Medical instrument production control method and device, terminal equipment and storage medium

Abstract

The invention discloses a medical instrument production control method and device, terminal equipment and a storage medium. The method comprises the following steps: collecting production parameters of each production link, and classifying the production parameters through correlation analysis to obtain a first parameter and a second parameter; determining a bottleneck production link from all production links in combination with the production parameters; judging whether the bottleneck production link reaches the maximum production load or not according to a second parameter corresponding to the bottleneck production link; if the bottleneck production link reaches the maximum production load, optimizing a first parameter corresponding to each production link through a multi-objective optimization algorithm until the yield of each production link meets a preset condition; and otherwise, optimizing the second parameter corresponding to each production link through a single-target optimization algorithm until the bottleneck production link reaches the maximum production load. The method can be used in a dynamic production environment, the complexity of production parameter optimization caused by complex time sequence constraints among links is reduced, and the production efficiency and the product quality are improved.

Description

Technical Field

[0001] The present application relates to the field of production control, and in particular to a method, apparatus, terminal device and storage medium for production control of medical devices. Background Art

[0002] The production process of medical devices often involves production links such as device casting, assembly, sterilization and packaging. Each link involves different production parameters. For example, device casting involves production parameters such as temperature, pressure and cooling time, sterilization involves production parameters such as the temperature of the sterilization environment, ultraviolet intensity and sterilization time, and assembly and packaging involve production parameters such as batch setting parameters and transmission speed. Different production parameters have different effects on product yield and production efficiency, and different production links have complex time-dependent relationships, and there are certain mutual influences between production parameters, which brings severe challenges to the optimization of production parameters.

[0003] The existing technology often establishes a simulation model to simulate the scheduling actions of the equipment production line, and uses a heuristic algorithm to find the optimal production parameter settings. This method often makes the simulation model and heuristic algorithm more complicated due to the increase in production scale. When the production environment changes, such as when some production equipment is damaged or updated, the complexity of the simulation model and heuristic algorithm makes it impossible to update the simulation model and algorithm in time. In addition, some existing technologies use big data analysis methods to mine the timing cycle rules between various links from previous production data to find the key production parameters that lead to reduced production quality and production efficiency. This method requires too high a computing cost and is unable to cope with a dynamically adjusted production environment.

[0004] Therefore, when faced with a dynamic production environment, how to consider the timing constraints between each link and adjust the production parameters of each link in a timely manner to ensure the product yield and production efficiency while ensuring the stability of the control method is a technical problem that needs to be solved at present. Summary of the invention

[0005] The present application provides a medical device production control method, apparatus, terminal device and storage medium to solve the technical problems of difficulty in optimizing production parameters, low efficiency and low generalization of control methods caused by complex timing constraints between various links in a dynamic production environment.

[0006] In order to solve the above technical problems, in a first aspect, an embodiment of the present application provides a medical device production control method, comprising:

[0007] Collecting production parameters of each production link; wherein the production parameters include: a first parameter and a second parameter; the first parameter is obtained by calculating the correlation between each production parameter and the yield rate through the Pearson correlation coefficient method; the second parameter is obtained by calculating the correlation between each production parameter and the production efficiency through the Pearson correlation coefficient method;

[0008] Acquire the production duration data of each production link within a preset time, and perform a time series pattern analysis on the production duration data corresponding to each production link in combination with the production parameters to determine the bottleneck production link;

[0009] According to the second parameter corresponding to the bottleneck production link, determining whether the bottleneck production link has reached the maximum production load;

[0010] If the bottleneck production link reaches the maximum production load, the first parameters corresponding to each of the production links are optimized through a multi-objective optimization algorithm until the yield rate of each of the production links meets the preset conditions; otherwise, the second parameters corresponding to each of the production links are optimized through a single-objective optimization algorithm until the bottleneck production link reaches the maximum production load.

[0011] Compared with the prior art, the embodiments of the present application have the following beneficial effects: in a dynamic production environment, when the production environment changes, the current bottleneck production link may change. Therefore, the bottleneck production link can be identified in real time through actual production time data, which can provide accurate basis for subsequent production parameter optimization in a timely manner; in addition, the processing rhythm of the bottleneck production link will affect the processing efficiency of the entire production line, and it is necessary to optimize the production parameters of the bottleneck production link more carefully, otherwise the entire production rhythm will be disrupted. The present application divides the production parameters into two categories, and prioritizes the optimization of the second parameter related to the production rhythm, so that the workload of the bottleneck production link is maximized, and then fixes the second parameter and optimizes the first parameter, thereby reducing the complexity of the multi-parameter optimization problem; finally, the present application starts with the production parameters and the bottleneck production link. Even if some production equipment fails to shut down or is updated during the production process, as long as the production equipment has the same function and the same production parameters, there is no need to adjust the control process, thereby improving the generalization of the overall control method.

