Intelligent adjusting method and system for corrugated paper production line

Abstract

The invention discloses an intelligent adjustment method and system for a corrugated paper production line, and relates to the technical field of intelligent control adjustment, and the method comprises the steps: monitoring and recognizing the position of corrugated paper through a sensor array disposed at a key node of the production line, and extracting technological characteristic parameters; the method comprises the following steps: constructing a process state characteristic data set through a sensor array deployed at a key node of a production line, analyzing the moisture content of the surface and the inner core layer of corrugated paper to obtain an internal humidity gradient value of a paperboard, and calculating evaporation rates under different humidity gradients in combination with drying plate temperature data and drying time to obtain a temperature evaporation rate set; the paperboard deformation change rate analysis is carried out based on the drying temperatures of the paperboard under different water contents, an adjustment decision model for controlling the drying board temperature during hot pressing is constructed by determining the safety deformation risk probability and obtaining a paperboard preliminary risk intervention data set, and the adjustment decision model is converted into an equipment execution command based on a collaborative regulation strategy. And transmitting to production line intelligent equipment for real-time adjustment.

Description

Technical Field

[0001] This invention relates to the field of intelligent control and adjustment technology, and in particular to an intelligent adjustment method and system for corrugated paper production lines. Background Technology

[0002] The production process of corrugated cardboard mainly includes cardboard preparation, corrugation forming, gluing and bonding, drying and setting, cooling and cutting. Among these, the drying and setting stage is the key process that determines the final cardboard quality, production efficiency, and energy consumption. In this stage, the cardboard needs to pass through a drying chamber, where heat conduction gelatinizes the glue and evaporates excess moisture to achieve the predetermined strength and moisture requirements. As a core product of packaging materials, the quality of corrugated cardboard is directly affected by its moisture content. In traditional corrugated cardboard production lines, the drying and setting stages typically use a fixed parameter control mode, that is, the cardboard is dried and set by preset drying chamber temperature (steam pressure) and production line speed.

[0003] However, this model has the following technical drawbacks: Traditional systems rely on offline detection or empirical parameters, which cannot respond in real time to fluctuations in raw material humidity, changes in ambient temperature and humidity, or differences in equipment operating status. This results in unstable moisture content in the finished product. The moisture detector at the outlet may show that the overall moisture content meets the standard, but the internal bonding may be poor, and the surface fibers may become brittle due to excessive dehydration, which seriously affects the strength of the cardboard. Setting a fixed drying plate temperature can easily cause localized overheating, especially when using thick cardboard or high-grammage cardboard. The surface moisture evaporates too quickly, causing the fibers to shrink, while the internal moisture does not migrate sufficiently, resulting in a "dry outside and wet inside" state, which further causes the cardboard to bend and deform. To address the aforementioned technical shortcomings, a solution is proposed. Summary of the Invention

[0004] The purpose of this invention is to analyze the moisture content of the surface and inner core of corrugated paper to obtain the internal humidity gradient value of the paperboard. Combined with the drying temperature data and drying time, the paperboard deformation rate is analyzed based on the drying temperature of the paperboard at different moisture contents. By determining the probability of safe deformation risk and obtaining the preliminary risk intervention dataset of the paperboard, a regulation decision model for controlling the drying temperature during hot pressing is constructed. Based on the collaborative control strategy, the model is transformed into equipment execution commands and transmitted to the intelligent equipment of the production line for real-time adjustment.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: an intelligent adjustment method for corrugated paper production lines, comprising the following steps: Step 1: By deploying sensor arrays at key nodes of the production line, monitor and identify the location of corrugated paper and extract process characteristic parameters, including real-time collection of paperboard moisture content, ambient temperature and humidity, corrugated paper parameters and drying temperature data, and construct a process status characteristic dataset. Step 2: Based on the real-time collection of cardboard moisture content, analyze the moisture content of the corrugated paper surface and inner core layer to obtain the internal humidity gradient value of the cardboard. Combine the drying temperature data and drying time to calculate the evaporation rate under different humidity gradients and obtain the temperature evaporation rate set. Based on the drying temperature of the cardboard at different moisture contents, analyze the deformation rate of the cardboard to obtain the risk probability of the cardboard shrinking and deforming. Step 3: Based on the evaporation rate under different humidity gradients, set the drying safety gradient difference, and combine it with the risk probability of paperboard shrinkage and deformation to determine the safe deformation risk probability. When the gradient difference exceeds the preset drying safety gradient difference, combine it with real-time drying temperature data to obtain the paperboard preliminary risk intervention dataset. Step 4: Construct a regulation decision model for controlling the temperature of the drying board during hot pressing. Use the extracted process feature parameters as model inputs and the preliminary risk intervention dataset of the cardboard as decision trigger conditions. Dynamically output coordinated control strategies including temperature setting, time adjustment, and spray start / stop. Step 5: Based on the collaborative control strategy, the commands are converted into equipment execution commands, transmitted to the intelligent equipment on the production line for real-time adjustment, and fed back to the equipment control and management terminal.

