An optimization system and method for intelligent operation and maintenance of new energy generator sets

Abstract

The present invention discloses an optimization system for intelligent operation and maintenance of a new energy generator set, including: a data acquisition module: collecting the operating status data and external environment data of the generator set through a sensor network; a data processing and storage module: using edge computing equipment for preliminary data processing; an algorithm model module: including a maintenance optimization model based on reinforcement learning and a dynamic energy efficiency optimization model; an optimization method for intelligent operation and maintenance of a new energy generator set includes the following steps: S1: data acquisition and preprocessing; S2: construction of a maintenance optimization model based on reinforcement learning; S3: construction of a dynamic energy efficiency optimization model; S4: fault prediction and maintenance strategy optimization; S5: system integration and feedback execution. The present invention adjusts the operating parameters of the unit in real time, ensuring that the generator set is always in the optimal operating state under different external environmental conditions, achieving the dual goals of maximizing resource utilization and minimizing energy consumption.

Description

Technical Field

[0001] The present invention relates to the technical field of generator set operation and maintenance, and in particular to an optimization system and method for intelligent operation and maintenance of new energy generator sets. Background Art

[0002] With the rapid development of new energy technologies, new energy generators are playing an increasingly important role in the power system. Traditional generator operation and maintenance methods mainly rely on manual monitoring and regular maintenance, and cannot respond to the operating status of the equipment and changes in the external environment in real time. In addition, with the continuous expansion of the scale of generators, traditional operation and maintenance models often lead to waste of resources and inefficiency. Therefore, intelligent, data-driven operation and maintenance management systems have become an important direction for improving the operating efficiency of generators and reducing downtime. In recent years, operation and maintenance optimization systems combining sensor networks, cloud computing and intelligent algorithms have begun to be widely used.

[0003] Existing operation and maintenance optimization systems mostly rely on static models for data collection and processing, and cannot fully consider the dynamic changes of generator sets in actual operation, resulting in insufficient accuracy in fault prediction and maintenance decisions. Traditional operation and maintenance methods lack the ability to respond to environmental changes in real time and cannot flexibly adjust operation strategies for different generator sets or operating conditions. Therefore, it is necessary to design an optimization system and method for intelligent operation and maintenance of new energy generator sets to solve the above problems. Summary of the invention

[0004] The purpose of this section is to summarize some aspects of embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0005] In view of the problems existing in the above-mentioned existing optimization system and method for intelligent operation and maintenance of new energy power generation sets, the present invention is proposed.

[0006] Therefore, the purpose of the present invention is to provide an optimization system and method for intelligent operation and maintenance of new energy power generation sets, which is suitable for solving the problems of insufficient accuracy of fault prediction and maintenance decisions, and inability to flexibly adjust operating strategies for different power generation sets or operating conditions.

[0007] In order to solve the above technical problems, the present invention provides the following technical solutions: an optimization system for intelligent operation and maintenance of new energy generator sets, comprising:

[0008] Data acquisition module: collects the operating status data and external environment data of the generator set through the sensor network;

[0009] Data processing and storage module: Use edge computing devices to perform preliminary data processing and upload key parameters to the cloud database for storage and analysis;

[0010] Algorithm model module: including maintenance optimization model based on reinforcement learning and dynamic energy efficiency optimization model;

[0011] Execution feedback module: adjusts generator set operating parameters in real time and provides maintenance suggestions.

[0012] An optimization method for intelligent operation and maintenance of a new energy generator set, the optimization method is applicable to the above optimization system, and the optimization method comprises the following steps:

[0013] S1: Data collection and preprocessing;

[0014] S2: Construction of maintenance optimization model based on reinforcement learning;

[0015] S3: Construction of dynamic energy efficiency optimization model;

[0016] S4: Fault prediction and maintenance strategy optimization;

[0017] S5: System integration and feedback execution.

