Digital intelligent school uniform production task management method and system

Abstract

The invention relates to the technical field of production task management, in particular to a digital intelligent school uniform production task management method and system, and the method comprises the steps: carrying out the statistics of historical fault data pairs in a production task; obtaining a workflow scheme of the production task by combining the type of a production line and the number of processes in the production task; obtaining the fault density per minute after the production line is started; the fault density and the corresponding time duration are combined to obtain the fault instantaneous probability and the fault cumulative probability of each minute after the production line is started, and the potential risk duration of each process in each production line is obtained by combining the fault cumulative probability and the fault maintenance duration before each minute; and obtaining an anti-risk assessment coefficient of the workflow scheme according to all the potential risk durations of all the production lines, and obtaining an optimal workflow scheme in combination with an optimization algorithm. Therefore, the efficiency and the anti-risk capability of the production task are improved.

Description

Technical Field

[0001] The present application relates to the technical field of production task management, and specifically to a digital intelligent school uniform production task management method and system. Background Art

[0002] In the past, clothing production management was completed by managers coordinating production tasks and scheduling them manually. As production tasks gradually increased and the division of labor in production workshops became increasingly refined, it became difficult to achieve optimal scheduling of production tasks through manual scheduling by managers. Therefore, factories entered production tasks into digital systems and used intelligent optimization algorithms to plan the best workflow for clothing production, thereby achieving the goal of efficient management of clothing production tasks.

[0003] The current method of planning clothing production workflows using intelligent optimization algorithms is based on the prerequisite that all production lines do not have production failures, which results in the resulting clothing production workflow planning possibly using a certain production line intensively in a short period of time, which may increase the failure probability of the production line; at the same time, the resulting clothing production workflow planning has low risk resistance, which may cause a significant drop in the efficiency of the entire production task when a production line fails. Summary of the invention

[0004] In order to solve the above technical problems, the purpose of this application is to provide a digital intelligent school uniform production task management method and system, and the technical solutions adopted are as follows:

[0005] In a first aspect, an embodiment of the present application provides a digital intelligent school uniform production task management method, the method comprising the following steps:

[0006] Record the continuous working time and fault repair time of each production line from start to stop in the production task to form a historical fault data pair;

[0007] Combined with the types of production lines and the number of processes in the production task, a workflow solution for the production task is obtained;

[0008] Analyze the distribution of continuous working time and number of failures in all historical fault data pairs to obtain the fault density per minute after the production line starts working; combine the fault density and the corresponding time length to obtain the instantaneous probability of failure per minute after the production line starts working;

[0009] Analyze the instantaneous probability of failure every minute after the production line starts working and the failure conditions of all minutes before each minute to obtain the cumulative probability of failure every minute. Combine the cumulative probability of failure and the fault repair time before each minute to obtain the potential risk time of each process in each production line.

[0010] According to the duration of all potential risks of all production lines, the anti-risk assessment coefficient of the workflow solution is obtained, and the optimal workflow solution is obtained by combining the optimization algorithm.

[0011] In one embodiment, the construction of the workflow scheme includes:

[0012] Each production line contained in each production line is replaced with data in turn as the interval element in the temporary sub-vector, and the remaining elements in the temporary sub-vector are the sequence numbers of each process in the production task. Thus, a temporary sub-vector of each production line is randomly generated, and the process sequence after each interval element in the temporary sub-vector is logically processed to obtain the sub-vector of each production line. The sub-vectors of all production lines are used to obtain the workflow solution using a Gantt chart.

[0013] In one embodiment, the determination of the fault density includes:

[0014] For all historical fault data pairs, starting from the first minute, calculations are performed for each minute in sequence, and the number of historical fault data pairs with faults in the historical fault data pairs with continuous working duration equal to any minute is counted, recorded as the fault cardinality, and the number of historical fault data pairs with continuous working duration greater than any minute is counted, and the sum of the number and the number of historical fault data pairs without faults in the historical fault data pairs with continuous working duration equal to any minute is calculated, recorded as the non-fault cardinality;

[0015] The proportion of the fault base in the sum of the fault base and the non-fault base is determined as the fault density in any one minute.

