Thermoforming energy-saving system and method for plastic vacuum forming machine based on double-station time sequence collaboration

Abstract

The invention belongs to the technical field of thermoforming of plastic vacuum forming machines, and provides a thermoforming energy-saving system and method for a plastic vacuum forming machine based on double-station time sequence collaboration.The thermoforming energy-saving method comprises the steps that a heat needing sensing system is constructed through a heating station inlet sensor, heating partitions are divided, the heat needing state of a sheet is dynamically matched, and an outlet sensor conducts real-time feedback and correction; relying on the process parameter knowledge base and the energy consumption model, a heating strategy is optimized through a genetic algorithm; a fault judgment mechanism is introduced, a standby heating pipe is rapidly switched when a fault occurs, a double-station cooperation mechanism is synchronously established, and power pre-compensation of a rear station is achieved through temperature deviation transmission of a front station; a digital twin management module is constructed, faults and time sequence deviation are actively predicted through a long-short-term memory network in combination with historical data, a forming time sequence is accurately regulated and controlled, the double-station precision consistency and the energy utilization rate are improved, and production continuity is guaranteed.

Description

Technical Field

[0001] This invention belongs to the field of thermoforming technology for vacuum forming machines, specifically an energy-saving system and method for thermoforming vacuum forming machines based on dual-station sequential coordination. Background Technology

[0002] Traditional heating methods mostly adopt an overall constant temperature mode, which does not accurately control the heat demand differences in different areas of the sheet. The heat loss rate is high, and there is a lack of real-time feedback and correction mechanism, resulting in prominent problems of overheating or underheating. Existing dual-station equipment mostly operates independently and has not established a parameter coordination link. Temperature deviations caused by heating tube aging, environmental interference, etc. cannot be compensated across stations, resulting in large fluctuations in the quality of dual-station products.

[0003] Heating element malfunctions rely on manual troubleshooting, with judgment based on a single parameter, making misdiagnosis easy and causing delays in switching. Downtime due to malfunctions leads to increased batch scrap rates. Fluctuations in heating duration are not linked to the molding station sequence; overheating causes molding waiting, while premature completion results in idle equipment, reducing efficiency and increasing wasted energy. The lack of digital twin technology support prevents proactive prediction of malfunctions and timing deviations based on historical data; process parameter optimization relies on experience, resulting in poor flexibility for adapting to multi-material production.

[0004] Therefore, the present invention provides an energy-saving system and method for thermoforming of a vacuum forming machine based on dual-station timing coordination. Summary of the Invention

[0005] In order to overcome the shortcomings of the prior art, at least one technical problem raised in the background art is solved.

[0006] The technical solution adopted by this invention to solve its technical problem is: On one hand, the present invention provides an energy-saving method for thermoforming of a vacuum forming machine based on dual-station timing coordination, comprising: S1: Deploy sensors at the entrance of the heating station to build a temperature sensing system, identify the heat demand status of each area of ​​the sheet, divide the heating area into multiple heating zones, optimize the overall temperature distribution of the heating area by dynamically matching the heat demand status of the sheet, and deploy sensors at the exit of the heating station to build a temperature feedback model to provide real-time feedback and correction of the dynamic matching results. S2: Construct a process parameter knowledge base, match process parameter combinations for sheets of different materials, introduce an energy consumption model, and dynamically adjust the heating control strategy of the heating zone based on real-time production data and a genetic algorithm. S3: Introducing a main heating tube fault determination mechanism to determine whether the heating zone is faulty. If a fault occurs, the backup heating tube is activated, and a dual-station collaborative mechanism is established to improve the heating accuracy consistency of the two stations. Based on the difference between the actual heating time of the heating station and the original planned heating time, the timing deviation of the forming station is precisely controlled. S4: Construct a digital twin management module to proactively predict heating zones through historical heating zone fault records, further improving the heating accuracy consistency of the two workstations. Based on historical records of the difference between the actual heating time and the original planned heating time of the heating workstation, a long short-term memory network is used to proactively predict the timing deviation of the molding workstation, thereby improving the energy utilization rate of the molding workstation.

[0007] As a further improvement of the present invention, the specific process of identifying the heat demand state of each region of the sheet is as follows: At the entrance of the heating station, an infrared thermal imager and a fiber optic sensor are used to construct a temperature sensing system to generate a two-dimensional temperature distribution cloud map of the sheet along the X and Y axes. The infrared thermal imager has a temperature measurement accuracy of ±0.5℃, and the fiber optic sensor has a sampling period of ≤0.1 seconds, so as to accurately identify the heating status of each area of ​​the sheet. The specific requirements for heat demand include: hot zone location and the difference between the target temperature and the current temperature.

[0008] As a further improvement of the present invention, the specific process of real-time feedback correction of the dynamic matching results is as follows: The heating area is divided into multiple heating zones according to the X×Y matrix. A micro frequency converter is configured for each heating zone. Based on the two-dimensional temperature distribution cloud map data of the sheet along the XY axis and the required heating status, the output power of the micro frequency converter is adjusted to dynamically match the heating power of each heating zone with the current temperature difference of the corresponding area and the target temperature.

