Performance detection optimization method and system for small-diameter pipe

Abstract

The invention relates to the technical field of copper pipe performance detection, in particular to a performance detection optimization method and system for a small-diameter pipe, and the method comprises the steps: scanning and collecting three-dimensional parameter data, and constructing a collaborative model based on the three-dimensional parameter data; determining a plurality of performance detection targets, determining and collecting production process parameters of corresponding process links, and detecting to obtain live performance parameters; mapping the production process parameters of the corresponding process links to the collaborative model, and constructing a matched performance mimicry calculation model; the performance of the small-diameter pipe under different performance detection targets and different process conditions is tested through the performance mimicry calculation model, and mimicry performance parameters corresponding to the performance detection targets are obtained; determining a performance change fitting relationship corresponding to each performance detection target; and according to the performance change fitting relationship, determining the corresponding abnormal performance and optimization direction. By constructing the relevance between the production process parameters and the performance detection results, the accuracy between the detection results and the live performance parameters is improved.

Description

Technical Field

[0001] This invention relates to the field of copper tube performance testing technology, and in particular to a method and system for optimizing the performance testing of small-diameter tubes. Background Technology

[0002] Small-diameter copper tubes, with their advantages of high dimensional accuracy, excellent thermal conductivity, and strong corrosion resistance, are widely used in many key fields such as refrigeration appliances, energy industry, precision instruments, and medical devices to realize fluid transportation and heat exchange within equipment. Their performance directly affects the reliability, safety, and operating efficiency of the products.

[0003] In related technologies, performance testing of small-diameter copper tubes mainly involves offline methods such as digital imaging, ultrasonic testing, and experimental verification to detect indicators such as processing parameters and internal defects. However, these offline testing methods are disconnected from the actual production environment. Testing in a fixed laboratory environment cannot fully simulate the complex working conditions such as high temperature, high pressure, and media corrosion during actual processing and forming. Furthermore, they do not establish a correlation with the various process parameters in the actual production process, leading to deviations between the test results and reality. In addition, the testing methods are limited by factors such as applicable scenarios. The testing process is often carried out on the same target section, making it difficult to integrate the data to form a correlation. The causes of defects can only be artificially inferred based on the test results, making it difficult to provide clear optimization directions.

[0004] The information disclosed in this background section is intended only to enhance the understanding of the overall background of the present invention and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide a method and system for optimizing the performance testing of small-diameter pipes, to establish the correlation between production process parameters and performance testing results, and to improve the accuracy between testing results and actual performance parameters.

[0006] To achieve the above objectives, the technical solution adopted by this invention is: a method for performance testing and optimization of small-diameter pipes, comprising: Three-dimensional parameter data of small-diameter pipes are collected by scanning, and a collaborative model for performance testing is constructed based on the three-dimensional parameter data; Multiple performance testing targets for small-diameter pipes are identified. For each performance testing target, the corresponding production process parameters of the process steps are determined and collected, and the actual performance parameters are obtained through testing. Based on each performance detection target, the production process parameters of the corresponding process step are mapped to the collaborative model to construct a performance mimicry calculation model that matches the performance detection target. The performance of small-diameter pipes under different performance testing targets and different process conditions is tested using the performance mimicry calculation model to obtain the mimicry performance parameters corresponding to the performance testing targets. Based on the actual performance parameters and the mimicry performance parameters, determine the performance change fitting relationship corresponding to each performance detection target; Based on the performance change fitting relationship, the abnormal performance and optimization direction corresponding to the performance detection target are determined.

[0007] Furthermore, the scanning and acquisition of three-dimensional parameter data of the small-diameter tube, and the construction of a collaborative model for performance testing based on the three-dimensional parameter data, includes the following steps: Several small-diameter pipe samples were selected from the batch to be tested, and the pipe geometry parameters and surface quality parameters of the samples were collected by three-dimensional laser scanning and CT detection. An initial collaborative model is constructed based on the tube's geometric parameters and surface quality parameters; The key parameters of the initial collaborative model were verified through offline testing to obtain the collaborative model.

[0008] Furthermore, the performance testing targets include dimensional performance, heat transfer performance, molding performance, and microgram weight performance.

[0009] Furthermore, the process of determining and collecting the corresponding production process parameters for each performance testing target, and detecting and obtaining the actual performance parameters, includes the following steps: For each performance testing target, the key influencing process steps are identified in reverse, and a differentiated parameter acquisition scheme is determined based on different process steps. Based on the differentiated parameter acquisition scheme, different sensing components are arranged in the corresponding process steps, and each sensing component is responsible for acquiring a type of production process parameter. The sensing component collects the production process parameters in real time during the production of small-diameter pipes to obtain the actual performance parameters.

[0010] Furthermore, the step of mapping the production process parameters of the corresponding process step to the collaborative model based on each performance detection target, and constructing a performance mimicry calculation model that matches the performance detection target, includes the following steps: For each performance testing target, determine the corresponding data mapping rules; The production process parameters of the corresponding process steps are classified according to their attributes, and the classified production process parameters are mapped to the collaborative model according to the corresponding data mapping rules. Based on the construction rules for different detection performance targets, performance mimicry calculation models corresponding to each performance detection target are constructed respectively.

[0011] Furthermore, the performance mimicry calculation model includes a size structure model, a heat transfer performance model, a molding defect model, and a microgram weight model.

[0012] Furthermore, the step of testing the performance of small-diameter pipes under different performance testing targets and different process conditions using the performance mimicry calculation model, and obtaining the mimicry performance parameters corresponding to the performance testing targets, includes the following steps: For each performance testing target, the key parameter range and boundary conditions of the operating conditions are determined and input; wherein, a uniform process parameter variation gradient is set, and when testing a single performance testing target, other irrelevant process parameters are fixed, and multiple sets of parameter coupling operating conditions are set. The performance mimicry calculation model calculates the mimicry performance parameters corresponding to different performance detection targets based on the input key parameter range of the working condition and the boundary conditions. The obtained mimicry performance parameters are corrected through model self-validation, and the qualified mimicry performance parameters are classified and stored to form a dataset.

