Intelligent Maintenance Method, System, Device and Medium for Aluminum Foil Cutting Machine

Abstract

The present invention discloses a smart maintenance method, system, device and medium for an aluminum foil cutting machine, relating to the field of data processing. The method includes: loading monitoring elements of the cutting machine; performing real-time monitoring based on the monitoring elements of the cutting machine to obtain a monitoring source of the cutting machine; calculating the variation of the standard state of the monitoring source of the cutting machine to obtain a variation vector of the cutting machine; selecting the variation vector of the cutting machine to generate an abnormal variation vector of the cutting machine; activating a maintenance channel of the cutting machine to conduct maintenance decision analysis and generate a maintenance plan for the cutting machine; and performing maintenance on the aluminum foil cutting machine according to the maintenance plan for the cutting machine. By adopting this method, the technical problem in the prior art that excessive emphasis is placed on repair after a failure occurs, resulting in insufficient preventive maintenance and low maintenance efficiency of the cutting machine, is solved. Through strengthening preventive maintenance and making targeted decisions by referring to the variation vector, the technical effects of improving the preventive maintenance of the cutting machine and specifically solving the faults of the cutting machine are achieved.

Description

Technical Field

[0001] This application relates to the field of data processing technologies, particularly to the field of data processing for cutting machines, specifically to an intelligent maintenance method, system, device, and medium for aluminum foil cutting machines. Background Art

[0002] Currently, the intelligent maintenance method for aluminum foil cutting machines can already monitor the device operation data in real time through devices such as sensors. Through Internet of Things technology, remote monitoring and maintenance of aluminum foil cutting machines can be achieved, and engineers can perform fault diagnosis and repair without going to the site. Based on historical data and algorithm models, some aluminum foil cutting machines can predict potential faults and perform maintenance in advance to avoid equipment downtime. Although aluminum foil cutting machines can monitor and collect a large amount of data, due to factors such as sensor quality and environmental interference, the accuracy and integrity of the data are sometimes difficult to guarantee. This may lead to a decrease in the accuracy rate of fault prediction, affecting the maintenance effect. There may be differences between different models of aluminum foil cutting machines, and general models cannot fully adapt to all situations. In terms of maintenance decision-making, it still relies on manual judgment and experience, lacking an intelligent maintenance decision-making system.

[0003] In summary, there is a technical problem in the prior art that excessive emphasis is placed on repair after a fault occurs, resulting in insufficient preventive maintenance and low maintenance efficiency of the cutting machine. Summary of the Invention

[0004] Based on this, it is necessary to provide an intelligent maintenance method, system, device, and medium for aluminum foil cutting machines that can improve the preventive maintenance of the cutting machine and solve the problems of cutting machine faults.

[0005] In the first aspect, an intelligent maintenance method for an aluminum foil cutting machine is provided. The method includes: loading U-dimensional cutting machine monitoring elements, where the U-dimensional cutting machine monitoring elements include U preset cutting machine monitoring elements, and U is a positive integer greater than 1; according to the U-dimensional cutting machine monitoring elements, combining with a pre-deployed Internet of Things sensing network to monitor the aluminum foil cutting machine in real time, obtaining a cutting machine monitoring source, where the cutting machine monitoring source includes U cutting machine monitoring data streams corresponding to the U preset cutting machine monitoring elements; performing standard state variation calculation on the cutting machine monitoring source according to the U-dimensional cutting machine monitoring elements to obtain a U-dimensional cutting machine variation vector; selecting the U-dimensional cutting machine variation vector according to a cutting machine variation recognition channel to generate a T-dimensional cutting machine abnormal variation vector, where T is a positive integer and T is less than or equal to U; according to the T-dimensional cutting machine abnormal variation vector, activating a U-dimensional cutting machine maintenance channel to perform maintenance decision analysis and generating a cutting machine maintenance plan; performing maintenance on the aluminum foil cutting machine according to the cutting machine maintenance plan.

[0006] Second aspect, a smart maintenance system for an aluminum foil cutting machine is provided. The system includes: a cutting machine monitoring element loading module for loading U-dimensional cutting machine monitoring elements, where the U-dimensional cutting machine monitoring elements include U preset cutting machine monitoring elements, and U is a positive integer greater than 1; a cutting machine monitoring source obtaining module for obtaining a cutting machine monitoring source by performing real-time monitoring on the aluminum foil cutting machine according to the U-dimensional cutting machine monitoring elements in combination with a pre-deployed Internet of Things sensing network, where the cutting machine monitoring source includes U cutting machine monitoring data streams corresponding to the U preset cutting machine monitoring elements; a cutting machine mutation vector obtaining module for performing standard state mutation calculation on the cutting machine monitoring source according to the U-dimensional cutting machine monitoring elements to obtain a U-dimensional cutting machine mutation vector; a selected cutting machine mutation vector module for selecting the U-dimensional cutting machine mutation vector according to a cutting machine mutation recognition channel to generate a T-dimensional cutting machine abnormal mutation vector, where T is a positive integer and T is less than or equal to U; a cutting machine maintenance plan generating module for activating a U-dimensional cutting machine maintenance channel for maintenance decision analysis according to the T-dimensional cutting machine abnormal mutation vector to generate a cutting machine maintenance plan; and a cutting machine maintenance module for maintaining the aluminum foil cutting machine according to the cutting machine maintenance plan.

[0007] Third aspect, a computer device is provided, including a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, the steps described in the first aspect are implemented.

[0008] Fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps described in the first aspect are implemented.

[0009] For the above-mentioned smart maintenance method, system, device and medium of the aluminum foil cutting machine, this method solves the technical problem in the prior art that excessive attention is paid to the repair after a failure occurs, resulting in insufficient preventive maintenance and low maintenance efficiency of the cutting machine. By strengthening preventive maintenance and introducing targeted decision-making with mutation vectors, the technical effects of improving the preventive maintenance of the cutting machine and specifically solving the cutting machine failure are achieved.

