Method and system for optimizing mold opening and closing parameters of injection molding machine for energy conservation and efficiency improvement

Abstract

The invention provides an injection molding machine mold opening and closing parameter optimization method and system oriented to energy conservation and efficiency improvement, and relates to the technical field of industrial process intelligent control. The method comprises the steps that mold temperature, hydraulic pressure and vibration signals are collected in real time through a multi-source sensor, and a composite optimization target of a dynamic energy consumption coefficient and a process stability index is constructed; an improved multi-target genetic algorithm is adopted to iteratively generate a candidate parameter set meeting energy consumption and stability constraints, and the algorithm fuses hydraulic system safety boundary dynamic constraints and an adaptive variation strategy; a parameter adjustment effect is rehearsed through a digital twin model, and motion track deviation is calibrated online in combination with a recursive least square method, so that parameter dynamic injection is realized; and triggering abnormal working condition recovery and material self-adaptive optimization based on a closed-loop feedback mechanism. The system comprises a multi-source data acquisition module, a composite optimization calculation module, a dynamic parameter injection module and a closed-loop feedback control module, and the real-time performance and generalization ability are improved through an FPGA hardware acceleration optimization engine and a transfer learning algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent control of industrial processes, and particularly to a method and system for optimizing the opening and closing die parameters of an injection molding machine for energy conservation and efficiency improvement. Background Art

[0002] In the field of control of the opening and closing die process of injection molding machines, the parameter optimization methods in the existing technologies mainly rely on static empirical rules or offline simulation models and cannot adapt to the dynamic change requirements in actual production. Traditional methods usually preset parameters according to fixed material types or ideal environmental conditions, while factors such as fluctuations in the melt viscosity of materials, changes in environmental temperature and humidity, and aging and wear of mechanical components of the equipment will significantly change the system operation state during actual processing. This static setting mode results in the mismatch between key parameters such as holding pressure time and speed switching points and the actual working conditions, leading to problems such as insufficient clamping force and abnormal die vibration, and further causing energy waste or defects in molded products. For example, when processing materials in different batches, if the parameters are not adjusted in real time, the hydraulic system may frequently trigger the protection mechanism due to pressure overshoot or response delay, reducing the production efficiency.

[0003] There are obvious limitations in the multi-objective collaborative optimization of the existing technologies, and it is difficult to achieve the comprehensive balance of energy consumption efficiency, process stability and equipment safety. Conventional optimization algorithms usually take a single index as the guide, such as minimizing the cycle time or maximizing the clamping force, but ignore the coupling effects of multi-dimensional parameters. For example, excessive pursuit of energy consumption reduction may lead to sudden changes in the pressure gradient and increase the risk of hydraulic shock; while only taking stability as the goal may sacrifice production efficiency. In addition, traditional genetic algorithms lack the dynamic adaptation ability to physical boundaries when dealing with non-linear constraints, and may generate parameter combinations that exceed the maximum load of the hydraulic system or the safety temperature threshold, resulting in equipment overload or attenuation of the service life of key components.

[0004] The existing control systems generally lack an efficient real-time feedback mechanism and closed-loop regulation ability, seriously restricting the intelligent level. Most optimization schemes adopt an offline calculation mode, and parameter adjustment depends on historical data or preset rules, and cannot dynamically correct the control strategy according to the mold temperature, vibration signal or hydraulic response delay collected in real time. At the same time, the calculation efficiency of traditional software algorithms is difficult to meet the requirements of millisecond-level response in high-speed injection molding scenarios, and the insufficient application of hardware acceleration technology further exacerbates the control delay. For example, in scenarios of sudden changes in environmental temperature or material switching, the system is difficult to identify the change of working conditions in time and update the parameters, resulting in problems such as clamping force drift or sudden increase in energy consumption during the production process.

