A medical instrument production process quality closed-loop management method and system

Abstract

The application discloses a kind of medical instrument production process quality closed loop management and control method and system, it is related to manufacturing process control technical field, including, acquisition medical instrument production process in multi-source data, and based on historical production state information establishes quality memory state, obtains production quality state data, based on production quality state data to the change trend of quality state is analyzed, determines quality defect evolution state, and generates quality risk prediction result;According to quality risk prediction result, risk influence propagation analysis is carried out to associated production process parameter, determines the key process parameter and parameter influence relationship leading to quality risk change, generates corresponding production process quality regulation strategy based on key process parameter and parameter influence relationship.The application improves the accuracy and stability of production process quality control by constructing a quality risk evolution prediction mechanism based on quality memory state.

Description

Technical Field

[0001] This invention relates to the field of manufacturing process control technology, and in particular to a method and system for closed-loop quality control in the production process of medical devices. Background Technology

[0002] As the medical device manufacturing industry moves towards digitalization, intelligence, and integration, the production process is gradually shifting from traditional manual management to intelligent manufacturing based on information systems. Currently, technologies such as Manufacturing Execution Systems (MES), Statistical Process Control (SPC), and the Industrial Internet are widely used in the quality management of medical device production. These technologies, by configuring data acquisition units in production equipment, testing equipment, and environmental monitoring equipment, acquire real-time equipment operating parameters, process execution parameters, environmental status parameters, and product testing results during the production process. Data analysis methods are then used to monitor the production process status, enabling the identification of abnormal production conditions and the control of quality fluctuations.

[0003] However, existing quality control technologies in medical device manufacturing processes typically rely on currently collected production status data or historical statistical data for quality status assessment. They primarily focus on whether current process parameters are within set ranges and whether the final product test results meet quality requirements. However, they lack effective methods to characterize the defect evolution process resulting from the cumulative changes in quality status over time during production. Because medical devices require high production precision, involve complex processes, and have a continuous quality formation process, some quality anomalies are not directly caused by parameter fluctuations at a single moment, but rather by the gradual accumulation of status changes across multiple production stages. Furthermore, existing technologies, after identifying quality risks, usually adjust based on the degree of parameter deviation, making it difficult to further identify the transmission paths of quality risk changes between different process parameters and the contribution of each parameter to the formation of quality risks. This leaves room for improvement in the targeted nature of control strategies. Summary of the Invention

[0004] In view of the aforementioned existing problems, the present invention is proposed.

[0005] Therefore, this invention provides a closed-loop quality control method for the medical device manufacturing process, which solves the problems of difficulty in accurately predicting the evolution of quality status and insufficient identification of risk transmission in process parameters during the medical device manufacturing process.

[0006] To solve the above-mentioned technical problems, the present invention provides the following technical solution: In a first aspect, the present invention provides a closed-loop quality control method for the medical device manufacturing process, comprising, Collect multi-source data during the medical device manufacturing process, establish a quality memory state based on historical production status information, obtain production quality status data, analyze the changing trend of quality status based on production quality status data, determine the evolution state of quality defects, and generate quality risk prediction results. Based on the quality risk prediction results, risk impact propagation analysis is conducted on related production process parameters to identify key process parameters that lead to changes in quality risk and their influence relationships. Based on the key process parameters and their influence relationships, corresponding production process quality control strategies are generated. Collect information on changes in production status after the implementation of quality control strategies, determine the quality control feedback results based on the changes in production status, update the quality memory state based on the quality control feedback results, and adjust the quality control strategies based on the updated quality memory state.

[0007] As a preferred embodiment of the closed-loop quality control method for the medical device manufacturing process described in this invention, the step of collecting multi-source data during the medical device manufacturing process and establishing a quality memory state based on historical production status information to obtain production quality status data includes the following steps: Collect equipment operation data, process execution data, environmental status data, and product quality testing data during the medical device manufacturing process as multi-source production data; Preprocess and extract state features from multi-source production data to establish a set of state features for different production stages; Acquire information on process status changes and corresponding quality results during the historical production of medical devices, and establish a quality memory association between historical production status and quality results; Based on the quality memory association information, the current production state characteristics are integrated with the historical production state characteristics to generate the quality memory state; By associating and integrating the set of production status features with the quality memory status, production quality status data can be obtained.