[0006] Furthermore, in step one, the specific method for constructing the process state feature dataset is as follows: Based on the production line layout, sensors are rationally arranged at key nodes in the cardboard conveying section, forming section, and drying section. High-definition industrial cameras are installed at key locations on the production line to form a vision sensor array. The images collected by the cameras are analyzed through image processing algorithms to identify the position information of the corrugated paper on the production line in real time. The monitored and identified corrugated paper location information is associated with the extracted process feature parameters, and integrated according to time series and corrugated paper batches to ensure that the process feature parameters at each time point are accurately matched with the corresponding corrugated paper location, forming a complete process status data record. Statistical analysis was performed on the real-time collected cardboard moisture content data to extract the average, standard deviation, maximum, and minimum values ​​of the moisture content, resulting in a moisture content and humidity dataset. The environmental temperature and humidity data are processed to calculate the average temperature and humidity and the rate of change of temperature and humidity over different time periods, thus obtaining a temperature dataset. Real-time monitoring and analysis of baking plate temperature data are performed to extract real-time temperature and statistically analyze the average temperature, temperature rise rate, and temperature fall rate characteristic parameters to obtain baking plate temperature dataset. A process state feature dataset is constructed by combining the moisture content and humidity datasets, the temperature dataset, and the baking plate temperature dataset.

[0007] Furthermore, the evaporation rate under different humidity gradients is calculated to obtain a set of temperature evaporation rates, specifically including the following: S100. Obtain the process state feature dataset, and perform moisture content analysis of the corrugated paper surface and inner core layer based on the paperboard moisture content. Use the gradient calculation formula: Humidity gradient = (surface moisture content - inner core layer moisture content) / paperboard thickness. S101. Based on the drying temperature used for different paperboard moisture contents, obtain the drying time sequence of the paperboard location points and form a temperature-time synergistic effect matrix; S102. Based on the surface-core layer humidity gradient, baking plate temperature, drying time and relative humidity, establish a nonlinear relationship model between evaporation rate and temperature-humidity gradient, perform batch calculations on evaporation rate under different humidity gradients, and form a temperature-evaporation rate dataset.

[0008] Furthermore, an analysis of the paperboard deformation rate is performed to obtain the probability of paperboard shrinkage and deformation, specifically including the following: S200: Based on the drying temperature of the paperboard at different moisture contents, obtain the temperature and shape of the paperboard before and after drying, and obtain the corresponding length dimensions; S201. Analyze the deformation rate of the cardboard based on its length dimension. Deformation rate = (length after drying - original length) / original length × 100%; S202. Based on the initial moisture content, drying time, drying temperature and temperature and humidity gradient, the risk probability is predicted to obtain the risk probability of the cardboard shrinking and deforming. Based on the risk probability, the risk level is divided into low risk, medium risk and high risk. Based on the moisture content of the paperboard that produces the deformation rate, the relationship between moisture content and deformation rate is established. The moisture content stages at which paperboard is prone to deformation are divided into low moisture content, medium moisture content and high moisture content.

[0009] Furthermore, by combining real-time drying temperature data, a preliminary risk intervention dataset for cardboard was obtained. The specific process is as follows: S300: Obtain the temperature evaporation rate, and based on the evaporation rate under different humidity gradients, set the drying safety gradient difference, divide the drying environment into multiple humidity gradient intervals, and calculate the variance based on the average value of different intervals to obtain the safety gradient difference T. S301. Based on the risk probability of cardboard shrinkage and deformation, set a safe risk probability for different levels of risk probability. Safe deformation risk probability = (T-T1)*0.8; S302. By analyzing how rising temperature accelerates evaporation, the difference in evaporation rate that needs to be corrected is obtained. Based on the risk probability of paperboard shrinkage and deformation, the safety gradient difference T, and the difference in corrected evaporation rate, the total risk assessment of paperboard is carried out, the total risk index of paperboard is generated, and the preliminary risk intervention dataset of paperboard is generated.

