Thermal insulation color steel sandwich composite board product quality detection system based on digital twinning

Abstract

The invention discloses a thermal insulation color steel sandwich composite board product quality detection system based on digital twinning, and particularly relates to the field of quality control. The system comprises a composite board full-dimension three-dimensional digital model construction module, a production digital twinborn body creation module, a total-factor real-time data acquisition module, a data preprocessing module, a twinborn data driving and model calibration module, a quality intelligent analysis decision module and an optimization execution module. The model construction module constructs a reference model and embeds a process standard and a quality threshold value; the twin creation module builds a virtual production line, standardizes a data interface and assigns an ID to a plate; the data acquisition module acquires real-time data; the preprocessing module removes abnormal values, standardizes data and associates the data; the calibration module updates the twin body, calculates the deviation and calibrates the model; the analysis module realizes compliance judgment, defect analysis and quality prediction; and the optimization module generates and executes an instruction, so that the problems of low efficiency, data splitting and no closed loop of traditional detection are solved, and the quality control precision and efficiency are improved.

Description

TECHNICAL FIELD

[0001] The application relates to the technical field of quality control, in particular to a heat-insulating color steel sandwich composite board product quality detection system based on digital twinning. BACKGROUND

[0002] As a light, heat-insulating and easy-to-install building material, the heat-insulating color steel sandwich composite board is widely used in industrial plants, temporary buildings, cold chain warehouses and the like, and the quality of the board directly determines the structural safety, heat-insulating performance and service life of the building. The core quality indicators of the composite board include the flatness of the color steel panel, the thickness uniformity of the sandwich layer, the bonding strength of the bonding layer, the heat-insulating coefficient of the sandwich layer and the area of appearance defects, which need to be strictly controlled in the production process.

[0003] At present, the quality control of the composite board in the industry mainly relies on three traditional methods: one is manual sampling and offline measurement, for example, 3-5 samples are taken from each batch to detect the bonding strength in the laboratory, and the thickness of the sandwich layer is measured by a manual caliper; the second is the application of single-point automatic detection equipment, some enterprises introduce laser thickness meters to monitor the thickness of the sandwich layer and surface imaging instruments to identify surface scratches; and the third is the preliminary exploration of digital twinning technology.

[0004] However, in actual use, there are still some shortcomings, such as the small sample size of manual sampling in the prior art, which cannot represent the quality of the whole batch of products and is prone to miss hidden defects; the offline detection process is time-consuming, and by the time the detection result is issued, the unqualified products have been produced in batches, causing waste of raw materials and working hours, increasing production costs, the production parameters in the prior art are stored in the PLC control system, the quality detection data are recorded in the independent quality inspection terminal, and the environmental parameters are collected by scattered sensors, so that the data are stored in isolation and there is no correlation mechanism, when a quality defect occurs, the production and environmental parameters need to be checked manually one by one, it takes a long time to locate the root cause, the existing detection equipment can only output a binary decision result of qualified / unqualified, it cannot predict the quality trend based on historical data, nor can it automatically feedback adjustment instructions to the production line, for example, when the deviation of the thickness of the sandwich layer is detected to be out of limit, the operator needs to adjust the opening degree of the feeding valve based on experience, the adjustment accuracy is low, and the same problem is prone to occur repeatedly, the detection-analysis-adjustment-verification closed loop cannot be formed, the composite board is a three-layer heterogeneous structure of color steel panel-bonding layer-sandwich layer, the traditional single-part twinning modeling method cannot accurately represent the physical properties of each layer at the same time, the production data are multi-source and heterogeneous, and there is no unified interface, so that the virtual model cannot reflect the physical production line state in real time, there is no special simulation model for the quality defects of the composite board, the defects cannot be reproduced and the root cause cannot be verified in the virtual scene, and the digital twinning only stays at the visualization level and does not play a control value. SUMMARY

[0005] In order to overcome the above-mentioned defects of the prior art, embodiments of the present application provide a digital twin-based heat-insulating color steel sandwich composite board product quality detection system, which solves the problems raised in the above background art through the following scheme.

