Equipment maintenance strategy determination method and device based on industrial internet, equipment and medium

Abstract

The invention discloses an industrial internet-based equipment maintenance strategy determination method and device, equipment and a medium, and relates to the field of intelligent production and manufacturing, and the method comprises the steps: dividing a plurality of pieces of production equipment and a plurality of buffer regions in a production line into a plurality of sub-equipment units; determining an initial maintenance strategy and a first state transition probability matrix of each sub-device unit, determining a second state transition probability matrix of the virtual device corresponding to each sub-device unit, and calculating a first internal blocking rate of each sub-device unit; updating the first state transition probability matrix based on the first internal blocking rate to obtain a new first state transition probability matrix; and iteratively updating the initial maintenance strategy based on the new first state transition probability matrix, the first internal blocking rate and the second state transition probability matrix to obtain a target maintenance strategy of each production device. According to the method, the maintenance decision problem of the multi-machine pipeline system can be effectively solved, and the feasibility and efficiency of the solving process can be improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of intelligent production manufacturing, and particularly relates to a device maintenance strategy determination method and device based on an industrial internet, equipment and medium. BACKGROUND

[0002] In modern manufacturing, predictive maintenance can predict the remaining service life of a machine according to its real-time operating state, and determine the optimal maintenance intervention time before failure occurs.

[0003] In the prior art, maintenance decisions are mostly made for a single machine or two machines. For a multi-machine production line system, as the number of machines increases, the state degradation of each machine needs to be considered to directly affect the product quality, and complex linkage effects are generated. The prior art is difficult to effectively deal with the problem of predictive maintenance decision-making for a multi-machine production line, especially considering the overall output performance of the production line. The effectiveness in practical application is limited. Therefore, new modeling and solving methods are needed to achieve globally optimal maintenance decision-making in a multi-machine system to solve the computational complexity and decision coordination problems of the multi-machine system. SUMMARY

[0004] The present application provides a device maintenance strategy determination method and device based on an industrial internet, equipment and medium, which can effectively handle the maintenance decision-making problem of a large-scale multi-machine production line system and improve the feasibility and efficiency of the solving process.

[0005] In a first aspect, the present application provides a device maintenance strategy determination method based on an industrial internet, which comprises:

[0006] dividing a plurality of production devices and a plurality of buffer zones in a production line into a plurality of sub-device units according to the upstream and downstream order of the production line;

[0007] determining an initial maintenance strategy corresponding to each sub-device unit;

[0008] determining a first state transition probability matrix of each sub-device unit under the corresponding initial maintenance strategy, determining a second state transition probability matrix of a virtual device corresponding to each sub-device unit, and calculating a first internal blocking rate of each sub-device unit;

[0009] updating the first state transition probability matrix based on the first internal blocking rate to obtain a new first state transition probability matrix;

[0010] iteratively updating the initial maintenance strategy based on the new first state transition probability matrix, the first internal blocking rate and the second state transition probability matrix to obtain a target maintenance strategy for each production device.

[0011] Further, the first sub-device unit of the plurality of sub-device units comprises a first production device, a first buffer corresponding to the first production device and a second production device, and a non-first sub-device unit of the plurality of sub-device units comprises a previous virtual device, a previous buffer corresponding to a previous production device and a current production device, wherein the previous virtual device is a virtual device composed of all production devices upstream of the current production device.

[0012] Further, the method further comprises: determining a steady-state probability distribution of the sub-device unit; calculating a failure probability of the sub-device unit in a failure state and a repair probability of the sub-device unit from the failure state to a running state based on the steady-state probability distribution and product quality data of the current production device; and constructing the second state transition probability matrix of the virtual device based on the failure probability and the repair probability.

[0013] Further, the first internal blocking rate is generated by an upstream production device, and the first state transition probability matrix is composed of state transition probabilities corresponding to different device maintenance modes under the initial maintenance strategy; and the updating of the first state transition probability matrix based on the first internal blocking rate to obtain a new first state transition probability matrix comprises: obtaining, from the first internal blocking rate of each sub-device unit, a second internal blocking rate generated by a downstream production device for the sub-device unit; and updating, based on the second internal blocking rate, a state transition probability corresponding to a preset device maintenance mode to obtain the new first state transition probability matrix.

[0014] Further, the iterative updating of the initial maintenance strategy based on the new first state transition probability matrix, the first internal blocking rate and the second state transition probability matrix to obtain the target maintenance strategy of each production device comprises: updating the initial maintenance strategy based on the new first state transition probability for each sub-device unit to obtain an intermediate maintenance strategy; obtaining a new first internal blocking rate in the process of updating the second state transition probability matrix based on the intermediate maintenance strategy and the new first state transition probability; if the difference between the new first internal blocking rate corresponding to each sub-device unit and the first internal blocking rate does not satisfy a preset convergence threshold, continuing to perform the updating of the initial maintenance strategy based on the new first state transition probability, the first internal blocking rate and the second state transition probability matrix for each sub-device unit to obtain an intermediate maintenance strategy and a new first internal blocking rate of each sub-device unit; if the difference between the new first internal blocking rate and the first internal blocking rate satisfies the preset convergence threshold, taking the intermediate maintenance strategy as the target maintenance strategy.

[0015] Further, for the first sub-device unit, the determining of the initial maintenance strategy corresponding to the sub-device unit comprises: constructing a Markov decision process model for the first production device, the first buffer and the second production device; and calculating the initial maintenance strategy of the first production device and the second production device based on the Markov decision process model.

