Visual light guide plate production intelligent management and control system and method

Abstract

The invention relates to the technical field of light guide plate production, and particularly discloses a visual light guide plate production intelligent management and control system and method, and the system comprises a data collection module, a data processing module, a risk assessment module and a visualization module. The data acquisition module respectively acquires key process parameters and environmental parameters through an equipment sensor and an environmental sensor; the data processing module performs cleaning, noise reduction, standardization and feature extraction on the data, and calculates risk coefficients of injection molding, laser engraving and coating deposition in stages; the risk assessment module realizes dual judgment of significant risks and potential risks through threshold comparison and vector matching degree analysis; and the visualization module displays whole-process data and early warning information in real time. According to the invention, whole-course visual monitoring, multi-parameter fusion risk assessment and intelligent early warning of the production process of the light guide plate are realized, and the stability of the production process and the product quality controllability are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of light guide plate production technology, specifically to a visualized intelligent control system and method for light guide plate production. Background Technology

[0002] As a core optical component in the backlight module, the quality of the light guide plate directly determines the brightness uniformity, optical efficiency, and overall display effect of the screen. The production process of the light guide plate typically involves multiple precision stages, such as injection molding, laser engraving, and coating deposition. Each stage involves numerous key process parameters (such as injection pressure, laser power, and coating thickness) and is susceptible to fluctuations in the production workshop environment (temperature and humidity). Any abnormal fluctuations in these parameters and the environment can lead to quality defects in the light guide plate, such as warping, uneven haze, and dot accuracy deviations, severely impacting product yield and production efficiency.

[0003] Currently, there are significant shortcomings in the control of light guide plate production processes: 1. Traditional methods often only monitor single process parameters (such as pressure or temperature) by setting fixed thresholds, lacking the ability to comprehensively analyze the coordinated changes of multiple parameters, temporal trends, and the coupled effects of the environment; 2. Existing early warning mechanisms are mostly based on the instantaneous exceedance judgment of parameters, failing to reflect the fluctuation trend of parameters within a time window and the dynamic superposition effect of environmental disturbances. This results in the system only being able to alarm when defects have occurred or are about to occur, failing to achieve pre-emptive warnings and trend-based risk prevention, and severely lacking in the timeliness and preventative nature of early warnings.

[0004] Therefore, this invention proposes a visual intelligent control system and method for light guide plate production. Summary of the Invention

[0005] The purpose of this invention is to provide a visualized intelligent control system and method for light guide plate production, thereby solving the above-mentioned technical problems: The objective of this invention can be achieved through the following technical solutions: A visualized intelligent control system for light guide plate production, the system comprising a data acquisition module, a data processing module, a risk assessment module, and a visualization module; The data acquisition module includes equipment sensors and environmental sensors; The equipment sensors are used to collect key process parameters of the production equipment, and the environmental sensors are used to collect environmental parameters of the production workshop. The data processing module is used to process the collected data, including data cleaning, noise reduction, format standardization, and feature extraction of the processed data, and transmit the feature extraction results to the visualization module. The risk assessment module is used to assess the risks of the light guide plate production process based on the feature extraction results, and issue corresponding warnings based on the assessment results. The visualization module is used to visualize and provide early warnings for the entire production process.

[0006] As a further description of the technical solution of the present invention, the working process of the data processing module includes: First, data cleaning removes invalid data caused by sensor malfunctions, extreme values ​​exceeding reasonable ranges, and duplicate data. Missing key data is supplemented by interpolation based on adjacent time-series data or historical baseline data of the equipment to ensure data integrity and accuracy. Second, noise reduction is performed to smooth signals using Kalman filtering or moving average filtering algorithms to address environmental noise introduced by equipment vibration, electromagnetic interference, etc., and to extract core data features. Third, format standardization normalizes data from different sources and in different formats, such as material identification sensors, equipment sensors, and vision inspection units, to ensure that the data are of the same order of magnitude.

[0007] As a further description of the technical solution of the present invention, the working process of the data processing module also includes: Key process parameters for the three stages of light guide plate production—injection molding, laser engraving, and coating deposition—were obtained respectively. The key process parameters include: injection pressure and injection speed in the injection molding stage; laser power and scanning speed in the laser engraving stage; and coating thickness and deposition rate in the coating deposition stage. Acquire the time-series data of key process parameters at each stage within a set time window, and calculate the injection molding risk coefficient, laser engraving risk coefficient, and coating deposition risk coefficient based on the processed time-series data.