[0012] In some embodiments of the first aspect of the present application, the obtaining of the production duration data of each of the production links within a preset time, combining the production parameters, performing a time series pattern analysis on the production duration data corresponding to each of the production links, and determining the bottleneck production link, includes:

[0013] Determine available production equipment corresponding to the production link according to the production parameters;

[0014] Calculating a first production speed of the available production equipment corresponding to the production link according to the production duration data;

[0015] Calculating a second production speed of the corresponding production link according to the number of available production equipment of the production link and the first production speed;

[0016] The production link with the second smallest production speed is determined as the bottleneck production link.

[0017] Compared with the prior art, the above embodiment has the following beneficial effects: since the faulty equipment may still be able to participate in production although it is faulty, but will produce a large number of unusable parts, the available production equipment is first determined, and the actual production speed of each available production equipment in each production link is dynamically calculated through the real-time collected production time data, and the overall production speed of the corresponding production link is re-determined in combination with the number of available production equipment in the current production link, thereby accurately identifying the actual bottleneck production link in a dynamic production environment, improving the dynamic adaptability of the production system, and further improving the accuracy of subsequent production parameter optimization.

[0018] In some embodiments of the first aspect of the present application, determining, according to the production parameters, available production equipment corresponding to the production link includes:

[0019] Inputting the production parameters of each production equipment in the production link into the decision tree of the corresponding production link in sequence to obtain the classification result of the corresponding production equipment; the decision tree is obtained by training the historical production parameters of the corresponding production link;

[0020] When the classification result is normal, the corresponding production equipment is determined to be available production equipment.

[0021] Compared with the prior art, the above embodiment has the following beneficial effects: since the decision tree can not only ensure the accuracy of the classification results when facing simple classification problems, but also has the characteristic of high computational efficiency, the decision tree can accurately identify the abnormal production parameters under different faults through historical data, thereby accurately and quickly identifying the faulty equipment in the dynamic production link, improving the accuracy of the subsequent bottleneck production link identification and the stability of production control.

[0022] In some embodiments of the first aspect of the present application, judging whether the bottleneck production link has reached the maximum production load according to the second parameter corresponding to the bottleneck production link includes:

[0023] Calculating a third production speed of the bottleneck production link according to the second parameter;

[0024] When the difference between the second production speed and the third production speed of the bottleneck production link is less than or equal to a preset threshold, it is determined that the bottleneck production link has reached the maximum production load.

[0025] Compared with the prior art, the above embodiment has the following beneficial effects: since the second production speed is the real production speed calculated according to the actual number of available production equipment, and the third production speed is the theoretical production speed calculated according to the production parameters, when the second production speed of the bottleneck production link is close to the third production speed, the bottleneck link is in a state close to full load operation, which also means that the production speed of each production link has reached the maximum production speed under the current production conditions. Through this load determination method, a clear basis is provided for the subsequent optimization of production parameters, so that the production efficiency of the entire production line can be maximized.

[0026] In some embodiments of the first aspect of the present application, if the bottleneck production link reaches the maximum production load, optimizing the first parameter corresponding to each of the production links by a multi-objective optimization algorithm until the yield rate of each of the production links meets a preset condition includes:

[0027] Taking the second parameter existing in the first parameter in each of the production links as a fixed parameter;

[0028] Initializing a preset regression analysis model according to the fixed parameters to obtain a first fitness function for calculating the yield rate of the corresponding production link; the regression analysis model is obtained by training the historical production parameters and yield rate data of the corresponding production link;

[0029] Optimizing all the first fitness functions through the multi-objective optimization algorithm to obtain multiple Pareto solutions;

[0030] From all the Pareto solutions, the Pareto solution with the maximum yield rate in the bottleneck production link is selected, and the optimal first parameter of each of the production links is determined based on the Pareto solution with the maximum yield rate.

[0031] Compared with the prior art, the above embodiment has the following beneficial effects: due to the complex correlation between different production links, when the first production parameter of a certain production link is adjusted, it will not only affect the yield rate in the current production link, but also indirectly affect the yield rate of the upstream and downstream production links of the production link. Therefore, through a multi-objective optimization algorithm, respective fitness functions are established for different production links, and the yield rates of all production links are simultaneously optimized through a multi-objective optimization algorithm, thereby obtaining multiple feasible Pareto solutions. Since the optimality of Pareto solutions cannot be compared, the Pareto solution with the largest yield rate in the bottleneck production link is selected from multiple Pareto solutions as the optimal solution based on the characteristic that the bottleneck production link has a greater impact, thereby improving the overall yield rate of the production line.