[0016] Further, for the non-first sub-device unit, the determining of the initial maintenance strategy corresponding to the sub-device unit comprises: constructing a Markov decision process model for the previous virtual device, the previous buffer and the current production device; and calculating the initial maintenance strategy of the current production device based on the Markov decision process model.

[0017] In a second aspect, the present application provides a device maintenance strategy determination device based on industrial internet, which comprises:

[0018] A device unit division module is configured to divide a plurality of production devices and a plurality of buffers in a production line into a plurality of sub-device units according to the upstream and downstream sequence of the production line.

[0019] An initial strategy determination module is configured to determine an initial maintenance strategy corresponding to each sub-device unit.

[0020] a data operation module, configured to determine a first state transition probability matrix of each of the sub-device units under a corresponding initial maintenance strategy, determine a second state transition probability matrix of a corresponding virtual device of each of the sub-device units, and calculate a first internal blocking rate of each of the sub-device units;

[0021] a data update module, configured to update the first state transition probability matrix based on the first internal blocking rate to obtain a new first state transition probability matrix;

[0022] a target strategy determination module, configured to iteratively update the initial maintenance strategy based on the new first state transition probability matrix, the first internal blocking rate and the second state transition probability matrix to obtain a target maintenance strategy of each of the production devices.

[0023] In a third aspect, an electronic device is provided. The electronic device includes at least one processor and a memory communicatively connected to the at least one processor. The memory stores a computer program executable by the at least one processor. The computer program is executed by the at least one processor to enable the at least one processor to perform the method for determining a device maintenance strategy based on an industrial internet according to any of the embodiments of the present disclosure.

[0024] In a fourth aspect, a computer readable storage medium is provided. The computer readable storage medium stores computer instructions for causing a processor to implement the method for determining a device maintenance strategy based on an industrial internet according to any of the embodiments of the present disclosure.

[0025] In a fifth aspect, a computer program product is provided. The computer program product includes a computer program. The computer program, when executed by a processor, implements the method for determining a device maintenance strategy based on an industrial internet according to any of the embodiments of the present disclosure.

[0026] To solve the defects of the prior art in the background art, the embodiments of the present disclosure provide a method for determining a device maintenance strategy based on an industrial internet. Executing the method can bring the following beneficial effects: the present disclosure splits a multi-machine flow line into multiple two-machine sub-device units, and independently solves the optimal maintenance strategy for each unit. Then, by iteratively updating the state transition probability and the maintenance strategy of each sub-device unit, the predictive maintenance strategy of the multi-machine flow line is effectively approximated. The present disclosure can solve the problem that as the number of production devices and the capacity of the buffer zone increase, the state space and the action space of the system will increase explosively, causing the solution of MDP to encounter the "curse of dimensionality" problem, and causing the dynamic programming solution to be difficult. The present disclosure can effectively handle the maintenance decision problem of large-scale multi-machine flow line systems, and can improve the feasibility and efficiency of the solution process.

[0027] It should be noted that the above computer instructions can be stored on a computer readable storage medium in whole or in part. The computer readable storage medium can be packaged together with the processor of the device maintenance strategy determination apparatus based on the industrial internet, or can be packaged separately from the processor of the device maintenance strategy determination apparatus based on the industrial internet, and the present application does not limit this.

[0028] The description of the second aspect, the third aspect, and the fifth aspect in the present application can refer to the detailed description of the first aspect, and the beneficial effects of the description of the second aspect, the third aspect, and the fifth aspect can refer to the beneficial effect analysis of the first aspect, which will not be described here.

[0029] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor to limit the scope of the present application. Other features of the present application will become apparent through the following description.

[0030] It can be understood that, before using the technical solutions disclosed in the embodiments of the present application, the type, use range, and use scenario of the personal information involved in the present application should be informed to the user and the authorization of the user should be obtained through appropriate means according to relevant laws and regulations. BRIEF DESCRIPTION OF DRAWINGS

[0031] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings needed in the embodiment description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creating any labor.

[0032] Figure 1 A first flowchart of a device maintenance strategy determination method based on the industrial internet provided by the embodiments of the present application;

[0033] Figure 2 A composition schematic diagram of a production line provided by the embodiments of the present application;

[0034] Figure 3 A second flowchart of a device maintenance strategy determination method based on the industrial internet provided by the embodiments of the present application;

[0035] Figure 4 A comparison result of four maintenance methods provided by the embodiments of the present application;

[0036] Figure 5 A structure schematic diagram of a device maintenance strategy determination apparatus based on the industrial internet provided by the embodiments of the present application;

[0037] Figure 6 is a block diagram of an electronic device for implementing a device maintenance strategy determination method based on an industrial internet according to an embodiment of the present application. DETAILED DESCRIPTION

[0038] In order to make the objectives, technical solutions and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work should belong to the protection scope of the present application.

[0039] It should be noted that the terms “first”, “second”, “target” and “original” and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms “include”, “have” and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but can include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0040] Figure 1 A first flowchart of a device maintenance strategy determination method based on an industrial internet according to an embodiment of the present application is provided. The embodiment can be applicable to a scenario of determining a predictive maintenance decision for a production line of multiple machines (i.e., production devices). The device maintenance strategy determination method based on an industrial internet provided by the embodiment of the present application can be executed by a device maintenance strategy determination apparatus based on an industrial internet provided by the embodiment of the present application. The apparatus can be implemented in a software and / or hardware manner and integrated in an electronic device for executing the method.

[0041] Referring to Figure 1 , the method of the embodiment includes but is not limited to the following steps:

[0042] S110, dividing multiple production devices and multiple buffer zones in the production line into multiple sub-device units according to the upstream and downstream order of the production line.