[0016] In one embodiment, the determination of the instantaneous probability of failure includes:

[0017] For each minute before any minute, calculate the time interval between each minute and any minute as the fault density weight of each minute;

[0018] For each minute after any one minute, calculate the inverse of the time interval between each minute and any one minute as the fault density weight of each minute;

[0019] The normalized value of the fault density weight of each minute is used as the weight, and the fault densities of all minutes are weighted and fused to obtain the instantaneous probability of failure in any minute.

[0020] In one embodiment, the cumulative probability of failure at any minute is a fusion of the probability that no failure occurs in all minutes before the minute and the instantaneous probability of failure at the minute.

[0021] In one embodiment, determining the duration of the potential risk includes:

[0022] Get the failure time per minute in each production line;

[0023] For each process in each production line, the fusion result of all the fault durations and the cumulative fault probabilities from the start to the end time of each process is used as the local potential risk duration of each process. The local potential risk duration of any process is spliced ​​with the original duration, and the workflow plan is re-obtained. The difference between the total duration of the re-obtained workflow plan and the total duration of the original workflow plan is used as the potential risk duration of any process.

[0024] In one embodiment, the fault duration of any one minute is the average of all fault repair durations in the historical fault data pairs whose continuous working duration is equal to the any one minute.

[0025] In one embodiment, the anti-risk assessment coefficient is a fusion result of the potential risk duration of all processes in all production lines.

[0026] In one embodiment, the combining optimization algorithm to obtain the optimal workflow solution includes:

[0027] Taking the anti-risk assessment coefficient as the optimization target of the optimization algorithm, all possible workflow schemes are optimized, and the workflow scheme with the smallest anti-risk assessment coefficient is selected as the optimal workflow scheme.

[0028] In the second aspect, an embodiment of the present application also provides a digital intelligent school uniform production task management system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of any one of the above methods when executing the computer program.

[0029] This application has at least the following beneficial effects:

[0030] The present application records the continuous working time and fault repair time of each production line from the start to the shutdown in the production task to form a historical fault data pair, combines the type of production line and the number of processes in the production task, obtains the workflow plan of the production task, quantifies the planning and arrangement of the production task, and improves the rationality and convenience of the planning and arrangement of the production task; analyzes the distribution of continuous working time and the number of failures in all historical fault data pairs to obtain the fault density per minute after the production line is started; combines the fault density and the corresponding time length to obtain the instantaneous probability of failure per minute after the production line is started, which solves the problem of uneven time distribution of data collected by the production line, resulting in inaccurate calculation of fault statistical probability; improves the accuracy of the calculation of the fault probability per minute; merges the instantaneous probability of failure of all minutes before each minute after the production line is started to obtain the The cumulative probability of failure reflects the impact of the failure probability of all minutes before the current moment on the working time of the production line on the failure at the current moment. It takes into account the problem of fault propagation and the existence of before and after correlation on the production line, and improves the accuracy of fault analysis. Combined with the cumulative probability of failure and the fault repair time every minute before, the potential risk time of each process in each production line is obtained, reflecting the degree of influence of a single process on the entire production task. According to all the potential risk times of all production lines, the risk resistance assessment coefficient of the workflow scheme is obtained, and combined with the optimization algorithm, the optimal workflow scheme is obtained. Compared with the traditional production task management scheme, the risk resistance assessment coefficient takes into account the impact of production line failures on the production task workflow, and can avoid the problems of a significant decrease in production task efficiency caused by production line failures and weak risk resistance of intelligent production task management. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0032] Figure 1 A flowchart of a digital intelligent school uniform production task management method provided in one embodiment of the present application;

[0033] Figure 2 is a schematic diagram of a temporary sub-vector;

[0034] Figure 3 is a schematic diagram of a sub-vector;

[0035] Figure 4 Construct a flow chart for the risk resistance assessment factor. DETAILED DESCRIPTION

[0036] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the specific implementation method, structure, features and effects of a digital intelligent school uniform production task management method and system proposed in accordance with the present application, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0037] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0038] The following is a detailed description of the specific scheme of a digital intelligent school uniform production task management method and system provided by the present application in conjunction with the accompanying drawings.

[0039] See also Figure 1 , which shows a flowchart of a digital intelligent school uniform production task management method provided by an embodiment of the present application, the method comprising the following steps:

[0040] S1, records the continuous working time and fault maintenance time of each production line from start to stop in the production task, forming a historical fault data pair.

