Selective maintenance decision method and system based on uncertain maintenance quality

Abstract

The application provides a selective maintenance decision-making method and system based on uncertain maintenance quality, a storage medium and an electronic device, and relates to the technical field of intelligent manufacturing. In the application, a service age influence factor is introduced to construct a service age model of equipment under different maintenance levels; according to the service age influence factor, maintenance cost and maintenance time of the equipment under different maintenance levels are obtained; according to the service age model, system reliability is obtained; at least according to the maintenance cost, maintenance time and system reliability, a selective maintenance decision-making model is constructed; the selective maintenance decision-making model is solved, and a global optimal solution selected maintenance decision-making scheme is output and decoded. Through the above process, more accurate maintenance quality can be described, more reasonable maintenance types can be selected, production efficiency can be improved as much as possible, cost can be reduced, and production sustainability can be improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent manufacturing technology, and specifically to a selective maintenance decision-making method, system, storage medium, and electronic device based on uncertain maintenance quality. Background Technology

[0002] For complex, repairable, and large-scale production systems, equipment maintenance is a crucial means of ensuring system safety, reliability, and availability. For example, intelligent tire manufacturing systems, including hydraulic vulcanizing machines and forming machines, have complex mechanical mechanisms composed of numerous precision components with frequent movements. To increase the probability of successfully completing successive tasks, enterprise maintenance personnel need to perform comprehensive maintenance on the equipment during any interval between consecutive tasks to ensure the equipment is always in a stable operating state, maximizing output and production efficiency, reducing costs, and improving sustainability.

[0003] In real-world production environments, tire intelligent manufacturing systems operate under continuous, long-term loads in complex environments. Equipment in each production process is prone to varying degrees of failure. To improve system reliability, ensure continuous task execution, and reduce maintenance costs, companies perform preventative maintenance on different equipment during system task intervals. However, the quality of maintenance varies depending on the experience, methods, and skill level of maintenance personnel, making it difficult to accurately determine the maintenance quality of tire intelligent manufacturing systems. Furthermore, for critical components, if the failure is minor, replacement is costly and labor-intensive, making selective maintenance strategies with multiple maintenance levels essential.

[0004] However, most current studies assume that maintenance optimizes equipment condition as a constant, meaning that maintenance operations have a definite quality effect, such as performing preventive maintenance to increase the effective service life of equipment by N years or reduce the failure rate by 20%, which is obviously not in line with the actual production environment. Summary of the Invention

[0005] (a) Technical problems to be solved

[0006] To address the shortcomings of existing technologies, this invention provides a selective maintenance decision-making method, system, storage medium, and electronic device based on uncertain maintenance quality, thus solving the technical problem of ignoring the uncertainty of maintenance quality.

[0007] (II) Technical Solution

[0008] To achieve the above objectives, the present invention provides the following technical solution:

[0009] A selective maintenance decision-making method based on uncertain maintenance quality, for use in intelligent manufacturing production systems, includes:

[0010] Introducing service life influencing factors, constructing service life models for equipment under different maintenance levels;

[0011] Based on the service life influencing factors, obtain the maintenance costs and maintenance time of the equipment under different maintenance levels;

[0012] Based on the service life model, the system reliability is obtained;

[0013] At least based on the aforementioned maintenance costs, maintenance time, and system reliability, a selective maintenance decision model should be constructed;

[0014] Solve the selective maintenance decision model, output and decode the global optimal solution to select the maintenance decision scheme.

[0015] Preferably, the service life model of the construction equipment under different maintenance levels includes:

[0016] S11. Define the corresponding maintenance level according to different maintenance types:

[0017] For preventative maintenance, the maintenance level is defined as l. ij =0; For intermediate maintenance, define maintenance level l ij ∈(0, L); For corrective maintenance, define maintenance level l ij =L;

[0018] S12. Based on the aforementioned maintenance level, introduce corresponding service life influencing factors:

[0019] For l ij =0, introducing the service life influencing factor. For l ij ∈(0,L), introduce the influence factor of service age. For l ij =0, introducing the service life influencing factor.

[0020] S13. Construct service life models for equipment under different maintenance levels;

[0021]

[0022] Where i is the index of the production process in the intelligent manufacturing production system, i = {i | i = 1, 2, ..., J}, and J is the total number of processes;

[0023] j is the equipment index in the i-th production process, j = {j | j = 1, 2, ..., N} i}, N i Let be the total number of equipment in the i-th production process;

[0024] C ij Let j be the j-th device in the i-th production process of the intelligent manufacturing production system;

[0025] It follows a Beta distribution;

[0026] T ij (m), T ij (m+1) represent equipment C respectively. ij The effective remaining lifespan of the equipment before completing the m-th and m+1-th tasks;

[0027] Δ is a constant representing the duration of each task traversing all processes.

