Medical device production scheduling optimization system and method based on artificial intelligence

Abstract

The artificial intelligence-based medical device production scheduling optimization system and method provided in the present application relate to the field of data processing technology, obtain real-time and updated production information of the medical device production line, identify the handover nodes of the production line, and obtain key handover nodes; decompose the tasks of the key handover nodes; input the decomposed tasks into the handover scheduling optimization model for analysis, and obtain the handover scheduling strategy for production scheduling optimization, which solves the technical problem that the production scheduling in the medical device production process cannot update the production information in real time, resulting in inaccurate handover node identification, slow response speed, difficulty in efficiently and accurately processing the configuration tasks and production rhythm on the production line, resulting in the technical problem that equipment utilization and product quality cannot be guaranteed, and achieves the technical effect of improving the response speed and accuracy of production scheduling, ensuring the continuity and efficiency of the production process, and significantly improving the overall operation efficiency of the production line and product quality.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to an artificial intelligence-based medical device production scheduling optimization system and method. Background Art

[0002] With the increase in global medical needs and the rapid advancement of technology, the production of medical devices must also keep pace with the times. Against this background, the medical device manufacturing industry has shifted from traditional production models to more automated and intelligent production processes. However, with the continuous expansion of production scale and the complexity of process flow, the production scheduling process of medical devices faces more and more challenges. Traditional medical device production scheduling methods mainly rely on manual experience for equipment arrangement and process management. This method often fails to meet the high efficiency, precision and safety requirements of modern industrial production in terms of control accuracy, response speed and system stability. For example, when production items are frequently changed on the production line, traditional scheduling methods may lead to low production efficiency, insufficient resource utilization, and even affect the quality of the final product due to untimely information updates or insufficient optimization of scheduling strategies.

[0003] In summary, the existing technology in the medical device production process has the problem that production scheduling cannot update production information in real time, resulting in inaccurate handover node identification and slow response speed. It is difficult to efficiently and accurately handle the configuration tasks and production rhythm on the production line, resulting in technical problems such as equipment utilization and product quality cannot be guaranteed. Summary of the invention

[0004] The present application provides an artificial intelligence-based medical device production scheduling optimization system and method, which is used to solve the technical problems in the prior art of medical device production process, that is, the production scheduling cannot update the production information in real time, resulting in inaccurate handover node identification, slow response speed, difficulty in efficiently and accurately processing the configuration tasks and production rhythm on the production line, resulting in the inability to guarantee equipment utilization and product quality.

[0005] In view of the above problems, the present application provides a medical device production scheduling optimization system and method based on artificial intelligence.

[0006] In a first aspect of the present application, a medical device production scheduling optimization system based on artificial intelligence is provided, the system comprising:

[0007] Real-time information acquisition module, used to obtain real-time production information of medical device production lines;

[0008] An update information acquisition module is used to obtain updated production information of the medical device production line; a handover node identification module is used to identify the handover nodes of the medical device production line according to the real-time production information and the updated production information, and obtain key handover nodes, wherein the handover node is the node where the production of the same production line switches from an old type of device to a new type of device; a task decomposition module is used to decompose the key handover nodes and obtain multiple decomposed tasks, wherein the multiple decomposed tasks include at least equipment control tasks, production line debugging tasks, tool replacement tasks and parameter control tasks; a model analysis module is used to input the multiple decomposed tasks into a handover scheduling optimization model, analyze the multiple decomposed tasks according to the handover scheduling optimization model, and obtain an optimized handover scheduling strategy; a production scheduling optimization module is used to optimize the production scheduling of the medical device production line according to the handover scheduling strategy.

[0009] The second aspect of the present application provides a method for optimizing production scheduling of medical devices based on artificial intelligence, the method comprising:

[0010] Acquire real-time production information of a medical device production line; acquire updated production information of the medical device production line; identify handover nodes of the medical device production line based on the real-time production information and the updated production information, and acquire key handover nodes, wherein a handover node is a node where production of an old type of device is switched to a new type of device on the same production line; decompose tasks of the key handover nodes to acquire multiple decomposed tasks, wherein the multiple decomposed tasks include at least equipment control tasks, production line debugging tasks, tool replacement tasks, and parameter control tasks; input the multiple decomposed tasks into a handover scheduling optimization model, analyze the multiple decomposed tasks according to the handover scheduling optimization model, and acquire an optimized handover scheduling strategy; the medical device production line performs production scheduling optimization according to the handover scheduling strategy.

