Printing temperature control simulation method and system based on PLC control

Abstract

The invention relates to the technical field of production control, and discloses a printing temperature control simulation method and system based on PLC control. According to the method, infrared temperature sensors are evenly installed in a printing temperature monitoring area, historical temperature data of the printing temperature monitoring area and the surrounding environment are gathered and collected, meanwhile, the historical temperature data collected in real time are processed through a data processing method, and after processing is completed, the printing temperature monitoring area is monitored. Analyzing the processed historical temperature data through a control variable method and an environment temperature method to obtain analyzed historical temperature data, constructing a temperature prediction model based on the analyzed historical temperature data, training the temperature prediction model through a model optimization algorithm, and obtaining a trained equipment temperature prediction model; and finally, simulation control is performed through a PLC based on the trained temperature prediction model, so that the accuracy of printing temperature control simulation is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of production control, and in particular to a printing temperature control simulation method and system based on PLC control. Background Art

[0002] As the degree of automation in industrial production becomes increasingly higher, the requirements for the control accuracy and speed of PCL logic controllers are also constantly increasing. In addition, due to the continuous increase in the number of printing production, long-term printing will cause overheating and reduce the printing effect. However, the method of real-time acquisition and feedback control has great limitations in some specific places.

[0003] The existing patent application CN101825891A, which has been publicly applied for, utilizes a raw material preparation module, a plate preparation module, a monitoring module, an alarm module, and a management client. The monitoring module monitors the temperature, flow rate, and flow duration during raw material and CTP plate preparation, while the alarm module monitors temperature, liquid flow rates, and flow duration in real time for abnormalities, sending corresponding alarm signals when an abnormality occurs. Finally, the management client implements different alarm processing methods for different received alarm signals, achieving automation, real-time monitoring, and abnormality handling during the CTP plate manufacturing process. However, since only temperature monitoring and early warning are performed during the preparation process, temperature control during the preparation process is neglected, resulting in certain limitations. Summary of the Invention

[0004] (1) Technical problems solved

[0005] In response to the shortcomings of the existing technology, the present invention provides a printing temperature control simulation method and system based on PLC control, which has the advantages of real-time, accuracy, and stability, and solves the problem that long-term printing will cause overheating and reduce printing effects.

[0006] (2) Technical solution

[0007] In order to solve the above technical problem that long-term printing may cause overheating and reduce printing effect, the present invention provides the following technical solutions:

[0008] The present invention discloses a printing temperature control simulation method based on PLC control, which specifically includes the following steps:

[0009] S1. Install infrared temperature sensors evenly in the printing temperature monitoring area to collect historical temperature data of the printing temperature monitoring area and the surrounding environment;

[0010] S2. Processing the historical temperature data collected in real time by a data processing method to obtain processed historical temperature data;

[0011] S3. Analyze the processed historical temperature data using a control variable method and an ambient temperature method to obtain analyzed historical temperature data, and construct a temperature prediction model based on the analyzed historical temperature data;

[0012] S31, collecting PLC control parameters corresponding to the temperature data of the printing temperature monitoring area and the surrounding environment;

[0013] S32. Based on the collected PLC control parameters, a dynamic compensation analysis is performed on the processed historical temperature data in combination with the ambient temperature method and the control variable method;

[0014] S33, summarizing the analysis results to construct a temperature prediction model;

[0015] S4. Training the temperature prediction model through a model optimization algorithm and obtaining a trained device temperature prediction model;

[0016] S5. Perform simulation control through PLC based on the trained temperature prediction model.

[0017] The present invention evenly installs infrared temperature sensors in the printing temperature monitoring area, collects historical temperature data of the printing temperature monitoring area and the surrounding environment, and processes the historical temperature data collected in real time through a data processing method. After the processing is completed, the processed historical temperature data is analyzed by a control variable method and an ambient temperature method to obtain the analyzed historical temperature data, and a temperature prediction model is constructed based on the analyzed historical temperature data. At the same time, the temperature prediction model is trained by a model optimization algorithm to obtain a trained equipment temperature prediction model. Finally, simulation control is performed through a PLC based on the trained temperature prediction model, thereby improving the accuracy of printing temperature control simulation.