[0010] Furthermore, a decision-making model for controlling the temperature of the baking plate during hot pressing is constructed, specifically including the following: The process feature parameters are obtained and fused with the preliminary risk intervention dataset of paperboard to construct a multi-dimensional comprehensive feature vector, which is used as input sample data. An initial model was established based on a fully connected neural network architecture. Physical constraints were set, and the total risk index of cardboard in the preliminary risk intervention dataset was set as the adjustment trigger condition. The adjustment amount was analyzed, and a three-dimensional control strategy vector was generated. The architecture of the moderating decision-making model and the multinomial regression model are designed, and the analytical function of the multinomial regression model is obtained: ; In the above formula, The value set for temperature. Temperature is used to compensate for moisture content deviation. Temperature is used to compensate for humidity gradient differences. The risk probability compensation temperatures are respectively, Temperature is used to compensate for time deviation; Output layer: Outputs a three-dimensional control strategy vector, corresponding to the temperature setpoint, time adjustment amount, and spray start / stop command, respectively.

[0011] Furthermore, the specific method for starting and stopping the spray in step four is as follows: Based on the spray volume and spray range, combined with the overall area of ​​the cardboard, real-time range spray analysis is performed to determine the coverage area of ​​the cardboard spray. Based on the spraying amount, the humidity of the paperboard is analyzed, and a curve graph of spraying amount and paperboard humidity is established to generate a mapping table of the relationship between spraying amount and paperboard humidity, which is used to display the paperboard humidity caused by different spraying amounts. Obtain the safe humidity gradient value, analyze the difference between the safe humidity gradient value and the real-time paperboard humidity value to obtain the real-time humidity value, and adjust the coating amount of the paperboard in real time based on the humidity value to generate an automatically adjusted coating amount.

[0012] Furthermore, it also includes a feedback module, which performs closed-loop adjustment of the parameters of each workstation through the actuator according to the collaborative control strategy, and calculates the quality stability index based on the adjusted feedback data. According to the preset quality standard, it calculates the deviation of each sample quality indicator from the standard value, and uses statistical standard deviation to calculate the quality stability index. This index reflects the degree of fluctuation in product quality. The smaller the index, the more stable the product quality.

[0013] A corrugated paper production line intelligent adjustment system, applied to the intelligent adjustment method for a corrugated paper production line according to any one of claims 1-8, comprises the following modules: The data acquisition module monitors and identifies the location of corrugated paper and extracts process characteristic parameters through sensor arrays deployed at key nodes of the production line. This includes real-time collection of paperboard moisture content, ambient temperature and humidity, corrugated paper parameters, and drying temperature data to construct a process status characteristic dataset. The paperboard analysis module analyzes the moisture content of corrugated paperboard surface and inner core layer based on real-time data acquisition, obtains the internal humidity gradient value of paperboard, calculates the evaporation rate under different humidity gradients by combining drying temperature data and drying time, obtains the temperature evaporation rate set, and analyzes the deformation rate of paperboard based on the drying temperature of paperboard at different moisture contents, and obtains the risk probability of paperboard shrinkage and deformation. The impact analysis module sets a drying safety gradient difference based on the evaporation rate under different humidity gradients. Combined with the risk probability of paperboard shrinkage and deformation, it determines the safe deformation risk probability. When the gradient difference exceeds the preset drying safety gradient difference, it combines real-time drying temperature data to obtain a preliminary risk intervention dataset for paperboard. The model building module constructs a regulatory decision model for controlling the temperature of the drying board during hot pressing. It takes the extracted process feature parameters as the model input, the preliminary risk intervention dataset of the cardboard as the decision trigger condition, and dynamically outputs a coordinated control strategy including temperature setting, time adjustment, and spray start / stop. The intelligent adjustment module, based on the collaborative control strategy, transforms the commands into equipment execution commands, transmits them to the intelligent equipment on the production line for real-time adjustment, and feeds back to the equipment control and management terminal.