[0043] The production line in the embodiment can refer to a production organization form that raw materials are processed into finished products step by step through a series of production equipment and operations in a specific order. For example, the production of electronic products will use a production line, from the assembly of parts to the completion of the electrical appliance, through the operation of multiple links and equipment.

[0044] The multiple production equipment in the embodiment can refer to various devices with different functions on the production line, each of which undertakes a specific production task. For example, in the production line of electronic products, there can be welding equipment, detection equipment, assembly equipment, etc., which jointly complete the production process of the product.

[0045] The buffer zone in the embodiment can be a temporary storage area set in the production line. Its role is to adjust the production rhythm difference between different links in the production process. When the production speed of the upstream production equipment and the production speed of the downstream production equipment are inconsistent, the buffer zone can temporarily store the intermediate products produced, to avoid interruption of the production process. For example, when the upstream equipment produces faster, and the downstream equipment has limited processing capacity, the intermediate products can be stored in the buffer zone first, waiting for the downstream equipment to process.

[0046] The upstream and downstream sequence in the embodiment can refer to the production sequence of the production line, that is, the raw materials enter from one end, pass through each production equipment and buffer zone in turn, and gradually process into finished products from the other end. In this process, the equipment and buffer zone close to the raw material entering end are in the upstream position, and the equipment and buffer zone close to the finished product output end are in the downstream position.

[0047] In the embodiment of the application, according to the upstream and downstream sequence of the production line, the multiple production equipment and buffer zones are grouped, and each group constitutes a sub-equipment unit. Each sub-equipment unit includes at least one buffer zone and one production equipment, and each sub-equipment unit also includes a virtual device composed of all production equipment upstream of the production equipment or another production equipment.

[0048] It can be understood that the first sub-equipment unit in the multiple sub-equipment units includes the first production equipment in the multiple production equipment, the first buffer zone corresponding to the first production equipment, and the second production equipment. The non-first sub-equipment unit in the multiple sub-equipment units includes the last virtual device, the last buffer zone corresponding to the last production equipment, and the current production equipment, and the last virtual device is a virtual device composed of all production equipment upstream of the current production equipment.

[0049] As Figure 2 The figure shows that the production line is composed of M production equipment and M-1 buffer zones, and the buffer zone is represented by B m (1≤m≤M-1) represents, and the buffer zone capacity is also represented as Bm M m (1≤m≤M) represents. The reference signs M1 to M M represent M production devices, the reference signs B1 to B M-1 represent M-1 buffer zones, and the production line is divided into M-1 two-machine sub-device units, denoted as BU m (1≤m≤M-1) represents. For example, the first production device M1, the first buffer zone B1 corresponding to the first production device, and the second production device M2 are divided into a sub-device unit, denoted as BU1. BU1 can be regarded as a virtual device, denoted as The virtual device BU1, the buffer zone B2, and the production device M3 form a sub-device unit BU2, and so on, so that M-1 sub-device units can be obtained.

[0050] S120, determining an initial maintenance strategy corresponding to each sub-device unit.

[0051] In the embodiment, the production devices M m have N m +1 deteriorating operating states, which can be denoted as α m representing the operating state of the production device M m , that is, α m ∈{0,1,…,N m}. Specifically, α m =0 represents that the production device M m is in a healthy state, and α m =N m represents that the production device M m is in a fault state. If the production device M m is in a non-fault state, it produces a piece of qualified product with a probability of q m (α m (t)), and produces a piece of defective product with a probability of 1-q m (α m (t)). When the production device M m is in a fault state, it cannot produce a workpiece.

[0052] In the embodiment, for the first sub-device unit, the initial maintenance strategy corresponding to the sub-device unit is determined, including: constructing a Markov Decision Process (MDP) model for the first production device, the first buffer zone, and the second production device; and calculating the initial maintenance strategy of the first production device and the second production device based on the MDP model. The maintenance strategy in the application is a predictive maintenance strategy in production.

[0053] In the embodiments of the present application, for the non-first sub-device unit, determining the initial maintenance strategy corresponding to the sub-device unit comprises: constructing an MDP model for the last virtual device, the last buffer and the current production device; and calculating the initial maintenance strategy of the current production device based on the MDP model. In this way, based on the two-machine flow line MDP problem, the initial maintenance strategy of each production device is obtained in turn from the production device M1 to the production device M M by analysis.

[0054] For example, the production device can have states such as "normal operation", "minor fault", "major fault", etc.; and the buffer can have states such as "storage capacity of zero", "storage capacity of half", "storage capacity full", etc. Then, actions that can be taken on them are defined, such as preventive maintenance of the production device, adjustment of the production speed of the production device, input or output operation of the product on the buffer, etc. Then, the rewards brought by each action are determined, such as the production income brought by the normal operation of the device, the cost of maintaining the device, etc. Finally, the state transition probability is calculated, i.e. the possibility of transitioning from one operating state to another operating state after taking a certain action. Through the determination of these elements, the MDP model for the first sub-device unit is constructed.

[0055] The state transition matrix and the reward function of each production device are initialized, and the reward function is composed of three parts: output reward, work-in-process inventory cost and maintenance cost. The output income, work-in-process cost and maintenance cost are comprehensively considered to maximize the system income to construct the reward function, analyze the influence of factors such as machine state degradation, product quality rejection and maintenance activities on the system state transition process, and construct the MDP model; the optimal value function of each state is calculated by using the MDP model constructed, through a specific algorithm (such as value iteration algorithm, policy iteration algorithm, etc.), until the optimal maintenance strategy is obtained, which is recorded as the initial maintenance strategy. The maintenance strategy refers to the plan of deciding when and how to maintain the device under different device states. The solution goal of the predictive maintenance dynamic decision problem is to obtain the maximum cumulative expected discount reward and find the optimal maintenance strategy. For example, when the production device is in the normal operation state, it is more beneficial (from the perspective of maximizing the long-term reward) to immediately perform preventive maintenance or to continue running for a period of time and then maintain.