[0028] Preferably, the maintenance cost of the equipment under different maintenance levels refers to:

[0029]

[0030] Among them, MC ij (l ij ) for device C ij Select maintenance level l ij Repair costs for different repair types;

[0031] For device C ij The highest historical repair cost for performing intermediate-level repairs; For device C ij The highest historical repair cost for performing corrective maintenance;

[0032] For the reason The obtained mean, For the reason The variance obtained; For random variables The probability density function;

[0033] r c d c All of these are adjustable parameters related to maintenance costs;

[0034] And / or the maintenance time of the equipment at different maintenance levels refers to:

[0035]

[0036] Among them, MC ij (l ij ) for device C ij Select maintenance level l ij Repair time for the type of repair;

[0037] For device C ij The maximum historical maintenance duration for preventative or intermediate maintenance; For device C ij The maximum historical maintenance duration for corrective maintenance;

[0038] r c d c These are all adjustable parameters related to maintenance time.

[0039] Preferably, the process of obtaining the system reliability includes:

[0040] S31. Obtain the reliability of a single device;

[0041]

[0042]

[0043] in, Select maintenance level l after the system performs m tasks. ij Repair type, equipment C ij The reliability of the conditions when executing the (m+1)th task;

[0044] P is a probability function; T ij For device C ij Effective remaining lifespan; For random variables The cumulative density function;

[0045] S32. Obtain system reliability;

[0046]

[0047] Where R(m+1|m,l) ij () represents system reliability.

[0048] Preferably, the selective maintenance decision model includes:

[0049] (1) The first objective function f(x)1 is to minimize maintenance costs;

[0050] f(x)1=min(PMcost+CMcost+Fcost+Dcost)

[0051]

[0052]

[0053]

[0054]

[0055] Among them, PMcost, CMcost, Fcost, and Dcost correspond to the total cost of intermediate maintenance, the total cost of corrective maintenance, the total cost of failure, and the total cost of downtime in a smart manufacturing production system.

[0056] Y ij (m) is the decision variable. If device C ends after completing the m-th task... ij It can still work normally, so we take 1. At this time, l ij ∈[0, L); otherwise, take 0, in which case l ij =L;

[0057] As the decision variable, if device C ij After completing the m-th task, select maintenance level l. ij If the repair type is specified, select 1; otherwise, select 0.

[0058] -lnR(m+1)+lnR(m) represents the number of failures in the system during the time period from the end of the m-th task to the end of the (m+1)-th task;

[0059] Mf cost The unit failure cost of the system during the task production process;

[0060] Df cost This refers to the unit downtime cost incurred during system maintenance during the production process.

[0061] (2) The second objective function f(x)2, which aims to maximize reliability:

[0062] f(x)2=Max(R(m+1|m,l ij )).

[0063] Preferably, the selective maintenance decision model further includes constraints:

[0064] 1) Reliability constraints:

[0065]

[0066] Among them, R min The minimum reliability required for the system to complete its task;

[0067] 2) Repair time constraints:

[0068]

[0069] Among them, T max This refers to the maximum maintenance time during the system task interval.

[0070] 3) Restricted corrective maintenance is only performed on equipment C at the end of the m-th task. ij Situations where the system cannot function properly:

[0071]

[0072] 4) In any process, any piece of equipment can select at most one maintenance type after completing the m-th task:

[0073]

[0074] Preferably, the selective maintenance decision model is solved using the simulated annealing algorithm, including:

[0075] S51. Set the initial temperature T0, the number of iterations k = 1; and randomly generate an initial solution;

[0076] S52, For the current solution SM prev A random perturbation is applied, and a new solution SM is generated in its neighborhood. new Calculate the corresponding If ΔC k If the value is less than 0, then the new solution is accepted as the current solution; otherwise, it is accepted by probability. Determine whether to accept the new solution; where T k The temperature during the k-th iteration;

[0077] S53, T k =ρT k-1 , where ρ is the cooling rate, ρ∈(0,1);

[0078] S54. Determine if the temperature has reached the termination temperature level. If so, terminate the algorithm and output the global optimal solution; otherwise, let k = k + 1 and return to S52.