[0014] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: This intelligent adjustment method and system for corrugated paper production lines constructs a process state characteristic dataset by deploying sensor arrays at key nodes of the production line. It analyzes the moisture content of the corrugated paper surface and inner core layer to obtain the internal humidity gradient value. Combined with drying temperature data and drying time, it calculates the evaporation rate under different humidity gradients, obtaining a temperature evaporation rate set. Based on the drying temperature of the paperboard at different moisture contents, it analyzes the paperboard deformation rate to obtain the risk probability of paperboard shrinkage and deformation. Based on the evaporation rate under different humidity gradients, it sets a drying safety gradient difference. Combined with the risk probability of paperboard shrinkage and deformation, it determines the safe deformation risk probability. When the gradient difference exceeds the preset drying safety gradient difference, it combines real-time drying temperature data to obtain a preliminary risk intervention dataset for the paperboard. By determining the safe deformation risk probability and obtaining the preliminary risk intervention dataset, it constructs an adjustment decision model for controlling the drying temperature during hot pressing. Based on a collaborative control strategy, this is translated into equipment execution commands, transmitted to the intelligent equipment on the production line for real-time adjustment, and fed back to the equipment control and management terminal. This achieves automated and closed-loop control of production adjustment, reduces errors and delays caused by manual intervention, and improves the timeliness and accuracy of adjustment. Attached Figure Description

[0015] Figure 1 A schematic diagram of the method steps of the present invention is shown; Figure 2 A schematic diagram of the system flow structure of the present invention is shown. Detailed Implementation

[0016] 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.

[0017] Example 1: like Figure 1 As shown, the intelligent adjustment method for a corrugated paper production line includes the following steps: Step 1: By deploying sensor arrays at key nodes of the production line, monitor and identify the location of corrugated paper and extract process characteristic parameters, including real-time collection of paperboard moisture content, ambient temperature and humidity, corrugated paper parameters and drying temperature data, and construct a process status characteristic dataset. Step 2: Based on the real-time collection of cardboard moisture content, analyze the moisture content of the corrugated paper surface and inner core layer to obtain the internal humidity gradient value of the cardboard. Combine the drying temperature data and drying time to calculate the evaporation rate under different humidity gradients and obtain the temperature evaporation rate set. Based on the drying temperature of the cardboard at different moisture contents, analyze the deformation rate of the cardboard to obtain the risk probability of the cardboard shrinking and deforming. Step 3: Based on the evaporation rate under different humidity gradients, set the drying safety gradient difference, and combine it with the risk probability of paperboard shrinkage and deformation to determine the safe deformation risk probability. When the gradient difference exceeds the preset drying safety gradient difference, combine it with real-time drying temperature data to obtain the paperboard preliminary risk intervention dataset. Step 4: Construct a regulation decision model for controlling the temperature of the drying board during hot pressing. Use the extracted process feature parameters as model inputs and the preliminary risk intervention dataset of the cardboard as decision trigger conditions. Dynamically output coordinated control strategies including temperature setting, time adjustment, and spray start / stop. Step 5: Based on the collaborative control strategy, the commands are converted into equipment execution commands, transmitted to the intelligent equipment on the production line for real-time adjustment, and fed back to the equipment control and management terminal.

[0018] In step one, the specific method for constructing the process state feature dataset is as follows: Based on the production line layout, sensors are rationally arranged at key nodes in the cardboard conveying section, forming section, and drying section. High-definition industrial cameras are installed at key locations on the production line to form a vision sensor array. The images collected by the cameras are analyzed through image processing algorithms to identify the position information of the corrugated paper on the production line in real time. The monitored and identified corrugated paper location information is associated with the extracted process feature parameters, and integrated according to time series and corrugated paper batches to ensure that the process feature parameters at each time point are accurately matched with the corresponding corrugated paper location, forming a complete process status data record. Statistical analysis was performed on the real-time collected cardboard moisture content data to extract the average, standard deviation, maximum, and minimum values ​​of the moisture content, resulting in a moisture content and humidity dataset. The environmental temperature and humidity data are processed to calculate the average temperature and humidity and the rate of change of temperature and humidity over different time periods, thus obtaining a temperature dataset. Real-time monitoring and analysis of baking plate temperature data are performed to extract real-time temperature and statistically analyze the average temperature, temperature rise rate, and temperature fall rate characteristic parameters to obtain baking plate temperature dataset. A process state feature dataset is constructed by combining the moisture content and humidity datasets, the temperature dataset, and the baking plate temperature dataset.

[0019] Four monitoring points were set up on the cardboard production line, and a temperature compensation algorithm was used to correct the impact of ambient temperature on the sensor accuracy.

[0020] The evaporation rate under different humidity gradients was calculated to obtain a set of temperature-based evaporation rates, specifically including the following: S100. Obtain the process state feature dataset, and perform moisture content analysis of the corrugated paper surface and inner core layer based on the paperboard moisture content. Use the gradient calculation formula: Humidity gradient = (surface moisture content - inner core layer moisture content) / paperboard thickness. S101. Based on the drying temperature used for different paperboard moisture contents, obtain the drying time sequence of the paperboard location points and form a temperature-time synergistic effect matrix; S102. Based on the surface-core layer humidity gradient, baking plate temperature, drying time and relative humidity, establish a nonlinear relationship model between evaporation rate and temperature-humidity gradient, perform batch calculations on evaporation rate under different humidity gradients, and form a temperature-evaporation rate dataset.

