Dynamic optimization method for sterilization dose of thermosensitive medical device based on artificial intelligence

Abstract

The invention discloses a method for dynamically optimizing the sterilization dose of a thermosensitive medical device based on artificial intelligence, and relates to the technical field of optimization of the sterilization dose of the thermosensitive medical device, and the method specifically comprises the following steps: under the condition that different device materials in the same batch have thermal response differences, determining all devices with the thermal response differences, the thermal response difference instrument is calibrated as a thermal response difference instrument; response characteristic information of each thermal response difference instrument is obtained and analyzed, the material heat absorption difference degree of each thermal response difference instrument is evaluated, and each thermal response difference instrument is classified according to the evaluation result; and according to the classification result of each thermal response difference instrument, correspondingly adjusting the irradiation dose of the thermal response difference instrument and dynamically optimizing the irradiation dose of the thermal response difference instrument. The problem that the sterilization dosage cannot be dynamically optimized under the thermal response difference of the same batch of thermosensitive medical instruments is solved, and accurate matching and intelligent adjustment of dosage distribution are achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of sterilization dose optimization for thermosensitive medical devices, and in particular to a dynamic optimization method for sterilization dose for thermosensitive medical devices based on artificial intelligence. Background Art

[0002] As medical devices evolve towards precision and biocompatibility, the application of heat-sensitive materials (such as polymer plastics, biological agents, etc.) in sterile products is becoming increasingly widespread, placing higher demands on temperature control and dosage adjustment during the sterilization process. Electron beam sterilization technology has become one of the mainstream methods for sterilizing heat-sensitive devices due to its low temperature, no chemical residues, and strong penetration. Currently, the biopharmaceutical field has gradually built automated production lines covering automatic loading, irradiation acceleration, sterilization treatment and intelligent sorting, which not only improves production line efficiency but also provides a multi-source data foundation for process control. In this context, focusing on the material structure, packaging method and sterilization environment of different medical devices, combined with historical operation information and real-time process parameters, and through intelligent information processing mechanisms, dynamic adjustment and optimization control of sterilization doses are being achieved. This is becoming an important development trend that is driving the sterilization technology of heat-sensitive medical devices towards high adaptability and high precision.

[0003] Existing AI-based dynamic optimization technology for sterilization doses of heat-sensitive medical devices is commonly used in electron beam sterilization systems. Relying on sensors and data acquisition systems deployed along the production line, these technologies capture key data in real time, including the medical device's structural parameters, material type, packaging format, batch characteristics, ambient temperature and humidity, electron beam device operating status, and historical sterilization results. Through an intelligent information processing module within a central control platform, the system dynamically determines and fine-tunes the sterilization dose (i.e., irradiation dose) required for each batch of heat-sensitive devices. This dose is typically controlled by adjusting beam intensity, under-beam transport speed, and dwell time to ensure that each device receives adequate sterilization while avoiding material degradation or performance loss due to excessive irradiation. The entire process typically includes data acquisition, product identification, parameter matching, dose generation, and process feedback, creating an intelligent closed-loop system spanning sterilization preparation, dose control, and effect verification, enabling precise control and dynamic optimization of the electron beam sterilization dose.

[0004] The existing technology has the following deficiencies:

[0005] Existing AI-based dynamic optimization technology for sterilization doses of thermosensitive medical devices can lead to differences in their thermal response to the electron beam when the same batch contains devices made of different materials. This is because different materials have varying electron beam absorption capacities. Some devices have low electron beam absorption, while others absorb more heat due to factors like thickness and density. This results in significant differences in their actual thermal response when exposed to the same irradiation intensity and duration. Existing technologies typically calculate a uniform sterilization dose based on information such as material and type. However, existing AI-based dynamic optimization technology for sterilization doses of thermosensitive medical devices cannot dynamically optimize the irradiation dose based on the degree of heat absorption differences among the materials within the same batch. This problem arises because existing technologies assume that all devices have a uniform thermal response, ignoring the heat absorption characteristics of different materials. As a result, within the same batch, some devices, due to low heat absorption, fail to achieve the adequate sterilization dose, resulting in microbial residues, while others, due to excessive heat absorption, suffer material damage, deformation, or degradation. Failure to dynamically adjust the irradiation dose can seriously affect sterilization effectiveness, compromising product quality and safety, and even leading to batch rework, waste, and increased rejects.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not form the prior art that is already known to a person of ordinary skill in the art. Summary of the Invention

[0007] The purpose of the present invention is to provide an artificial intelligence-based dynamic optimization method for the sterilization dose of heat-sensitive medical devices to solve the problems in the above-mentioned background technology.

[0008] To achieve the above objectives, the present invention provides the following technical solution: a method for dynamic optimization of sterilization dosage of thermosensitive medical devices based on artificial intelligence, specifically comprising the following steps:

[0009] Identify the materials of thermosensitive medical devices of different materials in the same batch and analyze their thermal characteristics to determine whether there are differences in thermal response between different device materials in the same batch;

[0010] In the event that different device materials within the same batch exhibit variability in thermal response, identify all devices exhibiting variability in thermal response and designate them as variability devices;

[0011] Obtaining and analyzing response characteristic information of each differential thermal response device, evaluating the degree of heat absorption difference of the material of each differential thermal response device, and classifying each differential thermal response device based on the evaluation results;

[0012] According to the classification results of each device with different thermal responses, the irradiation dose is adjusted accordingly and dynamically optimized;

[0013] Record the adjustment status, optimization strategy and microbial test results of each instrument, generate a sterilization process report, and continuously optimize the irradiation dose adjustment strategy based on the actual sterilization effect feedback information.

[0014] Preferably, when different device materials in the same batch have different thermal responses, all devices with different thermal responses are identified and calibrated as devices with different thermal responses, specifically:

[0015] In the case that different device materials in the same batch have different thermal responses, the thermal conductivity, specific heat capacity and thickness values ​​of each device are extracted separately and compared with the corresponding thermal conductivity, specific heat capacity and thickness values ​​of any other device in the same batch. If the difference between any of the three values ​​and the corresponding value of any other device exceeds the preset corresponding threshold, the device is determined to be a device with different thermal response. After the comparison is completed, all devices that meet this condition are calibrated as devices with different thermal responses.

[0016] Preferably, obtaining and analyzing the response characteristic information of each thermal response difference device, evaluating the degree of heat absorption difference of the material of each thermal response difference device, and classifying each thermal response difference device according to the evaluation result specifically includes the following steps:

[0017] Acquire response characteristic information of each thermal response difference device and perform preprocessing after acquisition;

[0018] Extracting heat capacity composition information and diffusion resistance information from the pre-processed response characteristic information, and analyzing the extracted information to generate the structural heat capacity coefficient and thermal diffusion inhibition index of each thermal response difference device;

[0019] Based on the generated structural heat capacity coefficient and thermal diffusion inhibition index of each thermal response difference device, a material heat absorption index of each thermal response difference device is generated by weighted summation;

[0020] Determine a pre-set threshold range of the material heat absorption index, and after determination, compare it with the generated material heat absorption index of each thermal response difference device, evaluate the degree of material heat absorption difference of each thermal response difference device based on the comparison result, and classify each thermal response difference device based on the evaluation result.