[0013] Furthermore, determining the performance change fitting relationship corresponding to each performance detection target based on the actual performance parameters and the mimicry performance parameters includes the following steps: The actual performance parameters and the simulated performance parameters are preprocessed to establish an associated dataset; Based on the parameter variation characteristics in the associated dataset, a suitable fitting model is selected, and a fitting operation is performed on the associated dataset to construct the corresponding fitting relationship; The reliability of the fitting relationship is evaluated and the accuracy of the fitting model is iteratively optimized, and the final fitting relationship of performance change corresponding to each performance detection target is output.

[0014] Furthermore, determining the abnormal performance and optimization direction corresponding to the performance detection target based on the performance change fitting relationship includes the following steps: For different performance testing targets, corresponding qualified threshold ranges are set, and single performance parameter anomaly screening is performed through the qualified threshold ranges to obtain single performance influencing factors. Based on the coupling relationship between multiple performance parameters, cross-joint anomaly screening of multiple performance parameters is performed to obtain the joint impact performance factor. Based on the performance change fitting relationship, the change trend and sensitivity of each performance parameter are determined; Based on the changing trend and sensitivity, a target priority and weighting system for performance parameters is established, and the balance value of each performance parameter is determined based on the qualified threshold range. The optimized process parameters corresponding to the equilibrium value are substituted into the performance change fitting relationship for verification. It is determined whether the performance parameters are qualified. If qualified, the equilibrium value and the corresponding post-process parameters are output. If unqualified, the optimization direction is readjusted and the verification is performed again until the performance parameters are qualified.

[0015] The present invention also provides a performance testing and optimization system for small-diameter pipes, comprising: The collaborative model building module is used to scan and collect three-dimensional parameter data of small-diameter pipes, and to build a collaborative model for performance testing based on the three-dimensional parameter data. The real-time performance parameter acquisition module is used to determine multiple performance testing targets for small-diameter pipes, determine and collect the corresponding production process parameters for each performance testing target, and detect and obtain the real-time performance parameters. The computational model building module is used to map the production process parameters of the corresponding process step to the collaborative model based on each performance detection target, and to build a performance mimicry computational model that matches the performance detection target. The mimicry performance parameter acquisition module is used to test the performance of small-diameter pipes under different performance testing targets and different process conditions through the performance mimicry calculation model, and to acquire the mimicry performance parameters corresponding to the performance testing targets. The fitting relationship confirmation module is used to determine the performance change fitting relationship corresponding to each performance detection target based on the actual performance parameters and the mimicry performance parameters. An anomaly optimization module is used to determine the corresponding abnormal performance and optimization direction under the performance detection target based on the performance change fitting relationship.

[0016] The beneficial effects of this invention are as follows: This invention constructs a collaborative model by scanning and collecting three-dimensional parameters, and generates a performance mimicry calculation model by mapping the production process parameters of the process links. This achieves accurate simulation of actual complex working conditions, improves the fit between mimicry performance parameters and actual performance parameters, and effectively reduces the deviation between test results and actual service performance. Furthermore, it constructs the correlation between performance test targets, the performance of small-diameter pipes, and process links. By fitting the relationship, the process influence parameters corresponding to abnormal performance can be determined, and the optimization direction can be accurately given. This effectively avoids the problems of over-correction or under-correction caused by manual derivation, and improves production efficiency and product qualification rate. Attached Figure Description

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

[0018] Figure 1 This is a flowchart illustrating the performance testing and optimization method for small-diameter pipes in an embodiment of the present invention. Figure 2 This is a schematic diagram of the process of constructing a collaborative model in an embodiment of the present invention; Figure 3 This is a schematic diagram of the process for obtaining real-time performance parameters in an embodiment of the present invention; Figure 4 This is a schematic diagram of the process for constructing the performance mimicry calculation model in an embodiment of the present invention; Figure 5 This is a schematic diagram of the process for obtaining mimicry performance parameters in an embodiment of the present invention; Figure 6 This is a schematic diagram of the process for determining the fitting relationship of performance changes in an embodiment of the present invention; Figure 7 This is a flowchart illustrating the process of determining abnormal performance and optimization direction in an embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments.