[0079] A selective maintenance decision-making system based on uncertain maintenance quality, for use in intelligent manufacturing production systems, includes:

[0080] An introduction module is used to introduce service life influencing factors and construct service life models for equipment under different maintenance levels;

[0081] The first acquisition module is used to acquire the maintenance cost and maintenance time of the equipment under different maintenance levels based on the service life influencing factor.

[0082] The second acquisition module is used to acquire system reliability based on the service life model;

[0083] A construction module is used to build a selective maintenance decision model based at least on the maintenance cost, maintenance time, and system reliability.

[0084] The solution module is used to solve the selective maintenance decision model, output and decode the global optimal solution to select the maintenance decision scheme.

[0085] A storage medium storing a computer program for selective maintenance decisions based on uncertain maintenance quality, wherein the computer program causes a computer to perform the selective maintenance decision-making method as described above.

[0086] An electronic device, comprising:

[0087] One or more processors; a memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including methods for performing selective maintenance decisions as described above.

[0088] (III) Beneficial Effects

[0089] This invention provides a selective maintenance decision-making method, system, storage medium, and electronic device based on uncertain maintenance quality. Compared with the prior art, it has the following advantages:

[0090] This invention introduces a service life influencing factor to construct a service life model for equipment under different maintenance levels. Based on the service life influencing factor, the maintenance cost and maintenance time of the equipment under different maintenance levels are obtained. Based on the service life model, system reliability is obtained. At least based on the maintenance cost, maintenance time, and system reliability, a selective maintenance decision model is constructed. The selective maintenance decision model is solved, and the globally optimal solution is output and decoded to select a maintenance decision scheme. Through the above process, a more accurate portrayal of maintenance quality and the selection of a more reasonable maintenance type can be achieved, maximizing output and production efficiency, reducing costs, and improving production sustainability. Attached Figure Description

[0091] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0092] Figure 1 A production flow chart of a tire intelligent manufacturing system provided in an embodiment of the present invention;

[0093] Figure 2 A block diagram illustrating a selective maintenance decision-making method based on uncertain maintenance quality, provided in an embodiment of the present invention;

[0094] Figure 3A flowchart of a simulated annealing algorithm provided for an embodiment of the present invention. Detailed Implementation

[0095] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are described clearly and completely. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0096] This application provides a selective maintenance decision-making method, system, storage medium, and electronic device based on uncertain maintenance quality, which solves the technical problem of ignoring the uncertainty of maintenance quality and achieves multi-objective optimization that balances minimizing maintenance costs and maximizing equipment reliability.

[0097] The technical solution in this application is to solve the above-mentioned technical problems, and the general idea is as follows:

[0098] The selective maintenance decision-making scheme provided in this invention is applicable to intelligent manufacturing production systems, including but not limited to tire intelligent manufacturing production systems. These tire intelligent manufacturing production systems include multiple production devices, such as... Figure 1 As shown, its production process includes multiple continuous processes such as mixing, calendering, molding, vulcanization, and testing. At the same time, several production devices will operate in parallel for each production process. When each production task ends, maintenance personnel will perform testing and maintenance operations during the task interval to ensure that the reliability of the tire intelligent manufacturing production system is maintained at an ideal level when the system completes the next production task. After the appropriate testing or maintenance activities are completed, the new production task will start immediately.

[0099] Since the quality of equipment maintenance varies depending on the maintenance method, environment, equipment condition, and technician experience, selective maintenance considering the uncertainty of maintenance quality is essential. Furthermore, a robust maintenance decision-making model is needed to address the maintenance decision-making problem of real-world intelligent tire manufacturing equipment. This invention considers actual maintenance scenarios and incorporates the uncertainties of maintenance experience and environment into the maintenance decision-making model, establishing a selective maintenance decision-making model for an intelligent tire manufacturing system with uncertain maintenance quality. The main contributions are as follows:

[0100] 1) Multi-objective maintenance decision-making that comprehensively considers maximizing the reliability of the intelligent tire manufacturing production system and minimizing maintenance costs;

[0101] 2) Determine which equipment in which production process of the tire intelligent manufacturing production system will perform maintenance activities at what level during which task interval.

[0102] The selective maintenance decision model based on the uncertainty of maintenance quality can make timely decisions according to the service status of equipment in the intelligent tire manufacturing system. It can effectively improve the probability of the intelligent tire manufacturing system successfully completing the succession task and provide targeted measures and effective models for the scientific management of maintenance decisions in the intelligent tire manufacturing system.