[0041] This application determines the failure probability of the production line through the historical data of the production line, and then uses an intelligent optimization algorithm to select a workflow plan that has a strong ability to resist the risk of production line failure as the production plan, solving the problem of weak risk resistance in traditional production task management.

[0042] First, obtain the historical fault data of the factory production line: Assuming that the factory has N production lines, start recording data when the nth production line starts to perform production tasks, and record the working time of the nth production line until the nth production line completes all tasks and rests, or until the nth production line fails. When the nth production line stops working due to completing the task, the fault maintenance time of the production line is recorded as 0; when the nth production line stops working due to a fault, the maintenance time is recorded as the fault maintenance time.

[0043] It is set that when the production line has not produced for a consecutive minutes, or stops production due to a malfunction, it is determined that the production line has stopped working at this time; if the production line stops working for no more than a minutes, it is determined that the production line is still in continuous production. In one embodiment of the present application, a=3, and the implementer can set it according to the actual situation, and the present application does not impose any restrictions on this.

[0044] Finally, each time the nth production line starts and stops, a historical fault data is recorded. The data is in the form of a data pair, recorded as a historical fault data pair (W, F), where W represents the continuous working time of this production line, and F represents the fault maintenance time of this production line.

[0045] As an embodiment of the present application, the continuous working time and the fault repair time are both recorded in minutes.

[0046] For the production tasks in the factory, which include multiple processes, there are two relationship modes between different processes: serial and parallel. Taking process A and process B as an example, the serial relationship means that process A and process B need to be carried out in sequence, that is, process B can only be carried out after process A is completed. The parallel relationship means that process A and process B do not affect each other and can be carried out at the same time. The known serial and parallel relationships between different processes are recorded as logical relationships.

[0047] S2, combining the types of production lines and the number of processes in the production task, obtains the workflow solution for the production task.

[0048] In order to digitally intelligentize the school uniform production task, it is necessary to characterize the workflow scheme with a unified digital task. This embodiment uses a workflow vector to digitally characterize the workflow scheme.

[0049] Assuming that there are M=4 types of production lines in the production task, the final workflow vector has M sub-vectors; assuming that the factory has R=3 production lines for the m-th production line, R=3 interval elements are set in the m-th sub-vector; assuming that in the production task, the m-th production task has a total of S=10 processes, S=10 process elements are set in the m-th sub-vector; therefore, the m-th sub-vector is a vector with a length of R+S, with R interval elements, represented by 1, 2, and 3 here, representing 3 different production lines, and S process elements, represented by numbers from 4 to 13 here, representing different processes.

[0050] Furthermore, a vector is randomly generated, the length of which is R+S=13, and the elements of which contain numbers from 1 to 13, which is recorded as the temporary sub-vector of the m-th production line; the schematic diagram of the temporary sub-vector is shown in Figure 2 shown.

[0051] Figure 2 is a vector with randomly arranged numbers; 3 is set as the interval element, and the following processes 4, 8, 11, 7 represent that the third production line needs to work in the order of 4, 8, 11, 7.

[0052] However, the 4th, 8th, 11th, and 7th processes may have logical conflicts when they are performed in sequence. Therefore, it is necessary to perform logical processing on the temporary sub-vectors to obtain sub-vectors, specifically:

[0053] like Figure 2 As shown, the third production line needs to produce according to processes 4, 8, 11, and 7. At this time, the fourth process is first judged to determine whether there is a serial process before the fourth process in the subsequent processes 8, 11, and 7. If so, the fourth process is placed at the back of the corresponding process. For example, in the normal process sequence, the seventh process should be in front of the fourth process. Therefore, the fourth process needs to be placed at the back of the seventh process. By analogy, processes 8, 11, and 7 are judged in turn to complete the logical processing of the temporary sub-vector. The temporary sub-vector after the logical processing is recorded as a sub-vector. The schematic diagram of the sub-vector is shown in FIG. Figure 3 shown.

[0054] Figure 3 In the example, the 4th process is moved to the back of the 7th process; all process elements are processed in this way to complete the logical processing and obtain sub-vectors, which can avoid logical errors in the process sequence and enable the workflow represented by the sub-vector to proceed normally.

[0055] Furthermore, M seed vectors can be obtained for M production lines, and a workflow vector can be obtained by connecting the M seed vectors end to end. According to the workflow vector, the order of clothing production tasks can be arranged. Among them, when the r-th production line completes a process, before entering the next process, if the next process has a serial process that has not been completed, it means that the raw materials of the next process are still being produced by other production lines, then the r-th production line enters a rest state.