[0032] In some embodiments of the first aspect of the present application, optimizing the second parameter corresponding to each of the production links by a single-objective optimization algorithm until the bottleneck production link reaches the maximum production load includes:

[0033] According to the second parameters of the other production links, constructing the timing constraints between the production links;

[0034] Constructing a second fitness function for calculating a third production speed of the bottleneck production link according to the second parameter of the bottleneck production link;

[0035] According to the timing constraint, a penalty term is added to the second fitness function, and the second fitness function is optimized through the single-objective optimization algorithm to obtain the optimal second parameters of each of the production links.

[0036] Compared with the prior art, the above embodiment has the following beneficial effects: since there is a mutual influence relationship between different production links, the second fitness function is constructed in combination with the timing constraint to evaluate the impact of changes in the second parameters of other production links on the third production speed of the bottleneck production link, and through the single-objective optimization algorithm, the second fitness function is optimized, which is equivalent to adjusting the second parameters of all production links at the same time until the impact on the third production speed of the bottleneck production link is minimized. When the production speed of the bottleneck production link reaches the maximum, the production speed of the production line will also reach the maximum, thereby improving the operating efficiency of the entire production line.

[0037] In some embodiments of the first aspect of the present application, after optimizing the second parameters corresponding to each of the production links through a single-objective optimization algorithm, it also includes: fixing the second parameters corresponding to each of the production links, and optimizing the first parameters corresponding to each of the production links through a multi-objective optimization algorithm until the yield rate of each of the production links meets the preset conditions.

[0038] Compared with the prior art, the above embodiment has the following beneficial effects: after optimizing the second parameters corresponding to each production link, by fixing the second parameters and optimizing the first parameters, the yield rate is improved without affecting the production efficiency, thereby achieving stable and efficient production scheduling and significantly improving the robustness and scalability of the production system.

[0039] In a second aspect, an embodiment of the present application further provides a medical device production control device, comprising: a data acquisition module, a bottleneck calculation module, a first judgment module, and a first execution module;

[0040] Wherein, the data acquisition module is used to collect production parameters of each production link; wherein, the production parameters include: a first parameter and a second parameter; the first parameter is obtained by calculating the correlation between each of the production parameters and the yield rate by the Pearson correlation coefficient method; the second parameter is obtained by calculating the correlation between each of the production parameters and the production efficiency by the Pearson correlation coefficient method;

[0041] The bottleneck calculation module is used to obtain the production time data of each production link within a preset time, and perform a time series pattern analysis on the production time data corresponding to each production link in combination with the production parameters to determine the bottleneck production link;

[0042] The first judgment module is used to judge whether the bottleneck production link has reached the maximum production load according to the second parameter corresponding to the bottleneck production link;

[0043] The first execution module is used to optimize the first parameters corresponding to each of the production links through a multi-objective optimization algorithm if the bottleneck production link reaches the maximum production load until the yield rate of each of the production links meets the preset conditions; otherwise, optimize the second parameters corresponding to each of the production links through a single-objective optimization algorithm until the bottleneck production link reaches the maximum production load.

[0044] In a third aspect, an embodiment of the present application further provides a terminal device, comprising a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements the above-mentioned medical device production control method when executing the computer program.

[0045] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned medical device production control method. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic diagram of a process flow of a medical device production control method provided in some embodiments of the present application;

[0047] Figure 2 This is a schematic diagram of the structure of a medical device production control device provided in some embodiments of the present application. DETAILED DESCRIPTION

[0048] The existing technology often establishes a simulation model to simulate the scheduling actions of the equipment production line, and uses a heuristic algorithm to find the optimal production parameter settings. This method often makes the simulation model and heuristic algorithm more complicated due to the increase in production scale. When the production environment changes, such as when some production equipment is damaged or updated, the complexity of the simulation model and heuristic algorithm makes it impossible to update the simulation model and algorithm in time. In addition, some existing technologies use big data analysis methods to mine the timing cycle rules between various links from previous production data to find the key production parameters that lead to reduced production quality and production efficiency. This method requires too high a computing cost and is unable to cope with a dynamically adjusted production environment.

[0049] In order to solve the above technical problems, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0050] Embodiment 1

[0051] Please refer to Figure 1 , a medical device production control method provided in an embodiment of the present application, including S10 to S40, specifically:

[0052] S10: Collecting production parameters of each production link; wherein the production parameters include: a first parameter and a second parameter; the first parameter is obtained by calculating the correlation between each production parameter and the yield rate through the Pearson correlation coefficient method; the second parameter is obtained by calculating the correlation between each production parameter and the production efficiency through the Pearson correlation coefficient method.