[0008] As a further description of the technical solution of the present invention, the calculation process of the injection molding risk coefficient includes: The maximum injection pressure influence factor is obtained by calculating the ratio of the highest pressure value that occurs during the actual injection process within the set time window to the maximum allowable pressure set by the system. The pressure stability influencing factor is obtained by calculating the ratio of the standard deviation of injection pressure to the average value of injection pressure during the entire injection phase within a set time window. Calculate the deviation between the average injection speed within the set time window and the optimal injection speed set by the system, then calculate the ratio of this deviation to the optimal injection speed set by the system, and take the absolute value to obtain the injection speed deviation factor. The weighted sum of the maximum injection pressure influence factor, pressure stability influence factor, and injection speed deviation factor yields the basic value of the injection molding risk coefficient. The basic value of the injection molding risk coefficient is then multiplied by the environmental influence factor to obtain the final injection molding risk coefficient.

[0009] As a further description of the technical solution of the present invention, the calculation process of the laser engraving risk factor also includes: Obtain the actual values ​​of laser power and scanning speed at the current moment, obtain the optimal values ​​of laser power and scanning speed set by the system, and the maximum allowable deviation range of laser power and scanning speed set by the system; The influence factors for laser power and scanning speed are calculated as follows: Impact factor = |current actual value − optimal value| / maximum allowable deviation range; The basic value of the laser engraving risk coefficient is obtained by taking the square root of the sum of the squares of the laser power influence factor and the scanning speed influence factor. The laser engraving risk coefficient is then multiplied by the environmental influence factor to obtain the laser engraving risk coefficient.

[0010] As a further description of the technical solution of the present invention, the calculation process of the coating deposition risk coefficient also includes: Obtain the actual values ​​of coating thickness and deposition rate at the current moment, obtain the optimal values ​​of coating thickness and deposition rate set by the system, and the maximum allowable deviation range of coating thickness and deposition rate set by the system. The influencing factors for coating thickness and deposition rate are calculated as follows: Impact factor = |current actual value − optimal value| / maximum allowable deviation range; The basic value of the coating deposition risk coefficient is obtained by taking the square root of the sum of the squares of the coating thickness influence factor and the deposition rate influence factor. The coating deposition risk coefficient is then multiplied by the environmental influence factor to obtain the coating deposition risk coefficient.

[0011] As a further description of the technical solution of the present invention, the environmental impact factor is obtained by weighted summation of the temperature impact factor and the humidity impact factor; The temperature influence factor is calculated in the following way: Obtain the deviation between the current ambient temperature and the system-set reference temperature, multiply the deviation by the system's preset temperature sensitivity coefficient, and then add 1 to obtain the temperature influence factor. The humidity influence factor is calculated in the following way: Obtain the relative humidity value of the current environment, multiply the relative humidity value by the system's preset humidity sensitivity coefficient, and then add 1 to obtain the humidity influence factor; The environmental impact factors are: Environmental impact factors = ×Temperature Influence Factor+ × Humidity influencing factors; in, and These are the weighting coefficients for temperature and humidity, respectively. + =1.

[0012] As a further description of the technical solution of the present invention, the dynamic adjustment process of the temperature sensitivity coefficient and humidity sensitivity coefficient includes: The system sets a sliding time window and accumulates production data within the sliding time window. The production data includes: environmental parameters, risk coefficients for each stage calculated based on the current sensitivity coefficient, and corresponding production quality results. The production data is divided into multiple environmental intervals based on the environmental parameters, and the quality non-conformity rate is calculated for each environmental interval based on the production quality results. ; Get the system-set quality defect rate threshold ,like - If the absolute value of the value exceeds the preset deviation threshold within M consecutive sliding windows, where M is greater than 1 and the risk coefficients of each stage calculated by the current sensitivity coefficient do not increase accordingly, the corresponding sensitivity coefficient is adjusted upward by a preset step size; otherwise, it is adjusted downward.

[0013] As a further description of the technical solution of the present invention, the working process of the risk assessment module includes: The risk coefficients of injection molding, laser engraving, and coating deposition are compared with the corresponding risk thresholds set by the system. If any risk coefficient is greater than or equal to its corresponding threshold, then the production process is deemed to have significant risks. If all risk coefficients are less than their corresponding thresholds, then further assess the potential risks; The further assessment includes: Construct a risk feature vector A = [Injection molding risk coefficient, laser engraving risk coefficient, coating deposition risk coefficient]; Construct a risk label vector B = [Injection molding risk threshold, laser engraving risk threshold, coating deposition risk threshold]; Calculate the matching degree S between risk feature vector A and risk label vector B. If the matching degree S is less than or equal to the structural risk threshold set by the system, then the production process is assessed to have potential risks.