[0005] The above technical defects indicate that the existing methods have significant deficiencies in adapting to dynamic working conditions, multi-objective collaborative optimization and real-time closed-loop control, and there is an urgent need for a technical solution that deeply integrates data-driven modeling, intelligent optimization algorithms and hardware acceleration control to achieve efficient energy conservation and stable operation of the opening and closing die process of injection molding machines. Summary of the Invention

[0006] To solve the technical problems in the prior art, such as the inability of static parameter setting to adapt to dynamic working condition changes, the lack of multi-objective collaborative optimization ability leading to the imbalance between energy consumption and stability, and the lack of real-time closed-loop feedback mechanism causing control lag, the present invention provides an injection molding machine mold opening and closing parameter optimization method and system for energy conservation and efficiency improvement.

[0007] The technical solutions provided by the present invention are as follows:

[0008] First aspect:

[0009] An injection molding machine mold opening and closing parameter optimization method for energy conservation and efficiency improvement provided by the present invention includes:

[0010] S1. Real-time obtain dynamic process parameters during the operation of the injection molding machine through a multi-source data acquisition module, including mold temperature, injection pressure, melt viscosity, clamping force, and mold opening and closing cycle time, and synchronously collect ambient temperature and equipment energy consumption data;

[0011] S2. Based on the data collected in step S1, establish a composite optimization objective function including a Dynamic Energy Consumption Coefficient (DECC) and a Process Stability Index (PSI), where DECC is used to characterize the comprehensive energy consumption efficiency per unit output, and PSI is used to quantify the coupling effect of pressure fluctuation and time deviation in the mold opening and closing action;

[0012] S3. Use a multi-objective optimization algorithm to iteratively optimize the holding pressure time, speed switching point, and pressure gradient parameters during the mold opening and closing stage to generate a candidate parameter set that satisfies the dual constraints of DECC and PSI;

[0013] S4. Inject the optimized parameter set into the injection molding machine controller through a dynamic adjustment module, and perform parameter adaptive calibration within 3 consecutive production cycles. During the calibration process, real-time monitor the mold vibration amplitude and the hydraulic system response delay;

[0014] S5. Based on the calibration results, construct an energy consumption - efficiency feedback model. When it is detected that the material batch changes or the ambient temperature fluctuation exceeds the threshold, trigger the parameter re-optimization process to form a closed-loop control mechanism.

[0015] Second aspect:

[0016] An injection molding machine mold opening and closing parameter optimization system for energy conservation and efficiency improvement provided by the present invention includes:

[0017] A multi-source data acquisition module, including an embedded temperature sensor array, a high-frequency pressure transmitter, and a vibration accelerometer;

[0018] The composite optimization calculation module is equipped with an FPGA accelerator to solve the coupling relationship between DECC and PSI in real time;

[0019] Dynamic parameter injection module, bidirectional data exchange with the injection molding machine PLC controller through industrial Ethernet protocol;

[0020] Closed-loop feedback control module, integrating abnormal condition identification unit and parameter version management database.

[0021] The beneficial effects brought about by the technical solution provided by the present invention include at least:

[0022] (1) In the present invention, through the composite optimization mechanism of dynamic energy consumption coefficient and process stability index, the system accurately balances energy consumption and process quality during the mold opening and closing process. The closed-loop feedback model constructed based on multi-source sensor data can perceive material properties, environmental changes and equipment status fluctuations in real time, and dynamically adjust key parameters such as holding time and speed switching point to avoid energy waste and quality fluctuations in the traditional fixed parameter mode. Combined with the improved genetic algorithm and digital twin verification technology, it ensures that the optimized parameter set not only meets the safety constraints of the hydraulic system, but also adapts to changes in complex working conditions, ultimately achieving a dual improvement in energy consumption reduction and production stability;

[0023] (2) In the present invention, the system enables the equipment to quickly adapt to new materials and new environments through the deep integration of the transfer learning algorithm and the historical process knowledge base. When a material batch change or a sudden change in ambient temperature is detected, the intelligent feedback module automatically calls the historical optimal parameters of similar process characteristics, and fine-tunes the control strategy in real time in combination with the online calibration mechanism. The multi-dimensional anomaly detection engine can identify potential risks such as clamping force offset and pressure fluctuation, and quickly restore the stable state through the parameter rollback mechanism, significantly reducing the risk of downtime and the frequency of manual intervention caused by changes in working conditions;