[0053] Preferably, in some embodiments of the present application, the production links include but are not limited to: component manufacturing link, component assembly link, sterilization link and packaging link of medical devices; wherein, the production parameters of the component manufacturing link include: casting temperature, pressure, cooling time and other parameters; the production parameters of the component assembly link include: component transmission speed, robot arm movement speed, number of robot arm configurations and other parameters; the production parameters of the sterilization link include: ultraviolet intensity, disinfection time and other parameters; the production parameters of the packaging link include: medical device transmission speed and other parameters.

[0054] Preferably, in some embodiments of the present application, the production parameters of any production link can be classified by the following preferred implementation method, which is described below by taking the production parameters of the component manufacturing link as an example:

[0055] S11: Collect historical production parameter data and corresponding output data of each production equipment in the component manufacturing process, wherein the historical production parameter data includes the temperature, pressure, cooling time and other parameter settings of each production equipment in each historical production batch; the output data includes the yield rate of components produced in each historical production batch and the number of components produced per unit time (equivalent to production efficiency);

[0056] S12: Assume that the sample set of temperature in the historical production parameter data collected is X = {x1, x2, …, x n}, the sample set of the yield rate of the corresponding output data is Y = {y1,y2,…,y n}, standardize the data in the two sample sets respectively. Specifically, the Z-score standardization method can be used to convert the value of each sample into the Z value under the standard normal distribution, so that the mean of different parameters is 0 and the variance is 1, further eliminating the differences between sample data and improving the statistical characteristics of the data;

[0057] S13: Process all collected historical production parameter data and output data through the steps in S12, and calculate the correlation between each historical production parameter data and output data based on the new historical production parameter data and output data obtained in S12 through the following formula:

[0058]

[0059] Among them, x i is the historical production parameter data of the i-th batch; y i is the output data corresponding to the historical production parameter data of the i-th batch; and are the average values ​​of historical production parameter data and output data respectively; n is the number of batches; r is the correlation between historical production parameter data and output data.

[0060] The correlation between each historical production parameter and the yield rate and production efficiency in each production link is calculated through the above S11 to S13. If the correlation between the historical production parameter and the yield rate exceeds the preset threshold, the corresponding production parameter is determined to be the first parameter; if the correlation between the historical production parameter and the production efficiency exceeds the preset threshold, the production parameter is determined to be the second parameter. For example, in the above-mentioned component manufacturing link, the production parameter related to the production efficiency is: cooling time; the production parameters related to the yield rate are: temperature, pressure, cooling time. It should be noted here that there may be partial overlap between the first parameter and the second parameter.

[0061] S20: Obtain the production duration data of each production link within a preset time, and perform a time series pattern analysis on the production duration data corresponding to each production link in combination with the production parameters to determine the bottleneck production link.

[0062] Further, in some embodiments of the present application, the obtaining of the production duration data of each of the production links within a preset time, combining the production parameters, performing a time series pattern analysis on the production duration data corresponding to each of the production links, and determining the bottleneck production link, includes:

[0063] Determine available production equipment corresponding to the production link according to the production parameters;

[0064] Calculating a first production speed of the available production equipment corresponding to the production link according to the production duration data;

[0065] Calculating a second production speed of the corresponding production link according to the number of available production equipment of the production link and the first production speed;

[0066] The production link with the second smallest production speed is determined as the bottleneck production link.

[0067] Since the faulty equipment may still be able to participate in production although it is faulty, but it will produce a large number of unusable parts, the available production equipment is first determined, and the actual production speed of each available production equipment in each production link is dynamically calculated through the real-time collected production time data. Combined with the number of available production equipment in the current production link, the overall production speed of the corresponding production link is re-determined, thereby accurately identifying the actual bottleneck production link in the dynamic production environment, improving the dynamic adaptability of the production system, and further improving the accuracy of subsequent production parameter optimization.

[0068] Preferably, in some embodiments of the present application, the bottleneck production link can be determined by the following preferred implementation steps:

[0069] S21: obtaining an average time taken by each production device to process one production operation within a preset time, and using the average time as a unit time of one production operation, thereby obtaining a first production speed of each production device;

[0070] S22: After the available production equipment of each production link is determined, only the first production speed of the available production equipment is used, and the second production speed of the corresponding production link is determined according to the parallel and serial processing relationship of the available production equipment. The specific steps include S221 to S222:

[0071] S221: When multiple available production equipment are in a serial processing relationship, the smallest first production speed among them is taken as the first production speed of the multiple available production equipment; when multiple available production equipment are in a parallel processing relationship, the parallel available production equipment is regarded as a virtual available production equipment, and the sum of the first production speeds of the parallel available production equipment is taken as the first production speed of the virtual available production equipment;

[0072] S222: Repeat S221 until only serially available production equipment (including virtual available production equipment) or only one available production equipment is left in the production link, and the first production speed finally obtained is used as the second production speed of the production link.