[0014] A method for intelligent control of light guide plate production with visualization, the method comprising the following steps: S1. Data Acquisition Steps: Key process parameters, quality parameters, and production workshop environmental parameters are collected during the production of the light guide plate using equipment sensors and environmental sensors, respectively. S2. Data processing steps: Clean, reduce noise, and standardize the format of the collected raw data, and extract features. The feature extraction includes: extracting the injection pressure and speed in the injection molding stage, the laser power and scanning speed in the laser engraving stage, and the coating thickness and deposition rate in the coating deposition stage, and calculating the feature risk coefficient of each stage based on the processed data. S3. Risk assessment steps: Compare the risk coefficients of injection molding, laser engraving, and coating deposition with the corresponding thresholds set by the system. If any risk coefficient is greater than or equal to the corresponding threshold, the production process is determined to have significant risks and an early warning is triggered. If all risk coefficients are less than the corresponding threshold, then the matching degree between the risk feature vector and the risk label vector is further calculated to determine whether there is a potential risk. S4. Visualization and Early Warning Steps: The visualization module presents real-time data of the entire production process, risk coefficients at each stage, and early warning information, supporting users to monitor and intervene in the production process.

[0015] The beneficial effects of this invention are: This invention comprises a data acquisition module, a data processing module, a risk assessment module, and a visualization module. The data acquisition module collects key process parameters and environmental parameters through equipment sensors and environmental sensors, respectively. The data processing module cleans, reduces noise, standardizes, and extracts features from the data, and calculates the risk coefficients for injection molding, laser engraving, and coating deposition in stages. The risk assessment module uses threshold comparison and vector matching degree analysis to achieve dual determination of significant and potential risks. The visualization module presents real-time data and early warning information for the entire process. This invention achieves full-process visualized monitoring, multi-parameter fusion risk assessment, and intelligent early warning for the light guide plate production process, significantly improving the stability of the production process and the controllability of product quality. Attached Figure Description

[0016] The invention will now be further described with reference to the accompanying drawings.

[0017] Figure 1 This is a partial structural diagram of the intelligent control system for the production of visualized light guide plates according to the present invention. Detailed Implementation

[0018] 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.

[0019] Please see Figure 1 As shown, the present invention provides a visualized intelligent control system for light guide plate production, the system comprising a data acquisition module, a data processing module, a risk assessment module, and a visualization module; The data acquisition module includes equipment sensors and environmental sensors; The equipment sensors are used to collect key process parameters of the production equipment, and the environmental sensors are used to collect environmental parameters of the production workshop. The data processing module is used to process the collected data, including data cleaning, noise reduction, format standardization, and feature extraction of the processed data, and transmit the feature extraction results to the visualization module. The working process of the data processing module includes: First, data cleaning removes invalid data caused by sensor malfunctions, extreme values ​​exceeding reasonable ranges, and duplicate data. Missing key data is supplemented by interpolation based on adjacent time-series data or historical baseline data of the equipment to ensure data integrity and accuracy. Second, noise reduction is performed to smooth signals using Kalman filtering or moving average filtering algorithms to address environmental noise introduced by equipment vibration, electromagnetic interference, etc., and to extract core data features. Third, format standardization normalizes data from different sources and in different formats, such as material identification sensors, equipment sensors, and vision inspection units, to ensure that the data are of the same order of magnitude.

[0020] The operation of the data processing module also includes: Key process parameters for the three stages of light guide plate production—injection molding, laser engraving, and coating deposition—were obtained respectively. The key process parameters include: injection pressure and injection speed in the injection molding stage; laser power and scanning speed in the laser engraving stage; and coating thickness and deposition rate in the coating deposition stage. Acquire the time-series data of key process parameters at each stage within a set time window, and calculate the injection molding risk coefficient, laser engraving risk coefficient, and coating deposition risk coefficient based on the processed time-series data.

[0021] Through the aforementioned technical solution, the data processing module acquires specific process parameters for three key stages in the light guide plate production process (injection molding, laser engraving, and coating deposition), and collects time-series data of these parameters within a set time window. Based on the processed time-series data, it calculates the characteristic risk coefficients for each stage. Specifically, the system first extracts injection pressure and injection speed for the injection molding stage, laser power and scanning speed for the laser engraving stage, and coating thickness and deposition rate as key monitoring indicators for the coating deposition stage. Subsequently, within a set time window (such as several recent production cycles or a specific period), it continuously collects the time-series variation data of these parameters and performs preprocessing such as cleaning, noise reduction, and standardization. Finally, based on the processed time-series data, it calculates the risk coefficients for injection molding, laser engraving, and coating deposition, respectively. This process transforms multi-source heterogeneous raw data into structured risk indicators, providing a quantitative basis for the subsequent risk assessment module, thereby supporting the dynamic identification and early warning of potential risks at each stage of the production process.