[0024] (3) In the present invention, from high-precision data acquisition, hardware acceleration optimization to closed-loop control instruction issuance, the system forms a complete intelligent decision-making chain. The deep integration of multi-source heterogeneous data and FPGA parallel computing architecture breaks through the real-time bottleneck of traditional software optimization, and makes the parameter optimization response speed reach millisecond level. Through digital twin rehearsal, redundant communication guarantee and encrypted log management, a safe and reliable control ecosystem is built, which provides technical support for the standardization and traceability of the production process, and promotes the upgrading of injection molding manufacturing towards intelligence and greenness. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] To more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the accompanying drawings required for the description of the embodiments. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can also be obtained based on these drawings.

[0026] Figure 1 It is a schematic flowchart of a method for optimizing the mold opening and closing parameters of an injection molding machine for energy conservation and efficiency improvement provided by an embodiment of the present invention;

[0027] Figure 2 It is a schematic flowchart of an improved NSGA-II algorithm for a method for optimizing the mold opening and closing parameters of an injection molding machine for energy conservation and efficiency improvement provided by an embodiment of the present invention;

[0028] Figure 3 It is a schematic flowchart of the S4 process of a method for optimizing the mold opening and closing parameters of an injection molding machine for energy conservation and efficiency improvement provided by an embodiment of the present invention;

[0029] Figure 4 It is a schematic structural diagram of a system for optimizing the mold opening and closing parameters of an injection molding machine for energy conservation and efficiency improvement provided by an embodiment of the present invention. Detailed implementation manners

[0030] The following will describe the technical solutions in the present invention with reference to the accompanying drawings.

[0031] In the embodiments of the present invention, words such as "exemplarily" and "for example" are used to represent examples, illustrations or explanations. Any embodiment or design solution described as "example" in the present invention should not be construed as being more preferred or having more advantages than other embodiments or design solutions. Exactly speaking, the use of the word "example" aims to present concepts in a specific way. In addition, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or either one of the two can be selected.

[0032] In the embodiments of the present invention, "image" and "picture" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meaning they express is the same. "(of)", "corresponding", and "corresponding" can sometimes be used interchangeably. It should be noted that when the difference is not emphasized, the meaning they express is the same.

[0033] In the embodiments of the present invention, sometimes subscripts such as W1 may be miswritten as non-subscript forms such as W1. When the difference is not emphasized, the meaning they express is the same.

[0034] To make the technical problems, technical solutions, and advantages to be solved by the present invention clearer, the following will be described in detail with reference to the accompanying drawings and specific embodiments.

[0035] Refer to the attached drawings of the specification Figure 1 , which shows a schematic flow chart of a method for optimizing the mold opening and closing parameters of an injection molding machine for energy conservation and efficiency improvement provided by an embodiment of the present invention.

[0036] An embodiment of the present invention provides a method for optimizing the mold opening and closing parameters of an injection molding machine for energy conservation and efficiency improvement. This method can be implemented by a device for optimizing the mold opening and closing parameters of an injection molding machine for energy conservation and efficiency improvement. This device for optimizing the mold opening and closing parameters of an injection molding machine for energy conservation and efficiency improvement can be a terminal or a server. The processing flow of a method for optimizing the mold opening and closing parameters of an injection molding machine for energy conservation and efficiency improvement can include the following steps:

[0037] S1. Real-time obtain dynamic process parameters during the operation of the injection molding machine through a multi-source data acquisition module, including mold temperature, injection pressure, melt viscosity, clamping force, and mold opening and closing cycle time, and synchronously collect ambient temperature and equipment energy consumption data;

[0038] S2. Based on the data collected in step S1, establish a composite optimization objective function including a Dynamic Energy Consumption Coefficient (DECC) and a Process Stability Index (PSI). Among them, DECC is used to characterize the comprehensive energy consumption efficiency per unit output, and PSI is used to quantify the coupling effect of pressure fluctuation and time deviation in the mold opening and closing action;