[0056] The Gantt chart of the workflow vector of the production task is obtained, which represents a workflow solution. The Gantt chart is an existing well-known technology in the field of workflow analysis, and this application will not elaborate on it in detail.

[0057] S3, analyzing the distribution of continuous working time and number of failures in all historical fault data pairs to obtain the fault density per minute after the production line starts; combining the fault density and the corresponding time length to obtain the instantaneous probability of failure per minute after the production line starts.

[0058] This embodiment conducts risk assessment on the work of delaying production tasks due to production line failures in production tasks. Therefore, it is necessary to process historical failure data and evaluate the probability of failure of each production line, so as to construct the instantaneous probability of failure. In the historical data of a production line, the more failures occur and the shorter the continuous working time when a failure occurs, the more likely the production line is to fail.

[0059] For all historical fault data pairs of each production line, for example, for all historical fault data pairs of the r-th production line, starting from the first minute, calculations are performed for each minute in sequence, such as the second minute, the third minute, the fourth minute, etc. Taking the 20th minute as an example, among all historical fault data pairs of the r-th production line, the number of historical fault data pairs with faults occurring in the historical fault data pairs with continuous working time equal to the 20th minute is counted, recorded as the fault cardinality, the number of historical fault data pairs with continuous working time greater than the 20th minute is counted, recorded as the first number, the number of historical fault data pairs with no faults occurring in the historical fault data pairs with continuous working time equal to the 20th minute is counted, recorded as the second number, the sum of the first number and the second number is taken as the non-fault cardinality, the sum of the fault cardinality and the non-fault cardinality is calculated, recorded as the first sum, the ratio of the fault cardinality to the first sum is taken as the fault density for the 20th minute in the r-th production line, and the same calculation method is used to obtain the fault density per minute in each production line.

[0060] Furthermore, based on the fault density, the instantaneous probability of failure per minute is calculated.

[0061] Taking the 20th minute in the rth production line as an example, for each minute before the 20th minute, the time interval between each minute and the 20th minute is calculated as the failure density weight of each minute;

[0062] For each minute after the 20th minute, the inverse of the time interval between each minute and the 20th minute is calculated as the failure density weight of each minute;

[0063] The fault density weights of all minutes are normalized using the minimum-maximum normalization method. The normalized fault density weight of each minute is used as the weight, and the fault density of all minutes is weighted and fused to obtain the instantaneous probability of failure in the 20th minute.

[0064] It should be noted that the implementer can choose a normalization algorithm for normalization according to actual conditions, and this application does not impose any restrictions on this.

[0065] It should be understood that fusion means combining multiple variables in a form that enhances the overall effect, for example, adding, multiplying, etc.

[0066] In one embodiment of the present application, the normalized fault density weight per minute is used as the weight, and the weighted sum of the fault densities of all minutes is taken as the instantaneous probability of failure in the 20th minute.

[0067] The greater the instantaneous probability of failure at the 20th minute, the greater the probability of failure of the rth production line when the continuous working time reaches the 20th minute.

[0068] To facilitate subsequent calculations, calculate the proportion of the instantaneous probability of failure per minute in the sum of the instantaneous probability of failure in all minutes and re-record it as the instantaneous probability of failure per minute to ensure that the sum of the instantaneous probability of failure per minute is 1.

[0069] S4, the instantaneous probability of failure of all minutes before each minute after the production line starts is integrated to obtain the cumulative probability of failure per minute, and the potential risk duration of each process in each production line is obtained by combining the cumulative probability of failure and the fault repair duration before each minute.

[0070] When a production line fails, since production tasks are closely linked, the impact of a failure in one production line will spread to the entire production task. In order to evaluate the failure risk, this embodiment requires an overall analysis of the failure of the production line.

[0071] The total duration of the workflow plan is the optimization goal of the traditional intelligent school uniform management method. Therefore, it is necessary to analyze the potential risk duration of the workflow plan. For the rth production line, the longer the continuous working time is arranged for it, the greater the work risk and the longer the potential risk duration; in the historical fault data of the rth production line, the longer the fault repair time is, the longer the stagnation time of the entire production task is caused, and the longer the potential risk duration is.

