A method and system for detecting the sealing quality of a fermenter

Abstract

The present invention discloses a method and system for detecting the sealing quality of a fermentation tank, which relates to the technical field of sealing detection. The method includes: determining the type of the fermentation tank and determining the sealing environment variables; locating the air leakage point and the air leakage rate to determine the static sealing detection result; performing surface point cloud feature scanning on the fermentation tank, executing macroscopic contact modeling, and training a finite element model; performing finite element variable simulation and sealing failure limit analysis to determine the dynamic sealing detection result; weighting and combining with quality standards to evaluate the sealing quality and calculating the quality coefficient; integrating the static sealing detection result, the dynamic sealing detection result and the quality coefficient to generate a single column of sealing detection. It solves the technical problems existing in the existing sealing quality detection of fermentation tanks, such as the difficulty in accurately locating tiny air leakage points and the inability to simulate the sealing performance of fermentation tanks under different working conditions, which leads to inaccurate and incomplete sealing quality detection results, and achieves the technical effect of improving the accuracy and comprehensiveness of the sealing quality detection results of the sealing tank.

Description

Technical Field

[0001] The present application relates to the technical field of seal detection, and specifically relates to a method and system for detecting the sealing quality of a fermenter. Background Art

[0002] With the rapid development of modern biotechnology, as a key device in the biological fermentation process, the sealing performance of a fermenter is crucial for ensuring the safety, stability of the fermentation process and the quality of the final product. The sealing performance of a fermenter not only affects the growth environment of microorganisms in the fermenter, but also directly relates to production efficiency and economic benefits. Therefore, the detection and evaluation of the sealing quality of a fermenter is a key link in the current biological fermentation technology field. However, traditional fermenter seal detection methods mostly rely on manual inspections and simple physical detection means, such as pressure tests, airtightness detections, etc. Although they can reflect the sealing performance of the fermenter to a certain extent, there are many limitations. For example, simple physical detection means can often only detect large air leakage points and are difficult to detect tiny air leaks, and it is difficult to achieve dynamic simulation and analysis of the sealing performance of the fermenter, making it impossible to comprehensively and objectively reflect the sealing performance of the fermenter, thereby affecting the safety and stability of the biological fermentation process.

[0003] Therefore, in the current related technologies for detecting the sealing quality of a fermenter, there are technical problems such as difficulty in accurately locating tiny air leakage points and inability to simulate the sealing performance of the fermenter under different working conditions, which in turn leads to inaccurate and incomplete sealing quality detection results. Summary of the Invention

[0004] By providing a method and system for detecting the sealing quality of a fermenter, and adopting technical means such as point cloud feature scanning, training a finite element model, and seal failure boundary analysis, the present application solves the technical problems existing in the existing fermenter sealing quality detection, such as difficulty in accurately locating tiny air leakage points and inability to simulate the sealing performance of the fermenter under different working conditions, which in turn leads to inaccurate and incomplete sealing quality detection results, and achieves the technical effect of improving the accuracy and comprehensiveness of the sealing tank quality detection results.

[0005] The present application provides a method for detecting the sealing quality of a fermenter. The method includes: determining the type of the fermenter and determining the sealing environment variables; introducing a detection gas, performing air flow tracking based on a gas detector, locating the air leakage point and the air leakage rate, and determining the static sealing detection result; based on a laser scanning device, performing surface point cloud feature scanning on the fermenter, executing macroscopic contact modeling based on parallel disks, and training a finite element model, where the finite element model includes a simulation regulation layer and a decision analysis layer; for the sealing environment variables, combining the finite element model, performing finite element variable simulation and sealing failure boundary analysis, and determining the dynamic sealing detection result, where the dynamic sealing detection result includes a feature co-occurrence matrix, and the feature co-occurrence matrix is used to measure the relative relationship of the airtight feature pairs at the sealing position; based on the static sealing detection result and the dynamic sealing detection result, weighting and combining with a quality standard to evaluate the sealing quality and calculating a quality coefficient; integrating the static sealing detection result, the dynamic sealing detection result and the quality coefficient to generate a single column of sealing detection.

[0006] In a possible implementation, when determining the dynamic sealing detection result, the following processing is further performed: for compressible fluids, performing dynamic airtightness detection to determine a first sealing detection result; for incompressible fluids, performing dynamic airtightness detection to determine a second sealing detection result; mapping the first sealing detection result and the second sealing detection result, measuring the sealing difference degree under the same environment variables, and integrating to determine the dynamic sealing detection result.

[0007] In a possible implementation, when performing finite element variable simulation and sealing failure boundary analysis, the following processing is further performed: the finite element variables are at least one random variable; determining a first finite element variable, setting a variable migration rate, combining the finite element model to perform scenario simulation and sealing performance detection, and determining first simulation data; identifying the first simulation data, determining an air leakage vector and locating the air leakage feature, and determining a first sealing detection result, where the air leakage vector is the variable data of the sealing failure point, and the air leakage feature includes the air leakage point and the air leakage rate.