[0018] Preferably, the processing of the historical temperature data collected in real time by the data processing method to obtain the processed historical temperature data comprises the following steps:

[0019] S21, filtering the historical temperature data collected in real time to obtain filtered historical temperature data;

[0020] Traverse the historical temperature data collected in real time, and determine whether there is duplicate data based on the timestamp and data content of the corresponding historical temperature data;

[0021] When duplicate data exists within a group, the data that is traversed later is deleted based on the traversal order, and the data that is traversed earlier is retained;

[0022] The retained historical temperature data are aggregated to obtain filtered historical temperature data.

[0023] S22. Standardize the filtered historical temperature data to obtain processed historical temperature data.

[0024] Preferably, the step of normalizing the filtered historical temperature data to obtain the processed historical temperature data comprises the following steps:

[0025] The data standardization formula is as follows:

[0026]

[0027] Among them, X represents the data before standardization. represents the data after normalization; X max Indicates the maximum value of the collected data; X min Indicates the minimum value of the collected data;

[0028] The standardized data is set as the processed historical temperature data.

[0029] The present invention obtains filtered historical temperature data by filtering the historical temperature data collected in real time. After the filtering is completed, the filtered historical temperature data is standardized and the reliability of the temperature data is improved by the standardized processing method.

[0030] Preferably, the dynamic compensation analysis of the processed historical temperature data based on the collected PLC control parameters in combination with the ambient temperature method and the control variable method includes the following steps:

[0031] Set the ambient temperature range at different stages to monitor the specific temperature of the printing temperature monitoring area in real time. Every time the temperature changes by 1°C, record the PLC control parameter value within the corresponding ambient temperature range to determine the influencing factor between the ambient temperature and the PLC control parameter in the printing temperature monitoring area.

[0032] Dynamically compensate the processed historical temperature data based on the influencing factors between ambient temperature and PLC control parameters;

[0033] The temperature dynamic compensation formula is as follows:

[0034] dV=du+f m (dW);

[0035] Where, dV represents the temperature dynamic compensation change, du represents the PLC control parameter change, and dW represents the difference between the ambient temperature and the processed historical temperature; f m It is an m-order polynomial, which represents the influencing factor between the ambient temperature and the PLC control parameters in the printing temperature monitoring area.

[0036] Preferably, the process of constructing a temperature prediction model by summarizing the analysis results comprises the following steps:

[0037] Let A be the ambient temperature parameter matrix, B be the PLC control parameter matrix, and C be the temperature parameter matrix of the predicted printing temperature monitoring area;

[0038]

[0039] Where T represents the sampling period, k represents the kth moment, I represents the unit matrix, k+1 represents the k+1th moment, G represents the PLC control parameter matrix of the periodic input, and Φ represents the ambient temperature parameter matrix after being processed by the unit matrix.

[0040] The present invention collects the PLC control parameters corresponding to the temperature data of the printing temperature monitoring area and the surrounding environment, and records the corresponding PLC control parameter values ​​when the temperature changes through the control variable method, and performs analysis and dynamic compensation. At the same time, a temperature prediction model is constructed based on the dynamic compensation results, thereby improving the rationality of temperature prediction.

[0041] Preferably, the step of training the temperature prediction model by using a model optimization algorithm and obtaining the trained device temperature prediction model comprises the following steps:

[0042] S41, particle swarm optimization algorithm parameter initialization;

[0043] The ambient temperature parameters and PLC control parameters at the same moment are regarded as a set of parameter data;

[0044] Set each particle to represent a set of parameter data, set the group size, and the maximum number of iterations j max , particle random position q, particle velocity y and inertia factor

[0045] S42, using the correction function of the prediction error in the temperature and humidity prediction model as the fitness function of the particle swarm optimization algorithm, and calculating the fitness of each particle in the population;

[0046] S43, updating the optimal position of a single particle based on the calculated fitness;

[0047] The formula for updating the velocity of a single particle is as follows:

[0048]

[0049] Among them, y α (j+1) represents the velocity of particle α in the j+1th iteration, y α (j) represents the velocity of particle α during the jth iteration, represents the inertia factor, q α(j) represents the position of particle α in the jth iteration, b1 and b2 represent acceleration constants, r1 and r2 represent random numbers in the interval [0,1], β α represents the individual extreme value of particle α, β i Represents the global extreme value of all particles;

[0050] The formula for updating the position of a single particle is as follows:

[0051] q α (j+1)=y α (j+1)+q α (j);

[0052] Among them, q α (j+1) represents the position of particle α during the j+1th iteration;