[0008] As a preferred embodiment of the closed-loop quality control method for the medical device manufacturing process described in this invention, the step of analyzing the changing trend of quality status based on production quality status data, determining the evolution state of quality defects, and generating quality risk prediction results includes the following steps: Temporal features are extracted from production quality status data to obtain the variation characteristics of quality status parameters at different production times, and a quality status change feature sequence is constructed. Based on the feature sequence of quality state changes, the direction, magnitude and rate of quality state changes are extracted to generate quality state evolution features. By matching the evolution characteristics of quality status with the status characteristics of historical quality defect formation process, the evolution status of quality defects in the production process can be determined. Based on the evolution of quality defects, assess the risk of the current production state turning into a quality anomaly state, and generate quality risk prediction results.

[0009] As a preferred embodiment of the closed-loop quality control method for the medical device manufacturing process described in this invention, the step of performing risk impact propagation analysis on related production process parameters based on quality risk prediction results to determine the key process parameters leading to changes in quality risk and the parameter impact relationships includes the following steps: Obtain the set of production process parameters corresponding to the quality risk prediction results, extract the state features of each production process parameter, and obtain the process parameter state set. Based on the set of process parameter states, the parameter change characteristics of different process parameters during the quality state change process are extracted to determine the parameter nodes that characterize the transmission of risk impact. Based on the association direction of state changes and the order of risk transmission between different parameter nodes, construct risk propagation edges between parameter nodes; A process parameter risk propagation network is generated based on parameter nodes and risk propagation edges. Based on the process parameter risk propagation network, we analyze the impact characteristics of each parameter node on changes in quality risk and identify the key process parameters that lead to changes in quality risk. Based on the node positions and risk propagation edges of key process parameters in the process parameter risk propagation network, the parameter influence relationships between key process parameters are generated.

[0010] As a preferred embodiment of the closed-loop quality control method for the medical device manufacturing process described in this invention, the step of generating a corresponding production process quality control strategy based on key process parameters and their influence relationships includes the following steps: Based on the key process parameters and their influence relationships, determine the parameter control targets and control directions corresponding to changes in quality risks; Based on the parameter control object and control direction, obtain the deviation characteristics between the current state information of the corresponding process parameters and the target quality state, and generate parameter adjustment requirements; Based on the parameter adjustment requirements and the degree of influence of key process parameters in the risk propagation process, determine the control priority and parameter adjustment amount of each key process parameter; Based on the controlled priorities and parameter adjustments, a quality control strategy for the medical device manufacturing process is generated and sent to the production control terminal for execution.

[0011] As a preferred embodiment of the closed-loop quality control method for the medical device manufacturing process described in this invention, the step of collecting production status change information after implementing the quality control strategy and determining the quality control feedback result based on the production status change information includes the following steps: Acquire the status data of the medical device production process after the implementation of the quality control strategy, and extract the change information of the corresponding production status parameters before and after the implementation of the control to generate production status change information; Based on information on changes in production status, the parameter response characteristics of key process parameters during the control process are obtained, and the status change characteristics after quality control are determined. By comparing the characteristics of state changes with the target quality state corresponding to the quality control strategy, the degree of quality state improvement and the evaluation results of the control effect are determined. Based on the evaluation results of the regulation effect, quality regulation feedback results that characterize the effectiveness of the quality regulation strategy are generated.

[0012] As a preferred embodiment of the closed-loop quality control method for the medical device manufacturing process described in this invention, the step of updating the quality memory state based on the quality control feedback result and adjusting the quality control strategy according to the updated quality memory state includes the following steps: Obtain the evaluation information of the control effect from the quality control feedback results, and extract the characteristics of the production status changes before and after the implementation of the quality control strategy to generate quality feedback feature information; Based on the quality feedback feature information, the parameters affecting the historical state in the quality memory state are corrected, and the quality memory state is updated. Based on the updated quality memory state, the state mapping information between the current production state and the changes in quality risk is reconstructed to obtain optimized quality state representation information. Based on the optimized quality status characterization information, the configuration of control parameters in the original quality control strategy is adjusted to generate an updated quality control strategy.

[0013] Secondly, this invention provides a closed-loop quality control system for the medical device manufacturing process, comprising, The multi-source data acquisition module collects equipment operating status, process execution status, environmental status, and quality inspection data during the medical device production process to obtain multi-source data during the production process. The quality memory construction module extracts quality change characteristics based on historical production status information and establishes quality memory states that characterize the impact of historical states. The quality evolution prediction module extracts quality change trends from production quality status data, determines the evolution status of quality defects, and generates quality risk prediction results. The parameter propagation and identification module constructs the production process parameter risk propagation path based on the quality risk prediction results and identifies key process parameters that affect changes in quality risk. The quality strategy generation module generates production process quality control strategies for quality risks based on key process parameters and their impact information. The feedback and evaluation module collects information on changes in production status after the implementation of quality control strategies and generates quality control feedback results that characterize the control effect. The closed-loop update module corrects the quality memory state based on the quality control feedback results and adjusts subsequent quality control strategies.