[0103] Furthermore, the embodiments of this invention can provide technical support and platform services for the intelligent manufacturing upgrades of core tire manufacturing enterprises, component suppliers, and operation and maintenance companies. The data models and technologies can also be extended to other manufacturing industries, showing broad industrialization prospects. Service areas include tire manufacturers, component suppliers, and downstream automotive repair service providers. This has significant theoretical and practical value for promoting my country's automotive tire manufacturing industry and plays a crucial supporting role in driving the automotive manufacturing industry.

[0104] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0105] Example:

[0106] like Figure 2 As shown, this embodiment of the invention provides a selective maintenance decision-making method based on uncertain maintenance quality for use in intelligent manufacturing production systems, including:

[0107] S1. Introduce service life influencing factors and construct a service life model for equipment under different maintenance levels;

[0108] S2. Based on the service life influencing factors, obtain the maintenance cost and maintenance time of the equipment under different maintenance levels;

[0109] S3. Obtain system reliability based on the service life model;

[0110] S4. Construct a selective maintenance decision model based at least on the maintenance cost, maintenance time, and system reliability.

[0111] S5. Solve the selective maintenance decision model, output and decode the global optimal solution to select the maintenance decision scheme.

[0112] The embodiments of the present invention can accurately characterize the repair quality and select a more reasonable repair type, thereby maximizing output and production efficiency, reducing costs, and improving production sustainability.

[0113] Regarding the intelligent manufacturing production system in this embodiment of the invention, the following description only uses the tire intelligent manufacturing production system as an example, and it is necessary to supplement the description. The following three types of maintenance related to the tire intelligent manufacturing production system are now defined:

[0114] (1) Preventive maintenance is simply inspection: Equipment inspection incurs only a small maintenance cost, which is negligible. Inspection activities in the tire manufacturing system mainly include cleaning and lubrication, adjusting / calibrating equipment, tightening loose parts, and adding supplements (oil, water, etc.).

[0115] (2) Intermediate maintenance: Intermediate maintenance activities mainly include equipment disassembly and reassembly, internal and external handling and calibration of faulty components, etc. This type of maintenance activity is used to repair equipment components in certain processes with different degrees of damage, and usually puts the health status of the tire intelligent manufacturing production system between "new" and "old".

[0116] (3) Corrective maintenance, i.e., replacement or overhaul: Overhaul or replacement maintenance activities involve replacing or replacing critical components with new ones to avoid potential serious damage to the tire production system. In addition, this type of maintenance can also be used for equipment components that have undergone multiple intermediate maintenance and are no longer worth using.

[0117] Furthermore, it's easy to understand that different types of maintenance activities have varying degrees of impact on tire manufacturing equipment production systems. The impact of each type of maintenance operation needs to be modeled as a random variable. For a given piece of equipment, different types of maintenance levels correspond to specific maintenance costs and time requirements.

[0118] The following will detail each step of the above solution:

[0119] In step S1, service life influencing factors are introduced to construct service life models of equipment under different maintenance levels.

[0120] This step introduces a service life influencing factor to model the service life of intelligent tire manufacturing equipment. In reality, maintenance quality varies due to differences in maintenance worker experience, equipment operating environment, etc., so the equipment service life distribution is introduced to describe the continuous state of equipment operation and maintenance.

[0121] Set maintenance level l ij Corresponding service age influencing factor Following a certain distribution, through the influence factor of service years. Depicting repair quality, Corresponding maintenance level l ij .because Therefore, we choose a probability density function defined on the interval [0, 1]. and cumulative density function Let the maintenance level be l ij Corresponding service age influencing factor It follows a Beta distribution, and its probability density function is... as follows:

[0122]

[0123] Where, α ij >0, β ij All values ​​>0 represent shape parameters. The mean can be obtained from the probability density function. and variance mean The variance reflects the level of maintenance skill. Reflects the stability of maintenance quality. The smaller the value, the less impact external factors have on maintenance quality, and the higher the maintenance quality level.

[0124]

[0125] Accordingly, S1 includes:

[0126] S11. Define the corresponding maintenance level according to different maintenance types:

[0127] For preventative maintenance, the maintenance level is defined as l. ij =0; For intermediate maintenance, define maintenance level l ij ∈(0, L); For corrective maintenance, define maintenance level l ij =L;

[0128] S12. Based on the aforementioned maintenance level, introduce corresponding service life influencing factors:

[0129] For l ij =0, introducing the service life influencing factor. For l ij ∈(0,L), introduce the influence factor of service age. For l ij =0, introducing the service life influencing factor.

