Rotating machine testing and overhauling system based on digitization

Abstract

The invention relates to the technical field of rotating machine test and maintenance, and discloses a digital-based rotating machine test and maintenance system, which collects equipment operation data in real time through a data acquisition module to realize multi-angle data fusion; the data storage module transmits the equipment operation data to the cloud platform, so that the safety and stable storage of the data are ensured, and subsequent processing is facilitated; the fault prediction module is used for testing and analyzing the equipment operation data, predicting equipment faults and giving early warning in advance, generating equipment health conditions, and timely discovering the fault problems of the equipment; the maintenance plan module automatically generates a maintenance plan according to the equipment health condition and continuously trains a Q function so as to select an optimal maintenance plan; and the feedback optimization module collects feedback in the maintenance process, evaluates the maintenance effect, and continuously optimizes the maintenance plan based on the feedback result, so that the maintenance plan with the minimum total cost is selected, and the time cost and the resource cost are saved.

Description

Technical Field

[0001] The invention relates to the technical field of turnaround testing and maintenance, and in particular to a turnaround testing and maintenance system based on digitization. Background Art

[0002] With the development of science and technology, by installing sensors on the equipment, collecting equipment operation data in real time, and predicting faults, maintenance costs can be reduced. Through continuous monitoring and timely maintenance, the operation stability and life cycle of the equipment can be improved. Digital instruments can be used to replace traditional manual test tools to improve test accuracy and efficiency. However, most of them have not solved the problem of how to predict equipment failures by collecting equipment operation data in real time and conducting test analysis, giving early warnings to generate equipment health status, automatically generating maintenance plans, and continuously optimizing maintenance plans based on the evaluation results of maintenance effects.

[0003] For example, the patent with publication number CN117890130A discloses a vehicle maintenance management method and test system, including: judging whether the first clamp action is qualified, the first clamp action is the clamp action corresponding to the filling and deflation of the common brake cylinder; if the first clamp action is unqualified, the common brake cylinder is inflated to judge whether the clamp accessories are leaking; if the clamp accessories are leaking, it is judged that the current vehicle can be repaired on site; if the clamp accessories are not leaking, it is judged that at least the clamp accessories need to be returned to the factory for repair. In the process of detecting the common brake cylinder, the detection of whether the clamp accessories are leaking is interspersed, and whether the current vehicle can be repaired on site or needs to be returned to the factory for testing and repair is determined based on whether the clamp accessories are leaking, so as to avoid the problem of increasing labor and material costs due to unnecessary return to the factory process and ensure the normal operation of rail vehicles.

[0004] For example, a Chinese patent with authorization announcement number CN108519245B discloses a performance test device and test method for cable maintenance equipment. The performance test device for cable maintenance equipment is mainly composed of a movable support trolley, experimental components, and a shear wall. A metal frame is welded on the movable support trolley, and the slot at the upper end of the metal frame cooperates with the support shaft at the lower end of the hollow cylinder. The upper end of the hollow cylinder is installed in the arc groove at the upper end of the detachable bracket, and the detachable bracket is installed on the surface of the shear wall. The device is simple to assemble, can meet the performance test requirements of cable maintenance equipment, and can realize multi-angle performance testing. It has a wide range of applications and is suitable for comprehensive testing of cable maintenance equipment before it is put into use.

[0005] The above patents have the problem raised by the background technology: they do not solve the problem of how to predict equipment failures by collecting equipment operation data in real time and conducting test analysis, giving early warnings to generate equipment health status, automatically generating maintenance plans, and continuously optimizing maintenance plans based on the evaluation results of maintenance effects. To solve this problem, the present invention proposes a digital turnaround test and maintenance system. Summary of the invention

[0006] The purpose of this section is to summarize some aspects of the embodiments of the present invention and briefly introduce some preferred embodiments. Some simplifications or omissions may be made in this section and the specification abstract and the invention title of this application to avoid blurring the purpose of this section, the specification abstract and the invention title, and such simplifications or omissions cannot be used to limit the scope of the present invention.

[0007] In view of the above-mentioned problems existing in the existing digital-based turnaround test and maintenance system, the present invention is proposed.

[0008] Therefore, an object of the present invention is to provide a digital-based turnaround test and maintenance system.

[0009] In order to solve the above technical problems, the present invention provides the following technical solutions: a data acquisition module, a data storage module, a fault prediction module, a maintenance plan module and a feedback optimization module.