[0053] For each particle calculated, the fitness of its current position is compared with the best position q it has passed. best If the fitness of the current position is greater than the best position q it has passed, best The fitness of the current position is taken as the current best position q best , if the fitness of the current position is less than or equal to the best position q it has passed best The fitness of the current best position q is not changed. best ;

[0054] S44, updating the optimal position of the group based on the calculated fitness;

[0055] For each particle calculated, the fitness of its current position is compared with the best position g that the particle in its population has passed. best If the fitness of the current position is greater than the best position g that the particle in the population has passed through, best The fitness of the current position is taken as the current best position g best , if the fitness of the current position is less than or equal to the best position g that the particle in the population has passed best The fitness of the current best position g is not changed. best ;

[0056] S45, updating the inertia factor, and updating the positions and velocities of all particles based on the updated inertia factor;

[0057] S46, repeating steps S42-S45 until the maximum number of iterations is reached, and outputting the temperature prediction model corresponding to the optimal position;

[0058] The temperature prediction model corresponding to the optimal output position is set as the trained temperature prediction model.

[0059] Preferably, the method of using the correction function of the prediction error in the temperature and humidity prediction model as the fitness function of the particle swarm optimization algorithm and calculating the fitness of each particle in the population includes the following steps:

[0060] The correction function formula for the prediction error in the temperature and humidity prediction model is as follows:

[0061] C(k+1)=Φ(k)+f m G(k);

[0062] The fitness calculation formula for each particle is as follows:

[0063]

[0064] Among them, Fit(r) represents the fitness of the rth individual, and ε represents the correction function of the prediction error in the temperature and humidity prediction model.

[0065] Preferably, the updating of the inertia factor and updating the positions and velocities of all particles based on the updated inertia factor comprises the following steps:

[0066] The inertia factor update formula is as follows:

[0067]

[0068] in, represents the inertia factor at the beginning of the iteration, Indicates the inertia factor at the final iteration, j indicates the current number of iterations, j max Indicates the maximum number of iterations.

[0069] The present invention trains the temperature prediction model through a model optimization algorithm, uses a particle swarm optimization algorithm, and uses a correction function of the prediction error in the temperature and humidity prediction model as the fitness function of the particle swarm optimization algorithm. Based on the fitness function, the particle position is continuously iteratively calculated and updated until the trained temperature prediction model is output, thereby improving the stability of the temperature prediction model training optimization.

[0070] Preferably, the simulation control by PLC based on the trained temperature prediction model includes the following steps:

[0071] Collect PLC control parameters, ambient temperature data, and real-time temperature data of the printing temperature monitoring area in real time, and input the collected PLC control parameters and ambient temperature data into the trained temperature prediction model;

[0072] Based on the real-time collected temperature data of the printing temperature monitoring area, the predicted temperature set at the next moment is calculated;

[0073] Based on the predicted temperature set at the next moment, the printing temperature monitoring area is simulated and controlled and dynamically adjusted in real time.

[0074] This embodiment also discloses a printing temperature control simulation system based on PLC control, which is used to implement a printing temperature control simulation method based on PLC control. The system includes: a data acquisition module, a data processing module, a data analysis module, a prediction model construction module, and a simulation control module;

[0075] The data acquisition module is used to collect temperature data of the printing temperature monitoring area and the surrounding environment in real time;

[0076] The data processing module is used to process the temperature data collected in real time to obtain processed temperature data;

[0077] The data analysis module is used to analyze the processed temperature data to obtain analyzed temperature data;

[0078] The prediction model building module is used to build a temperature prediction model based on the analyzed temperature data;

[0079] The simulation control module is used to perform simulation control based on the constructed temperature prediction model.

[0080] (3) Beneficial effects

[0081] Compared with the existing technology, the present invention provides a printing temperature control simulation method and system based on PLC control, which has the following beneficial effects:

[0082] 1. The invention collects and summarizes historical temperature data of the printing temperature monitoring area and the surrounding environment by evenly installing infrared temperature sensors in the printing temperature monitoring area, and processes the historical temperature data collected in real time by a data processing method. After the processing is completed, the processed historical temperature data is analyzed by the control variable method and the ambient temperature method to obtain the analyzed historical temperature data, and a temperature prediction model is constructed based on the analyzed historical temperature data. At the same time, the temperature prediction model is trained by the model optimization algorithm to obtain a trained equipment temperature prediction model. Finally, simulation control is performed through PLC based on the trained temperature prediction model, thereby improving the accuracy of printing temperature control simulation.