[0072] Since there are many types of failures on the production line, and the maintenance time of different types of failures is different, and the maintenance time determines the impact of the production line failure on the production task, the failure risk should be analyzed according to the failure type; since a certain type of failure will occur in a certain time period, such as mechanical overheating, it will only occur during a period of too long continuous working time, and will not occur when the production line just starts to operate, the distribution of maintenance failure time based on the continuous working time can be used to characterize the time when different types of failures occur.

[0073] Therefore, taking the r-th production line as an example, in the historical fault data of the r-th production line, obtain the historical fault data pairs with continuous working time of w and faults, obtain all its fault repair time and calculate the average, which is recorded as the w-th minute fault time;

[0074] Based on the instantaneous probability of failure per minute, calculate the cumulative probability of failure per minute.

[0075] Taking the e-th minute as an example, the cumulative probability of failure in the e-th minute is the probability of failure occurring in the e-th minute when no failure occurs in all minutes before the e-th minute.

[0076] In one embodiment of the present application, the calculation method of the cumulative probability of failure can be: Among them, h e represents the cumulative probability of failure in the eth minute, h i-1represents the cumulative probability of failure in the i-1th minute, f e represents the instantaneous probability of failure in the eth minute. It should be noted that the cumulative probability of failure in the first minute is the instantaneous probability of failure in the first minute. represents the probability that no failure occurs in all minutes before the eth minute, and the cumulative probability of failure h e It represents the probability of a failure occurring in the e-th minute when no failure occurs in all minutes before the e-th minute.

[0077] Based on the cumulative probability of failure per minute and the failure duration per minute, the local potential risk duration of each process in each production line is calculated. Taking each fixed process as the basic analysis unit, the failure risk of each process in each production line and its impact on the entire production task are analyzed.

[0078] From the start time to the end time of each process, the fusion result of the cumulative failure probability and the failure duration of all minutes is used as the local potential risk duration of each process.

[0079] In one embodiment of the present application, from the start time to the end time of each process, the product of the cumulative probability of failure per minute and the failure duration is calculated, and the sum of the products for all minutes is used as the local potential risk duration of each process.

[0080] Taking the vth process in the rth production line as an example, add the local potential risk duration of the vth process to the original duration, re-obtain the workflow plan for the production task, and calculate the difference between the total duration of the re-obtained workflow plan and the total duration of the original workflow plan as the potential risk duration of the vth process.

[0081] For each process of each production line in the production task, the same calculation method as the vth process in the rth production line is used to obtain the potential risk duration of each process of each production line.

[0082] S5, according to all the potential risk durations of all production lines, the anti-risk assessment coefficient of the workflow solution is obtained, and the optimal workflow solution is obtained by combining the optimization algorithm.

[0083] The sum of the potential risk duration of all processes in all production lines in the production task is used as the anti-risk assessment coefficient of the production task. The anti-risk assessment coefficient construction flow chart is as follows: Figure 4 shown.

[0084] The smaller the risk resistance assessment coefficient is, the shorter the total time to complete the task when executing the production task plan, and the stronger the ability to resist the risk of production line failure.

[0085] Finally, the anti-risk assessment coefficient is used as an indicator to evaluate the workload vector of the school uniform production task, and the optimization algorithm is used to obtain the optimal workflow vector:

[0086] In one embodiment of the present application, a genetic algorithm is used as an optimization algorithm. The genetic algorithm is a well-known technology and will not be described in detail in the present application.

[0087] It should be noted that the implementer may select other existing feasible optimization algorithms according to actual conditions, such as ant colony algorithm, wolf pack algorithm, etc., and this application does not make any restrictions here.

[0088] In one embodiment of the present application, the process of using a genetic algorithm to obtain the optimal workflow vector is as follows:

[0089] Step P1 Initialization: Randomly generate C groups of vectors, each group of vectors has M sub-vectors, and the generation method of sub-vectors has been described above. M represents the number of production line types in the production task.

[0090] Step P2 population growth: perform crossover and mutation operations on group C vectors to generate group D vectors. In one embodiment of the present application, the crossover rate is 0.2 and the mutation rate is 0.05. The implementer can set them according to the actual situation, and the present application does not impose any restrictions on this.