[0039] S3. Use a multi-objective optimization algorithm to iteratively optimize the holding pressure time, speed switching point, and pressure gradient parameters during the mold opening and closing stage, and generate a candidate parameter set that meets the dual constraints of DECC and PSI;

[0040] S4. Inject the optimized parameter set into the injection molding machine controller through a dynamic adjustment module, and perform parameter adaptive calibration within 3 consecutive production cycles. During the calibration process, the vibration amplitude of the mold and the response delay of the hydraulic system are monitored in real time;

[0041] S5. Based on the calibration results, construct an energy consumption - efficiency feedback model. When it is detected that the material batch changes or the ambient temperature fluctuation exceeds the threshold, trigger the parameter re-optimization process to form a closed-loop control mechanism.

[0042] In a possible implementation manner, the calculation formula of the dynamic energy consumption coefficient DECC is:

[0043]

[0044] Where, Ti is the average injection pressure for the i-th time segment, in MPa, T i is the duration of the i-th time segment, in s, η i is the hydraulic system efficiency coefficient corresponding to the i-th time segment, and its value is obtained through calculation. N is the total number of time segments within a complete mold opening and closing cycle, and W is the mass of the molded product per cycle, in kg.

[0045] In a possible implementation, the calculation formula for the process stability index PSI is:

[0046]

[0047] where σ p is the standard deviation of the clamping force, in kN, μ p is the average value of the clamping force, in kN, Δt ma x is the maximum deviation of the mold opening time, in ms, T avg is the average mold opening time, in ms, F var is the variance of the hydraulic system pressure fluctuation, in MPa 2 , F nom is the nominal pressure value, in MPa, and α, β, γ are weighting factors, taking 0.45, 0.35, 0.20 respectively, and satisfying α + β + γ = 1.

[0048] In a possible implementation, as Figure 2 shown, S3 specifically includes:

[0049] The multi-objective optimization algorithm uses an improved NSGA-II algorithm, and its improvements include:

[0050] S301. Introduce the weighted constraint conditions of DECC and PSI in the non-dominated sorting stage, and eliminate the inferior solutions with DECC > 1.2 or PSI < 0.75 when generating the Pareto front;

[0051] S302. Incorporate the empirical parameter range based on the equipment historical data into the crossover operator, and limit the search space within the safe operating range of the hydraulic system;

[0052] S303. Adopt a dynamic mutation probability adjustment strategy. When the optimal solution has not been updated for 5 consecutive generations, increase the mutation probability from 0.1 to 0.3.

[0053] In a possible implementation, as Figure 3 shown, S4 specifically includes:

[0054] S401. Collect the feedback data of the hydraulic cylinder displacement sensor at intervals of 0.5 seconds, and calculate the root mean square error RMSE between the actual mold opening trajectory and the theoretical trajectory;

[0055] S402. When the RMSE exceeds 0.15 mm, update the speed-pressure compensation model using the recursive least squares method with a forgetting factor;

[0056] S403. After calibration is completed, recalculate the matching degree of DECC and PSI. If the decrease in DECC is less than 5% and the increase in PSI is less than 8%, roll back to the previous generation of parameter sets.

[0057] In this embodiment, the specific implementation manner of the present invention relates to the technical implementation process of an injection molding machine mold opening and closing parameter optimization method and system. In the method implementation, first, the mold temperature field distribution data is collected in real time through an 8×8 grid array composed of 64 platinum resistance temperature sensors embedded on the surface of the mold cavity. The sensors use the PT100 model and are configured with a self-compensation circuit to eliminate the influence of wire resistance on the measurement accuracy. The sampling interval is 50 milliseconds, and the data is subjected to 24-bit high-precision analog-to-digital conversion by the AD7793 chip. The pressure monitoring of the main oil circuit of the hydraulic system uses a piezoresistive high-frequency pressure transmitter with a range covering 0 to 250 MPa, and a built-in temperature compensation module is used to eliminate the zero drift caused by environmental temperature drift. The signal output is transmitted through a 4-20 mA current loop and passes through an anti-aliasing filter with a cut-off frequency of 2 kHz to eliminate high-frequency noise. Triaxial vibration accelerometers (model PCB 352C03) installed at the four corners of the moving platen synchronously collect vibration signals with a frequency response range of 5 to 2000 Hz. The signals are digitized by the NI-9234 data acquisition card at a sampling rate of 51.2 kHz, and the energy characteristics of specific frequency bands are extracted through the wavelet packet decomposition algorithm. Environmental temperature and humidity sensors (model SHT35) are deployed on the equipment shell, and the data is uploaded to the industrial control computer through the Modbus protocol. All original data is smoothed using the sliding window method with a window length of 10 sampling points, and each parameter is mapped to the [0,1] interval through min-max normalization to ensure the dimensional consistency of multi-source heterogeneous data.