[0073] S23: When the second production speed of a production link is smaller, it means that the time period required for the production link to execute a production operation of this link is longer, so the production link with the smallest second production speed is determined as the bottleneck production link.

[0074] Furthermore, in some embodiments of the present application, determining the available production equipment corresponding to the production link according to the production parameters includes:

[0075] Inputting the production parameters of each production equipment in the production link into the decision tree of the corresponding production link in sequence to obtain the classification result of the corresponding production equipment; the decision tree is obtained by training the historical production parameters of the corresponding production link;

[0076] When the classification result is normal, the corresponding production equipment is determined to be available production equipment.

[0077] Because decision trees can not only ensure the accuracy of classification results when facing simple classification problems, but also have the characteristics of high computational efficiency, historical data can enable decision trees to accurately identify abnormal production parameters under different faults, thereby accurately and quickly identifying faulty equipment in dynamic production links, improving the accuracy of subsequent bottleneck production link identification and the stability of production control.

[0078] Preferably, in some embodiments of the present application, the available production equipment can be determined by the following preferred implementations:

[0079] S24: establishing corresponding decision trees for different production equipment separately, using the production parameters corresponding to the production equipment as input features and whether the production equipment fails as the output target;

[0080] S25: The relevant production parameter data of the production equipment that failed within a preset time (e.g., one week) are included in the training set, and the warm_start parameter in the Scikit-learn library is used to continue training based on the original decision tree to improve the accuracy and adaptability of the decision tree model.

[0081] S30: judging whether the bottleneck production link has reached the maximum production load according to the second parameter corresponding to the bottleneck production link.

[0082] Further, in some embodiments of the present application, judging whether the bottleneck production link has reached the maximum production load according to the second parameter corresponding to the bottleneck production link includes:

[0083] Calculating a third production speed of the bottleneck production link according to the second parameter;

[0084] When the difference between the second production speed and the third production speed of the bottleneck production link is less than or equal to a preset threshold, it is determined that the bottleneck production link has reached the maximum production load.

[0085] Since the second production speed is the real production speed calculated according to the actual number of available production equipment, and the third production speed is the theoretical production speed calculated according to the production parameters, when the second production speed of the bottleneck production link is close to the third production speed, the bottleneck link is at a state close to full load, which also means that the production speed of each production link has reached the maximum production speed under the current production conditions. This load determination method provides a clear basis for subsequent optimization of production parameters, thereby maximizing the production efficiency of the entire production line.

[0086] Preferably, in some embodiments of the present application, the following method can be used to accurately determine whether the bottleneck production link has reached the maximum production load:

[0087] S31: Calculating the actual second production speed of the bottleneck production link according to S221 to S222;

[0088] S32: Calculate the theoretical third production speed of the bottleneck production link according to the second parameter. Specifically, the third production speed can be calculated through S321 to S322:

[0089] S321: determining the time taken for the production operation performed by each production device in the corresponding production link according to the second parameter, and obtaining a theoretical fourth production speed of each production device;

[0090] S322: According to the method from S221 to S222, the second speed is replaced by the fourth production speed to obtain the third production speed of the bottleneck production link;

[0091] S33: Since the actual collected time data is used in S221 to S222, and the second parameter used in S321 to S322 is collected in the available equipment and the value is actually the same as the manually set parameter, the second production speed may be due to production fluctuations (such as the bearings of the conveyor belt are not lubricated in time, resulting in a difference between the set speed and the actual speed, or the parameter settings of other production links cause the production rhythm of the bottleneck production link to be disrupted). There is a certain difference from the theoretical third production speed. Therefore, when the second production speed is close enough to the third production speed, it means that the bottleneck link has reached the maximum production load.

[0092] S40: If the bottleneck production link reaches the maximum production load, the first parameters corresponding to each of the production links are optimized through a multi-objective optimization algorithm until the yield rate of each of the production links meets the preset conditions; otherwise, the second parameters corresponding to each of the production links are optimized through a single-objective optimization algorithm until the bottleneck production link reaches the maximum production load.

[0093] Further, in some embodiments of the present application, if the bottleneck production link reaches the maximum production load, the first parameter corresponding to each of the production links is optimized by a multi-objective optimization algorithm until the yield rate of each of the production links meets a preset condition, including:

[0094] Taking the second parameter existing in the first parameter in each of the production links as a fixed parameter;

[0095] Initializing a preset regression analysis model according to the fixed parameters to obtain a first fitness function for calculating the yield rate of the corresponding production link; the regression analysis model is obtained by training the historical production parameters and yield rate data of the corresponding production link;

[0096] Optimizing all the first fitness functions through the multi-objective optimization algorithm to obtain multiple Pareto solutions;

[0097] From all the Pareto solutions, the Pareto solution with the maximum yield rate in the bottleneck production link is selected, and the optimal first parameter of each of the production links is determined based on the Pareto solution with the maximum yield rate.