[0021] Preferably, the logic for obtaining the structural heat capacity coefficient of each thermal response difference device is as follows:

[0022] The heat capacity composition information is extracted from the pre-processed response characteristic information, including the specific heat capacity, material density and mass of the surface material of each thermal response difference device, and calibrated as c i , ρ iand m i , c i represents the specific heat capacity of the surface material of the i-th thermal response difference device, ρ i represents the material density of the surface material of the i-th thermal response difference device, m i represents the mass of the i-th thermal response difference device, i = 1, 2, 3, ..., k, k is a positive integer;

[0023] Calculate the structural heat capacity coefficient of each device with different thermal response. The specific calculation formula is as follows:

[0024]

[0025] Where, SHC i is the structural heat capacity coefficient of the i-th thermal response difference device.

[0026] Preferably, the logic for obtaining the thermal diffusion inhibition index of each thermal response difference device is as follows:

[0027] Diffusion resistance information is extracted from the preprocessed response characteristic information, including the average thickness, thermal conductivity and surface area of ​​the surface material of each thermal response difference device, and calibrated as d i , γ i and A i , d i represents the average thickness of the surface material of the i-th thermal response difference device, γ i A represents the thermal conductivity of the surface material of the i-th thermal response difference device, i represents the surface area of ​​the i-th thermal response differential device, i = 1, 2, 3, ..., k, where k is a positive integer;

[0028] Calculate the thermal diffusion inhibition index of each device with different thermal response. The specific calculation formula is as follows:

[0029]

[0030] Where, TDS i is the thermal diffusion inhibition index of the i-th thermal response difference device.

[0031] Preferably, the structural heat capacity coefficient SHC of each thermal response difference device is generated based on i and thermal diffusion suppression index TDS i , the material heat absorption index of each thermal response difference device is generated by weighted summation. The specific calculation formula is as follows:

[0032] MHAI i =ω1*SHC i +ω2*TDS i

[0033] Where MHAI i is the material heat absorption index of the ith thermal response differential device, ω1 and ω2 are the structural heat capacity coefficients SHC of each thermal response differential device, respectively. i and thermal diffusion suppression index TDS i The non-zero weight coefficient of , and ω1+ω2=1.

[0034] Preferably, a predetermined material endothermic index threshold interval [MHAI min , MHAI max ], and after determination, the material endothermic index MHAI of each thermal response difference device is generated i Comparisons were conducted, and the degree of heat absorption differences of the materials of various thermal response difference devices was evaluated based on the comparison results. The various thermal response difference devices were classified based on the evaluation results. The specific comparison analysis and classification are as follows:

[0035] If MHAI i <MHAI min The thermal response difference device has a low degree of heat absorption difference in the material, and the thermal response difference device is classified as a low heat absorption difference device;

[0036] If MHAI min ≤MHAI i ≤MHAI max The thermal response differential device has a medium degree of thermal absorption difference in the material, and the thermal response differential device is classified as a medium thermal absorption differential device;

[0037] If MHAI i >MHAI max The degree of heat absorption difference of the material of the thermal response difference device is high, and the thermal response difference device is classified as a high heat absorption difference device.

[0038] Preferably, according to the classification results of each device with different thermal responses, the irradiation dose is adjusted accordingly and dynamically optimized, specifically:

[0039] For devices with differential thermal response that are classified as low-heat absorption differential devices, a standard irradiation dose is administered and the surface temperature trajectory is monitored during the irradiation process. If the surface temperature trajectory exceeds the preset temperature rise range, the irradiation duration is adjusted within a limited time interval to keep the surface heat input within the target range.

[0040] For devices with thermal response differences that are classified as medium endothermic devices, a dose adjustment interval is set, and the irradiation intensity is increased or decreased within the adjustment interval according to the temperature rise rate change trajectory during irradiation. The temperature rise rate is continuously compared with the preset reference trajectory during irradiation. When the comparison result meets the preset offset condition, the subsequent irradiation parameters are adjusted in steps;

[0041] For thermal response differential devices classified as high heat absorption differential devices, the irradiation process is divided into several fixed irradiation time periods. The irradiation operation is performed separately according to each time period. An interval is set between any irradiation time periods. The irradiation dose of the next irradiation period is adjusted in stages based on the temperature change trajectory after the previous irradiation period. At the same time, the start time of the subsequent irradiation period is determined based on the heat distribution of the previous stage.

[0042] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0043] 1. The present invention can identify the materials and analyze the thermal characteristics of thermosensitive medical devices in the same batch, and can identify devices with different thermal responses based on physical indicators such as thermal conductivity, specific heat capacity and structural thickness, and calibrate them as devices with different thermal responses. The heat absorption capacity of each device is further quantified by two parameters: structural heat capacity coefficient and thermal diffusion inhibition index, and a material heat absorption index is constructed, thus realizing for the first time an accurate assessment of the degree of heat absorption difference between materials of different devices. Unlike the existing technology that only distributes uniform doses based on surface parameters, this solution can carefully reflect the actual thermal response behavior of each device, provide a scientific basis for subsequent dose adjustments, and fundamentally solve the problem of insufficient sterilization or material damage caused by inconsistent thermal response.

[0044] 2. This invention establishes threshold ranges for the material's heat absorption index and categorizes devices with differential thermal response into three categories: low, medium, and high heat absorption. Based on the heat absorption characteristics of each device, strategies such as standard dose, limited floating dose, and segmented irradiation control are implemented, truly achieving refined dose management based on classification results. In particular, in the dynamic optimization phase, the solution incorporates an irradiation parameter adjustment mechanism based on temperature rise trajectory, temperature rise rate, and stage temperature trends. This eliminates the need for a static dose setting and allows for real-time adjustment of the irradiation dose. This maintains sterilization effectiveness while avoiding extreme situations such as thermal overload or insufficient dose, significantly improving the safety and adaptability of the sterilization process.

[0045] 3. The present invention systematically records the dosage adjustment records, optimization strategy selection and sterilization test results of each thermal response differential instrument during the sterilization process, automatically generates a sterilization process report, and introduces a sterilization effect feedback mechanism to achieve self-optimization of the strategy based on historical effects. Through feedback data modeling, the system can dynamically adjust the classification boundaries and adjustment strategies of the material heat absorption index, realizing the transformation of empirical parameters to data-driven. This design not only improves the traceability and reusability of the process, but also lays the foundation for the subsequent dynamic allocation of dosages for multiple batches and different types of instruments, and promotes the sterilization process from "standardized control" to a new stage of "intelligent scheduling". It is a key breakthrough in the integration of artificial intelligence and precision sterilization. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction to the drawings required for use in the embodiments will be given below. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can also be obtained based on these drawings.

[0047] Figure 1 The figure is a flow chart of the dynamic optimization method for sterilization dosage of thermosensitive medical devices based on artificial intelligence of the present invention. DETAILED DESCRIPTION

[0048] Example embodiments will now be described more fully with reference to the accompanying drawings. However, example embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of this disclosure will be thorough and complete and will fully convey the concepts of the example embodiments to those skilled in the art.