[0022] The calculation process for the injection molding risk factor includes: The maximum injection pressure influence factor is obtained by calculating the ratio of the highest pressure value that occurs during the actual injection process within the set time window to the maximum allowable pressure set by the system. The pressure stability influencing factor is obtained by calculating the ratio of the standard deviation of injection pressure to the average value of injection pressure during the entire injection phase within a set time window. Calculate the deviation between the average injection speed within the set time window and the optimal injection speed set by the system, then calculate the ratio of this deviation to the optimal injection speed set by the system, and take the absolute value to obtain the injection speed deviation factor. The weighted sum of the maximum injection pressure influence factor, pressure stability influence factor, and injection speed deviation factor yields the basic value of the injection molding risk coefficient. The basic value of the injection molding risk coefficient is then multiplied by the environmental influence factor to obtain the final injection molding risk coefficient.

[0023] The above technical solution first calculates the maximum injection pressure influence factor (the ratio of the highest pressure to the maximum allowable pressure) and the pressure stability influence factor (the ratio of the pressure standard deviation to the average pressure) based on injection pressure time-series data within a set time window, to measure the risk of pressure exceeding limits and fluctuations. Second, based on injection speed time-series data, the injection speed deviation factor (the ratio of the absolute value of the deviation between the average speed and the optimal speed to the optimal speed) is calculated to assess the degree of speed deviation from the optimal setting. Next, the three influence factors are weighted and summed to obtain the base value of the injection molding risk coefficient, which comprehensively reflects the degree of abnormality of the process parameters themselves. Finally, the base value is multiplied by the environmental influence factor to obtain the final injection molding risk coefficient. This calculation mechanism not only considers the absolute deviation and statistical fluctuation of the process parameters themselves but also introduces the coupled influence of environmental factors on molding quality, enabling the risk coefficient to more comprehensively characterize the actual risk level of the injection molding process under specific environmental conditions. This risk coefficient serves as the core input of the subsequent risk assessment module, used to determine whether an early warning is triggered and to support refined control and intervention decision-making in the injection molding process.

[0024] Injection pressure has a more direct and sensitive impact on the molding quality of light guide plates. Too low a pressure can lead to incomplete filling and shrinkage marks; too high a pressure or fluctuations (poor stability) can lead to flash, increased internal stress, and even mold damage. Therefore, both peak pressure (overpressure risk) and fluctuations (stability risk) are considered key risk sources and need to be quantified separately.

[0025] Injection speed primarily affects melt flow morphology and shear heat. In the process settings of this invention, whether the average setpoint of the speed deviates from the optimal window is considered the primary risk, as it directly affects filling time and molecular orientation. While fluctuations in speed within a short time window are indirectly reflected through pressure stability, short-term fluctuations in the speed signal may contain significant high-frequency noise, making direct calculation of the standard deviation largely meaningless and requiring more complex filtering or feature extraction methods. Therefore, this invention prioritizes addressing the most critical risk dimension—the deviation of the speed setpoint.

[0026] The calculation process for the laser engraving risk factor also includes: Obtain the actual values ​​of laser power and scanning speed at the current moment, obtain the optimal values ​​of laser power and scanning speed set by the system, and the maximum allowable deviation range of laser power and scanning speed set by the system; The influence factors for laser power and scanning speed are calculated as follows: Impact factor = |current actual value − optimal value| / maximum allowable deviation range; The basic value of the laser engraving risk coefficient is obtained by taking the square root of the sum of the squares of the laser power influence factor and the scanning speed influence factor. The laser engraving risk coefficient is then multiplied by the environmental influence factor to obtain the laser engraving risk coefficient.

[0027] The calculation process for the coating deposition risk coefficient also includes: Obtain the actual values ​​of coating thickness and deposition rate at the current moment, obtain the optimal values ​​of coating thickness and deposition rate set by the system, and the maximum allowable deviation range of coating thickness and deposition rate set by the system. The influencing factors for coating thickness and deposition rate are calculated as follows: Impact factor = |current actual value − optimal value| / maximum allowable deviation range; The basic value of the coating deposition risk coefficient is obtained by taking the square root of the sum of the squares of the coating thickness influence factor and the deposition rate influence factor. The coating deposition risk coefficient is then multiplied by the environmental influence factor to obtain the coating deposition risk coefficient.

[0028] Through the above technical solution, the system first acquires the actual values ​​of laser power and scanning speed in real time and compares them with the pre-stored optimal process parameters. Next, it calculates the influence factor for each parameter, obtained by the formula |current actual value - optimal value| / maximum allowable deviation range. Essentially, this transforms the absolute deviation of the parameter into a dimensionless relative risk index between 0 and 1 (or greater than 1), used to measure the severity of the parameter's deviation from the allowable range. Then, the system squares the sum of the squares of the two influence factors, laser power and scanning speed, and takes the square root to obtain the base value of the laser engraving risk coefficient. This calculation method ensures that a significant deviation of any parameter will lead to a significant increase in the base value, thus more sensitively capturing synergistic anomalies. Finally, this base value is multiplied by the environmental influence factor (which integrates the coupled effects of workshop environment factors such as temperature and humidity on laser processing stability) to output the final laser engraving risk coefficient. For the coating deposition stage, the working principle is exactly the same as the laser engraving stage, except that the monitored parameters are replaced by coating thickness and deposition rate. Similarly, the system calculates the influence factors of both, obtains the base value of the coating deposition risk, and then corrects it with the environmental influence factor to obtain the coating deposition risk coefficient.