[0006] To achieve the above object, the present application provides the following technical scheme: a digital twin-based heat-insulating color steel sandwich composite board product quality detection system, comprising a composite board full-dimension three-dimensional digital model construction module for constructing an integrated reference model of the composite board; A production digital twin creation module is constructed based on the integrated reference model to construct a dynamic digital twin; A full-element real-time data acquisition module is used to acquire full-dimension data through a distributed acquisition network to provide data support for twin calibration and quality analysis; A data preprocessing module is used to preprocess the original full-dimension data on the edge computing node to eliminate noise and outliers; A twin data driving and model calibration module is used to update the dynamic digital twin Mt through real-time data, calculate the virtual-real deviation and dynamically calibrate; A quality intelligent analysis and decision module is used to perform quality analysis based on the calibrated twin and output decision results; An optimization execution module generates optimization instructions based on the analysis and decision results of the quality intelligent analysis and decision module and executes the optimization instructions as production adjustment actions.

[0007] The technical effects and advantages of the present application are as follows: 1. The present application realizes real-time acquisition of production full-link data through a distributed acquisition network, assigns a unique RFID identifier to each composite board, realizes one-by-one detection, detects all core quality indicators, improves detection efficiency, and transmits data to the digital twin in real time without offline waiting, so that unqualified products can be identified in real time during the production process of the composite board, and batch waste is avoided; 2. The present application cleans and standardizes multi-source data through the data preprocessing module, binds the full-life cycle data of the same composite board based on the RFID identifier, and stores it in a unified database; the quality intelligent analysis and decision module can directly call associated data, calculate the correlation between quality defects and production parameters through the Pearson correlation coefficient, and combine virtual simulation verification to shorten the root cause positioning time from traditional hours to 5-10 minutes and improve positioning accuracy; 3. This invention trains an LSTM model based on historical data, which can predict the trend and fluctuation range of key quality indicators in the next 1-2 hours, enabling proactive prevention. The optimization execution module outputs two types of instructions: one type of instruction is automatically sent to the PLC through the OPCUA interface to control the equipment to adaptively adjust parameters; the other type of instruction pushes an optimization report containing root causes, measures, and expected effects to the operator. After execution, the effect is verified by comparing the quality data before and after the adjustment through a twin. The qualified data is stored in the knowledge base to iterate the model, continuously improving the prediction accuracy and forming a complete closed loop. 4. This invention employs layered parametric modeling, constructing and fusing sub-models for the color steel panel, adhesive layer, and sandwich layer respectively, accurately representing the physical properties of each layer. It achieves unified mapping of multi-source heterogeneous data through the OPCUA standardized interface, and combines virtual-real deviation calculation and model calibration to ensure high-fidelity consistency between the digital twin and the physical production line. It also includes a built-in simulation model for composite panel defects, which can reproduce issues such as thickness deviation and appearance defects in a virtual scene, verify the root cause, and upgrade the digital twin from visualization to a control tool, adapting to the needs of composite panel production lines. Attached Figure Description

[0008] Fig. 1 This is a schematic diagram of the overall structure of the present invention; Fig. 2 This is a schematic diagram of the process of the present invention. Detailed Implementation

[0009] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0010] As attached Figs. 1-2 The digital twin-based product quality inspection system for insulated color steel sandwich composite panels shown includes: Composite Panel Full-Dimensional 3D Digital Model Building Module: Used to build an integrated benchmark model of the composite panel; The method for constructing the integrated benchmark model M0 is as follows: Layered modeling: For the three-layer structure of the composite panel (A), adhesive layer (B), and core layer (C), a parametric modeling method is used to construct sub-models for each layer. Color steel panel (A): Define geometric parameters (length L1, width W1, thickness d1) and physical properties (elastic modulus E1, Poisson's ratio μ1, thermal conductivity λ1). Adhesive layer (B): Define geometric parameters (thickness d2) and physical properties, including design bond strength σ0 and curing temperature range Tsolid. Core layer (C): define geometric parameters thickness d3 and physical properties including design thermal insulation coefficient K0 and design density p0, the reason for using parameterized modeling is that composite board orders need to be customized in size (such as length L1 can be set to 6m, 9m or 12m), by modifying the geometric parameters, a new specification digital model can be quickly generated, which is suitable for flexible production; The process standard of the integrated reference model is embedded as follows: the ideal process parameters (qualified production baseline) of the production process are associated with the reference model M0, and the ideal process parameters include: Feeding stage: color steel coil tension F0 (2-3kN), core layer raw material design moisture content ω0 (≤5%); Pressing stage: design pressing temperature T0 (12-15℃), design pressing pressure P0 (1.5-2.MPa), design pressing time t0 (3-6s); Forming stage: design conveying speed V0 (1-1.5m / s), design cooling temperature Tcool0 (25-3℃).