[0049] The present invention provides Figure 1 The artificial intelligence-based dynamic optimization method for sterilization dose of thermosensitive medical devices shown in the figure specifically includes the following steps:

[0050] Identify the materials of thermosensitive medical devices of different materials in the same batch and analyze their thermal characteristics to determine whether there are differences in thermal response between different device materials in the same batch;

[0051] For material identification of thermosensitive medical devices of different materials in the same batch, the software system can call the preset device type and material information in the associated database for rapid matching and identification, or extract the device number by identifying the unique identification code on the device (such as a QR code, RFID tag or laser engraving), and perform an associated query with the preset material list to determine the material type corresponding to each device. In actual applications, the identification process can be performed by an image acquisition device or a code scanning module to collect the number information, transmit it to the processing software, and then the software automatically matches the preset material data; for new devices not included in the database, a manual re-entry mechanism can be preset, and the operator can mark the corresponding material and automatically archive it to achieve a closed-loop update of the software. The above method does not rely on manual judgment and can efficiently and accurately complete the material identification of the entire device at the batch level.

[0052] After completing material identification, the software will automatically retrieve the thermal characteristic information corresponding to each material, including but not limited to basic parameters such as thermal conductivity, specific heat capacity, density, thickness, and thermal expansion coefficient, and load it into the analysis engine in the form of a table or matrix. Subsequently, the system compares the relative differences between the thermal characteristic parameters of instruments of different materials in the same batch by establishing a thermal response characteristic model. The basis for determining whether there is a difference in thermal response is that the system has an internal multi-dimensional comparison algorithm to calculate the thermal behavior difference index between different materials, such as using the thermal conductivity deviation rate or the heat accumulation trend change range as the judgment standard. When the difference between any two or more types of instruments in the key thermal characteristic dimension exceeds the set threshold, or the trend of their predicted thermal response change curve is divergent, the software determines that there is a thermal response difference in the batch and marks the relevant material pairs as material pairs that need attention. The entire process is automatically completed based on known physical models and preset judgment rules to ensure that the analysis results are traceable and logically rigorous.

[0053] The purpose of performing this step is to automatically identify and analyze the differences in the basic characteristics of the instrument materials through software before the sterilization process is started, so as to establish the judgment basis for the subsequent dynamic dose optimization strategy from the source. Since the thermal response of thermosensitive medical devices under electron beam irradiation is closely related to the thermal characteristics of their materials, if the essential differences in thermal conductivity, heat absorption, etc. between different materials are ignored, some instruments may not receive sufficient doses and fail to be sterilized, or the instruments may be damaged due to excessive heat accumulation. Existing technologies often assume that the thermal response of instruments in the same batch is consistent, making it difficult to identify subtle but critical differences in thermal characteristics, resulting in unreasonable unified dose configuration. However, by using software to pre-identify material differences and analyze thermal characteristic information, a mathematical and data foundation can be laid for subsequent heat absorption difference assessment and dose classification adjustment, ultimately achieving truly precise sterilization control.

[0054] In the event that different device materials within the same batch exhibit variability in thermal response, identify all devices exhibiting variability in thermal response and designate them as variability devices;

[0055] In this embodiment, when different device materials in the same batch have different thermal responses, all devices with different thermal responses are identified and calibrated as devices with different thermal responses. Specifically,

[0056] In the case that different device materials in the same batch have different thermal responses, the thermal conductivity, specific heat capacity and thickness values ​​of each device are extracted separately and compared with the corresponding thermal conductivity, specific heat capacity and thickness values ​​of any other device in the same batch. If the difference between any of the three values ​​and the corresponding value of any other device exceeds the preset corresponding threshold, the device is determined to be a device with different thermal response. After the comparison is completed, all devices that meet this condition are calibrated as devices with different thermal responses.

[0057] In the case that different device materials in the same batch have different thermal responses, the thermal conductivity, specific heat capacity and thickness values ​​of each device can be extracted by software, which can be achieved by relying on the device association coding and material data management system. The specific operation method is: the software first reads the number information of each device based on the unique identification code (such as QR code, barcode or RFID code) in the device label, and automatically associates the corresponding material type in the database through the number. Subsequently, the software calls the pre-established material thermal performance data table to extract the thermal conductivity value and specific heat capacity value corresponding to the material type. For thickness data, if the device has a digital modeling file or a scanned model, the software can automatically parse the definitions of dimensions such as wall thickness and cladding structure in the CAD data or three-dimensional modeling file and extract the thickness value; if the modeling file is not integrated, the thickness measurement value collected by an external measuring instrument can be uploaded to the software in real time by the interface system for archiving and calling. The entire extraction process is automatically completed by the software, realizing the standardized acquisition and collection of key values ​​of thermal response of batch-level devices without manual intervention.

[0058] After extracting the thermal conductivity, specific heat capacity, and thickness values ​​for each device, the software system constructs a comparison matrix based on the overall list of devices in the same batch. Each device is assigned a numerical vector consisting of these three values. The system then performs a one-to-one comparison of the three values ​​for the current device with the corresponding values ​​for any other device in the batch through a cyclic comparison process. This comparison is based on the calculation of absolute numerical differences. For example, the difference in thermal conductivity, specific heat capacity, and thickness between two devices is calculated item by item, and each difference is compared to a preset threshold for that item. If any difference exceeds the corresponding threshold, the system automatically marks the device as having a different thermal response. The entire comparison process is performed in the software through batch calculation and an automatic threshold determination mechanism to ensure consistent and accurate data processing. This comparison is necessary because significant differences in thermal conductivity, heat capacity, or geometric characteristics (such as thickness) between different devices can directly affect their thermal response during electron beam irradiation. Identifying these different devices in advance helps establish a basis for subsequent dose classification and adjustment, avoiding issues such as inadequate sterilization or material damage caused by uniform treatment.

[0059] After comparing thermal conductivity, specific heat capacity, and thickness values ​​and identifying devices that meet the thermal response differential criteria, the software system calibrates these devices by updating identification data. Specifically, upon identifying the device number with a thermal response differential, the software automatically adds an identification field to the corresponding device's data record, setting the calibration status to "Device with Thermal Response Differentiation," and simultaneously writes this status field to the database. The system also generates separate groups or tags for these devices in the visual interface, facilitating their separate management and tracking in subsequent processes. In environments with an interface, this calibration status can also be automatically pushed to subsequent dose optimization modules or device execution units, enabling cross-module processing linkage. To enhance calibration traceability, the software also logs the calibration time, comparison basis, and determination results, ensuring that the calibration process for each device with a thermal response differential is traceable. This calibration method, achieved through data tag assignment and status management, is highly automated and consistent, making it suitable for dynamic differential identification and management of large volumes of heat-sensitive medical devices.