[0130] S13. Construct service life models for equipment under different maintenance levels;

[0131]

[0132] Where i is the index of the production process in the intelligent tire manufacturing system, i = {i | i = 1, 2, ..., J}, and J is the total number of processes;

[0133] j is the equipment index in the i-th production process, j = {j | j = 1, 2, ..., N} i}, N i Let be the total number of equipment in the i-th production process;

[0134] C ij This refers to the j-th device in the i-th production process of the intelligent tire manufacturing system.

[0135] T ij (m), T ij (m+1) represent equipment C respectively. ij The effective remaining lifespan of the equipment before completing the m-th and m+1-th tasks;

[0136] Δ is a constant (i.e., productivity is constant) and represents the duration for each task to traverse all processes.

[0137] In step S2, the maintenance cost and maintenance time of the equipment under different maintenance levels are obtained based on the service life influencing factor.

[0138] The operational status of a production system under normal maintenance can be measured by the effective service life of the equipment, while maintenance time and maintenance cost indirectly reflect maintenance quality. Therefore, how to determine maintenance time and maintenance cost under the background of uncertain maintenance quality is a key issue in the embodiments of the present invention.

[0139] I. Regarding maintenance costs:

[0140] Depending on the system's reliability, you may or may not choose to perform equipment maintenance.

[0141] If device C ij It can still function normally after executing m tasks. ij When (m) = 1, preventive maintenance can be performed to maintain system reliability, but preventive maintenance (l) ij When Y = 0, the cost is 0; and when Y = 0, the cost is 0. ij Intermediate maintenance can also be performed when (m) = 1 (0 < l). ij <L), at this time the maintenance cost is

[0142] If device C ij A fault Y occurred after executing m tasks. ij When (m) = 0, corrective maintenance is required, such as overhaul or replacement. In this case, the maintenance cost is at most [amount missing].

[0143] In summary, the specific costs for the three repair scenarios with uncertain repair quality are as follows:

[0144]

[0145] Among them, MC ij (l ij ) for device C ij Select maintenance level l ij The repair cost of the repair type;

[0146] For Equipment C ij The historical maximum maintenance cost for performing intermediate maintenance; For Equipment C ij The historical maximum maintenance cost for performing corrective maintenance;

[0147] The smaller, the formula The larger the value, the less the maintenance quality is affected by the external environment and the higher the maintenance quality, and the higher the corresponding overall maintenance cost;

[0148] r c , d c Are all adjustable parameters related to the maintenance cost.

[0149] II. Regarding the maintenance time:

[0150] The maintenance time is divided into two cases: preventive maintenance or intermediate maintenance time, and corrective maintenance time.

[0151] If Equipment C ij Can still work normally Y after performing m tasks ij (m)=1, then it is necessary to calculate the time for performing preventive maintenance and intermediate maintenance. It should be particularly noted that preventive maintenance does not occupy the maintenance cost, but will occupy a certain amount of maintenance time, that is, when the maintenance level l ij =0, the preventive maintenance time is not 0, so 0≤l ij <L's maintenance time is

[0152] If Equipment C ij Fails after performing m tasks Y ij (m)=0, then the corresponding maintenance time for corrective maintenance is

[0153] Based on the above, considering the preventive maintenance and corrective maintenance times with uncertain maintenance quality are specifically as follows:

[0154]

[0155] Among them, MC ij (l ij ) is the maintenance time of the maintenance type with the maintenance level l selected for Equipment C ij ; ij The maintenance time of the maintenance type with the maintenance level l selected for Equipment C

[0156] For Equipment C ij The maximum historical maintenance duration for performing preventive maintenance or intermediate maintenance; For Equipment C ij The maximum historical maintenance duration for performing corrective maintenance;

[0157] The smaller, the more... The larger the value, the less the repair quality is affected by the external environment and the higher the repair quality, but the longer the overall repair time.

[0158] r c d c These are all adjustable parameters related to maintenance time.

[0159] In step S3, the system reliability is obtained based on the service life model.

[0160] To facilitate the construction of the selective maintenance decision model involved in subsequent steps, it is necessary to quantitatively determine the overall reliability of the system in advance. Define device C. ij After executing the m-th task, select to execute l. ij When performing horizontal maintenance, equipment C ij The conditional reliability when executing the (m+1)th task is

[0161] To determine system reliability, S3 includes:

[0162] S31. Obtain the reliability of a single device;

[0163]

[0164]

[0165] in, Select maintenance level l after the system performs m tasks. ij Repair type, equipment c ij The reliability of the conditions when executing the (m+1)th task;

[0166] P is a probability function; T ij For device C ij Effective remaining lifespan; For random variables The cumulative density function;

[0167] S32. Obtain system reliability;

[0168]

[0169] Where R(m+1|m,l) ij () represents system reliability.