[0021] By performing a deformation rate analysis of the cardboard, the probability of the cardboard shrinking and deforming is obtained, specifically including the following: S200: Based on the drying temperature of the paperboard at different moisture contents, obtain the temperature and shape of the paperboard before and after drying, and obtain the corresponding length dimensions; S201. Analyze the deformation rate of the cardboard based on its length dimension. Deformation rate = (length after drying - original length) / original length × 100%; S202. Based on the initial moisture content, drying time, drying temperature and temperature and humidity gradient, the risk probability is predicted to obtain the risk probability of the cardboard shrinking and deforming. Based on the risk probability, the risk level is divided into low risk, medium risk and high risk. Based on the moisture content of the paperboard that produces the deformation rate, the relationship between moisture content and deformation rate is established. The moisture content stages at which paperboard is prone to deformation are divided into low moisture content, medium moisture content and high moisture content.

[0022] By combining real-time drying temperature data, a preliminary risk intervention dataset for cardboard was obtained. The specific process is as follows: S300: Obtain the temperature evaporation rate, and based on the evaporation rate under different humidity gradients, set the drying safety gradient difference, divide the drying environment into multiple humidity gradient intervals, and calculate the variance based on the average value of different intervals to obtain the safety gradient difference T. S301. Based on the risk probability of cardboard shrinkage and deformation, set a safe risk probability for different levels of risk probability. Safe deformation risk probability = (T-T1)*0.8; S302. By analyzing how rising temperature accelerates evaporation, the difference in evaporation rate that needs to be corrected is obtained. Based on the risk probability of paperboard shrinkage and deformation, the safety gradient difference T, and the difference in corrected evaporation rate, the total risk assessment of paperboard is carried out, the total risk index of paperboard is generated, and the preliminary risk intervention dataset of paperboard is generated.

[0023] A decision-making model for controlling the temperature of the baking plate during hot pressing is constructed, which includes the following: The process feature parameters are obtained and fused with the preliminary risk intervention dataset of paperboard to construct a multi-dimensional comprehensive feature vector, which is used as input sample data. An initial model was established based on a fully connected neural network architecture. Physical constraints were set, and the total risk index of cardboard in the preliminary risk intervention dataset was set as the adjustment trigger condition. The adjustment amount was analyzed, and a three-dimensional control strategy vector was generated. The architecture of the moderating decision-making model and the multinomial regression model are designed, and the analytical function of the multinomial regression model is obtained: ; In the above formula, The value set for temperature. Temperature is used to compensate for moisture content deviation. Temperature is used to compensate for humidity gradient differences. The risk probability compensation temperatures are respectively, Temperature is used to compensate for time deviation; Output layer: Outputs a three-dimensional control strategy vector, corresponding to the temperature setpoint, time adjustment amount, and spray start / stop command, respectively.

[0024] This also includes the specific method for starting and stopping the spray in step four: Based on the spray volume and spray range, combined with the overall area of ​​the cardboard, real-time range spray analysis is performed to determine the coverage area of ​​the cardboard spray. Based on the spraying amount, the humidity of the paperboard is analyzed, and a curve graph of spraying amount and paperboard humidity is established to generate a mapping table of the relationship between spraying amount and paperboard humidity, which is used to display the paperboard humidity caused by different spraying amounts. Obtain the safe humidity gradient value, analyze the difference between the safe humidity gradient value and the real-time paperboard humidity value to obtain the real-time humidity value, and adjust the coating amount of the paperboard in real time based on the humidity value to generate an automatically adjusted coating amount.

[0025] It also includes a feedback module, which performs closed-loop adjustment of parameters at each workstation through the actuator according to the collaborative control strategy, and calculates the quality stability index based on the adjusted feedback data. According to the preset quality standard, it calculates the deviation of each sample quality indicator from the standard value, and uses statistical standard deviation to calculate the quality stability index. This index reflects the degree of fluctuation in product quality. The smaller the index, the more stable the product quality.