[0060] Obtaining and analyzing response characteristic information of each differential thermal response device, evaluating the degree of heat absorption difference of the material of each differential thermal response device, and classifying each differential thermal response device based on the evaluation results;

[0061] In this embodiment, the response characteristic information of each thermal response differential device is obtained and analyzed, the degree of heat absorption difference of the material of each thermal response differential device is evaluated, and each thermal response differential device is classified according to the evaluation results. Specifically, the following steps are included:

[0062] Acquire response characteristic information of each thermal response difference device and perform preprocessing after acquisition;

[0063] Obtaining the response characteristic information of each thermal response differential device can be achieved by docking the software system with multiple data sources. The specific methods include: first, the software retrieves its material property records and structural models from the database by reading the unique identification code of each thermal response differential device (such as a barcode, QR code or RFID code); then, combined with the modeling file associated with the device (such as a three-dimensional structural model, CAD drawing) or production parameter table, extract its thermal conductivity, specific heat capacity, density, mass, wall thickness, surface area and other basic property data; in addition, it can also be connected to the data interface of online measurement equipment (such as laser thickness gauges, mass sensors) or digital production equipment to achieve real-time collection of physical characteristics such as thickness, surface area, and mass. All data collection processes are automatically triggered by the scheduling logic in the software and archived according to the device number to ensure that the response characteristic information of each thermal response differential device is a structured and traceable data set.

[0064] The purpose of preprocessing the acquired response characteristic information is to ensure data quality consistency, format standardization, and anomaly elimination, so as to facilitate subsequent high-precision parameter calculation and modeling analysis. Preprocessing mainly includes the following operations: First, the software performs unit dimensionless processing on various types of raw data to prevent calculation deviations due to inconsistent data dimensions; second, missing items or outliers are judged and repaired. The software will fill in the historical data mean of the type of device to which the device belongs, or mark values ​​exceeding three times the standard deviation as abnormal and exclude them; third, the software will convert data formats from different sources (such as floating point, string, enumeration) into a unified floating point value to adapt to the subsequent mathematical calculation engine. The entire preprocessing process is automatically completed by the built-in data verification, formatting, and rule-driven modules, and a preprocessing result log is generated to ensure that the data quality control process is transparent and controllable, laying a solid foundation for the subsequent extraction of heat capacity composition information and diffusion resistance information.

[0065] Extracting heat capacity composition information and diffusion resistance information from the pre-processed response characteristic information, and analyzing the extracted information to generate the structural heat capacity coefficient and thermal diffusion inhibition index of each thermal response difference device;

[0066] Extracting heat capacity composition information and diffusion resistance information from preprocessed response feature information can be automated through the software's built-in data parsing and information classification module. Specifically, upon receiving preprocessed structured data, the software automatically categorizes the specific heat capacity, material density, and mass fields of each device with differential thermal response as heat capacity composition information, and the average wall thickness, thermal conductivity, and surface area fields as diffusion resistance information, based on preset field mapping rules. This process is driven by the software's built-in field recognition logic and information archiving model. The software automatically identifies data labels or field names and parses and matches them based on the correspondence between feature information and information categories. After extraction, the system stores these two types of information in separate data structures and establishes an information mapping table indexed by the device number. This ensures that the corresponding information sets can be quickly and accurately accessed during the subsequent calculation of the structural heat capacity coefficient and thermal diffusion inhibition index, thereby completing the semantic decomposition and structural extraction of thermal response features. The entire process requires no human intervention and is highly automated and repeatable.

[0067] Based on the generated structural heat capacity coefficient and thermal diffusion inhibition index of each thermal response difference device, a material heat absorption index of each thermal response difference device is generated by weighted summation;

[0068] Determine a pre-set threshold range of the material heat absorption index, and after determination, compare it with the generated material heat absorption index of each thermal response difference device, evaluate the degree of material heat absorption difference of each thermal response difference device based on the comparison result, and classify each thermal response difference device based on the evaluation result.

[0069] Determining pre-set threshold ranges for the material endothermic index is accomplished through the software's built-in model parameter configuration and historical data analysis modules. Specifically, the software first accesses a data set of material endothermic indexes from historical sterilization batches, identified as devices with differential thermal responses. Cluster analysis or distribution fitting, such as using K-means clustering or Gaussian mixture models, is performed to model the numerical distribution characteristics of the material endothermic index across different endothermic performance categories. The system then identifies three typical range boundaries based on the cluster centers and boundaries of each category, combined with sterilization efficacy indicators (e.g., residual microorganisms and device integrity feedback): low, moderate, and significant endothermic variation. Based on the analysis results, the software automatically generates two boundary values, serving as the lower and upper limits of the pre-set material endothermic index threshold range, forming the threshold range. Furthermore, the system supports a manual adjustment mechanism, allowing users to manually modify the threshold range as necessary based on process changes or safety standards. The modified range is automatically archived in the parameter configuration file and applied simultaneously to subsequent comparisons, ensuring flexibility and adaptability in the material endothermic variation assessment process. The entire threshold determination process is automatically completed in the software through model calculation and parameter management modules, without the need for manual intervention and with traceability.

[0070] In this embodiment, the logic for obtaining the structural heat capacity coefficient of each thermal response difference device is as follows:

[0071] The heat capacity composition information is extracted from the preprocessed response characteristic information, including the specific heat capacity, material density and mass of the surface material of each thermal response difference device, and calibrated as c i , ρ i and m i , c i represents the specific heat capacity of the surface material of the i-th thermal response difference device, ρ i represents the material density of the surface material of the i-th thermal response difference device, m i represents the mass of the i-th thermal response difference device, i = 1, 2, 3, ..., k, k is a positive integer;

[0072] In order to achieve a dynamic evaluation of the structural heat capacity coefficient of each device with different thermal responses, it is necessary to obtain three types of basic data: the specific heat capacity, material density, and mass of its surface material in real time, and extract its value itself (i.e., the numerical size) in the software system, rather than its unit or dimension identification. Specifically, as inherent properties of the material, the specific heat capacity and material density are usually pre-stored in the material master data management system (such as the material database or BOM system). The software can retrieve the code of its surface covering material through the unique identification code of the device (such as a barcode, RFID, or electronic chip), and automatically index and obtain the specific heat capacity and density values ​​corresponding to the material; these two values ​​are maintained in a standardized form in the system and are fixed values ​​that do not fluctuate with batches. The software only extracts the pure numerical part and converts it into floating-point data for subsequent calculations. As for quality data, because it is related to the structural processing and assembly of the device, the actual weight value of the device needs to be obtained through real-time weighing equipment (such as an embedded weighing module or a quality detector at the end of the production line). The system writes the weight value directly into the response characteristic information table in numerical form through the device communication interface. All of the aforementioned data is automatically stripped of its units upon entering the software's processing flow, retaining only standard values. The software then binds these values ​​to predefined fields for subsequent calculations of the structural heat capacity coefficient, enabling fully automated data extraction and real-time processing without manual input. This approach automatically captures and processes the three key data types—specific heat capacity, material density, and mass—in a structured, numerical, and standardized format within the software system, meeting the prerequisites for calculating the structural heat capacity coefficient.