[0009] Near-infrared spectral sensors and laser thickness gauges are added at the heating station exit to detect the crystallinity, impurity content, and local thickness deviation of the sheet in real time. A neural network model was established with crystallinity, impurity content, and local thickness deviation as inputs and target temperature correction as output. The temperature feedback model was obtained after training and validating the neural network model with historical data. Based on the temperature feedback model, the target temperature correction is output, and the output power of the micro frequency converter is adjusted by the PID control algorithm to accurately meet the power requirements of the sheet after it reaches the required temperature.

[0010] As a further improvement of the present invention, the specific process of matching the sheet process parameters of different materials is as follows: Data on heating power, heating temperature, heating time, and forming qualification rate from historical production data are obtained. Regression analysis algorithms are used to obtain the optimal process parameter mapping relationship for different sheet types, forming a process knowledge base. The mathematical expression for the optimal process parameter mapping relationship for different sheet types is as follows: For the i-th sheet type and the j-th thickness, a temperature field function is constructed. Heating power function Molding quality function ; in, This represents the material property parameters of the i-th type of sheet, where i is the index of the sheet type. Let be the thickness of the j-th type of sheet, where j is the index of the sheet thickness. The temperature field is given by the combination of the i-th sheet material and the j-th thickness. The required heating power for the i-th sheet material and the j-th thickness combination. The forming quality is determined by the temperature field and heating power of the i-th sheet and j-th thickness combination. By training the model parameters of the temperature field function, heating power function, and molding quality function using historical production data, To meet the molding quality requirements, the final product will be This information is stored in the knowledge base as the optimal parameter for the sheet-thickness combination. When changing production, the optimal combination of process parameters is matched with the corresponding sheet type and thickness.

[0011] As a further improvement of the present invention, the specific process of dynamically adjusting the heating control strategy of the heating zone using a genetic algorithm is as follows: An energy consumption model is introduced, and the energy consumption model is defined as follows: Where E is the energy consumption per unit time, P is the total heating power of the heating area, i.e. the sum of the heating power of each heating zone, t is the heating time, ΔT is the difference between the workshop ambient temperature and the reference temperature; α, β, γ are preset weighting coefficients, reflecting the degree of influence of each factor on energy consumption; A genetic algorithm is used to randomly generate multiple sets of heating zones and heating zone power allocation schemes, as well as α, β, and γ as initial solutions. The fitness function is to select high-quality solutions with higher weights for molding quality pass rate and lower energy consumption. Selection, crossover, and mutation are performed on the high-quality solutions to generate a new generation population. Until the population fitness stabilizes, the optimal power allocation for heating zones and the combination of α, β, and γ are output, and the energy consumption model and heating control strategy are updated in real time. Based on the production plan, real-time production data is collected every x hours, and the genetic algorithm is automatically started to iterate to achieve dynamic optimization of the energy consumption model.

[0012] As a further improvement of the present invention, the specific process of activating the backup heating tube is as follows: Assume the rated current of the main heating element is The permissible current fluctuation threshold for the rated current of the main heating element is... ; The rated temperature of the main heating element is The temperature deviation judgment threshold of the main heating element is The detected current of the main heating element is The detected temperature of the main heating element is ; The main heating element is considered faulty when both of the following conditions are met: Condition 1: The actual current is within the allowable fluctuation range of the rated current. ; Condition 2: The deviation between the actual temperature and the rated temperature exceeds the judgment threshold. ; If a malfunction occurs, the system will switch to the backup heating element within a preset time.

[0013] As a further improvement of the present invention, the specific process of establishing a dual-station collaborative mechanism to improve the heating accuracy consistency of the two stations is as follows: Workstation A obtains real-time temperature deviation information for its own heating zone. The temperature deviation information will be transmitted to workstation B in real time. Based on the temperature deviation-power compensation quantization relationship calibrated in advance through experiments ,in, The power that needs to be compensated in advance for workstation B. This is the power compensation coefficient, calibrated experimentally. This coefficient represents the power compensation ratio corresponding to each unit temperature deviation. This represents the absolute value of the real-time temperature deviation information for workstation A. Workstation B performs power compensation adjustment for the corresponding heating zone in advance to avoid the same temperature deviation as workstation A, thus ensuring the consistency of heating accuracy between the two workstations. Based on the difference between the actual heating time and the original planned heating time at the heating station, the timing deviation of the molding station is precisely controlled; If the actual heating time at the heating station is longer than the originally planned heating time, the molding station will perform a delayed mold closing operation via a servo motor based on the difference in heating time between the two. If the actual heating time at the heating station is less than the originally planned heating time, the forming station will execute the ejection mechanism reset action in advance based on the time difference between the two.

[0014] As a further improvement of the present invention, the specific process for further improving the heating accuracy consistency of the dual-station system is as follows: A digital twin management module is constructed based on historical heating zone fault records. The fault records include: heating tube burnout, frequency converter power supply failure, and operating parameters at the time of the fault. Based on historical heating zone fault records, a digital twin management module is built for each heating zone of the dual-station system. By analyzing the dynamic evolution trend of parameters in historical heating zone fault records, the risk of heating zone faults can be predicted in advance. Before a fault occurs, preventive maintenance or dynamic parameter compensation is triggered to ensure the consistency of heating uniformity in the dual-station system.