[0058] It should be noted that for the calculation of the dynamic energy consumption coefficient, a single mold opening and closing cycle is divided into time segments of 100 milliseconds. The average injection pressure value, duration, and hydraulic system efficiency coefficient are extracted within each segment. The hydraulic efficiency coefficient is dynamically calculated through an exponential model established by fitting historical data. The specific expression is the exponential function of the ratio of the pressure in the current segment to the maximum system pressure, which reflects the efficiency decay characteristics of the hydraulic pump in the high-pressure section. The cumulative value of the product of the pressure, time, and efficiency coefficient in each time segment is divided by the product of the total cycle time and the mass of a single product, finally generating a normalized energy consumption evaluation index. The construction of the process stability index integrates three dimensions: the clamping force fluctuation, the deviation of the mold opening time, and the variance of the hydraulic pressure. The standard deviation of the clamping force is calculated based on the data of 10 consecutive cycles. The maximum time deviation is taken from the maximum offset between the actual mold opening time and the theoretical value. The variance of the hydraulic pressure is calculated by extracting the energy characteristics in the frequency band of 0 - 500 Hz through wavelet packet decomposition. The weight coefficients of each dimension are calibrated through multiple regression analysis of 300 groups of historical production data. The weight ratio of the clamping force fluctuation is the highest, followed by the time deviation, and the weight of the pressure variance is the lowest, with the total weight sum being 1.

[0059] It should be noted that for parameter optimization, an improved non-dominated sorting genetic algorithm is adopted. The initial population contains 200 groups of parameter combinations. The holding pressure time is limited within the physically feasible range of 1.5 to 4.0 seconds. The speed switching point is set in the interval of 30% to 70% of the mold stroke. The pressure gradient is limited to 5 to 20 MPa per millisecond to prevent hydraulic shock. During the non-dominated sorting stage of the algorithm, dual constraints of the dynamic energy consumption coefficient and the process stability index are introduced to screen out candidate solutions with an energy consumption coefficient lower than 1.2 and a stability index higher than 0.75, and a Pareto front is constructed. The crossover operator adopts the simulated binary crossover strategy, and the crossover probability is set to 0.8. During the crossover process, the parameter change range is limited to no more than 10% of the historical safe operating range. The mutation operation adopts the Gaussian mutation mode. When the optimal solution of the population has not been updated for 5 consecutive generations, the mutation probability is dynamically increased from 0.1 to 0.3, and the gradient information of the hydraulic system characteristic curve is introduced into the mutation amount to enhance the search directionality.

[0060] It should be noted that the optimized parameter set is sent to the injection molding machine PLC controller through the OPC UA protocol. Before parameter injection, the change trajectory of the clamping force is simulated through a digital twin model (built based on the AMESim platform). If the predicted deviation of the clamping force exceeds 2% of the nominal value, a red warning light and a buzzer will be triggered for warning and parameter injection will be aborted. During the actual operation stage, the data of the hydraulic cylinder displacement sensor is collected at intervals of 0.5 seconds, and the root mean square error between the actual motion trajectory and the theoretical trajectory is calculated. When the error exceeds 0.15 mm, the recursive least squares method with a forgetting factor of 0.95 is used to update the speed-pressure compensation model online. After calibration in 3 consecutive production cycles, if the reduction of the dynamic energy consumption coefficient does not reach 5% or the improvement of the process stability index is less than 8%, the system will automatically roll back to the previous valid parameter version and record the fault code in the log database.