[0010] The above description is only an overview of the technical solution of this application. In order to be able to understand the technical means of this application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of this application more obvious and understandable, the specific embodiments of this application are specifically cited below. Description of the Drawings

[0011] Figure 1Schematic flowchart of the intelligent maintenance method for an aluminum foil cutting machine in an embodiment;

[0012] Figure 2 Schematic flowchart of constructing the standard state vector of the U-dimensional cutting machine for the intelligent maintenance method of the aluminum foil cutting machine in an embodiment;

[0013] Figure 3 Block diagram of the structure of the intelligent maintenance system for the aluminum foil cutting machine in an embodiment;

[0014] Figure 4 Internal structure diagram of a computer device in an embodiment.

[0015] Explanation of reference numerals: cutting machine monitoring element loading module 11, cutting machine monitoring source obtaining module 12, cutting machine mutation vector obtaining module 13, selecting cutting machine mutation vector module 14, cutting machine maintenance plan generating module 15, cutting machine maintenance module 16. Detailed implementation manners

[0016] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0017] As Figure 1 shown, the present application provides an intelligent maintenance method for an aluminum foil cutting machine, and the method includes:

[0018] Loading U-dimensional cutting machine monitoring elements, where the U-dimensional cutting machine monitoring elements include U preset cutting machine monitoring elements, and U is a positive integer greater than 1;

[0019] The cutting machine is controlled by system software and then directly cuts the product. Corresponding parameters are set on the operation platform, and the computer transmits corresponding instructions to the cutting machine. The cutting machine then quickly cuts according to the received design drawing. The aluminum foil cutting machine is a mechanical device specifically used for cutting aluminum foil. The present application provides an intelligent maintenance method for the aluminum foil cutting machine, achieving the effects of effectively improving the operating efficiency and stability of the aluminum foil cutting machine and reducing the failure rate.

[0020] Loading U-dimensional cutting machine monitoring elements means combining U preset aluminum foil cutting machine monitoring elements. U is a positive integer greater than 1. The cutting machine monitoring elements include motor current, voltage, cutting machine temperature, pressure, vibration, ambient temperature, ambient humidity, etc. Combining U cutting machine monitoring elements forms a multi-dimensional monitoring system, which can more comprehensively reflect the operating state of the cutting machine, thereby improving the accuracy and efficiency of maintenance.

[0021] Based on the U - dimensional cutter monitoring elements, the aluminum foil cutter is monitored in real - time by combining with the pre - deployed Internet of Things (IoT) sensing network to obtain the cutter monitoring source. Among them, the cutter monitoring source includes U cutter monitoring data streams corresponding to the U preset cutter monitoring elements.

[0022] Based on the U - dimensional cutter monitoring elements, the aluminum foil cutter is monitored in real - time by combining with the pre - deployed Internet of Things (IoT) sensing network. The IoT sensing network is composed of a series of sensor nodes, which are deployed at key parts and key links of the aluminum foil cutter to collect the operation data of the cutter in real - time, including temperature sensors, humidity sensors, pressure sensors, vibration sensors, etc., for monitoring various state parameters of the cutter. When the IoT sensing network starts to work, it continuously collects data corresponding to the U cutter monitoring elements, including motor current, voltage, temperature, etc. Each of the U - dimensional cutter monitoring elements corresponds to one or more sensor nodes, and the sensor nodes transmit the collected data to the data processing center in real - time. At the data processing center, the received data is analyzed to obtain the cutter monitoring source, which includes U cutter monitoring data streams corresponding to the U preset cutter monitoring elements, that is, the cutter monitoring data groups corresponding to the U preset cutter monitoring elements. By monitoring and analyzing the cutter monitoring data streams in real - time, abnormal situations or potential problems of the cutter can be detected in a timely manner. Combining with the pre - deployed IoT sensing network to monitor the aluminum foil cutter in real - time and obtaining U cutter monitoring data streams can provide real - time and accurate data support, providing strong guarantee for the state monitoring, fault warning and maintenance optimization of the cutter.

[0023] Perform standard state variation calculation on the cutter monitoring source according to the U - dimensional cutter monitoring elements to obtain the U - dimensional cutter variation vector.

[0024] Calculate the standard state variation of the cutting machine monitoring source based on the U-dimensional cutting machine monitoring elements. Among them, the standard state is usually determined comprehensively according to the design parameters of the cutting machine, historical operation data, and industry experience, representing the performance indicators and state parameters that the cutting machine should achieve under normal working conditions. Use the U cutting machine monitoring data streams corresponding to the U-dimensional cutting machine monitoring elements to compare with the standard state, calculate the deviation or variation degree between the real-time data and the standard state, and obtain a value representing its variation degree for the U-dimensional cutting machine monitoring elements. Combine these values to form a U-dimensional cutting machine variation vector. This vector is a multi-dimensional data set that comprehensively reflects the variation of the cutting machine relative to the standard state under real-time monitoring. The acquisition of the U-dimensional cutting machine variation vector provides a basis for in-depth analysis of the operating state of the aluminum foil cutting machine. By observing and analyzing this vector, potential problems and hidden dangers that may exist during the operation of the aluminum foil cutting machine can be discovered, and corresponding maintenance measures can be taken.

[0025] Retrieve the standard state samples of the aluminum foil cutting machine according to the U-dimensional cutting machine monitoring elements to generate a U-dimensional cutting machine monitoring standard sample set;

[0026] According to the U-dimensional cutting machine monitoring elements, perform standard state sample retrieval on the homologous equipment of the aluminum foil cutting machine to generate a U-dimensional homologous extended monitoring standard sample set, where the homologous equipment includes multiple aluminum foil cutting machines of the same model corresponding to the aluminum foil cutting machine;

[0027] Calculate the standard state vector according to the U-dimensional cutting machine monitoring standard sample set and the U-dimensional homologous extended monitoring standard sample set to construct a U-dimensional cutting machine standard state vector;

[0028] Perform standardization processing according to the cutting machine monitoring source to construct a U-dimensional cutting machine monitoring vector;

[0029] Calculate the deviation of the U-dimensional cutting machine monitoring vector according to the U-dimensional cutting machine standard state vector to generate the U-dimensional cutting machine variation vector.