[0098] Preferably, in some embodiments of the present application, the step of constructing the fitness function of the multi-objective optimization algorithm can be performed by the following preferred implementations:

[0099] S41: Assume that the first fitness function of the component manufacturing link is currently constructed, wherein the first parameters include: mold temperature, pressure, cooling time, and the cooling time is also the second parameter, so the second parameter is fixed and only the other first parameters are optimized;

[0100] S42: Obtain a regression analysis model corresponding to the component manufacturing link, and initialize the regression analysis model using the currently acquired second parameter to obtain a first fitness function for calculating the yield rate of the component manufacturing link:

[0101] Q=β0+β1x1+β2x2+β3x3

[0102] Among them, x1 and x2 are the casting temperature and pressure in the first parameter, which are variables; x3 is the cooling time, which is a fixed quantity initialized according to the collected production data; β0, β1, β2 and β3 are regression coefficients obtained by fitting the historical production parameters and yield data of the component manufacturing link; Q is the yield.

[0103] S43: According to the method of S41 to S42, the first fitness function of each production link is obtained, and each first parameter is optimized through a multi-objective optimization algorithm, such as NSGA-Ⅱ, NSGA-Ⅲ algorithm, etc., to obtain several Pareto solutions, each Pareto solution is composed of the first parameters that need to be decided after each optimization.

[0104] Further, in some embodiments of the present application, the optimizing the second parameter corresponding to each of the production links by a single-objective optimization algorithm until the bottleneck production link reaches the maximum production load includes:

[0105] According to the second parameters of the other production links, constructing the timing constraints between the production links;

[0106] Constructing a second fitness function for calculating a third production speed of the bottleneck production link according to the second parameter of the bottleneck production link;

[0107] According to the timing constraint, a penalty term is added to the second fitness function, and the second fitness function is optimized through the single-objective optimization algorithm to obtain the optimal second parameters of each of the production links.

[0108] Preferably, in some embodiments of the application, the second fitness function can be constructed by the following preferred implementation:

[0109] S44: Constructing a function F(X) to calculate the third production speed of the bottleneck production link according to S321 to S322 ′ );

[0110] S45: According to the execution order of different production links and the specified maximum execution time, establish corresponding timing constraints and set corresponding penalty coefficients, specifically:

[0111]

[0112] Among them, P is the penalty term; α iand μ i are the penalty coefficients of the corresponding constraints; m is the number of production links; S i and E i are the start and end time points of the i-th production link; T i and T i,max The production time and the maximum allowed production time of the i-th production link;

[0113] S46: The function F(X ′ ) is added to the penalty term P of S45 to obtain the second fitness function.

[0114] Furthermore, in some embodiments of the present application, after optimizing the second parameter corresponding to each of the production links through a single-objective optimization algorithm, it also includes: fixing the second parameter corresponding to each of the production links, and optimizing the first parameter corresponding to each of the production links through a multi-objective optimization algorithm until the yield rate of each of the production links meets the preset conditions.

[0115] After optimizing the second parameters corresponding to each production link, the first parameters are optimized by fixing the second parameters, so that the yield rate is improved without affecting the production efficiency, thereby achieving stable and efficient production scheduling and significantly improving the robustness and scalability of the production system.

[0116] Preferably, in some embodiments of the present application, since the first parameters may include the second parameters, after optimizing the second parameters corresponding to each of the production links through the single-objective optimization algorithm, it is necessary to further fix the second parameters in the first parameters, that is, fix all the second parameters, and optimize the remaining first parameters until the yield rate of each of the production links meets the preset conditions.

[0117] In summary, a medical device production control method provided by an embodiment of the present application has the following beneficial effects: due to a dynamic production environment, when the production environment changes, the current bottleneck production link may change. Therefore, the bottleneck production link can be identified in real time through actual production time data, which can provide accurate basis for subsequent production parameter optimization in a timely manner; in addition, the processing rhythm of the bottleneck production link will affect the processing efficiency of the entire production line, and it is necessary to optimize the production parameters of the bottleneck production link more carefully, otherwise the entire production rhythm will be disrupted. The present application divides the production parameters into two categories, prioritizes the optimization of the second parameter related to the production rhythm, so that the workload of the bottleneck production link is maximized, and then fixes the second parameter and optimizes the first parameter, thereby reducing the complexity of the multi-parameter optimization problem; finally, the present application starts with the production parameters and the bottleneck production link. Even if some production equipment fails to shut down or is updated during the production process, as long as it is the same function production equipment with the same production parameters, there is no need to adjust the control process, thereby improving the generalization of the overall control method.