[0083] 2. The invention filters the historical temperature data collected in real time to obtain filtered historical temperature data. After the filtering is completed, the filtered historical temperature data is standardized and the reliability of the temperature data is improved through the standardized processing method.

[0084] 3. This invention collects the PLC control parameters corresponding to the temperature data of the printing temperature monitoring area and the surrounding environment, and records the corresponding PLC control parameter values ​​when the temperature changes through the control variable method, and performs analysis and dynamic compensation. At the same time, a temperature prediction model is constructed based on the dynamic compensation results, thereby improving the rationality of temperature prediction.

[0085] 4. The invention trains the temperature prediction model through a model optimization algorithm, and uses a particle swarm optimization algorithm, and uses the correction function of the prediction error in the temperature and humidity prediction model as the fitness function of the particle swarm optimization algorithm. Based on the fitness function, the particle position is continuously iteratively calculated and updated until the trained temperature prediction model is output, thereby improving the stability of the temperature prediction model training optimization. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] Figure 1 It is a schematic diagram of the process structure of the printing temperature control simulation method based on PLC control of the present invention. DETAILED DESCRIPTION

[0087] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0088] Example 1

[0089] See also Figure 1 This embodiment discloses a printing temperature control simulation method based on PLC control, which specifically includes the following steps:

[0090] S1. Install infrared temperature sensors evenly in the printing temperature monitoring area to collect historical temperature data of the printing temperature monitoring area and the surrounding environment;

[0091] S2. Processing the historical temperature data collected in real time by a data processing method to obtain processed historical temperature data;

[0092] S3. Analyze the processed historical temperature data using a control variable method and an ambient temperature method to obtain analyzed historical temperature data, and construct a temperature prediction model based on the analyzed historical temperature data;

[0093] S31, collecting PLC control parameters corresponding to the temperature data of the printing temperature monitoring area and the surrounding environment;

[0094] S32. Based on the collected PLC control parameters, a dynamic compensation analysis is performed on the processed historical temperature data in combination with the ambient temperature method and the control variable method;

[0095] S33, summarizing the analysis results to construct a temperature prediction model;

[0096] S4. Training the temperature prediction model through a model optimization algorithm and obtaining a trained device temperature prediction model;

[0097] S5. Perform simulation control through PLC based on the trained temperature prediction model;

[0098] Further, see Figure 1 , processing the historical temperature data collected in real time by a data processing method to obtain the processed historical temperature data includes the following steps:

[0099] S21, filtering the historical temperature data collected in real time to obtain filtered historical temperature data;

[0100] Traverse the historical temperature data collected in real time, and determine whether there is duplicate data based on the timestamp and data content of the corresponding historical temperature data;

[0101] When duplicate data exists within a group, the data that is traversed later is deleted based on the traversal order, and the data that is traversed earlier is retained;

[0102] The retained historical temperature data are aggregated to obtain filtered historical temperature data.

[0103] S22, performing standardization processing on the filtered historical temperature data to obtain processed historical temperature data;

[0104] The data standardization formula is as follows:

[0105]

[0106] Among them, X represents the data before standardization. represents the data after normalization; X max Indicates the maximum value of the collected data; X min Indicates the minimum value of the collected data;

[0107] Set the normalized data as the processed historical temperature data;

[0108] Further, see Figure 1 Based on the collected PLC control parameters, the dynamic compensation analysis of the processed historical temperature data combined with the ambient temperature method and the control variable method includes the following steps:

[0109] Set the ambient temperature range at different stages to monitor the specific temperature of the printing temperature monitoring area in real time. Every time the temperature changes by 1°C, record the PLC control parameter value within the corresponding ambient temperature range to determine the influencing factor between the ambient temperature and the PLC control parameter in the printing temperature monitoring area.