[0061] Refer to the attached instruction manual Figure 4 which shows the structural schematic diagram of an injection molding machine mold opening and closing parameter optimization system provided by an embodiment of the present invention.

[0062] The present invention also provides an injection molding machine mold opening and closing parameter optimization system for energy conservation and efficiency improvement, which is applied to the above-mentioned injection molding machine mold opening and closing parameter optimization method for energy conservation and efficiency improvement, and includes:

[0063] A multi-source data acquisition module, including an embedded temperature sensor array, a high-frequency pressure transmitter, and a vibration accelerometer;

[0064] A composite optimization calculation module, equipped with an FPGA accelerator for real-time solving of the coupling relationship between DECC and PSI;

[0065] A dynamic parameter injection module, which performs two-way data interaction with the injection molding machine PLC controller through the industrial Ethernet protocol;

[0066] A closed-loop feedback control module, integrating an abnormal condition identification unit and a parameter version management database.

[0067] In a possible implementation manner, the multi-source data acquisition module includes:

[0068] The temperature sensor array adopts an 8×8 matrix layout, covering the surface of the mold cavity and the key nodes of the hot runner; the sampling frequency of the high-frequency pressure transmitter is not less than 2 kHz, and the measurement range covers 0-250 MPa; the number of vibration accelerometers is not less than 4, which are respectively installed at the four corners of the moving template, and the frequency response range is 5-2000 Hz.

[0069] In a possible implementation manner, the composite optimization calculation module includes:

[0070] A process feature extraction unit based on time series analysis, which is used to generate a first derivative map of the pressure-time waveform; an energy consumption efficiency prediction unit, which uses an LSTM neural network to establish a non-linear mapping relationship between DECC and injection speed; a stability evaluation unit, which uses a wavelet packet decomposition algorithm to extract the pressure fluctuation characteristics required for PSI calculation.

[0071] In a possible implementation manner, the dynamic parameter injection module includes:

[0072] During the parameter switching process, maintain the pressure fluctuation of the hydraulic system not exceeding ±1.5 MPa; through the digital twin model, preview the equipment behavior after parameter adjustment. If the predicted clamping force deviation exceeds 2%, suspend the injection and issue an alarm; record the timestamp, operator ID, and equipment status snapshot of each parameter adjustment.

[0073] In a possible implementation manner, the closed-loop feedback control module includes:

[0074] An abnormal condition identification unit, which uses an isolation forest algorithm to detect the abnormal deviation combination mode of DECC and PSI; a parameter version management database, which stores at least 100 sets of historical optimization parameter sets and their corresponding material grades and environmental temperature and humidity combinations; a self-learning unit, when a new material grade is detected, initialize the optimization parameter set based on the transfer learning algorithm.

[0075] In this embodiment, the system hardware architecture is composed of a multi-source data acquisition module, a composite optimization calculation module, a dynamic parameter injection module, and a closed-loop feedback control module. In the data acquisition module, the temperature sensor array transmits data through a high-speed SPI bus. The signal of the pressure transmitter is connected to the industrial computer after the common-mode interference is eliminated by an isolation amplifier. The vibration signal realizes microsecond-level synchronization through the EtherCAT bus. The optimization calculation module is equipped with an Xilinx Kintex-7 XC7K325T type FPGA chip, and uses a parallel pipeline architecture to realize the real-time calculation of the dynamic energy consumption coefficient. Each clock cycle can simultaneously process the pressure-efficiency product operation of 8 time segments, and the calculation delay is less than 2 milliseconds. The long short-term memory neural network model is deployed in the hard-core processor of the FPGA. The input layer receives the injection speed sequence of 50 time steps. The hidden layer contains 64 neurons, and the weight matrix obtained through pre-training is used to predict the energy consumption change trend, and the inference error is controlled within 3%.