[0015] As a further improvement of the present invention, the specific process for improving the energy utilization rate of the forming station is as follows: Based on the historical records of the difference between the actual heating time and the original planned heating time at the heating station, and the associated production parameters, including sheet material, thickness, and workshop ambient temperature, a time-series dataset is constructed, which records the heating time deviation value, PET crystallinity, and ambient temperature change sequence by production batch. By inputting the time series dataset into the Long Short-Term Memory (LSTM) network, and leveraging the LSTM network's ability to capture long-term temporal dependencies, we can learn the potential patterns of heating duration differences and subsequent temporal deviations in the molding process. Based on the patterns learned from the Long Short-Term Memory network, the time required to delay mold closing or reset the ejection mechanism at the molding station can be predicted in advance.

[0016] On the other hand, the present invention provides an energy-saving thermoforming system for vacuum forming machines based on dual-station sequential coordination, comprising: Heating zone dynamic matching module: A temperature sensing system is built by deploying sensors at the entrance of the heating station to identify the heat demand status of each area of ​​the sheet, divide the heating area into multiple heating zones, optimize the overall temperature distribution of the heating area by dynamically matching the heat demand status of the sheet, and build a temperature feedback model by deploying sensors at the exit of the heating station to provide real-time feedback and correction of the dynamic matching results. Energy consumption optimization module: Construct a process parameter knowledge base, match process parameter combinations for different sheet materials, introduce an energy consumption model, and dynamically adjust the heating control strategy of the heating zone based on real-time production data and a genetic algorithm; Dual-station collaborative control module: Introduces a main heating tube fault determination mechanism to determine whether the heating zone is faulty. If a fault occurs, the backup heating tube is activated, establishing a dual-station collaborative mechanism to improve the heating accuracy consistency of the two stations. Based on the difference between the actual heating time of the heating station and the original planned heating time, the timing deviation of the forming station is precisely controlled. Timing Deviation Proactive Prediction Module: Construct a digital twin management module that proactively predicts heating zones based on historical heating zone fault records, further improving the heating accuracy consistency of the two workstations. Based on historical records of the difference between the actual heating time and the original planned heating time of the heating workstation, a long short-term memory network is used to proactively predict the timing deviation of the molding workstation, thereby improving the energy utilization rate of the molding workstation.

[0017] The beneficial effects of this invention are as follows: 1. The inlet heat sensing and outlet feedback form a closed loop, the heating zone dynamically matches the sheet characteristics, and the energy consumption model optimized by the genetic algorithm significantly reduces the energy consumption per unit product, reduces ineffective heat loss, and significantly improves energy utilization efficiency. The temperature deviation of the front station is transmitted to the back station in real time. The pre-compensation mechanism offsets the individual differences of equipment and environmental interference, solves the problem of uneven heating in dual stations, and greatly reduces the quality fluctuation of products in the same batch.

[0018] 2. The current-temperature dual-parameter judgment mechanism improves the accuracy of fault identification, and the backup heating tube switches in milliseconds. Combined with digital twin fault early warning, it minimizes downtime and improves production continuity. The heating time and molding sequence are linked and controlled to avoid waiting and idling. Combined with LSTM timing prediction, it realizes forward scheduling, which improves molding efficiency and reduces equipment power consumption. The process parameter knowledge base covers the requirements of different materials. The parameter iteration optimization driven by digital twin reduces the time for changeover and debugging, adapts to small batch and multi-variety production, and enhances the practicality and economy of the equipment. Attached Figure Description

[0019] The invention will now be further described with reference to the accompanying drawings.

[0020] Figure 1 This is a flowchart of the steps of the energy-saving thermoforming method for vacuum forming machines based on dual-station timing coordination of the present invention; Figure 2 This is a system module diagram of the thermoforming energy-saving system for vacuum forming machines based on dual-station timing coordination, as described in this invention. Detailed Implementation

[0021] To make the technical means, creative features, objectives and effects of this invention easier to understand, the invention will be further described below in conjunction with specific embodiments.