[0030] Standard state sample retrieval refers to collecting data of the aluminum foil cutter under normal operating conditions through the U-dimensional cutter monitoring element, reflecting the performance parameters of the cutter under optimal working conditions, integrating the parameters, and combining the sorted standard state data into a U-dimensional cutter monitoring standard sample set as a benchmark for subsequent analysis and comparison; identifying other cutters of the same model as the aluminum foil cutter, these devices are regarded as the same family devices, and performing the same standard state sample retrieval process as the aluminum foil cutter on the same family devices, collecting their data under normal operating conditions, and adding the standard state data of the same family devices to the U-dimensional cutter monitoring standard sample set to form an expanded monitoring standard sample set. This expanded sample set can improve the diversity and representativeness of the standard, making the subsequent analysis more accurate and comprehensive. Extract key features from the U-dimensional cutter monitoring standard sample set and the U-dimensional same family expanded monitoring standard sample set. These features should be able to fully reflect the operating status of the cutter, and calculate the standard state vector based on the extracted features. This vector is a multi-dimensional data set, each dimension corresponds to the standard state value of a monitoring element. The monitoring data of the aluminum foil cutter is collected in real time through the IoT sensor network, and the collected real-time monitoring data is standardized to ensure that the dimension and range of the data are consistent with the standard state vector. The standardized real-time monitoring data is combined into a U-dimensional cutter monitoring vector. The U-dimensional cutter monitoring vector is compared with the U-dimensional cutter standard state vector, and the deviation between the real-time monitoring state and the standard state of each monitoring element is calculated. The calculated deviation values are combined into a U-dimensional cutter variation vector, which reflects the abnormal situation of the aluminum foil cutter relative to the standard state during actual operation. The U-dimensional cutter variation vector is obtained to provide strong data support for subsequent fault diagnosis, performance evaluation and maintenance decisions.

[0031] like Figure 2 As shown, the U-dimensional cutting machine monitoring standard sample set and the U-dimensional homology expanded monitoring standard sample set are standardized to obtain a cutting machine standard sample library;

[0032] Partition the standard sample library of the cutting machine according to the U-dimensional cutting machine monitoring element to generate U element standard sample partitions;

[0033] Performing concentrated value calculations on the U element standard sample partitions respectively to generate U element standard concentrated value calculation results;

[0034] The U-dimensional clipper standard state vector is constructed according to the calculation results of the standard concentrated values of the U elements.

[0035] The U-dimensional clipper monitoring standard sample set and the U-dimensional homogeneous expanded monitoring standard sample set are standardized. According to the nature of the data and the purpose of analysis, a suitable standardization method is selected, including data scaling and translation, so that it conforms to the standard normal distribution or a specific range, and all standardized sample data are integrated into a unified clipper standard sample library for subsequent analysis and calculation. According to the definition and characteristics of the U-dimensional clipper monitoring element, determine how to partition the standard sample library, each partition will contain all sample data related to a specific monitoring element; according to the determined partition basis, the clipper standard sample library is partitioned to generate U element standard sample partitions. Each partition corresponds to a monitoring element and contains all standardized sample data of the element; according to the distribution characteristics of the data and the analysis requirements, a suitable concentration value indicator is selected, such as the mean, median, mode, etc., and the selected concentration value indicator is applied to the U element standard sample partitions for calculation, and the concentration value of each monitoring element is obtained. The concentration value of each monitoring element is used as the standard state value of the element to form U element standard concentration value calculation results, which are used to construct the U-dimensional clipper standard state vector. The standard concentrated values of U elements are combined in the order of monitoring elements to form a multidimensional vector, and the combined multidimensional vector is used as the standard state vector of the U-dimensional cutting machine, as the benchmark for subsequent variation analysis and state monitoring, and used to compare the difference between real-time monitoring data and standard state. Through the above method, the standard state vector of the U-dimensional cutting machine is obtained, which accurately reflects the operating characteristics of the aluminum foil cutting machine under the standard state, and provides a reliable basis for subsequent state monitoring and fault warning.

[0036] Selecting the U-dimensional clipper variation vector according to the clipper variation identification channel to generate a T-dimensional clipper abnormal variation vector, wherein T is a positive integer, and T is less than or equal to U;

[0037] The clipper variation identification channel refers to a model for identifying the abnormal state of the clipper determined according to the structural characteristics, working principle and historical fault data of the clipper. Selecting the U-dimensional clipper variation vector according to the clipper variation identification channel refers to inputting the U-dimensional clipper variation vector into the clipper variation identification channel for screening to form a T-dimensional clipper abnormal variation vector, that is, arranging the screened T elements according to their variation severity in the variation identification channel to generate a T-dimensional clipper abnormal variation vector; the value of T should be less than or equal to U to ensure that a variation vector with a higher risk of abnormal variation vector is selected. Effectively extract features with a higher risk of causing abnormal state of the clipper from multi-dimensional variation information to provide more accurate and effective support for subsequent diagnosis and maintenance.

[0038] Extracting a first cropper variation vector according to the U-dimensional cropper variation vector;

[0039] The cutting machine mutation identification channel includes a cutting machine mutation risk prediction network and a cutting machine mutation selector;

[0040] Perform risk prediction on the first cutting machine mutation vector according to the cutting machine mutation risk prediction network to obtain a first mutation risk index;

[0041] Input the first mutation risk index into the cutting machine mutation selector, where the cutting machine mutation selector includes a mutation risk index threshold;

[0042] If the first mutation risk index is greater than or equal to the mutation risk index threshold, set the first cutting machine mutation vector as the first cutting machine abnormal mutation vector;

[0043] Continue to select each cutting machine mutation vector in the U-dimensional cutting machine mutation vector according to the cutting machine mutation identification channel, and combine with the first cutting machine abnormal mutation vector to generate the T-dimensional cutting machine abnormal mutation vector.