[0091] The crossing rule is: when two groups of vectors cross, first cross the mth pair of subvectors of the two groups of vectors. When the subvectors cross, first randomly mark the same element positions in the two subvectors as intersection points, exchange the elements in the intersection points, and then fill in the remaining elements in each subvector to obtain a temporary subvector. Finally, perform logical processing on the temporary subvector to obtain the crossed subvector.

[0092] For example: the mth pair of subvectors are (1,3,5,2,7,4,6) and (6,7,3,5,2,1,4), and the selected intersection positions are the 3rd and 6th positions. Then the elements of the intersection point of (1,3,5,2,7,4,6) change from 5 to 3, and from 4 to 1. The intersection point is (,,3,,,1,), and the remaining elements are (5,2,7,4,6). Fill (5,2,7,4,6) into (,,3,,,1,) to obtain (5,2,3,7,4,1,6) as a temporary subvector. Finally, the temporary subvector is logically processed to obtain the corresponding subvector. Perform the same processing on each pair of subvectors in the two groups of vectors that intersect to complete the crossover operation.

[0093] The mutation rule is: when a group of vectors mutates, the mth sub-vector of the group of vectors is mutated. For example, when (1,3,5,2,7,4,6) is mutated, the mutation point is selected as the second element, which changes from 3 to 6. Then the position of the element that was originally 6 is changed to 3 synchronously to obtain a temporary sub-vector (1,6,5,2,7,4,3). Then the temporary sub-vector is logically processed to obtain the sub-vector to complete the mutation operation.

[0094] Step P3 population screening: Among the D groups of vectors produced in step P2, each group of vectors represents a production task workflow solution. The risk resistance assessment coefficient is calculated for each of the D groups of vectors, and the C group of vectors with the smallest risk resistance assessment coefficient is selected as the winning individual to be retained.

[0095] Step P4 iteration: Repeat steps P2 and P3. In one embodiment of the present application, the number of repetitions is set to 50 times. The implementer can set the number of repetitions according to the actual situation, and the present application does not limit this. After the last repetition, a group of C vectors is obtained. The group of vectors with the smallest anti-risk assessment coefficient is selected, and the production task workflow scheme represented by it is used as the final workflow scheme to complete the management of the school uniform production task.

[0096] Since the anti-risk assessment coefficient is used as the screening condition when screening the genetic algorithm, and the anti-risk assessment coefficient takes production line failure as a factor compared to the traditional workflow evaluation scheme, the final workflow scheme has the ability to resist the risk of production line failure, avoiding the problem of a significant decrease in production task efficiency due to production line failure.

[0097] Based on the same inventive concept as the above method, an embodiment of the present application also provides a digital intelligent school uniform production task management system, including a memory, a processor, and a computer program stored in the memory and running on the processor, and when the processor executes the computer program, it implements the steps of any one of the above-mentioned digital intelligent school uniform production task management methods.

[0098] In summary, the present application records the continuous working time and fault repair time of each production line from the start to the shutdown in the production task to form a historical fault data pair, combines the type of production line and the number of processes in the production task, obtains the workflow plan of the production task, quantifies the planning and arrangement of the production task, and improves the rationality and convenience of the planning and arrangement of the production task; analyzes the distribution of continuous working time and the number of failures in all historical fault data pairs to obtain the fault density every minute after the production line is started; combines the fault density and the corresponding time length to obtain the instantaneous probability of failure every minute after the production line is started, which solves the problem of uneven time distribution of data collected by the production line, resulting in inaccurate calculation of fault statistical probability; improves the accuracy of calculation of fault probability per minute; merges the instantaneous probability of failure of all minutes before each minute after the production line is started to obtain the fault probability per minute. The cumulative probability of failure per minute reflects the impact of the failure probability of all minutes before the current moment on the working time of the production line on the failure at the current moment, taking into account the problem of fault propagation and the existence of before and after correlation on the production line, thereby improving the accuracy of fault analysis; combined with the cumulative probability of failure and the fault repair time every minute before, the potential risk time of each process in each production line is obtained, reflecting the degree of influence of a single process on the entire production task, and according to all the potential risk times of all production lines, the risk resistance assessment coefficient of the workflow vector is obtained, and combined with the optimization algorithm, the optimal workflow solution is obtained. Compared with the traditional production task management solution, the risk resistance assessment coefficient takes into account the impact of production line failures on the production task workflow, and can avoid the problems of a significant decrease in production task efficiency caused by production line failures and weak risk resistance of intelligent production task management.

