Health state assessment method and system based on intelligent manufacturing equipment

Abstract

The invention discloses a health state assessment method and system based on intelligent manufacturing equipment, and the method comprises the steps: obtaining at least one fault type which may occur on the manufacturing equipment, and setting a corresponding maintenance mode based on each fault type; the method comprises the following steps: processing abnormal operation and maintenance data based on historical operation and maintenance data of manufacturing equipment, the operation and maintenance data comprising equipment part replacement data, maintenance mode data and fault type data, and obtaining normal operation and maintenance data; and determining all possible manufacturing equipment maintenance events based on the acquired normal data. According to the method, the indexes of faults of the manufacturing equipment are comprehensively analyzed based on the maintenance data of each time and the maintenance events in the adjacent detection intervals, and the optimal maintenance mode is specifically set based on the fault indexes, so that the maintenance efficiency is improved, the waste of maintenance resources is reduced, and the maintenance cost is reduced to a certain extent. And the service life of the intelligent manufacturing equipment is prolonged, and the requirements of workers are met.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a health status assessment method and system based on intelligent manufacturing equipment. Background Art

[0002] As an important part of the Industrial Internet of Things, the health status of smart manufacturing equipment is directly related to the quality level of industrial products and the safety of people's lives and property during the production process. Therefore, it is of great theoretical value and engineering practical significance to evaluate the status of smart manufacturing equipment to ensure the healthy operation of equipment and prevent accidents.

[0003] During the operation and maintenance of intelligent manufacturing equipment, there will be many different faults. Therefore, it is necessary to carry out reasonable maintenance methods for intelligent manufacturing equipment, so as to timely discover various types of faults that may occur in intelligent manufacturing equipment and timely perform maintenance on intelligent manufacturing equipment. The existing technology for the maintenance of intelligent manufacturing equipment lacks comprehensive analysis of the maintenance data of intelligent manufacturing equipment, which makes it difficult to meet the needs of staff. Summary of the invention

[0004] In order to solve the above technical problems, a health status assessment method and system based on intelligent manufacturing equipment are provided. This technical solution solves the problem that the existing technology for the maintenance of intelligent manufacturing equipment proposed in the above background technology lacks comprehensive analysis of the maintenance data of intelligent manufacturing equipment.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A health status assessment method based on intelligent manufacturing equipment, comprising:

[0007] Obtain at least one possible fault type of the manufacturing equipment, and set a corresponding maintenance method based on each fault type;

[0008] Based on the historical operation and maintenance data of the manufacturing equipment, the operation and maintenance data includes equipment component replacement data, maintenance method data and fault type data, abnormal operation and maintenance data is processed to obtain normal operation and maintenance data;

[0009] Based on the acquired normal data, determine all possible manufacturing equipment maintenance events;

[0010] Analyze the correlation between each manufacturing equipment maintenance event and the fault type, and build a manufacturing equipment fault type assessment model;

[0011] Based on the historical operation and maintenance data of manufacturing equipment, determine the closest maintenance time to the current time for each fault type and record it as the initial maintenance time;

[0012] Count all the manufacturing equipment maintenance events between the initial maintenance time and the current time, and record them as analysis maintenance events;

[0013] Substitute the analyzed maintenance events into the fault type evaluation model to obtain the evaluation index of each fault type;

[0014] Based on the evaluation index of the fault type, set the best maintenance method corresponding to the fault type.

[0015] Preferably, the processing of abnormal operation and maintenance data to obtain normal operation and maintenance data specifically includes the following steps:

[0016] According to the missing time of equipment component replacement data, the missing data of equipment component replacement is inserted into the corresponding time to determine the complete data of equipment component replacement;

[0017] According to the missing time of the maintenance mode data, the missing data of the maintenance mode is inserted into the corresponding time to determine the complete data of the maintenance mode;

[0018] According to the time when the fault type data is missing, the fault type data is inserted into the corresponding time to determine the complete data of the fault type;

[0019] The complete data of equipment component replacement, maintenance method and fault type are collected and processed to determine normal operation and maintenance data.