[0026] Step 1: Multidimensional feature engineering and input vector standardization; Feature fusion: Integrate the process status feature dataset with the paperboard preliminary risk intervention dataset (humidity gradient difference threshold, paperboard shrinkage risk probability index, safety gradient deviation value, and total risk index) to construct a comprehensive feature vector; Standardization: Min-Max normalization is used to map feature values ​​to the [0,1] interval to eliminate dimensional differences; logarithmic transformation or Box-Cox power transformation is performed on nonlinear features to improve the model convergence speed; Dataset partitioning: The training, validation, and test sets are split in a 7:2:1 ratio, and stratified sampling is used to ensure a balanced distribution of samples across risk levels. 3.2 Gradient descent optimization: The Adam optimizer is used for parameter updates, with an initial learning rate of 0.001, dynamically adjusted after each iteration using a learning rate decay strategy. 3.3 Convergence criteria: The model is considered converged when the validation set loss decreases by less than 0.001% over 10 consecutive iterations and the sum of squared prediction errors is less than 0.5%, and the optimal parameters are saved. Temperature setting strategy: A PID-fuzzy control composite algorithm is adopted to dynamically adjust the temperature within the set initial temperature range, and nonlinear compensation is performed by combining the risk probability index. Time and temperature coordination: A nonlinear compensation curve is established based on evaporation rate data. A "low temperature long time" strategy is adopted under high humidity conditions, and a "high temperature short time" strategy is adopted under low humidity conditions. Intelligent spray control: When the surface humidity is <45%RH and the risk probability index is >0.6, the pulse spray device is triggered. The amount of sprayed in a single spray is less than the set standard amount. Precise water replenishment is achieved through differential control.

[0027] Example 2: like Figure 2 As shown, the intelligent adjustment system for a corrugated paper production line, applied to the intelligent adjustment method for a corrugated paper production line according to any one of claims 1-8, includes the following modules: The data acquisition module monitors and identifies the location of corrugated paper and extracts process characteristic parameters through sensor arrays deployed at key nodes of the production line. This includes real-time collection of paperboard moisture content, ambient temperature and humidity, corrugated paper parameters, and drying temperature data to construct a process status characteristic dataset. The paperboard analysis module analyzes the moisture content of corrugated paperboard surface and inner core layer based on real-time data acquisition, obtains the internal humidity gradient value of paperboard, calculates the evaporation rate under different humidity gradients by combining drying temperature data and drying time, obtains the temperature evaporation rate set, and analyzes the deformation rate of paperboard based on the drying temperature of paperboard at different moisture contents, and obtains the risk probability of paperboard shrinkage and deformation. The impact analysis module sets a drying safety gradient difference based on the evaporation rate under different humidity gradients. Combined with the risk probability of paperboard shrinkage and deformation, it determines the safe deformation risk probability. When the gradient difference exceeds the preset drying safety gradient difference, it combines real-time drying temperature data to obtain a preliminary risk intervention dataset for paperboard. The model building module constructs a regulatory decision model for controlling the temperature of the drying board during hot pressing. It takes the extracted process feature parameters as the model input, the preliminary risk intervention dataset of the cardboard as the decision trigger condition, and dynamically outputs a coordinated control strategy including temperature setting, time adjustment, and spray start / stop. The intelligent adjustment module, based on the collaborative control strategy, transforms the commands into equipment execution commands, transmits them to the intelligent equipment on the production line for real-time adjustment, and feeds back to the equipment control and management terminal.

[0028] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by those skilled in the art for each set of sample data; as long as it does not affect the ratio between the parameter and the quantized value.

[0029] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters in the formulas are set by those skilled in the art according to the actual situation. In the two embodiments provided in this application, it should be understood that the disclosed apparatus and system can be implemented in other ways; for example, the apparatus embodiments described above are merely illustrative, and the division of modules is merely a logical functional division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed; furthermore, the coupling or direct coupling or communication connection between the shown or discussed mutuals can be through some interfaces, and the indirect coupling or communication connection between the apparatus or modules can be electrical, mechanical or other forms. The above description is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any equivalent substitutions or modifications made by those skilled in the art within the scope of the technology disclosed in the present invention, based on the technical solution and inventive concept of the present invention, should be covered within the scope of protection of the present invention.