[0010] The data acquisition module is used to collect equipment operation data in real time;

[0011] The data storage module is used to transmit the device operation data to the cloud platform;

[0012] The fault prediction module is used to test and analyze the equipment operation data, predict equipment failures and give early warnings, and generate equipment health status;

[0013] The maintenance plan module is used to automatically generate a maintenance plan based on the health status of the equipment;

[0014] The feedback optimization module is used to collect feedback during the maintenance process, evaluate the maintenance effect, and continuously optimize the maintenance plan based on the feedback results.

[0015] As a preferred solution of the digitalized turnaround test and maintenance system of the present invention, the real-time equipment operation data is tested and analyzed, and the function expression for predicting equipment failure is as follows:

[0016]

[0017] Where P(y=1|x) represents the probability of equipment failure y=1 under given input feature x, e represents a natural constant, α0, α1, α2, α3, α4, α5 and α6 represent learning parameters, x1 represents the temperature data of the equipment, x2 represents the vibration data of the equipment, x3 represents the operating time data of the equipment, x4 represents the load condition data of the equipment, x5 represents the maintenance record data of the equipment, and x6 represents the temperature data of the environment.

[0018] As a preferred solution of the digitalized turnaround test and maintenance system of the present invention, the formula for automatically generating a maintenance plan is as follows:

[0019] Q(s,m)=Q(s,m)+ε·(h+ρ·Q(s',m')-Q(s,m));

[0020] Where Q(s,m) represents the value function of taking maintenance task allocation action m under the equipment health state s, ε represents the learning rate, h represents the reward after generating the maintenance plan, ρ represents the discount factor for generating the maintenance plan, and Q(s',m') represents the value function of taking the next maintenance task allocation action m' under the next equipment health state s'.

[0021] As a preferred solution of the digitalized turnaround test and maintenance system of the present invention, the equipment operation data is transmitted to the cloud platform, and the transmission process is as follows:

[0022] First, a group of nodes are selected as data storage nodes in the cloud platform, and the backup strategy of each node is determined; secondly, the device operation data collected by the sensor is cut into fragments, the cut device operation data fragments are encrypted, and a unique identifier is assigned to each device operation data fragment to ensure the security of the device operation data during transmission and storage; then the encrypted device operation data fragments are transmitted to the designated node, and the secure communication protocol is used to ensure the confidentiality and integrity of data transmission; then each node verifies and decrypts the received device operation data fragments, and stores the device operation data fragments in real time; finally, each node backs up the device operation data fragments of adjacent nodes according to the backup strategy to ensure redundant storage and recoverability of data; authorized users can obtain device operation data fragments through a secure access mechanism, decrypt and recombine the device operation data fragments, and restore the original device operation data. When a node cannot provide the required device operation data fragments, the cloud platform can use the backup strategy to obtain the missing device operation data fragments from the adjacent nodes;

[0023] The backup strategy means that the node needs to back up the device operation data of the adjacent nodes.

[0024] As a preferred solution of the digitalized turnaround test and maintenance system of the present invention, each node verifies and decrypts the received equipment operation data fragments, and the strategy for verifying the equipment operation data fragments includes:

[0025] Verify the data timeliness and data consistency of the device operation data fragments respectively, configure a preset time sequence, and if the timestamp displayed in the identifier of each device operation data fragment is inconsistent with the preset time sequence, the data timeliness verification fails;

[0026] If the timestamp displayed in the identifier of each device operation data fragment is consistent with the preset time sequence, the data time sequence verification is passed;

[0027] If the device operation data collected by sensors with the same timestamp are inconsistent, the data consistency verification fails;

[0028] If the device operation data collected by sensors with the same timestamp are consistent, the data consistency verification is passed;

[0029] If the data timing verification passes and the data consistency verification passes, the verification of the device running data fragments passes;

[0030] If the data timing verification fails or the data consistency verification fails, the verification of the device operation data fragments fails.

[0031] As a preferred solution of the digitalized turnaround test and maintenance system of the present invention, the device operation data fragments are decrypted and reassembled, and the strategy for reassembling the device operation data fragments includes:

[0032] Identify the identifier of each device operation data fragment, sort the device operation data fragments according to the timestamp in the identifier, move the device operation data fragments to the fragment group one by one in the sorted order, connect each device operation data fragment in turn according to the timestamp order of the fragment group, and restore the original device operation data.