[0020] Preferably, the analysis of the correlation between each manufacturing equipment maintenance event and the fault type and the construction of a manufacturing equipment fault type assessment model specifically includes the following steps:

[0021] Based on each maintenance data in the historical maintenance data, analyze the probability of occurrence of the fault type during each maintenance;

[0022] Calculate the difference between the probability of occurrence of the fault type during maintenance and the probability of occurrence of the fault type during the previous maintenance;

[0023] Collect statistics on all manufacturing equipment maintenance events that occurred between the maintenance time and the previous maintenance time;

[0024] The difference between the probability of occurrence of the fault type during maintenance and the probability of occurrence of the fault type during the previous maintenance and all the maintenance events of manufacturing equipment occurring between the maintenance and the previous maintenance are combined into several groups of sample data;

[0025] Obtain several groups of sample data to form a sample data set;

[0026] Based on the sample data set, all the manufacturing equipment maintenance events that occurred between the maintenance and the previous maintenance were taken as input, and the difference between the probability of occurrence of the fault type during maintenance and the risk probability of occurrence of the fault type during the previous maintenance was taken as output. A neural network was used to train a manufacturing equipment failure type assessment model.

[0027] Preferably, the method of using a neural network to train a manufacturing equipment fault type assessment model specifically includes:

[0028] Divide all data in the sample data set into training set, validation set and test set in a ratio of 8:1:1;

[0029] Construct a compensation function, preset a regularization coefficient, introduce a regularization term into the compensation function, and obtain a regularized compensation function;

[0030] Based on the regularized compensation function, several candidate models are trained through the neural network using the training set;

[0031] Use the compensation function to evaluate the compensation values ​​of several candidate models on the validation set;

[0032] The candidate model corresponding to the minimum compensation value is selected as the training manufacturing equipment fault type assessment model. Preferably, the calculation formula of the regularized compensation function is:

[0033] L'(θ)=L(θ)+L 1 ∑|θj|

[0034] Where L'(θ) is the regularization compensation function, L(θ) is the compensation function, and L 1 is the regularization coefficient, and θj is the jth parameter of the neural network.

[0035] Preferably, the method of determining the maintenance time closest to the current time for each fault type based on the historical operation and maintenance data of the manufacturing equipment, and recording it as the initial maintenance time, specifically comprises the following steps:

[0036] Get the current time of smart manufacturing equipment;

[0037] Retrieve the maintenance time in all historical operation and maintenance data;

[0038] Calculate the difference between the maintenance time in all historical operation and maintenance data and the current time;

[0039] The calculation formula of the initial maintenance time is:

[0040]

[0041] Where Tm is the initial maintenance time, and ti is the difference between the maintenance time in the historical operation and maintenance data and the current time.

[0042] Preferably, the setting of the optimal maintenance method corresponding to the fault type based on the evaluation index of the fault type specifically includes the following steps:

[0043] Based on the maintenance data corresponding to the initial detection time, the probability of occurrence of the fault type at the initial detection is analyzed as the basic indicator of the fault type;

[0044] The basic index of the fault type is added to the evaluation index of the fault type as the actual evaluation value corresponding to the fault type;

[0045] Determine several maintenance methods corresponding to the fault type;

[0046] Determine the best maintenance method based on the actual risk assessment value corresponding to the fault type;

[0047] Test manufacturing equipment according to best maintenance methods.

[0048] Preferably, the determining of the best maintenance method specifically comprises the following steps:

[0049] Several maintenance methods based on the fault type;

[0050] Retrieve from the database the time interval value of the next failure of the manufacturing equipment that has been repaired in several ways in the past;

[0051] Compare the time interval value with a preset threshold;

[0052] If the time interval value is greater than or equal to the preset threshold, the corresponding maintenance method is selected;

[0053] If the time interval value is less than the preset threshold, the corresponding maintenance method is eliminated;

[0054] Count all the selected corresponding maintenance methods, compare the time interval values ​​in turn, and obtain the maintenance method corresponding to the largest time interval value, which is the best maintenance method.

[0055] Preferably, the calculation formula for the maximum time interval value is:

[0056]

[0057] Where Gm is the maximum time interval value, and gi is the i-th time interval value.