[0076] It should be noted that the dynamic parameter injection module adopts a primary and standby redundant design. The primary channel realizes millisecond-level instruction transmission based on the Profinet protocol, and the standby channel ensures communication reliability under extreme working conditions through the CANopen bus. During the parameter switching process, the pressure fluctuation of the hydraulic system is limited within ±1.5 MPa, and the digital twin model updates the equipment status prediction data every 100 milliseconds. Each parameter adjustment generates a complete log containing the timestamp, operator ID, and snapshots of 50 key status variables of the equipment, which is stored in the SQLite database and encrypted and backed up to the cloud. The closed-loop feedback control module integrates the Isolation Forest anomaly detection algorithm, constructs a two-dimensional feature space of the dynamic energy consumption coefficient and the process stability index, calculates the deviation degree of the sample points from the mainstream distribution, and automatically isolates the current parameter set and starts the emergency optimization process when the anomaly score exceeds 0.65. For the new material processing scenario, the system calls a transfer learning model based on the ResNet-18 architecture, maps the process characteristics of historical material grades to the new material parameter space, generates an initial optimization parameter set, and extracts the correlation characteristics between the melt index and the pressure curve of the material through the convolutional layer, shortening the optimization iteration cycle by more than 40%.

[0077] It should be noted that during the operation of the system, multi-source data is preprocessed and then input into the optimization engine. The FPGA accelerator calculates the objective function value in parallel, and the optimization algorithm outputs a generation of Pareto optimal solution sets every 2 seconds. The control instructions are injected into the equipment controller through the security verification mechanism. The feedback module continuously monitors the production status. When the environmental temperature fluctuation exceeds ±3°C or the hydraulic response delay is greater than 50 milliseconds, the parameter re-optimization process is automatically triggered. This solution realizes the refined energy consumption management and stability improvement of the injection molding machine's mold opening and closing process through the deep integration of a high-precision sensing network, hardware acceleration optimization, and intelligent closed-loop control, forming an intelligent manufacturing solution that can adapt to multiple materials and working conditions.

[0078] The injection molding machine mold opening and closing parameter optimization system for energy conservation and efficiency improvement provided by the present invention can execute the injection molding machine mold opening and closing parameter optimization method for energy conservation and efficiency improvement described above and achieve the same or similar technical effects. To avoid repetition, the present invention will not be elaborated herein.

[0079] The beneficial effects brought by the technical solution provided by the embodiments of the present invention at least include:

[0080] (1) In the present invention, through the composite optimization mechanism of dynamic energy consumption coefficient and process stability index, the system accurately balances energy consumption and process quality during the mold opening and closing process. The closed-loop feedback model constructed based on multi-source sensor data can perceive material properties, environmental changes and equipment status fluctuations in real time, and dynamically adjust key parameters such as holding time and speed switching point to avoid energy waste and quality fluctuations in the traditional fixed parameter mode. Combined with the improved genetic algorithm and digital twin verification technology, it ensures that the optimized parameter set not only meets the safety constraints of the hydraulic system, but also adapts to changes in complex working conditions, ultimately achieving a dual improvement in energy consumption reduction and production stability;

[0081] (2) In the present invention, the system enables the equipment to quickly adapt to new materials and new environments through the deep integration of the transfer learning algorithm and the historical process knowledge base. When a material batch change or a sudden change in ambient temperature is detected, the intelligent feedback module automatically calls the historical optimal parameters of similar process characteristics, and fine-tunes the control strategy in real time in combination with the online calibration mechanism. The multi-dimensional anomaly detection engine can identify potential risks such as clamping force offset and pressure fluctuation, and quickly restore the stable state through the parameter rollback mechanism, significantly reducing the risk of downtime and the frequency of manual intervention caused by changes in working conditions;

[0082] (3) In the present invention, from high-precision data acquisition, hardware acceleration optimization to closed-loop control instruction issuance, the system forms a complete intelligent decision-making chain. The deep integration of multi-source heterogeneous data and FPGA parallel computing architecture breaks through the real-time bottleneck of traditional software optimization, and makes the parameter optimization response speed reach millisecond level. Through digital twin rehearsal, redundant communication guarantee and encrypted log management, a safe and reliable control ecosystem is built, which provides technical support for the standardization and traceability of the production process, and promotes the upgrading of injection molding manufacturing towards intelligence and greenness.