[0014] Thirdly, the present invention provides a computer device including a memory and a processor, wherein the memory stores a computer program, wherein when the computer program is executed by the processor, it implements any step of the medical device manufacturing process quality closed-loop control method as described in the first aspect of the present invention.

[0015] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the closed-loop quality control method for the medical device manufacturing process as described in the first aspect of the present invention.

[0016] The beneficial effects of this invention are as follows: By collecting multi-source state data during the medical device manufacturing process and constructing a quality memory state based on historical production state information, the production quality state data can comprehensively represent the current production state and the impact of historical processes, improving the completeness of the quality state representation of the production process; by extracting time-series features from the production quality state data, constructing a quality state change feature sequence, and generating quality risk prediction results based on the evolution of quality defects, the invention enables early identification of the trend of quality anomalies, improving the ability to predict quality risks in the production process; by constructing a process parameter risk propagation network, determining key process parameters and their influence relationships, the invention enables accurate identification of the sources and propagation paths of quality risks, providing a reliable basis for the formulation of subsequent control strategies; by combining the control priority of key process parameters and parameter adjustment needs to generate quality control strategies, the invention achieves precise process control for quality risks, improving the adaptability of production process control; by collecting information on changes in production state after control and generating quality control feedback results, the invention further corrects the quality memory state and optimizes the quality control strategy, achieving dynamic adjustment of the production process quality control strategy and improving the stability and effectiveness of closed-loop quality management in the medical device manufacturing process. Attached Figure Description

[0017] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a flowchart of a closed-loop quality control method for the medical device manufacturing process.

[0019] Figure 2 This is a schematic diagram of a closed-loop quality control system for the medical device manufacturing process.

[0020] Figure 3 Establish a flowchart for multi-source data acquisition and quality memory status.

[0021] Figure 4 Generate a flowchart for the quality control strategy. Detailed Implementation

[0022] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0023] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0024] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0025] Reference Figures 1-4 This is one embodiment of the present invention, which provides a method for closed-loop quality control in the production process of medical devices, including the following steps: Collect multi-source data during the medical device manufacturing process, establish a quality memory state based on historical production status information, obtain production quality status data, analyze the changing trend of quality status based on production quality status data, determine the evolution state of quality defects, and generate quality risk prediction results.

[0026] Specifically, data on equipment operation, process execution, environmental conditions, and product quality testing during the medical device manufacturing process are collected as multi-source production data. The equipment operating status data includes equipment operating time, operating load, and equipment vibration status; Process execution parameter data includes processing temperature, pressure, speed, and execution time; Environmental status data includes temperature, humidity, and cleanliness of the production area; Product testing data includes dimensional testing results, performance testing results, and appearance testing results.

[0027] Preprocess and extract state features from multi-source production data to establish a set of state features for different production stages; The production process of medical devices is divided into stages, and state features that characterize changes in production status are extracted from the data corresponding to each production stage. For the processing and shaping stage, extract the characteristics of equipment operation stability, process parameter fluctuation, and processing response; For the testing phase, extract the characteristics of changes in product quality. Based on the state characteristics corresponding to each production stage, a set of state features containing state information of different production stages is constructed.

[0028] Acquire information on process status changes and corresponding quality results during the historical production of medical devices, and establish a quality memory association between historical production status and quality results; Acquire information on temperature changes, pressure changes, and equipment operating status changes during the production process of each batch of medical devices, and associate them with quality results information such as dimensional deviations and performance abnormalities of the products in that batch; Based on the influence relationship between the characteristics of historical production status changes and quality results, quality memory association information describing the impact of historical production status on current quality status is established.

[0029] Based on the quality memory association information, the current production state characteristics are integrated with the historical production state characteristics to generate the quality memory state; Obtain the production status characteristics corresponding to the current production stage, and retrieve the historical production status characteristics that match the current production status based on the quality memory association information; Based on the degree of influence of historical production state characteristics on current production state, the current state characteristics and historical state characteristics are fused together. If changes in equipment status or process parameters occur in the current production process that are similar to the formation stage of historical quality anomalies, the influence weight of the corresponding historical status characteristics will be increased.

[0030] By associating and integrating the set of production status features with the quality memory status, production quality status data can be obtained. Among them, the production state feature set represents the real-time state changes in the current production process, and the quality memory state represents the impact of the historical production process on the current quality state.