[0044] Extract a mutation vector from the U-dimensional cutter mutation vectors as the first cutter mutation vector. According to the staff's self-selection, the selected cutter mutation vector is denoted as the first cutter mutation vector, which represents the mutation situation of the aluminum foil cutter in a certain specific monitoring feature. Input the first cutter mutation vector into the cutter mutation risk prediction network. The cutter mutation risk prediction network can predict the corresponding mutation risk according to the characteristics of the mutation vector. By inputting the first cutter mutation vector, a first mutation risk index can be obtained. The first mutation risk index characterizes the abnormal risk degree of the first cutter mutation vector. The higher the first mutation risk index, the higher the risk that the mutation situation corresponding to the mutation vector is more likely to lead to the abnormal state of the cutter. Input the first mutation risk index into the cutter mutation selector. The cutter mutation selector contains a mutation risk index threshold, which is set according to historical data, expert experience and system requirements and is used to judge whether the mutation risk reaches the degree that needs attention. If the first mutation risk index is greater than or equal to the mutation risk index threshold, it indicates that the mutation situation corresponding to the mutation vector has a relatively high risk and may lead to the abnormality of the cutter. Therefore, set the first cutter mutation vector as the first cutter abnormal mutation vector. Use the same cutter mutation identification channel to continue to select other mutation vectors in the U-dimensional cutter mutation vectors. Repeat the above method to perform risk prediction and selection on the U-dimensional cutter mutation vectors, add the mutation vectors that meet the selection conditions to the set of abnormal mutation vectors, and combine all the identified abnormal mutation vectors, including the first cutter abnormal mutation vector and other qualified abnormal mutation vectors, to generate a T-dimensional cutter abnormal mutation vector. The T-dimensional cutter abnormal mutation vector reflects the compilation information with a relatively high risk of the abnormal state of the cutter and can be used for subsequent fault diagnosis, early warning and maintenance decision-making. Extract the T-dimensional abnormal mutation vector most relevant to the abnormal state of the cutter from the U-dimensional cutter mutation vectors to provide strong data support for the intelligent maintenance of the cutter.

[0045] According to the T-dimensional cutter abnormal mutation vector, activate the U-dimensional cutter maintenance channel for maintenance decision analysis and generate a cutter maintenance plan;

[0046] The maintenance channel of the U-dimensional cutting machine refers to a maintenance model for different abnormalities of the cutting machine, which is constructed according to a neural network model. The abnormal mutation vector of the T-dimensional cutting machine is analyzed to obtain the mutation situation represented by the abnormal mutation vector of the T-dimensional cutting machine and its impact on the performance of the cutting machine. According to the abnormal mutation vector of the T-dimensional cutting machine, a detailed maintenance decision analysis is carried out, including determining the priority, measures and methods of maintenance according to the specific situation of the abnormal mutation vector. For example, for the abnormal mutation of some key components, it may be necessary to stop the machine immediately for maintenance; for the mutation of some secondary components, parameter adjustment or regular observation is required. According to the results of the maintenance decision analysis, a specific cutting machine maintenance plan is generated. This plan should include information such as the specific content, steps, time, and personnel of the maintenance to ensure the effectiveness and safety of the maintenance work. At the same time, the plan should also consider the cost and benefit of the maintenance work to ensure the economy and rationality of the maintenance work. According to the abnormal mutation vector of the T-dimensional cutting machine, the corresponding maintenance channel is activated, targeted maintenance decision analysis is carried out, and a practical cutting machine maintenance plan is generated. This helps to timely detect and solve the abnormal problems of the cutting machine, ensure its normal operation and extend its service life.

[0047] The maintenance channel of the U-dimensional cutting machine includes U element abnormal mutation predictors and a cutting machine maintenance decision registration model;

[0048] According to the abnormal mutation vector of the T-dimensional cutting machine, T matching element abnormal mutation predictors in the maintenance channel of the U-dimensional cutting machine are activated, and the abnormal mutation vector of the T-dimensional cutting machine is used for fault prediction by the T matching element abnormal mutation predictors to generate T abnormal mutation prediction results;

[0049] Fault fusion is carried out according to the T abnormal mutation prediction results to generate a cutting machine fault prediction result;

[0050] According to the cutting machine maintenance decision registration model, maintenance decision analysis is carried out on the cutting machine fault prediction result to obtain the cutting machine maintenance plan.

[0051] According to the elements in the T-dimensional cutter abnormal mutation vector, activate T element abnormal mutation predictors that match them from the U-dimensional cutter maintenance channel. Each of the element abnormal mutation predictors is used to predict the abnormal mutation of a specific cutter element. It is constructed based on a neural network model and is used to predict the fault situation of the cutter abnormal mutation vector. Use these T activated element abnormal mutation predictors to perform fault prediction on the T-dimensional cutter abnormal mutation vector. The T matching element abnormal mutation predictors will analyze the corresponding elements in the vector and generate an abnormal mutation prediction result. After obtaining T abnormal mutation prediction results, perform fault fusion, that is, synthesize the results of each predictor to form a comprehensive cutter fault prediction result. The fault fusion can adopt methods such as majority voting and Bayesian fusion to obtain the complete fault prediction situation of the aluminum foil cutter. Input the cutter fault prediction result into the cutter maintenance decision registration model. The cutter maintenance decision registration model is a neural network model that generates a specific cutter maintenance plan according to the fault prediction result and a preset maintenance strategy. The cutter maintenance plan includes various measures such as replacing components, adjusting parameters, and optimizing the process flow, aiming to eliminate or reduce the impact of the fault on the cutter performance. Through the cutter maintenance decision registration model, finally output a maintenance plan for the current abnormal state of the cutter. Utilize the function of the U-dimensional cutter maintenance channel to quickly generate an effective maintenance plan according to the T-dimensional cutter abnormal mutation vector, ensuring the stable operation and efficient production of the cutter.

[0052] The cutter maintenance decision registration model includes a cutter maintenance record library, a maintenance registration identifier, and a maintenance registration selector. Among them, the cutter maintenance record library includes multiple groups of cutter maintenance records, and each group of cutter maintenance records includes sample aluminum foil cutter fault data and sample aluminum foil cutter maintenance decisions.

[0053] Perform maintenance decision selection on the cutter fault prediction result according to the cutter maintenance record library, the maintenance registration identifier, and the maintenance registration selector to generate multiple selected maintenance decisions that meet the selection capacity constraint.

[0054] Collect the maintenance evaluation record data of the multiple selected maintenance decisions to obtain multiple selected decision maintenance evaluation record sets.

[0055] Perform maintenance evaluation equilibrium calculation according to the multiple selected decision maintenance evaluation record sets to generate multiple selected decision evaluation coefficients.

[0056] According to the multiple selected decision evaluation coefficients, select the optimal selected decision evaluation coefficient, and match the multiple selected maintenance decisions according to the optimal selected decision evaluation coefficient to generate the cutter maintenance plan.