[0020] It should be noted that when an element is referred to as being "fixed to" another element, it can be directly attached to the other element or there may be an intervening element. When an element is referred to as being "connected to" another element, it can be directly connected to the other element or there may be an intervening element. The terms "vertical," "horizontal," "left," "right," and similar expressions used herein are for illustrative purposes only and do not represent the only possible implementation.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used in this specification is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0022] The collaborative model includes at least a geometric layer characterizing the three-dimensional structure of the tube, a physical layer characterizing the material properties of the tube, and an interface layer for preset process parameters. like Figures 1 to 7 The performance testing and optimization method for small-diameter pipes shown includes: Three-dimensional parameter data of small-diameter pipes are collected by scanning, and a collaborative model for performance testing is constructed based on the three-dimensional parameter data. The three-dimensional parameter data refers to the information of the geometric dimensions, shape, surface texture, and internal structure of the small-diameter pipe in three-dimensional space. By obtaining the three-dimensional geometric parameters such as the outer diameter, wall thickness, and ellipticity of the small-diameter pipe, the physical characteristics of the pipe body can be comprehensively and accurately described. The collaborative model can integrate multiple attributes of the pipe body such as geometry, material, and structure, and provide an accurate basic model for performance testing. This ensures that the subsequent biomimetic calculation model can truly reflect the physical morphology of the pipe and avoid detection deviations caused by geometric parameter distortion. Multiple performance testing targets for small-diameter pipes were identified. For each performance testing target, corresponding process parameters for the manufacturing process were determined and collected, and actual performance parameters were obtained. Performance testing targets refer to the key performance indicators that need to be monitored and evaluated during the production and application of small-diameter pipes, such as dimensional accuracy, heat exchange efficiency, forming stability, and mass per unit length. Process parameters refer to controllable or measurable physical quantities involved in the stretching, annealing, and cooling processes during the manufacturing of small-diameter pipes, such as temperature, pressure, stretching speed, cooling medium flow rate, and material composition ratio. Actual performance parameters refer to the actual values ​​of various performance indicators measured under the specific operating conditions and during production, reflecting the performance of small-diameter pipes under actual operating conditions. On the one hand, by defining multiple performance testing targets, the comprehensiveness of the testing is ensured; on the other hand, by collecting corresponding process parameters and actual performance parameters, real-world data is provided for the construction of a performance mimicry calculation model, establishing a correlation between the manufacturing process and the performance of small-diameter pipe products. Based on each performance testing target, the production process parameters of the corresponding process link are mapped to the collaborative model to construct a performance mimicry calculation model that matches the performance testing target. By mapping the production process parameters of specific production links to the collaborative model, the coupling between the actual working conditions and the performance mimicry calculation model is ensured, so that the mimicry calculation model can accurately simulate the performance of pipes under different process conditions, thereby solving the problem of the disconnect between traditional testing and the production environment. The performance of small-diameter pipes under different performance testing targets and different process conditions is tested by using a performance mimicry calculation model to obtain the mimicry performance parameters corresponding to the performance testing targets. The performance mimicry calculation model refers to a simulation model built based on a collaborative model and combined with specific performance testing targets, using mathematical algorithms and principles to reproduce the performance under different process conditions in a mimicry environment and predict its performance parameters. This eliminates the need for repeated verification under actual working conditions, reduces testing costs and material consumption, and can quickly obtain mimicry performance parameters under different working conditions. It accurately reflects the simulation results of the model on the performance of small-diameter pipes and provides sufficient samples for subsequent fitting analysis. Based on the actual performance parameters and the mimicry performance parameters, the fitting relationship of performance change corresponding to each performance detection target is determined; by establishing the fitting relationship of performance change between the actual performance parameters and the mimicry performance parameters, the function or curve of the performance of small diameter pipe with the change of process parameters or operating conditions is obtained, and the influence of process parameter changes on performance is analyzed and clarified, so that the output results of the performance mimicry calculation model have verifiability and reliability, and provide a basis for anomaly diagnosis. Based on the performance change fitting relationship, the abnormal performance and optimization direction corresponding to the performance testing target are determined; the performance change fitting relationship is used to identify the performance of small-diameter pipes that exceed the expectations or do not meet the standard requirements under specific performance testing targets, and the test results are transformed into the optimization direction required for the production process, so as to further form targeted process adjustment or improvement suggestions as production optimization schemes to guide the adjustment of production processes, forming a process of detection, diagnosis and optimization to be applicable to diverse performance testing and optimization needs; This invention constructs a collaborative model by scanning and collecting three-dimensional parameters, and generates a performance mimicry calculation model by mapping production process parameters of each process step. This achieves accurate simulation of actual complex working conditions, improves the fit between mimicry performance parameters and actual performance parameters, and effectively reduces the deviation between test results and actual service performance. Furthermore, it establishes the correlation between performance test targets, the performance of small-diameter pipes, and process steps. By fitting the relationship, the process influence parameters corresponding to abnormal performance can be determined, and the optimization direction can be accurately given. This effectively avoids the problems of over-correction or under-correction caused by manual derivation, and improves production efficiency and product qualification rate.

[0023] The following detailed example illustrates the above technical solution: Assume performance testing and optimization of copper tubes produced on a production line are required. First, on the production line, a handheld laser scanner scans each small-diameter tube, collecting three-dimensional parameter data such as its external geometric dimensions and surface roughness. This data is input into the factory's central control system, and a digital collaborative model is constructed based on this data. For example, a copper tube with a length of 2000mm and an outer diameter of 5mm is constructed. Next, multiple performance testing targets are determined, such as dimensional accuracy, heat transfer performance, and forming performance. For the dimensional accuracy target, production process parameters such as stretching speed and annealing temperature in key process steps such as the stretching machine and annealing furnace are automatically identified and collected. Simultaneously, the actual length and outer diameter of the copper tube are measured in real time by online sensors to obtain real-time performance parameters. For example, in the stretching process, the stretching speed is set to 5 m / s, and the annealing temperature is 600 degrees Celsius. Through online measurement, the actual length is 2000.1mm, and the outer diameter is 5.02mm. Then, based on the performance testing objective of dimensional accuracy, the system maps the collected production process parameters, such as tensile speed and annealing temperature, into the aforementioned collaborative model through preset mapping rules. For example, changes in tensile speed affect the elongation of the tube, while annealing temperature affects the material's hardness and plasticity. Through these mapping relationships, a performance mimicry calculation model matching the dimensional accuracy objective is constructed to simulate the dimensional changes of the copper tube under different tensile speeds and annealing temperatures. Subsequently, this performance mimicry calculation model is used to test the dimensional performance of the copper tube under different combinations of tensile speeds and annealing temperatures. For example, various working conditions are simulated, such as tensile speeds ranging from 4.5 m / s to 5.5 m / s and annealing temperatures ranging from 580℃ to 620℃. Under each working condition, the corresponding mimicry length and mimicry outer diameter parameters are calculated. For example, when the tensile speed is 5.1 m / s and the annealing temperature is 605℃, the model predicts a mimicry length of 2000.3 mm and a mimicry outer diameter of 5.01 mm. Subsequently, the system compared and analyzed the actual length of 2000.1 mm and outer diameter of 5.02 mm collected online with the mimic length of 2000.3 mm and mimic outer diameter of 5.01 mm predicted by the model. A performance change fitting relationship was established between the actual and mimic dimensions using a data fitting algorithm. This relationship specifically represents the correlation between the actual trend of copper tube dimensions and the trend predicted by the model under different process parameters. Finally, based on the established performance change fitting relationship, potential abnormal dimensional performance in the current production batch can be identified, and specific optimization directions can be provided. For example, the fitting relationship shows that when the stretching speed exceeds 5.2 m / s, the actual outer diameter of the copper tube will significantly exceed the acceptable range. The system will then issue a warning and suggest adjusting the stretching speed to below 5.1 m / s to ensure the product dimensions are acceptable. Through these steps, the production process can be adjusted in a timely manner to avoid producing unqualified products.

[0024] Based on the above embodiments, three-dimensional parameter data of small-diameter pipes are scanned and collected. A collaborative model for performance testing is constructed based on the three-dimensional parameter data, including the following steps: Several small-diameter pipe samples are selected from the batch to be tested. The geometric parameters and surface quality parameters of the samples are acquired through 3D laser scanning and CT inspection. Specifically, by randomly or in a specific manner selecting a certain number of small-diameter pipe samples from the entire batch to be tested, the problem of insufficient model generalization ability due to sample selection bias can be effectively avoided. For example, random sampling can be used, drawing one sample from the production line at certain intervals or after each certain quantity is produced. Alternatively, stratified sampling can be used, classifying small-diameter pipes according to factors such as production batch, production date, and raw material batch, and then sampling is drawn proportionally from each category to ensure that samples under different production conditions are covered. Alternatively, a combination of stratified sampling and random sampling can be used to ensure that the data used for model construction and validation is representative.