[0018] As a preferred solution of the optimization method for intelligent operation and maintenance of a new energy generator set described in the present invention, the construction of the maintenance optimization model is achieved by the following steps:

[0019] S21: Use the sensor network to collect the operating status data of the generator set and construct a health status evaluation formula, and the health status evaluation formula is as follows: ,in, The health status score reflects the overall health of the generator set. is the maintenance benefit function, which indicates the improvement effect of maintenance operation on the status of the generator set. is the probability density function of failure, which indicates the possibility of equipment failure at time t'. To maintain the collection weights, used to adjust The importance of is the failure risk weight, which is used to adjust the impact of failure probability on health status;

[0020] S22: reinforcement learning model initialization;

[0021] S23: In the reinforcement learning training, the maintenance cost and benefit optimization formula is constructed according to the output results of the health status assessment formula;

[0022] S24: Generate dynamic maintenance recommendations based on the health status of the generator set and output maintenance strategies.

[0023] As a preferred solution of the optimization method for intelligent operation and maintenance of a new energy generator set described in the present invention, the health status standard threshold is set in the output result of the health status evaluation formula. ;

[0024] like ≤ , indicating that the health status of the generator set is poor and it is necessary to enter the maintenance decision-making stage;

[0025] like , indicating that the generator set is in normal health and does not require maintenance.

[0026] As a preferred solution of the optimization method of intelligent operation and maintenance of a new energy generator set described in the present invention, the maintenance cost and benefit optimization formula is as follows: ,in, For the optimized maintenance cost-benefit ratio, is the direct cost of the ith maintenance operation, It is equivalent to the output result of the health status assessment formula, that is, the health status score, which represents the health status of the generator set after the i-th maintenance. Delayed loss for maintenance operations, is the maintenance cost weight, which is used to adjust the importance of maintenance cost. is the health status influence coefficient, which is used to control the effect of health status on the cost-benefit ratio. is the delay loss weight, which is used to adjust the impact of delay loss.

[0027] As a preferred solution of the optimization method for intelligent operation and maintenance of a new energy generator set described in the present invention, in which: in the output result of the maintenance cost and benefit optimization formula, a threshold is set ;

[0028] like ≤ When , it means that the current maintenance strategy has low cost and high benefit, so the strategy is implemented;

[0029] like , it means that the current maintenance strategy has high cost or low benefit, and the maintenance strategy needs to be adjusted.

[0030] As a preferred solution of the optimization method for intelligent operation and maintenance of a new energy generator set described in the present invention, the construction of a dynamic energy efficiency optimization model is achieved by the following steps:

[0031] S31: Real-time monitoring of external environment data through sensors;

[0032] S32: construct a dynamic energy efficiency optimization model formula, and substitute the external environment data collected above into the dynamic energy efficiency optimization model formula;

[0033] S33: Dynamic adjustment of operating parameters;

[0034] S34: Optimize feedback and continuous improvement.

[0035] As a preferred solution of the optimization method for intelligent operation and maintenance of a new energy generator set described in the present invention, the dynamic energy efficiency optimization model formula is as follows: ,in, represents the optimized energy efficiency value, represents the power generation efficiency, Indicates the decay rate of load change, Indicates the load variation range, It represents the total output power per unit time. represents the power loss, is the loss function.

[0036] As a preferred solution of the optimization method for intelligent operation and maintenance of a new energy generator set described in the present invention, wherein: a threshold is set in the output result of the dynamic energy efficiency optimization model formula ;

[0037] like ≤ and > , indicating that the current maintenance strategy has controllable cost and high energy efficiency, so the maintenance strategy is implemented;

[0038] like or , maintenance and energy efficiency optimization strategies need to be re-evaluated.

[0039] As a preferred solution of the optimization method of intelligent operation and maintenance of a new energy generator set described in the present invention, wherein: in S4, the maintenance strategy selection is optimized according to the failure probability and the maintenance cost;

[0040] If the risk of failure is high and the maintenance cost is low, perform maintenance immediately;

[0041] If the risk of failure is low and the energy efficiency gain is low, defer maintenance and optimize operating parameters.