[0033] As a preferred solution of the digitalized turnaround test and maintenance system of the present invention, the backup strategy includes:

[0034] While each node receives the specified device operation data fragments, it backs up the device operation data fragments of the adjacent nodes, and backs up the device operation data fragments received by each node to the local storage, and regularly synchronizes the backup of the local storage to the cloud platform.

[0035] As a preferred solution of the digital-based turnaround test and maintenance system of the present invention, wherein: the equipment operation data includes structural performance data, working status data, maintenance record data and environmental parameter data;

[0036] The structural performance data includes the temperature, pressure and vibration of the equipment, which are used to evaluate the physical state and performance of the equipment during operation;

[0037] The working status data includes the running time, load condition and rotation speed of the equipment, which is used to judge the workload and operation condition of the equipment;

[0038] The maintenance record data includes the maintenance history and repair records of the equipment, which are used to evaluate the reliability and maintenance requirements of the equipment;

[0039] The environmental parameter data includes the temperature, humidity and air pressure of the environment, which are used to assist in analyzing the operating performance of the equipment under different environmental conditions.

[0040] Beneficial effects of the present invention: The present invention collects equipment operation data in real time through the data acquisition module to realize multi-angle data fusion; the data storage module transmits the equipment operation data to the cloud platform to ensure the security and stable storage of the data, which is convenient for subsequent processing; the fault prediction module tests and analyzes the equipment operation data, predicts equipment failures and gives early warnings, generates equipment health status, and can timely discover equipment failure problems; the maintenance plan module automatically generates a maintenance plan according to the equipment health status, continuously trains the Q function, and thus selects the optimal maintenance plan; the feedback optimization module collects feedback during the maintenance process, evaluates the maintenance effect, and continuously optimizes the maintenance plan based on the feedback results, thereby selecting the maintenance plan with the lowest total cost, saving time cost and resource cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0042] Figure 1 This is a system structure diagram of the digitalized turnaround test and maintenance system of the present invention;

[0043] Figure 2 The present invention is a method flow chart of the digitalized turnaround test and maintenance method. DETAILED DESCRIPTION

[0044] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the accompanying drawings.

[0045] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention can also be implemented in other ways different from those described herein, and those skilled in the art can make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0046] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0047] Example 1

[0048] In this embodiment, a system structure diagram of a digital turnaround test and maintenance system is provided, such as Figure 1 As shown, the digital-based turnaround test and maintenance system includes a data acquisition module, a data storage module, a fault prediction module, a maintenance plan module and a feedback optimization module.

[0049] The data acquisition module is used to collect equipment operation data in real time.

[0050] Equipment operation data includes structural performance data, working status data, maintenance record data and environmental parameter data;

[0051] Structural performance data includes the temperature, pressure, and vibration of the equipment, which is used to evaluate the physical state and performance of the equipment during operation;

[0052] Working status data includes the equipment’s operating time, load condition, and speed, which are used to determine the equipment’s workload and operating conditions;

[0053] Maintenance record data includes equipment maintenance history and repair records, which are used to assess equipment reliability and maintenance needs;

[0054] Environmental parameter data includes ambient temperature, humidity and air pressure, which are used to assist in analyzing the operating performance of equipment under different environmental conditions.

[0055] In specific applications, in order to comprehensively evaluate the operating status of the equipment, it is necessary to collect equipment cloud core data from multiple angles, including structural performance data, working status data, maintenance record data and environmental parameter data. The structural performance data includes the temperature, pressure and vibration of the equipment, so it is necessary to install temperature sensors, pressure sensors and vibration sensors at the key working parts of the equipment to collect the temperature, pressure and vibration data of the equipment respectively; the working status data includes the running time, load condition and speed of the equipment, so it is necessary to install counter sensors, power sensors and speed sensors on the equipment to collect the running time, load condition and speed of the equipment respectively; the maintenance record data includes the maintenance history and maintenance records of the equipment, which need to be known from the maintenance log and maintenance report; the environmental parameter data includes temperature, humidity and air pressure, so it is necessary to use temperature sensors, humidity sensors and pressure sensors to collect the temperature, humidity and pressure of the environment respectively.

[0056] The data storage module is used to transmit the equipment operation data to the cloud platform to ensure the security and stable storage of the data for subsequent processing.