[0057] Use the cutting machine maintenance record library, maintenance registration identifier, and maintenance registration selector to select a maintenance decision for the cutting machine fault prediction result. The cutting machine maintenance record library contains multiple groups of cutting machine maintenance records, and each group of records contains the fault data of the sample aluminum foil cutting machine and the corresponding maintenance decision. The maintenance registration identifier will perform a preliminary match based on the similarity between the fault prediction result and the sample fault data, and then the maintenance registration selector will further screen according to the preset selection conditions, such as cost, time, feasibility, etc., to generate multiple selected maintenance decisions that meet the selection capacity constraint. The selection capacity constraint refers to the maintenance decision that meets the fault prediction result, that is, the threshold of the number of selected maintenance decisions. Collect the maintenance evaluation record data of multiple selected maintenance decisions, including the time, cost, personnel input of the maintenance process, and the performance improvement of the cutting machine after maintenance, etc. By collecting these data, multiple selected decision maintenance evaluation record sets can be formed. Perform a maintenance evaluation balance calculation based on multiple selected decision maintenance evaluation record sets, and comprehensively consider the performance of different maintenance decisions in various aspects, such as cost, efficiency, effect, etc. A weighted method can be used for calculation to generate multiple selected decision evaluation coefficients. After obtaining multiple selected decision evaluation coefficients, according to the preset screening conditions, such as maximizing the comprehensive benefit, minimizing the cost, etc., select the optimal selected decision evaluation coefficient. The maintenance decision corresponding to the optimal selected decision evaluation coefficient reaches an ideal state in all aspects. Match multiple selected maintenance decisions according to the optimal selected decision evaluation coefficient to generate the final cutting machine maintenance plan. The cutting machine maintenance decision registration model can effectively utilize the information in the cutting machine maintenance record library, combine the current fault prediction result, and generate a cutting machine maintenance plan that meets the actual needs. This will help improve the maintenance efficiency and operation stability of the cutting machine and reduce the maintenance cost.

[0058] Extract the first group of cutting machine maintenance records according to the cutting machine maintenance record library, wherein the first group of cutting machine maintenance records includes the fault data of the first sample aluminum foil cutting machine and the maintenance decision of the first sample aluminum foil cutting machine;

[0059] Perform similarity identification on the cutting machine fault prediction result and the fault data of the first sample aluminum foil cutting machine according to the maintenance registration identifier to generate a first maintenance registration identification coefficient;

[0060] Input the first maintenance registration identification coefficient into the maintenance registration selector, wherein the maintenance registration selector includes a maintenance registration selection threshold;

[0061] If the first maintenance registration identification coefficient is greater than or equal to the maintenance registration selection threshold, use the maintenance decision of the first sample aluminum foil cutting machine as the first selected maintenance decision;

[0062] Taking the selection capacity constraint as the maintenance decision selection objective, continue to perform maintenance decision selection on the fault prediction result of the cutting machine according to the cutting machine maintenance record library, the maintenance registration identifier, and the maintenance registration selector, and generate the multiple selection maintenance decisions in combination with the first selection maintenance decision.

[0063] Extract the first set of cutting machine maintenance records from the cutting machine maintenance record library. This set of records should include the fault data of the first sample aluminum foil cutting machine and the corresponding maintenance decisions. The fault data of the first sample aluminum foil cutting machine and the maintenance decisions of the first sample aluminum foil cutting machine refer to the maintenance records randomly selected from the cutting machine maintenance record library, denoted as the first set of cutting machine maintenance records. Use the maintenance registration identifier to perform similarity identification on the fault prediction result of the cutting machine and the fault data of the first sample aluminum foil cutting machine. This step is to evaluate the applicability of the sample maintenance decision to the current fault situation by comparing the similarity between the current fault situation of the cutting machine and the sample fault data. After the identification is completed, generate a first maintenance registration identification coefficient, which reflects the similarity degree between the current fault and the sample fault. Input the first maintenance registration identification coefficient into the maintenance registration selector. A maintenance registration selection threshold is preset in the maintenance registration selector to determine whether the identification coefficient reaches the selection standard. If the first maintenance registration identification coefficient is greater than or equal to the maintenance registration selection threshold, it indicates that the maintenance decision of the first sample aluminum foil cutting machine is relatively matched with the current fault situation of the cutting machine, so it is determined as the first selection maintenance decision. Taking the selection capacity constraint as the objective of maintenance decision selection, the quantity and quality of maintenance decisions need to be considered during the selection process to ensure that the multiple selection maintenance decisions finally generated can meet the actual needs. According to the cutting machine maintenance record library, the maintenance registration identifier, and the maintenance registration selector, continue to perform maintenance decision selection on the fault prediction result of the cutting machine. Combine the first selection maintenance decision and other candidate maintenance decisions generated during the subsequent selection process to form the final multiple selection maintenance decisions. The multiple selection maintenance decisions are all selected through similarity identification and the selection process based on the historical data in the cutting machine maintenance record library and the fault prediction result of the current cutting machine. Utilize the information in the cutting machine maintenance record library, combine the functions of the maintenance registration identifier and the maintenance registration selector, perform maintenance decision selection on the fault prediction result of the cutting machine, and generate multiple selection maintenance decisions that meet the actual needs. This will provide strong support for the subsequent formulation of the maintenance plan.

[0064] Perform maintenance on the aluminum foil cutting machine according to the cutting machine maintenance plan.

[0065] According to the cutting machine maintenance plan, implement the maintenance measures one by one, and perform meticulous maintenance on the aluminum foil cutting machine according to the cutting machine maintenance plan, which can ensure the stable operation and high efficiency of the aluminum foil cutting machine.

[0066] In summary, the beneficial effects of the present method include:

[0067] 1. Various data of the cutting machine can be completely saved, realizing fault prediction, and all devices can be connected to the network, thus effectively avoiding the problem of missing dynamic data, greatly improving the fault handling efficiency, and comprehensively solving the problem of low traditional work efficiency;

[0068] 2. Intelligent operation and maintenance can simplify complex work processes and reduce work costs. Once various vulnerabilities occur, solutions can be quickly provided and specific problems can be determined, so that the management process can be comprehensively optimized;

[0069] 3. It can accurately judge the equipment status, timely warn of potential risks, and ensure the stable operation of the cutting machine.