[0022] Example 1

[0023] like Figure 1 As shown in the embodiment of the present invention, the energy-saving method for thermoforming of a vacuum forming machine based on dual-station timing coordination includes: S1: Deploy sensors at the entrance of the heating station to build a temperature sensing system, identify the heat demand status of each area of ​​the sheet, divide the heating area into multiple heating zones, optimize the overall temperature distribution of the heating area by dynamically matching the heat demand status of the sheet, and deploy sensors at the exit of the heating station to build a temperature feedback model to provide real-time feedback and correction of the dynamic matching results. Deploy sensors to build a temperature sensing system to identify the heat demand status of different areas of the sheet; At the entrance of the heating station, an infrared thermal imager and a fiber optic sensor are used to construct a temperature sensing system to generate a two-dimensional temperature distribution cloud map of the sheet along the X and Y axes. The infrared thermal imager has a temperature measurement accuracy of ±0.5℃, and the fiber optic sensor has a sampling period of ≤0.1 seconds, so as to accurately identify the heating status of each area of ​​the sheet. The heat demand state specifically includes: heat zone location (edge ​​area and center area of ​​the sheet), and the difference between the target temperature and the current temperature; The heating area is divided into multiple heating zones, and the overall temperature distribution of the heating area is optimized by dynamically matching the heat demand state of the sheet. The heating area is divided into multiple heating zones according to an X×Y matrix (e.g., it can be divided into 32 independent and controllable rectangular modules, with an 8×4 matrix layout). Each heating zone is equipped with a micro frequency converter. Based on the XY axis two-dimensional temperature distribution cloud map data of the sheet and the heating status, the output power of the micro frequency converter is adjusted (the power output power adjustment range is 30%-100%) to dynamically match the heating power of each heating zone with the current temperature difference of the corresponding area and the target temperature. In some embodiments, taking a PVC sheet with a processing specification of 1000×800mm as an example, the surface temperature of the sheet is continuously collected by an infrared thermal imager and a fiber optic sensor to generate a two-dimensional temperature distribution cloud map of the sheet along the XY axis. During the production process, if a heat-required state is detected, such as the edge area α temperature reaching the target value of 160℃ in the heat zone positioning, while the central area β temperature is only 150℃, and the target value is 180℃, the system will synchronously acquire the temperature parameters of each area. Based on the two-dimensional temperature distribution cloud map data of the sheet along the XY axis, the power of the heating zone is controlled differently. The power of the micro frequency converter corresponding to the edge region α is reduced from 100% to 30% to maintain the current temperature and avoid overheating. The power of the micro frequency converter corresponding to the center region β is increased to 100% to quickly replenish heat and achieve precise heat replenishment. The energy-saving effect of this step is that, within a single production cycle, by avoiding the energy waste of heating the entire process in one go, this step can effectively reduce the energy consumption of the heating process. It should be noted that the X×Y matrix and power adjustment range of 30%-100% parameters in the embodiments can be flexibly adjusted according to the equipment structure and sheet characteristics in terms of technical parameters as needed. The above values ​​are exemplary selections adapted to typical dual-station vacuum forming machine scenarios. In this invention, the X×Y matrix and power adjustment range of 30%-100% parameters are not limited. Real-time feedback and correction of dynamic matching results; Near-infrared spectral sensors and laser thickness gauges are added at the heating station exit to detect the crystallinity, impurity content, and local thickness deviation of the sheet in real time. A neural network model was established with crystallinity, impurity content, and local thickness deviation as inputs and target temperature correction as output. The temperature feedback model was obtained after training and validating the neural network model with historical data. Based on the temperature feedback model, the target temperature correction amount is output, and the output power of the micro frequency converter is adjusted by the PID control algorithm to accurately meet the power required for the sheet to maintain the required temperature. The maintenance power is the output power required to maintain the target temperature after the sheet temperature matches the target temperature when the sheet is detected to be in a heat-demanding state during the production process and the rectangular module output power is rapidly increased to the maximum power. In this step, adjusting the output power of the rectangular module through a temperature feedback model and a PID control algorithm can effectively reduce energy consumption in the heating process and improve the yield of the sheet material. S2: Construct a process parameter knowledge base, match process parameter combinations for sheets of different materials, introduce an energy consumption model, and dynamically adjust the heating control strategy of the heating zone based on real-time production data and a genetic algorithm. Build a knowledge base of process parameters to match the process parameters of sheets of different materials; Data on heating power, heating temperature, heating time, and forming qualification rate from historical production data are obtained. Regression analysis algorithms are used to obtain the optimal process parameter mapping relationship for different sheet types, forming a process knowledge base. The mathematical expression for the optimal process parameter mapping relationship for different sheet types is as follows: For the i-th sheet type and the j-th thickness, a temperature field function is constructed. Heating power function Molding quality function ; in, This represents the material property parameters of the i-th type of sheet, where i is the index of the sheet type. Let be the thickness of the j-th type of sheet, where j is the index of the sheet thickness. The temperature field is given by the combination of the i-th sheet material and the j-th thickness. The required heating power for the i-th sheet material and the j-th thickness combination. The forming quality is determined by the temperature field and heating power of the i-th sheet and j-th thickness combination. By training the model parameters of the temperature field function, heating power function, and molding quality function using historical production data, To meet molding quality requirements (e.g., pass rate ≥ 95%), the final product will be... This information is stored in the knowledge base as the optimal parameter for the sheet-thickness combination. When changing production models, the optimal combination of process parameters for the corresponding sheet type and thickness is matched to replace the manual trial and error process; For example, taking a PET sheet with a thickness of d=0.5mm as an example, based on historical production data, heating power, heating temperature, heating time, and molding qualification rate data are obtained. Through regression analysis algorithm, the following is obtained: When the sheet type S=PET and the thickness d=0.5mm, the ideal temperature field center temperature corresponds to a heating power P=85% (rated power benchmark), a heating time t=150 seconds, and a heating temperature T=155 degrees Celsius. At this time, the molding quality qualification requirements are met. The optimal combination of process parameters for a PET sheet with a thickness of d=0.5mm is obtained when the heating power P=85% (rated power benchmark), the heating time t=150 seconds, and the heating temperature T=155 degrees Celsius. When production is switched to PET sheet with a thickness of -0.5mm, the system directly calls the optimal combination of process parameters, eliminating the need for manual adjustments to power and time and verification of molding quality, thus reducing production time and improving production efficiency. This step, by building a process parameter knowledge base and matching process parameter combinations for sheets of different materials, effectively reduces the manual trial and error process, thereby reducing energy consumption in the heating process and further improving production efficiency. An energy consumption model is introduced, and the heating control strategy of the heating zone is dynamically adjusted through a genetic algorithm based on real-time production data. An energy consumption model is introduced, and the energy consumption model is defined as follows: Where E is the energy consumption per unit time, P is the total heating power of the heating area, i.e. the sum of the heating power of each heating zone, t is the heating time, ΔT is the difference between the workshop ambient temperature and the reference temperature; α, β, γ are preset weighting coefficients, reflecting the degree of influence of each factor on energy consumption; A genetic algorithm is used to randomly generate multiple sets of heating zones and heating zone power allocation schemes, as well as α, β, and γ as initial solutions. The fitness function is to select high-quality solutions with higher weights for molding quality pass rate and lower energy consumption. Selection, crossover, and mutation are performed on the high-quality solutions to generate a new generation population. Until the population fitness stabilizes, the optimal power allocation for heating zones and the combination of α, β, and γ are output, and the energy consumption model and heating control strategy are updated in real time. Based on the production plan, real-time production data is collected every x hours, and the genetic algorithm iteration is automatically started to achieve dynamic optimization of the energy consumption model. For example, in summer, the ambient temperature in the workshop rises. For instance, the base temperature is 25 degrees Celsius, and the actual measured temperature is 30 degrees Celsius, i.e., ΔT = 5 degrees Celsius. Let the initial energy consumption model weights be α = 0.6, β = 0.3, and γ = 0.1. During the iteration process of the genetic algorithm, the population individuals include: power P1 of heating zone 1, power P2 of heating zone 2, ..., α, β, γ. After iterative convergence, new weights α=0.5, β=0.2, and γ=0.3 are obtained. At the same time, the power of heating zone 1 decreases from 80% to 75%, and the power of heating zone 2 increases from 70% to 72%. At this point, the overall energy consumption of the workshop is reduced, and the molding quality qualification rate meets the standards; the system collects real-time production data every 24 hours and automatically starts the genetic algorithm iteration to achieve dynamic optimization of the energy consumption model.