[0011] Quality threshold definition: embed the qualified range of each quality index in the reference model M0 as the basis for subsequent quality judgment: Color steel panel flatness AL (deviation of measured flatness from design value): the qualified range is AL∈[-1mm,+1mm]; Core layer thickness uniformity Ad3 (deviation of measured thickness from design thickness d3): the qualified range is Ad3∈[-.5mm,+.5mm]; Bonding strength σ (measured value): the qualified range is σ≥.8σ0; Thermal insulation coefficient K (measured value): the qualified range is K∈[0.95K0,1.5K0]; Appearance defect area Sdef (measured value): the qualified range is Sdef≤5mm².

[0012] Production digital twin creation module: build a dynamic digital twin based on the integrated reference model; The construction method of the dynamic digital twin is as follows: S1.1 Virtual production line construction: in the digital twin platform (such as Unity, TwinBuilder), build a virtual scene according to the layout of the physical production line (feeding unit → pressing unit → forming unit → detection unit → stacking unit), including virtual equipment (virtual roller press, virtual laser detector), virtual materials (composite board digital model) and virtual environment (virtual workshop temperature Tvirtual, virtual workshop humidity Hvirtual); S1.2 Data interface standardization: Develop a standardized data interface (using OPCUA protocol) for the PLC, sensors, and detection instruments of the physical production line, so that the twin Mt can read real-time data from the physical equipment through the interface (such as the actual pressing temperature Treal and the actual pressing pressure Preai of the roller press), ensuring real-time data transmission and compatibility; S1.3 Unique identity assignment: Assign a unique identity ID to each piece of composite board entering the production line (using RFID tags), and assign the same ID to the corresponding virtual composite board in the twin Mt, realizing the binding of physical and virtual boards. The reason for choosing RFID tags is that they can withstand the high temperature of 150°C during the pressing stage and can be quickly identified by the readers of each production node, allowing real-time updates of board position and state data.

[0013] Full-factor real-time data acquisition module: used to collect full-dimensional data through a distributed acquisition network, providing data support for twin calibration and quality analysis; The acquisition objects and functions of each device in the distributed acquisition network are as follows: Laser thickness gauge: deployed at the core layer inlet, collecting the actual core layer thickness d3real, with a measurement accuracy of ±0.01mm and a collection frequency of 1 per board; Moisture content sensor: deployed at the core layer raw material warehouse outlet, collecting the actual core layer raw material moisture content ωreal, with a collection frequency of 1 per roll of raw material; Thermocouple sensor: installed on the surface of the roller press pressing roller, collecting the actual pressing temperature Treal, with a collection frequency of 10 times per second; Pressure sensor: installed on the hydraulic system of the roller press, collecting the actual pressing pressure Preai, with a collection frequency of 10 times per second; Encoder: installed on the shaft end of the conveying roller motor, collecting the actual conveying speed Vreal, with a collection frequency of 5 times per second; 3D laser scanner: deployed at the molding unit outlet, collecting the actual flatness ΔLreal of the composite board, with a scanning speed of 500,000 points per second; Industrial camera: deployed with a ring light source at the appearance detection station, collecting the appearance image of the composite board, and calculating the actual appearance defect area Sdefact through image recognition algorithm, with a camera resolution of 20 million pixels and a frame rate of 15fps; Infrared thermal imager: deployed at the detection unit, collecting the surface temperature distribution of the composite board, calculating the actual thermal insulation coefficient Kreal, with a detection accuracy of ±0.001 W / (m・K); Human-machine interaction terminal (HMI): deployed at the operator station, recording operator ID, parameter adjustment records (such as manually adjusted pressing temperature values), and data recording mode is event triggered (automatic recording when adjustment operation occurs).