[0057] The equipment operation data is transmitted to the cloud platform. The transmission process includes:

[0058] First, a group of nodes are selected as data storage nodes in the cloud platform, and the backup strategy of each node is determined; secondly, the device operation data collected by the sensor is cut into fragments, the cut device operation data fragments are encrypted, and a unique identifier is assigned to each device operation data fragment to ensure the security of the device operation data during transmission and storage; then the encrypted device operation data fragments are transmitted to the designated node, and a secure communication protocol is used to ensure the confidentiality and integrity of data transmission; then each node verifies and decrypts the received device operation data fragments, and stores the device operation data fragments in real time to ensure the integrity and authenticity of the data; finally, each node backs up the device operation data fragments of adjacent nodes according to the backup strategy to ensure redundant storage and recoverability of the data; authorized users can obtain the device operation data fragments through a secure access mechanism, decrypt and recombine the device operation data fragments, and restore the original device operation data. When a node cannot provide the required device operation data fragments, the cloud platform can use the backup strategy to obtain the missing device operation data fragments from the adjacent nodes to ensure the integrity and availability of the data.

[0059] The backup strategy means that the node needs to back up the device operation data of the adjacent nodes.

[0060] Each node verifies and decrypts the received device operation data fragments. The device operation data fragment verification strategy includes:

[0061] Verify the data timeliness and data consistency of the device operation data fragments respectively, configure the preset time sequence, if the timestamp displayed in the identifier of each device operation data fragment is inconsistent with the preset time sequence, the data timeliness verification fails;

[0062] If the timestamp displayed in the identifier of each device operation data fragment is consistent with the preset time sequence, the data time sequence verification is passed;

[0063] If the device operation data collected by sensors with the same timestamp are inconsistent, the data consistency verification fails;

[0064] If the device operation data collected by sensors with the same timestamp are consistent, the data consistency verification is passed;

[0065] If the data timing verification passes and the data consistency verification passes, the verification of the device running data fragments passes;

[0066] If the data timing verification fails or the data consistency verification fails, the verification of the device operation data fragments fails.

[0067] Decrypt and reassemble the device operation data fragments. The strategies for reassembling the device operation data fragments include:

[0068] Identify the identifier of each device operation data fragment, sort the device operation data fragments according to the timestamp in the identifier, move the device operation data fragments to the fragment group one by one in the sorted order, connect each device operation data fragment in turn according to the timestamp order of the fragment group, and restore the original device operation data.

[0069] The backup strategy includes:

[0070] While each node receives the specified device operation data fragments, it backs up the device operation data fragments of the adjacent nodes, and backs up the device operation data fragments received by each node to the local storage, and regularly synchronizes the backup of the local storage to the cloud platform.

[0071] In specific applications, in order to ensure the secure transmission and stable storage of device operation data collected by sensors, a transmission process is designed here. According to the above transmission process, the device operation data is cut into multiple fragments, and a unique identifier is assigned to the device operation data fragment and encrypted, where the identifier contains the timestamp corresponding to the device operation data fragment, and then transmitted to the data storage node in the cloud platform. The node will verify and decrypt the received device operation data fragment. If a node cannot receive data or fails, the cloud platform can transmit the device operation data fragment to the adjacent available node according to the backup strategy, ensuring the continuous transmission and storage of data. When the user needs to use the device operation data, the device operation data fragment is obtained through a secure access mechanism, and it is decrypted and reassembled to restore the original device operation data. If a node cannot provide the required device operation data fragment, the cloud platform can obtain the missing device operation data fragment from the adjacent node according to the backup strategy, ensuring the integrity and availability of the data. The tamper-proof characteristics of the blockchain are used throughout the transmission process to record and track each data transmission, ensuring the traceability and transparency of data transmission.

[0072] The fault prediction module is used to analyze equipment operation data, predict equipment failures and provide early warnings to generate equipment health status.

[0073] The function expression for analyzing the real-time equipment operation data and predicting equipment failure is as follows:

[0074]

[0075] Where P(y=1|x) represents the probability of equipment failure y=1 under given input feature x, e represents a natural constant, α0, α1, α2, α3, α4, α5 and α6 represent learning parameters, x1 represents the temperature data of the equipment, x2 represents the vibration data of the equipment, x3 represents the operating time data of the equipment, x4 represents the load condition data of the equipment, x5 represents the maintenance record data of the equipment, and x6 represents the temperature data of the environment.

[0076] It should be explained that the load condition data of the equipment is recorded as 1 when it is loaded and 0 when it is not loaded; the maintenance record data of the equipment is recorded as the number of times of maintenance.