[0024] It should be noted that the setting of every x hours in the embodiment can be flexibly adjusted according to production needs. In this invention, there is no limit to every x hours. This step addresses the energy consumption problem of model changeover trial and error by pre-storing optimal parameters in a knowledge base, and solves the energy consumption fluctuation problem under environmental changes through dynamic optimization using a genetic algorithm. This achieves high efficiency in model changeover, dynamic energy consumption, and stable quality, providing core technical support for the energy-saving and intelligent production of dual-station thermoforming machine systems.

[0025] S3: Introducing a main heating tube fault determination mechanism to determine whether the heating zone is faulty. If a fault occurs, the backup heating tube is activated, and a dual-station collaborative mechanism is established to improve the heating accuracy consistency of the two stations. Based on the difference between the actual heating time of the heating station and the original planned heating time, the timing deviation of the forming station is precisely controlled. A main heating element fault detection mechanism is introduced to determine whether the heating zone is faulty. If a fault occurs, the backup heating element is activated. Assume the rated current of the main heating element is The permissible current fluctuation threshold for the rated current of the main heating element is... (That is, the current of the main heating element is allowed to be within) (fluctuation within a range) The rated temperature of the main heating element is The temperature deviation judgment threshold of the main heating element is The detected current of the main heating element is The detected temperature of the main heating element is ; The main heating element is considered faulty when both of the following conditions are met: Condition 1: The actual current is within the allowable fluctuation range of the rated current. ; Condition 2: The deviation between the actual temperature and the rated temperature exceeds the judgment threshold. ; Example illustration: If the rated current of a certain heating zone is... For a certain benchmark value, its allowable fluctuation threshold The actual current detected is 5% of this benchmark value (the specific percentage can be adjusted according to the process, and is not limited in this invention). Falling Within the range (i.e., current is normal), but the actual temperature... With rated temperature The absolute value of the difference exceeds (If the temperature deviation exceeds 10℃, the specific threshold can be adjusted according to the material properties), then the main heating tube of the heating zone is determined to be faulty. If a malfunction occurs, within a preset time (e.g.) (The specific time can be adjusted according to the equipment performance) Switch to the backup heating tube and upload the heating zone fault information to the digital twin management module at the same time; Establish a dual-station collaborative mechanism to improve the consistency of heating accuracy between the two stations. Workstation A (any preset workstation in the dual-workstation configuration) acquires real-time temperature deviation information for its own heating zone. The temperature deviation information is transmitted to workstation B (the remaining workstation in the dual-workstation system) in real time. Based on the temperature deviation-power compensation quantization relationship calibrated in advance through experiments ,in, The power that needs to be compensated in advance for workstation B. This is the power compensation coefficient, calibrated experimentally. This coefficient represents the power compensation ratio corresponding to each unit temperature deviation. This represents the absolute value of the real-time temperature deviation information for workstation A. Workstation B performs power compensation adjustment for the corresponding heating zone in advance to avoid the same temperature deviation as workstation A, thus ensuring the consistency of heating accuracy between the two workstations. Based on the difference between the actual heating time and the original planned heating time at the heating station, the timing deviation of the molding station is precisely controlled; If the actual heating time at the heating station is longer than the originally planned heating time, the forming station will use a servo motor to perform a delayed mold closing operation based on the difference between the two times, ensuring that the sheet is fully heated before forming. If the actual heating time at the heating station is less than the originally planned heating time, the forming station will execute the ejection mechanism reset action in advance based on the time difference between the two, thereby shortening the idle waiting time before forming. This enables precise timing matching between the heating and molding processes, promoting synergistic optimization of molding efficiency and quality. This step ensures heating continuity through automatic fault switching, improves heating accuracy consistency through dual-station temperature deviation pre-compensation, and links heating and forming timing for control, achieving continuous and stable production, consistent heating accuracy in both stations, and synergistic optimization of forming efficiency and quality. It also enhances the system's adaptability to flexible production.