[0070] As Figure 3 shown, the embodiment of the present application includes an intelligent maintenance system for an aluminum foil cutting machine, and the system includes:

[0071] A cutting machine monitoring element loading module 11, which is used to load U-dimensional cutting machine monitoring elements, where the U-dimensional cutting machine monitoring elements include U preset cutting machine monitoring elements, and U is a positive integer greater than 1;

[0072] A cutting machine monitoring source obtaining module 12, which is used to perform real-time monitoring on the aluminum foil cutting machine according to the U-dimensional cutting machine monitoring elements in combination with the pre-deployed Internet of Things sensor network to obtain a cutting machine monitoring source, where the cutting machine monitoring source includes U cutting machine monitoring data streams corresponding to the U preset cutting machine monitoring elements;

[0073] A cutting machine mutation vector obtaining module 13, which is used to perform standard state mutation calculation on the cutting machine monitoring source according to the U-dimensional cutting machine monitoring elements to obtain a U-dimensional cutting machine mutation vector;

[0074] A selected cutting machine mutation vector module 14, which is used to select the U-dimensional cutting machine mutation vector according to the cutting machine mutation identification channel to generate a T-dimensional cutting machine abnormal mutation vector, where T is a positive integer and T is less than or equal to U;

[0075] A cutting machine maintenance plan generating module 15, which is used to activate the U-dimensional cutting machine maintenance channel for maintenance decision analysis according to the T-dimensional cutting machine abnormal mutation vector to generate a cutting machine maintenance plan;

[0076] The cutting machine maintenance module 16 is used to maintain the aluminum foil cutting machine according to the cutting machine maintenance plan.

[0077] Furthermore, the embodiment of the present application also includes:

[0078] A standard state sample retrieval module, the standard state sample retrieval module is used to perform a standard state sample retrieval on the aluminum foil cutting machine according to the U-dimensional cutting machine monitoring element, and generate a U-dimensional cutting machine monitoring standard sample set;

[0079] A homologous extended monitoring standard sample set generation module, the homologous extended monitoring standard sample set generation module is used to perform standard state sample retrieval on homologous devices of the aluminum foil cutting machine according to the U-dimensional cutting machine monitoring element, and generate a U-dimensional homologous extended monitoring standard sample set, wherein the homologous devices include multiple aluminum foil cutting machines of the same model corresponding to the aluminum foil cutting machine;

[0080] A standard state vector calculation module, the standard state vector calculation module is used to calculate the standard state vector according to the U-dimensional clipper monitoring standard sample set and the U-dimensional homogeneous expanded monitoring standard sample set, and construct a U-dimensional clipper standard state vector;

[0081] A standardization processing module, the standardization processing module is used to perform standardization processing according to the cutting machine monitoring source to construct a U-dimensional cutting machine monitoring vector;

[0082] A deviation calculation module is used to perform deviation calculation on the U-dimensional clipper monitoring vector according to the U-dimensional clipper standard state vector to generate the U-dimensional clipper variation vector.

[0083] Furthermore, the embodiment of the present application also includes:

[0084] A cutting machine standard sample library acquisition module, the cutting machine standard sample library acquisition module is used to perform standardization processing on the U-dimensional cutting machine monitoring standard sample set and the U-dimensional homogeneous expanded monitoring standard sample set to obtain a cutting machine standard sample library;

[0085] An element standard sample partition generation module, the element standard sample partition generation module is used to partition the sample of the cutting machine standard sample library according to the U-dimensional cutting machine monitoring element, and generate U element standard sample partitions;

[0086] A concentrated value calculation module, the concentrated value calculation module is used to perform concentrated value calculations on the U element standard sample partitions respectively to generate U element standard concentrated value calculation results;

[0087] Standard state vector construction module, which is used to construct the U-dimensional standard state vector of the cutting machine according to the calculation results of the values in the U-element standard set.

[0088] Furthermore, the embodiment of the present application further includes:

[0089] Cutting machine mutation vector extraction module, which is used to extract the first cutting machine mutation vector according to the U-dimensional cutting machine mutation vector;

[0090] Cutting machine mutation recognition channel inclusion module, which is used to include a cutting machine mutation risk prediction network and a cutting machine mutation selector in the cutting machine mutation recognition channel;

[0091] Risk prediction module, which is used to perform risk prediction on the first cutting machine mutation vector according to the cutting machine mutation risk prediction network to obtain the first mutation risk index;

[0092] Mutation risk index input module, which is used to input the first mutation risk index into the cutting machine mutation selector, where the cutting machine mutation selector includes a mutation risk index threshold;

[0093] Mutation risk index judgment module, which is used to set the first cutting machine mutation vector as the first cutting machine abnormal mutation vector if the first mutation risk index is greater than or equal to the mutation risk index threshold;

[0094] Mutation vector selection module, which is used to continue to select each cutting machine mutation vector in the U-dimensional cutting machine mutation vector according to the cutting machine mutation recognition channel, and combine the first cutting machine abnormal mutation vector to generate the T-dimensional cutting machine abnormal mutation vector.

[0095] Furthermore, the embodiment of the present application further includes:

[0096] Cutting machine maintenance channel module, which is used to include U element abnormal mutation predictors and a cutting machine maintenance decision registration model in the U-dimensional cutting machine maintenance channel;

[0097] Matching element abnormal mutation predictor activation module, which is used to activate the T matching element abnormal mutation predictors in the U-dimensional cutting machine maintenance channel according to the T-dimensional cutting machine abnormal mutation vector, and perform fault prediction on the T-dimensional cutting machine abnormal mutation vector according to the T matching element abnormal mutation predictors to generate T abnormal mutation prediction results;

[0098] A fault fusion module, which is used to perform fault fusion based on the T abnormal mutation prediction results to generate a cutting machine fault prediction result;

[0099] A maintenance decision analysis module, which is used to perform maintenance decision analysis on the cutting machine fault prediction result according to the cutting machine maintenance decision registration model to obtain the cutting machine maintenance plan.