[0031] By collecting multi-source production data, including equipment operation, process execution, environmental conditions, and quality testing during the medical device manufacturing process, comprehensive information on the production process status is obtained, providing a data foundation for quality status identification. Preprocessing and extracting state features from the multi-source production data establishes a set of state features for different production stages, enabling a structured representation of the dynamic state of the production process. Acquiring information on state changes and quality results from historical production processes establishes a quality memory association between historical production states and quality results, allowing for the retention and utilization of historical influencing factors. Finally, by fusing current and historical production state features to generate a quality memory state, and combining this with the set of state features to obtain production quality status data, a comprehensive description of the current production state and historical influencing factors is achieved, providing a reliable data foundation for subsequent prediction of quality defect evolution and closed-loop control of the production process.

[0032] Furthermore, time-series features are extracted from the production quality status data to obtain the variation characteristics of quality status parameters at different production times, and a quality status variation feature sequence is constructed. After obtaining the production quality status data, the production quality status data is sorted according to the time sampling nodes in the medical device production process to generate a data sequence arranged according to the changes in production time. Extract quality status parameters that characterize changes in production status from the production quality status data corresponding to each time point, including equipment operation status parameters, process execution parameters, and product quality inspection parameters; By comparing the changes in quality status parameters between adjacent time points, the characteristics of quality status parameter changes at different production times are obtained, and a sequence of quality status change characteristics is generated by arranging them in chronological order.

[0033] Based on the feature sequence of quality state changes, the direction, magnitude and rate of quality state changes are extracted to generate quality state evolution features. The direction of quality status change is determined based on the increase or decrease of quality status parameters between adjacent time points; The magnitude of the change in mass state is determined based on the degree to which the mass state parameters deviate from the initial state; The rate of change of mass state is determined based on the degree of change of mass state parameters per unit time. Based on information on the direction, magnitude, and rate of change, the dynamic changes in quality status during the production process are characterized, generating quality status evolution characteristics.

[0034] By matching the evolution characteristics of quality status with the status characteristics of historical quality defect formation process, the evolution status of quality defects in the production process can be determined. Acquire data on changes in production status corresponding to quality defects that occurred during the historical production process of medical devices; Extract the equipment operating status, process parameter change status, and product quality change status during the defect formation stage, and establish the status characteristics of the historical quality defect formation process; By comparing the evolution characteristics of the quality state generated in the current production process with the state characteristics of the historical quality defect formation process, the similarity between the current quality state change process and the historical defect formation process can be obtained. If the similarity between the current quality state evolution characteristics and the state characteristics in the formation process of a certain historical quality defect exceeds a preset threshold, then the quality defect evolution state corresponding to the current production process is determined.

[0035] Based on the evolution of quality defects, assess the risk of the current production state turning into a quality anomaly state, and generate quality risk prediction results. Based on the determined quality defect evolution state, obtain information on the development stage of the current production state in the process of quality defect formation; By combining the current quality status evolution characteristics with the changing trends in the historical quality defect formation process, the degree to which the current production status is close to the development of an abnormal quality state can be determined. Generate quality risk prediction results based on the current level of production development; Among them, the quality risk prediction results characterize the trend of quality anomalies in the current production status.

[0036] By extracting temporal features from production quality status data, a feature sequence representing the quality status change process at different production moments is constructed, enabling effective acquisition of dynamic change information in the production process. By extracting evolutionary features such as the direction, magnitude, and rate of quality status change, the trend of quality status change is characterized, providing a process basis for identifying potential quality anomalies. By matching the quality status evolutionary features with the status features in the historical quality defect formation process, the quality defect evolution status is determined, enabling early identification of the quality risk formation process. By assessing the risk level of the current production state turning into a quality anomaly state based on the quality defect evolution status, quality risk prediction results are generated, realizing the transformation from traditional post-event quality inspection to proactive risk prediction in the production process, improving the foresight and reliability of quality risk management in the medical device production process.

[0037] Based on the quality risk prediction results, risk impact propagation analysis is conducted on related production process parameters to identify key process parameters that lead to changes in quality risk and their influence relationships. Based on these key process parameters and their influence relationships, corresponding production process quality control strategies are generated.

[0038] Specifically, the set of production process parameters corresponding to the quality risk prediction results is obtained, and the state features of each production process parameter are extracted to obtain the process parameter state set. Based on the quality risk prediction results, obtain production process parameter information related to the current quality risk changes, and generate a set of production process parameters. The production process parameters include production equipment operating parameters, process execution parameters, and environmental control parameters; Feature extraction is performed on the historical change data and current operating status data corresponding to each production process parameter to obtain the change status information of each parameter in the production process; For example, extracting the trend of process temperature changes, pressure fluctuations, equipment operating stability, and environmental condition changes to form a set of process parameter states.