[0025] By employing 3D laser scanning and CT inspection, the geometric and surface quality parameters of the sample are acquired, providing accurate and comprehensive foundational data for the construction of the collaborative model. 3D laser scanning primarily acquires external geometric features, while CT inspection can penetrate the material to obtain information on internal structure and defects. Specifically, a high-precision industrial-grade 3D laser scanner can be used to quickly acquire geometric dimensional data such as the outer diameter, wall thickness, roundness, and straightness of small-diameter pipes through non-contact scanning, as well as precise 3D coordinate data of surface defects such as surface roughness, scratches, and dents. Simultaneously, industrial computed tomography (CT) equipment can be used to perform non-destructive testing on small-diameter pipe samples, acquiring their internal structural information, such as the size, location, and morphology of internal pores, inclusions, cracks, and other defects, as well as more precise internal wall thickness distribution and other pipe geometric parameters.

[0026] An initial co-model is constructed based on the pipe's geometric parameters and surface quality parameters. This initial co-model can establish the relationship between the structure, characteristics, and performance of a small-diameter pipe. For example, finite element analysis software can be used to input the pipe's geometric parameters and surface quality parameters to construct a geometric model and material property model of the small-diameter pipe, and define its boundary conditions to form an initial co-model capable of simulating mechanical, thermal, or fluid performance. Alternatively, based on parametric modeling methods, CAD / CAE software can be used to automatically generate or adjust a digital model of the small-diameter pipe based on the collected pipe geometric parameters and surface quality parameters, and integrate a material database to construct an initial co-model that can be used for preliminary performance evaluation.

[0027] The key parameters of the initial collaborative model are validated through offline field tests to obtain the collaborative model. By comparing the output of the initial collaborative model with the actual physical test results, deviations in the model can be identified and corrected, thus making the model more accurately reflect the true performance of small-diameter pipes. Specifically, physical performance tests can be performed on small-diameter pipe samples, such as tensile tests, bending tests, pressure tests, or heat conduction tests, to obtain their true mechanical, fluid, or thermal performance data. Then, these measured data are compared with the performance data predicted by the initial collaborative model under the same conditions, and the material parameters, boundary conditions, or calculation methods in the model are adjusted until the model prediction results highly match the measured results. In addition, destructive or non-destructive tests can be performed on small-diameter pipes, such as metallographic analysis, hardness testing, and eddy current testing, to obtain the actual situation of their microstructure, material homogeneity, or internal defects. These measured results are cross-validated with the corresponding parameters in the initial collaborative model to improve the accuracy of the model, ultimately forming a validated collaborative model.

[0028] Based on the above embodiments, the performance testing targets include dimensional performance, heat transfer performance, forming performance, and per-unit weight performance. Specifically, dimensional performance refers to the geometrical accuracy of small-diameter pipes, such as outer diameter, inner diameter, wall thickness, ellipticity, and straightness, which affect the assembly accuracy and fluid transport performance of the pipe. Heat transfer performance refers to the efficiency and capacity of small-diameter pipes in heat exchange during fluid transport, typically related to factors such as the thermal conductivity, surface area, wall thickness, and internal fluid flow regime of the pipe. Forming performance refers to the plastic deformation capacity, crack resistance, and final forming quality of the material during manufacturing processes such as stretching, bending, and welding, including surface defects such as scratches and dents, internal defects such as cracks and inclusions, and geometric deviations. Per-unit weight performance refers to the mass per unit length of small-diameter pipe, typically used to assess material utilization, cost, and weight requirements in specific applications. It is related to parameters such as the density, outer diameter, inner diameter, and wall thickness of the pipe.

[0029] By taking a comprehensive view of performance dimensions, we ensure that all key performance aspects of small-diameter pipes are fully covered in the subsequent process of collecting production process parameters, detecting real-time performance parameters, and building performance mimicry calculation models. This avoids detection blind spots and optimization deviations caused by missing performance targets.

[0030] Based on the above embodiments, for each performance testing target, the corresponding production process parameters of the process steps are determined and collected, and the actual performance parameters are detected and obtained, including the following steps: For each performance testing target, the key influencing process steps are identified through reverse engineering, and differentiated parameter acquisition schemes are determined based on these steps. The aim is to accurately pinpoint the production steps that have the greatest impact on specific performance targets and tailor data acquisition strategies for these steps. Reverse engineering to identify key influencing process steps can be based on historical production data analysis, expert knowledge bases, or by using machine learning models (such as decision trees and random forests) to mine the correlation between process parameters and performance targets. For example, for dimensional performance, the key influencing steps might be drawing and annealing; for heat transfer performance, it might be annealing and surface treatment. Determining differentiated parameter acquisition schemes means selecting different sensor types, data sampling frequencies, and data transmission methods based on the characteristics of different process steps and their degree of influence on performance targets. For example, high-frequency sampling may be needed for rapidly changing process parameters; periodic sampling may be used for environmental parameters.

[0031] Based on a differentiated parameter acquisition scheme, different sensing components are arranged in corresponding process stages. Each sensing component is responsible for acquiring a specific type of production process parameter. Specifically, the sensing components can be various types of sensors, such as temperature sensors, pressure sensors, flow sensors, displacement sensors, vibration sensors, and vision inspection systems. These sensing components are installed in the corresponding process stages of the small-diameter pipe production line according to the predetermined arrangement requirements of the differentiated parameter acquisition scheme. For example, a laser diameter gauge and a tension sensor are arranged in the drawing stage to monitor the pipe diameter and drawing force in real time; a furnace temperature sensor and a gas composition analyzer can be arranged in the annealing stage to monitor the annealing temperature and atmosphere uniformity. Each sensing component is configured to specifically acquire a particular type of production process parameter to ensure the specificity and accuracy of the data.

[0032] By using sensing components to collect production process parameters in real time during the production of small-diameter pipes, actual performance parameters can be obtained. These sensing components can acquire various parameters during the production process, such as temperature, pressure, speed, composition, and dimensions, forming the actual performance parameters of the small-diameter pipes under actual production conditions. These parameters directly reflect the current production status, providing a real and timely basis for subsequent performance analysis and optimization.