[0110] Furthermore, the processed historical temperature data is dynamically compensated based on the influencing factors between the ambient temperature and the PLC control parameters;

[0111] The temperature dynamic compensation formula is as follows:

[0112] dV=du+f m (dW);

[0113] Where, dV represents the temperature dynamic compensation change, du represents the PLC control parameter change, and dW represents the difference between the ambient temperature and the processed historical temperature; f m is an m-order polynomial, which represents the influencing factor between the ambient temperature and the PLC control parameters in the printing temperature monitoring area;

[0114] Further, see Figure 1 ,The ,summarizing the analysis results and constructing the ,temperature prediction model includes the following steps:

[0115] Let A be the ambient temperature parameter matrix, B be the PLC control parameter matrix, and C be the temperature parameter matrix of the predicted printing temperature monitoring area;

[0116]

[0117] Where T represents the sampling period, k represents the kth moment, I represents the unit matrix, k+1 represents the k+1th moment, G represents the PLC control parameter matrix of the periodic input, and Φ represents the ambient temperature parameter matrix after being processed by the unit matrix;

[0118] Further, see Figure 1 , training the temperature prediction model through the model optimization algorithm and obtaining the trained device temperature prediction model includes the following steps:

[0119] S41, particle swarm optimization algorithm parameter initialization;

[0120] The ambient temperature parameters and PLC control parameters at the same moment are regarded as a set of parameter data;

[0121] Set each particle to represent a set of parameter data, set the group size, and the maximum number of iterations j max , particle random position q, particle velocity y and inertia factor

[0122] S42, using the correction function of the prediction error in the temperature and humidity prediction model as the fitness function of the particle swarm optimization algorithm, and calculating the fitness of each particle in the population;

[0123] The correction function formula for the prediction error in the temperature and humidity prediction model is as follows:

[0124] C(k+1)=Φ(k)+f m G(k);

[0125] The fitness calculation formula for each particle is as follows:

[0126]

[0127] Among them, Fit(r) represents the fitness of the rth individual, ε represents the correction function of the prediction error in the temperature and humidity prediction model;

[0128] S43, updating the optimal position of a single particle based on the calculated fitness;

[0129] The formula for updating the velocity of a single particle is as follows:

[0130]

[0131] Among them, y α (j+1) represents the velocity of particle α in the j+1th iteration, y α (j) represents the velocity of particle α during the jth iteration, represents the inertia factor, q α (j) represents the position of particle α in the jth iteration, b1 and b2 represent acceleration constants, r1 and r2 represent random numbers in the interval [0,1], β α represents the individual extreme value of particle α, β i Represents the global extreme value of all particles;

[0132] The formula for updating the position of a single particle is as follows:

[0133] q α (j+1)=y α (j+1)+q α (j);

[0134] Among them, q α (j+1) represents the position of particle α during the j+1th iteration;

[0135] For each particle calculated, the fitness of its current position is compared with the best position q it has passed. best If the fitness of the current position is greater than the best position q it has passed, bestThe fitness of the current position is taken as the current best position q best , if the fitness of the current position is less than or equal to the best position q it has passed best The fitness of the current best position q is not changed. best ;

[0136] S44, updating the optimal position of the group based on the calculated fitness;

[0137] For each particle calculated, the fitness of its current position is compared with the best position g that the particle in its population has passed. best If the fitness of the current position is greater than the best position g that the particle in the population has passed through, best The fitness of the current position is taken as the current best position g best , if the fitness of the current position is less than or equal to the best position g that the particle in the population has passed best The fitness of the current best position g is not changed. best ;

[0138] S45, updating the inertia factor, and updating the positions and velocities of all particles based on the updated inertia factor;

[0139] The inertia factor update formula is as follows:

[0140]

[0141] in, represents the inertia factor at the beginning of the iteration, Indicates the inertia factor at the final iteration, j indicates the current number of iterations, j max Indicates the maximum number of iterations;

[0142] S46, repeating steps S42-S45 until the maximum number of iterations is reached, and outputting the temperature prediction model corresponding to the optimal position;

[0143] The temperature prediction model corresponding to the optimal output position is set as the trained temperature prediction model.

[0144] Further, see Figure 1 , the simulation control through PLC based on the trained temperature prediction model includes the following steps:

[0145] Collect PLC control parameters, ambient temperature data, and real-time temperature data of the printing temperature monitoring area in real time, and input the collected PLC control parameters and ambient temperature data into the trained temperature prediction model;

[0146] Furthermore, based on the real-time collected temperature data of the printing temperature monitoring area, the predicted temperature set at the next moment is calculated;

[0147] Furthermore, based on the predicted temperature set at the next moment, the printing temperature monitoring area is simulated and controlled and dynamically adjusted in real time;