[0056] It should be noted that for the first sub-device unit BU1, the production device M1, the buffer B1 and the production device M2 are not processed by using the aggregation method, and the optimal initial maintenance strategy can be directly solved by using the two-machine MDP For the non-first sub-device unit BU m , m≥2, since the virtual machine The decision space of the MDP is characterized by only two states, working and failed, and thus the maintenance policy and the maintenance policy only contains maintenance decisions for the production machines M m+1 The solution process of the initial maintenance policy π m is represented by the following equation (1):

[0057]

[0058] wherein π represents the initial maintenance policy for the first production machine and the second production machine in the first sub-unit of machines, represents the MDP model corresponding to the first sub-unit of machines, represents the decision space for the first production machine and the second production machine, represents the first state transition probability matrix corresponding to the first sub-unit of machines, represents the initial maintenance policy for the (m+1)th production machine in the mth sub-unit of machines, represents the MDP model corresponding to the mth sub-unit of machines, represents the decision space for the (m+1)th production machine, represents the first state transition probability matrix corresponding to the (m+1)th sub-unit of machines.

[0059] In this step, the maintenance decision of the multi-machine flow line system is modeled by MDP, the multi-machine flow line is split into multiple two-machine sub-units of machines, and a dynamic programming algorithm is used to solve the initial maintenance policy. Specifically, for a two-machine flow line, a predictive maintenance decision model is established based on Markov decision process, and the optimal initial maintenance policy is obtained by using a dynamic programming algorithm. For a multi-machine flow line, the predictive maintenance policy of the multi-machine flow line is approximately solved based on the aggregation iteration method of the two-machine flow line maintenance policy.

[0060] In S130, the first state transition probability matrix of each sub-unit of machines under the corresponding initial maintenance policy is determined, the second state transition probability matrix of the virtual machine corresponding to each sub-unit of machines is determined, and the first internal blocking rate of each sub-unit of machines is calculated.

[0061] In the embodiments of the present application, the determination process of the first state transition probability matrix is as follows: for the sub-unit of machines BU1 composed of the production machine M1, the buffer B1 and the production machine M2, the initial maintenance policy π Based on the policy π The first state transition probability matrix can be obtained by using the existing calculation method, denoted as P For the virtual machine The sub-device unit BU2 composed of the buffer B2 and the production device M3 obtains the initial maintenance strategy by using a two-machine flow shop MDP problem Based on the strategy The first state transition probability matrix is obtained by using the existing calculation method, denoted as For the case of m>3, the same is true until the production device M M End, get each sub-device unit under the corresponding initial maintenance strategy of the first state transition probability matrix.

[0062] Specifically, determining the second state transition probability matrix of the virtual device corresponding to the sub-device unit comprises: determining the steady-state probability distribution of the sub-device unit; calculating the failure probability of the sub-device unit in the failure state and the repair probability of the sub-device unit from the failure state to the running state based on the steady-state probability distribution and the product quality data of the current production device; and constructing the second state transition probability matrix of the virtual device based on the failure probability and the repair probability.

[0063] In an embodiment, the idea of algorithm state aggregation is to use a running state and a repair state to represent the aggregation performance of the aggregation block, and the probability p represents the failure probability of the aggregation block and r represents the repair probability of the aggregation block. Through such aggregation, the sub-device unit can be modeled by a geometric reliability model, and the second state transition probability matrix Φ of the virtual machine is represented by the following formula (2):

[0064]

[0065] For the solution of the failure probability p and the repair probability r, the embodiment is to solve the system state transition matrix of the subsystem to be aggregated first, and then solve the steady-state probability distribution P sys by the balance equation. Then, the failure probability p, the repair probability r, and the internal blocking rate bl of the aggregation block are solved by the steady-state probability and the formula, and the state aggregation of the subsystem is successfully performed.

[0066] In the embodiment, the product quality data of the current production device is considered in the determination process of the second state transition probability matrix, so that the state degradation of the production device and the product quality can be comprehensively considered.

[0067] S140, update the first state transition probability matrix based on the first internal blocking rate to obtain a new first state transition probability matrix.

[0068] Specifically, the first state transition probability matrix is ​​updated based on the first internal blocking rate to obtain a new first state transition probability matrix, including: obtaining the second internal blocking rate of each sub-equipment unit due to downstream production equipment from the first internal blocking rate corresponding to each sub-equipment unit; and updating the state transition probability corresponding to the preset equipment maintenance method based on the second internal blocking rate to obtain a new first state transition probability matrix.

[0069] The first internal blocking rate is generated by the upstream production equipment to the sub-equipment unit, and the second internal blocking rate is generated by the downstream production equipment to the sub-equipment unit. The second internal blocking rate can be determined by: for the current sub-equipment unit (such as BU m ), the first internal blocking rate bl can be obtained through step S130. m , the next sub-equipment unit (such as BU m+1 ) corresponds to the first internal blocking rate bl m+1 As the current sub-equipment unit BU m The second internal blocking rate.

[0070] The first state transition probability matrix is ​​composed of the state transition probabilities corresponding to different equipment maintenance modes under the initial maintenance strategy. The preset equipment maintenance modes include no maintenance activity and predictive maintenance.

[0071] The above step S120, when determining the initial maintenance strategy, only considers the starvation effect of upstream machines on downstream machines, and does not consider the blocking effect of downstream machines on upstream machines. This step considers the blocking effect and uses the machine's blocking rate to update the state transition probability of the machine under no maintenance activity and predictive maintenance.