[0011] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0012] The artificial intelligence-based medical device production scheduling optimization system provided by the present application obtains real-time production information of the medical device production line; obtains updated production information of the medical device production line; identifies the handover nodes of the medical device production line according to the real-time production information and the updated production information, and obtains key handover nodes, wherein the handover nodes are nodes where the production of the same production line switches from an old type of device to a new type of device; decomposes the key handover nodes to obtain multiple decomposed tasks, wherein the multiple decomposed tasks include at least equipment control tasks, production line debugging tasks, tool replacement tasks, and parameter control tasks; and inputs the multiple decomposed tasks into the handover scheduling optimization system. In the optimization model, the multiple decomposed tasks are analyzed according to the handover scheduling optimization model to obtain the optimized handover scheduling strategy; the medical device production line performs production scheduling optimization according to the handover scheduling strategy, which solves the technical problems that the production scheduling in the prior art in the medical device production process cannot update the production information in real time, resulting in inaccurate handover node identification, slow response speed, difficulty in efficiently and accurately processing the configuration tasks and production rhythm on the production line, resulting in the technical problem that equipment utilization and product quality cannot be guaranteed, and achieves the technical effect of improving the response speed and accuracy of production scheduling, ensuring the continuity and efficiency of the production process, and significantly improving the overall operation efficiency of the production line and product quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A schematic diagram of the structure of an artificial intelligence-based medical device production scheduling optimization system provided in an embodiment of the present application.

[0014] Figure 2 A flowchart of an artificial intelligence-based medical device production scheduling optimization method provided in an embodiment of the present application.

[0015] Explanation of reference numerals: real-time information acquisition module 11 , update information acquisition module 12 , handover node identification module 13 , task decomposition module 14 , model analysis module 15 . DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0017] Embodiment 1, as Figure 1 As shown, the present application provides a medical device production scheduling optimization system based on artificial intelligence, the system comprising:

[0018] The real-time information acquisition module 11 is used to acquire the real-time production information of the medical device production line.

[0019] Specifically, a large-scale medical device manufacturing plant has a variety of equipment on its production line, each of which is used to produce a specific type of medical device. These equipment must operate efficiently to produce a variety of medical devices, such as pacemakers, artificial joints, and surgical tools. However, due to the ever-changing market demand, production plans need to be adjusted frequently, including equipment conversion, maintenance, and optimization of the production process. In this scenario, the AI-based medical device production scheduling optimization system runs through an integrated software and hardware platform, using sensors to collect real-time production line data, such as equipment status, production rate, and quality control parameters. These data are transmitted to the central processing unit via a high-speed network, and are analyzed by artificial intelligence algorithms to give node control strategies to improve scheduling accuracy and efficiency.

[0020] The medical device production scheduling optimization system based on artificial intelligence includes a real-time information acquisition module, an update information acquisition module, a handover node identification module, a task decomposition module, a model analysis module, and a production scheduling optimization module. Among them, the real-time information acquisition module is used to continuously capture real-time production data on the production line to ensure that all subsequent analysis and decisions are based on the latest and most accurate information. Specifically, the real-time information acquisition module is mainly responsible for monitoring various key parameters on the medical device production line, such as production speed, equipment status, product quality, and raw material consumption. This module is implemented through sensors and data acquisition systems. Sensors are deployed at key nodes of the production line to capture real-time data on equipment operations. The data acquisition system is responsible for collecting data from these sensors and converting it into a format that can be used for further processing.

[0021] Assuming that the production line is producing pacemakers and plans to switch to the production of blood glucose testing equipment, the real-time information acquisition module will continuously monitor the final node stage of the currently produced pacemakers and collect real-time quality control data of the finished products, equipment operating speed, and the remaining amount of raw materials. These data are essential for deciding when and how to start a smooth transition to the next product. In addition, the real-time information acquisition module can also monitor the maintenance status of the equipment and possible fault warnings. These data can help the production management team make scheduling decisions in advance and avoid production interruptions, thereby ensuring the continuity and efficiency of the production process.

[0022] In summary, the real-time information acquisition module not only provides the necessary data support for the optimization of medical device production scheduling, but also significantly improves the response speed and accuracy of production scheduling through real-time monitoring and data analysis, ensuring the efficiency of the production process and the consistency of product quality. In this way, the entire production process is optimized, minimizing the time and resource losses caused by production switching.

[0023] The update information acquisition module 12 is used to acquire the updated production information of the medical device production line.

[0024] The update information acquisition module focuses on capturing information that has changed or been updated compared to existing data. It not only monitors all data, but also filters out data points that have changed. These data are particularly important for decision-making and scheduling. They can identify key change points and obtain the best time for the handover of new and old products in the production process. The update information acquisition module directly connects to various sensors and control systems on the production line to collect data on equipment operating status, production speed, etc. in real time, and iteratively updates these data to ensure the real-time nature of dynamic information. These data are the basis for efficient scheduling and real-time response. The acquisition of updated production information not only ensures the real-time update of production data, but also supports the efficient operation and management of the production line through accurate data analysis, significantly improving production efficiency and product quality.

[0025] The handover node identification module 13 is used to identify the handover nodes of the medical device production line according to the real-time production information and the updated production information, and obtain key handover nodes, wherein the handover node is the node where the production of the same production line switches from the old type of device to the new type of device.