[0118] Embodiment 2

[0119] refer to Figure 2 , a medical device production control device provided in an embodiment of the present application, includes: a data acquisition module 11, a bottleneck calculation module 12, a first judgment module 13 and a first execution module 14.

[0120] Further, in some embodiments of the present application, the data acquisition module 11 is used to collect production parameters of each production link; wherein the production parameters include: a first parameter and a second parameter; the first parameter is obtained by calculating the correlation between each of the production parameters and the yield rate by the Pearson correlation coefficient method; the second parameter is obtained by calculating the correlation between each of the production parameters and the production efficiency by the Pearson correlation coefficient method; the bottleneck calculation module 12 is used to obtain the production time data of each of the production links within a preset time, and perform a time series pattern analysis on the production time data corresponding to each of the production links in combination with the production parameters to determine the bottleneck production link; the first judgment module 13 is used to judge whether the bottleneck production link has reached the maximum production load according to the second parameter corresponding to the bottleneck production link; the first execution module 14 is used to optimize the first parameter corresponding to each of the production links through a multi-objective optimization algorithm if the bottleneck production link reaches the maximum production load, until the yield rate of each of the production links meets the preset conditions; otherwise, optimize the second parameter corresponding to each of the production links through a single-objective optimization algorithm until the bottleneck production link reaches the maximum production load.

[0121] It can be understood that the above-mentioned device item embodiments correspond to the method item embodiments of the present invention. A medical device production control device provided by the embodiment of the present invention can implement any method item embodiment of the present invention, that is, the medical device production control method provided in embodiment one.

[0122] In summary, a medical device production control device provided by an embodiment of the present application has the following beneficial effects: due to a dynamic production environment, when the production environment changes, the current bottleneck production link may change. Therefore, the bottleneck production link can be identified in real time through actual production time data, which can provide accurate basis for subsequent production parameter optimization in a timely manner; in addition, the processing rhythm of the bottleneck production link will affect the processing efficiency of the entire production line, and it is necessary to optimize the production parameters of the bottleneck production link more carefully, otherwise the entire production rhythm will be disrupted. The present application divides the production parameters into two categories, prioritizes the optimization of the second parameter related to the production rhythm, so that the workload of the bottleneck production link is maximized, and then fixes the second parameter and optimizes the first parameter, thereby reducing the complexity of the multi-parameter optimization problem; finally, the present application starts with the production parameters and the bottleneck production link. Even if some production equipment fails to shut down or is updated during the production process, as long as it is the same function production equipment with the same production parameters, there is no need to adjust the control process, thereby improving the generalization of the overall control method.

[0123] Embodiment 3

[0124] Based on the above-mentioned embodiment of the medical device production control method, another embodiment of the present application provides a medical device production control terminal device, which includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the medical device production control method of any embodiment of the present application is implemented.

[0125] Exemplarily, in this embodiment, the computer program may be divided into one or more modules, which are stored in the memory and executed by the processor to complete the present application. The one or more modules may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program in the medical device production control device.

[0126] The medical device production control device may be a computing device such as a desktop computer, a notebook, a PDA, a cloud server, etc. The medical device production control terminal device may include, but is not limited to, a processor and a memory.

[0127] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The processor is the control center of the medical device production control device, and uses various interfaces and lines to connect the various parts of the entire medical device production control device. The memory may be used to store the computer program and / or module, and the processor implements various functions of the medical device production control device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function, etc.; the data storage area may store data created according to the use of the mobile phone, etc. In addition, the memory may include high-speed random access memory and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0128] Embodiment 4

[0129] Based on the above-mentioned embodiments of the medical device production control method, another embodiment of the present application provides a storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the storage medium is located is controlled to execute the medical device production control method of any embodiment of the present application.

[0130] In this embodiment, the storage medium is a computer-readable storage medium, and the computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium may be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0131] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the scope of protection of the present application. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A medical device production control method, characterized in that: include: Collecting production parameters of each production link; wherein the production parameters include: a first parameter and a second parameter; the first parameter is obtained by calculating the correlation between each production parameter and the yield rate through the Pearson correlation coefficient method; the second parameter is obtained by calculating the correlation between each production parameter and the production efficiency through the Pearson correlation coefficient method; Acquire the production duration data of each production link within a preset time, and perform a time series pattern analysis on the production duration data corresponding to each production link in combination with the production parameters to determine the bottleneck production link; According to the second parameter corresponding to the bottleneck production link, determining whether the bottleneck production link has reached the maximum production load; If the bottleneck production link reaches the maximum production load, the first parameters corresponding to each of the production links are optimized through a multi-objective optimization algorithm until the yield rate of each of the production links meets the preset conditions; otherwise, the second parameters corresponding to each of the production links are optimized through a single-objective optimization algorithm until the bottleneck production link reaches the maximum production load.