[0039] Based on the set of process parameter states, the parameter change characteristics of different process parameters during the quality state change process are extracted to determine the parameter nodes that characterize the transmission of risk impact. Based on the set of process parameter states, the variation patterns of different production process parameters during the quality state change process are extracted; Based on the time, magnitude and trend of change of each process parameter, obtain the state change characteristics when each process parameter affects the quality state. Process parameters with quality risk impact characteristics are used as risk propagation nodes, and a set of parameter nodes is constructed based on the risk impact attributes corresponding to the process parameters. Each parameter node represents the state of a process parameter involved in the transmission of quality risk changes.

[0040] Based on the association direction of state changes and the order of risk transmission between different parameter nodes, construct risk propagation edges between parameter nodes; Based on the order of change of different parameter nodes during the quality state change process, the direction of influence transmission between parameter nodes is identified. When a parameter node undergoes a state change, and another parameter node subsequently undergoes a corresponding change, resulting in a change in the quality risk status, a risk transmission path will be established between the two. Based on the risk transmission direction and order between parameter nodes, a risk propagation edge is constructed to describe the relationship of parameter influence transmission.

[0041] A process parameter risk propagation network is generated based on parameter nodes and risk propagation edges. Based on the process parameter risk propagation network, we analyze the impact characteristics of each parameter node on changes in quality risk and identify the key process parameters that lead to changes in quality risk. Obtain the connection relationship, propagation position, and corresponding risk propagation path of each parameter node in the process parameter risk propagation network; When the degree of change in the quality risk status exceeds the set threshold, the corresponding risk transmission path will be identified as the main risk propagation path. The parameter nodes located on the main risk propagation path are the focus of analysis. By combining the upstream and downstream parameter node relationships of each parameter node in the risk propagation process, the parameter nodes that have a continuous impact on the formation of quality risks are identified. The identified parameter nodes are screened, and those that directly participate in the formation of quality risks or can affect multiple risk propagation paths are identified as key process parameters.

[0042] Based on the node positions and risk propagation edges of key process parameters in the process parameter risk propagation network, the parameter influence relationships between key process parameters are generated. Based on the node positions of key process parameters in the process parameter risk propagation network, obtain the risk propagation path between key process parameters; Based on the risk propagation edges connecting the key process parameters, determine the direction of influence and the order of transmission between different key process parameters; Based on the direction of influence and the order of transmission, the parameter influence relationships between key process parameters are generated.

[0043] By constructing a process parameter risk propagation network, the risk transmission path between production process parameters is characterized, revealing the impact of different process parameters on the formation of quality risks and avoiding the problem of making quality judgments based solely on deviations of a single parameter. By calculating the contribution of parameter nodes to changes in quality risk, key process parameters are identified, enabling precise positioning of the main sources of quality risk and reducing the interference of irrelevant parameter adjustments on the production process. By generating parameter influence relationships between key process parameters, more accurate parameter basis is provided for quality control strategies, enabling dynamic optimization of production process control based on actual risk sources and improving the accuracy and adaptability of quality control in medical device manufacturing processes.

[0044] Furthermore, based on key process parameters and their influence relationships, the parameter control targets and control directions corresponding to changes in quality risks are determined; Identify the key process parameters that are located at the starting point of quality risk changes or directly affect the results of quality risk changes, and determine the key process parameters as the objects of parameter control. Obtain the parameter status information of the parameter control object in the current production process, and match the current parameter status change trend with the quality risk change trend; When a change in the state of a parameter leads to an increase in quality risk, the adjustment direction corresponding to that parameter is determined as the direction to reduce risk. When the direction of parameter state change can suppress the change in quality risk, the adjustment direction corresponding to that parameter is determined as the direction of maintaining or enhancing the current state.

[0045] Based on the parameter control object and control direction, obtain the deviation characteristics between the current state information of the corresponding process parameters and the target quality state, and generate parameter adjustment requirements; Based on the difference between the current process parameter state and the corresponding parameter state of the target quality state, determine the direction and degree of deviation of the current state of the parameter control object relative to the target quality state; The direction and degree of deviation are used as deviation characteristics of process parameters; Based on the deviation characteristics and the predetermined parameter control direction, determine whether the current process parameters need to be adjusted, and determine the type of process parameters to be adjusted, the direction of adjustment, and the adjustment requirements.