[0148] Example 2

[0149] See also Figure 1 , this embodiment also discloses a printing temperature control simulation system based on PLC control, which is used to implement a printing temperature control simulation method based on PLC control. The system includes: a data acquisition module, a data processing module, a data analysis module, a prediction model construction module and a simulation control module;

[0150] The data acquisition module is used to collect temperature data of the printing temperature monitoring area and the surrounding environment in real time;

[0151] The data processing module is used to process the temperature data collected in real time to obtain processed temperature data;

[0152] The data analysis module is used to analyze the processed temperature data to obtain analyzed temperature data;

[0153] The prediction model building module is used to build a temperature prediction model based on the analyzed temperature data;

[0154] The simulation control module is used to perform simulation control based on the constructed temperature prediction model.

[0155] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A printing temperature control simulation method based on PLC control, characterized in that: The following steps are involved: S1. Install infrared temperature sensors evenly in the printing temperature monitoring area to collect historical temperature data of the printing temperature monitoring area and the surrounding environment; S2. Processing the historical temperature data collected in real time by a data processing method to obtain processed historical temperature data; S3. Analyze the processed historical temperature data using a control variable method and an ambient temperature method to obtain analyzed historical temperature data, and construct a temperature prediction model based on the analyzed historical temperature data; S31, collecting PLC control parameters corresponding to the temperature data of the printing temperature monitoring area and the surrounding environment; S32. Based on the collected PLC control parameters, a dynamic compensation analysis is performed on the processed historical temperature data in combination with the ambient temperature method and the control variable method; S33, summarizing the analysis results to construct a temperature prediction model; S4. Training the temperature prediction model through a model optimization algorithm and obtaining a trained device temperature prediction model; S5. Perform simulation control through PLC based on the trained temperature prediction model.

2. A printing temperature control simulation method based on PLC control according to claim 1, characterized in that: The method of processing the historical temperature data collected in real time by the data processing method to obtain the processed historical temperature data comprises the following steps: S21, filtering the historical temperature data collected in real time to obtain filtered historical temperature data; Traverse the historical temperature data collected in real time, and determine whether there is duplicate data based on the timestamp and data content of the corresponding historical temperature data; When duplicate data exists within a group, the data that is traversed later is deleted based on the traversal order, and the data that is traversed earlier is retained; The retained historical temperature data are aggregated to obtain filtered historical temperature data. S22. Standardize the filtered historical temperature data to obtain processed historical temperature data.

3. The printing temperature control simulation method based on PLC control according to claim 2 is characterized in that: The standardization processing of the filtered historical temperature data to obtain the processed historical temperature data comprises the following steps: The data standardization formula is as follows: Among them, X represents the data before standardization. represents the data after normalization; X max Indicates the maximum value of the collected data; X min Indicates the minimum value of the collected data; The normalized data is set as the processed historical temperature data.

4. The printing temperature control simulation method based on PLC control according to claim 1 is characterized in that: The method of performing dynamic compensation analysis on the processed historical temperature data based on the collected PLC control parameters in combination with the ambient temperature method and the control variable method includes the following steps: Set the ambient temperature range at different stages to monitor the specific temperature of the printing temperature monitoring area in real time. Every time the temperature changes by 1°C, record the PLC control parameter value within the corresponding ambient temperature range to determine the influencing factor between the ambient temperature and the PLC control parameter in the printing temperature monitoring area. Dynamically compensate the processed historical temperature data based on the influencing factors between ambient temperature and PLC control parameters; The temperature dynamic compensation formula is as follows: dV=du+f m (dW); Where, dV represents the temperature dynamic compensation change, du represents the PLC control parameter change, and dW represents the difference between the ambient temperature and the processed historical temperature; f m It is an m-order polynomial, which represents the influencing factor between the ambient temperature and the PLC control parameters in the printing temperature monitoring area.

5. The printing temperature control simulation method based on PLC control according to claim 1 is characterized in that: The summary analysis results to construct a temperature prediction model include the following steps: Let A be the ambient temperature parameter matrix, B be the PLC control parameter matrix, and C be the temperature parameter matrix of the predicted printing temperature monitoring area; Where T represents the sampling period, k represents the kth moment, I represents the unit matrix, k+1 represents the k+1th moment, G represents the PLC control parameter matrix of the periodic input, and Φ represents the ambient temperature parameter matrix after being processed by the unit matrix.