[0077] In specific applications, the transmitted equipment operation data is cleaned, including the processing of missing values, noise data and outliers. Because not every piece of collected equipment operation data is of research value, the extracted features here include equipment temperature, vibration, operating time, load conditions, maintenance records and ambient temperature. The correlation between the extracted features and whether the equipment fails is studied. Normal equipment is recorded as 0 and equipment failure is recorded as 1. The data set is divided into a training set and a test set. The training set is used to train the above formula to improve the accuracy of predicting the probability of equipment failure. At the same time, a fault threshold is set to determine whether the equipment fails, and an early warning is given to generate equipment health status. At the same time, problematic features and equipment parts are located, and relevant personnel are notified to perform repairs.

[0078] The maintenance plan module is used to automatically generate maintenance plans based on the health status of the equipment, including scheduling of maintenance tasks and resource allocation.

[0079] The formula for automatically generating a maintenance plan is as follows:

[0080] Q(s,m)=Q(s,m)+ε·(h+ρ·Q(s',m')-Q(s,m));

[0081] Where Q(s,m) represents the value function of taking maintenance task allocation action m under the equipment health state s, ε represents the learning rate, h represents the reward after generating the maintenance plan, ρ represents the discount factor for generating the maintenance plan, and Q(s',m') represents the value function of taking the next maintenance task allocation action m' under the next equipment health state s'.

[0082] In specific applications, the health status of the equipment is represented as state s, and the maintenance task is defined as action m. The reward is designed according to the maintenance cost and the degree of equipment life extension. A simulation environment is established. In each time step, the agent selects actions according to the current state and interacts with the environment. Through interaction with the environment, the Q function is continuously updated to optimize the decision-making strategy of the maintenance plan. According to the trained Q function, the optimal maintenance plan is selected in practical applications.

[0083] The feedback optimization module is used to collect feedback during the maintenance process, evaluate the maintenance effect, and continuously optimize the maintenance plan based on the feedback results.

[0084] The generated maintenance plan is selected according to the cost. The expression of the maintenance plan cost function is as follows:

[0085]

[0086] In the formula, min C represents the minimum overall cost of the maintenance plan, n represents the total number of maintenance tasks, and c i represents the cost of the i-th maintenance task, t i Indicates the execution of the i-th maintenance task. When t i = 0 means that the i-th maintenance task will not be executed. i =1 means executing the i-th maintenance task.

[0087] At the same time, the cost function is constrained, and the function expression of the resource constraint condition is as follows:

[0088]

[0089] Where n represents the total number of maintenance tasks, r i represents the resources used for the i-th maintenance task, t i Indicates the execution of the i-th maintenance task. When t i = 0 means that the i-th maintenance task will not be executed. i =1 indicates that the i-th maintenance task is executed, and R indicates the available resources for maintenance.

[0090] The function expression of the time constraint is as follows:

[0091] b i +d i ≤T i ;

[0092] Where b i represents the start time of the i-th maintenance task, d i represents the duration of the ith maintenance task, T i Represents the stipulated time for the ith maintenance task.

[0093] In specific applications, each device needs to be maintained within the specified time to ensure the normal operation of the production line. At the same time, the available resources for maintenance are limited, so it is necessary to arrange the maintenance tasks reasonably and use operations research to build and solve the optimization model of the maintenance plan. By defining the objective function and constraints, and then using the optimization algorithm to solve the optimization model, the best maintenance plan can be obtained.

[0094] Example 2

[0095] In this embodiment, a method flow chart of a digital turnaround test and maintenance method is provided, such as Figure 2 As shown in the figure, the digital-based turnaround test and maintenance method includes:

[0096] S1. Install sensors on the equipment to collect equipment operation data in real time.

[0097] In order to comprehensively evaluate the operating status of the equipment, it is necessary to collect equipment cloud core data from multiple angles, including structural performance data, working status data, maintenance record data and environmental parameter data. The structural performance data includes the temperature, pressure and vibration of the equipment, so it is necessary to install temperature sensors, pressure sensors and vibration sensors at the key working parts of the equipment to collect the temperature, pressure and vibration data of the equipment respectively; the working status data includes the running time, load condition and speed of the equipment, so it is necessary to install counter sensors, power sensors and speed sensors on the equipment to collect the running time, load condition and speed of the equipment respectively; the maintenance record data includes the maintenance history and maintenance records of the equipment, which need to be obtained from the maintenance log and maintenance report; the environmental parameter data includes temperature, humidity and air pressure, so it is necessary to use temperature sensors, humidity sensors and pressure sensors to collect the temperature, humidity and pressure of the environment respectively.

