Complex system preventive maintenance decision generation method, system and equipment considering repair fatigue phenomenon and medium

By introducing failure rate increase factor and service age rollback factor models in complex systems, the prevention of maintenance strategies is optimized, and the problem of waste of maintenance resources caused by repair fatigue is solved, and optimal maintenance decision-making and cost management are achieved.

CN118967094APending Publication Date: 2024-11-15NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410987127.0
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-23
Publication Date
2024-11-15

AI Technical Summary

Technical Problem

The prior art fails to effectively consider repair fatigue when dealing with the prevention and maintenance of complex systems, resulting in waste of maintenance resources and excessive maintenance.

Method used

By introducing the failure rate increase factor and service age rollback factor model, recursive equations of complex systems are derived, and prevention and maintenance strategies are optimized according to the update remuneration theorem, and the optimal prevention and maintenance intervals and times are set to minimize the maintenance cost rate.

Benefits of technology

It provides more scientific maintenance decisions, reduces waste of maintenance resources, avoids excessive repairs, and improves the effectiveness of equipment life and failure rate management.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118967094A_ABST
    Figure CN118967094A_ABST
Patent Text Reader

Abstract

The invention discloses a complex system preventive maintenance decision generation method, system and device considering a repair fatigue phenomenon, and a medium, and relates to the technical field of complex system preventive maintenance management. The method comprises the following steps: introducing a failure rate increasing factor model and a service age backspacing factor model to describe the influence of imperfect preventive maintenance on system failure rate change and effective service age, sequentially deducing a recursive equation of a system failure rate in a preventive maintenance period, deducing a maintenance cost rate of long-term operation of the complex system, deducing an optimal preventive maintenance interval of the complex system when a preventive maintenance frequency is given, and deducing an optimal preventive maintenance frequency of the complex system when the preventive maintenance interval is given; and finally, deducing an optimal preventive maintenance interval and an optimal preventive maintenance frequency when the maintenance cost rate is minimized by using a heuristic algorithm. According to the method, a periodic imperfect prevention and maintenance strategy for a single-component system or a single-fault-mode degradation system is established and optimized according to the update reward theorem, and a theoretical basis and technical support are provided for better planning and maintenance decisions for industrial enterprises.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of complex system preventive maintenance management, and in particular to a complex system preventive maintenance decision-making method, system, equipment and medium taking into account repair fatigue phenomenon. Background Art

[0002] Preventive Maintenance (PM) mainly refers to a maintenance method that starts a series of maintenance on the premise that the product has not failed or has not been damaged. It is a full range of activities carried out to prevent functional failures and keep it in a specified state through systematic inspection, equipment testing and replacement of products. Preventive maintenance is also receiving widespread attention from engineering and technical personnel because it can timely and accurately eliminate potential failure hazards of components and improve their operational reliability.

[0003] According to the different degrees of repair, preventive maintenance can usually be divided into three categories, namely perfect maintenance, imperfect maintenance and minimum maintenance. Perfect maintenance can make the system as good as new, that is, after maintenance, the system failure rate is reduced to zero; minimum maintenance is "repaired as old", which means that the system can be restored to operation after maintenance, but the failure rate is the same as the last moment before the failure. Perfect maintenance and minimum maintenance are both ideal situations. In actual engineering, the structure of key components is relatively complex, and their performance will produce fatigue and wear and aging with the increase of operating time. The maintenance activities implemented on them are mostly imperfect maintenance, that is, after maintenance, the system status will be at a level between "repaired as new" and "repaired as old".

[0004] As the service life of equipment continues to decline and the number of maintenance times increases, the equipment in actual projects will gradually experience "repair fatigue", that is, the marginal contribution of maintenance activities to improving equipment life and failure rate will become smaller and smaller. At this time, blindly relying on increasing the number of maintenance times to improve equipment performance will lead to a greater waste of maintenance resources and excessive maintenance. Summary of the invention

[0005] The purpose of the present invention is to provide a method, system, equipment and medium for generating preventive maintenance decisions for complex systems taking into account the repair fatigue phenomenon, which can establish and optimize a periodic imperfect preventive maintenance strategy for a single-component system or a single-fault mode degradation system based on the renewal reward theorem, and provide a theoretical basis and technical support for industrial enterprises to better plan maintenance decisions.