[0008] In a possible implementation, when determining the first sealing detection result, the following processing is further performed: using the air leakage vector as the sealing failure boundary; based on the air leakage feature, determining an airtight feature pair based on the air leakage point, performing feature relative trend change analysis, and determining a first co-occurrence relationship, where the airtight feature pair is a relative contact point; determining a first data chain based on the first simulation data and identifying the link nodes based on the sealing failure boundary; based on the first data chain and the first co-occurrence relationship, determining the first sealing detection result.

[0009] In a possible implementation manner, when determining the dynamic seal detection result, the following processing is further performed: taking the time flow rate as a regulation variable, and combining with the finite element model, performing a simulation analysis on the attenuation of the seal performance over the entire service life cycle to determine the service seal trend; adding the service seal trend to the dynamic seal detection result.

[0010] In a possible implementation manner, when weighting and combining the quality standard to evaluate the seal quality and calculating the quality coefficient, the following processing is further performed: performing homologous clustering on the static seal detection result and the dynamic seal detection result to determine a plurality of evaluation groups; for each evaluation group, performing a primary weight distribution based on homology, and combining with the quality standard to determine a first quality coefficient distribution, where the quality coefficient distribution corresponds to the plurality of evaluation groups one by one; traversing the quality coefficient distribution, performing a secondary weight distribution based on the importance of the clustering source target, and calculating the quality coefficient by weighting.

[0011] In a possible implementation manner, when generating the single column of seal detection, the following processing is further performed: identifying the single column of seal detection, and locating the seal defect points; based on the seal defect points, combining with the production process of the fermenter to trace and optimize the process defects to determine the optimized production points; based on the optimized production points, reversely performing the production optimization of the fermenter.

[0012] The present application further provides a fermenter seal quality detection system, including: a seal environment variable determination module, which is used to determine the type of the fermenter and determine the seal environment variables; a static seal detection result determination module, which is used to introduce a detection gas, perform air flow tracking based on a gas detector, locate the air leakage points and the air leakage rate, and determine the static seal detection result; a finite element model training module, which is based on a laser scanning device to perform surface point cloud feature scanning on the fermenter, perform macroscopic contact modeling based on parallel disks, and train a finite element model, where the finite element model includes a simulation regulation layer and a decision analysis layer; a dynamic seal detection result determination module, which is used to perform finite element variable simulation and seal failure limit analysis on the seal environment variables in combination with the finite element model to determine the dynamic seal detection result, where the dynamic seal detection result includes a feature co-occurrence matrix, and the feature co-occurrence matrix is used to measure the relative relationship of the airtight feature pairs at the seal positions; a quality coefficient calculation module, which is based on the static seal detection result and the dynamic seal detection result, weights and combines the quality standard to evaluate the seal quality and calculates the quality coefficient; a seal detection single column generation module, which is used to integrate the static seal detection result, the dynamic seal detection result and the quality coefficient to generate a single column of seal detection.

[0013] A method and system for detecting the sealing quality of a fermentation tank are proposed in this application to determine the type of fermentation tank and the sealing environment variables; introduce a detection gas, perform air flow tracking based on a gas detector to locate the air leakage point and air leakage rate, and determine the static sealing detection result; based on a laser scanning device, scan the surface point cloud characteristics of the fermentation tank, perform macroscopic contact modeling based on parallel disks, and train a finite element model, where the finite element model includes a simulation regulation layer and a decision analysis layer; for the sealing environment variables, combine the finite element model to perform finite element variable simulation and sealing failure limit analysis to determine the dynamic sealing detection result, where the dynamic sealing detection result includes a feature co-occurrence matrix, and the feature co-occurrence matrix is used to measure the relative relationship of the airtight feature pairs at the sealing position; based on the static sealing detection result and the dynamic sealing detection result, assign weights and combine them with quality standards to evaluate the sealing quality and calculate the quality coefficient; integrate the static sealing detection result, the dynamic sealing detection result and the quality coefficient to generate a single column of sealing detection. This solves the technical problems existing in the existing detection of the sealing quality of fermentation tanks, such as the difficulty in accurately locating small air leakage points and the inability to simulate the sealing performance of fermentation tanks under different working conditions, resulting in inaccurate and incomplete sealing quality detection results, and achieves the technical effect of improving the accuracy and comprehensiveness of the sealing quality detection results of the sealing tank. Description of the Drawings

[0014] To more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments of the present disclosure will be briefly introduced below. Flowcharts are used in this application to illustrate the operations performed by the system according to the embodiments of the application. It should be understood that the operations in the front or below do not necessarily need to be executed precisely in sequence. On the contrary, according to needs, they can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.

[0015] Figure 1 Schematic diagram of the flow of a method for detecting the sealing quality of a fermentation tank provided by an embodiment of the present application;

[0016] Figure 2 Schematic diagram of the structure of a system for detecting the sealing quality of a fermentation tank provided by an embodiment of the present application.

[0017] Description of the reference numerals: The sealing environment variable determination module 10, the static sealing detection result determination module 20, the finite element model training module 30, the dynamic sealing detection result determination module 40, the quality coefficient calculation module 50, and the sealing detection single-column generation module 60. Detailed Embodiments

[0018] The above description is only an overview of the technical solution of the present application. In order to understand the technical means of the present application more clearly, it can be implemented according to the content of the specification. And in order to make the above and other purposes, features and advantages of the present application more obvious and understandable, the following specifically illustrates the specific embodiments of the present application.