[0033] The above technical solution can accurately identify and efficiently collect key process parameters in the production of small-diameter pipes, ensuring the comprehensiveness, real-time nature and accuracy of the acquired real-world performance parameters. This provides high-quality input data for the subsequent construction of performance mimicry calculation models, thereby significantly improving the accuracy of small-diameter pipe performance testing results and laying the foundation for determining reliable optimization directions.

[0034] Based on the above embodiments, for each performance testing target, the production process parameters of the corresponding process step are mapped to the collaborative model to construct a performance mimicry calculation model that matches the performance testing target, including the following steps: For each performance testing target, a corresponding data mapping rule is determined. A data mapping rule refers to the logic or algorithm that establishes a connection between production process parameters of a specific technological stage and corresponding input variables in the collaborative model. This ensures that production process parameters from different sources and in different formats are accurately and effectively input into the collaborative model, providing a data foundation for subsequent performance mimicry calculations. In practical applications, the mapping relationship can be determined according to the specific requirements of the performance testing target. For example, dimensional performance testing requires mapping parameters such as pipe tensile speed and mold temperature, while heat exchange performance testing requires mapping parameters such as cooling medium flow rate and heating power. During processing, data mapping rules can be predefined as a series of data transformation functions, lookup tables, or machine learning-based mapping models. For example, an expert-experience-based rule engine can be used to define the mapping relationship, that is, based on the knowledge of domain experts, specific production parameters are mapped to specific physical quantities in the collaborative model; or, through historical data analysis, algorithms such as regression analysis or neural networks can be used to automatically learn and generate the mapping relationship between parameters and model inputs.

[0035] The production process parameters for corresponding technological stages are categorized according to their attributes, and then mapped to the collaborative model based on corresponding data mapping rules. Attribute classification of production process parameters refers to the structured organization of massive amounts of collected production data based on characteristics such as the physical meaning, measurement unit, data type, scope of influence, or technological stage to which the parameters belong, thereby improving data management efficiency and mapping accuracy. For example, production process parameters can be categorized into geometric dimensions, material properties, thermodynamic parameters, and fluid dynamics parameters. Based on this, the categorized production process parameters are mapped to the collaborative model according to corresponding data mapping rules. This involves inputting key influencing factors from the actual production environment into the model in a format and logic that the collaborative model can understand and process, thereby driving the model's calculations and simulations. The mapping process may include preprocessing operations such as data format conversion, unit unification, missing value imputation, and outlier handling. Furthermore, the mapping can be a many-to-one or one-to-many relationship, meaning that multiple production parameters may jointly affect a variable in the collaborative model, or a single production parameter may affect multiple variables in the collaborative model.

[0036] Based on the construction rules for different performance testing targets, performance mimicry calculation models are constructed for each performance testing target. The construction rules for performance mimicry calculation models refer to defining the structure, algorithm, and parameters of their respective mathematical, physical, or simulation models for different performance testing targets such as dimensional performance, heat transfer performance, molding performance, and per-unit weight performance. This ensures that each mimicry calculation model has high specificity and accuracy, and can accurately simulate the performance of specific characteristics. For example, for dimensional performance testing, a structural mechanics model based on finite element analysis can be constructed to simulate the deformation of the pipe under different stress conditions; for heat transfer performance testing, a heat transfer model based on computational fluid dynamics can be constructed to simulate the heat exchange process of the fluid inside and outside the pipe.

[0037] Based on the above embodiments, the performance mimicry calculation model includes a dimensional structure model, a heat transfer performance model, a forming defect model, and a microgram weight model. The dimensional structure model aims to simulate the geometry, dimensional accuracy, and structural changes of small-diameter pipes under different process conditions. It accurately characterizes the three-dimensional geometric features of the pipe body using digital means and predicts its deformation under the influence of external factors such as stress and heat. The heat transfer performance model simulates the heat transfer efficiency and thermodynamic behavior of small-diameter pipes under specific operating conditions to quantify the heat exchange capacity between the pipe body and the fluid, or between the pipe body and the external environment. The forming defect model predicts and analyzes various defects that may occur during the forming process of small-diameter pipes, such as cracks, wrinkles, eccentricity, and abnormal surface roughness, to establish the correlation between forming process parameters and the type and degree of defects. The microgram weight model simulates and predicts the mass per unit length of small-diameter pipes, which is typically related to material density, pipe wall thickness uniformity, and pipe diameter accuracy. This allows for precise control and evaluation of the material usage and uniformity of the pipe.

[0038] The above-mentioned performance mimicry calculation model ensures that high-precision mimicry performance parameters can be obtained under different performance testing targets, making optimization suggestions more accurate and improving the overall production quality and efficiency of small-diameter pipes.

[0039] Based on the above embodiments, the performance of small-diameter pipes under different performance testing targets and different process conditions is tested using a performance mimicry calculation model to obtain the mimicry performance parameters corresponding to the performance testing targets, including the following steps: For each performance testing target, key parameter ranges and boundary conditions are determined and input. A uniform gradient for process parameter changes is set, and when testing a single performance target, other irrelevant process parameters are fixed, and multiple sets of parameter-coupled operating conditions are set. Determining and inputting key parameter ranges and boundary conditions provides a clear input range and limitations for performance simulation. Specifically, reasonable key parameter ranges and boundary conditions can be determined by analyzing historical production data, expert experience, or industry standards. For example, the temperature parameter range can be set to [200℃, 400℃], the pressure parameter range to [5MPa, 15MPa], and boundary conditions such as maximum tensile speed and minimum cooling rate can be defined. These parameter ranges and boundary conditions can be manually input through the user interface or automatically imported by reading preset configuration files or parameter tables from a database. Furthermore, setting a uniform gradient for process parameter changes ensures the systematicity and comparability of the simulation test, avoiding deviations in simulation results due to inconsistent parameter change steps. For example, for temperature parameters, a test can be set to be performed every 10°C; for pressure parameters, a test can be set to be performed every 1 MPa; the gradient can be uniform or a non-uniform gradient can be preset according to the sensitivity of the parameter. When testing a single performance target, fixing other irrelevant process parameters is to isolate variables and ensure that the test results accurately reflect the impact of the target parameters on performance. For example, when testing the effect of tensile speed on dimensional properties, other process parameters such as heating temperature and cooling rate can be fixed. This can be achieved by locking the input values ​​of specific parameters in the simulation software or by setting these parameters as constants in the model configuration.