[0073] Calculate the structural heat capacity coefficient of each device with different thermal response. The specific calculation formula is as follows:

[0074]

[0075] Where, SHC iis the structural heat capacity coefficient of the i-th thermal response difference device.

[0076] The purpose of using this formula to calculate the structural heat capacity coefficient of each device with different thermal response is to comprehensively and reasonably evaluate the structural absorption capacity of each device for thermal energy in the early stage of thermal response, and to ensure that the calculation logic and physical meaning are highly consistent through mathematical structure. Specifically, first, the specific heat capacity c of the device surface material is calculated. i The square operation is performed to increase its weight in the overall heat capacity, because the specific heat capacity directly determines the heat storage capacity per unit mass of the material; then it is combined with the material density ρ i Multiplication is equivalent to expanding the heat storage capacity per unit mass to the heat storage capacity per unit volume, forming the expression of the material's heat capacity density; performing a square root operation on this product is to amplify the thermal response trend while avoiding a sharp increase in the value, thereby enhancing data stability and comparability. Next, the device mass m is introduced. i , and taking its cube root is to reflect the structural influence of the overall heat carrying capacity of the device, while suppressing the excessive dominance of large-mass devices on the final coefficient through the power function. Finally, the natural logarithm function is added to the entire expression to compress the range of numerical distribution, improve the distinguishability of indicators and model convergence between different devices, and ensure the continuity and stability of the final coefficient value in engineering calculations. Therefore, each mathematical operation of this formula serves the physical goal, that is, to accurately evaluate the response ability of the device to thermal input at its structural level, and ultimately make the structural heat capacity coefficient both discriminable and operational.

[0077] Structural heat capacity coefficient SHC of the i-th thermal response difference device i There is a direct quantitative correlation between the size of and the degree of heat absorption difference of its materials. Specifically, SHC i The larger the SHC, the higher the heat capacity of the device during the thermal response process. That is, the surface material not only has a strong heat storage capacity per unit volume (determined by specific heat capacity and density), but also has an overall structural quality sufficient to slow down the temperature rise process, thereby showing a lower instantaneous temperature rise rate and stronger thermal stability under the same electron beam irradiation conditions. This heat absorption "slow rise and slow release" characteristic will cause the heat absorption performance of the device to be significantly different from that of devices with smaller heat capacity in the same batch. Therefore, SHC i The larger the value, the smaller the temperature rise of the device when absorbing the same energy and the stronger the heat absorption capacity, reflecting that it belongs to the "slow thermal response type" or "high thermal absorption hysteresis type" device in the heat absorption difference assessment, which helps to distinguish it from devices with fast thermal response and classify them for management, thereby supporting subsequent dose differentiation optimization.

[0078] In this embodiment, the logic for obtaining the thermal diffusion inhibition index of each thermal response difference device is as follows:

[0079] Diffusion resistance information is extracted from the preprocessed response characteristic information, including the average thickness, thermal conductivity and surface area of ​​the surface material of each thermal response difference device, and calibrated as d i , γ i and A i , d i represents the average thickness of the surface material of the i-th thermal response difference device, γ i A represents the thermal conductivity of the surface material of the i-th thermal response difference device, i represents the surface area of ​​the i-th thermal response differential device, i = 1, 2, 3, ..., k, where k is a positive integer;

[0080] To achieve real-time calculation of the thermal diffusion inhibition index for each device with different thermal responses, the software system needs to extract three key data types: the average thickness, thermal conductivity, and surface area of ​​the surface material. During the extraction process, it is clear that only the specific numerical values ​​are used, without involving unit dimensions, to ensure a unified data format and facilitate calculation and processing. The specific acquisition method is as follows: the software first calls its structural design information in the manufacturing execution system (MES) or product structure database (BOM) based on the unique identification code of each device (such as a QR code, barcode, or RFID electronic tag). For the average thickness of the surface material, the preset wall thickness field in the 3D modeling file (such as an STL or STEP file) can be read, or it can be linked with external equipment such as a laser thickness gauge or industrial CT to obtain the thickness measurement value of each device at a key position in real time. The software then takes a weighted average and records the value. Thermal conductivity is a physical property constant of the material. The software automatically searches the physical property database by material number and extracts its standard thermal conductivity value to ensure stability and consistency. For surface area, the software can calculate the total external surface area based on the three-dimensional model data of the device through the CAD parsing module or surface mesh processing tool; if the model is not available, the shape contour can be established through the laser scanning device to automatically complete the surface area calculation. In the above process, all data will be stripped of their units through the pre-processing module when entering the software system, retaining only floating-point values, and classified into the data record entries corresponding to the device number. The software automatically identifies these three types of data through field labels, and writes them into the structured feature information table as diffusion resistance information for subsequent index calculation calls, thereby realizing the full process automation of real-time data acquisition, numerical processing and unified format input.

[0081] Calculate the thermal diffusion inhibition index of each device with different thermal response. The specific calculation formula is as follows:

[0082]

[0083] Where, TDS i is the thermal diffusion inhibition index of the i-th thermal response difference device.

[0084] The purpose of using this formula to calculate the thermal diffusion inhibition index of each device with different thermal response is to accurately characterize the thermal diffusion hysteresis ability of the device under specific structural and material property conditions, and to quantitatively express the thermal diffusion differences of different devices through the fusion calculation of multi-dimensional parameters. In this formula, (d i ) 2 It represents the square of the average thickness of the surface material of the i-th device. The greater the thickness, the longer the heat flow propagation path in the device and the slower the diffusion process. Therefore, the square is used to amplify its dominant role in the model; γ i Indicates the thermal conductivity of the material. The larger the thermal conductivity, the easier it is for heat to diffuse and the smaller the diffusion resistance. Therefore, it is placed in the denominator to correct the diffusion retardation caused by thickness. i It represents the surface area of ​​the device. The larger the surface area, the stronger the heat dissipation capacity of the device, and the easier it is for heat energy to diffuse along the surface. Therefore, through ln(1+A i ) is compressed in the form of a logarithmic function and nonlinear adjustment is introduced to avoid excessive exponential attenuation caused by a large area and calculation distortion of small area devices. The whole is wrapped in an exponential function in order to amplify the difference in thermal diffusion performance caused by subtle structural differences in the exponential space, thereby making TDS i This value can more sensitively distinguish between devices with different heat diffusion speeds, and serves as a high-precision discriminant factor in evaluating heat absorption differences. Each calculation strictly corresponds to the actual physical mechanism of heat conduction, ensuring that the calculation results are both mathematically discernible and engineering interpretable.

[0085] Thermal Diffusion Suppression Index TDS of the i-th Thermal Response Difference Device i The size of TDS is closely related to the degree of heat absorption difference of its materials and is an important basis for judging whether there is a significant heat retention effect in the heat diffusion process of the device. i The larger the value, the thicker the surface material of the device (d i The larger the thermal conductivity, the worse the i The smaller the surface area (A i The smaller the TDS, the more difficult it is for heat to diffuse out of the device structure per unit time. This limited diffusion makes it easier for the device to form local heat accumulation under the same electron beam irradiation conditions, resulting in a slow thermal response process and continuous temperature rise, which in turn produces a significant difference in heat absorption behavior compared to devices with faster thermal diffusion. Therefore, TDS i The higher the TDS, the greater the resistance of the device on the heat diffusion path, and the more significant the difference in heat absorption; conversely, i The lower the TDS, the faster the device dissipates heat, the more active the thermal response, and the smaller the difference in heat absorption. i The size of the material can be used to effectively identify and evaluate the hysteresis characteristics of each device in terms of heat absorption performance.