[0042] Beneficial effects of the present invention: The present invention adopts a maintenance optimization model based on reinforcement learning and a dynamic energy efficiency optimization model, realizes the coordinated optimization of the two, combines real-time data analysis, realizes intelligent and data-driven maintenance decision-making, and can effectively avoid excessive or insufficient maintenance of generator sets through accurate fault prediction and dynamic adjustment;

[0043] The maintenance optimization model can not only predict faults and make maintenance decisions based on the real-time operating status of the generator set, but also provide the necessary operating parameters for the energy efficiency optimization model through a feedback mechanism. The dynamic energy efficiency optimization model ensures that the generator set is always in the optimal operating state under different external environmental conditions by adjusting the operating parameters of the unit in real time. This interaction enables a dynamic balance to be maintained between maintenance decisions and energy efficiency improvements, avoiding the disconnection between maintenance and energy efficiency optimization in the traditional model, and achieving the dual goals of maximizing resource utilization and minimizing energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. Among them:

[0045] Figure 1 This is a schematic diagram of the overall framework structure of an optimization system for intelligent operation and maintenance of a new energy generator set proposed by the present invention;

[0046] Figure 2 A schematic diagram of the implementation steps of an optimization method for intelligent operation and maintenance of a new energy generator set proposed in the present invention. DETAILED DESCRIPTION

[0047] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0048] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0049] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0050] Secondly, the present invention is described in detail with reference to the schematic diagram. When describing the embodiments of the present invention in detail, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0051] Example 1

[0052] Reference Figure 1-Figure 2 , which is an embodiment of the present invention, provides an optimization system for intelligent operation and maintenance of new energy generator sets, including:

[0053] Data acquisition module: collects the operating status data of the generator set (such as vibration, temperature, current and voltage parameters) and external environment data (such as wind speed and light intensity) through the sensor network;

[0054] Data processing and storage module: Use edge computing devices to perform preliminary data processing and upload key parameters to the cloud database for storage and analysis;

[0055] Algorithm model module: including maintenance optimization model based on reinforcement learning and dynamic energy efficiency optimization model;

[0056] Execution feedback module: adjusts generator set operating parameters in real time and provides maintenance suggestions.

[0057] An optimization method for intelligent operation and maintenance of a new energy generator set, the optimization method is applicable to the above optimization system, and the optimization method includes the following steps:

[0058] S1: Data collection and preprocessing;

[0059] Sensors collect the operating status of generator sets and external environmental parameters in real time. Historical maintenance records are stored through blockchain technology to ensure data integrity and traceability, and normalize different data dimensions.

[0060] S2: Construction of maintenance optimization model based on reinforcement learning;

[0061] Building a maintenance optimization model is achieved through the following steps:

[0062] S21: Use the sensor network to collect the operating status data of the generator set and construct a health status evaluation formula, and the health status evaluation formula is as follows: ,in, The health status score reflects the overall health of the generator set. is the maintenance benefit function, which indicates the improvement effect of maintenance operation on the status of the generator set. is the probability density function of failure, which indicates the possibility of equipment failure at time t'. To maintain the collection weights, used to adjust The importance of is the failure risk weight, which is used to adjust the impact of failure probability on health status;

[0063] Set the health status standard threshold in the output of the health status assessment formula ;

[0064] like ≤ , indicating that the health status of the generator set is poor and it is necessary to enter the maintenance decision-making stage;

[0065] like , indicating that the generator set is in normal health and does not require maintenance.

[0066] S22: Initialize the reinforcement learning model, define the state space of reinforcement learning, including H(t) and failure probability, action space (such as different maintenance decision plans) and reward function (comprehensive consideration of maintenance costs and benefits), and use the scoring result of the health state H(t) as the initial state to guide the model's strategy learning.