[0040] Setting up multiple sets of coupled parameter conditions is to simulate the complex interactions between various process parameters in actual production, thereby improving the realism and comprehensiveness of the simulation results. For example, different levels of multiple key process parameters can be selected for combined testing; or all parameter combinations can be automatically generated by an algorithm. These coupled conditions can then be input as a simulation task list into the performance mimicry calculation model to perform simulation operations.

[0041] The performance mimicry calculation model calculates the mimicry performance parameters corresponding to different performance detection targets based on the input key parameter range and boundary conditions. After receiving the key parameter range and boundary conditions, different performance mimicry calculation models calculate the performance of small-diameter pipes under corresponding conditions, such as size, heat transfer, forming, and weight per meter, according to their internal algorithms and logic, and output the corresponding mimicry performance parameters.

[0042] The obtained mimicry performance parameters are corrected through model self-validation, and the qualified mimicry performance parameters are categorized and stored to form a dataset. Correcting the obtained mimicry performance parameters through model self-validation improves the accuracy and reliability of simulation results. Specifically, the mimicry performance parameters are compared with known historical measured data to calculate and correct errors; or compared with benchmark values ​​calculated based on theoretical formulas to adjust parameters that exceed reasonable ranges. For example, an error threshold can be set; when the deviation between the mimicry parameter and the measured parameter exceeds this threshold, a correction mechanism is triggered, and the model is fine-tuned through iterative optimization algorithms or parameter adjustment rules until the deviation is within an acceptable range. The qualified mimicry performance parameters are categorized and stored to form a dataset for subsequent data analysis, model optimization, and performance prediction. Data storage can be categorized according to dimensions such as performance testing targets, process conditions, and batch information, and stored in a structured database; specific details are not provided here.

[0043] Based on the above embodiments, the performance change fitting relationship corresponding to each performance detection target is determined according to the actual performance parameters and the mimicry performance parameters, including the following steps: Preprocessing is performed on both real-world and pseudo-performance parameters to create an associated dataset. This preprocessing eliminates noise, missing values, and outliers in the original parameters, ensuring temporal, spatial, or logical alignment for effective subsequent correlation analysis. Creating the associated dataset matches and integrates the preprocessed real-world and pseudo-performance data into a unified dataset, guaranteeing the accuracy of the subsequent fitting model input. Specifically, preprocessing can be achieved through data cleaning techniques, such as mean imputation, regression imputation, or interpolation to handle missing values; scaling the data using Z-score standardization and Min-Max normalization to eliminate dimensionality effects; smoothing the data using moving averages and wavelet denoising to reduce noise interference; feature reduction using principal component analysis or independent component analysis to extract key information; identifying and processing outlier data points using clustering algorithms; and integrating real-world and pseudo-performance parameters from different sources through database joins or data fusion techniques to ensure data consistency and integrity.

[0044] Based on the parameter variation characteristics of the associated dataset, an appropriate fitting model is selected, and fitting operations are performed on the associated dataset to construct the corresponding fitting relationship. The accuracy of the model is ensured by selecting the mathematical model that best reflects the above pattern, and the data is mapped onto the model through fitting operations, thereby constructing a fitting relationship that can accurately describe the performance variation pattern.

[0045] The reliability of the fitted relationship is evaluated, and the accuracy of the fitted model is iteratively optimized, outputting the final fitted relationship of performance changes corresponding to each performance detection target. Through continuous iterative evaluation and optimization, the prediction accuracy and evaluation reliability of the model are improved, ensuring that the final output fitted relationship can be used for subsequent analysis.

[0046] Based on the above embodiments, the abnormal performance and optimization direction corresponding to the performance detection target are determined according to the performance change fitting relationship, including the following steps: For different performance testing targets, corresponding qualified threshold ranges are set, and single performance parameter anomalies are screened through qualified threshold ranges to obtain single performance influencing factors. The acceptable threshold range refers to the pre-defined acceptable performance range for each performance testing target. The acceptable threshold range can be set based on industry standards, customer specifications, historical production data statistical analysis, or expert experience. Single performance parameter anomaly screening refers to independently checking a single performance parameter to determine whether it exceeds the preset acceptable threshold range, thereby quickly identifying performance anomalies caused by a single factor, i.e., a single influencing performance factor. Specifically, this can be achieved by directly comparing the real-time collected performance parameters with the upper and lower limits of the acceptable threshold range; or by using statistical process control charts to identify anomalies.

[0047] Based on the coupling relationship between multiple performance parameters, cross-joint anomaly screening of multiple performance parameters is performed to obtain the joint impact performance factor. The coupling relationship between multiple performance parameters refers to the mutual influence and correlation between different performance parameters. By considering the interaction between multiple performance parameters, anomalies caused by the combined effect of multiple parameters can be identified. This reveals anomalies where a single parameter may be within acceptable limits, but the combination leads to poor overall performance, i.e., a joint performance factor. Specifically, implementation methods may include: constructing a multivariate statistical model to predict comprehensive performance and performing anomaly detection on the prediction results; or using cluster analysis to distinguish between normal and abnormal multidimensional performance data.

[0048] Based on the performance change fitting relationship, the changing trend and sensitivity of each performance parameter are determined. Using the performance change fitting relationship, the changes of performance parameters under different process conditions can be predicted. Among them, the changing trend refers to whether the corresponding performance parameter tends to increase, decrease, or remain stable when a certain process parameter changes. Sensitivity refers to the degree of response of the performance parameter to the change of a certain process parameter. The higher the sensitivity, the more sensitive the performance parameter is to the change of the process parameter. Determining the changing trend and sensitivity helps to identify the key process parameters that have the greatest impact on performance.

[0049] Based on the changing trends and sensitivity, a target priority and weighting system for performance parameters is established, and the balance value of each performance parameter is determined based on the qualified threshold range to ensure that the most important performance requirements are met first when multiple objectives conflict. Specifically, the target priority and weighting system refers to assigning different importance levels and influence coefficients to each performance parameter according to its criticality to product quality, function, cost, etc., and its sensitivity to changes in process parameters. The establishment method can be based on expert scoring, analytic hierarchy process (AHP), or analysis of the influence of different performance parameters on the final product qualification rate through historical data analysis, without specific limitations here. The balance value refers to the process parameter combination that, after considering the priority, weight, and mutual coupling relationship of all performance parameters, makes all performance parameters meet the qualified threshold range requirements as much as possible at the same time, or reaches the optimal compromise state when not all can be met. The determination method can be a multi-objective optimization algorithm to find the process parameter combination that optimizes the weighted performance index under the premise of satisfying constraints.