[0006] To achieve the above object, the present invention provides the following solutions:

[0007] A method for making preventive maintenance decisions for complex systems considering repair fatigue phenomena, comprising:

[0008] The failure rate increase factor and service age regression factor are used to describe the impact of imperfect preventive maintenance on the system failure rate variation and effective service age, and the recursive equation of the system failure rate within the preventive maintenance cycle is derived.

[0009] According to the renewal reward theorem, the maintenance cost rate of the long-term operation of the complex system is derived based on the recursive equation;

[0010] Setting the number of preventive maintenance times, and deriving an optimal preventive maintenance interval for the complex system based on the number of preventive maintenance times and the recursive equation;

[0011] Setting a preventive maintenance interval, and deriving an optimal preventive maintenance number of the complex system based on the preventive maintenance interval and the recursive equation;

[0012] With the goal of minimizing the maintenance cost rate, a heuristic algorithm is used to derive the final optimal preventive maintenance interval and the optimal number of preventive maintenance, and generate preventive maintenance decisions for complex systems.

[0013] Optionally, the derivation process of the recursive equation is:

[0014] Let the failure rate function h of the system in the nTth (n=2,3,...,N-1)th maintenance cycle be n (t) means:

[0015] h n (t) = a n-1 h n-1 (t+(1-b n-1 )T)

[0016] Among them, a n Increase the nth failure rate by factor a k ; b n is the nth service age regression factor b k ;

[0017] Using the recursive algorithm, the failure rate function of the system in the kTth (k = 1, 2, ..., N) maintenance cycle can be obtained as follows:

[0018]

[0019] Among them, a n Increase the factor a for the i-th failure rate k ; b n is the i-th service age regression factor b k .

[0020] Optionally, the maintenance cost rate is the ratio of the total cost of an update cycle to the expected length of the update cycle, and the formula is:

[0021]

[0022] in, is the minimum number of maintenance times of the system in the kth maintenance cycle; h k is a recursive equation; a i Increase the factor a for the i-th failure rate k ; b j is the j-th service age regression factor b k ;c m is the cost of each minimum maintenance; c p is the cost of each periodic maintenance; c r For replacement cost.

[0023] Optionally, the derivation process of the optimal preventive maintenance interval of the complex system is:

[0024] Given the number of preventive maintenance N, Get the T that minimizes the complex system maintenance cost rate C(N,T) * satisfy:

[0025]

[0026] make For any N:

[0027]

[0028] Since L(N,T) increases monotonically with T, it is deduced that when the number of preventive maintenance times N is given, the optimal preventive maintenance interval of the complex system is:

[0029] when When T * =∞, minimal maintenance of complex systems only in case of failure;

[0030] when Hour, 0 <T * <∞, in kT * (k=1,2,…,N-1) to perform preventive maintenance, * Replace it periodically.

[0031] Optionally, the derivation process of the optimal preventive maintenance times of the complex system is:

[0032] Given a preventive maintenance interval T, the N that minimizes the complex system maintenance cost rate C(N,T) is obtained by C(N+1,T)≥C(N,T) * satisfy:

[0033]

[0034] make For any T, we have:

[0035]

[0036] Since Q(N,T) increases monotonically with N, it is deduced that the optimal number of preventive maintenance times for a complex system given a preventive maintenance interval T is:

[0037] when When N * =1, no preventive maintenance is performed, and the complex system is replaced only when the operating time reaches T;

[0038] when 1 <N * <∞, no preventive maintenance is performed, in kT(k=1,2,...,N * -1) and replace at N*T period.