[0029] The environmental impact factors are obtained by weighted summation of temperature impact factors and humidity impact factors; The temperature influence factor is calculated in the following way: Obtain the deviation between the current ambient temperature and the system-set reference temperature, multiply the deviation by the system's preset temperature sensitivity coefficient, and then add 1 to obtain the temperature influence factor. The humidity influence factor is calculated in the following way: Obtain the relative humidity value of the current environment, multiply the relative humidity value by the system's preset humidity sensitivity coefficient, and then add 1 to obtain the humidity influence factor; The environmental impact factors are: Environmental impact factors = ×Temperature Influence Factor+ × Humidity influencing factors; in, and These are the weighting coefficients for temperature and humidity, respectively. + =1.

[0030] Through the above technical solution, the system first multiplies the deviation between the current ambient temperature and the preset reference temperature by a preset temperature sensitivity coefficient and adds 1 to obtain a temperature influence factor. This factor reflects the linear influence of temperature deviation on process conditions such as material flowability and equipment precision. Simultaneously, the system multiplies the current relative humidity value by a preset humidity sensitivity coefficient and adds 1 to obtain a humidity influence factor. This factor reflects the impact of humidity changes on material hygroscopicity, coating drying, and static electricity accumulation. Finally, these two independent temperature and humidity influence factors are weighted according to preset coefficients (…). and The weighted sums are then used to obtain the final environmental impact factor. This factor, acting as a multiplier greater than or equal to 1, will be multiplied into the base value of the risk coefficient for each process stage. Its core function is to transform the abstract changes in workshop temperature and humidity into a quantifiable risk amplification coefficient. This ensures that the final calculated risk coefficients for injection molding, laser engraving, and coating deposition not only reflect the anomalies in the process parameters themselves but also dynamically couple the additional risks brought about by fluctuations in the production environment, achieving a more comprehensive and realistic risk assessment of the production status.

[0031] It should be noted that the temperature sensitivity coefficient can be preset through experimental calibration or expert experience based on specific production processes and material characteristics. For example, for the injection molding stage of a certain type of PMMA material, this coefficient can be initially set to 0.03, meaning that for every 1°C deviation of the ambient temperature from the reference temperature, a 3% correction effect will be generated on the risk coefficient. The system also supports dynamic calibration of this coefficient based on production quality feedback data during operation.

[0032] The humidity sensitivity coefficient can be determined comprehensively based on the characteristics of the production materials, the process stage, and historical quality data. For example, for the coating deposition process, since humidity directly affects the solvent evaporation rate and coating leveling, this coefficient can be calibrated to 0.015 / %RH through preliminary process experiments; for the laser engraving stage, to suppress dust adsorption caused by static electricity, this coefficient can be set to 0.01 / %RH. The system supports periodic verification and adjustment of the coefficient based on actual production quality feedback.

[0033] The dynamic adjustment process for the temperature sensitivity coefficient and humidity sensitivity coefficient includes: The system sets a sliding time window and accumulates production data within the sliding time window. The production data includes: environmental parameters, risk coefficients for each stage calculated based on the current sensitivity coefficient, and corresponding production quality results. The production data is divided into multiple environmental intervals based on the environmental parameters, and the quality non-conformity rate is calculated for each environmental interval based on the production quality results. ; Get the system-set quality defect rate threshold ,like - If the absolute value of the value exceeds the preset deviation threshold within M consecutive sliding windows, where M is greater than 1 and the risk coefficients of each stage calculated by the current sensitivity coefficient do not increase accordingly, the corresponding sensitivity coefficient is adjusted upward by a preset step size; otherwise, it is adjusted downward.

[0034] The risk assessment module is used to assess the risks of the light guide plate production process based on the feature extraction results, and issue corresponding warnings based on the assessment results. The working process of the risk assessment module includes: The risk coefficients of injection molding, laser engraving, and coating deposition are compared with the corresponding risk thresholds set by the system. If any risk coefficient is greater than or equal to its corresponding threshold, then the production process is deemed to have significant risks. If all risk coefficients are less than their corresponding thresholds, then further assess the potential risks; The further assessment includes: Construct a risk feature vector A = [Injection molding risk coefficient, laser engraving risk coefficient, coating deposition risk coefficient]; Construct a risk label vector B = [Injection molding risk threshold, laser engraving risk threshold, coating deposition risk threshold]; Calculate the matching degree S between risk feature vector A and risk label vector B. If the matching degree S is less than or equal to the structural risk threshold set by the system, then the production process is assessed to have potential risks.