[0058] A health status assessment system based on intelligent manufacturing equipment, comprising:

[0059] A data acquisition module, the data acquisition module is used to acquire at least one type of fault that may occur in the manufacturing equipment, and set a corresponding maintenance method based on each type of fault;

[0060] A data processing module, the data processing module is used to process abnormal operation and maintenance data based on historical operation and maintenance data of manufacturing equipment, the operation and maintenance data including equipment component replacement data, maintenance method data and fault type data, obtain normal operation and maintenance data, and determine all possible manufacturing equipment maintenance events based on the obtained normal data;

[0061] A data analysis module, the data analysis module is used to analyze the correlation between each manufacturing equipment maintenance event and the fault type, and to build a manufacturing equipment fault type assessment model;

[0062] An index evaluation module, which is used to determine the closest maintenance time to the current time for each fault type based on the historical operation and maintenance data of the manufacturing equipment, record it as the initial maintenance time, count all the manufacturing equipment maintenance events between the initial maintenance time and the current time, record it as the analysis maintenance event, substitute the analysis maintenance event into the fault type evaluation model, and obtain the evaluation index of each fault type;

[0063] The module for determining the best maintenance method is used to set the best maintenance method corresponding to the fault type based on the evaluation index of the fault type.

[0064] Compared with the prior art, the present invention provides a health status assessment method and system based on intelligent manufacturing equipment, which has the following beneficial effects:

[0065] The present invention proposes a health status assessment method and system based on intelligent manufacturing equipment, which comprehensively analyzes the indicators of manufacturing equipment failure based on each maintenance data and maintenance events in adjacent detection intervals, and sets the best maintenance method based on the fault indicators, thereby improving maintenance efficiency and reducing the waste of maintenance resources. To a certain extent, the service life of intelligent manufacturing equipment is improved and the needs of staff are met. This method is conducive to popularization and use. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] Figure 1 is a schematic diagram of the evaluation method of the present invention;

[0067] Figure 2 A schematic diagram of a method for obtaining normal operation and maintenance data in the present invention;

[0068] Figure 3 A schematic diagram of a method for constructing a manufacturing equipment fault type assessment model in the present invention;

[0069] Figure 4 A schematic diagram of a method for training a manufacturing equipment fault type assessment model using a neural network in the present invention;

[0070] Figure 5A schematic diagram of a method for setting an optimal maintenance method corresponding to a fault type in the present invention;

[0071] Figure 6 A schematic diagram of a method for determining the best maintenance method in the present invention. DETAILED DESCRIPTION

[0072] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0073] Example 1

[0074] Please refer to Figure 1-Figure 6 As shown, a health status assessment method based on intelligent manufacturing equipment includes:

[0075] Obtain at least one possible fault type of the manufacturing equipment, and set a corresponding maintenance method based on each fault type;

[0076] Based on the historical operation and maintenance data of manufacturing equipment, which includes equipment component replacement data, maintenance method data, and fault type data, abnormal operation and maintenance data is processed to obtain normal operation and maintenance data;

[0077] Based on the acquired normal data, determine all possible manufacturing equipment maintenance events;

[0078] Analyze the correlation between each manufacturing equipment maintenance event and the fault type, and build a manufacturing equipment fault type assessment model;

[0079] Based on the historical operation and maintenance data of manufacturing equipment, determine the closest maintenance time to the current time for each fault type and record it as the initial maintenance time;

[0080] Count all the manufacturing equipment maintenance events between the initial maintenance time and the current time, and record them as analysis maintenance events;

[0081] Substitute the analyzed maintenance events into the fault type evaluation model to obtain the evaluation index of each fault type;

[0082] Based on the evaluation index of the fault type, set the best maintenance method corresponding to the fault type.

[0083] It can be understood by those skilled in the art that the present invention conducts a comprehensive analysis of the indicators of manufacturing equipment failure based on each maintenance data and maintenance events within adjacent detection intervals, and sets the best maintenance method in a targeted manner based on the failure indicators, thereby improving maintenance efficiency and reducing the waste of maintenance resources. To a certain extent, the service life of intelligent manufacturing equipment is improved and the needs of staff are met. This method is conducive to popularization and use.

[0084] Processing abnormal operation and maintenance data and obtaining normal operation and maintenance data specifically includes the following steps:

[0085] According to the missing time of equipment component replacement data, the missing data of equipment component replacement is inserted into the corresponding time to determine the complete data of equipment component replacement;

[0086] According to the missing time of the maintenance mode data, the missing data of the maintenance mode is inserted into the corresponding time to determine the complete data of the maintenance mode;

[0087] According to the time when the fault type data is missing, the fault type data is inserted into the corresponding time to determine the complete data of the fault type;

[0088] The complete data of equipment component replacement, maintenance method and fault type are collected and processed to determine normal operation and maintenance data.