[0099] It should be noted that the above sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above is a description of a specific embodiment of this specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0100] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0101] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present application should be included in the protection scope of the present application.

Claims

1. A digital intelligent school uniform production task management method, characterized in that: The method comprises the following steps: Record the continuous working time and fault repair time of each production line from start to stop in the production task to form a historical fault data pair; Combined with the types of production lines and the number of processes in the production task, a workflow solution for the production task is obtained; Analyze the distribution of continuous working time and number of failures in all historical fault data pairs to obtain the fault density per minute after the production line starts working; combine the fault density and the corresponding time length to obtain the instantaneous probability of failure per minute after the production line starts working; Analyze the instantaneous probability of failure every minute after the production line starts working and the failure conditions of all minutes before each minute to obtain the cumulative probability of failure every minute. Combine the cumulative probability of failure and the fault repair time before each minute to obtain the potential risk time of each process in each production line. According to the duration of all potential risks of all production lines, the anti-risk assessment coefficient of the workflow solution is obtained, and the optimal workflow solution is obtained by combining the optimization algorithm.

2. A digital intelligent school uniform production task management method as claimed in claim 1, characterized in that: The construction of the workflow scheme includes: Each production line contained in each production line is replaced with data in turn as the interval element in the temporary sub-vector, and the remaining elements in the temporary sub-vector are the sequence numbers of each process in the production task. Thus, a temporary sub-vector of each production line is randomly generated, and the process sequence after each interval element in the temporary sub-vector is logically processed to obtain the sub-vector of each production line. The sub-vectors of all production lines are used to obtain the workflow solution using a Gantt chart.

3. A digital intelligent school uniform production task management method as claimed in claim 1, characterized in that: The determination of the fault density includes: For all historical fault data pairs, starting from the first minute, calculations are performed for each minute in sequence, and the number of historical fault data pairs with faults in the historical fault data pairs with continuous working duration equal to any minute is counted, recorded as the fault cardinality, and the number of historical fault data pairs with continuous working duration greater than any minute is counted, and the sum of the number and the number of historical fault data pairs without faults in the historical fault data pairs with continuous working duration equal to any minute is calculated, recorded as the non-fault cardinality; The proportion of the fault base in the sum of the fault base and the non-fault base is determined as the fault density in any one minute.

4. A digital intelligent school uniform production task management method as claimed in claim 3, characterized in that: The determination of the instantaneous probability of failure includes: For each minute before any minute, calculate the time interval between each minute and any minute as the fault density weight of each minute; For each minute after any one minute, calculate the inverse of the time interval between each minute and any one minute as the fault density weight of each minute; The normalized value of the fault density weight of each minute is used as the weight, and the fault densities of all minutes are weighted and fused to obtain the instantaneous probability of failure in any minute.

5. A digital intelligent school uniform production task management method as claimed in claim 1, characterized in that: The cumulative probability of failure at any minute is the fusion of the probability that no failure occurs in all minutes before the minute and the instantaneous probability of failure at the minute.

6. A digital intelligent school uniform production task management method as claimed in claim 1, characterized in that: The determination of the duration of the potential risk includes: Get the failure time per minute in each production line; For each process in each production line, the fusion result of all the fault durations and the cumulative fault probabilities from the start to the end time of each process is used as the local potential risk duration of each process. The local potential risk duration of any process is spliced ​​with the original duration, and the workflow plan is re-obtained. The difference between the total duration of the re-obtained workflow plan and the total duration of the original workflow plan is used as the potential risk duration of any process.

7. A digital intelligent school uniform production task management method as claimed in claim 6, characterized in that: The fault duration of any one minute is the average of all fault repair durations in the historical fault data pairs whose continuous working duration is equal to the any one minute.

8. A digital intelligent school uniform production task management method as claimed in claim 6, characterized in that: The anti-risk assessment coefficient is the fusion result of the potential risk duration of all processes in all production lines.

9. A digital intelligent school uniform production task management method as claimed in claim 1, characterized in that: The combined optimization algorithm to obtain the optimal workflow solution includes: Taking the anti-risk assessment coefficient as the optimization target of the optimization algorithm, all possible workflow schemes are optimized, and the workflow scheme with the smallest anti-risk assessment coefficient is selected as the optimal workflow scheme.

10. A digital intelligent school uniform production task management system, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 9 are implemented.

Images