[0014] Data preprocessing module: used for preprocessing the original full-dimensional data at the edge computing node, eliminating noise and outliers, specifically including: Outlier rejection: using 3σ criterion, if the measured value x of a certain parameter exceeds the interval [μ-3σ, μ+3σ] (where μ is the historical mean of the parameter, and σ is the historical standard deviation of the parameter), it is determined as an outlier and is rejected, for example, the historical mean μ of the pressing pressure P is 1.8 MPa, and the standard deviation σ is 0.1 MPa, if the P of a certain collection is 10 MPa, which exceeds the interval [1.5 MPa, 2.1 MPa], it is determined as an outlier and is rejected; Data standardization: converting parameters of different dimensions to the interval [0, 1] through the standardization formula; Data association: through the unique identity ID of the composite board, the material data including d3, ω, the equipment data including T, P, and the quality data including ΔL, S, K corresponding to the same ID are bound to form a single plate full life cycle data file.

[0015] Twin data driving and model calibration module: used for updating the dynamic digital twin Mt through real-time data, calculating the virtual-real deviation and dynamically calibrating to ensure that Mt is highly consistent with the physical production line Pt.

[0016] The data mapping rule of the twin data driving and model calibration module is as follows: According to the ID matching and parameter corresponding principle, the preprocessed real-time data is mapped to the twin Mt: Geometric parameter mapping: the measured flatness ΔL and the measured length L1 collected by the 3D laser scanner are updated to the corresponding geometric parameters of the virtual composite board model; Physical property mapping: the measured moisture content ω collected by the moisture content sensor is used to correct the density of the virtual core layer model - the increase of moisture content will lead to the increase of the density of the core layer, and the correction formula is: Where ρ is the calibrated density of the virtual core layer, ρ0 is the design density of the core layer, and 0.02 is the correlation coefficient of moisture content-density measured by experiment; Process parameter mapping: the measured pressing temperature T and the measured pressing pressure P collected by the PLC are synchronized to the running parameters of the virtual roll press, so that the temperature and pressure of the virtual roll press are consistent with those of the physical equipment; The calculation and calibration method of the virtual-real deviation is as follows: Virtual prediction: based on the current twin Mt, the simulation module is run to predict the quality indicators of the composite board, including the predicted bonding strength σ and the predicted thermal insulation coefficient K; Deviation calculation: the absolute deviation of the predicted value and the measured value is calculated, and the formula is: , where Δσ is the bonding strength deviation, and ΔK is the thermal insulation coefficient deviation; Model calibration: if the deviation exceeds the allowable range (e.g., Δσ > 0.05σ0, σ0 is the designed bonding strength), the curing kinetics model parameters of the virtual bonding layer are calibrated, and the initial model of the curing degree αpre (the curing degree is positively correlated with the bonding strength, σpre = σ0 x αpre) of the virtual bonding layer, the pressing temperature, and the pressing time is: where k is the initial base coefficient, a is the initial temperature influence coefficient, and b is the initial time influence coefficient. The calibration process updates the model parameters by fitting the historical data (historical measured pressing temperature Thistory, historical measured pressing time thistory, and historical measured curing degree αhistory) through the least squares method: where 0.1 is the parameter adjustment coefficient (verified through a large number of experiments to balance the calibration speed and stability), knew, anew, and bnew are the calibrated parameters, and substituting the curing degree model can make the next predicted σpre closer to σreal.