[0026] The handover node identification module is mainly responsible for identifying the key moment when the old type of instrument parts are switched to the new type of instrument parts during the production process. Specifically, the handover node identification module first receives data from the real-time information acquisition module and the update information acquisition module. This step ensures that all relevant production information can be comprehensively considered and provides data support for the accurate identification of the handover point. Next, the module uses the data analysis algorithm to process the received information and identify potential handover nodes on the production line, which usually involves complex pattern recognition and prediction technologies, such as machine learning models, which are trained to identify specific signals for the conversion from old products to new products. Once the potential handover nodes are predicted, the system will further analyze the importance and urgency of these nodes and screen out the key handover nodes, which usually involves multiple factors, such as the potential cost of production delays, the complexity of product replacement, and previous historical data. Among them, the handover node refers to the specific operation point or moment in the production process when the production of the old type of instrument parts is switched to the production of the new type of instrument parts; and the key handover node is the handover node that has a greater impact on production efficiency and product quality, and its optimization is the key to improving production efficiency and reducing costs. Ultimately, the identified critical handover nodes will be used to optimize production scheduling. Specific optimization strategies may include adjusting production speed, rearranging production sequence, or modifying production line configuration to ensure optimal efficiency and minimal loss in production switching.

[0027] The handover node identification module plays a core role in ensuring smooth transition of the production line and optimizing production scheduling. This module not only improves the continuity and efficiency of the production process, but also helps to reduce time and resource waste in production, thereby significantly improving the performance and output quality of the entire production line.

[0028] The task decomposition module 14 is used to decompose the key handover node into tasks and obtain multiple decomposed tasks, wherein the multiple decomposed tasks at least include equipment control tasks, production line debugging tasks, tool replacement tasks and parameter control tasks.

[0029] The task decomposition module is responsible for breaking down the identified key handover nodes into specific and actionable subtasks to ensure that each step can be completed efficiently and accurately. Specifically, the task decomposition module first receives the information of the key handover nodes from the handover node identification module, which includes the time of the node, the equipment involved, the expected operation tasks, etc. This step is the premise of task decomposition and ensures that all necessary data are ready. Next, based on the received key handover node information, the operation requirements of each node are decomposed into multiple specific tasks, including equipment control tasks, production line debugging tasks, tool replacement tasks, and parameter control tasks, where each task is designed for specific operation requirements and goals. Furthermore, in order to improve efficiency, each decomposed task will be further optimized to ensure that it is completed in the shortest time with the least resources. In addition, these tasks will be scheduled at the appropriate time point in the entire production scheduling to avoid any conflicts or delays in production. At the same time, the results of task execution will be continuously fed back to the task decomposition module, and necessary adjustments will be made to subsequent tasks based on the actual execution situation, which ensures the flexibility of the production process and the rapid response to emergencies.

[0030] The task decomposition module not only improves the accuracy and efficiency of the production process, but also increases the adaptability to production changes, thereby significantly improving the performance and output quality of the entire production line.

[0031] The model analysis module 15 is used to input the multiple decomposed tasks into the handover scheduling optimization model, analyze the multiple decomposed tasks according to the handover scheduling optimization model, and obtain the optimized handover scheduling strategy.

[0032] The model analysis module is responsible for inputting multiple decomposed tasks received from the task decomposition module into the handover scheduling optimization model, and analyzing these tasks to formulate the optimal handover scheduling strategy. Specifically, the model analysis module first receives the decomposed tasks output by the task decomposition module, which include equipment control tasks, production line debugging tasks, tool change tasks, and parameter control tasks. After receiving, the module integrates these task data for further analysis and optimization. The integrated task data is input into the handover scheduling optimization model, which is designed based on machine learning or other advanced algorithms and can adjust its parameters based on historical data and real-time feedback to improve the accuracy and efficiency of decision-making.

[0033] In the model analysis phase, the module uses the optimization model to evaluate different scheduling strategies, taking into account multiple dimensions such as time efficiency, cost, and resource allocation, and finds the best production scheduling strategy through algorithm analysis to ensure the smooth handover process and maximize production efficiency. Once the optimal handover scheduling strategy is determined, the model analysis module outputs this strategy to the production management system, and the production line then adjusts operations according to these strategies, such as adjusting the production line speed, rearranging the production sequence, or replacing necessary tools and equipment.

[0034] The model analysis module significantly improves the efficiency and effectiveness of medical device production scheduling. The module ensures the scientific nature and timeliness of production scheduling decisions, greatly reduces delays and costs in the production process, and improves the overall performance and output quality of the production line.

[0035] The production scheduling optimization module 16 is used for optimizing the production scheduling of the medical device production line according to the handover scheduling strategy.