[0072] When the maintenance decision is not executed, the production equipment M m From healthy state to fault state, Represents state α m (t) = i transitions to state α m (t+1)=j, where j≥i. When predictive maintenance is performed, the production equipment M m To recover from a deteriorated state to a healthier state, Represents state α m (t) = i transitions to state α m The probability of (t+1)=j, where j≤i.

[0073] Since the update of the machine state transition probability will cause the change of the state transition probability matrix of the MDP, the new first state transition probability matrix after the change is expressed by the following formula (3):

[0074]

[0075] wherein, denotes the new first state transition probability matrix corresponding to the mthsub-device unit, denotes an update function for updating the state transition probability, denotes the first state transition probability matrix corresponding to the mthsub-device unit, bl m+1 denotes the second internal blocking rate corresponding to the m+1thsub-device unit.

[0076] S150, iteratively update the initial maintenance strategy based on the new first state transition probability matrix, the first internal blocking rate and the second state transition probability matrix to obtain the target maintenance strategy of each production device.

[0077] In the embodiments of the present application, updating the first state transition probability matrix of the production device will cause the update of the blocking rate of the machine and the MDP state transition probability matrix, and further cause the change of the optimal predictive maintenance strategy. At the same time, when the optimal predictive maintenance strategy changes, the blocking rate of the production device will also change. Therefore, the embodiments meet the iterative update requirements of the predictive maintenance strategy and the blocking rate based on the initial strategy by using the aggregation iterative algorithm to obtain the target maintenance strategy of each production device.

[0078] In practical applications, the operation process of the present application can be as follows: before the start of the assembly line production, system initialization is first performed, including the installation of sensors, the setting of databases and the configuration of central processing systems. During the production process, the sensors monitor the running state of the machine and the product quality in real time, and transmit the data to the central processing system. The central processing system uses the MDP model and the dynamic programming algorithm to dynamically formulate the optimal predictive maintenance strategy according to the collected data. The maintenance personnel or robots perform the corresponding maintenance activities, such as predictive maintenance or after-maintenance, according to the maintenance decision. After the completion of the maintenance activities, the maintenance effect is fed back to the system for evaluating the effectiveness of the maintenance strategy and providing a reference for subsequent maintenance decisions. Through the cyclic process of real-time monitoring, dynamic decision-making and feedback adjustment, the present application can ensure the efficient operation of the assembly line system, minimize the unexpected downtime, and improve the operation efficiency and product quality level.

[0079] The technical scheme provided by the embodiment comprises the following steps: a plurality of production devices and a plurality of buffer zones in a production line are divided into a plurality of sub-device units according to the upstream and downstream sequence of the production line; an initial maintenance strategy corresponding to each sub-device unit is determined; a first state transition probability matrix of each sub-device unit under the corresponding initial maintenance strategy is determined, a second state transition probability matrix of a virtual device corresponding to each sub-device unit is determined, and a first internal blocking rate of each sub-device unit is calculated; the first state transition probability matrix is updated based on the first internal blocking rate, to obtain a new first state transition probability matrix; and the initial maintenance strategy is iteratively updated based on the new first state transition probability matrix, the first internal blocking rate and the second state transition probability matrix, to obtain a target maintenance strategy of each production device. For a multi-machine production line, as the number of production devices and the capacity of buffer zones increase, the system state space and the action space will increase explosively, which causes the MDP to encounter a curse of dimensionality problem, and makes it difficult to solve the dynamic programming. Therefore, the application proposes an aggregation iteration method, which splits the multi-machine production line into a plurality of two-machine sub-device units, and independently solves the optimal maintenance strategy for each unit. Then, the state transition probability and the maintenance strategy of each sub-device unit are iteratively updated, to effectively approximate the predictive maintenance strategy of the multi-machine production line. The innovation of this method lies in that it can effectively handle the maintenance decision problem of a large-scale multi-machine production line system, and can improve the feasibility and efficiency of the solving process.

[0080] The method for determining the equipment maintenance strategy based on the industrial internet provided by the embodiment of the application is further described below, Figure 3 The second flowchart of the method for determining the equipment maintenance strategy based on the industrial internet provided by the embodiment of the application is shown in FIG. 6. The embodiment of the application is optimized on the basis of the above-mentioned embodiments, and the process of iteratively updating the initial maintenance strategy to obtain the target maintenance strategy is explained in detail.

[0081] Referring to Figure 3 The method of the embodiment of the application comprises but is not limited to the following steps:

[0082] In S210, for each sub-device unit, the initial maintenance strategy is updated based on the new first state transition probability, to obtain an intermediate maintenance strategy.

[0083] In the embodiment of the application, updating the first state transition probability matrix of the production device will cause the optimal predictive maintenance strategy to change. The initial maintenance strategy can be updated based on the new first state transition probability by using the above-mentioned formula (1), to obtain an intermediate maintenance strategy.

[0084] S220 : In the process of updating the second state transition probability matrix based on the intermediate maintenance strategy and the new first state transition probability, a new first internal blocking rate is obtained.

[0085] In the embodiment of the present application, for the sub-equipment unit BU1 composed of the production equipment M1, the buffer zone B1 and the production equipment M2, the initial maintenance strategy is updated to obtain the intermediate maintenance strategy Strategy-based and the new first state transition probability Based on the following formula (4), the virtual machine is obtained The new second state transition probability matrix Φ ’ 2. For virtual machines The sub-equipment unit BU2, which consists of the buffer zone B2 and the production equipment M3, updates the initial maintenance strategy to obtain the intermediate maintenance strategy Strategy-based and the new first state transition probability Based on the following formula (4), the virtual machine is obtained The new second state transition probability matrix Φ ’ 3. New first internal blocking rate bl of production equipment M2 ’ 2. For the case of m>3, the same process is repeated until the production equipment M M Finally, a new first internal blocking rate corresponding to each sub-device unit is obtained.