[0098] S2. Transmit the equipment operation data to the cloud platform to ensure the security and stable storage of the data for subsequent processing.

[0099] In order to ensure the secure transmission and stable storage of the device operation data collected by the sensor, a transmission process is designed here. According to the above transmission process, the device operation data is cut into multiple fragments, and a unique identifier is assigned to the device operation data fragments and encrypted, and then transmitted to the data storage node in the cloud platform. The node will verify and decrypt the received device operation data fragments. If a node cannot receive data or fails, the cloud platform can transmit the device operation data fragments to adjacent available nodes according to the backup strategy, ensuring the continuous transmission and storage of data. When the user needs to use the device operation data, the device operation data fragments are obtained through a secure access mechanism, and decrypted and reassembled to restore the original device operation data. If a node cannot provide the required device operation data fragments, the cloud platform can obtain the missing device operation data fragments from the adjacent nodes according to the backup strategy, ensuring the integrity and availability of the data. The tamper-proof characteristics of the blockchain are used throughout the transmission process to record and track each data transmission, ensuring the traceability and transparency of data transmission.

[0100] S3. Analyze equipment operation data, predict equipment failures and give early warnings to generate equipment health status.

[0101] The transmitted equipment operation data is cleaned, including the processing of missing values, noise data and outliers. Because not every piece of collected equipment operation data is of research value, the features extracted here include equipment temperature, vibration, operating time, load conditions, maintenance records and ambient temperature. The correlation between the extracted features and whether the equipment fails is studied. Normal equipment is recorded as 0 and equipment failure is recorded as 1. The data set is divided into a training set and a test set. The training set is used to train the above formula to improve the accuracy of predicting the probability of equipment failure. At the same time, a fault threshold is set to determine whether the equipment fails, and an early warning is given to generate equipment health status. At the same time, the problematic features and equipment parts are located, and relevant personnel are notified to perform repairs.

[0102] S4. Automatically generate maintenance plan based on equipment health status.

[0103] The health status of the equipment is represented as state s, and the maintenance task is defined as action m. The reward is designed according to the maintenance cost and the degree of equipment life extension. A simulation environment is established. At each time step, the agent selects an action according to the current state and interacts with the environment. Through interaction with the environment, the Q function is continuously updated to optimize the decision-making strategy of the maintenance plan. According to the trained Q function, the optimal maintenance plan is selected in practical applications.

[0104] S5. Collect feedback during the maintenance process, evaluate the maintenance results, and continuously optimize the maintenance plan based on the feedback results.

[0105] Each device needs to be maintained within the specified time to ensure the normal operation of the production line. At the same time, the available resources for maintenance are limited, so it is necessary to arrange the maintenance tasks reasonably. Operations research is used to build and solve the optimization model of the maintenance plan. By defining the objective function and constraints, and then using the optimization algorithm to solve the optimization model, the best maintenance plan can be obtained.

[0106] Example 3

[0107] In this embodiment, a computer device is provided, including a memory and a processor, wherein the memory is used to store instructions, and the processor is used to execute the instructions, so that the computer device executes the steps of implementing the above-mentioned digital-based turnaround test and maintenance method.

[0108] Example 4

[0109] In this embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed, the steps of the above-mentioned digital-based turnaround test and maintenance method are implemented.

[0110] The computer-readable storage medium includes: a U disk, a mobile hard disk, a read-only memory, a random access memory, a magnetic disk or an optical disk, and other media for storing program codes.

[0111] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should be included in the scope of the claims of the present invention.

Claims

1. Based on digital turnaround test and maintenance system, it is characterized by: include, Data acquisition module, data storage module, fault prediction module, maintenance plan module and feedback optimization module; The data acquisition module is used to collect equipment operation data in real time; The data storage module is used to transmit the device operation data to the cloud platform; The fault prediction module is used to test and analyze the equipment operation data, predict equipment failures and give early warnings, and generate equipment health status; The maintenance plan module is used to automatically generate a maintenance plan based on the health status of the equipment; The feedback optimization module is used to collect feedback during the maintenance process, evaluate the maintenance effect, and continuously optimize the maintenance plan based on the feedback results.