[0039] Optionally, the method of deriving the final optimal preventive maintenance interval and optimal preventive maintenance times by using a heuristic algorithm with the goal of minimizing the maintenance cost rate specifically includes:

[0040] (1) Initialize c m , c p , c r , h(t), a k , b k , k = 1;

[0041] (2) Let N = N k , derive the optimal preventive maintenance interval of complex systems and obtain T k ;

[0042] (3) Let T = T k , perform the optimal preventive maintenance times for complex systems and obtain N k+1 ;

[0043] (4) If N k+1 =N k , stop the calculation; otherwise, let k = k + 1 and repeat the above steps;

[0044] (5) Set N * =N k , T * =T k , we get C(N * ,T * );

[0045] (6) Output N * , T * ,C(N * ,T * ).

[0046] The present invention also provides a complex system preventive maintenance decision generation system taking into account the repair fatigue phenomenon, comprising:

[0047] A recursive equation derivation unit is used to describe the impact of imperfect preventive maintenance on the system failure rate variation and effective service age by using the failure rate increase factor and service age regression factor, and to derive the recursive equation of the system failure rate within the preventive maintenance cycle;

[0048] The maintenance cost rate derivation unit is used to derive the maintenance cost rate of the long-term operation of the complex system based on the recursive equation according to the renewal reward theorem;

[0049] An optimal preventive maintenance interval derivation unit, used for setting the number of preventive maintenance times and deriving the optimal preventive maintenance interval of the complex system based on the number of preventive maintenance times and the recursive equation;

[0050] An optimal preventive maintenance number derivation unit, used for setting a preventive maintenance interval and deriving an optimal preventive maintenance number of the complex system based on the preventive maintenance interval and the recursive equation;

[0051] The preventive maintenance decision generation unit is used to derive the final optimal preventive maintenance interval and the optimal number of preventive maintenance by using a heuristic algorithm with the goal of minimizing the maintenance cost rate, and to generate preventive maintenance decisions for complex systems.

[0052] The present invention also provides an electronic device, including a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the above-mentioned complex system preventive maintenance decision-making method considering the repair fatigue phenomenon.

[0053] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the complex system preventive maintenance decision-making method considering the repair fatigue phenomenon as described above.

[0054] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0055] The present invention discloses a complex system preventive maintenance decision generation method, system, equipment and medium considering the repair fatigue phenomenon. The method introduces a failure rate increase factor model and a service age regression factor model to describe the impact of imperfect preventive maintenance on the system failure rate change and effective service age, and sequentially derives the recursive equation of the system failure rate within the preventive maintenance cycle, derives the maintenance cost rate of the long-term operation of the complex system, derives the optimal preventive maintenance interval of the complex system when the number of preventive maintenance is given, and derives the optimal number of preventive maintenance times of the complex system when the preventive maintenance interval is given. Finally, a heuristic algorithm is used to derive the optimal preventive maintenance interval and the optimal number of preventive maintenance times when the maintenance cost rate is minimized. The present invention establishes and optimizes a periodic imperfect preventive maintenance strategy for a single-component system or a single-fault mode degradation system based on the renewal reward theorem, providing a theoretical basis and technical support for industrial enterprises to better plan maintenance decisions. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. 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 paying creative labor.

[0057] Figure 1 It is a flow chart of the method for generating preventive maintenance decisions for complex systems according to the present invention.

[0058] Figure 2 is a curve diagram of the failure rate function variation of the system in each maintenance cycle in this embodiment;

[0059] Figure 3 Schematic diagram of the system cycle imperfect preventive maintenance strategy in this embodiment. DETAILED DESCRIPTION

[0060] 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] The purpose of the present invention is to provide a method, system, equipment and medium for generating preventive maintenance decisions for complex systems taking into account the repair fatigue phenomenon, which can establish and optimize a periodic imperfect preventive maintenance strategy for a single-component system or a single-fault mode degradation system based on the renewal reward theorem, and provide a theoretical basis and technical support for industrial enterprises to better plan maintenance decisions.