[0100] Furthermore, the embodiment of the present application further includes:

[0101] A cutting machine maintenance decision registration module, the cutting machine maintenance decision registration model of the cutting machine maintenance decision registration module includes a cutting machine maintenance record library, a maintenance registration identifier, and a maintenance registration selector. Among them, the cutting machine maintenance record library includes multiple groups of cutting machine maintenance records, and each group of cutting machine maintenance records includes sample aluminum foil cutting machine fault data and sample aluminum foil cutting machine maintenance decisions;

[0102] A maintenance decision selection module, which is used to perform maintenance decision selection on the cutting machine fault prediction result according to the cutting machine maintenance record library, the maintenance registration identifier, and the maintenance registration selector to generate multiple selection maintenance decisions that meet the selection capacity constraint;

[0103] A maintenance evaluation record data acquisition module, which is used to collect the maintenance evaluation record data of the multiple selection maintenance decisions to obtain multiple selection decision maintenance evaluation record sets;

[0104] A selection decision evaluation coefficient generation module, which is used to perform maintenance evaluation balance calculation according to the multiple selection decision maintenance evaluation record sets to generate multiple selection decision evaluation coefficients;

[0105] A cutting machine maintenance plan generation module, which is used to screen the optimal selection decision evaluation coefficient according to the multiple selection decision evaluation coefficients, and match the multiple selection maintenance decisions according to the optimal selection decision evaluation coefficient to generate the cutting machine maintenance plan.

[0106] Furthermore, the embodiment of the present application further includes:

[0107] A cutting machine maintenance record extraction module, which is used to extract the first group of cutting machine maintenance records according to the cutting machine maintenance record library, where the first group of cutting machine maintenance records includes first sample aluminum foil cutting machine fault data and first sample aluminum foil cutting machine maintenance decisions;

[0108] A similarity recognition module, which is used to perform similarity recognition on the fault prediction result of the cutting machine and the first sample aluminum foil cutting machine fault data according to the maintenance registration recognizer, and generate a first maintenance registration recognition coefficient;

[0109] A maintenance registration recognition coefficient input module, which is used to input the first maintenance registration recognition coefficient into the maintenance registration selector. Among them, the maintenance registration selector includes a maintenance registration selection threshold;

[0110] A maintenance registration recognition coefficient judgment module, which is used to, if the first maintenance registration recognition coefficient is greater than or equal to the maintenance registration selection threshold, use the first sample aluminum foil cutting machine maintenance decision as the first selected maintenance decision;

[0111] A plurality of selected maintenance decision module generation modules, which are used to use the selection capacity constraint as the maintenance decision selection target, and continue to perform maintenance decision selection on the fault prediction result of the cutting machine according to the cutting machine maintenance record library, the maintenance registration recognizer, and the maintenance registration selector, and combine the first selected maintenance decision to generate the plurality of selected maintenance decisions.

[0112] For a specific embodiment of the intelligent maintenance system for the aluminum foil cutting machine, reference can be made to the embodiment of the intelligent maintenance method for the aluminum foil cutting machine in the above text, which will not be elaborated here. The above-mentioned modules can be embedded in the processor in the computer device in the form of hardware or independent of it, or stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0113] In one embodiment, a computer device is provided. This computer device can be a server, and its internal structure diagram can be as Figure 4 shown. This computer device includes a processor, a memory, and a network interface connected through a system bus. Among them, the processor of this computer device is used to provide computing and control capabilities. The memory of this computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of this computer device is used to store news data and data such as time decay factors. The network interface of this computer device is used to communicate with an external terminal through a network connection. The computer program is executed by the processor to implement the intelligent maintenance method for the aluminum foil cutting machine.

[0114] Those skilled in the art can understand, Figure 4The structure shown is only a block diagram of some structures related to the solution of this application, and does not constitute a limitation on the computer device to which the solution of this application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have different component arrangements.

[0115] In one embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps of the intelligent maintenance method of the aluminum foil cutting machine are implemented.

[0116] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the intelligent maintenance method of the aluminum foil cutting machine are implemented.

[0117] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0118] The above-described embodiments only represent several implementation manners of this application, and their descriptions are relatively specific and detailed, but they should not be construed as limitations on the scope of the invention patent. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application patent shall be subject to the appended claims.

Claims

1. A method for intelligent maintenance of an aluminum foil cutting machine, characterized in that, The method comprises: Loading a U-dimensional clipper monitoring element, wherein the U-dimensional clipper monitoring element includes U preset clipper monitoring elements, wherein U is a positive integer greater than 1; According to the U-dimensional cutting machine monitoring elements, the aluminum foil cutting machine is monitored in real time in combination with the pre-deployed Internet of Things sensor network to obtain a cutting machine monitoring source, wherein the cutting machine monitoring source includes U cutting machine monitoring data streams corresponding to the U preset cutting machine monitoring elements; Performing standard state variation calculation on the clipper monitoring source according to the U-dimensional clipper monitoring element to obtain a U-dimensional clipper variation vector; Selecting the U-dimensional clipper variation vector according to the clipper variation identification channel to generate a T-dimensional clipper abnormal variation vector, wherein T is a positive integer, and T is less than or equal to U; According to the T-dimensional cutting machine abnormal variation vector, the U-dimensional cutting machine maintenance channel is activated to perform maintenance decision analysis and generate a cutting machine maintenance plan; Maintaining the aluminum foil cutter according to the cutter maintenance plan; Among them, performing standard state variation calculation on the cutting machine monitoring source according to the U-dimensional cutting machine monitoring element to obtain the U-dimensional cutting machine variation vector includes: Performing a standard state sample search on the aluminum foil cutting machine according to the U-dimensional cutting machine monitoring element to generate a U-dimensional cutting machine monitoring standard sample set; According to the U-dimensional cutting machine monitoring element, a standard state sample retrieval is performed on the same family equipment of the aluminum foil cutting machine to generate a U-dimensional same family expanded monitoring standard sample set, wherein the same family equipment includes multiple aluminum foil cutting machines of the same model corresponding to the aluminum foil cutting machine; Calculate the standard state vector according to the U-dimensional clipper monitoring standard sample set and the U-dimensional homology expanded monitoring standard sample set to construct a U-dimensional clipper standard state vector; Performing standardization processing according to the cutting machine monitoring source to construct a U-dimensional cutting machine monitoring vector; Perform deviation calculation on the U-dimensional clipper monitoring vector according to the U-dimensional clipper standard state vector to generate the U-dimensional clipper variation vector; The standard state vector is calculated based on the U-dimensional clipper monitoring standard sample set and the U-dimensional homogeneous expanded monitoring standard sample set to construct the U-dimensional clipper standard state vector, including: Standardizing the U-dimensional cutting machine monitoring standard sample set and the U-dimensional homology expanded monitoring standard sample set to obtain a cutting machine standard sample library; Partition the standard sample library of the cutting machine according to the U-dimensional cutting machine monitoring element to generate U element standard sample partitions; Performing concentrated value calculations on the U element standard sample partitions respectively to generate U element standard concentrated value calculation results; The U-dimensional clipper standard state vector is constructed according to the calculation results of the standard concentrated values of the U elements.