[0026] S4: Construct a digital twin management module to proactively predict heating zones through historical heating zone fault records, further improving the heating accuracy consistency of the two workstations. Based on the historical difference records between the actual heating time and the original planned heating time of the heating workstation, a long short-term memory network is used to proactively predict the timing deviation of the molding workstation, thereby improving the energy utilization rate of the molding workstation. A digital twin management module is built to proactively predict heating zones based on historical heating zone fault records, thereby further improving the consistency of heating accuracy between the two workstations. A digital twin management module is constructed based on historical heating zone fault records. The fault records include: heating tube burnout, frequency converter power supply failure, and operating parameters at the time of the fault (heating current fluctuation, abnormal temperature field points, and cumulative working time). Based on historical heating zone fault records, a digital twin management module is built for each heating zone of the dual-station system. By analyzing the dynamic evolution trend of parameters in historical heating zone fault records (e.g., the current of a certain heating tube shows a slow upward trend over a long period of time, and the temperature response speed gradually delays), the risk of heating zone faults can be predicted in advance (e.g., a warning of "potential short circuit caused by aging of the heating tube insulation layer" is issued 2 to 4 hours in advance).

[0027] Before a fault occurs, preventative maintenance (such as replacing sub-optimal heating elements) or dynamic parameter compensation (such as temporarily increasing the power of adjacent zones to compensate for the lack of heat output in the faulty zone) can be triggered to prevent the imbalance of heating accuracy in the dual-station heating system caused by abnormal heating zones, thus ensuring the uniformity of heating in the dual-station system.

[0028] Based on historical records of the difference between the actual heating time and the original planned heating time at the heating station, a long short-term memory network is used to actively predict the timing deviation of the molding station, thereby improving the energy utilization rate of the molding station. Based on the historical records of the difference between the actual heating time and the original planned heating time at the heating station, and the associated production parameters, including sheet material, thickness, and workshop ambient temperature, a time-series dataset is constructed, which records the heating time deviation value, PET crystallinity, and ambient temperature change sequence by production batch. The time series dataset is input into a Long Short-Term Memory (LSTM) network. By leveraging the LSTM network's ability to capture long-term time dependencies, the potential patterns of heating time differences and subsequent timing deviations in the molding process are learned (for example, when the crystallinity of the PET sheet is 3% higher, the heating time exceeds the original plan by an average of 5 seconds, and the molding and mold closing need to be delayed by 4 seconds). Based on the patterns learned by the Long Short-Term Memory Network, the time when the molding station needs to delay mold closing or reset the ejection mechanism in advance can be predicted in advance. This transforms the timing adjustment of the molding station from a passive response to an active look-ahead, reducing the idle waiting time of the molding station equipment and improving the energy utilization and production efficiency of the molding station.

[0029] Example 2

[0030] like Figure 2 As shown, based on Embodiment 1, the present invention provides an energy-saving thermoforming system for a vacuum forming machine based on dual-station timing coordination, comprising: Heating zone dynamic matching module: A temperature sensing system is built by deploying sensors at the entrance of the heating station to identify the heat demand status of each area of ​​the sheet, divide the heating area into multiple heating zones, optimize the overall temperature distribution of the heating area by dynamically matching the heat demand status of the sheet, and build a temperature feedback model by deploying sensors at the exit of the heating station to provide real-time feedback and correction of the dynamic matching results. Energy consumption optimization module: Construct a process parameter knowledge base, match process parameter combinations for different sheet materials, introduce an energy consumption model, and dynamically adjust the heating control strategy of the heating zone based on real-time production data and a genetic algorithm; Dual-station collaborative control module: Introduces a main heating tube fault determination mechanism to determine whether the heating zone is faulty. If a fault occurs, the backup heating tube is activated, establishing a dual-station collaborative mechanism to improve the heating accuracy consistency of the two stations. Based on the difference between the actual heating time of the heating station and the original planned heating time, the timing deviation of the forming station is precisely controlled. Timing Deviation Proactive Prediction Module: Construct a digital twin management module that proactively predicts heating zones based on historical heating zone fault records, further improving the heating accuracy consistency of the two workstations. Based on historical records of the difference between the actual heating time and the original planned heating time of the heating workstation, a long short-term memory network is used to proactively predict the timing deviation of the molding workstation, thereby improving the energy utilization rate of the molding workstation.

[0031] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of the present invention is defined by the appended claims and their equivalents.