[0046] Based on the parameter adjustment requirements and the degree of influence of key process parameters in the risk propagation process, determine the control priority and parameter adjustment amount of each key process parameter; Based on the positional relationship of each key process parameter in the risk propagation path, identify the order of the impact of different key process parameters on changes in quality risk; When a critical process parameter is located at the front end of the quality risk propagation path and can affect the status changes of multiple subsequent related parameters, the critical process parameter is identified as the priority control target. When a critical process parameter is located at the end of the risk propagation path or only affects a local production status, it is identified as the target for subsequent control. Based on the order of influence of key process parameters in the risk propagation process, establish the control priority corresponding to each key process parameter; Based on the parameter adjustment requirements corresponding to each key process parameter, obtain the direction and degree of deviation between the current process parameter state and the target quality state, and determine the parameter adjustment amount corresponding to each key process parameter in combination with the control direction of the corresponding key process parameter.

[0047] Based on the controlled priorities and parameter adjustments, a quality control strategy for the medical device manufacturing process is generated and sent to the production control terminal for execution.

[0048] By identifying the control targets and directions corresponding to changes in quality risks based on key process parameters and their influencing relationships, targeted control of quality risk sources is achieved, avoiding ineffective parameter adjustments during production. By acquiring the deviation characteristics between the current state of process parameters and the target quality state, parameter adjustment requirements are generated, accurately representing the degree of deviation in process state and providing a dynamic basis for quality control. By combining the influence of key process parameters in the risk propagation process to determine control priorities and parameter adjustment amounts, a reasonable configuration of multi-parameter control processes is achieved, improving the accuracy and adaptability of quality control strategies. By generating quality control strategies based on control priorities and parameter adjustment amounts and driving execution at the production control end, the effective transformation of quality risk prediction results into production process control actions is realized, improving the initiative and reliability of closed-loop quality control in medical device production processes.

[0049] Collect information on changes in production status after the implementation of quality control strategies, determine the quality control feedback results based on the changes in production status, update the quality memory state based on the quality control feedback results, and adjust the quality control strategies based on the updated quality memory state.

[0050] Specifically, the system acquires the status data of the medical device production process after the implementation of the quality control strategy, extracts the change information of the corresponding production status parameters before and after the implementation of the control strategy, and generates production status change information. Based on information on changes in production status, the parameter response characteristics of key process parameters during the control process are obtained, and the status change characteristics after quality control are determined. By comparing the characteristics of state changes with the target quality state corresponding to the quality control strategy, the degree of quality state improvement and the evaluation results of the control effect are determined. Based on the evaluation results of the regulation effect, quality regulation feedback results that characterize the effectiveness of the quality regulation strategy are generated.

[0051] By acquiring production process status data after the execution of quality control strategies and extracting information on changes in production status parameters before and after control execution, effective acquisition of the response status of the quality control process is achieved, providing data basis for evaluating the control effect. By identifying the response characteristics of key process parameters during the control process, accurate characterization of quality status changes after process parameter adjustments is achieved, facilitating the judgment of the actual effect of control measures on the production process. By comparing the status change characteristics with the target quality status, the degree of quality status improvement and the evaluation results of control effect are determined, achieving an objective evaluation of the effectiveness of the quality control strategy and avoiding blind adjustments due to a lack of feedback basis. By generating quality control feedback results based on the control effect evaluation results, status feedback in the quality control process is realized, providing a basis for subsequent quality memory status updates and control strategy optimization, and improving the stability and continuous optimization capability of closed-loop control in the medical device production process.

[0052] Furthermore, the evaluation information of the control effect in the quality control feedback results is obtained, and the characteristics of the production status change before and after the implementation of the quality control strategy are extracted to generate quality feedback feature information. Based on the quality feedback feature information, the parameters affecting the historical state in the quality memory state are corrected, and the quality memory state is updated. Based on the updated quality memory state, the state mapping information between the current production state and the changes in quality risk is reconstructed to obtain optimized quality state representation information. Based on the optimized quality status characterization information, the configuration of control parameters in the original quality control strategy is adjusted to generate an updated quality control strategy.

[0053] By acquiring the evaluation information of the control effect from the quality control feedback results and extracting the characteristics of production state changes before and after quality control, an effective representation of the actual effect of the control process is achieved, providing feedback basis for the optimization of quality control strategies. By correcting the historical state influence parameters in the quality memory state based on the quality feedback characteristic information, the influence mechanism of historical production states is dynamically updated, enabling the quality state representation to adapt to changes in the production process and improving the accuracy of quality state description. By reconstructing the state mapping information between production state and quality risk changes based on the updated quality memory state, the evolution law of quality risk is continuously optimized, improving the adaptability of subsequent quality risk identification. By adjusting the parameter configuration in the quality control strategy based on the optimized quality state representation information, the control strategy is dynamically optimized with changes in the production process, transforming production quality control from a single adjustment to a continuous feedback optimization process, and improving the stability and intelligence level of closed-loop quality control in the medical device production process.