[0019] In order to make the purpose, technical solution and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings. The described embodiments should not be regarded as limitations on the present application. All other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present application.

[0020] In the following description, "some embodiments" are involved, which describe a subset of all possible embodiments. However, it can be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments, and can be combined with each other without conflict. The terms "first / second" involved are only used to distinguish similar objects and do not represent a specific order for the objects. The terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or server that includes a series of steps or units does not necessarily limit to those steps or units clearly listed, but may include other steps or modules not clearly listed or inherent to these processes, methods, products or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field of the present application. The terms used herein are only for the purpose of describing the embodiments of the present application.

[0021] The embodiment of the present application provides a method for detecting the sealing quality of a fermenter, as Figure 1 shown, the method includes:

[0022] Step S100, determine the type of fermenter and determine the sealed environment variables. Determining the type of fermenter means clarifying its type according to the design, function, and usage scenario of the fermenter. The types of fermenters include, but are not limited to, aerobic fermenters and anaerobic fermenters classified according to the growth and metabolism needs of microorganisms, mechanical agitation ventilation fermenters and non-mechanical agitation ventilation fermenters classified according to the equipment characteristics of the fermenter, laboratory fermenters (below 500L), pilot-scale fermenters (between 500L and 5000L), and production-scale fermenters (above 5000L) classified according to volume, and liquid fermenters and solid fermenters classified according to the water content of the culture medium; determining the sealed environment variables means determining the key environmental factors affecting the sealing performance according to the sealing requirements and usage environment of the fermenter, which may include, but are not limited to, temperature, pressure, humidity, corrosive media, the shape and size of the sealing surface, etc. Specifically, temperature changes may occur during the operation of the fermenter, and it is necessary to ensure that the sealing material maintains good sealing performance within the corresponding temperature range; pressure changes may exist inside the fermenter, and it is necessary to ensure that the sealing structure can withstand these pressure changes without leakage; certain fermentation processes may have specific requirements for humidity, and the sealing material needs to have corresponding moisture resistance; if corrosive media are involved in the fermentation process, it is necessary to select sealing materials and structures that can resist the erosion of these media; the shape and size of the sealing surface have an important impact on the sealing performance and need to be designed and selected according to the actual situation.

[0023] Step S200: Introduce the detection gas, conduct airflow tracking based on a gas detector, locate the gas leakage point and gas leakage rate, and determine the static seal detection result. In the static stage of the fermentation tank seal quality detection, a specific detection gas is introduced. This gas is usually non-toxic, odorless, non-flammable, and easy to detect, such as nitrogen, helium, etc. Introducing the detection gas is to simulate the sealing performance of the fermentation tank under real working conditions and judge whether there is leakage in the fermentation tank by detecting the flow of the detection gas. Specifically, after introducing the detection gas, use a gas detector to track the gas flow in the fermentation tank. Among them, the gas detector is a device that can detect the concentration and flow of specific gases and usually has the characteristics of high sensitivity, high precision, and fast response. Through the gas detector, the concentration distribution and flow of the detection gas in the fermentation tank can be monitored in real time, thereby judging the sealing performance of the fermentation tank; during the airflow tracking process, if it is found that the concentration of the detection gas abnormally increases or decreases in a certain area, it indicates that there may be leakage in this area. Then, through more refined detection means (such as using a more sensitive gas detector, increasing the density of detection points, etc.) to further locate the specific location of the leakage point. At the same time, calculate the leakage rate according to the concentration change rate of the detection gas, that is, the amount of gas leaked per unit time. After locating the gas leakage point and gas leakage rate, determine the static seal detection result of the fermentation tank based on this information. If no leakage point is found or the leakage rate is lower than the set threshold, it is considered that the static sealing performance of the fermentation tank is qualified; if a leakage point is found or the leakage rate is higher than the set threshold, it is considered that the static sealing performance of the fermentation tank is unqualified and needs to be repaired.