[0036] The production scheduling optimization module is responsible for implementing the handover scheduling strategy proposed by the model analysis module. This module ensures that the operation of the production line is fully in line with the optimized scheduling plan to improve overall production efficiency and product quality. Specifically, the production scheduling optimization module first receives the optimized handover scheduling strategy from the model analysis module. Before implementation, the module verifies the rationality and feasibility of these strategies to ensure that they match the current production line capacity and resource status. Then, the resources are reconfigured and adjusted according to the received strategy, including but not limited to the reconfiguration of equipment, adjustment of production line speed, and necessary human resource allocation. This step is the key to ensure the effective implementation of the strategy. Once the resource allocation is completed, the production scheduling optimization module begins to adjust the operation of the production line according to the optimization strategy, such as changing the production sequence, adjusting the production rhythm, or starting the operation of specific equipment. In addition, during the implementation of the optimization strategy, the module continuously monitors the performance and output of the production line, and any deviation from expectations will be quickly identified and adjusted as needed. At the same time, the implementation results will be input into the model analysis module as feedback for further optimization of future strategies.

[0037] The production scheduling optimization module ensures efficient and precise operation of the medical device production line. This module not only achieves a high degree of automation and optimization of the production process, but also ensures that the production system can flexibly respond to various production needs and emergencies through continuous monitoring and feedback mechanisms. This systematic optimization method has greatly improved production efficiency and product quality, bringing significant competitive advantages to the medical device manufacturing industry.

[0038] Furthermore, the handover node identification is performed on the medical device production line to obtain key handover nodes, and the handover node identification module is also used to:

[0039] Obtain N production nodes of the medical device production line.

[0040] Differential production information is obtained according to the real-time production information and the updated production information.

[0041] According to the difference production information, correlation analysis is performed on the N production nodes to determine the relevant Handover nodes, among which, ;

[0042] From the said Filter in the handover nodes handover nodes are output as key handover nodes, where .

[0043] Specifically, the system first obtains real-time data of N production nodes from the production line. These data include the operating status, output, operating parameters, etc. of each node. Then, the collected real-time production information is analyzed to identify production information that has changed significantly compared to the updated production information. The key to this step is to determine which production nodes show significant changes in production parameters or performance, indicating nodes that may need to be optimized or adjusted. Correlation analysis is performed on the identified production nodes with changes to determine which of these nodes are related to each other, and then determine which are related. This process involves analyzing the data connections between nodes, such as the flow of raw materials, energy consumption distribution, etc., to identify the key handover nodes in the production process. The key handover nodes refer to the nodes that have a decisive impact on the overall production efficiency and product quality in the production process, and are usually the focus of resource allocation and process control. Next, from the relevant Nodes are further filtered out Nodes are considered key handover nodes. The screening criteria include the node’s impact range, production interruption risk, and contribution to production efficiency. and The relationship follows , to ensure that all selected key nodes are necessary.

[0044] By systematically collecting and analyzing production line data, we can not only identify the key handover nodes in the production process, but also formulate specific optimization strategies for these nodes, thereby improving production efficiency and reducing potential production risks. The application of this method can significantly improve the management level and operational efficiency in complex production environments.

[0045] Furthermore, from the Filter in the handover nodes A handover node, the handover node identification module is further used for:

[0046] Regarding the Each node in the handover node performs equipment status evaluation, usage time evaluation and tooling change evaluation, and outputs the equipment status evaluation results, usage time evaluation results and tooling change evaluation results according to the equipment status evaluation results, usage time evaluation results and tooling change evaluation results. The probability of an impact.

[0047] According to the impact probability, filter out those with a greater than preset impact probability A handover node.

[0048] Optional, yes A detailed assessment is conducted on each node, including but not limited to equipment status assessment, usage time assessment, and tooling change assessment. This assessment aims to determine the potential impact and criticality of each node for further screening. The equipment status assessment refers to analyzing the current working condition of the equipment, including but not limited to its performance stability, failure rate, and maintenance history; the usage time assessment refers to calculating the total time that the equipment runs without major maintenance or failure intervention to assess its reliability and the urgency of replacement or maintenance; and the tooling change assessment is to analyze the frequency and complexity of tooling replacement on the production line, especially the impact of tooling replacement on production efficiency in a multi-product production environment. Based on the above assessment results, an impact probability is calculated for each node. This probability reflects the possibility that the node will affect the entire production process due to changes in technology or operational requirements during the production process. The calculation of the impact probability may take into account multiple factors, such as the aging of the equipment, frequent maintenance needs, or the criticality of production efficiency. Further, from Among the evaluated nodes, select the nodes with a probability greater than the preset threshold according to the impact probability of each node. Nodes, which are the nodes that need the most attention and optimization in the conversion process from old products to new products, because they have a decisive impact on ensuring production quality and efficiency. Among them, the preset impact probability can be set based on actual conditions and is not specifically limited here.