Claims

1. A method for intelligent adjustment of a corrugated paper production line, characterized in that, The method comprises the following steps: Step one: through the sensor array deployed at the key nodes of the production line, the position of the corrugated paper is monitored and identified, and process characteristic parameters are extracted, including real-time collection of paperboard moisture content, environmental temperature and humidity, corrugated paper parameters, and drying plate temperature data, to construct a process state characteristic data set; Step two: based on the real-time collection of paperboard moisture content, the surface and inner core layer moisture content of the corrugated paper is analyzed to obtain the paperboard internal humidity gradient value, combined with the drying plate temperature data and drying time, the evaporation rate under different humidity gradients is calculated to obtain the temperature evaporation rate set, and based on the drying temperature of the paperboard under different moisture contents, the paperboard deformation change rate is analyzed to obtain the risk probability of paperboard shrinkage and deformation; Step three: according to the evaporation rate under different humidity gradients, a set drying safety gradient difference is determined, combined with the risk probability of paperboard shrinkage and deformation, the safe deformation risk probability is determined, when the gradient difference exceeds the preset drying safety gradient difference, combined with the real-time drying plate temperature data, a preliminary risk intervention data set of the paperboard is obtained; Step four: an adjustment decision model for the drying plate temperature control during hot pressing is constructed, the extracted process characteristic parameters are used as the model input, the preliminary risk intervention data set of the paperboard is used as the decision trigger condition, and a coordinated control strategy including temperature setting, time adjustment, and spray start-stop is dynamically output; Step five: based on the coordinated control strategy, the device execution command is converted, and is transmitted to the intelligent device of the production line for real-time adjustment, and is fed back to the device control management end.

2. The method of claim 1, wherein, In step one, the process state characteristic data set is constructed in the following manner: According to the layout of the production line, sensors are reasonably arranged at the key nodes of the paperboard conveying section, the forming section, and the drying section, high-definition industrial cameras are installed at the key positions of the production line to form a visual sensor array, the image collected by the camera is analyzed through an image processing algorithm, and the position information of the corrugated paper on the production line is identified in real time; The position information of the corrugated paper monitored and identified is associated with the extracted process characteristic parameters, is integrated according to the time sequence and the corrugated paper batch, and it is ensured that the process characteristic parameters at each time point are accurately matched with the corresponding corrugated paper position to form a complete process state data record; The real-time collected paperboard moisture content data is statistically analyzed to extract the average value, standard deviation, maximum value, and minimum value statistical characteristic parameters of the moisture content to obtain a moisture content humidity data set; The environmental temperature and humidity data is processed to calculate the average temperature and humidity, temperature and humidity change rate parameters in different time periods to obtain a temperature data set; The drying plate temperature data is monitored and analyzed in real time to extract the real-time temperature and calculate the average value, temperature rise rate, and temperature drop rate characteristic parameters to obtain a drying plate temperature data set; The moisture content humidity data set, the temperature data set, and the drying plate temperature data set are used to construct the process state characteristic data set.

3. The method of claim 1, wherein, The evaporation rate under different humidity gradients is calculated to obtain the temperature evaporation rate set, which specifically includes the following: S100, obtain the process state characteristic data set, analyze the surface and inner core layer moisture content of the corrugated paper based on the paperboard moisture content, and use the gradient calculation formula: humidity gradient=(surface moisture content-inner core layer moisture content) / paperboard thickness; S101. Based on the drying temperature used for different paperboard moisture contents, obtain the drying time sequence of the paperboard location points and form a temperature-time synergistic effect matrix; S102. Based on the surface-core layer humidity gradient, baking plate temperature, drying time and relative humidity, establish a nonlinear relationship model between evaporation rate and temperature-humidity gradient, perform batch calculations on evaporation rate under different humidity gradients, and form a temperature-evaporation rate dataset.

4. The method of claim 1, wherein, By performing a deformation rate analysis of the cardboard, the probability of the cardboard shrinking and deforming is obtained, specifically including the following: S200: Based on the drying temperature of the paperboard at different moisture contents, obtain the temperature and shape of the paperboard before and after drying, and obtain the corresponding length dimensions; S201. Analyze the deformation rate of the cardboard based on its length dimension. Deformation rate = (length after drying - original length) / original length × 100%; S202. Based on the initial moisture content, drying time, drying temperature and temperature and humidity gradient, the risk probability is predicted to obtain the risk probability of the cardboard shrinking and deforming. Based on the risk probability, the risk level is divided into low risk, medium risk and high risk. Based on the moisture content of the paperboard that produces the deformation rate, the relationship between moisture content and deformation rate is established. The moisture content stages at which paperboard is prone to deformation are divided into low moisture content, medium moisture content and high moisture content.