[0067] S23: In the reinforcement learning training, the maintenance cost and benefit optimization formula is constructed according to the output results of the health status assessment formula;

[0068] The maintenance cost and benefit optimization formula is as follows: ,in, For the optimized maintenance cost-benefit ratio, is the direct cost of the ith maintenance operation, It is equivalent to the output result of the health status assessment formula, that is, the health status score, which represents the health status of the generator set after the i-th maintenance. Delayed loss for maintenance operations, is the maintenance cost weight, which is used to adjust the importance of maintenance cost. is the health status influence coefficient, which is used to control the effect of health status on the cost-benefit ratio. is the delay loss weight, which is used to adjust the impact of delay loss.

[0069] In the output of the maintenance cost and benefit optimization formula, set the threshold ;

[0070] like ≤ When , it means that the current maintenance strategy has low cost and high benefit, so the strategy is implemented;

[0071] like , it means that the current maintenance strategy has high cost or low benefit, and the maintenance strategy needs to be adjusted.

[0072] S24: Generate dynamic maintenance recommendations based on the health status of the generator set, prioritize maintenance for equipment in poor health status, reduce additional losses caused by delayed maintenance, output maintenance strategies, and feed back optimized model parameters for continuous iteration.

[0073] S3: Construction of dynamic energy efficiency optimization model;

[0074] The construction of dynamic energy efficiency optimization model is achieved through the following steps:

[0075] S31: Real-time monitoring of external environment data through sensors;

[0076] S32: construct a dynamic energy efficiency optimization model formula, and substitute the external environment data collected above into the dynamic energy efficiency optimization model formula;

[0077] The dynamic energy efficiency optimization model formula is as follows: ,in, represents the optimized energy efficiency value, represents the power generation efficiency, Indicates the decay rate of load change, Indicates the load variation range, It represents the total output power per unit time. represents the power loss, is the loss function.

[0078] Set thresholds in the output of the dynamic energy efficiency optimization model formula ;

[0079] like ≤ and > , indicating that the current maintenance strategy has controllable cost and high energy efficiency, so the maintenance strategy is implemented;

[0080] like or , maintenance and energy efficiency optimization strategies need to be re-evaluated;

[0081] S33: Dynamic adjustment of operating parameters;

[0082] according to > Based on the judgment results, the operating parameters of the generator set (such as speed and power generation) are adjusted. When the energy efficiency is lower than the threshold, the energy efficiency is improved by optimizing the load distribution and operating parameters.

[0083] S34: Optimizing feedback and continuous improvement;

[0084] According to the historical records and real-time change trends of power generation efficiency, the weight parameters in the model are adjusted, and the dynamic energy efficiency optimization model formula is continuously optimized to make the energy efficiency optimization model more in line with actual operation needs.

[0085] By introducing a comprehensive judgment of health status, maintenance cost and energy efficiency, the system can maximize power generation efficiency and reduce maintenance costs while ensuring the safe operation of equipment, thereby achieving intelligent operation and maintenance optimization.

[0086] S4: Fault prediction and maintenance strategy optimization;

[0087] Optimize maintenance strategy selection based on failure probability and maintenance cost;

[0088] If the risk of failure is high and the maintenance cost is low, perform maintenance immediately;

[0089] If the risk of failure is low and the energy efficiency gain is low, defer maintenance and optimize operating parameters.

[0090] S5: System integration and feedback execution;

[0091] The system interface displays the current status of the generator set, fault prediction results and maintenance recommendations, provides real-time feedback on dynamic energy efficiency optimization, uses actuators to adjust operating parameters in real time, generates maintenance plans and notifies maintenance personnel.

[0092] During use, the present invention adopts a maintenance optimization model based on reinforcement learning and a dynamic energy efficiency optimization model to achieve coordinated optimization of the two. Combined with real-time data analysis, it realizes intelligent, data-driven maintenance decision-making. Through accurate fault prediction and dynamic adjustment, it can effectively avoid excessive or insufficient maintenance of the generator set.

[0093] The maintenance optimization model can not only predict faults and make maintenance decisions based on the real-time operating status of the generator set, but also provide the necessary operating parameters for the energy efficiency optimization model through a feedback mechanism. The dynamic energy efficiency optimization model ensures that the generator set is always in the optimal operating state under different external environmental conditions by adjusting the operating parameters of the unit in real time. This interaction enables a dynamic balance to be maintained between maintenance decisions and energy efficiency improvements, avoiding the disconnection between maintenance and energy efficiency optimization in the traditional model, and achieving the dual goals of maximizing resource utilization and minimizing energy consumption.