[0050] The optimized process parameters corresponding to the equilibrium value are substituted into the performance change fitting relationship for verification to determine whether the performance parameters are qualified. If qualified, the equilibrium value and the corresponding subsequent process parameters are output. If unqualified, the optimization direction is readjusted and verification is performed again until the performance parameters are qualified. By substituting the optimized equilibrium value into the previously established performance change fitting relationship, the various performance parameters of small-diameter pipes under this process condition can be predicted. That is, the effectiveness of the optimization scheme can be evaluated through model simulation, thereby determining whether the performance parameters are qualified. Specifically, the performance parameters predicted by the fitting relationship are compared with the preset qualified threshold range to determine whether they fall within the acceptable range. When the verification result shows that the performance parameters are unqualified, the optimization strategy or parameters are adjusted according to the specific circumstances of the unqualification, and then verification is performed again. After multiple iterations, it is ensured that the final output optimization scheme can make all key performance parameters meet the qualified standards.

[0051] As a specific implementation method, in the production process of small-diameter pipes, it is assumed that four performance testing targets need to be optimized: wall thickness uniformity, surface roughness, tensile strength, and heat transfer efficiency. First, for each of these four performance testing targets, a qualified threshold range can be set. For example, the qualified threshold range for wall thickness uniformity can be set to ±5% of the nominal wall thickness, surface roughness can be set to Ra value less than 0.8 micrometers, tensile strength can be set to greater than 200 MPa, and heat transfer efficiency can be set to greater than 90%. The system monitors these performance parameters in real time and further analyzes the coupling relationship between them. For example, historical data analysis reveals that a higher draw ratio may lead to a decrease in wall thickness uniformity, but simultaneously increase tensile strength; while a lower annealing temperature may lead to an increase in surface roughness and affect heat transfer efficiency. Based on this coupling, a cross-linked anomaly screening of multiple performance parameters can be performed. For example, if the wall thickness uniformity is on the edge of ±5%, but the tensile strength is also low, it indicates a problem with the drawing process parameters, thus identifying the draw ratio and annealing temperature as joint influencing performance factors. Next, using the previously established performance change fitting relationship, the system can determine the trends and sensitivities of each process parameter to changes in wall thickness uniformity, surface roughness, tensile strength, and heat transfer efficiency. For example, the model might show that wall thickness uniformity has the highest sensitivity to the draw ratio, while heat transfer efficiency has a relatively high sensitivity to surface roughness. Then, based on these trends and sensitivities, a target priority and weighting system for the performance parameters can be established. For example, if tensile strength is a key indicator of product safety, it can be assigned the highest priority and weight; wall thickness uniformity is moderate, while surface roughness and heat transfer efficiency are the lowest. Based on these priorities and weights, and combined with the acceptable threshold range, the system can use a multi-objective optimization algorithm to determine a set of equilibrium values, i.e., obtain an optimal combination of process parameters such as draw ratio, annealing temperature, and cooling rate, so that other performance parameters are also optimized as much as possible while meeting the tensile strength requirement. Finally, the optimized process parameters corresponding to this set of equilibrium values ​​are substituted into the performance change fitting relationship for verification. For example, the optimized draw ratio, annealing temperature, and cooling rate are input into the model to predict new wall thickness uniformity, surface roughness, tensile strength, and heat transfer efficiency. If the prediction results show that all performance parameters are within their respective acceptable threshold ranges, then the optimized process parameters are output as the final optimization direction. If the prediction results show that one or more performance parameters are still unacceptable, such as surface roughness still being too high, then the parameters or weights of the optimization algorithm are readjusted after feedback, and the optimization calculation and verification process are repeated until all performance parameters meet the acceptable standards.

[0052] The present invention also provides a performance testing and optimization system for small-diameter pipes, comprising: The collaborative model building module is used to scan and collect three-dimensional parameter data of small-diameter pipes, and to build a collaborative model for performance testing based on the three-dimensional parameter data. The real-time performance parameter acquisition module is used to determine multiple performance testing targets for small-diameter pipes, identify and collect the corresponding production process parameters for each performance testing target, and detect and obtain the real-time performance parameters. The computational model building module is used to map the production process parameters of the corresponding process steps to the collaborative model based on each performance detection target, and build a performance mimicry computational model that matches the performance detection target. The mimicry performance parameter acquisition module is used to test the performance of small-diameter pipes under different performance testing targets and different process conditions through a performance mimicry calculation model, and to obtain the mimicry performance parameters corresponding to the performance testing targets. The fitting relationship confirmation module is used to determine the fitting relationship of performance changes corresponding to each performance detection target based on the actual performance parameters and the mimicry performance parameters. The anomaly optimization module is used to determine the corresponding abnormal performance and optimization direction under the performance detection target based on the fitting relationship of performance changes.

[0053] This invention constructs a collaborative model by scanning and collecting three-dimensional parameters, and generates a performance mimicry calculation model by mapping production process parameters of each process step. This achieves accurate simulation of actual complex working conditions, improves the fit between mimicry performance parameters and actual performance parameters, and effectively reduces the deviation between test results and actual service performance. Furthermore, it establishes the correlation between performance test targets, the performance of small-diameter pipes, and process steps. By fitting the relationship, the process influence parameters corresponding to abnormal performance can be determined, and the optimization direction can be accurately given. This effectively avoids the problems of over-correction or under-correction caused by manual derivation, and improves production efficiency and product qualification rate.

[0054] The working method of the above system has been explained in the above embodiments, and will not be repeated here.