Claims

1. An energy-saving method for thermoforming in a vacuum forming machine based on dual-station sequential coordination, characterized in that: include: S1: Deploy sensors at the entrance of the heating station to build a temperature sensing system, identify the heat demand status of each area of ​​the sheet, divide the heating area into multiple heating zones, optimize the overall temperature distribution of the heating area by dynamically matching the heat demand status of the sheet, and deploy sensors at the exit of the heating station to build a temperature feedback model to provide real-time feedback and correction of the dynamic matching results. S2: Construct a process parameter knowledge base, match process parameter combinations for sheets of different materials, introduce an energy consumption model, and dynamically adjust the heating control strategy of the heating zone based on real-time production data and a genetic algorithm. S3: Introducing a main heating tube fault determination mechanism to determine whether the heating zone is faulty. If a fault occurs, the backup heating tube is activated, and a dual-station collaborative mechanism is established to improve the heating accuracy consistency of the two stations. Based on the difference between the actual heating time of the heating station and the original planned heating time, the timing deviation of the forming station is precisely controlled. S4: Construct a digital twin management module to proactively predict heating zones through historical heating zone fault records, further improving the heating accuracy consistency of the two workstations. Based on historical records of the difference between the actual heating time and the original planned heating time of the heating workstation, a long short-term memory network is used to proactively predict the timing deviation of the molding workstation, thereby improving the energy utilization rate of the molding workstation.

2. The energy-saving method for thermoforming of a vacuum forming machine based on dual-station timing coordination according to claim 1, characterized in that: The specific process for identifying the heat demand status of different areas of the sheet is as follows: At the entrance of the heating station, an infrared thermal imager and a fiber optic sensor are used to construct a temperature sensing system to generate a two-dimensional temperature distribution cloud map of the sheet along the X and Y axes. The infrared thermal imager has a temperature measurement accuracy of ±0.5℃, and the fiber optic sensor has a sampling period of ≤0.1 seconds, so as to accurately identify the heating status of each area of ​​the sheet. The specific requirements for heat demand include: hot zone location and the difference between the target temperature and the current temperature.

3. The energy-saving method for thermoforming of a vacuum forming machine based on dual-station timing coordination according to claim 1, characterized in that: The specific process for real-time feedback correction of the dynamic matching results is as follows: The heating area is divided into multiple heating zones according to the X×Y matrix. A micro frequency converter is configured for each heating zone. Based on the two-dimensional temperature distribution cloud map data of the sheet along the XY axis and the required heating status, the output power of the micro frequency converter is adjusted to dynamically match the heating power of each heating zone with the current temperature difference of the corresponding area and the target temperature.

4. Near-infrared spectral sensor and laser thickness gauge are added at the outlet of the heating station to detect the crystallinity, impurity content and local thickness deviation of the sheet in real time; A neural network model was established with crystallinity, impurity content, and local thickness deviation as inputs and target temperature correction as output. The temperature feedback model was obtained after training and validating the neural network model with historical data. Based on the temperature feedback model, the target temperature correction is output, and the output power of the micro frequency converter is adjusted by the PID control algorithm to accurately meet the power requirements of the sheet after it reaches the required temperature.

5. The energy-saving method for thermoforming of a vacuum forming machine based on dual-station timing coordination according to claim 1, characterized in that: The specific process for matching the sheet processing parameters of different materials is as follows: Data on heating power, heating temperature, heating time, and forming qualification rate from historical production data are obtained. Regression analysis algorithms are used to obtain the optimal process parameter mapping relationship for different sheet types, forming a process knowledge base. The mathematical expression for the optimal process parameter mapping relationship for different sheet types is as follows: For the i-th sheet type and the j-th thickness, a temperature field function is constructed. Heating power function Molding quality function ; in, This represents the material property parameters of the i-th type of sheet, where i is the index of the sheet type. Let be the thickness of the j-th type of sheet, where j is the index of the sheet thickness. The temperature field is given by the combination of the i-th sheet material and the j-th thickness. The heating power required for the i-th sheet material and the j-th thickness combination is... The forming quality is determined by the temperature field and heating power of the i-th sheet and j-th thickness combination. By training the model parameters of the temperature field function, heating power function, and molding quality function using historical production data, To meet the molding quality requirements, the final product will be This information is stored in the knowledge base as the optimal parameter for the sheet-thickness combination. When changing production, the optimal combination of process parameters is matched with the corresponding sheet type and thickness.

6. The energy-saving method for thermoforming of a vacuum forming machine based on dual-station timing coordination according to claim 1, characterized in that: The specific process of dynamically adjusting the heating control strategy of the heating zone using a genetic algorithm is as follows: An energy consumption model is introduced, and the energy consumption model is defined as follows: Where E is the energy consumption per unit time, P is the total heating power of the heating area, i.e. the sum of the heating power of each heating zone, t is the heating time, ΔT is the difference between the workshop ambient temperature and the reference temperature; α, β, γ are preset weighting coefficients, reflecting the degree of influence of each factor on energy consumption; A genetic algorithm is used to randomly generate multiple sets of heating zones and heating zone power allocation schemes, as well as α, β, and γ as initial solutions. The fitness function is to select high-quality solutions with higher weights for molding quality pass rate and lower energy consumption. Selection, crossover, and mutation are performed on the high-quality solutions to generate a new generation population. Until the population fitness stabilizes, the optimal power allocation for heating zones and the combination of α, β, and γ are output, and the energy consumption model and heating control strategy are updated in real time. Based on the production plan, real-time production data is collected every x hours, and the genetic algorithm is automatically started to iterate to achieve dynamic optimization of the energy consumption model.