[0024] Step S300, based on the laser scanning equipment, the surface point cloud feature scanning of the fermenter is performed, the macro contact modeling based on the parallel disk is performed, and the finite element model is trained, and the finite element model includes a simulation control layer and a decision analysis layer. The laser scanning equipment is used to perform non-contact scanning on the surface of the fermenter, that is, based on the principle of laser ranging, by emitting a laser beam and receiving the reflected light, the round-trip time of the light is calculated to quickly and accurately obtain the three-dimensional coordinate data of the fermenter surface (including analytical geometry, surface texture, roughness, material and other features), and form point cloud feature data. These point cloud data can be used to completely reconstruct the three-dimensional model of the fermenter. Macro contact modeling refers to establishing a macro contact relationship between the tank body and other objects (such as pipelines, support structures, etc.) based on the obtained fermenter point cloud data, and establishing a contact relationship between the fermenter and other pipelines and support structures from the overall or larger scale. The macro contact based on the parallel disk The modeling method simulates the complex contact area by simplifying it into multiple parallel disks. These parallel disks can effectively represent the contact interface, and calculate the contact pressure, deformation and contact area on each disk to obtain the comprehensive contact characteristics of the entire contact area. Specifically, the complex contact interface is simplified into multiple parallel disks. The disks are usually parallel to the normal direction of the contact interface and are evenly distributed in the contact area. The contact force and contact pressure on each disk are calculated, and the deformation of each disk is determined by calculating the contact force. The contact force and deformation results of each disk are summarized to obtain the macroscopic contact characteristics of the entire contact area, such as the total contact force, total contact area, contact pressure distribution, etc. The finite element model (FEM) is used to simulate the structure, materials and stress conditions of the fermentation tank, including a simulation control layer and a decision analysis layer. The simulation control layer is mainly responsible for the performance simulation and parameter adjustment of the fermentation tank under different conditions, such as temperature distribution, pressure change, fluid flow, etc., and the control simulation of various parameters (such as temperature, pH value, stirring speed, etc.) in the fermentation process; the decision analysis layer performs decision analysis and optimization based on the results of the simulation control layer. For example, by analyzing the simulation results, the optimal fermentation conditions, stirring strategy, temperature control scheme, etc. can be determined, thereby achieving accurate simulation and optimal control of the fermentation tank.

[0025] Step S400: For the sealed environmental variables, in combination with the finite element model, perform finite element variable simulation and sealed failure limit analysis to determine the dynamic seal detection result. Among them, the dynamic seal detection result includes a feature co-occurrence matrix, and the feature co-occurrence matrix is used to measure the relative relationship of the airtight feature pairs at the seal positions. During the process of detecting the sealing quality of the fermenter, performing finite element variable simulation and sealed failure limit analysis for the sealed environmental variables in combination with the finite element model actually means simulating and analyzing the sealing performance of the fermenter under different operating conditions (i.e., sealed environmental variables), that is, the dynamic simulation of the sealing structure of the fermenter to predict and evaluate its sealing effect under actual working conditions. Specifically, the finite element variable simulation refers to, based on the finite element model, simulating the stress distribution, deformation conditions, etc. of the fermenter under different sealed environmental variables. These simulation results can understand the sealing performance of the fermenter under different conditions and predict possible sealing problems. The sealed failure limit analysis refers to, through the analysis of the finite element simulation results, determining the failure limit of the sealing structure of the fermenter, such as the evaluation of key factors such as sealing materials and sealing structures to determine their load-bearing capacity and durability under different conditions. The dynamic seal detection result refers to the evaluation result of the sealing performance of the fermenter obtained through finite element simulation and sealed failure limit analysis, which may include various parameters and indicators for evaluating the sealing effect of the fermenter under different conditions. Among them, in the dynamic seal detection result, the feature co-occurrence matrix may be used to measure the relative relationship between the airtight feature pairs at the seal positions (i.e., different seal positions and corresponding airtight performances). Through the feature co-occurrence matrix, the airtight performance differences between different seal positions and their mutual influences can be more intuitively understood.

[0026] In a possible implementation, step S400 further includes step S410 of performing a dynamic airtightness detection on the compressible fluid to determine a first seal detection result. The dynamic airtightness detection technology is applicable to the airtightness performance test of fluid systems, especially suitable for testing the tightness of hydraulic and pneumatic systems. Specifically, the fermenter to be tested is usually connected to a compressor, and the airtightness performance of the fermenter is detected by changing the flow rate and pressure of the compressor to obtain the first seal detection result, which reflects the airtightness performance of the compressible fluid under dynamic conditions, including but not limited to indicators such as pressure change and leakage rate. It further includes step S420 of performing a dynamic airtightness detection on the incompressible fluid to determine a second seal detection result. Similarly, a dynamic airtightness detection is performed on the incompressible fluid to obtain the second seal detection result, which reflects the airtightness performance of the incompressible fluid under dynamic conditions. It further includes step S430 of mapping the first seal detection result and the second seal detection result to measure the seal difference degree under the same environmental variables and integrally determine the dynamic seal detection result. The first seal detection result and the second seal detection result are mapped, that is, the two sets of detection results are compared under the same environmental variables (such as temperature, pressure, humidity, etc.) to determine the difference between the first seal detection result and the second seal detection result. For example, the difference value, ratio, etc. of the pressure change and leakage rate are calculated. The magnitude of the seal difference degree will reflect the difference in the dynamic airtightness performance between the compressible fluid and the incompressible fluid. The two sets of seal detection results after mapping and measurement are comprehensively evaluated to obtain a comprehensive final result that can reflect the dynamic airtightness performance of the two fluids, which is the dynamic seal detection result.