[0049] Through the above steps, not only the effective management of key nodes in the production process is ensured, but also the overall performance and output quality of the production line are enhanced through a scientific evaluation and screening process. This systematic methodology helps to significantly improve production efficiency and reduce production delays caused by node problems.

[0050] Furthermore, the handover node identification module further includes:

[0051] The expression for the influence probability identification of each handover node is as follows:

[0052] ;

[0053] in, is the handover probability, It indicates that the equipment status of the old type of equipment is evaluated by the equipment utilization rate and usage time of the old type of equipment. is the utilization rate of the i-th device of the old type of equipment, is the total usage time of the i-th device of the old type of equipment, and n is the number of devices of the old type of equipment.

[0054] It indicates that the equipment status of new types of equipment is evaluated by the equipment utilization rate and usage time of new types of equipment. is the utilization rate of the jth device of the new type of equipment, The total usage time of the jth device of the new type of equipment, m is the number of devices of the new type of equipment.

[0055] It represents the total time required to switch from an old type of instrument to a new type of instrument. is the replacement time of the kth tool, The number of tools that need to be replaced.

[0056] For example, define the impact probability , affecting the probability Based on equipment utilization , Usage time , and equipment replacement time Calculated, the formula is defined by the following equation: Where n represents the number of old equipment, m represents the number of new equipment, and p represents the number of tools that need to be replaced. For each old equipment i, calculate its utilization rate The product of the old equipment utilization rate and its own utilization rate is added up as part of the numerator, which reflects the overall impact of the old equipment's usage intensity on production handover. Further, the usage time of all old equipment is accumulated as part of the denominator and the average utilization of new equipment The time required to change all tooling Finally, the impact probability is calculated comprehensively, and the impact of the old equipment is multiplied by the ratio of the replacement time of the new equipment, and the final impact probability is obtained after integration. , used to evaluate the criticality of the handover nodes in the production process. Among them, the utilization rate Refers to the ratio of the actual working time of the equipment within the operable time to the total available time, which reflects the workload of the equipment; usage time It refers to the cumulative operating time of the equipment without major maintenance or failure. It is usually used to evaluate the durability and maintenance needs of the equipment. Characterizes the time required to change or adjust tooling during production, which directly affects the downtime and efficiency of the production line; Impact probability It is a quantitative indicator used to evaluate the influence of the handover node in the production line. A value of 0 indicates that the node has a greater potential impact on the stability and continuity of the production process.

[0057] Through the above calculations, a scientific calculation framework is provided for understanding and optimizing the key handover nodes in the production process, which helps to accurately evaluate and manage the use and replacement strategies of equipment, thereby improving production efficiency and reducing downtime caused by equipment handover. The application of this method can significantly improve the operating efficiency and output quality of the production line, especially in a highly variable production environment where equipment needs to be replaced frequently.

[0058] Furthermore, the multiple decomposed tasks are input into the handover scheduling optimization model, and the multiple decomposed tasks are analyzed according to the handover scheduling optimization model. The model analysis module is also used to:

[0059] An initial population is generated, wherein each individual in the initial population represents a handover scheduling strategy.

[0060] The fitness of the initial population is calculated according to the fitness function, and a sign handover scheduling strategy with a fitness greater than a preset fitness is selected to perform a crossover operation to obtain a crossover population.

[0061] Introduce random changes to mutate the handover scheduling strategy in the crossover population, repeat iterations until a preset iteration round is met, output the handover scheduling strategy corresponding to the first fitness under the preset iteration round, and output the optimized handover scheduling strategy.

[0062] Optionally, the model analysis module first generates an initial population, in which each individual represents a potential handover scheduling strategy. These strategies are set based on the multiple tasks decomposed in the previous step, aiming to cover as wide a combination of strategies as possible so as to find the optimal solution. Then, the fitness of each strategy in the initial population is calculated. The fitness function is designed based on the possible execution effect of the strategy in practical applications, taking into account factors such as production efficiency, resource utilization, cost control, etc. Only those strategies with fitness higher than the preset threshold will be selected for the next genetic operation. The selected strategies generate a new population through crossover operations. During the crossover process, the characteristics of the two strategies (such as the execution order of tasks, resource allocation, etc.) are partially exchanged, aiming to combine the advantages of the parent generation and produce offspring with potentially better performance. At the same time, in order to increase the diversity of the population and avoid local optimality, random changes are introduced for mutation operations, which involves randomly modifying certain parameters of the individuals after the crossover, such as adjusting the execution time or resource allocation of specific tasks. Mutation can help explore the strategy space not covered by the previous step. The above process is repeated for multiple iterations. After each iteration, the fitness of individuals in the population is evaluated, and genetic operations and mutations are continued. The iteration continues until the preset iteration rounds are met, and finally the handover scheduling strategy with the highest fitness is output.