2. The digitalized turnaround test and maintenance system according to claim 1, characterized in that: The real-time equipment operation data is tested and analyzed, and the function expression for predicting equipment failure is as follows: Where P(y=1|x) represents the probability of equipment failure y=1 under the given input feature x, e represents a natural constant, α0, α1, α2, α3, α4, α5 and α6 represent learning parameters, x1 represents the temperature data of the equipment, x2 represents the vibration data of the equipment, x3 represents the running time data of the equipment, x4 represents the load condition data of the equipment, x5 represents the maintenance record data of the equipment, and x6 represents the temperature data of the environment; The formula for automatically generating a maintenance plan is as follows: Q(s,m)=Q(s,m)+ε·(h+ρ·Q(s',m')-Q(s,m)); Where Q(s,m) represents the value function of taking maintenance task allocation action m under the equipment health state s, ε represents the learning rate, h represents the reward after generating the maintenance plan, ρ represents the discount factor for generating the maintenance plan, and Q(s',m') represents the value function of taking the next maintenance task allocation action m' under the next equipment health state s'.

3. The digitalized turnaround test and maintenance system according to claim 1 or 2, characterized in that: The device operation data is transmitted to the cloud platform, and the transmission process includes: Select a group of nodes in the cloud platform as data storage nodes, and determine the backup strategy for each node; cut the device operation data collected by the sensor into fragments, encrypt the cut device operation data fragments, and assign a unique identifier to each device operation data fragment; transmit the encrypted device operation data fragments to the designated node; each node verifies and decrypts the received device operation data fragments, and stores the device operation data fragments in real time; each node backs up the device operation data fragments of adjacent nodes according to the backup strategy; authorized users can obtain the device operation data fragments through a secure access mechanism, decrypt and reassemble the device operation data fragments, and restore the original device operation data. When a node cannot provide the required device operation data fragments, the cloud platform can use the backup strategy to obtain the missing device operation data fragments from the adjacent nodes; The backup strategy means that the node needs to back up the device operation data of the adjacent nodes.

4. The digitalized turnaround test and maintenance system according to claim 3, characterized in that: Each node verifies and decrypts the received device operation data fragments. The device operation data fragment verification strategy includes: Verify the data timeliness and data consistency of the device operation data fragments respectively, configure a preset time sequence, and if the timestamp displayed in the identifier of each device operation data fragment is inconsistent with the preset time sequence, the data timeliness verification fails; If the timestamp displayed in the identifier of each device operation data fragment is consistent with the preset time sequence, the data time sequence verification is passed; If the device operation data collected by sensors with the same timestamp are inconsistent, the data consistency verification fails; If the device operation data collected by sensors with the same timestamp are consistent, the data consistency verification is passed; If the data timing verification passes and the data consistency verification passes, the verification of the device running data fragments passes; If the data timing verification fails or the data consistency verification fails, the verification of the device operation data fragments fails.

5. The digitalized turnaround test and maintenance system according to claim 4, characterized in that: The device operation data fragments are decrypted and reassembled, and the strategy for reassembling the device operation data fragments includes: Identify the identifier of each device operation data fragment, sort the device operation data fragments according to the timestamp in the identifier, move the device operation data fragments to the fragment group one by one in the sorted order, connect each device operation data fragment in turn according to the timestamp order of the fragment group, and restore the original device operation data.

6. The digitalized turnaround test and maintenance system according to claim 5, characterized in that: The backup strategy includes: While each node receives the specified device operation data fragments, it backs up the device operation data fragments of the adjacent nodes, and backs up the device operation data fragments received by each node to the local storage, and regularly synchronizes the backup of the local storage to the cloud platform.

7. The digitalized turnaround test and maintenance system according to claim 5, characterized in that: The equipment operation data includes structural performance data, working status data, maintenance record data and environmental parameter data; The structural performance data includes the temperature, pressure and vibration of the equipment, which are used to evaluate the physical state and performance of the equipment during operation; The working status data includes the running time, load condition and rotation speed of the equipment, which is used to judge the workload and operation condition of the equipment; The maintenance record data includes the maintenance history and repair records of the equipment, which are used to evaluate the reliability and maintenance requirements of the equipment; The environmental parameter data includes the temperature, humidity and air pressure of the environment, which are used to assist in analyzing the operating performance of the equipment under different environmental conditions.

Images