[0055] Those skilled in the art should understand that this invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to this invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for performance testing and optimization of small-diameter pipes, characterized in that, Includes the following steps: Three-dimensional parameter data of small-diameter pipes are collected by scanning, and a collaborative model for performance testing is constructed based on the three-dimensional parameter data; Multiple performance testing targets for small-diameter pipes are identified. For each performance testing target, the corresponding production process parameters of the process steps are determined and collected, and the actual performance parameters are obtained through testing. Based on each performance detection target, the production process parameters of the corresponding process step are mapped to the collaborative model to construct a performance mimicry calculation model that matches the performance detection target. The performance of small-diameter pipes under different performance testing targets and different process conditions is tested using the performance mimicry calculation model to obtain the mimicry performance parameters corresponding to the performance testing targets. Based on the actual performance parameters and the mimicry performance parameters, determine the performance change fitting relationship corresponding to each performance detection target; Based on the performance change fitting relationship, the abnormal performance and optimization direction corresponding to the performance detection target are determined.

2. The performance testing and optimization method for small-diameter pipes according to claim 1, characterized in that, The scanning and acquisition of three-dimensional parameter data of small-diameter tubes, and the construction of a collaborative model for performance testing based on the three-dimensional parameter data, includes the following steps: Several small-diameter pipe samples were selected from the batch to be tested, and the pipe geometry parameters and surface quality parameters of the samples were collected by three-dimensional laser scanning and CT detection. An initial collaborative model is constructed based on the tube's geometric parameters and surface quality parameters; The key parameters of the initial collaborative model were verified through offline testing to obtain the collaborative model.

3. The performance testing and optimization method for small-diameter pipes according to claim 1, characterized in that, The performance testing targets include dimensional performance, heat transfer performance, molding performance, and per-unit weight performance.

4. The performance testing and optimization method for small-diameter pipes according to claim 3, characterized in that, The process of determining and collecting the corresponding production process parameters for each performance testing target, and obtaining the actual performance parameters, includes the following steps: For each performance testing target, the key influencing process steps are identified in reverse, and a differentiated parameter acquisition scheme is determined based on different process steps. Based on the differentiated parameter acquisition scheme, different sensing components are arranged in the corresponding process steps, and each sensing component is responsible for acquiring a type of production process parameter. The sensing component collects the production process parameters in real time during the production of small-diameter pipes to obtain the actual performance parameters.

5. The performance testing and optimization method for small-diameter pipes according to claim 4, characterized in that, The step of mapping the production process parameters of the corresponding process step to the collaborative model based on each performance detection target, and constructing a performance mimicry calculation model that matches the performance detection target, includes the following steps: For each performance testing target, determine the corresponding data mapping rules; The production process parameters of the corresponding process steps are classified according to their attributes, and the classified production process parameters are mapped to the collaborative model according to the corresponding data mapping rules. Based on the construction rules for different detection performance targets, performance mimicry calculation models corresponding to each performance detection target are constructed respectively.

6. The performance testing and optimization method for small-diameter pipes according to claim 5, characterized in that, The performance mimicry calculation model includes a size structure model, a heat transfer performance model, a molding defect model, and a microgram weight model.

7. The performance testing and optimization method for small-diameter pipes according to claim 1, characterized in that, The process of testing the performance of small-diameter pipes under different performance testing targets and different process conditions using the performance mimicry calculation model, and obtaining the mimicry performance parameters corresponding to the performance testing targets, includes the following steps: For each performance testing target, the key parameter range and boundary conditions of the operating conditions are determined and input; wherein, a uniform process parameter variation gradient is set, and when testing a single performance testing target, other irrelevant process parameters are fixed, and multiple sets of parameter coupling operating conditions are set. The performance mimicry calculation model calculates the mimicry performance parameters corresponding to different performance detection targets based on the input key parameter range of the working condition and the boundary conditions. The obtained mimicry performance parameters are corrected through model self-validation, and the qualified mimicry performance parameters are classified and stored to form a dataset.

8. The performance testing and optimization method for small-diameter pipes according to claim 7, characterized in that, The step of determining the performance change fitting relationship corresponding to each performance detection target based on the actual performance parameters and the mimicry performance parameters includes the following steps: The actual performance parameters and the simulated performance parameters are preprocessed to establish an associated dataset; Based on the parameter variation characteristics in the associated dataset, a suitable fitting model is selected, and a fitting operation is performed on the associated dataset to construct the corresponding fitting relationship; The reliability of the fitting relationship is evaluated and the accuracy of the fitting model is iteratively optimized, and the final fitting relationship of performance change corresponding to each performance detection target is output.

9. The performance testing and optimization method for small-diameter pipes according to claim 8, characterized in that, The step of determining the abnormal performance and optimization direction corresponding to the performance detection target based on the performance change fitting relationship includes the following steps: For different performance testing targets, corresponding qualified threshold ranges are set, and single performance parameter anomaly screening is performed through the qualified threshold ranges to obtain single performance influencing factors. Based on the coupling relationship between multiple performance parameters, cross-joint anomaly screening of multiple performance parameters is performed to obtain the joint impact performance factor. Based on the performance change fitting relationship, the change trend and sensitivity of each performance parameter are determined; Based on the changing trend and sensitivity, a target priority and weighting system for performance parameters is established, and the balance value of each performance parameter is determined based on the qualified threshold range. The optimized process parameters corresponding to the equilibrium value are substituted into the performance change fitting relationship for verification. It is determined whether the performance parameters are qualified. If qualified, the equilibrium value and the corresponding post-process parameters are output. If unqualified, the optimization direction is readjusted and the verification is performed again until the performance parameters are qualified.

10. A performance testing and optimization system for small-diameter pipes, characterized in that, include: The collaborative model building module is used to scan and collect three-dimensional parameter data of small-diameter pipes, and to build a collaborative model for performance testing based on the three-dimensional parameter data. The real-time performance parameter acquisition module is used to determine multiple performance testing targets for small-diameter pipes, identify and collect the corresponding production process parameters for each performance testing target, and detect and obtain the real-time performance parameters. The computational model building module is used to map the production process parameters of the corresponding process step to the collaborative model based on each performance detection target, and to build a performance mimicry computational model that matches the performance detection target. The mimicry performance parameter acquisition module is used to test the performance of small-diameter pipes under different performance testing targets and different process conditions through the performance mimicry calculation model, and to acquire the mimicry performance parameters corresponding to the performance testing targets. The fitting relationship confirmation module is used to determine the performance change fitting relationship corresponding to each performance detection target based on the actual performance parameters and the mimicry performance parameters. An anomaly optimization module is used to determine the corresponding abnormal performance and optimization direction under the performance detection target based on the performance change fitting relationship.

Images