[0063] The model analysis module effectively improves the overall efficiency and effectiveness of production scheduling by using genetic algorithms to optimize the handover scheduling strategy, ensuring the efficiency and adaptability of the production process. The implementation of this method significantly improves the operational flexibility and response speed of the production line, bringing important competitive advantages to the medical device manufacturing industry.

[0064] Furthermore, the model analysis module also includes:

[0065] The fitness calculation of the initial population according to the fitness function includes evaluating the handover downtime, resource utilization and production quality index of each handover scheduling strategy.

[0066] By performing information entropy calculation on the handover downtime, the resource utilization rate and the production quality index, a fitness calculation result is output.

[0067] Furthermore, when performing fitness calculations, relevant data of each individual in the initial population, that is, each handover scheduling strategy, is collected first. These data cover the impact of the strategy on the three performance indicators of handover downtime, resource utilization, and production quality. Among them, the handover downtime refers to the evaluation of the non-operating time of the production line caused by each strategy. Shorter downtime usually means higher production efficiency; the resource utilization refers to the analysis of the efficiency of each strategy in the use of production resources (such as machines, workers, raw materials, etc.). High resource utilization means that resources are used to the greatest extent and waste is reduced; and the production quality index refers to the measurement of the impact of each strategy on the quality of the final product. High quality indicators indicate lower defect rates and rework rates.

[0068] Next, the information entropy is calculated for the three calculated indicator data to obtain the final fitness calculation results. Information entropy is a statistical measure used to represent the uncertainty and randomness of variables. Here, it is used to measure the variation and distribution of various performance indicators in different strategies. Information entropy is calculated for the handover downtime, resource utilization, and production quality indicators of each strategy to quantify the uncertainty of each strategy in the expected performance. Lower information entropy values ​​indicate more stable performance and higher predictability. Based on the information entropy results, the model analysis module calculates the comprehensive fitness of each strategy. Strategies with higher fitness indicate better performance in reducing handover downtime, improving resource utilization, and ensuring production quality.

[0069] Strategies with low information entropy and high fitness are selected for further genetic algorithm operations, such as crossover and mutation.

[0070] Through the above steps, the model analysis module not only accurately calculates the fitness of each handover scheduling strategy, but also introduces information entropy as a tool to evaluate the stability and reliability of the strategy, making the production scheduling optimization process more scientific and accurate.

[0071] Furthermore, after obtaining the updated production information, the update information obtaining module is further used to:

[0072] Enter multiple medical device production lines.

[0073] Acquire multiple real-time production information corresponding to the multiple medical device production lines.

[0074] A plurality of difference production information is acquired by analyzing each piece of the plurality of real-time production information with the updated production information.

[0075] A plurality of difference indicators are obtained according to the plurality of difference production information.

[0076] A first handover production line corresponding to the updated production information is selected according to the multiple difference indicators, and the difference indicator of the first handover production line is the largest value among the multiple difference indicators.

[0077] The first handover production line is used as the handover production line for updating production information to perform production scheduling optimization.

[0078] Specifically, the update information acquisition module first enters the information of multiple medical device production lines into the system, including the basic configuration of each production line, the current production task, and the expected production output. Real-time production information is collected from each production line, which covers key parameters such as the production line's operating status, production speed, and product quality. Then, the collected real-time production information is compared and analyzed with the existing updated production information to identify any changes or anomalies in the production process, and the results of the analysis are used as differential production information, which highlights the areas that need attention or possible intervention in the production process. Next, the difference indicators of each production line are calculated based on the differential production information. These indicators quantify the degree of deviation from the standard production parameters, such as production delays, increased resource consumption rates, or increased product defect rates. The difference indicators of all production lines are evaluated, and the production line with the largest difference indicator is selected as the first handover production line, which indicates that the production status of this production line is the most different from the expected, and urgent scheduling optimization may be required. Finally, the selected first handover production line is selected as the key optimization object, and the production scheduling is adjusted according to its specific difference indicators to solve the identified problems and optimize production efficiency and product quality.

[0079] The updated information acquisition module ensures real-time monitoring and rapid response in the production process through advanced data analysis, making the entire production system more intelligent and responsive, significantly improving production efficiency and product quality. The implementation of this method not only optimizes production scheduling, but also enhances the company's ability to respond to emergencies in the production process.

[0080] Through the technical solutions of the above-mentioned embodiments, the artificial intelligence-based medical device production scheduling optimization system provided by the present application solves the technical problems that the existing technology has problems in the production process of medical devices, such as the inability of production scheduling to update production information in real time, resulting in inaccurate handover node identification, slow response speed, and difficulty in efficiently and accurately processing configuration tasks and production rhythm on the production line, resulting in equipment utilization and product quality cannot be guaranteed. It achieves the technical effect of improving the response speed and accuracy of production scheduling, ensuring the continuity and efficiency of the production process, and thus significantly improving the overall operating efficiency of the production line and product quality.