[0027] In a possible implementation, step S410 further includes step S411 where the finite element variables are at least one random variable. The finite element variables being at least one random variable means multiple variables that have an important impact on the seal performance of the fermenter, such as pressure, temperature, material properties (such as elastic modulus, Poisson's ratio), etc. It further includes step S412 of determining a first finite element variable and setting a variable migration rate, and performing a scenario simulation and seal tightness detection in combination with the finite element model to determine first simulation data. The first finite element variable is any one of the multiple finite element variables, and the variable migration rate refers to the rate at which these variables change over time during the simulation. After determining the finite element variable and its migration rate, the finite element model is used for scenario simulation and seal tightness detection. Specifically, the finite element model is combined with a solver, and by simulating different scenarios (such as pressure change, temperature change, etc.), by inputting various conditions and parameters, the response and performance of the seal structure under different conditions are observed and analyzed. After the simulation is completed, first simulation data is generated, which may include displacement, stress, strain, etc., as well as various parameters related to the seal performance.

[0028] Step S410 further includes step S414 of identifying the first simulation data, determining the air leakage vector and locating the air leakage characteristics, and determining the first seal detection result. The air leakage vector is variable data of the seal failure point, and the air leakage characteristics include the air leakage point and the air leakage rate. Analyze and identify the first simulation data to obtain the air leakage vector and locate the air leakage characteristics. The air leakage vector refers to the variable data indicating the seal failure point detected in the simulation, such as the pressure change, displacement, or other relevant parameters at the seal failure position. The air leakage characteristics include the air leakage point and the air leakage rate. The air leakage point is the specific position of the seal failure, and the air leakage rate is a parameter describing the leakage speed, usually expressed as the leakage amount per unit time. Based on the identification and analysis of the simulation data, determine the first seal detection result, providing direct information about the seal performance, including whether there is leakage, the location and rate of leakage, etc.

[0029] In a possible implementation, step S414 further includes step S4141 of using the air leakage vector as the seal failure limit. In seal detection, when the air leakage vector (i.e., the variable data of the seal failure point) reaches or exceeds a certain threshold, it is considered that the seal structure has failed or leaked. Using the air leakage vector as the seal failure limit means that when the detected air leakage vector exceeds this limit, the seal is considered to have failed. It also includes step S4142 of determining the first co - existence relationship through characteristic relative trend analysis based on the air leakage characteristics and determining the airtight characteristic pairs based on the air leakage point. The airtight characteristic pairs are relative contact points. Determine the airtight characteristic pairs, i.e., relative contact points, based on the air leakage characteristics and the air leakage point. These are usually key seal positions, and their states (such as contact pressure, gap, etc.) directly affect the seal performance. Characteristic relative trend analysis is a method for analyzing the change trends between two or more characteristics, used to analyze the change trends between the air leakage point and the relative contact points (i.e., airtight characteristic pairs). The first co - existence relationship refers to the association or dependence relationship between the air leakage point and the relative contact points. For example, when the pressure at a certain contact point drops, the air leakage point may be more likely to leak.

[0030] Step S414 further includes step S4143 of determining a first data chain based on the first simulation data and identifying link nodes based on the seal failure limit. A series of relevant data points or variables are extracted from the first simulation data and arranged in a certain logical relationship or chronological order to form a continuous data stream or chain, i.e., the first data chain. In the data chain, specific data points or variables related to the seal failure limit are identified as link nodes, which are key points in the data chain. The values or states of the link nodes directly reflect whether the seal structure has reached the failure limit. It further includes step S4144 of determining the first seal detection result based on the first data chain and the first symbiotic relationship. By combining the first data chain (describing the response and performance of the seal structure) and the first symbiotic relationship (describing the association between the air leakage point and the relative contact point), the performance of the seal structure is comprehensively evaluated, and the first seal detection result is determined.

[0031] In a possible implementation, step S400 further includes step S440 of taking the time flow rate as a control variable and combining with the finite element model to conduct a simulation analysis of the seal performance attenuation under the full service life cycle to determine the service seal trend. The time flow rate refers to the speed at which time elapses during the simulation. Specifically, by adjusting the time flow rate, the finite element model simulates the change in the seal performance within the full service life cycle in a relatively short real time, that is, through simulation analysis, to understand the performance attenuation trend of the seal structure within the full service life cycle, thereby shortening the R & D and testing cycles, including the influence of factors such as material aging, wear, and temperature change on the seal performance, and obtaining the seal performance change curve within the full service life cycle, including the initial performance, the performance attenuation stage, and possible failure points. It further includes step S450 of adding the service seal trend to the dynamic seal detection result. Adding the service seal trend to the dynamic seal detection result means combining the results of long-term simulation analysis with real-time or dynamic detection results to form a more comprehensive seal performance evaluation report, which not only includes the current seal performance state but also can predict future performance change trends.

[0032] Step S500: Based on the static seal detection result and the dynamic seal detection result, assign weights and combine them to evaluate the seal quality according to the quality standard, and calculate the quality coefficient. Weights are assigned to the static seal detection result and the dynamic seal detection result respectively based on their importance and reliability in evaluating the seal quality. For example, in some cases, the static seal detection result may be more critical and be assigned a higher weight; conversely, the dynamic seal detection result may be more important and be assigned a higher weight. According to the quality standard of the fermenter quality detection industry, a comprehensive evaluation is carried out on the static seal detection result and the dynamic seal detection result. For example, the leakage rate, seal pressure, seal time, seal reliability, etc. are detected, and the detection results are compared with the quality standard to determine whether the seal quality of the fermenter meets the requirements. The quality coefficient is used to measure the seal quality of the fermenter. When calculating the quality coefficient, it can be calculated based on the weighted situation of the static seal detection result and the dynamic seal detection result, combined with the specific values of each evaluation index. Generally speaking, the quality coefficient can comprehensively reflect the seal performance of the fermenter, and is convenient for horizontal and vertical comparisons, which helps to improve the accuracy and reliability of the seal quality detection and better master the seal performance of the fermenter.