[0054] This embodiment also provides a closed-loop quality control system for the medical device manufacturing process, including: The multi-source data acquisition module collects equipment operating status, process execution status, environmental status, and quality inspection data during the medical device production process to obtain multi-source data during the production process. The quality memory construction module extracts quality change characteristics based on historical production status information and establishes quality memory states that characterize the impact of historical states. The quality evolution prediction module extracts quality change trends from production quality status data, determines the evolution status of quality defects, and generates quality risk prediction results. The parameter propagation and identification module constructs the production process parameter risk propagation path based on the quality risk prediction results and identifies key process parameters that affect changes in quality risk. The quality strategy generation module generates production process quality control strategies for quality risks based on key process parameters and their impact information. The feedback and evaluation module collects information on changes in production status after the implementation of quality control strategies and generates quality control feedback results that characterize the control effect. The closed-loop update module corrects the quality memory state based on the quality control feedback results and adjusts subsequent quality control strategies.

[0055] This embodiment also provides a computer device applicable to the closed-loop quality control method for medical device manufacturing processes, comprising: a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the closed-loop quality control method for medical device manufacturing processes proposed in the above embodiments.

[0056] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0057] This embodiment also provides a storage medium storing a computer program. When executed by a processor, the program implements the closed-loop quality control method for the medical device manufacturing process as proposed in the above embodiments. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0058] In summary, this invention achieves the following: First, by collecting multi-source state data during the medical device manufacturing process and constructing a quality memory state based on historical production state information, the production quality state data can comprehensively represent the current production state and the impact of historical processes, thus improving the completeness of the production process quality state representation. Second, by extracting temporal features from the production quality state data and constructing a quality state change feature sequence, and generating quality risk prediction results based on the evolution of quality defects, the invention enables early identification of quality anomaly formation trends, improving the ability to predict production process quality risks. Third, by constructing a process parameter risk propagation network and determining key process parameters and their influence relationships, the invention achieves accurate identification of quality risk sources and propagation paths, providing a reliable basis for subsequent control strategy formulation. Fourth, by combining the control priority of key process parameters and parameter adjustment needs to generate quality control strategies, the invention achieves precise process control for quality risks, improving the adaptability of production process control. Fifth, by collecting information on changes in production state after control and generating quality control feedback results, the invention further corrects the quality memory state and optimizes the quality control strategy, achieving dynamic adjustment of the production process quality control strategy and improving the stability and effectiveness of closed-loop quality management in the medical device manufacturing process.

[0059] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A closed-loop quality control method for the medical device manufacturing process, characterized in that: include, Collect multi-source data during the medical device manufacturing process, establish a quality memory state based on historical production status information, obtain production quality status data, analyze the changing trend of quality status based on production quality status data, determine the evolution state of quality defects, and generate quality risk prediction results. Based on the quality risk prediction results, risk impact propagation analysis is conducted on related production process parameters to identify key process parameters that lead to changes in quality risk and their influence relationships. Based on the key process parameters and their influence relationships, corresponding production process quality control strategies are generated. Collect information on changes in production status after the execution of quality control strategies, determine the quality control feedback results based on the changes in production status, update the quality memory state based on the quality control feedback results, and adjust the quality control strategies based on the updated quality memory state.

2. The closed-loop quality control method for the medical device manufacturing process as described in claim 1, characterized in that: The process of collecting multi-source data during the medical device manufacturing process and establishing a quality memory state based on historical production status information to obtain production quality status data includes the following steps: Collect equipment operation data, process execution data, environmental status data, and product quality testing data during the medical device manufacturing process as multi-source production data; Preprocess and extract state features from multi-source production data to establish a set of state features for different production stages; Acquire information on process status changes and corresponding quality results during the historical production of medical devices, and establish a quality memory association between historical production status and quality results; Based on the quality memory association information, the current production state characteristics are integrated with the historical production state characteristics to generate the quality memory state; By associating and integrating the set of production status features with the quality memory status, production quality status data can be obtained.

3. The closed-loop quality control method for the medical device manufacturing process as described in claim 2, characterized in that: The process of analyzing the changing trends of quality status based on production quality status data, determining the evolution state of quality defects, and generating quality risk prediction results includes the following steps: Temporal features are extracted from production quality status data to obtain the variation characteristics of quality status parameters at different production times, and a quality status change feature sequence is constructed. Based on the feature sequence of quality state changes, the direction, magnitude and rate of quality state changes are extracted to generate quality state evolution features. By matching the evolution characteristics of quality status with the status characteristics of historical quality defect formation process, the evolution status of quality defects in the production process can be determined. Based on the evolution of quality defects, assess the risk of the current production state turning into a quality anomaly state, and generate quality risk prediction results.