[0081] Embodiment 2 is based on the same inventive concept as the medical device production scheduling optimization system based on artificial intelligence in the previous embodiment. Figure 2 As shown, the embodiment of the present application provides a medical device production scheduling optimization method based on artificial intelligence, the method comprising:

[0082] Get real-time production information for medical device production lines.

[0083] Obtain updated production information of the medical device production line.

[0084] According to the real-time production information and the updated production information, the handover nodes of the medical device production line are identified to obtain key handover nodes, wherein the handover nodes are nodes where the production of the same production line switches from an old type of device to a new type of device.

[0085] The key handover node is task-decomposed to obtain a plurality of decomposed tasks, wherein the plurality of decomposed tasks at least include an equipment control task, a production line debugging task, a tool replacement task, and a parameter control task.

[0086] The multiple decomposed tasks are input into a handover scheduling optimization model, and the multiple decomposed tasks are analyzed according to the handover scheduling optimization model to obtain an optimized handover scheduling strategy.

[0087] The medical device production line performs production scheduling optimization according to the handover scheduling strategy.

[0088] Furthermore, the handover nodes of the medical device production line are identified to obtain key handover nodes, and the method includes:

[0089] Obtain N production nodes of the medical device production line.

[0090] Differential production information is obtained according to the real-time production information and the updated production information.

[0091] According to the difference production information, correlation analysis is performed on the N production nodes to determine the relevant Handover nodes, among which, .

[0092] From the said Filter in the handover nodes handover nodes are output as key handover nodes, where .

[0093] Furthermore, from the Filter in the handover nodes The handover node includes:

[0094] Regarding the Each node in the handover node performs equipment status evaluation, usage time evaluation and tooling change evaluation, and outputs the equipment status evaluation results, usage time evaluation results and tooling change evaluation results according to the equipment status evaluation results, usage time evaluation results and tooling change evaluation results. The probability of an impact.

[0095] According to the impact probability, filter out those with a greater than preset impact probability A handover node.

[0096] Furthermore, the expression for identifying the influence probability of each handover node is as follows:

[0097] ;

[0098] in, is the handover probability, It indicates that the equipment status of the old type of equipment is evaluated by the equipment utilization rate and usage time of the old type of equipment. is the utilization rate of the i-th device of the old type of equipment, is the total usage time of the i-th device of the old type of equipment, and n is the number of devices of the old type of equipment.

[0099] It indicates that the equipment status of new types of equipment is evaluated by the equipment utilization rate and usage time of new types of equipment. is the utilization rate of the jth device of the new type of equipment, The total usage time of the jth device of the new type of equipment, m is the number of devices of the new type of equipment.

[0100] It represents the total time required to switch from an old type of instrument to a new type of instrument. is the replacement time of the kth tool, The number of tools that need to be replaced.

[0101] Further, the multiple decomposed tasks are input into a handover scheduling optimization model, and the multiple decomposed tasks are analyzed according to the handover scheduling optimization model. The method includes:

[0102] An initial population is generated, wherein each individual in the initial population represents a handover scheduling strategy.

[0103] The fitness of the initial population is calculated according to the fitness function, and a sign handover scheduling strategy with a fitness greater than a preset fitness is selected to perform a crossover operation to obtain a crossover population.

[0104] Introduce random changes to mutate the handover scheduling strategy in the crossover population, repeat iterations until a preset iteration round is met, output the handover scheduling strategy corresponding to the first fitness under the preset iteration round, and output the optimized handover scheduling strategy.

[0105] Furthermore, the fitness of the initial population is calculated according to the fitness function, including evaluating the handover downtime, resource utilization and production quality indicators of each handover scheduling strategy.

[0106] By performing information entropy calculation on the handover downtime, the resource utilization rate and the production quality index, a fitness calculation result is output.

[0107] Further, after obtaining the updated production information, the method includes:

[0108] Enter multiple medical device production lines.

[0109] Acquire multiple real-time production information corresponding to the multiple medical device production lines.

[0110] A plurality of difference production information is acquired by analyzing each piece of the plurality of real-time production information with the updated production information.

[0111] A plurality of difference indicators are obtained according to the plurality of difference production information.

[0112] A first handover production line corresponding to the updated production information is selected according to the multiple difference indicators, and the difference indicator of the first handover production line is the largest value among the multiple difference indicators.

[0113] The first handover production line is used as the handover production line for updating production information to perform production scheduling optimization.

[0114] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. The processes depicted in the accompanying drawings do not necessarily require the specific order and continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0115] 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 spirit and principles of the present application shall be included in the protection scope of the present application.