[0086]

[0087] Where, Φ ’ 2 is the new second state transition probability matrix of the first virtual machine, Indicates the intermediate maintenance strategy between the first production equipment and the second production equipment in the first sub-equipment unit. Represents the new first state transition probability matrix corresponding to the first sub-device unit, Φ ’ m+1 is the new second state transition probability matrix of the mth virtual machine, bl ’ m The new first internal blocking rate corresponding to the mth sub-device unit, The function for calculating the second state transition probability matrix for the mth sub-device unit, represents the intermediate maintenance strategy for the m+1th production equipment in the mth sub-equipment unit, Represents the new first state transition probability matrix corresponding to the mth sub-device unit.

[0088] S230, if the difference between the new first internal blocking rate corresponding to each sub-device unit and the first internal blocking rate does not satisfy the preset convergence threshold, continue to perform, for each sub-device unit, updating of the initial maintenance strategy based on the new first state transition probability, the first internal blocking rate and the second state transition probability matrix to obtain an intermediate maintenance strategy of each sub-device unit and a new first internal blocking rate.

[0089] In the embodiments of the present application, the value of the preset convergence threshold can be determined according to the actual application situation. The number of iterations can also be set.

[0090] S240, if the difference between the new first internal blocking rate and the first internal blocking rate satisfies the preset convergence threshold, the intermediate maintenance strategy is taken as the target maintenance strategy.

[0091] The technical scheme provided by the embodiments can be used for a multi-machine flow line. With the increase of the number of production devices and the capacity of the buffer zone, the system state space and the action space will increase explosively, which causes the MDP solution to encounter the problem of "dimension disaster", resulting in difficulty in dynamic programming solution. Therefore, the present application proposes an aggregation iteration method, which splits the multi-machine flow line into multiple two-machine sub-device units, and independently solves the optimal maintenance strategy for each unit. Then, the state transition probability and the maintenance strategy of each sub-device unit are updated through iteration, and the predictive maintenance strategy of the multi-machine flow line is effectively approximated. The innovation of this method lies in its ability to effectively handle maintenance decision problems of large-scale complex systems while maintaining the feasibility and efficiency of the solution process.

[0092] The present application verifies the effectiveness of the proposed predictive maintenance decision method through numerical experiments. For the convenience of expression, the flow line that only uses after-service repair is defined as the benchmark flow line, denoted as BL, and the proposed predictive maintenance decision method is simply referred to as predictive maintenance (PM) method, denoted as PM. The three other maintenance methods are described as follows:

[0093] (1) Time-based Maintenance (TM): This is a traditional maintenance method that performs maintenance according to fixed time intervals, without considering the actual state of the machine. This method is simple and easy to implement, but may not be able to adapt to dynamic changes in the production process.

[0094] (2) Machine State-based Maintenance (MSM): This method determines the maintenance time according to the operating state of the machine, and uses simulation experiments to maximize system revenue to determine the state threshold for implementing maintenance activities on each machine.

[0095] (3) Buffer State-based Maintenance (BSM): This method adjusts the maintenance strategy according to the work-in-process level of the buffer, considering the balance of the production process. Simulation experiments are used to maximize system revenue, and the buffer threshold for each machine to implement maintenance activities is determined.

[0096] In order to conduct comparative experiments, 5000 pipelines were randomly generated, and the corresponding parameter selection intervals are shown in Tables 1 and 2:

[0097] Table 1 Related parameters of the pipeline

[0098]

[0099] Table 2 Machine state transition probability parameters under different maintenance decisions

[0100]

[0101]

[0102] For the 5000 generated pipelines, the proposed PM method can converge, with a maximum convergence time of 4 minutes and a maximum iteration number of 22. For each pipeline, the pipeline operates on a three-shift rotation system, with each shift working for 8 hours. Under each maintenance method, the pipeline runs for 10 days of warm-up time and 100 days of subsequent operation time, and the output (Throughput, TH), work-in-process (Work-in-process, WIP), and maintenance cost (Maintenance Cost, MC) are calculated. Under each maintenance method, the deviation of the performance indicators from the BL is calculated, and the deviation (denoted by δ) of the output, work-in-process level, and maintenance cost of each pipeline is calculated as follows:

[0103]

[0104] where (·) and (·) BL represent the performance indicator values obtained by different maintenance methods and BL, respectively.

[0105] As Figure 4 shown in Table 3, compared with BL, the average improvement of the pipeline under the PM method, TM method, MSM method, and BSM method is as follows: Figure 4The specific experimental results are as follows: (1) in terms of output benefits, the four maintenance methods can effectively improve the output benefits of the production line. Among them, the output benefits brought by the PM method are the largest, which is 34.88%. (2) in terms of work-in-process cost, compared with the other three methods, the PM method achieves the largest work-in-process cost reduction percentage, which is 37.12%. (3) in terms of maintenance cost, the PM method also brings the lowest maintenance cost, and the reduction percentage is 36.35%.

[0106] The experimental results show that the method of the application has advantages in output benefits, work-in-process cost and maintenance cost. In the comprehensive comparison of the four maintenance methods, the method of the application can effectively mine the maintenance activity intervention time in the production line based on the system state, reduce the maintenance cost and work-in-process cost, and effectively improve the output of the system.