[0094] Example 2

[0095] Referring to Tables 1 to 3, which are the second embodiment of the present invention, this embodiment is different from the first embodiment in that, in order to verify its beneficial effects, experimental comparison data between the present invention and the prior art are provided.

[0096] In order to verify the effect of the "intelligent operation and maintenance optimization system and method for new energy generator sets" of the present invention in practical applications, five wind turbines in a coastal area were selected as experimental objects. The experiment included four steps: data collection, model optimization, actual operation test and comparative analysis.

[0097] The following is the specific implementation process:

[0098] Experimental preparation: Install a sensor network at the test site, including temperature sensors, vibration sensors, voltage and current sensors, and environmental data acquisition equipment (such as wind speed and direction sensors). Collect key operating data of the generator set in real time through edge computing devices, and upload it to the cloud database for storage using wireless communication modules. Configure the calculation logic of the health status assessment formula, maintenance cost and benefit optimization formula, and dynamic energy efficiency optimization model formula, deploy them in the algorithm module, and prepare existing technologies (traditional fixed-cycle maintenance strategies and manual energy efficiency adjustment models) for comparison.

[0099] Experimental implementation process

[0100] Data collection: Run 5 generator sets and collect the operating status data of each device, including vibration value, temperature, load change, etc. The collection cycle of each device is 5 minutes. The operation lasts for 7 days, and a total of 1,000 sets of data samples are generated;

[0101] Model optimization and execution: The collected data is analyzed in real time using the health status assessment formula to generate a health status score H(t). When H(t) ≤ 80, the maintenance optimization process is triggered, and the optimal maintenance timing and strategy are calculated based on the maintenance cost and benefit optimization formula. The dynamic energy efficiency optimization model adjusts the operating parameters of the generator set, such as load distribution and speed, based on environmental data and operating status.

[0102] Comparative operation test: Under the same operating environment, the differences in energy efficiency, maintenance cost and failure rate between the optimization system of the present invention and the traditional maintenance strategy are compared, and key indicators before and after the system operation, such as changes in health score, maintenance cost and power generation efficiency, are recorded. The obtained data are recorded in separate tables, as follows.

[0103] Table 1 Comparison of health status scores and maintenance effects

[0104]

[0105] Table 2 Comparison of dynamic energy efficiency optimization effects

[0106]

[0107] Table 3 Comparison of maintenance costs and benefits

[0108]

[0109] Referring to Table 1, Table 2 and Table 3 above, the analysis is specifically conducted from the following three aspects:

[0110] Health status score and maintenance effect: The optimization system of the present invention can significantly improve the health status score of the equipment. After optimization, the health status score increased by about 8.6 points on average, and the number of failures decreased by 60%-100%. In particular, generator sets 1 and 5 did not have any failures during operation, showing high operational reliability. In the traditional method, the equipment failure frequency was high, which easily led to unplanned downtime of the equipment.

[0111] Dynamic energy efficiency optimization: The dynamic energy efficiency optimization model of the present invention significantly improves the energy efficiency value. The energy efficiency value after optimization is improved by 5.88%-8.33%. Compared with the traditional method, the present invention dynamically adjusts the parameters of the generator set according to the load changes and wind speed conditions, thereby improving the operating efficiency, especially the generator set 5, whose energy efficiency value is improved from 84 to 91, and the power generation efficiency is improved by 8.33%. The traditional method cannot achieve a similar effect due to the lack of real-time adjustment capability.

[0112] Maintenance costs and benefits: The optimized system significantly reduced the number of maintenance times, and the total maintenance cost decreased by an average of 22.00%. In particular, the maintenance cost saving rate of generator set 5 reached 22.2%, showing a high economic benefit. The maintenance frequency of traditional maintenance methods was high, the operation and maintenance costs increased significantly, and it was difficult to avoid the occurrence of failures.