[0116] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. The medical device production scheduling optimization system based on artificial intelligence is characterized by: The system comprises: Real-time information acquisition module, used to obtain real-time production information of medical device production lines; An updated information acquisition module, used to acquire updated production information of the medical device production line; A handover node identification module, used to identify the handover nodes of the medical device production line according to the real-time production information and the updated production information, and obtain key handover nodes, wherein the handover node is a node where the production of the same production line switches from an old type of device to a new type of device; A task decomposition module, used to decompose the key handover node to obtain multiple decomposed tasks, wherein the multiple decomposed tasks at least include equipment control tasks, production line debugging tasks, tool replacement tasks and parameter control tasks; A model analysis module, used for inputting the plurality of decomposed tasks into a handover scheduling optimization model, analyzing the plurality of decomposed tasks according to the handover scheduling optimization model, and obtaining an optimized handover scheduling strategy; A production scheduling optimization module, used for optimizing the production scheduling of the medical device production line according to the handover scheduling strategy; Wherein, the handover node identification module is also used for: Obtain N production nodes of the medical device production line; Acquire differential production information according to the real-time production information and the updated production information; According to the difference production information, correlation analysis is performed on the N production nodes to determine the relevant Handover nodes, among which, ; From the said Filter in the handover nodes handover nodes are output as key handover nodes, where ; Wherein, the handover node identification module is also used for: Regarding the Each node in the handover node performs equipment status evaluation, usage time evaluation and tooling change evaluation, and outputs the equipment status evaluation results, usage time evaluation results and tooling change evaluation results according to the equipment status evaluation results, usage time evaluation results and tooling change evaluation results. Probability of impact; According to the impact probability, filter out those with a greater than preset impact probability Handover nodes; Wherein, the handover node identification module further includes: The expression for the influence probability identification of each handover node is as follows: ； in, is the handover probability, It indicates that the equipment status of the old type of equipment is evaluated by the equipment utilization rate and usage time of the old type of equipment. is the utilization rate of the i-th device of the old type of equipment, is the total usage time of the i-th device of the old type of equipment, and n is the number of devices of the old type of equipment; It indicates that the equipment status of new types of equipment is evaluated by the equipment utilization rate and usage time of new types of equipment. is the utilization rate of the jth device of the new type of equipment, The total usage time of the jth device of the new type of equipment, m is the number of devices of the new type of equipment; It represents the total time required to switch from an old type of instrument to a new type of instrument. is the replacement time of the kth tool, The number of tools that need to be replaced.

2. The artificial intelligence-based medical device production scheduling optimization system according to claim 1, characterized in that: The model analysis module is also used for: Generate an initial population, wherein each individual in the initial population represents a handover scheduling strategy; Calculating the fitness of the initial population according to the fitness function, selecting a sign handover scheduling strategy with a fitness greater than a preset fitness to perform a crossover operation, and obtaining a crossover population; Introduce random changes to mutate the handover scheduling strategy in the crossover population, repeat iterations until a preset iteration round is met, output the handover scheduling strategy corresponding to the first fitness under the preset iteration round, and output the optimized handover scheduling strategy.

3. The artificial intelligence-based medical device production scheduling optimization system according to claim 2, characterized in that: The model analysis module also includes: The fitness calculation of the initial population according to the fitness function includes evaluating the handover downtime, resource utilization and production quality index of each handover scheduling strategy; By performing information entropy calculation on the handover downtime, the resource utilization rate and the production quality index, a fitness calculation result is output.

4. The artificial intelligence-based medical device production scheduling optimization system according to claim 1, characterized in that: The update information acquisition module is also used for: Enter multiple medical device production lines; Acquire multiple real-time production information corresponding to the multiple medical device production lines; Analyze each piece of real-time production information in the plurality of real-time production information and the updated production information to obtain a plurality of difference production information; Acquire multiple difference indicators according to the multiple difference production information; Selecting a first handover production line corresponding to the updated production information according to the multiple difference indicators, wherein the difference indicator of the first handover production line is the largest value among the multiple difference indicators; The first handover production line is used as the handover production line for updating production information to perform production scheduling optimization.

5. The medical device production scheduling optimization method based on artificial intelligence is characterized by: The method is applied to the artificial intelligence-based medical device production scheduling optimization system according to any one of claims 1 to 4, and the method comprises: Obtain real-time production information of medical device production lines; Obtaining updated production information of the medical device production line; According to the real-time production information and the updated production information, the handover node of the medical device production line is identified to obtain key handover nodes, wherein the handover node is a node where the production of the same production line switches from an old type of device to a new type of device; Decomposing the key handover node into tasks to obtain a plurality of decomposed tasks, wherein the plurality of decomposed tasks at least include a device control task, a production line debugging task, a tool replacement task, and a parameter control task; Inputting the multiple decomposed tasks into a handover scheduling optimization model, analyzing the multiple decomposed tasks according to the handover scheduling optimization model, and obtaining an optimized handover scheduling strategy; The medical device production line performs production scheduling optimization according to the handover scheduling strategy.

Images