[0033] In a possible implementation manner, step S500 further includes step S510: perform homologous clustering on the static seal detection result and the dynamic seal detection result to determine multiple evaluation groups. Homologous clustering refers to using appropriate clustering algorithms (such as K-means, hierarchical clustering, etc.) to cluster the static and dynamic detection results, clustering the static seal detection results and dynamic seal detection results with similar characteristics or sources together, and dividing them into multiple evaluation groups. The results within each evaluation group should have similar characteristics or trends. It also includes step S520: for each evaluation group, perform a primary weight distribution based on homology, and combine the quality standard to determine the first quality coefficient distribution, where the quality coefficient distribution corresponds one-to-one to the multiple evaluation groups. The primary weight assignment means that according to the data characteristics and importance within the evaluation group, a weight is assigned to each evaluation group, that is, based on the data distribution, variance, and trend within the evaluation group, a weight value is assigned to each evaluation group to reflect the importance of the evaluation group in the entire result set. For each evaluation group, according to the detection data and the assigned primary weight within it, combined with the quality standard (such as leakage rate, pressure holding capacity, etc.), a corresponding quality coefficient is calculated to reflect the seal performance quality within the evaluation group. Then, the quality coefficients of all evaluation groups are combined to form the first quality coefficient distribution.

[0034] Step S500 further includes step S530, which traverses the quality coefficient distribution, performs a secondary weight distribution based on the importance of the clustering source targets, and determines the quality coefficient through weighted calculation. The importance of the clustering source targets refers to the relative importance of different clustering evaluation groups in the overall evaluation. For example, some evaluation groups may contain more critical seal performance data and thus have a higher importance. Specifically, after obtaining the first quality coefficient distribution, a secondary weight distribution is performed according to the importance of each evaluation group (i.e., the clustering source targets). After the secondary weight distribution, a weighted calculation is performed on the adjusted quality coefficient to obtain the final seal performance quality coefficient.

[0035] Step S600 integrates the static seal detection results, the dynamic seal detection results, and the quality coefficient to generate a single column of seal detection. The integration and summary of the static seal detection results, the dynamic seal detection results, and the quality coefficient to generate a single column of seal detection may be a table or a report, which contains all the important information about the seal detection. For example, basic information such as the fermenter identification (number), detection date, equipment type, etc.; static seal detection results such as the leakage point location, leakage rate, seal pressure, etc.; dynamic seal detection results such as the results of seal failure limit analysis, finite element simulation data, seal reliability assessment, etc.; the quality coefficient calculated based on the static and dynamic seal detection results in combination with the quality standards; an evaluation of the seal performance of the equipment based on the detection results and the quality coefficient, and corresponding suggestions are given (for example, if the quality coefficient is lower than a certain threshold, further maintenance or replacement of the seal is required, etc.), thereby providing a clear and comprehensive record of the fermenter seal quality detection.

[0036] In a possible implementation, step S600 further includes step S610 of identifying the single column of seal detection and locating the seal defect points. By analyzing the data of the single column of seal detection, data points that are abnormal or do not meet the preset standards are identified, and based on these abnormal data points, the positions of seal defects are located. For example, water seepage (possibly due to inappropriate seal materials or poor quality of the seal contact surface), gas leakage (possibly due to insufficient seal performance at the connection or seal material problems). It also includes step S620 of tracing and optimizing process defects based on the seal defect points in combination with the production process of the fermenter to determine the optimized production points. When seal defect points are found, the causes are traced, that is, a detailed analysis of the production process of the fermenter is carried out, including material selection, processing process, assembly process, etc. By comparing the production processes of normal and abnormal products, the key factors leading to seal defects can be found. After determining the process problems causing seal defects, the optimized production points are determined and process optimization is carried out on them, such as replacing more suitable seal materials, improving the seal structure at the connection, adjusting processing process parameters, etc., to improve the seal performance of the fermenter. It also includes step S630 of reversely optimizing the production of the fermenter based on the optimized production points. According to the determined optimized production points, the production of the fermenter is reversely optimized, that is, the abnormal production points of the fermenter production process are adjusted to ensure that each production link can reach the best state, such as improving the quality of raw materials, improving equipment, optimizing process parameters, etc., so as to solve the current seal problem and improve the overall seal quality of the fermenter.

[0037] In the above, reference is made to Figure 1 A method for detecting the seal quality of a fermenter according to an embodiment of the present invention is described in detail. Next, reference will be made to Figure 2 Describe a system for detecting the seal quality of a fermenter according to an embodiment of the present invention.