[0089] Analyzing the correlation between each manufacturing equipment maintenance event and the fault type, and building a manufacturing equipment fault type assessment model specifically includes the following steps:

[0090] Based on each maintenance data in the historical maintenance data, analyze the probability of occurrence of the fault type during each maintenance;

[0091] Calculate the difference between the probability of occurrence of the fault type during maintenance and the probability of occurrence of the fault type during the previous maintenance;

[0092] Collect statistics on all manufacturing equipment maintenance events that occurred between the maintenance time and the previous maintenance time;

[0093] The difference between the probability of occurrence of the fault type during maintenance and the probability of occurrence of the fault type during the previous maintenance and all the maintenance events of manufacturing equipment occurring between the maintenance and the previous maintenance are combined into several groups of sample data;

[0094] Obtain several groups of sample data to form a sample data set;

[0095] Based on the sample data set, all the manufacturing equipment maintenance events that occurred between the maintenance and the previous maintenance were taken as input, and the difference between the probability of occurrence of the fault type during maintenance and the risk probability of occurrence of the fault type during the previous maintenance was taken as output. A neural network was used to train a manufacturing equipment failure type assessment model.

[0096] It can be understood by those skilled in the art that neural networks are computational models that mimic the structure and function of biological neural networks. They are composed of a large number of processing units connected to each other through weighted connections, and can process and learn complex nonlinear relationships and data patterns. In this solution, based on the neural network model, a large number of maintenance events and the change rates of fault indicators are used as training data to explore the data relationship between the maintenance events and the change rates of fault indicators, and then build a manufacturing equipment fault type assessment model.

[0097] The use of neural networks to train manufacturing equipment fault type assessment models specifically includes:

[0098] Divide all data in the sample data set into training set, validation set and test set in a ratio of 8:1:1;

[0099] Construct a compensation function, preset a regularization coefficient, introduce a regularization term into the compensation function, and obtain a regularized compensation function;

[0100] Based on the regularized compensation function, several candidate models are trained through the neural network using the training set;

[0101] Use the compensation function to evaluate the compensation values ​​of several candidate models on the validation set;

[0102] The candidate model corresponding to the minimum compensation value is selected as the training manufacturing equipment fault type evaluation model. The calculation formula of the regularized compensation function is:

[0103] L'(θ)=L(θ)+L 1 ∑|θj|

[0104] Where L'(θ) is the regularization compensation function, L(θ) is the compensation function, and L 1 is the regularization coefficient, and θj is the jth parameter of the neural network.

[0105] Based on the historical operation and maintenance data of manufacturing equipment, determine the closest maintenance time to the current time for each fault type and record it as the initial maintenance time. The specific steps include the following:

[0106] Get the current time of smart manufacturing equipment;

[0107] Retrieve the maintenance time in all historical operation and maintenance data;

[0108] Calculate the difference between the maintenance time in all historical operation and maintenance data and the current time;

[0109] The calculation formula for the initial maintenance time is:

[0110]

[0111] Where Tm is the initial maintenance time, and ti is the difference between the maintenance time in the historical operation and maintenance data and the current time.

[0112] Based on the evaluation index of the fault type, setting the best maintenance method corresponding to the fault type specifically includes the following steps:

[0113] Based on the maintenance data corresponding to the initial detection time, the probability of occurrence of the fault type at the initial detection is analyzed as the basic indicator of the fault type;

[0114] The basic index of the fault type is added to the evaluation index of the fault type as the actual evaluation value corresponding to the fault type;

[0115] Determine several maintenance methods corresponding to the fault type;

[0116] Determine the best maintenance method based on the actual risk assessment value corresponding to the fault type;

[0117] Test manufacturing equipment according to best maintenance methods.

[0118] Determining the best maintenance method includes the following steps:

[0119] Several maintenance methods based on the fault type;

[0120] Retrieve from the database the time interval value of the next failure of the manufacturing equipment that has been repaired in several ways in the past;

[0121] Compare the time interval value with a preset threshold;

[0122] If the time interval value is greater than or equal to the preset threshold, the corresponding maintenance method is selected;

[0123] If the time interval value is less than the preset threshold, the corresponding maintenance method is eliminated;

[0124] Count all the selected corresponding maintenance methods, compare the time interval values ​​in turn, and obtain the maintenance method corresponding to the largest time interval value, which is the best maintenance method.