[0062] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0063] like Figure 1-Figure 3 As shown, the present invention provides a method for generating preventive maintenance decisions for complex systems taking into account repair fatigue phenomena, comprising:

[0064] Step 100: Using the failure rate increase factor and the service age regression factor, describe the impact of imperfect preventive maintenance on the system failure rate variation and effective service age, and derive a recursive equation for the system failure rate within the preventive maintenance cycle;

[0065] Step 200: According to the renewal reward theorem, the maintenance cost rate of the complex system in the long term operation is derived based on the recursive equation;

[0066] Step 300: setting the number of preventive maintenance times, and deriving the optimal preventive maintenance interval of the complex system based on the number of preventive maintenance times and the recursive equation;

[0067] Step 400: setting a preventive maintenance interval, and deriving an optimal preventive maintenance number of the complex system based on the preventive maintenance interval and the recursive equation;

[0068] Step 500: With the goal of minimizing the maintenance cost rate, a heuristic algorithm is used to derive the final optimal preventive maintenance interval and the optimal number of preventive maintenance times, and a preventive maintenance decision for the complex system is generated.

[0069] Based on the above technical solution, each step is further elaborated in detail.

[0070] The specific content of step 100 is as follows:

[0071] (1) The failure rate increase factor model and the service life regression factor model are introduced to describe the impact of imperfect preventive maintenance on the system failure rate variation and effective service life.

[0072] Introducing the failure rate increase factor a k represents the increase rate of system failure rate after the kth preventive maintenance, and the service age regression factor b k It represents the regression ratio of the effective service life of the system after the kth preventive maintenance.

[0073] As the service life of equipment continues to decline and the number of maintenance times increases, the equipment in actual projects will gradually experience the phenomenon of "repair fatigue", that is, the marginal contribution of maintenance activities to the positive impact of improving equipment life and failure rate will become smaller and smaller. At this time, blindly relying on increasing the number of maintenance times to improve equipment performance will lead to a greater degree of waste of maintenance resources and excessive maintenance. Based on the failure rate increase factor and the service life decline factor, considering the "repair fatigue" phenomenon of equipment in actual projects, assuming ak As the number of maintenance increases, b k It decreases gradually with the number of maintenance. Specifically, 1=a0 <a1<…<a N , 1=b0>b1>…>b N >0.

[0074] (2) Derivation of the recursive equation for the system failure rate within the preventive maintenance cycle

[0075] For the periodic imperfect preventive maintenance strategy, the system performs preventive maintenance at time kT (k = 1, 2, ..., N-1) and replaces it at NT. The failure rate function h of the system in the nT (n = 2, 3, ..., N-1)th maintenance cycle is n (t) can be expressed as:

[0076] h n (t) = a n-1 h n-1 (t+(1-b n-1 )T)

[0077] Using the recursive algorithm, the failure rate function of the system in the kTth (k = 1, 2, ..., N) maintenance cycle can be obtained as follows:

[0078]

[0079] The specific content of step 200 is as follows:

[0080] According to the renewal reward theorem, the maintenance cost rate C(N,T) of the long-term operation of a complex system is defined as the ratio of the total cost of an update cycle to the expected length of the update cycle, that is:

[0081]

[0082] in, is the minimum number of maintenance times of the system in the kth maintenance cycle.

[0083] The specific content of step 300 is as follows:

[0084] Given the number of preventive maintenance N, The T that minimizes the maintenance cost rate C(N,T) of the complex system can be obtained * satisfy:

[0085]

[0086] make For any N, we have:

[0087]

[0088] That is, L(N,T) increases monotonically with T. Therefore, when the number of preventive maintenance times N is given, the optimal preventive maintenance interval of the complex system is derived as:

[0089] (1) When When T * =∞, minimal maintenance of complex systems only in case of failure;

[0090] (2) When Hour, 0 <T * <∞, in kT * (k=1,2,...,N-1) to perform preventive maintenance, * Replace it when necessary.