[0086] In this embodiment, the structural heat capacity coefficient SHC of each thermal response difference device is generated. i and thermal diffusion suppression index TDS i , the material heat absorption index of each thermal response difference device is generated by weighted summation. The specific calculation formula is as follows:

[0087] MHAI i =ω1*SHC i +ω2*TDS i

[0088] Where MHAI i is the material heat absorption index of the ith thermal response differential device, ω1 and ω2 are the structural heat capacity coefficients SHC of each thermal response differential device, respectively. i and thermal diffusion suppression index TDS i The non-zero weight coefficient of , and ω1+ω2=1.

[0089] Material heat absorption index MHAI in achieving different thermal response devices i During the process, the software system will first calculate the structural heat capacity coefficient SHC of each device. i and thermal diffusion suppression index TDS i , and then linearly combine the weighted rules to generate the material heat absorption index MHAI of the device. i In the specific operation, the system presets two non-zero weight coefficients ω1 and ω2, corresponding to SHC i and TDS i The influencing factors are used to regulate the proportion of these two parameters in the total index. The weight coefficient is usually set based on statistical analysis of historical batch data and expert experience, or optimized in the training set through machine learning algorithms. For example, the sensitivity of each parameter to the final sterilization performance can be compared based on actual sterilization effect feedback (such as temperature rise response, residual temperature of the instrument, or sterilization integrity), and the values ​​of ω1 and ω2 can be dynamically adjusted. The two always satisfy ω1+ω2=1 to ensure that the weighted calculation results are normalized and stable. In actual operation, the software will SHC i With TDS i The values ​​of are multiplied by the corresponding weights and then added to generate MHAI i This value is used as the basic input indicator for subsequent heat absorption difference judgment and classification. The entire process is completed automatically by software, ensuring efficiency, traceability and flexible parameter adjustment.

[0090] In this embodiment, the predetermined material endothermic index threshold interval [MHAI min , MHAI max], and after determination, the material endothermic index MHAI of each thermal response difference device is generated i Comparisons were conducted, and the degree of heat absorption differences of the materials of various devices with different thermal responses were evaluated based on the comparison results. The devices with different thermal responses were classified based on the evaluation results. The specific comparison analysis and classification are as follows:

[0091] If MHAI i <MHAI min The thermal response difference device has a low degree of heat absorption difference in the material, and the thermal response difference device is classified as a low heat absorption difference device;

[0092] This indicates that the device's heat absorption performance during the thermal response process is highly consistent with that of most devices in the same batch, with virtually no significant deviation. Its structural heat capacity coefficient and thermal diffusion inhibition index are in a relatively balanced range, allowing for rapid and uniform heat transfer and release after absorption, making heat retention and localized overheating less likely to occur. During the actual sterilization process, these devices exhibit a stable temperature rise curve and minimal heat load fluctuations. Therefore, a standard dosage strategy can be directly adopted without individual adjustments, optimizing resource scheduling and improving sterilization efficiency.

[0093] If MHAI min ≤MHAI i ≤MHAI max The thermal response differential device has a medium degree of thermal absorption difference in the material, and the thermal response differential device is classified as a medium thermal absorption differential device;

[0094] This situation indicates that the endothermic response of the device has slightly shifted within the same batch, but is still within the control range. Due to certain medium-thickness structures, thermally conductive materials or complex geometries, the device may have a certain local temperature rise hysteresis or edge heat flow changes during the sterilization process, and its sensitivity to the sterilization dose is slightly higher than that of the standard device. If the difference is ignored, it may lead to uneven sterilization effects or overkill risks in the boundary area of ​​​​the sterilization. Therefore, such devices should be optimized through slight dynamic adjustments (such as ± 5% dose fluctuations) based on the standard dose to ensure their thermal stability and sterilization integrity.

[0095] If MHAI i >MHAI max The degree of heat absorption difference of the material of the thermal response difference device is high, and the thermal response difference device is classified as a high heat absorption difference device.

[0096] This situation indicates that the thermal response behavior of the device deviates significantly from the normal range, and is characterized by a thick structure, slow thermal conductivity, or an extremely small surface area, resulting in slow thermal diffusion and significant heat absorption and retention. This type of device is very prone to heat accumulation under electron beam irradiation, and the local temperature remains high for a long time. If treated with a uniform dose, it is very likely to cause material deformation, aging, or even functional failure, or conversely, incomplete sterilization due to temperature hysteresis in the core area. Therefore, such devices must adopt a refined control strategy, combined with real-time thermal analysis results, to differentially reduce the irradiation dose or perform segmented irradiation to ensure balanced release of the heat load and ensure the sterilization effect and structural integrity of the device.

[0097] According to the classification results of each device with different thermal responses, the irradiation dose is adjusted accordingly and dynamically optimized;

[0098] In this embodiment, according to the classification results of each device with different thermal responses, the irradiation dose is adjusted accordingly and dynamically optimized, specifically:

[0099] For devices with differential thermal response that are classified as low-heat absorption differential devices, a standard irradiation dose is administered and the surface temperature trajectory is monitored during the irradiation process. If the surface temperature trajectory exceeds the preset temperature rise range, the irradiation duration is adjusted within a limited time interval to keep the surface heat input within the target range.

[0100] To achieve stable control and dynamic adjustment of the irradiation dose for devices classified as low-heat-absorption differential devices, a temperature monitoring and time control mechanism can be collaboratively driven, combined with the software's data processing logic to manage the entire process. Specifically, during the irradiation process, non-contact infrared temperature sensors or thermocouple arrays placed in the irradiation area continuously collect temperature data from key locations on the surface of each device. The collected temperature values ​​are input into the software as a real-time temperature data stream. Upon receiving the temperature data, the software automatically compares it with a temperature rise reference trajectory corresponding to this device type. The reference trajectory is based on historical data modeling or expert process presets and represents the standard thermal response behavior. If the current temperature change trajectory deviates from the temperature rise range defined by the reference trajectory at any moment (for example, from the upper or lower limits of the interval), the software triggers the irradiation time control logic. Without changing the irradiation intensity, the duration of the current irradiation phase is adjusted to appropriately shorten or extend the heat input within a short period of time, thereby returning the device surface temperature to the target heat input range. This adjustment process can be repeated multiple times without causing intensity fluctuations, ensuring irradiation stability. Adjusting time rather than intensity is used because low-heat-absorption differential devices have a stable thermal response, and irradiation intensity should not be varied to avoid affecting process consistency. Adjusting time allows for more precise control of unit heat input, ensuring consistent sterilization results while avoiding the risk of overheating. This approach ensures operational accuracy while facilitating the implementation of continuous dynamic optimization logic in software, improving process robustness and control precision.