[0107] Figure 5 A structural schematic diagram of an equipment maintenance strategy determination device based on an industrial internet provided for an embodiment of the application is shown in FIG. 5, and the device 500 can include: Figure 5

[0108] A device unit division module 510 is configured to divide a plurality of production devices and a plurality of buffer zones in a production line into a plurality of sub-device units according to the upstream and downstream sequence of the production line.

[0109] An initial strategy determination module 520 is configured to determine an initial maintenance strategy corresponding to each sub-device unit.

[0110] A data operation module 530 is configured to determine a first state transition probability matrix of each sub-device unit under the corresponding initial maintenance strategy, determine a second state transition probability matrix of a virtual device corresponding to each sub-device unit, and calculate a first internal blocking rate of each sub-device unit.

[0111] A data update module 540 is configured to update the first state transition probability matrix based on the first internal blocking rate to obtain a new first state transition probability matrix.

[0112] A target strategy determination module 550 is configured to iteratively update the initial maintenance strategy based on the new first state transition probability matrix, the first internal blocking rate and the second state transition probability matrix to obtain a target maintenance strategy of each production device.

[0113] ​In an embodiment, the first sub-device unit of the plurality of sub-device units comprises a first production device of the plurality of production devices, a first buffer corresponding to the first production device, and a second production device, and a non-first sub-device unit of the plurality of sub-device units comprises a previous virtual device, a previous buffer corresponding to a previous production device, and a current production device, wherein the previous virtual device is a virtual device composed of all production devices upstream of the current production device.

[0114] In an embodiment, the data operation module 530 can be specifically configured to: determine a steady-state probability distribution of the sub-device unit; calculate a failure probability of the sub-device unit in a failure state and a repair probability of the sub-device unit from the failure state to a running state based on the steady-state probability distribution and product quality data of the current production device; and construct a second state transition probability matrix of the virtual device based on the failure probability and the repair probability.

[0115] In an embodiment, the first internal blocking rate is generated by an upstream production device, and the first state transition probability matrix is composed of state transition probabilities corresponding to different device maintenance manners under the initial maintenance strategy.

[0116] In an embodiment, the data update module 540 can be specifically configured to: obtain a second internal blocking rate generated by a downstream production device from the first internal blocking rate corresponding to each sub-device unit; and update state transition probabilities corresponding to a preset device maintenance manner based on the second internal blocking rate to obtain a new first state transition probability matrix.

[0117] In an embodiment, the target strategy determination module 550 can be specifically configured to: for each sub-device unit, update the initial maintenance strategy based on the new first state transition probability to obtain an intermediate maintenance strategy; obtain a new first internal blocking rate in the process of updating the second state transition probability matrix based on the intermediate maintenance strategy and the new first state transition probability; if a difference between the new first internal blocking rate corresponding to each sub-device unit and the first internal blocking rate does not satisfy a preset convergence threshold, continue to perform, for each sub-device unit, updating the initial maintenance strategy based on the new first state transition probability, the first internal blocking rate, and the second state transition probability matrix to obtain an intermediate maintenance strategy of each sub-device unit and a new first internal blocking rate; and if the difference between the new first internal blocking rate and the first internal blocking rate satisfies the preset convergence threshold, take the intermediate maintenance strategy as the target maintenance strategy.

[0118] In an embodiment, for the first sub-equipment unit, the initial strategy determination module 520 can be specifically configured to: construct a Markov decision process model for the first production equipment, the first buffer and the second production equipment; and calculate the initial maintenance strategy of the first production equipment and the second production equipment based on the Markov decision process model.

[0119] In an embodiment, for the non-first sub-equipment unit, the initial strategy determination module 520 can be specifically configured to: construct a Markov decision process model for the last virtual equipment, the last buffer and the current production equipment; and calculate the initial maintenance strategy of the current production equipment based on the Markov decision process model.

[0120] The device maintenance strategy determination apparatus based on the industrial internet provided in the embodiment can be applied to the device maintenance strategy determination method based on the industrial internet provided in any of the above embodiments, and has the corresponding functions and advantages.

[0121] Figure 6 is a block diagram of an electronic device for implementing a device maintenance strategy determination method based on the industrial internet according to an embodiment of the present application. The electronic device 10 is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital assistants, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0122] As shown in Figure 6 The electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which are communicatively connected to the at least one processor 11, wherein the memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12 and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0123] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0124] The processor 11 can be various general and / or special purpose processing components having processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as the industrial internet-based device maintenance policy determination method.

[0125] In some embodiments, the industrial internet-based device maintenance policy determination method can be implemented as a computer program tangibly embodied in a computer readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded onto the RAM 13 and executed by the processor 11, one or more steps of the industrial internet-based device maintenance policy determination method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the industrial internet-based device maintenance policy determination method by any other appropriate means, such as by means of firmware.

[0126] Various implementations of the systems and techniques described above can be realized in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0127] Computer programs used to practice the methods of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program

[0128] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of a machine-readable storage medium will include one or more lines of electrical connections, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0129] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0130] The systems and techniques described herein can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described herein), or any combination of these, such as client- server, peer-to-peer, or cloud computing. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0131] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0132] It is noted that the above describes only the preferred embodiments of the present application and the principles of the technology applied. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, re-adjustments and substitutions can be made by those skilled in the art without departing from the scope of the present application. For example, those skilled in the art can use the above-mentioned various forms of flow, reordering, adding or deleting steps; can perform the steps described in the present application in parallel, sequentially or in different order, as long as the desired results of the technical solutions of the present application can be achieved, which is not limited herein.