[0035] The visualization module is used to visualize and provide early warnings for the entire production process.

[0036] Through the above technical solution, firstly, the module directly compares the independent risk coefficients of the three stages—injection molding, laser engraving, and coating deposition—with their respective preset thresholds. If any coefficient exceeds the limit, a significant risk is immediately identified and an early warning is triggered, enabling rapid response to sudden anomalies in a single stage. Secondly, if all risk coefficients do not exceed the limit, the module proceeds to a deeper potential risk assessment stage: the three risk coefficients are combined to construct a risk feature vector A, and their corresponding thresholds are constructed to construct a risk label vector B; the matching degree S between the two vectors is calculated (the formula is...). This mechanism quantifies the overall deviation between the current risk distribution and the ideal safety threshold structure. If the matching degree S is lower than the preset structural risk threshold, it determines that there are potential risks in the production process that are not easily captured by a single threshold. For example, although each parameter is not exceeding the standard, it is already close to the threshold as a whole, or there are structural hidden dangers such as an imbalance between parameters. This mechanism not only realizes real-time monitoring of explicit risks, but also achieves the forward-looking identification of implicit, systemic, and trend risks through similarity analysis in vector space, thereby significantly improving the comprehensiveness and intelligence of the risk warning system.

[0037] A method for intelligent control of light guide plate production with visualization, the method comprising the following steps: S1. Data Acquisition Steps: Key process parameters, quality parameters, and production workshop environmental parameters are collected during the production of the light guide plate using equipment sensors and environmental sensors, respectively. S2. Data processing steps: Clean, reduce noise, and standardize the format of the collected raw data, and extract features. The feature extraction includes: extracting the injection pressure and speed in the injection molding stage, the laser power and scanning speed in the laser engraving stage, and the coating thickness and deposition rate in the coating deposition stage, and calculating the feature risk coefficient of each stage based on the processed data. S3. Risk assessment steps: Compare the risk coefficients of injection molding, laser engraving, and coating deposition with the corresponding thresholds set by the system. If any risk coefficient is greater than or equal to the corresponding threshold, the production process is determined to have significant risks and an early warning is triggered. If all risk coefficients are less than the corresponding threshold, then the matching degree between the risk feature vector and the risk label vector is further calculated to determine whether there is a potential risk. S4. Visualization and Early Warning Steps: The visualization module presents real-time data of the entire production process, risk coefficients at each stage, and early warning information, supporting users to monitor and intervene in the production process.

[0038] Working Principle: This invention provides a visualized intelligent control system and method for light guide plate production. Its core working principle lies in achieving multi-dimensional and forward-looking risk monitoring and decision support throughout the entire light guide plate production process through a closed-loop intelligent link of data acquisition, processing, risk assessment, and visualization. The system first acquires multi-dimensional heterogeneous data in real time from equipment sensors (such as injection pressure and laser power) and environmental sensors (temperature and humidity) through an integrated data acquisition module, comprehensively covering process, quality, and environmental conditions. The data processing module then performs deep cleaning (removing invalid, extreme, and duplicate values), noise reduction (using Kalman filtering or moving average algorithms), and standardization on the raw data, transforming it into a high-quality, dimensionless time-series data stream.

[0039] Building upon this foundation, the system's core innovation lies in its phased, multi-factor dynamic risk assessment model. For the three key stages of injection molding, laser engraving, and coating deposition, the system extracts core process parameters (such as pressure / speed, power / scanning speed, and thickness / deposition rate) and performs feature mining and risk quantification based on time-series data within a defined time window. For the injection molding stage, the system calculates the maximum injection pressure influence factor (peak pressure risk), pressure stability influence factor (fluctuation risk), and injection speed deviation factor (set deviation risk), then weights and corrects these factors using environmental impact factors to obtain a comprehensive injection molding risk coefficient. For the laser engraving and coating deposition stages, the system calculates the ratio of the absolute deviation between the actual and optimal values ​​of each parameter to the allowable deviation range (influence factor), then uses geometric synthesis (square root and square root) to obtain the basic risk value, and finally couples the environmental impact factors to output the stage risk coefficient. The environmental impact factor is itself a dynamic correction multiplier derived by weighted summation of the temperature impact factor (calculated based on temperature deviation and sensitivity coefficient) and the humidity impact factor (calculated based on relative humidity and sensitivity coefficient). This scientifically embeds the real-time fluctuations of the production environment into the process risk assessment, realizing the integrated analysis of process parameters and environmental disturbances.