4. The closed-loop quality control method for the medical device manufacturing process as described in claim 3, characterized in that: The step of conducting risk impact propagation analysis on related production process parameters based on the quality risk prediction results to determine the key process parameters that lead to changes in quality risk and the relationship between these parameters includes the following steps: Obtain the set of production process parameters corresponding to the quality risk prediction results, extract the state features of each production process parameter, and obtain the process parameter state set. Based on the set of process parameter states, the parameter change characteristics of different process parameters during the quality state change process are extracted to determine the parameter nodes that characterize the transmission of risk impact. Based on the association direction of state changes and the order of risk transmission between different parameter nodes, construct risk propagation edges between parameter nodes; A process parameter risk propagation network is generated based on parameter nodes and risk propagation edges. Based on the process parameter risk propagation network, we analyze the impact characteristics of each parameter node on changes in quality risk and identify the key process parameters that lead to changes in quality risk. Based on the node positions and risk propagation edges of key process parameters in the process parameter risk propagation network, the parameter influence relationships between key process parameters are generated.

5. The closed-loop quality control method for the medical device manufacturing process as described in claim 4, characterized in that: The process of generating corresponding production process quality control strategies based on key process parameters and their influence relationships includes the following steps: Based on the key process parameters and their influence relationships, determine the parameter control targets and control directions corresponding to changes in quality risks; Based on the parameter control object and control direction, obtain the deviation characteristics between the current state information of the corresponding process parameters and the target quality state, and generate parameter adjustment requirements; Based on the parameter adjustment requirements and the degree of influence of key process parameters in the risk propagation process, determine the control priority and parameter adjustment amount of each key process parameter; Based on the controlled priorities and parameter adjustments, a quality control strategy for the medical device manufacturing process is generated and sent to the production control terminal for execution.

6. The closed-loop quality control method for the medical device manufacturing process as described in claim 5, characterized in that: The process of collecting and implementing production status change information after executing the quality control strategy, and determining the quality control feedback result based on the production status change information, includes the following steps: Acquire the status data of the medical device production process after the implementation of the quality control strategy, and extract the change information of the corresponding production status parameters before and after the implementation of the control to generate production status change information; Based on information on changes in production status, the parameter response characteristics of key process parameters during the control process are obtained, and the status change characteristics after quality control are determined. By comparing the characteristics of state changes with the target quality state corresponding to the quality control strategy, the degree of quality state improvement and the evaluation results of the control effect are determined. Based on the evaluation results of the regulation effect, quality regulation feedback results that characterize the effectiveness of the quality regulation strategy are generated.

7. The closed-loop quality control method for the medical device manufacturing process as described in claim 6, characterized in that: The process of updating the quality memory state based on the quality control feedback result and adjusting the quality control strategy according to the updated quality memory state includes the following steps: Obtain the evaluation information of the control effect from the quality control feedback results, and extract the characteristics of the production status changes before and after the implementation of the quality control strategy to generate quality feedback feature information; Based on the quality feedback feature information, the parameters affecting the historical state in the quality memory state are corrected, and the quality memory state is updated. Based on the updated quality memory state, the state mapping information between the current production state and the changes in quality risk is reconstructed to obtain optimized quality state representation information. Based on the optimized quality status characterization information, the configuration of control parameters in the original quality control strategy is adjusted to generate an updated quality control strategy.

8. A closed-loop quality control system for medical device manufacturing process, based on the closed-loop quality control method for medical device manufacturing process according to any one of claims 1 to 7, characterized in that: include, The multi-source data acquisition module collects equipment operating status, process execution status, environmental status, and quality inspection data during the medical device production process to obtain multi-source data during the production process. The quality memory construction module extracts quality change characteristics based on historical production status information and establishes quality memory states that characterize the impact of historical states. The quality evolution prediction module extracts quality change trends from production quality status data, determines the evolution status of quality defects, and generates quality risk prediction results. The parameter propagation and identification module constructs the production process parameter risk propagation path based on the quality risk prediction results and identifies key process parameters that affect changes in quality risk. The quality strategy generation module generates production process quality control strategies for quality risks based on key process parameters and their impact information. The feedback and evaluation module collects information on changes in production status after the implementation of quality control strategies and generates quality control feedback results that characterize the control effect. The closed-loop update module corrects the quality memory state based on the quality control feedback results and adjusts subsequent quality control strategies.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the closed-loop quality control method for the medical device manufacturing process as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the closed-loop quality control method for the medical device manufacturing process as described in any one of claims 1 to 7.

Images