[0017] Quality intelligent analysis and decision module: used for quality analysis based on the calibrated twin and outputting decision results; The quality analysis method is as follows: S2.1 Compliance automatic determination: comparing the measured quality indicators of physical detection with the qualified range defined by the composite board full-dimensional three-dimensional digital model construction module, and determining the product grade by using the one-vote veto system: Premium product: all measured indicators are within the qualified range, and the deviation of key indicators (σreal, Kreal) is ≤0.05 times the design value (i.e., |σreal-σ0|≤0.05σ0, |Kreal-K0|≤0.05K0); Qualified product: all measured indicators are within the qualified range, but the deviation of key indicators is >0.05 times the design value; Unqualified product: any one measured indicator exceeds the qualified range (e.g., ΔLreal = 1.2 mm > 1 mm, or σreal = 0.7σ0 < 0.8σ0), and a quality determination report containing ID, measured values of each indicator, and grade is generated for each composite board after determination, and is synchronized to the twin Mt, which is marked with different colors in the virtual scene (green = premium product, yellow = qualified product, and red = unqualified product); S2.2 Defect root cause analysis: when the product is determined to be unqualified or qualified but the deviation of key indicators is large, the root cause is located through parameter correlation analysis and virtual simulation verification: The parameter correlation analysis is as follows: the Pearson correlation coefficient r of the quality defect indicators and each production parameter is calculated to quantify the correlation, and the formula is: ​​wherein n is the number of samples, xi is the measured value of the i th production parameter (such as T real, P real ), yi is the measured value of the defect index of the corresponding sample (such as Δd3 real ), the absolute value of r is closer to 1, the stronger the correlation between the production parameter and the defect index; The virtual simulation verification is as follows: in the twin Mt, fixing other parameters, only adjusting 2-3 production parameters with the strongest correlation (such as reducing T real from 120℃ to 100℃), running the simulation module, and observing whether the defect of the virtual composite board is reproduced (such as whether Δd3 virtual increases from 0.3mm to 1.2mm), if it is reproduced, it is confirmed that the parameter is the root cause.

[0018] S2.3 Quality Trend Prediction: Based on historical data (production parameter and quality index data in the past 3 months), an LSTM (Long Short-Term Memory Network) model is trained to predict the quality trend in the next 1-2 hours, and to give early warning of potential defects: Model input: time series production parameter data (such as T real, P real, V real, ω real, T ring real, H real ) divided by 10-minute time windows, each time window contains 600 data points (10 times / second x 60 seconds x 10 minutes); Model output: predicted mean and fluctuation range of key quality indicators (σ, K, Δd3) in the next 1 hour; Prediction accuracy measurement: the root mean square error (RMSE) is used to measure the deviation between the predicted value and the measured value, the formula is: wherein yi is the i th measured quality index value, is the corresponding predicted value, n is the number of prediction samples, and the model training target is RMSE<0.03x design value (to ensure prediction accuracy); Early warning trigger: if the predicted quality index fluctuation range touches the boundary of the qualified threshold (such as the minimum value of the predicted σ = 0.81σ0, close to the unqualified line of 0.8σ0), the early warning is triggered, and the prompt information of potential insufficient bonding strength is output.

[0019] Optimization execution module: based on the analysis and decision results of the quality intelligent analysis and decision module, optimization instructions are generated, and the optimization instructions are executed as production adjustment actions; The classification generation method of the optimization instructions is as follows: according to the analysis results of the quality intelligent analysis and decision module, the optimization instructions are generated in two categories: One type of instruction (adaptive adjustment): for simple linear deviation (such as T real =130℃ lower than the design value 140℃, and T real is confirmed as the root cause), the system automatically generates parameter adjustment instructions (such as increasing the pressing temperature to 145℃, and then reducing it to 140℃ after 5 minutes), without human intervention; Class II instructions (manual decision support): for complex nonlinear problems (such as the existence of Δd3 real overage and S lack of real overage at the same time, the root cause is the uneven particle size of the core layer raw material + uneven pressure distribution of the roller press), the system generates an optimization recommendation report, including problem description, root cause analysis, recommended measures (such as replacing the core layer raw material supplier and simultaneously performing dynamic balance calibration on the roller press), expected effect (such as adjusting Δd3 real to be controlled within ±0.3mm and S lack of real ≤30mm²), and pushing to the operator's HMI terminal; The execution method of the optimization instruction is as follows: Instruction issuance: Class I instructions are directly issued to the production line PLC through the OPCUA interface to control the corresponding equipment to perform adjustment (such as the temperature control module of the roller press receiving a temperature adjustment instruction, adjusting the power of the electric heating pipe to raise T real from 130℃ to 145℃); Class II instructions are manually triggered for execution by the operator after confirmation through the HMI terminal (such as starting the roller press dynamic balance calibration program); Effect data collection: after the execution of the instruction, the adjusted production parameters (such as adjusted T real and P real) and quality indicators (such as adjusted σ real and Δd3 real) are continuously collected and synchronized to the twin body; Verification and iteration: the digital twin engine compares the quality data before and after adjustment (such as σ real =0.7σ0 before adjustment and σ real =0.95σ0 after adjustment), judges whether the optimization effect meets the expectation (such as whether σ real ≥0.8σ0 is met), if the expectation is met, the data is stored in the knowledge base for subsequent iteration training of the LSTM model; if the expectation is not met, the quality intelligent analysis and decision module is returned to perform root cause analysis again until the problem is solved, forming a complete closed loop.