[0038] A system for detecting the seal quality of a fermenter according to an embodiment of the present invention is used to solve the technical problems existing in the detection of the seal quality of existing fermenters, such as it is difficult to accurately locate tiny air leakage points, and it is impossible to simulate the seal performance of fermenters under different working conditions, resulting in inaccurate and incomplete seal quality detection results, and achieves the technical effect of improving the accuracy and comprehensiveness of the seal quality detection results of the seal tank. A system for detecting the seal quality of a fermenter includes: a seal environment variable determination module 10, a static seal detection result determination module 20, a finite element model training module 30, a dynamic seal detection result determination module 40, a quality coefficient calculation module 50, and a seal detection single column generation module 60.

[0039] The seal environment variable determination module 10, and the seal environment variable determination module 10 is used to determine the type of the fermenter and determine the seal environment variables;

[0040] Static seal detection result determination module 20, which is configured to introduce a detection gas, perform air flow tracking based on a gas detector, locate the air leakage point and air leakage rate, and determine the static seal detection result;

[0041] Finite element model training module 30, which is configured to perform surface point cloud feature scanning on the fermentation tank based on a laser scanning device, perform macroscopic contact modeling based on parallel disks, and train a finite element model, where the finite element model includes a simulation regulation layer and a decision analysis layer;

[0042] Dynamic seal detection result determination module 40, which is configured to perform finite element variable simulation and seal failure limit analysis in combination with the finite element model for the seal environment variables to determine the dynamic seal detection result, where the dynamic seal detection result includes a feature co-occurrence matrix for measuring the relative relationship of airtight feature pairs at the seal position;

[0043] Quality coefficient calculation module 50, which is configured to assign weights and combine quality standards to evaluate the seal quality based on the static seal detection result and the dynamic seal detection result, and calculate the quality coefficient;

[0044] Seal detection single-column generation module 60, which is configured to integrate the static seal detection result, the dynamic seal detection result, and the quality coefficient to generate a seal detection single-column.

[0045] Next, the specific configuration of the dynamic seal detection result determination module 40 will be described in detail. The dynamic seal detection result determination module 40 further includes: performing dynamic airtight detection on compressible fluids to determine a first seal detection result; performing dynamic airtight detection on incompressible fluids to determine a second seal detection result; mapping the first seal detection result and the second seal detection result to measure the seal difference degree under the same environmental variables, and integrating to determine the dynamic seal detection result.

[0046] Next, the specific configuration of the dynamic seal detection result determination module 40 will be further described in detail. The dynamic seal detection result determination module 40 may further include: the finite element variable is at least one random variable; determining a first finite element variable and setting a variable migration rate, performing scenario simulation and seal tightness detection in combination with the finite element model to determine first simulation data; identifying the first simulation data, determining an air leakage vector and locating air leakage features to determine a first seal detection result, where the air leakage vector is variable data of the seal failure point, and the air leakage features include an air leakage point and an air leakage rate.

[0047] Next, the specific configuration of the dynamic seal detection result determination module 40 will be further described in detail. The dynamic seal detection result determination module 40 may further include: using the air leakage vector as the seal failure limit; based on the air leakage characteristics, determining airtight characteristic pairs based on air leakage points, performing relative trend change analysis of the characteristics, and determining the first coexistence relationship, where the airtight characteristic pairs are relative contact points; determining a first data chain based on the first simulation data and identifying link nodes based on the seal failure limit; and determining the first seal detection result based on the first data chain and the first coexistence relationship.

[0048] Next, the specific configuration of the dynamic seal detection result determination module 40 will be further described in detail. The dynamic seal detection result determination module 40 further includes: using the time flow rate as a control variable, combining with the finite element model, performing simulation analysis of the seal performance attenuation under the full service cycle, and determining the service seal trend; and adding the service seal trend to the dynamic seal detection result.

[0049] Next, the specific configuration of the quality coefficient calculation module 50 will be described in detail. The quality coefficient calculation module 50 further includes: performing homologous clustering on the static seal detection result and the dynamic seal detection result to determine multiple evaluation groups; for each evaluation group, performing a primary weight distribution based on homology, combining with the quality standard, and determining the first quality coefficient distribution, where the quality coefficient distribution corresponds to the multiple evaluation groups one by one; traversing the quality coefficient distribution, performing a secondary weight distribution based on the importance of the clustering source target, and calculating the quality coefficient by weighting.

[0050] Next, the specific configuration of the seal detection single column generation module 60 will be described in detail. The seal detection single column generation module 60 may further include: identifying the seal detection single column and locating the seal defect points; based on the seal defect points, combining with the production process of the fermenter to trace and optimize the process defects, and determining the optimized production points; and based on the optimized production points, reversely optimizing the production of the fermenter.

[0051] The fermentation tank seal quality detection system provided by the embodiments of the present invention can execute the fermentation tank seal quality detection method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0052] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or the server. The included individual units and modules are only divided according to the functional logic, but are not limited to the above division, as long as the corresponding functions can be realized; in addition, the specific names of the functional units are only for the convenience of mutual distinction and do not limit the protection scope of the present invention.

[0053] The above specific embodiments do not constitute a limitation on the protection scope of this application. Those skilled in the art should understand that various modifications, combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of this application shall be included within the protection scope of this application.