[0040] After calculating the risk coefficients for each stage, the system's risk assessment module executes a dual-judgment mechanism. The first layer involves direct threshold comparison: if any stage's risk coefficient exceeds its independent preset threshold, it is immediately identified as a significant risk and triggers an immediate warning. The second layer, when all coefficients are within limits, initiates a deeper structural risk detection: the three risk coefficients are constructed as a risk feature vector A, and their corresponding thresholds are constructed as a risk label vector B. The normalized distance matching degree between the vectors is then calculated (…). This assesses the degree of deviation between the current overall risk distribution and the ideal safety structure. If the matching degree is lower than the preset structural risk threshold, it determines that there is a potential risk, thereby identifying hidden dangers where parameters, although not exceeding the standard, have become unbalanced or deteriorated in synergy.

[0041] Ultimately, all raw data, processed features, calculated risk coefficients, and early warning information are integrated and presented by the visualization module. The system uses dynamic charts, trend curves, risk heatmaps, and real-time warning pop-ups to intuitively and clearly display the complex production status and risk situation to operators, supporting real-time monitoring, root cause tracing, and rapid intervention of the production process. The entire system represents a leap from traditional result sampling and single-point alarms to full-process, multi-parameter, and forward-looking intelligent risk management, significantly improving the stability, yield, and intelligent management level of light guide plate production.

[0042] It should be noted that the thresholds and coefficients involved in this application are all empirical values, and the selection should be made by those skilled in the art based on the actual situation.

[0043] The foregoing has provided a detailed description of one embodiment of the present invention, but this description is merely a preferred embodiment and should not be construed as limiting the scope of the invention. All equivalent variations and modifications made within the scope of the claims of this invention should still fall within the patent coverage of this invention.

Claims

1. A visualized intelligent control system for light guide plate production, characterized in that, The system includes a data acquisition module, a data processing module, a risk assessment module, and a visualization module; The data acquisition module includes equipment sensors and environmental sensors; The equipment sensors are used to collect key process parameters of the production equipment, and the environmental sensors are used to collect environmental parameters of the production workshop. The data processing module is used to process the collected data, including data cleaning, noise reduction, format standardization, and feature extraction of the processed data, and transmit the feature extraction results to the visualization module. The risk assessment module is used to assess the risks of the light guide plate production process based on the feature extraction results, and issue corresponding warnings based on the assessment results. The visualization module is used to visualize and provide early warnings for the entire production process.

2. The intelligent control system for visual light guide plate production according to claim 1, characterized in that, The working process of the data processing module includes: First, data cleaning removes invalid data caused by sensor malfunctions, extreme values ​​exceeding reasonable ranges, and duplicate data. Missing key data is supplemented by interpolation based on adjacent time-series data or historical baseline data of the equipment to ensure data integrity and accuracy. Second, noise reduction is performed to smooth signals using Kalman filtering or moving average filtering algorithms to address environmental noise introduced by equipment vibration, electromagnetic interference, etc., and to extract core data features. Third, format standardization normalizes data from different sources and in different formats, such as material identification sensors, equipment sensors, and vision inspection units, to ensure that the data are of the same order of magnitude.

3. The intelligent control system for visual light guide plate production according to claim 1, characterized in that, The operation of the data processing module also includes: Key process parameters for the three stages of light guide plate production—injection molding, laser engraving, and coating deposition—were obtained respectively. The key process parameters include: injection pressure and injection speed in the injection molding stage; laser power and scanning speed in the laser engraving stage; and coating thickness and deposition rate in the coating deposition stage. Acquire the time-series data of key process parameters at each stage within a set time window, and calculate the injection molding risk coefficient, laser engraving risk coefficient, and coating deposition risk coefficient based on the processed time-series data.

4. The intelligent control system for visual light guide plate production according to claim 3, characterized in that, The calculation process for the injection molding risk factor includes: The maximum injection pressure influence factor is obtained by calculating the ratio of the highest pressure value that occurs during the actual injection process within the set time window to the maximum allowable pressure set by the system. The pressure stability influencing factor is obtained by calculating the ratio of the standard deviation of injection pressure to the average value of injection pressure during the entire injection phase within a set time window. Calculate the deviation between the average injection speed within the set time window and the optimal injection speed set by the system, then calculate the ratio of this deviation to the optimal injection speed set by the system, and take the absolute value to obtain the injection speed deviation factor. The weighted sum of the maximum injection pressure influence factor, pressure stability influence factor, and injection speed deviation factor yields the basic value of the injection molding risk coefficient. The basic value of the injection molding risk coefficient is then multiplied by the environmental influence factor to obtain the final injection molding risk coefficient.

5. The intelligent control system for the production of visualized light guide plates according to claim 3, characterized in that, The calculation process for the laser engraving risk factor also includes: Obtain the actual values ​​of laser power and scanning speed at the current moment, obtain the optimal values ​​of laser power and scanning speed set by the system, and the maximum allowable deviation range of laser power and scanning speed set by the system; The influence factors for laser power and scanning speed are calculated as follows: Impact factor = |current actual value − optimal value| / maximum allowable deviation range; The basic value of the laser engraving risk coefficient is obtained by taking the square root of the sum of the squares of the laser power influence factor and the scanning speed influence factor. The laser engraving risk coefficient is then multiplied by the environmental influence factor to obtain the laser engraving risk coefficient.

