget assessment and supplier selection, and obtains life cycle extension solutions.

[0096] In the maintenance impact analysis submodule, based on the risk level and management strategy, the time series analysis method is adopted. The Python language and Pandas library are used to collect and analyze the maintenance activity data. The maintenance activities are processed in time series. The resample method is used to resample the data on a monthly basis. The maintenance activity frequency of each month is calculated. The ARIMA model is adopted, and the model parameters are set to (2, 1, 2), which represents the autoregressive term of 2, the difference order of 1, and the moving average term of 2. The fit method is used to train the model, and the forecast method is used to evaluate the impact of differential maintenance measures on the service life of FTU. The contribution of multiple maintenance measures to the extension of equipment performance and life is analyzed to generate maintenance contribution indicators.

[0097] In the equipment update planning submodule, based on the maintenance contribution index, a linear programming algorithm is adopted, and the Python language and PuLP library are used to determine the key stages of equipment performance degradation. The equipment performance degradation rate and expected service life are used as constraints of the linear programming problem. The objective function is set to minimize the total maintenance cost. A problem instance is created through the LpProblem class, and the goal is set to LpMinimize. LpVariable is used to define the variables of the equipment update time nodes and technical paths. The solve method is called to solve the linear programming problem, and an overview of the update strategy is formulated, including the time nodes and technical path planning for equipment updates.

[0098] Linear programming algorithm, according to the formula:

[0099] ;

[0100] Calculate total maintenance costs;

[0101] in, is the total maintenance cost, represents the maintenance cost at time t, is the device performance decay rate at time t, For the additional maintenance costs due to performance degradation, is the technological progress adjustment coefficient at time t, is the demand fluctuation coefficient of the equipment at time t, is the environmental impact coefficient, It is an indicator of the stability of the equipment.

[0102] Execution process:

[0103] Set annual maintenance costs and additional maintenance costs due to performance degradation As a basic calculation element, consider the device performance decay rate As a key variable affecting maintenance costs, the technology progress adjustment coefficient is introduced To adjust the cost savings effect brought about by technological progress each year, taking into account the fluctuation coefficient of equipment demand To reflect the impact of market demand on equipment usage intensity, environmental impact coefficient Used to adjust the impact of external environmental changes on equipment maintenance costs, and finally add equipment stability indicators To evaluate the impact of long-term equipment reliability on maintenance costs, and to minimize total maintenance costs by solving linear programming problems , determine the optimal equipment update time node and technical path planning, to determine , and The specific value of can be determined by statistical analysis based on historical data to determine its impact coefficient value.

[0104] In the replacement plan formulation submodule, the replacement strategy for old equipment is planned based on the update strategy overview. The Project software is used to formulate a replacement schedule based on the equipment update time nodes determined in the update strategy overview. The built-in cost management tool is used for budget evaluation. The appropriate supplier is selected based on the market research results. The replacement process is optimized through task dependency and resource allocation functions to ensure that the replacement activities are coordinated with the overall life cycle management goals and obtain a life cycle extension plan.

[0105] See also Figure 2 and Figure 8 ,The energy efficiency optimization module includes the energy efficiency status ,evaluation submodule, the consumption pattern analysis submodule, and the ,configuration optimization submodule;

[0106] The energy efficiency status assessment submodule collects FTU energy consumption data based on the life cycle extension plan, evaluates the current energy efficiency level, identifies the key causes of low energy efficiency, sets a baseline for energy use, and generates energy efficiency baseline records;

[0107] The consumption pattern analysis submodule analyzes the patterns and trends of energy consumption based on the energy efficiency baseline records, identifies the unreasonable parts of energy use, including over-consumption and energy leakage points, and evaluates the impact of energy consumption on the overall energy efficiency to obtain an energy consumption overview;

[0108] The configuration optimization submodule designs the optimization scheme of FTU equipment configuration and load distribution based on the energy consumption profile, and implements energy-saving measures and optimized operations in combination with the energy efficiency optimization of equipment operation to establish an energy efficiency optimization strategy.

[0109] In the energy efficiency status assessment submodule, based on the life cycle extension plan, an energy efficiency evaluation model is adopted, and the energy consumption data of FTU is collected using Python language and NumPy library to evaluate the current energy efficiency level and calculate energy utilization efficiency indicators, including the total energy consumption and output ratio. The np.mean function is used to calculate the average energy consumption, and the np.std function is used to calculate the energy consumption fluctuation. By comparing the energy efficiency indicators with the industry standards, the key causes of low energy efficiency are identified, the baseline of energy use is set, and the energy efficiency baseline record is generated.

[0110] In the consumption pattern analysis submodule, based on the energy efficiency baseline records, the cluster analysis method is adopted, and the Python language and Scikit-learn library are used to analyze the patterns and trends of energy consumption. The KMeans algorithm is used, and the n_clusters parameter is set to 3, which means that the energy consumption data is divided into three types of consumption patterns: high, medium and low. The fit_predict method is used to classify the energy usage data, identify the unreasonable parts of energy usage, including excessive consumption and energy leakage points, and evaluate the impact of energy consumption on total energy efficiency to obtain an energy consumption overview.

[0111] In the configuration optimization submodule, based on the energy consumption profile, a genetic algorithm is used to design the optimization scheme for FTU equipment configuration and load distribution. Python language and DEAP library are used, and the population size is set to 50, representing 50 different configuration schemes. The crossover rate is 0.7 and the mutation rate is 0.2. New configuration schemes are generated by crossover and mutation operations. The evaluation function is defined as maximizing the energy efficiency of equipment operation. The best performing configuration scheme is retained through selection operations. The optimal solution is found through 100 iterations. Energy-saving measures and optimization operations are implemented to establish an energy efficiency optimization strategy.