[0020] Secondly: in the drawings of the disclosed embodiments, only the structures related to the disclosed embodiments are involved, other structures can be referred to the usual design, and in the case of no conflict, the same embodiment and different embodiments of the present application can be combined with each other; Finally: the above only describes the preferred embodiments of the present application and is not used to limit the present application, any modification, equivalent replacement, improvement, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A product quality inspection system for thermally insulated color steel sandwich composite panels based on digital twins, characterized in that, include: Composite Panel Full-Dimensional 3D Digital Model Building Module: Used to build an integrated benchmark model of the composite panel; Digital twin creation module: Constructs dynamic digital twins based on an integrated baseline model; Real-time data acquisition module: Used to collect full-dimensional data through a distributed acquisition network, providing data support for twin calibration and quality analysis; Data preprocessing module: Used to preprocess raw full-dimensional data at edge computing nodes to eliminate noise and outliers; Twin data-driven and model calibration module: used to update the dynamic digital twin Mt through real-time data, calculate the virtual-real deviation and perform dynamic calibration; Quality Intelligent Analysis and Decision Module: Used for quality analysis based on calibrated twins and outputting decision results; Optimization Execution Module: Generates optimization instructions based on the analysis and decision results of the quality intelligent analysis and decision module, and executes the optimization instructions as production adjustment actions.

2. The product quality inspection system for thermally insulated color steel sandwich composite panels based on digital twins as described in claim 1, characterized in that: The method for constructing the integrated benchmark model M0 is as follows: Layered modeling: For the three-layer structure of the composite panel color steel panel A, adhesive layer B, and sandwich layer C, a parametric modeling method is used to construct sub-models for each layer. Color steel panel A: Define geometric parameters including length L1, width W1, thickness d1 and physical properties including elastic modulus E1, Poisson's ratio μ1, thermal conductivity λ1; Adhesive layer B: Defines geometric parameters, thickness d2, and physical properties including design bond strength σ0 and curing temperature range Tsolid; Sandwich layer C: Defines geometric parameters, thickness d3, and physical properties including design thermal insulation coefficient K0 and design density ρ0; The process standard embedding of the integrated benchmark model is as follows: The ideal process parameters of the production process are associated with the benchmark model M0. The ideal process parameters include: Feeding stage: tension of color steel coil F0, design moisture content of core layer raw material ω0; Pressing stage: Design pressing temperature T0, design pressing pressure P0, design pressing time t0; Forming stage: Design conveying speed V0, design cooling temperature Tcooling0; Quality threshold definition: The acceptable range of each quality indicator is embedded in the baseline model M0 as the basis for subsequent quality judgment. The flatness of the color steel panel ΔL: the acceptable range is ΔL∈[-1mm,+1mm]; Sandwich layer thickness uniformity Δd3: The acceptable range is Δd3∈[-.5mm,+.5mm]; Bond strength σ: The acceptable range is σ≥.8σ0; Thermal insulation coefficient K: The acceptable range is K∈[0.95K0,1.5K0]; The area of ​​the appearance defect, S_defect, is within acceptable limits: S_defect ≤ 5mm².