[0125] The maximum time interval value is calculated as:

[0126]

[0127] Where Gm is the maximum time interval value, and gi is the i-th time interval value.

[0128] A health status assessment system based on intelligent manufacturing equipment, comprising:

[0129] A data acquisition module, the data acquisition module is used to acquire at least one type of fault that may occur in the manufacturing equipment, and set a corresponding maintenance method based on each type of fault;

[0130] A data processing module, the data processing module is used to process abnormal operation and maintenance data based on historical operation and maintenance data of manufacturing equipment, the operation and maintenance data including equipment component replacement data, maintenance method data and fault type data, obtain normal operation and maintenance data, and determine all possible manufacturing equipment maintenance events based on the obtained normal data;

[0131] A data analysis module, the data analysis module is used to analyze the correlation between each manufacturing equipment maintenance event and the fault type, and to build a manufacturing equipment fault type assessment model;

[0132] An index evaluation module, which is used to determine the closest maintenance time to the current time for each fault type based on the historical operation and maintenance data of the manufacturing equipment, record it as the initial maintenance time, count all the manufacturing equipment maintenance events between the initial maintenance time and the current time, record it as the analysis maintenance event, substitute the analysis maintenance event into the fault type evaluation model, and obtain the evaluation index of each fault type;

[0133] The module for determining the best maintenance method is used to set the best maintenance method corresponding to the fault type based on the evaluation index of the fault type.

[0134] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. A health status assessment method based on intelligent manufacturing equipment, characterized in that: include: Obtain at least one possible fault type of the manufacturing equipment, and set a corresponding maintenance method based on each fault type; Based on the historical operation and maintenance data of the manufacturing equipment, the operation and maintenance data includes equipment component replacement data, maintenance method data and fault type data, abnormal operation and maintenance data is processed to obtain normal operation and maintenance data; Based on the acquired normal data, determine all possible manufacturing equipment maintenance events; Analyze the correlation between each manufacturing equipment maintenance event and the fault type, and build a manufacturing equipment fault type assessment model; Based on the historical operation and maintenance data of manufacturing equipment, determine the closest maintenance time to the current time for each fault type and record it as the initial maintenance time; Count all the manufacturing equipment maintenance events between the initial maintenance time and the current time, and record them as analysis maintenance events; Substitute the analyzed maintenance events into the fault type evaluation model to obtain the evaluation index of each fault type; Based on the evaluation index of the fault type, set the best maintenance method corresponding to the fault type.

2. According to claim 1, a health status assessment method based on intelligent manufacturing equipment is characterized in that: The processing of abnormal operation and maintenance data to obtain normal operation and maintenance data specifically includes the following steps: According to the missing time of equipment component replacement data, the missing data of equipment component replacement is inserted into the corresponding time to determine the complete data of equipment component replacement; According to the missing time of the maintenance mode data, the missing data of the maintenance mode is inserted into the corresponding time to determine the complete data of the maintenance mode; According to the time when the fault type data is missing, the fault type data is inserted into the corresponding time to determine the complete data of the fault type; The complete data of equipment component replacement, maintenance method and fault type are collected and processed to determine normal operation and maintenance data.

3. A health status assessment method based on intelligent manufacturing equipment according to claim 2, characterized in that: The analysis of the correlation between each manufacturing equipment maintenance event and the fault type and the construction of a manufacturing equipment fault type assessment model specifically includes the following steps: Based on each maintenance data in the historical maintenance data, analyze the probability of occurrence of the fault type during each maintenance; Calculate the difference between the probability of occurrence of the fault type during maintenance and the probability of occurrence of the fault type during the previous maintenance; Collect statistics on all manufacturing equipment maintenance events that occurred between the maintenance time and the previous maintenance time; The difference between the probability of occurrence of the fault type during maintenance and the probability of occurrence of the fault type during the previous maintenance and all the maintenance events of manufacturing equipment occurring between the maintenance and the previous maintenance are combined into several groups of sample data; Obtain several groups of sample data to form a sample data set; Based on the sample data set, all the manufacturing equipment maintenance events that occurred between the maintenance and the previous maintenance were taken as input, and the difference between the probability of occurrence of the fault type during maintenance and the risk probability of occurrence of the fault type during the previous maintenance was taken as output. A neural network was used to train a manufacturing equipment failure type assessment model.