6. The printing temperature control simulation method based on PLC control according to claim 1 is characterized in that: The method of training the temperature prediction model by the model optimization algorithm and obtaining the trained device temperature prediction model includes the following steps: S41, particle swarm optimization algorithm parameter initialization; The ambient temperature parameters and PLC control parameters at the same moment are regarded as a set of parameter data; Set each particle to represent a set of parameter data, set the group size, and the maximum number of iterations j max , particle random position q, particle velocity y and inertia factor S42, using the correction function of the prediction error in the temperature and humidity prediction model as the fitness function of the particle swarm optimization algorithm, and calculating the fitness of each particle in the population; S43, updating the optimal position of a single particle based on the calculated fitness; The formula for updating the velocity of a single particle is as follows: Among them, y α (j+1) represents the velocity of particle α in the j+1th iteration, y α (j) represents the velocity of particle α during the jth iteration, represents the inertia factor, q α (j) represents the position of particle α in the jth iteration, b1 and b2 represent acceleration constants, r1 and r2 represent random numbers in the interval [0,1], β α represents the individual extreme value of particle α, β i Represents the global extreme value of all particles; The formula for updating the position of a single particle is as follows: q α (j+1)=y α (j+1)+q α (j); Among them, q α (j+1) represents the position of particle α during the j+1th iteration; For each particle calculated, the fitness of its current position is compared with the best position q it has passed. best If the fitness of the current position is greater than the best position q it has passed, best The fitness of the current position is taken as the current best position q best , if the fitness of the current position is less than or equal to the best position q it has passed best The fitness of the current best position q is not changed. best ; S44, updating the optimal position of the group based on the calculated fitness; For each particle calculated, the fitness of its current position is compared with the best position g that the particle in its population has passed. best If the fitness of the current position is greater than the best position g that the particle in the population has passed through, best The fitness of the current position is taken as the current best position g best , if the fitness of the current position is less than or equal to the best position g that the particle in the population has passed best The fitness of the current best position g is not changed. best ; S45, updating the inertia factor, and updating the positions and velocities of all particles based on the updated inertia factor; S46, repeating steps S42-S45 until the maximum number of iterations is reached, and outputting the temperature prediction model corresponding to the optimal position; The temperature prediction model corresponding to the optimal output position is set as the trained temperature prediction model.

7. The printing temperature control simulation method based on PLC control according to claim 6 is characterized in that: The method of using the correction function of the prediction error in the temperature and humidity prediction model as the fitness function of the particle swarm optimization algorithm and calculating the fitness of each particle in the population includes the following steps: The correction function formula for the prediction error in the temperature and humidity prediction model is as follows: C(k+1)=Φ(k)+f m G(k); The fitness calculation formula for each particle is as follows: Among them, Fit(r) represents the fitness of the rth individual, and ε represents the correction function of the prediction error in the temperature and humidity prediction model.

8. The printing temperature control simulation method based on PLC control according to claim 6 is characterized in that: The updating of the inertia factor and the updating of the positions and velocities of all particles based on the updated inertia factor include the following steps: The inertia factor update formula is as follows: in, represents the inertia factor at the beginning of iteration, Indicates the inertia factor at the final iteration, j indicates the current number of iterations, j max Indicates the maximum number of iterations.

9. The printing temperature control simulation method based on PLC control according to claim 1, characterized in that: The simulation control based on the trained temperature prediction model by PLC includes the following steps: Collect PLC control parameters, ambient temperature data, and real-time temperature data of the printing temperature monitoring area in real time, and input the collected PLC control parameters and ambient temperature data into the trained temperature prediction model; Based on the real-time collected temperature data of the printing temperature monitoring area, the predicted temperature set at the next moment is calculated; Based on the predicted temperature set at the next moment, the printing temperature monitoring area is simulated and controlled and dynamically adjusted in real time.

10. A system for implementing the printing temperature control simulation method based on PLC control according to any one of claims 1 to 9, characterized in that: It includes data acquisition module, data processing module, data analysis module, prediction model building module and simulation control module; The data acquisition module is used to collect temperature data of the printing temperature monitoring area and the surrounding environment in real time; The data processing module is used to process the temperature data collected in real time to obtain processed temperature data; The data analysis module is used to analyze the processed temperature data to obtain analyzed temperature data; The prediction model building module is used to build a temperature prediction model based on the analyzed temperature data; The simulation control module is used to perform simulation control based on the constructed temperature prediction model.

Images