3. The product quality inspection system for thermally insulated color steel sandwich composite panels based on digital twins as described in claim 1, characterized in that: The method for constructing the dynamic digital twin is as follows: S1.1 Virtual Production Line Setup: In the digital twin platform, a virtual scene is built according to the layout of the physical production line, including virtual equipment, virtual materials, and a virtual environment; S1.2 Data Interface Standardization: Develop standardized data interfaces for PLCs, sensors, and testing instruments in physical production lines, enabling twins to read real-time data from physical equipment through the interfaces; S1.3 Unique Identifier Assignment: Assign a unique identifier (ID) to each composite board entering the production line, and assign the same ID to the corresponding virtual composite board in the twin entity Mt.

4. The product quality inspection system for thermally insulated color steel sandwich composite panels based on digital twins according to claim 1, characterized in that: The data acquisition objects and functions of each device in the distributed data acquisition network are as follows: Laser thickness gauge: Deployed at the core layer feed inlet, it collects the actual thickness d3 of the core layer with a measurement accuracy of ±0.01mm and a collection frequency of once per board; Moisture content sensor: Deployed at the outlet of the core layer raw material silo, it collects the measured moisture content ωactual of the core layer raw material, with a collection frequency of once per roll of raw material; Thermocouple sensor: installed on the surface of the pressing roller of the roller press, to collect the measured pressing temperature Tactual, with a sampling frequency of 10 times / second; Pressure sensor: installed in the hydraulic system of the roller press, to collect the measured pressing pressure P_actual, with a sampling frequency of 10 times / second; Encoder: Installed on the end of the conveyor roller motor shaft, it collects the actual conveying speed Vactual at a frequency of 5 times / second; 3D laser scanner: Deployed at the outlet of the molding unit, it collects the actual flatness ΔL of the composite board, with a scanning speed of 500,000 points / second; Industrial camera: Deployed at the appearance inspection station in conjunction with a ring light source to capture images of the composite board's appearance. The actual area of ​​the appearance defect, S_defect, is calculated using an image recognition algorithm. The camera has a resolution of 20 megapixels and a frame rate of 15fps. Infrared thermal imager: Deployed in the detection unit, it collects the surface temperature distribution of the composite board, calculates the measured thermal insulation coefficient Kactual, and has a detection accuracy of ±0.001 W / (m·K). Human-computer interaction terminal: Deployed at the workstation, it records operator ID and parameter adjustment records, and the data recording method is event-triggered.

5. The product quality inspection system for thermally insulated color steel sandwich composite panels based on digital twins according to claim 1, characterized in that: The data mapping rules for the twin data-driven and model calibration module are as follows: Based on the principle of ID matching and parameter correspondence, the preprocessed real-time data is mapped to the twin Mt: Geometric parameter mapping: The measured flatness ΔL and measured length L1 collected by the 3D laser scanner are updated to the corresponding geometric parameters of the virtual composite plate model; Physical property mapping: The measured moisture content ωactual collected by the moisture content sensor is used to correct the density of the virtual core layer model. The correction formula is as follows: , where ρvirtual is the calibrated density of the virtual sandwich layer, ρ0 is the designed density of the sandwich layer, and 0.02 is the correlation coefficient between the moisture content and density measured in the experiment; Process parameter mapping: The actual pressing temperature Tactual and actual pressing pressure Pactual collected by the PLC are synchronized to the operating parameters of the virtual roller press, so that the temperature and pressure of the virtual roller press are consistent with those of the physical equipment.

6. The product quality inspection system for thermally insulated color steel sandwich composite panels based on digital twins according to claim 1, characterized in that: The calculation and calibration method for the virtual-real deviation is as follows: Virtual prediction: Based on the current twin, run the simulation module to predict the quality indicators of the composite board, including predicting the bond strength σpre and the thermal insulation coefficient Kpre. Deviation calculation: Calculate the absolute deviation between the predicted value and the measured value. The formula is: , Where Δσ is the bond strength deviation and ΔK is the thermal insulation coefficient deviation; Model calibration: If the deviation exceeds the allowable range, calibrate the curing kinetic model parameters of the virtual adhesive layer. The initial model for the curing degree α of the virtual adhesive layer and the pressing temperature and pressing time is as follows: Where k is the initial baseline coefficient, a is the initial temperature influence coefficient, and b is the initial time influence coefficient. The calibration process uses the least squares method to fit historical data and update the model parameters. , , , where 0.1 is the parameter adjustment coefficient, and k new, a new, and b new are the calibrated parameters.