2. The method according to claim 1, characterized in that, The U-dimensional clipper variation vector is selected according to the clipper variation identification channel to generate a T-dimensional clipper abnormal variation vector, including: Extracting a first cropper variation vector according to the U-dimensional cropper variation vector; The clipper variation identification channel includes a clipper variation risk prediction network and a clipper variation selector; Perform risk prediction on the first cutting machine mutation vector according to the cutting machine mutation risk prediction network to obtain a first mutation risk index; Input the first mutation risk index into the cutting machine mutation selector, where the cutting machine mutation selector includes a mutation risk index threshold; If the first mutation risk index is greater than or equal to the mutation risk index threshold, set the first cutting machine mutation vector as the first cutting machine abnormal mutation vector; Continue to select each cutting machine mutation vector in the U-dimensional cutting machine mutation vector according to the cutting machine mutation recognition channel, and combine with the first cutting machine abnormal mutation vector to generate the T-dimensional cutting machine abnormal mutation vector.

3. The method according to claim 1, characterized in that, According to the T-dimensional cutting machine abnormal mutation vector, activate the U-dimensional cutting machine maintenance channel for maintenance decision analysis to generate a cutting machine maintenance plan, including: The U-dimensional cutting machine maintenance channel includes U element abnormal mutation predictors and a cutting machine maintenance decision registration model; According to the T-dimensional cutting machine abnormal mutation vector, activate T matching element abnormal mutation predictors in the U-dimensional cutting machine maintenance channel, and perform fault prediction on the T-dimensional cutting machine abnormal mutation vector according to the T matching element abnormal mutation predictors to generate T abnormal mutation prediction results; Perform fault fusion according to the T abnormal mutation prediction results to generate a cutting machine fault prediction result; Perform maintenance decision analysis on the cutting machine fault prediction result according to the cutting machine maintenance decision registration model to obtain the cutting machine maintenance plan.

4. The method according to claim 3, wherein Perform maintenance decision analysis on the cutting machine fault prediction result according to the cutting machine maintenance decision registration model to obtain the cutting machine maintenance plan, including: The cutting machine maintenance decision registration model includes a cutting machine maintenance record library, a maintenance registration identifier, and a maintenance registration selector. The cutting machine maintenance record library includes multiple groups of cutting machine maintenance records, and each group of cutting machine maintenance records includes sample aluminum foil cutting machine fault data and sample aluminum foil cutting machine maintenance decisions; Perform maintenance decision selection on the cutting machine fault prediction result according to the cutting machine maintenance record library, the maintenance registration identifier, and the maintenance registration selector to generate multiple selected maintenance decisions that meet the selection capacity constraint; Collect the maintenance evaluation record data of the multiple selected maintenance decisions to obtain multiple selected decision maintenance evaluation record sets; Perform maintenance evaluation equilibrium calculation according to the multiple selected decision maintenance evaluation record sets to generate multiple selected decision evaluation coefficients; According to the multiple selected decision evaluation coefficients, select the optimal selected decision evaluation coefficient, and match the multiple selected maintenance decisions according to the optimal selected decision evaluation coefficient to generate the cutting machine maintenance plan.

5. The method according to claim 4, characterized in that, Perform maintenance decision selection on the cutting machine fault prediction result according to the cutting machine maintenance record library, the maintenance registration identifier, and the maintenance registration selector to generate multiple selected maintenance decisions that meet the selection capacity constraint, including: Extract a first set of cutter maintenance records from the cutter maintenance record library, where the first set of cutter maintenance records includes first sample aluminum foil cutter fault data and first sample aluminum foil cutter maintenance decisions; Perform similarity recognition on the cutter fault prediction result and the first sample aluminum foil cutter fault data according to the maintenance registration recognizer to generate a first maintenance registration recognition coefficient; Input the first maintenance registration recognition coefficient into the maintenance registration selector, where the maintenance registration selector includes a maintenance registration selection threshold; If the first maintenance registration recognition coefficient is greater than or equal to the maintenance registration selection threshold, use the first sample aluminum foil cutter maintenance decision as the first selected maintenance decision; Use the selection capacity constraint as the maintenance decision selection target, and continue to perform maintenance decision selection on the cutter fault prediction result according to the cutter maintenance record library, the maintenance registration recognizer, and the maintenance registration selector, and combine the first selected maintenance decision to generate the multiple selected maintenance decisions.

6. The intelligent maintenance system of an aluminum foil cutting machine, characterized in that, The system is used to execute the method according to any one of claims 1 to 5, and the system includes: A cutter monitoring element loading module, which is used to load U-dimensional cutter monitoring elements, where the U-dimensional cutter monitoring elements include U preset cutter monitoring elements, and U is a positive integer greater than 1; A cutter monitoring source obtaining module, which is used to perform real-time monitoring on the aluminum foil cutter according to the U-dimensional cutter monitoring elements and in combination with a pre-deployed Internet of Things sensor network to obtain a cutter monitoring source, where the cutter monitoring source includes U cutter monitoring data streams corresponding to the U preset cutter monitoring elements; A cutter mutation vector obtaining module, which is used to perform standard state mutation calculation on the cutter monitoring source according to the U-dimensional cutter monitoring elements to obtain a U-dimensional cutter mutation vector; A selected cutter mutation vector module, which is used to select the U-dimensional cutter mutation vector according to a cutter mutation recognition channel to generate a T-dimensional cutter abnormal mutation vector, where T is a positive integer and T is less than or equal to U; A cutter maintenance plan generating module, which is used to activate a U-dimensional cutter maintenance channel for maintenance decision analysis according to the T-dimensional cutter abnormal mutation vector to generate a cutter maintenance plan; A cutter maintenance module, which is used to maintain the aluminum foil cutter according to the cutter maintenance plan.

7. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 5.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 5.

Images