[0113] To sum up, this embodiment verifies the innovation and practicality of the present invention through the combination of health status assessment, dynamic energy efficiency optimization and maintenance cost optimization. Compared with traditional technologies, the present invention significantly improves the reliability, energy efficiency and economic benefits of equipment operation, makes up for the defects of lagging traditional maintenance strategies and insufficient energy efficiency optimization capabilities, and has extremely high practical application value and innovative advantages.

[0114] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. An optimization method for intelligent operation and maintenance of new energy generator sets, characterized in that: And the optimization method includes the following steps: S1: Data collection and preprocessing; S2: Construction of maintenance optimization model based on reinforcement learning; Building a maintenance optimization model is achieved through the following steps: S21: Use the sensor network to collect the operating status data of the generator set and construct a health status evaluation formula, and the health status evaluation formula is as follows: in, The health status score reflects the overall health of the generator set. is the maintenance benefit function, which indicates the improvement effect of maintenance operation on the status of the generator set. is the probability density function of failure, which indicates the possibility of equipment failure at time t'. To maintain the collection weights, used to adjust The importance of is the failure risk weight, which is used to adjust the impact of failure probability on health status; S22: reinforcement learning model initialization; S23: In the reinforcement learning training, the maintenance cost and benefit optimization formula is constructed according to the output results of the health status assessment formula; S24: Generate dynamic maintenance suggestions based on the health status of the generator set and output maintenance strategies; Set the health status standard threshold in the output of the health status assessment formula ; like ≤ , indicating that the health status of the generator set is poor and it is necessary to enter the maintenance decision-making stage; like , indicating that the generator set is in normal health and does not require maintenance; The maintenance cost and benefit optimization formula is as follows: in, For the optimized maintenance cost-benefit ratio, is the direct cost of the ith maintenance operation, It is equivalent to the output result of the health status assessment formula, that is, the health status score, which represents the health status of the generator set after the i-th maintenance. Delayed loss for maintenance operations, is the maintenance cost weight, which is used to adjust the importance of maintenance cost. is the health status influence coefficient, which is used to control the effect of health status on the cost-benefit ratio. is the delay loss weight, which is used to adjust the impact of delay loss; In the output of the maintenance cost and benefit optimization formula, set the threshold ; like ≤ When , it means that the current maintenance strategy has low cost and high benefit, so the strategy is implemented; like When , it means that the current maintenance strategy has high cost or low benefit, and the maintenance strategy needs to be adjusted; S3: Construction of dynamic energy efficiency optimization model; The construction of dynamic energy efficiency optimization model is achieved through the following steps: S31: Real-time monitoring of external environment data through sensors; S32: construct a dynamic energy efficiency optimization model formula, and substitute the external environment data collected above into the dynamic energy efficiency optimization model formula; S33: Dynamic adjustment of operating parameters; S34: Optimizing feedback and continuous improvement; The dynamic energy efficiency optimization model formula is as follows: in, represents the optimized energy efficiency value, represents the power generation efficiency, Indicates the decay rate of load change, Indicates the load variation range, It represents the total output power per unit time. represents the power loss, is the loss function; S4: Fault prediction and maintenance strategy optimization; S5: System integration and feedback execution.

2. The optimization method for intelligent operation and maintenance of a new energy generator set according to claim 1 is characterized in that: Setting thresholds in the output of the dynamic energy efficiency optimization model formula ; like ≤ and > , indicating that the current maintenance strategy has controllable cost and high energy efficiency, and the maintenance strategy is implemented; like or , maintenance and energy efficiency optimization strategies need to be re-evaluated.

3. The optimization method for intelligent operation and maintenance of a new energy generator set according to claim 1 is characterized in that: In said S4, optimizing the maintenance strategy selection according to the failure probability and the maintenance cost; If the risk of failure is high and the maintenance cost is low, perform maintenance immediately; If the risk of failure is low and the energy efficiency gain is low, defer maintenance and optimize operating parameters.

Images