[0101] For devices with thermal response differences that are classified as medium endothermic devices, a dose adjustment interval is set, and the irradiation intensity is increased or decreased within the adjustment interval according to the temperature rise rate change trajectory during irradiation. The temperature rise rate is continuously compared with the preset reference trajectory during irradiation. When the comparison result meets the preset offset condition, the subsequent irradiation parameters are adjusted in steps;

[0102] To address temperature excursions during irradiation for devices with moderate endothermic differences, a "real-time tracking of temperature rise rate and linked intensity adjustment mechanism" can be implemented, combined with software to achieve closed-loop irradiation parameter adjustment. Specifically, before irradiation begins, a preset dose adjustment interval is established for the device. This interval consists of a series of intensity levels (e.g., 5% or 10% increments) that fluctuate above and below the standard dose, serving as selectable segments for dynamic adjustment. During irradiation, a high-speed infrared temperature sensor acquires device surface temperature data. The software calculates the temperature rise rate (i.e., the temperature change per unit time) within a specified time interval and compares the calculated result with a preset temperature rise rate benchmark trajectory. This benchmark trajectory represents the ideal thermal response rate and is typically derived from well-performing devices with moderate endothermic differences in historical batches. If the real-time temperature rise rate exceeds a preset excursion threshold (e.g., temperature rise is too fast or too slow), the software immediately invokes the corresponding intensity level, adjusting the current irradiation intensity up or down within the irradiation interval to quickly correct the heat input trend. At the same time, during the subsequent irradiation process, the software will continue to monitor the difference between the temperature rise rate and the currently adjusted trajectory. If it is identified that the offset persists, the irradiation step will be switched, such as entering the next dose segment in advance or inserting a temperature stabilization time window. The reason why the temperature rise rate is used as the basis for judgment is that the temperature rise rate is more sensitive to changes in thermal response, and it can provide early warning before the absolute value of the temperature deviates, thereby improving response efficiency. This method can continuously track and judge through software, and achieve differentiated fine adjustment for medium-difference instruments without deviating from the standard process, thereby ensuring the balance of the sterilization effect and safety boundary control.

[0103] For thermal response differential devices classified as high heat absorption differential devices, the irradiation process is divided into several fixed irradiation time periods. The irradiation operation is performed separately according to each time period. An interval is set between any irradiation time periods. The irradiation dose of the next irradiation period is adjusted in stages based on the temperature change trajectory after the previous irradiation period. At the same time, the start time of the subsequent irradiation period is determined based on the heat distribution of the previous stage.

[0104] To address the significant heat accumulation and temperature rise hysteresis characteristic of devices with high thermal endothermy, a "segmented irradiation + intermittent cooling + phased dose adjustment" strategy can be implemented to avoid localized overheating or uneven sterilization during a single high-intensity irradiation. Software manages and executes the entire process. Specifically, the continuous irradiation process is divided into multiple time periods, each with a fixed duration or adjustable interval set by the device. After each irradiation period, a preset interval is inserted to allow the device to cool naturally or for heat to diffuse. The duration of this interval is determined by the system based on the device's thermal endothermic hysteresis. Furthermore, the system uses temperature sensors to analyze the temperature trajectory after each irradiation period, focusing on indicators such as peak temperature, temperature decay rate, and dwell time to determine whether the heat input exceeded the material's tolerance threshold or whether the heat dissipation efficiency met the required standards. Based on this analysis, a decision is made as to whether to maintain the original dose, reduce the dose, or extend the interval for the next irradiation period. If the temperature continues to remain high or drops slowly after the previous irradiation, the next irradiation will be carried out at a lower intensity, or the start time will be delayed to allow for sufficient heat dissipation. In addition, in order to achieve a balanced distribution of heat load, the system will dynamically plan the start-up rhythm of subsequent irradiation segments based on the spatial distribution of heat in the previous segment (such as the distribution trend of surface hot spots), thereby staggering the heat accumulation peaks on the time axis. The core purpose of this segmented control strategy is to break the local overload caused by thermal response lag through time-domain dose allocation and multi-segment decision-making mechanisms, reduce the risk of thermal damage to the material, and ensure that the total sterilization dose accurately covers the target area. The entire strategy can be controlled uninterruptedly through software logic flow to ensure both sterilization stability and structural safety.

[0105] Record the adjustment status, optimization strategy and microbial test results of each instrument, generate a sterilization process report, and continuously optimize the irradiation dose adjustment strategy based on the actual sterilization effect feedback information to ensure the accuracy and consistency of the sterilization dose.

[0106] In order to achieve full-process traceability and closed-loop optimization of the sterilization process, this can be achieved by building a "data recording and feedback-driven irradiation dose optimization mechanism". This mechanism takes each thermal response differential instrument as the object and tracks its key control nodes throughout the sterilization process. The specific method is: after each irradiation task is completed, the system automatically archives the differential category into which the instrument is classified during the classification stage, the corresponding dose adjustment measures taken (such as irradiation time adjustment, intensity modification, segmentation plan) and its parameter change process to form a complete "adjustment behavior trajectory". Subsequently, after completing sterilization, the system receives the microbial test results associated with the instrument number, including indicators such as the number of residual colonies, detection time, and detection method, and compares them with the preset sterilization standards to determine whether the sterilization meets the standards or there are deviations. All the above information is uniformly integrated into the sterilization process report as structured data, which is automatically generated and archived by the software to support subsequent calls, analysis and audits. The report also contains a statistical analysis summary of each type of instrument to discover common problems or extreme deviations in process execution.

[0107] Based on the sterilization effect feedback information recorded in the sterilization process report, the software can further build a continuous optimization mechanism. Specifically, the system performs cluster analysis and trend modeling on the sterilization strategy execution results of similar instruments in multiple batches, identifies the sterilization success rate and failure mode of different instrument categories under different dose adjustment conditions, and adjusts the classification boundary values ​​(such as the material heat absorption index threshold range) and optimizes the irradiation parameter preset values ​​(such as time period configuration, intensity level) based on this, so as to automatically implement the improved strategy in subsequent batches. This type of feedback optimization mechanism not only improves the responsiveness and adaptability of dose regulation, but also enables the system to continuously self-learn and evolve, avoiding problems of excessive or insufficient sterilization due to inaccurate experience or outdated parameter configuration, thereby ensuring the accuracy and consistency of the sterilization dose distribution among different instruments, and achieving the dynamic closed-loop control goal of "each device can be tracked and each policy can be corrected."

[0108] The above formulas are all dimensionless and numerical calculations. The formulas are obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formulas are set by technicians in this field according to actual conditions.