7. The product quality inspection system for thermally insulated color steel sandwich composite panels based on digital twins according to claim 1, characterized in that: The method for quality analysis is as follows: S2.1 Automatic Compliance Determination: The measured quality indicators of physical testing are compared with the acceptable range defined by the composite board full-dimensional three-dimensional digital model construction module, and a veto system is used to determine the product grade. Superior grade: All measured indicators are within the qualified range, and the deviation of the key indicators σactual and Kactual is ≤0.05 times the design value, that is, |σactual-σ0|≤0.05σ0, |Kactual-K0|≤0.05K0. Qualified product: All measured indicators are within the qualified range, but the deviation of key indicators is >0.05 times the design value; Non-conforming products: If any measured index exceeds the acceptable range, a quality judgment report containing ID, measured values ​​of each index, and grade will be generated for each composite board and synchronized to the twin, where it will be marked with different colors in the virtual scene. S2.2 Defect Root Cause Analysis: When a product is determined to be non-conforming or conforming but with significant deviations in key indicators, the root cause is located through parameter correlation analysis and virtual simulation verification. The parameter correlation analysis is as follows: The Pearson correlation coefficient r between the quality defect index and each production parameter is calculated to quantify the correlation. The formula is: , where n is the number of samples, xi is the measured value of the i-th production parameter, yi is the measured value of the defect index of the corresponding sample, and the closer the absolute value of r is to 1, the stronger the correlation between the production parameter and the defect index. The virtual simulation verification is as follows: In the twin, other parameters are fixed, and only the 2-3 production parameters with the strongest correlation are adjusted. The simulation module is run, and the defects of the virtual composite board are observed to be reproduced. If they are reproduced, the parameter is confirmed as the root cause. S2.3 Quality Trend Prediction: Based on historical data, an LSTM model is trained to predict the quality trend for the next 1-2 hours, providing early warning of potential defects. Model input: Time-series production parameter data divided into 10-minute time windows, with each time window containing 600 data points; Model output: Predicted mean and fluctuation range of key quality indicators σ, K, and Δd3 for the next hour; Prediction accuracy measurement: The root mean square error (RMSE) is used to measure the deviation between the predicted and measured values. The formula is: Where yi is the i-th measured quality index value. The corresponding predicted value is n, which is the number of predicted samples. The model training objective is RMSE < 0.03 × design value. Warning Trigger: If the predicted quality index fluctuation range reaches the qualified threshold boundary, a warning will be triggered, and a prompt message indicating insufficient potential bonding strength will be output.

8. The product quality inspection system for thermally insulated color steel sandwich composite panels based on digital twins according to claim 1, characterized in that: The method for generating the optimization instructions is as follows: Based on the analysis results of the quality intelligent analysis and decision-making module, optimization instructions are generated in two categories: One type of instruction: For linear deviation, the system automatically generates parameter adjustment instructions without manual intervention; Type 2 instructions: For nonlinear problems, the system generates an optimization suggestion report, which includes a problem description, root cause analysis, suggested measures, and expected results, and pushes it to the operator's HMI terminal.

9. The product quality inspection system for thermally insulated color steel sandwich composite panels based on digital twins according to claim 1, characterized in that: The method for executing the optimization instructions is as follows: Command issuance: One type of command is directly issued to the production line PLC via the OPCUA interface to control the corresponding equipment to perform adjustments; the other type of command is manually triggered and executed via the HMI terminal after operator confirmation. Results data acquisition: After the command is executed, the acquisition network continuously collects the adjusted production parameters and quality indicators and synchronizes them to the twin. Verification and Iteration: The digital twin engine compares the quality data before and after the adjustment to determine whether the optimization effect has met expectations. If it has, the data is stored in the knowledge base for subsequent iterative training of the LSTM model. If it has not met expectations, it returns to the quality intelligent analysis and decision module to re-analyze the root cause until the problem is solved.

Images