[0091] The specific content of step 400 is as follows:

[0092] Given a preventive maintenance interval T, C(N+1,T)≥C(N,T) can be used to obtain the N that minimizes the complex system maintenance cost rate C(N,T) * satisfy:

[0093]

[0094] make For any T, we have:

[0095]

[0096] That is, Q(N,T) increases monotonically with N. Therefore, it is deduced that when the preventive maintenance interval T is given, the optimal number of preventive maintenance times for the complex system is:

[0097] (1) When When N * =1, no preventive maintenance is performed, and the complex system is replaced only when the operating time reaches T;

[0098] (2) When 1 <N * <∞, no preventive maintenance is performed, in kT (k=1,2,…,N * -1) and perform preventive maintenance and replace at N*T.

[0099] The specific content of step 500 is as follows:

[0100] The optimal preventive maintenance interval and optimal preventive maintenance times are derived using a heuristic algorithm to minimize the maintenance cost rate:

[0101] (1) Initialize c m , c p , c r , h(t), a k , bk , k = 1;

[0102] (2) Let N = N k , obtained from step 3 k ;

[0103] (3) Let T = T k , get N from step 4 k+1 ;

[0104] (4) If N k+1 =N k , stop the calculation; otherwise, let k = k + 1 and repeat the above steps;

[0105] (5) Set N * =N k , T * =T k , we get C(N * ,T * );

[0106] (6) Output N * , T * ,C(N * ,T * ).

[0107] Therefore, as the number of maintenance times continues to increase, the repairable systems in engineering practice will gradually experience the phenomenon of "repair fatigue", that is, the marginal contribution of maintenance activities to the positive impact of improving equipment life and reducing system failure rate will gradually decrease. The innovation of the present invention is to consider the "repair fatigue" phenomenon of equipment in engineering practice, establish a periodic imperfect maintenance decision model based on the dynamic failure rate increase factor and the service age regression factor, and optimize the optimal strategy of the preventive maintenance model based on the renewal reward theorem. The present invention confirms that not considering the "repair fatigue" phenomenon often leads to the existence of excessive maintenance, which not only wastes maintenance resources but also may cause delays in spare parts ordering, providing a theoretical basis and technical support for industrial enterprises to better plan maintenance decisions.

[0108] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0109] This article uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the core idea of ​​the present invention. At the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for generating preventive maintenance decisions for complex systems taking into account repair fatigue phenomena, characterized in that: include: The failure rate increase factor and service age regression factor are used to describe the impact of imperfect preventive maintenance on the system failure rate variation and effective service age, and the recursive equation of the system failure rate within the preventive maintenance cycle is derived. According to the renewal reward theorem, the maintenance cost rate of the long-term operation of the complex system is derived based on the recursive equation; Setting the number of preventive maintenance times, and deriving an optimal preventive maintenance interval for the complex system based on the number of preventive maintenance times and the recursive equation; Setting a preventive maintenance interval, and deriving an optimal preventive maintenance number of the complex system based on the preventive maintenance interval and the recursive equation; With the goal of minimizing the maintenance cost rate, a heuristic algorithm is used to derive the final optimal preventive maintenance interval and the optimal number of preventive maintenance, and generate preventive maintenance decisions for complex systems.

2. The method for generating preventive maintenance decisions for complex systems considering repair fatigue according to claim 1, characterized in that: The derivation process of the recursive equation is: The failure rate function h of the system in the nTth (n=2, 3, ..., N-1) maintenance cycle n (t) means: h n (t)=a n-1 h n-1 (t+(1-b n-1 )T) Among them, a n Increase the nth failure rate by factor a k ; b n is the nth service age regression factor b k ; Using the recursive algorithm, the failure rate function of the system in the kTth (k=1, 2, ..., N) maintenance cycle can be obtained as follows: Among them, a n Increase the factor a for the i-th failure rate k ; b n is the i-th service age regression factor b k .