5. The method of claim 1, wherein, By combining real-time drying temperature data, a preliminary risk intervention dataset for cardboard was obtained. The specific process is as follows: S300: Obtain the temperature evaporation rate, and based on the evaporation rate under different humidity gradients, set the drying safety gradient difference, divide the drying environment into multiple humidity gradient intervals, and calculate the variance based on the average value of different intervals to obtain the safety gradient difference T. S301. Based on the risk probability of cardboard shrinkage and deformation, set a safe risk probability for different levels of risk probability. Safe deformation risk probability = (T-T1)*0.8; S302. By analyzing how rising temperature accelerates evaporation, the difference in evaporation rate that needs to be corrected is obtained. Based on the risk probability of paperboard shrinkage and deformation, the safety gradient difference T, and the difference in corrected evaporation rate, the total risk assessment of paperboard is carried out, the total risk index of paperboard is generated, and the preliminary risk intervention dataset of paperboard is generated.

6. The method of claim 1, wherein, A decision-making model for controlling the temperature of the baking plate during hot pressing is constructed, which includes the following: The process feature parameters are obtained and fused with the preliminary risk intervention dataset of paperboard to construct a multi-dimensional comprehensive feature vector, which is used as input sample data. An initial model was established based on a fully connected neural network architecture. Physical constraints were set, and the total risk index of cardboard in the preliminary risk intervention dataset was set as the adjustment trigger condition. The adjustment amount was analyzed, and a three-dimensional control strategy vector was generated. The polynomial regression model architecture design of the adjustment decision model is established, and a polynomial regression model analysis function is obtained: ; In the above formulae, is the value set for the temperature, is the water content deviation compensation temperature, is the humidity gradient difference compensation temperature, is the risk probability compensation temperature, respectively, is the time deviation compensation temperature; Output layer: Outputs a three-dimensional control strategy vector, corresponding to the temperature setpoint, time adjustment amount, and spray start / stop command, respectively.

7. The method of claim 1, wherein, This also includes the specific method for starting and stopping the spray in step four: Based on the spray volume and spray range, combined with the overall area of ​​the cardboard, real-time range spray analysis is performed to determine the coverage area of ​​the cardboard spray. Based on the spraying amount, the humidity of the paperboard is analyzed, and a curve graph of spraying amount and paperboard humidity is established to generate a mapping table of the relationship between spraying amount and paperboard humidity, which is used to display the paperboard humidity caused by different spraying amounts. Obtain the safe humidity gradient value, analyze the difference between the safe humidity gradient value and the real-time paperboard humidity value to obtain the real-time humidity value, and adjust the coating amount of the paperboard in real time based on the humidity value to generate an automatically adjusted coating amount.

8. The method of claim 1, wherein, It also includes a feedback module, which performs closed-loop adjustment of parameters at each workstation through the actuator according to the collaborative control strategy, and calculates the quality stability index based on the adjusted feedback data. According to the preset quality standard, it calculates the deviation of each sample quality indicator from the standard value, and uses statistical standard deviation to calculate the quality stability index. This index reflects the degree of fluctuation in product quality. The smaller the index, the more stable the product quality.

9. The intelligent adjusting system of the corrugated paper production line, applied to the intelligent adjusting method of the corrugated paper production line according to any one of claims 1-8, characterized in that, Includes the following modules: The data acquisition module monitors and identifies the location of corrugated paper and extracts process characteristic parameters through sensor arrays deployed at key nodes of the production line. This includes real-time collection of paperboard moisture content, ambient temperature and humidity, corrugated paper parameters, and drying temperature data to construct a process status characteristic dataset. The paperboard analysis module analyzes the moisture content of corrugated paperboard surface and inner core layer based on real-time data acquisition, obtains the internal humidity gradient value of paperboard, calculates the evaporation rate under different humidity gradients by combining drying temperature data and drying time, obtains the temperature evaporation rate set, and analyzes the deformation rate of paperboard based on the drying temperature of paperboard at different moisture contents, and obtains the risk probability of paperboard shrinkage and deformation. The impact analysis module sets a drying safety gradient difference based on the evaporation rate under different humidity gradients. Combined with the risk probability of paperboard shrinkage and deformation, it determines the safe deformation risk probability. When the gradient difference exceeds the preset drying safety gradient difference, it combines real-time drying temperature data to obtain a preliminary risk intervention dataset for paperboard. The model building module constructs a regulatory decision model for controlling the temperature of the drying board during hot pressing. It takes the extracted process feature parameters as the model input, the preliminary risk intervention dataset of the cardboard as the decision trigger condition, and dynamically outputs a coordinated control strategy including temperature setting, time adjustment, and spray start / stop. The intelligent adjustment module, based on the collaborative control strategy, transforms the commands into equipment execution commands, transmits them to the intelligent equipment on the production line for real-time adjustment, and feeds back to the equipment control and management terminal.

Images