[0170] In fact, besides system reliability, determining the number of equipment failures is equally important for subsequent modeling. Therefore, in this step, we also assume that the failure rate function of the intelligent tire manufacturing system over time is... Based on the previous formula, it can be deduced that... right Integrating both sides over the interval [0, t] yields

[0171] Therefore, the number of failures that occur in the tire intelligent manufacturing production system during the time period from the end of the m-th task to the end of the m+1-th task can be derived as h(m+1)-h(m)=-lnR(m+1)+lnR(m).

[0172] In step S4, a selective maintenance decision model is constructed based at least on the maintenance cost, maintenance time, and system reliability.

[0173] To achieve multi-objective optimization that balances minimizing maintenance costs and maximizing reliability in intelligent tire manufacturing systems, this invention fully considers actual maintenance scenarios and incorporates maintenance experience and the uncertainty of the maintenance environment into the maintenance decision model, establishing a selective maintenance decision model for intelligent tire manufacturing systems with stochastic maintenance quality.

[0174] Therefore, in the preferred case, in addition to the maintenance cost, maintenance time and system reliability, when constructing the objective function of the selective maintenance decision model, other factors such as the failure cost and downtime cost that the system may generate during the task production process, as well as the number of equipment failures obtained in the previous steps, should also be considered.

[0175] Accordingly, the selective maintenance decision model includes:

[0176] (1) The first objective function f(x)1 is to minimize maintenance costs;

[0177] f(x)1=min(PMcost+CMcost+Fcost+Dcost)

[0178]

[0179]

[0180]

[0181]

[0182] Among them, PMcost, CMcost, Fcost, and Dcost correspond to the total cost of intermediate maintenance in the tire intelligent manufacturing production system (i.e., the intermediate maintenance cost in the tire intelligent manufacturing production system is the sum of the costs of all parallel equipment in all processes of all tasks in the tire intelligent manufacturing production system when performing intermediate maintenance), the total cost of corrective maintenance (i.e., the corrective maintenance cost in the tire intelligent manufacturing production system is the sum of the costs of all parallel equipment in all processes of all tasks in the tire intelligent manufacturing production system when performing corrective maintenance), the total cost of failure (mainly related to equipment damage and depreciation in the tire intelligent manufacturing system during production, and this cost is measured by the number of failures that occur in the system during the task production process), and the total cost of downtime (performing different levels of maintenance operations during task intervals will lead to production suspension in the tire intelligent manufacturing production system, mainly referring to the total cost incurred by all equipment in all processes of the system when the task production is stopped).

[0183] Y ij (m) is the decision variable. If device C ends after completing the m-th task... ij It can still work normally, so we take 1. At this time, l ij ∈[0, L); otherwise, take 0, in which case l ij =L;

[0184] As the decision variable, if device C ij After completing the m-th task, select maintenance level l. ij If the repair type is specified, select 1; otherwise, select 0.

[0185] Mf cost The unit failure cost of the system during the task production process;

[0186] Df cost This refers to the unit downtime cost incurred during system maintenance during the production process.

[0187] (2) The second objective function f(x)2, which aims to maximize reliability:

[0188] f(x)2=Max(R(m+1|m,l ij )).

[0189] In addition, the selective maintenance decision model also includes constraints:

[0190] 1) Reliability constraints:

[0191]

[0192] Among them, R min The minimum reliability required for the system to complete its task;

[0193] 2) Repair time constraints:

[0194]

[0195] Among them, T max This refers to the maximum maintenance time during the system task interval.

[0196] 3) Restricted corrective maintenance is only performed on equipment C at the end of the m-th task. ij Situations where it cannot work normally (if Y) ij If (m) = 1, the equipment can work normally. Right now For equipment C ij No maintenance operations will be performed; if Y ij If (m) = 0, the equipment cannot function properly. That is, for device C ij Maintenance level 1 can be performed ij =The maintenance operation for L can be skipped:

[0197]

[0198] 4) In any process, any piece of equipment can select at most one maintenance type after completing the m-th task:

[0199]

[0200] In step S5, the selective maintenance decision model is solved, and the global optimal solution is output and decoded to select the maintenance decision scheme.

[0201] Because the maintenance decision-making model for intelligent tire manufacturing equipment based on uncertain maintenance quality involves numerous parameters and nonlinear dependencies between them, finding the optimal selective maintenance strategy is a very challenging task. Therefore, heuristic algorithms are applied to maintenance decision optimization techniques for this type of problem. Although heuristic algorithms cannot guarantee a globally optimal solution, they can provide high-quality solutions within a reasonable search time. These high-quality solutions can be approximated as the globally optimal solution, and the solution efficiency can be significantly improved.