3. The method for generating preventive maintenance decisions for complex systems considering repair fatigue according to claim 1, characterized in that: The maintenance cost rate is the ratio of the total cost of an update cycle to the expected length of the update cycle, and the formula is: in, is the minimum number of maintenance times of the system in the kth maintenance cycle; h k is a recursive equation; a i Increase the factor a for the i-th failure rate k ; b j is the j-th service age regression factor b k ;c m is the cost of each minimum maintenance; c p is the cost of each periodic maintenance; c r For replacement cost.

4. The method for generating preventive maintenance decisions for complex systems considering repair fatigue according to claim 3, characterized in that: The derivation process of the optimal preventive maintenance interval of the complex system is: Given the number of preventive maintenance N, Get the T that minimizes the complex system maintenance cost rate C(N,T) * satisfy: Since L(N, T) increases monotonically with T, it is deduced that when the number of preventive maintenance times N is given, the optimal preventive maintenance interval of the complex system is: when When T * =∞, minimal maintenance of complex systems only in case of failure; when When 0<T * <∞, in kT * (k=1,2,…,N-1) to perform preventive maintenance, * Replace it periodically.

5. The method for generating preventive maintenance decisions for complex systems considering repair fatigue according to claim 3, characterized in that: The derivation process of the optimal preventive maintenance times of the complex system is as follows: Given a preventive maintenance interval T, the N that minimizes the complex system maintenance cost rate c(N, T) is obtained by C(N+1, T) ≥ C(N, T) * satisfy: now For any T, we have: Since Q(N, T) increases monotonically with N, it is deduced that the optimal number of preventive maintenance times for a complex system given a preventive maintenance interval T is: when When N * =1, no preventive maintenance is performed, and the complex system is replaced only when the operating time reaches T; when When 1<N * <∞, no preventive maintenance is performed, in kT (k=1,2,…,N * -1) to carry out preventive maintenance, * Replace it at T cycle.

6. The method for generating preventive maintenance decisions for complex systems considering repair fatigue according to claim 3, characterized in that: The goal of minimizing the maintenance cost rate is to use a heuristic algorithm to derive the final optimal preventive maintenance interval and optimal preventive maintenance times, specifically including: (1) Initialize c m , c p , c r , h(t), a k , b k , k = 1; (2) TodayN=N k , derive the optimal preventive maintenance interval of complex systems and obtain T k ; (3)Today T=T k , perform the optimal preventive maintenance times for complex systems and obtain N k+1 ; (4) If N k+1 =N k , stop the calculation; otherwise, now k=k+1, repeat the above steps; (5) Set N * =N k , T * =T k , we get C(N * , T * ); (6) Output N * , T * ,C(N * , T * ).

7. A complex system preventive maintenance decision generation system considering repair fatigue phenomenon, characterized in that: include: A recursive equation derivation unit is used to describe the impact of imperfect preventive maintenance on the system failure rate variation and effective service age by using the failure rate increase factor and service age regression factor, and to derive the recursive equation of the system failure rate within the preventive maintenance cycle; The maintenance cost rate derivation unit is used to derive the maintenance cost rate of the long-term operation of the complex system based on the recursive equation according to the renewal reward theorem; An optimal preventive maintenance interval derivation unit, used for setting the number of preventive maintenance times and deriving the optimal preventive maintenance interval of the complex system based on the number of preventive maintenance times and the recursive equation; An optimal preventive maintenance number derivation unit, used for setting a preventive maintenance interval and deriving an optimal preventive maintenance number of the complex system based on the preventive maintenance interval and the recursive equation; The preventive maintenance decision generation unit is used to derive the final optimal preventive maintenance interval and the optimal number of preventive maintenance by using a heuristic algorithm with the goal of minimizing the maintenance cost rate, and to generate preventive maintenance decisions for complex systems.

8. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the complex system preventive maintenance decision-making method considering repair fatigue phenomenon according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: The device stores a computer program, which, when executed by a processor, implements a complex system preventive maintenance decision-making method taking repair fatigue into consideration as described in any one of claims 1 to 6.