[0112] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A cloud-based FTU management system, characterized in that: The system comprises: The fault mode identification module collects current, voltage and temperature change information based on the FTU operation data received from the cloud, analyzes power load fluctuations and voltage abnormality patterns, identifies potential fault sources, and obtains abnormal mode characteristics; The maintenance strategy optimization module analyzes the frequency and impact of failures based on the abnormal mode characteristics, evaluates the impact of failure modes on FTU operation, and generates maintenance priorities and plans; The health assessment and prediction module applies the random forest algorithm based on the maintenance priority and plan, combines the collected FTU operation data, analyzes the equipment operation trend, evaluates the current health status of the equipment, predicts future performance changes, and obtains equipment health prediction records; The risk management module evaluates the impact of potential failures on the safety of FTU operation based on the equipment health prediction records, analyzes the downtime risk caused by the failure, formulates risk control measures, and obtains the risk level and management strategy; The life cycle management module uses a linear programming algorithm based on the risk level and management strategy to evaluate the impact of maintenance measures on the service life of FTU, analyze the effect of maintenance activities on the extension of equipment life, and obtain a life cycle extension plan; The energy efficiency optimization module evaluates the current status of FTU energy efficiency, analyzes energy consumption patterns, optimizes equipment configuration and load distribution, and establishes energy efficiency optimization strategies based on the life cycle extension plan; The health assessment and prediction module includes: The trend analysis submodule aggregates FTU operation data through the cloud platform based on the maintenance priority and plan, analyzes the long-term change trend of current, voltage and temperature, identifies normal and abnormal operation modes, and generates operation trend identification records; The health assessment submodule applies a random forest algorithm based on the operation trend identification record, evaluates the current health status of the equipment according to the usage history and maintenance records of the FTU, and identifies key health indicators to obtain a health status index; The performance prediction submodule predicts the performance of the FTU in the future operation cycle based on the health status index, historical performance degradation trends and maintenance records, determines potential performance degradation points and maintenance requirement time, and obtains equipment health prediction records; The random forest algorithm is based on the formula: ; Calculate the health index of the device; in, Predict the health status of the equipment. is the number of decision trees, is the weight coefficient of the i-th tree, is the i-th tree pair sample The prediction results, is the standard deviation of the sample data, for The weight coefficient of is the frequency of device use, for The weight coefficient of is the equipment running time, for The weight coefficient of The maintenance strategy optimization module includes: The fault assessment submodule analyzes the fault mode based on the abnormal mode characteristics, evaluates the severity of each fault mode according to the impact of the fault on the safety and efficiency of FTU operation, combined with the fault frequency and historical maintenance records, and generates an impact severity record; The resource allocation submodule analyzes the availability of the maintenance team and the inventory status of maintenance materials based on the impact severity records, verifies whether resource allocation matches maintenance requirements, optimizes resource utilization efficiency, and establishes a resource allocation plan; The priority determination submodule assigns priorities to maintenance activities based on the resource allocation plan, combined with the degree of fault impact and the degree of resource shortage, and generates maintenance priorities and plans; The risk management module includes: The risk assessment submodule analyzes the impact of potential failures on the safety of FTU operation based on the equipment health prediction record, classifies the risk levels with reference to the downtime and maintenance costs caused by the failure, and generates a risk level assessment record; The risk control submodule formulates control measures for the level risk based on the risk level assessment record, including preventive measures and emergency response plans, and obtains a risk control measures plan; The response process optimization submodule evaluates the efficiency and effectiveness of the existing operation and maintenance response process based on the risk control measures plan, makes process design adjustments, optimizes the fault response and maintenance execution process, and obtains the risk level and management strategy; The life cycle management module includes: The maintenance impact analysis submodule applies time series analysis based on the risk level and management strategy, collects and analyzes maintenance activity data, evaluates the impact of differential maintenance measures on the service life of FTU, and analyzes the contribution of multiple maintenance measures to the extension of equipment performance and life, and generates maintenance contribution indicators; The equipment update planning submodule uses a linear programming algorithm based on the maintenance contribution index to determine the key stages of equipment performance degradation, evaluate future development trends and equipment upgrade requirements, plan the time nodes and technical paths for equipment updates, and develop an update strategy overview; The replacement plan formulation submodule plans the replacement strategy for old equipment based on the update strategy overview, including replacement schedule, budget assessment and supplier selection, and obtains a life cycle extension plan; The linear programming algorithm is according to the formula: ; Calculate total maintenance costs; in, is the total maintenance cost, represents the maintenance cost at time t, is the device performance decay rate at time t, For the additional maintenance costs due to performance degradation, is the technological progress adjustment coefficient at time t, is the demand fluctuation coefficient of the equipment at time t, is the environmental impact coefficient, It is the stability index of the equipment; The abnormal mode characteristics include abnormal current patterns, abnormal voltage fluctuations, and temperature exceeding the standard index; the maintenance priority and plan include maintenance urgency, resources required for maintenance, and scheduled maintenance schedule; the equipment health prediction record includes performance degradation trends, predicted maintenance time points, and potential failure warnings; the life cycle extension plan includes maintenance cycle adjustment, key component replacement strategy, and expected service life extension; the energy efficiency optimization strategy includes energy consumption analysis, equipment configuration adjustment, and load distribution optimization.