2. A medical device production control method as claimed in claim 1, characterized in that: The obtaining of the production duration data of each production link within a preset time, combining the production parameters, performing a time series pattern analysis on the production duration data corresponding to each production link, and determining the bottleneck production link, includes: Determine available production equipment corresponding to the production link according to the production parameters; Calculating a first production speed of the available production equipment corresponding to the production link according to the production duration data; Calculating a second production speed of the corresponding production link according to the number of available production equipment of the production link and the first production speed; The production link with the second smallest production speed is determined as the bottleneck production link.

3. A medical device production control method as claimed in claim 2, characterized in that: The step of determining available production equipment corresponding to the production link according to the production parameters includes: Inputting the production parameters of each production equipment in the production link into the decision tree of the corresponding production link in sequence to obtain the classification result of the corresponding production equipment; the decision tree is obtained by training the historical production parameters of the corresponding production link; When the classification result is normal, the corresponding production equipment is determined to be available production equipment.

4. A medical device production control method as claimed in claim 2, characterized in that: The step of judging whether the bottleneck production link has reached the maximum production load according to the second parameter corresponding to the bottleneck production link includes: Calculating a third production speed of the bottleneck production link according to the second parameter; When the difference between the second production speed and the third production speed of the bottleneck production link is less than or equal to a preset threshold, it is determined that the bottleneck production link has reached the maximum production load.

5. A medical device production control method as claimed in claim 1, characterized in that: If the bottleneck production link reaches the maximum production load, the first parameter corresponding to each production link is optimized by a multi-objective optimization algorithm until the yield rate of each production link meets the preset conditions, including: Taking the second parameter existing in the first parameter in each of the production links as a fixed parameter; Initializing a preset regression analysis model according to the fixed parameters to obtain a first fitness function for calculating the yield rate of the corresponding production link; the regression analysis model is obtained by training the historical production parameters and yield rate data of the corresponding production link; Optimizing all the first fitness functions through the multi-objective optimization algorithm to obtain multiple Pareto solutions; From all the Pareto solutions, the Pareto solution with the maximum yield rate in the bottleneck production link is selected, and the optimal first parameter of each of the production links is determined based on the Pareto solution with the maximum yield rate.

6. A medical device production control method as claimed in claim 1, characterized in that: The optimizing the second parameter corresponding to each of the production links by a single-objective optimization algorithm until the bottleneck production link reaches the maximum production load includes: According to the second parameters of the other production links, constructing the timing constraints between the production links; Constructing a second fitness function for calculating a third production speed of the bottleneck production link according to the second parameter of the bottleneck production link; According to the timing constraint, a penalty term is added to the second fitness function, and the second fitness function is optimized through the single-objective optimization algorithm to obtain the optimal second parameters of each of the production links.

7. A medical device production control method as claimed in claim 1, characterized in that: After optimizing the second parameter corresponding to each of the production links through a single-objective optimization algorithm, it also includes: fixing the second parameter corresponding to each of the production links, and optimizing the first parameter corresponding to each of the production links through a multi-objective optimization algorithm until the yield rate of each of the production links meets the preset conditions.

8. A medical device production control device, characterized in that: include: A data collection module, a bottleneck calculation module, a first judgment module and a first execution module; Wherein, the data acquisition module is used to collect production parameters of each production link; wherein, the production parameters include: a first parameter and a second parameter; the first parameter is obtained by calculating the correlation between each of the production parameters and the yield rate by the Pearson correlation coefficient method; the second parameter is obtained by calculating the correlation between each of the production parameters and the production efficiency by the Pearson correlation coefficient method; The bottleneck calculation module is used to obtain the production time data of each production link within a preset time, and perform a time series pattern analysis on the production time data corresponding to each production link in combination with the production parameters to determine the bottleneck production link; The first judgment module is used to judge whether the bottleneck production link has reached the maximum production load according to the second parameter corresponding to the bottleneck production link; The first execution module is used to optimize the first parameters corresponding to each of the production links through a multi-objective optimization algorithm if the bottleneck production link reaches the maximum production load until the yield rate of each of the production links meets the preset conditions; otherwise, optimize the second parameters corresponding to each of the production links through a single-objective optimization algorithm until the bottleneck production link reaches the maximum production load.

9. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a medical device production control method as described in any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute a medical device production control method as described in any one of claims 1 to 7.

Images