4. A health status assessment method based on intelligent manufacturing equipment according to claim 3, characterized in that: The method of using a neural network to train a manufacturing equipment fault type assessment model specifically includes: Divide all data in the sample data set into training set, validation set and test set in a ratio of 8:1:1; Construct a compensation function, preset a regularization coefficient, introduce a regularization term into the compensation function, and obtain a regularized compensation function; Based on the regularized compensation function, several candidate models are trained through the neural network using the training set; Use the compensation function to evaluate the compensation values ​​of several candidate models on the validation set; The candidate model corresponding to the minimum compensation value is selected as the training manufacturing equipment fault type evaluation model.

5. A health status assessment method based on intelligent manufacturing equipment according to claim 4, characterized in that: The calculation formula of the regularized compensation function is: L'(θ)=L(θ)+L1∑|θj| In the formula, L'(θ) is the regularization compensation function, L(θ) is the compensation function, L1 is the regularization coefficient, and θj is the jth parameter of the neural network.

6. A health status assessment method based on intelligent manufacturing equipment according to claim 5, characterized in that: The method of determining the closest maintenance time to the current time for each fault type based on the historical operation and maintenance data of the manufacturing equipment, and recording it as the initial maintenance time, specifically includes the following steps: Get the current time of smart manufacturing equipment; Retrieve the maintenance time in all historical operation and maintenance data; Calculate the difference between the maintenance time in all historical operation and maintenance data and the current time; The calculation formula of the initial maintenance time is: Where Tm is the initial maintenance time, and ti is the difference between the maintenance time in the historical operation and maintenance data and the current time.

7. A health status assessment method based on intelligent manufacturing equipment according to claim 6, characterized in that: The method of setting the optimal maintenance method corresponding to the fault type based on the evaluation index of the fault type specifically includes the following steps: Based on the maintenance data corresponding to the initial detection time, the probability of occurrence of the fault type at the initial detection is analyzed as the basic indicator of the fault type; The basic index of the fault type is added to the evaluation index of the fault type as the actual evaluation value corresponding to the fault type; Determine several maintenance methods corresponding to the fault type; Determine the best maintenance method based on the actual risk assessment value corresponding to the fault type; Test manufacturing equipment according to best maintenance methods.

8. A health status assessment method based on intelligent manufacturing equipment according to claim 7, characterized in that: Determining the best maintenance method specifically includes the following steps: Several maintenance methods based on the fault type; Retrieve from the database the time interval value of the next failure of the manufacturing equipment that has been repaired in several ways in the past; Compare the time interval value with a preset threshold; If the time interval value is greater than or equal to the preset threshold, the corresponding maintenance method is selected; If the time interval value is less than the preset threshold, the corresponding maintenance method is eliminated; Count all the selected corresponding maintenance methods, compare the time interval values ​​in turn, and obtain the maintenance method corresponding to the largest time interval value, which is the best maintenance method.

9. A health status assessment method based on intelligent manufacturing equipment according to claim 8, characterized in that: The calculation formula of the maximum time interval value is: Where Gm is the maximum time interval value, and gi is the i-th time interval value.

10. A health status assessment system based on intelligent manufacturing equipment, used to implement a health status assessment method based on intelligent manufacturing equipment as described in claims 1-9, characterized in that: include: A data acquisition module, the data acquisition module is used to acquire at least one type of fault that may occur in the manufacturing equipment, and set a corresponding maintenance method based on each type of fault; A data processing module, the data processing module is used to process abnormal operation and maintenance data based on historical operation and maintenance data of manufacturing equipment, the operation and maintenance data including equipment component replacement data, maintenance method data and fault type data, obtain normal operation and maintenance data, and determine all possible manufacturing equipment maintenance events based on the obtained normal data; A data analysis module, the data analysis module is used to analyze the correlation between each manufacturing equipment maintenance event and the fault type, and to build a manufacturing equipment fault type assessment model; An index evaluation module, which is used to determine the closest maintenance time to the current time for each fault type based on the historical operation and maintenance data of the manufacturing equipment, record it as the initial maintenance time, count all the manufacturing equipment maintenance events between the initial maintenance time and the current time, record it as the analysis maintenance event, substitute the analysis maintenance event into the fault type evaluation model, and obtain the evaluation index of each fault type; The module for determining the best maintenance method is used to set the best maintenance method corresponding to the fault type based on the evaluation index of the fault type.

Images