6. The intelligent control system for visual light guide plate production according to claim 3, characterized in that, The calculation process for the coating deposition risk coefficient also includes: Obtain the actual values ​​of coating thickness and deposition rate at the current moment, obtain the optimal values ​​of coating thickness and deposition rate set by the system, and the maximum allowable deviation range of coating thickness and deposition rate set by the system. The influencing factors for coating thickness and deposition rate are calculated as follows: Impact factor = |current actual value − optimal value| / maximum allowable deviation range; The basic value of the coating deposition risk coefficient is obtained by taking the square root of the sum of the squares of the coating thickness influence factor and the deposition rate influence factor. The coating deposition risk coefficient is then multiplied by the environmental influence factor to obtain the coating deposition risk coefficient.

7. The intelligent control system for the production of visualized light guide plates according to any one of claims 4-6, characterized in that, The environmental impact factors are obtained by weighted summation of temperature impact factors and humidity impact factors; The temperature influence factor is calculated in the following way: Obtain the deviation between the current ambient temperature and the system-set reference temperature, multiply the deviation by the system's preset temperature sensitivity coefficient, and then add 1 to obtain the temperature influence factor. The humidity influence factor is calculated in the following way: Obtain the relative humidity value of the current environment, multiply the relative humidity value by the system's preset humidity sensitivity coefficient, and then add 1 to obtain the humidity influence factor; The environmental impact factors are: Environmental impact factors = ×Temperature Influence Factor+ × Humidity influencing factors; in, and These are the weighting coefficients for temperature and humidity, respectively. + =1.

8. The intelligent control system for visual light guide plate production according to claim 7, characterized in that, The dynamic adjustment process for the temperature sensitivity coefficient and humidity sensitivity coefficient includes: The system sets a sliding time window and accumulates production data within the sliding time window. The production data includes: environmental parameters, risk coefficients for each stage calculated based on the current sensitivity coefficient, and corresponding production quality results. The production data is divided into multiple environmental intervals based on the environmental parameters, and the quality non-conformity rate is calculated for each environmental interval based on the production quality results. ; Get the system-set quality defect rate threshold ,like - If the absolute value of the value exceeds the preset deviation threshold within M consecutive sliding windows, where M is greater than 1 and the risk coefficients of each stage calculated by the current sensitivity coefficient do not increase accordingly, the corresponding sensitivity coefficient is adjusted upward by a preset step size; otherwise, it is adjusted downward.

9. The intelligent control system for visual light guide plate production according to claim 1, characterized in that, The working process of the risk assessment module includes: The risk coefficients of injection molding, laser engraving, and coating deposition are compared with the corresponding risk thresholds set by the system. If any risk coefficient is greater than or equal to its corresponding threshold, then the production process is deemed to have significant risks. If all risk coefficients are less than their corresponding thresholds, then further assess the potential risks; The further assessment includes: Construct a risk feature vector A = [Injection molding risk coefficient, laser engraving risk coefficient, coating deposition risk coefficient]; Construct a risk label vector B = [Injection molding risk threshold, laser engraving risk threshold, coating deposition risk threshold]; Calculate the matching degree S between risk feature vector A and risk label vector B. If the matching degree S is less than or equal to the structural risk threshold set by the system, then the production process is assessed to have potential risks.

10. A method for intelligent control of visual light guide plate production, the method being implemented based on the intelligent control system for visual light guide plate production as described in any one of claims 1-9, characterized in that, The method includes the following steps: S1. Data Acquisition Steps: Key process parameters, quality parameters, and production workshop environmental parameters are collected during the production of the light guide plate using equipment sensors and environmental sensors, respectively. S2. Data processing steps: Clean, reduce noise, and standardize the format of the collected raw data, and extract features. The feature extraction includes: extracting the injection pressure and speed in the injection molding stage, the laser power and scanning speed in the laser engraving stage, and the coating thickness and deposition rate in the coating deposition stage, and calculating the feature risk coefficient of each stage based on the processed data. S3. Risk assessment steps: Compare the risk coefficients of injection molding, laser engraving, and coating deposition with the corresponding thresholds set by the system. If any risk coefficient is greater than or equal to the corresponding threshold, the production process is determined to have significant risks and an early warning is triggered. If all risk coefficients are less than the corresponding threshold, then the matching degree between the risk feature vector and the risk label vector is further calculated to determine whether there is a potential risk. S4. Visualization and Early Warning Steps: The visualization module presents real-time data of the entire production process, risk coefficients at each stage, and early warning information, supporting users to monitor and intervene in the production process.

Images