Claims

1. A method for detecting the sealing quality of a fermentation tank, characterized in that: The method comprises: Determine the fermentation tank type and determine the sealing environment variables; Introduce test gas, track airflow based on gas detector, locate gas leakage point and gas leakage rate, and determine static sealing test results; Based on the laser scanning equipment, the surface point cloud feature scanning of the fermentation tank is performed, the macro contact modeling based on the parallel disk is performed, and the finite element model is trained. The finite element model includes a simulation control layer and a decision analysis layer; For the sealing environment variables, combined with the finite element model, finite element variable simulation and sealing damage limit analysis are performed to determine dynamic sealing detection results, wherein the dynamic sealing detection results include a feature co-occurrence matrix, and the feature co-occurrence matrix is ​​used to measure the relative relationship between the airtight feature pairs at the sealing position; Based on the static sealing test result and the dynamic sealing test result, weighting is performed and the sealing quality is evaluated in combination with the quality standard to calculate the quality coefficient; Integrate the static sealing test result, the dynamic sealing test result and the quality coefficient to generate a sealing test single column; Determining the dynamic sealing detection result includes: For the compressible fluid, a dynamic airtightness test is performed to determine a first sealing test result; For incompressible fluids, dynamic airtightness testing is performed to determine the second sealing test result; Mapping the first sealing test result and the second sealing test result, measuring the sealing difference under the same environmental variables, and integrating to determine the dynamic sealing test result; The finite element variable simulation and seal damage limit analysis include: The finite element variable is at least one random variable; Determine a first finite element variable, set a variable migration rate, perform scene simulation and sealing test in combination with the finite element model, and determine first simulation data; The first simulation data is identified, an air leakage vector is determined, and an air leakage feature is located, and a first sealing detection result is determined, wherein the air leakage vector is variable data of a sealing failure point, and the air leakage feature includes an air leakage point and an air leakage rate.

2. A fermentation tank sealing quality detection method as claimed in claim 1, characterized in that: The determining of the first sealing detection result comprises: Using the air leakage vector as the sealing failure limit; Based on the air leakage characteristics, an airtight feature pair is determined based on the air leakage point, and a feature relative trend analysis is performed to determine a first symbiotic relationship, wherein the airtight feature pair is a relative contact point; determining a first data link based on the first simulation data, and identifying a link node based on the seal breach limit; Based on the first data link and the first symbiotic relationship, the first sealing detection result is determined.

3. A fermentation tank sealing quality detection method as claimed in claim 1, characterized in that: The method further comprises: Taking the time flow rate as the control variable and combining the finite element model, a sealing performance attenuation simulation analysis under the full service cycle is performed to determine the service sealing trend; The service sealing trend is added to the dynamic sealing detection result.

4. A fermentation tank sealing quality detection method as claimed in claim 1, characterized in that: The weighting is combined with the quality standards to evaluate the sealing quality and calculate the quality coefficient, including: Performing homology clustering on the static sealing test results and the dynamic sealing test results to determine a plurality of evaluation groups; For each evaluation group, a primary weight distribution based on homology is performed, and a first quality coefficient distribution is determined in combination with the quality standard, wherein the quality coefficient distribution corresponds to the multiple evaluation groups one by one; The quality coefficient distribution is traversed, and secondary weight distribution is performed based on the importance of the clustering source target, and the quality coefficient is determined by weighted calculation.

5. A fermentation tank sealing quality detection method as claimed in claim 1, characterized in that: The method further comprises: Identify the sealing detection row and locate the sealing defect point; Based on the sealing defect points, combined with the production process of the fermenter, process defect tracing and optimization are performed to determine the optimized production point; Based on the optimized production point, the production optimization of the fermenter is reversely performed.

6. A fermentation tank sealing quality detection system, characterized in that: The system is used to implement a fermentation tank sealing quality detection method according to any one of claims 1 to 5, and the system comprises: A sealing environment variable determination module, wherein the sealing environment variable determination module is used to determine the fermentation tank type and the sealing environment variables; A static sealing test result determination module, which is used to introduce a test gas, track the airflow based on a gas detector, locate the gas leakage point and the gas leakage rate, and determine the static sealing test result; A finite element model training module, wherein the finite element model training module performs surface point cloud feature scanning on the fermentation tank based on a laser scanning device, performs macro contact modeling based on parallel disks, and trains a finite element model, wherein the finite element model includes a simulation control layer and a decision analysis layer; A dynamic sealing detection result determination module, the dynamic sealing detection result determination module is used to perform finite element variable simulation and sealing damage limit analysis on the sealing environment variables in combination with the finite element model to determine the dynamic sealing detection result, wherein the dynamic sealing detection result includes a feature co-occurrence matrix, and the feature co-occurrence matrix is ​​used to measure the relative relationship of the airtight feature pairs at the sealing position; A quality coefficient calculation module, which evaluates the sealing quality based on the static sealing test result and the dynamic sealing test result by assigning weights and combining the quality standards to calculate the quality coefficient; A sealing test single column generation module is used to integrate the static sealing test result, the dynamic sealing test result and the quality coefficient to generate a sealing test single column.

Images