[0202] like Figure 3 As shown, this step uses the simulated annealing algorithm to solve the selective maintenance decision model, including:

[0203] S51. Set the initial temperature T0, the number of iterations k = 1; and randomly generate an initial solution;

[0204] S52, For the current solution SM prev A random perturbation is applied, and a new solution SM is generated in its neighborhood. new Calculate the corresponding If ΔC k If the value is less than 0, then the new solution is accepted as the current solution; otherwise, it is accepted by probability. Determine whether to accept the new solution (Metropolis criterion); where T k The temperature during the k-th iteration;

[0205] S53, T k =ρT k-1 , where ρ is the cooling rate, ρ∈(0,1);

[0206] S54. Determine if the temperature has reached the termination temperature level. If so, terminate the algorithm and output the global optimal solution; otherwise, let k = k + 1 and return to S52.

[0207] After decoding the global optimal solution, it becomes possible to determine which maintenance level and type of maintenance should be selected for any equipment in any production process during any task interval in the intelligent tire manufacturing system, ensuring continuous system operation and improving production efficiency.

[0208] This invention provides a selective maintenance decision-making system based on uncertain maintenance quality for use in intelligent manufacturing production systems, comprising:

[0209] An introduction module is used to introduce service life influencing factors and construct service life models for equipment under different maintenance levels;

[0210] The first acquisition module is used to acquire the maintenance cost and maintenance time of the equipment under different maintenance levels based on the service life influencing factor.

[0211] The second acquisition module is used to acquire system reliability based on the service life model;

[0212] A construction module is used to build a selective maintenance decision model based at least on the maintenance cost, maintenance time, and system reliability.

[0213] The solution module is used to solve the selective maintenance decision model, output and decode the global optimal solution to select the maintenance decision scheme.

[0214] This invention provides a storage medium storing a computer program for selective maintenance decisions based on uncertain maintenance quality, wherein the computer program causes a computer to execute the selective maintenance decision-making method as described above.

[0215] This invention provides an electronic device, comprising:

[0216] One or more processors;

[0217] The memory; and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including methods for performing selective maintenance decisions as described above.

[0218] It is understood that the selective maintenance decision system, storage medium and electronic device based on uncertain maintenance quality provided in the embodiments of the present invention correspond to the selective maintenance decision method based on uncertain maintenance quality provided in the embodiments of the present invention. The explanation, examples and beneficial effects of the relevant contents can be referred to the corresponding parts of the selective maintenance decision method, and will not be repeated here.

[0219] In summary, compared with existing technologies, it has the following beneficial effects:

[0220] In this embodiment of the invention, a service life influencing factor is introduced to construct a service life model for equipment under different maintenance levels. Based on the service life influencing factor, the maintenance cost and maintenance time of the equipment under different maintenance levels are obtained. Based on the service life model, system reliability is obtained. At least based on the maintenance cost, maintenance time, and system reliability, a selective maintenance decision model is constructed. The selective maintenance decision model is solved, and the globally optimal solution is output and decoded to select a maintenance decision scheme. Through the above process, a more accurate portrayal of maintenance quality and the selection of a more reasonable maintenance type can be achieved, maximizing output and production efficiency, reducing costs, and improving production sustainability.