7. The energy-saving method for thermoforming of a vacuum forming machine based on dual-station timing coordination according to claim 1, characterized in that: The specific process for activating the backup heating element is as follows: Assume the rated current of the main heating element is The permissible current fluctuation threshold for the rated current of the main heating element is... ; The rated temperature of the main heating element is The temperature deviation judgment threshold of the main heating element is The detected current of the main heating element is The detected temperature of the main heating element is ; The main heating element is considered faulty when both of the following conditions are met: Condition 1: The actual current is within the allowable fluctuation range of the rated current. ; Condition 2: The deviation between the actual temperature and the rated temperature exceeds the judgment threshold. ; If a malfunction occurs, the system will switch to the backup heating element within a preset time.

8. The energy-saving method for thermoforming of a vacuum forming machine based on dual-station timing coordination according to claim 1, characterized in that: The specific process of establishing a dual-station collaborative mechanism to improve the consistency of heating accuracy between the two stations is as follows: Workstation A obtains real-time temperature deviation information for its own heating zone. The temperature deviation information will be transmitted to workstation B in real time. Based on the temperature deviation-power compensation quantization relationship calibrated in advance through experiments ,in, The power that needs to be compensated in advance for workstation B. This is the power compensation coefficient, calibrated experimentally. This coefficient represents the power compensation ratio corresponding to each unit temperature deviation. This represents the absolute value of the real-time temperature deviation information for workstation A. Workstation B performs power compensation adjustment for the corresponding heating zone in advance to avoid the same temperature deviation as workstation A, thus ensuring the consistency of heating accuracy between the two workstations. Based on the difference between the actual heating time and the original planned heating time at the heating station, the timing deviation of the molding station is precisely controlled; If the actual heating time at the heating station is longer than the originally planned heating time, the molding station will perform a delayed mold closing operation via a servo motor based on the difference in heating time between the two. If the actual heating time at the heating station is less than the originally planned heating time, the forming station will execute the ejection mechanism reset action in advance based on the time difference between the two.

9. The energy-saving method for thermoforming of a vacuum forming machine based on dual-station timing coordination according to claim 1, characterized in that: The specific process for further improving the heating accuracy consistency of the dual-station system is as follows: A digital twin management module is constructed based on historical heating zone fault records. The fault records include: heating tube burnout, frequency converter power supply failure, and operating parameters at the time of the fault. Based on historical heating zone fault records, a digital twin management module is built for each heating zone of the dual-station system. By analyzing the dynamic evolution trend of parameters in historical heating zone fault records, the risk of heating zone faults can be predicted in advance. Before a fault occurs, preventive maintenance or dynamic parameter compensation is triggered to ensure the consistency of heating uniformity in the dual-station system.

10. The energy-saving method for thermoforming of a vacuum forming machine based on dual-station timing coordination according to claim 1, characterized in that: The specific process for improving the energy utilization rate of the lifting and forming station is as follows: Based on the historical records of the difference between the actual heating time and the original planned heating time at the heating station, and the associated production parameters, including sheet material, thickness, and workshop ambient temperature, a time-series dataset is constructed, which records the heating time deviation value, PET crystallinity, and ambient temperature change sequence by production batch. By inputting the time series dataset into the Long Short-Term Memory (LSTM) network, and leveraging the LSTM network's ability to capture long-term temporal dependencies, we can learn the potential patterns of heating duration differences and subsequent temporal deviations in the molding process. Based on the patterns learned from the Long Short-Term Memory network, the time required to delay mold closing or reset the ejection mechanism at the molding station can be predicted in advance.

11. An energy-saving thermoforming system for vacuum forming machines based on dual-station sequential coordination, characterized in that: include: Heating zone dynamic matching module: A temperature sensing system is built by deploying sensors at the entrance of the heating station to identify the heat demand status of each area of ​​the sheet, divide the heating area into multiple heating zones, optimize the overall temperature distribution of the heating area by dynamically matching the heat demand status of the sheet, and build a temperature feedback model by deploying sensors at the exit of the heating station to provide real-time feedback and correction of the dynamic matching results. Energy consumption optimization module: Construct a process parameter knowledge base, match process parameter combinations for different sheet materials, introduce an energy consumption model, and dynamically adjust the heating control strategy of the heating zone based on real-time production data and a genetic algorithm; Dual-station collaborative control module: Introduces a main heating tube fault determination mechanism to determine whether the heating zone is faulty. If a fault occurs, the backup heating tube is activated, establishing a dual-station collaborative mechanism to improve the heating accuracy consistency of the two stations. Based on the difference between the actual heating time of the heating station and the original planned heating time, the timing deviation of the forming station is precisely controlled. Timing Deviation Proactive Prediction Module: Construct a digital twin management module that proactively predicts heating zones based on historical heating zone fault records, further improving the heating accuracy consistency of the two workstations. Based on historical records of the difference between the actual heating time and the original planned heating time of the heating workstation, a long short-term memory network is used to proactively predict the timing deviation of the molding workstation, thereby improving the energy utilization rate of the molding workstation.

Images