[0109] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless means (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0110] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0111] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0112] In the several embodiments provided in this application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0113] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0114] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0115] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. Dynamic optimization method for sterilization dose of thermosensitive medical devices based on artificial intelligence, characterized by: The specific steps include: Identify the materials of thermosensitive medical devices of different materials in the same batch and analyze their thermal characteristics to determine whether there are differences in thermal response between different device materials in the same batch; In the event that different device materials within the same batch exhibit variability in thermal response, identify all devices exhibiting variability in thermal response and designate them as variability devices; Obtaining and analyzing response characteristic information of each differential thermal response device, evaluating the degree of heat absorption difference of the material of each differential thermal response device, and classifying each differential thermal response device based on the evaluation results; According to the classification results of each device with different thermal responses, the irradiation dose is adjusted accordingly and dynamically optimized; Record the adjustment status, optimization strategy and microbial test results of each instrument, generate a sterilization process report, and continuously optimize the irradiation dose adjustment strategy based on the actual sterilization effect feedback information.

2. The artificial intelligence-based dynamic optimization method for sterilization dose of thermosensitive medical devices according to claim 1, characterized in that: When different device materials within the same batch exhibit thermal response differences, all devices exhibiting thermal response differences shall be identified and designated as thermal response differential devices, specifically: In the case of different device materials in the same batch that have different thermal responses, the thermal conductivity, specific heat capacity, and thickness values ​​of each device are extracted and compared with the corresponding thermal conductivity, specific heat capacity, and thickness values ​​of any other device in the same batch. If the difference between any of the three values ​​and the corresponding value of any other device exceeds the preset corresponding threshold, the device is determined to be a device with different thermal response; After the comparison is completed, all devices that meet the conditions are calibrated as thermal response difference devices.

3. The method for dynamic optimization of sterilization dose of thermosensitive medical devices based on artificial intelligence according to claim 2, characterized in that: Obtaining and analyzing response characteristic information of each thermal response differential device, evaluating the degree of material heat absorption difference of each thermal response differential device, and classifying each thermal response differential device according to the evaluation results, specifically comprising the following steps: Acquire response characteristic information of each thermal response difference device and perform preprocessing after acquisition; Extracting heat capacity composition information and diffusion resistance information from the pre-processed response characteristic information, and analyzing the extracted information to generate the structural heat capacity coefficient and thermal diffusion inhibition index of each thermal response difference device; Based on the generated structural heat capacity coefficient and thermal diffusion inhibition index of each thermal response difference device, a material heat absorption index of each thermal response difference device is generated by weighted summation; Determine a pre-set threshold range of the material heat absorption index, and after determination, compare it with the generated material heat absorption index of each thermal response difference device, evaluate the degree of material heat absorption difference of each thermal response difference device based on the comparison result, and classify each thermal response difference device based on the evaluation result.

4. The method for dynamic optimization of sterilization dose of thermosensitive medical devices based on artificial intelligence according to claim 3, characterized in that: The logic for obtaining the structural heat capacity coefficient of each thermal response difference device is as follows: The heat capacity composition information is extracted from the pre-processed response characteristic information, including the specific heat capacity, material density and mass of the surface material of each thermal response difference device, and calibrated as c i , ρ i and m i , c i represents the specific heat capacity of the surface material of the i-th thermal response difference device, ρ i represents the material density of the surface material of the i-th thermal response difference device, m i represents the mass of the i-th thermal response difference device, i = 1, 2, 3, ..., k, k is a positive integer; Calculate the structural heat capacity coefficient of each device with different thermal response. The specific calculation formula is as follows: Where, SHC i is the structural heat capacity coefficient of the i-th thermal response difference device.

5. The method for dynamic optimization of sterilization dose of thermosensitive medical devices based on artificial intelligence according to claim 4, characterized in that: The logic for obtaining the thermal diffusion inhibition index of each thermal response difference device is as follows: Diffusion resistance information is extracted from the preprocessed response characteristic information, including the average thickness, thermal conductivity and surface area of ​​the surface material of each thermal response difference device, and calibrated as d i , γ i and A i , d i represents the average thickness of the surface material of the i-th thermal response difference device, γ i A represents the thermal conductivity of the surface material of the i-th thermal response difference device, i represents the surface area of ​​the i-th thermal response differential device, i = 1, 2, 3, ..., k, where k is a positive integer; Calculate the thermal diffusion inhibition index of each device with different thermal response. The specific calculation formula is as follows: Where, TDS i is the thermal diffusion inhibition index of the i-th thermal response difference device.

6. The method for dynamic optimization of sterilization dose of thermosensitive medical devices based on artificial intelligence according to claim 5, characterized in that: Structural heat capacity (SHC) of each device with different thermal responses generated i and thermal diffusion suppression index TDS i , the material heat absorption index of each thermal response difference device is generated by weighted summation. The specific calculation formula is as follows: MHAI i =ω1*SHC i +ω2*TDS i Where MHAI i is the material heat absorption index of the ith thermal response differential device, ω1 and ω2 are the structural heat capacity coefficients SHC of each thermal response differential device, respectively. i and thermal diffusion suppression index TDS i The non-zero weight coefficient of , and ω1+ω2=1.

7. The artificial intelligence-based dynamic optimization method for sterilization dose of thermosensitive medical devices according to claim 6, characterized in that: Determine the pre-set material endothermic index threshold range [MHAI min , MHAI max ], and after determination, the material endothermic index MHAI of each thermal response difference device is generated i Comparisons were conducted, and the degree of heat absorption differences of the materials of various thermal response difference devices was evaluated based on the comparison results. The various thermal response difference devices were classified based on the evaluation results. The specific comparison analysis and classification are as follows: If MHAI i <MHAI min The thermal response difference device has a low degree of heat absorption difference in the material, and the thermal response difference device is classified as a low heat absorption difference device; If MHAI min ≤MHAI i ≤MHAI max The thermal response differential device has a medium degree of thermal absorption difference in the material, and the thermal response differential device is classified as a medium thermal absorption differential device; If MHAI i >MHAI max The degree of heat absorption difference of the material of the thermal response difference device is high, and the thermal response difference device is classified as a high heat absorption difference device.

8. The method for dynamic optimization of sterilization dose of thermosensitive medical devices based on artificial intelligence according to claim 7, characterized in that: Based on the classification results of each device with different thermal responses, the irradiation dose is adjusted accordingly and dynamically optimized, specifically: For devices with differential thermal response that are classified as low-heat absorption differential devices, a standard irradiation dose is administered and the surface temperature trajectory is monitored during the irradiation process. If the surface temperature trajectory exceeds the preset temperature rise range, the irradiation duration is adjusted within a limited time interval to keep the surface heat input within the target range. For devices with thermal response differences that are classified as medium endothermic devices, a dose adjustment interval is set, and the irradiation intensity is increased or decreased within the adjustment interval according to the temperature rise rate change trajectory during irradiation. The temperature rise rate is continuously compared with the preset reference trajectory during irradiation. When the comparison result meets the preset offset condition, the subsequent irradiation parameters are adjusted in steps; For thermal response differential devices classified as high heat absorption differential devices, the irradiation process is divided into several fixed irradiation time periods. The irradiation operation is performed separately according to each time period. An interval is set between any irradiation time periods. The irradiation dose of the next irradiation period is adjusted in stages based on the temperature change trajectory after the previous irradiation period. At the same time, the start time of the subsequent irradiation period is determined based on the heat distribution of the previous stage.

Images