[0221] It should be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0222] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A selective maintenance decision-making method based on uncertain maintenance quality, characterized in that, Used in intelligent manufacturing production systems, including: Introducing service life influencing factors, constructing service life models for equipment under different maintenance levels; Based on the service life influencing factors, obtain the maintenance costs and maintenance time of the equipment under different maintenance levels; Based on the service life model, the system reliability is obtained; At least based on the aforementioned maintenance costs, maintenance time, and system reliability, a selective maintenance decision model should be constructed; Solve the selective maintenance decision model, output and decode the global optimal solution to select the maintenance decision scheme; The construction of the service life model of the equipment under different maintenance levels includes: S11. Define the corresponding maintenance level according to different maintenance types: For preventative maintenance, the maintenance level is defined. For intermediate-level repairs, the repair level is defined. For corrective maintenance, define the maintenance level. ; S12. Based on the aforementioned maintenance level, introduce corresponding service life influencing factors: for Introducing the influence factor of service age 0; for Introducing the influence factor of service age ;for Introducing the influence factor of service age 1; S13. Construct service life models for equipment under different maintenance levels; in, An index for production processes in an intelligent manufacturing production system. }, This represents the total number of processes. For the first Equipment index in the production process, }, For the first The total number of equipment in each production process; For intelligent manufacturing production systems The first step in the production process One device; obey distributed; , Representing the equipment Execution completed The effective remaining lifespan of the equipment prior to this mission; This is a constant, representing the duration for each task to traverse all processes; The maintenance cost of the equipment at different maintenance levels refers to: in, For equipment Select maintenance level as Repair costs for different repair types; For equipment The highest historical repair cost for performing intermediate-level repairs; For equipment The highest historical repair cost for performing corrective maintenance; For the reason The obtained mean, For the reason The variance obtained; For random variables The probability density function; , All of these are adjustable parameters related to maintenance costs; And / or the maintenance time of the equipment at different maintenance levels refers to: in, For equipment Select maintenance level as Repair time for the type of repair; For equipment The maximum historical maintenance duration for preventative or intermediate maintenance; For equipment The maximum historical maintenance duration for corrective maintenance; , All of these are adjustable parameters related to maintenance time; The process of obtaining the system reliability includes: S31. Obtain the reliability of a single device; in, For system execution After this task, select the maintenance level as follows: Repair type, equipment Execute the Reliability of conditions during secondary tasks; It is a probability function; For equipment Effective remaining lifespan; For random variables The cumulative density function; S32. Obtain system reliability; in, For system reliability.

2. The selective maintenance decision-making method as described in claim 1, characterized in that, The selective maintenance decision model includes: (1) The first objective function aimed at minimizing maintenance costs ; in, These correspond to the total cost of intermediate maintenance, total cost of corrective maintenance, total cost of failure, and total cost of downtime for intelligent manufacturing production systems. Let be the decision variable, if the th The device at the end of the next task It can still work normally, so we take 1. Otherwise, take 0. ; As a decision variable, if the equipment Complete the first After this task, select the maintenance level as follows: If the repair type is specified, select 1; otherwise, select 0. For the system in the first The next task ended and the [number]th [time] The number of failures within the time period after the task ends; The unit failure cost of the system during the task production process; This refers to the unit downtime cost incurred during system maintenance during the production process. (2) The second objective function aimed at maximizing reliability : 。 3. The selective maintenance decision-making method as described in claim 2, characterized in that, The selective maintenance decision model also includes constraints: 1) Reliability constraints: in, The minimum reliability required for the system to complete its task; 2) Repair time constraints: in, This refers to the maximum maintenance time during the system task interval. 3) Restricted corrective maintenance is only applicable to the completion of the first stage. The device at the end of the next task Situations where the system cannot function properly: 4) In any process, any piece of equipment completes the first... After this task, you can select at most one repair type: 。 4. The selective maintenance decision-making method as described in claim 2, characterized in that, The selective maintenance decision model is solved using the simulated annealing algorithm, including: S51, Set initial temperature Number of iterations And randomly generate an initial solution; S52, Regarding the current solution A random perturbation is generated, producing a new solution in its neighborhood. Calculate the corresponding ;like If the solution is correct, then accept the new solution as the current solution; otherwise, accept it based on probability. Determine whether to accept the new solution; where, For the first Temperature during the next iteration; S53, Order ,in Cooling rate, ; S54. Determine if the temperature has reached the termination temperature level. If so, terminate the algorithm and output the global optimal solution; otherwise, let... Return to S52.

5. A selective maintenance decision-making system based on uncertain maintenance quality, characterized in that, For use in intelligent manufacturing production systems, the selective maintenance decision system is used to execute the selective maintenance decision method as described in any one of claims 1 to 4, including: An introduction module is used to introduce service life influencing factors and construct service life models for equipment under different maintenance levels; The first acquisition module is used to acquire the maintenance cost and maintenance time of the equipment under different maintenance levels based on the service life influencing factor. The second acquisition module is used to acquire system reliability based on the service life model; A construction module is used to build a selective maintenance decision model based at least on the maintenance cost, maintenance time, and system reliability. The solution module is used to solve the selective maintenance decision model, output and decode the global optimal solution to select the maintenance decision scheme.

6. A storage medium, characterized in that, It stores a computer program for making selective maintenance decisions based on uncertain maintenance quality, wherein the computer program causes the computer to perform the selective maintenance decision-making method as described in any one of claims 1 to 4.

7. An electronic device, characterized in that, include: One or more processors; Memory; as well as One or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the programs including methods for performing selective maintenance decision-making as described in any one of claims 1 to 4.

Images