[0133] The above detailed description does not constitute a limitation on the scope of protection of the present application. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for determining equipment maintenance strategy based on the Industrial Internet, characterized in that: The method comprises: Divide multiple production equipment and multiple buffers in the production line into multiple sub-equipment units according to the upstream and downstream order of the production line; Determining an initial maintenance strategy corresponding to each of the sub-equipment units; Determine a first state transition probability matrix of each of the sub-equipment units under the corresponding initial maintenance strategy, determine a second state transition probability matrix of the virtual device corresponding to each of the sub-equipment units, and calculate a first internal blocking rate of each of the sub-equipment units; updating the first state transition probability matrix based on the first internal blocking rate to obtain a new first state transition probability matrix; The initial maintenance strategy is iteratively updated based on the new first state transition probability matrix, the first internal blocking rate, and the second state transition probability matrix to obtain a target maintenance strategy for each production equipment.

2. The method for determining equipment maintenance strategy based on the industrial Internet according to claim 1, characterized in that: The first sub-equipment unit among the multiple sub-equipment units includes the first production equipment among the multiple production equipment, the first buffer zone corresponding to the first production equipment, and the second production equipment. The non-first sub-equipment units among the multiple sub-equipment units include the previous virtual equipment, the previous buffer zone corresponding to the previous production equipment, and the current production equipment. The previous virtual equipment is a virtual equipment composed of all production equipment located upstream of the current production equipment.

3. The method for determining equipment maintenance strategy based on the Industrial Internet according to claim 2, characterized in that: The determining of a second state transition probability matrix of the virtual device corresponding to the sub-device unit includes: determining a steady-state probability distribution of the sub-equipment unit; Calculate the failure probability of the sub-equipment unit being in a failure state and the repair probability of the sub-equipment unit transferring from the failure state to the operating state based on the steady-state probability distribution and the product quality data of the current production equipment; A second state transition probability matrix of the virtual device is constructed based on the failure probability and the repair probability.

4. The method for determining equipment maintenance strategy based on the industrial Internet according to claim 1, characterized in that: The first internal blocking rate is generated by upstream production equipment on the sub-equipment unit, and the first state transition probability matrix is ​​composed of state transition probabilities corresponding to different equipment maintenance methods under the initial maintenance strategy; the updating of the first state transition probability matrix based on the first internal blocking rate to obtain a new first state transition probability matrix includes: Obtaining, from the first internal blocking rate corresponding to each of the sub-equipment units, a second internal blocking rate of the sub-equipment unit caused by downstream production equipment; The state transition probability corresponding to the preset device maintenance mode is updated based on the second internal blocking rate to obtain a new first state transition probability matrix.

5. The method for determining equipment maintenance strategy based on the industrial Internet according to claim 1, characterized in that: The iterative updating of the initial maintenance strategy based on the new first state transition probability matrix, the first internal blocking rate, and the second state transition probability matrix to obtain a target maintenance strategy for each production equipment includes: For each of the sub-equipment units, updating the initial maintenance strategy based on the new first state transition probability to obtain an intermediate maintenance strategy; In the process of updating the second state transition probability matrix based on the intermediate maintenance strategy and the new first state transition probability, a new first internal blocking rate is obtained; If the difference between the new first internal blocking rate corresponding to each sub-equipment unit and the first internal blocking rate does not meet a preset convergence threshold, then continuing to execute the updating of the initial maintenance strategy for each sub-equipment unit based on the new first state transition probability, the first internal blocking rate, and the second state transition probability matrix to obtain an intermediate maintenance strategy and a new first internal blocking rate for each sub-equipment unit; If the difference between the new first internal blocking rate and the first internal blocking rate meets the preset convergence threshold, the intermediate maintenance strategy is used as the target maintenance strategy.

6. The method for determining equipment maintenance strategy based on the industrial Internet according to claim 2, characterized in that: For the first sub-equipment unit, determining an initial maintenance strategy corresponding to the sub-equipment unit includes: Constructing a Markov decision process model for the first production equipment, the first buffer zone, and the second production equipment; Initial maintenance strategies for the first production equipment and the second production equipment are calculated based on the Markov decision process model.

7. The method for determining equipment maintenance strategy based on the industrial Internet according to claim 2, characterized in that: For the non-first sub-equipment unit, determining the initial maintenance strategy corresponding to the sub-equipment unit includes: Constructing a Markov decision process model for the previous virtual device, the previous buffer zone, and the current production device; An initial maintenance strategy for the current production equipment is calculated based on the Markov decision process model.

8. An equipment maintenance strategy determination device based on the industrial Internet, characterized in that: The device comprises: The equipment unit division module is used to divide multiple production equipment and multiple buffers in the production line into multiple sub-equipment units according to the upstream and downstream order of the production line; An initial strategy determination module, configured to determine an initial maintenance strategy corresponding to each of the sub-equipment units; a data operation module, configured to determine a first state transition probability matrix of each of the sub-equipment units under a corresponding initial maintenance strategy, determine a second state transition probability matrix of a virtual device corresponding to each of the sub-equipment units, and calculate a first internal blocking rate of each of the sub-equipment units; a data updating module, configured to update the first state transition probability matrix based on the first internal blocking rate to obtain a new first state transition probability matrix; A target strategy determination module is configured to iteratively update the initial maintenance strategy based on the new first state transition probability matrix, the first internal blocking rate, and the second state transition probability matrix to obtain a target maintenance strategy for each production device.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; Wherein, the memory stores a computer program executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the method for determining equipment maintenance strategy based on the industrial Internet as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the method for determining an industrial Internet-based equipment maintenance strategy according to any one of claims 1 to 7 when executed.

Images