[0083] The above contents are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

[0084] There are a few points to note:

[0085] (1) The drawings of the embodiments of the present invention only relate to the structures related to the embodiments of the present invention, and other structures may refer to the general design.

[0086] (2) For clarity, in the drawings used to describe the embodiments of the present invention, the thickness of layers or regions is enlarged or reduced, that is, these drawings are not drawn to actual scale. It can be understood that when an element such as a layer, film, region, or substrate is referred to as being "on" or "under" another element, the element can be "directly" on or under the other element or there can be intervening elements.

[0087] (3) Without conflict, the embodiments of the present invention and the features in the embodiments can be combined with each other to obtain new embodiments.

[0088] The above is only the specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. The protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. An optimization method for the mold opening and closing parameters of an injection molding machine for energy conservation and efficiency improvement, characterized in that, Including: S1. Real-time obtain the dynamic process parameters during the operation of the injection molding machine through the multi-source data acquisition module, including mold temperature, injection pressure, melt viscosity, clamping force, and mold opening and closing cycle time, and synchronously collect the ambient temperature and equipment energy consumption data; S2. Based on the data collected in step S1, establish a composite optimization objective function including the Dynamic Energy Consumption Coefficient (DECC) and the Process Stability Index (PSI), where DECC is used to characterize the comprehensive energy consumption efficiency per unit output, and PSI is used to quantify the coupling effect of pressure fluctuation and time deviation in the mold opening and closing actions; S3. Use a multi-objective optimization algorithm to iteratively optimize the holding pressure time, speed switching point, and pressure gradient parameters during the mold opening and closing stage, and generate a candidate parameter set that satisfies the dual constraints of DECC and PSI; S4. Inject the optimized parameter set into the injection molding machine controller through the dynamic adjustment module, and perform parameter adaptive calibration within 3 consecutive production cycles. During the calibration process, real-time monitor the mold vibration amplitude and the response delay of the hydraulic system; S5. Based on the calibration results, construct an energy consumption-efficiency feedback model. When it is detected that the material batch changes or the ambient temperature fluctuation exceeds the threshold, trigger the parameter re-optimization process to form a closed-loop control mechanism.

2. The optimization method for the mold opening and closing parameters of an injection molding machine for energy conservation and efficiency improvement according to claim 1, characterized in that Including: The calculation formula of the dynamic energy consumption coefficient DECC is: Among them, T i is the average injection pressure of the i-th time segment, with the unit of MPa, T i is the duration of the i-th time segment, with the unit of s, η i is the hydraulic system efficiency coefficient corresponding to the i-th time segment, and its value is obtained through calculation. N is the total number of time segments within a complete mold opening and closing cycle, and W is the mass of the molded product per cycle, with the unit of kg.

3. The optimization method for the mold opening and closing parameters of an injection molding machine for energy conservation and efficiency improvement according to claim 1, wherein, Including: The calculation formula of the process stability index PSI is: Among them, σ p is the standard deviation of the clamping force, with the unit of kN, μ p is the average value of the clamping force, with the unit of kN, Δt max is the maximum deviation of the mold opening time, with the unit of ms, T avg is the average mold opening time, with the unit of ms, F var is the variance of the pressure fluctuation of the hydraulic system, with the unit of MPa 2 , F nom is the nominal pressure value, with the unit of MPa, and α, β, γ are weighting factors, taking 0.45, 0.35, 0.20 respectively, and satisfying α + β + γ = 1.

4. A method for optimizing the opening and closing die parameters of an injection molding machine for energy conservation and efficiency improvement, characterized in that, The specific content of S3 includes: The multi-objective optimization algorithm uses an improved NSGA-II algorithm, and its improvements include: S301. Introduce the weighted constraint conditions of DECC and PSI in the non-dominated sorting stage, and eliminate the inferior solutions with DECC > 1.2 or PSI < 0.75 when generating the Pareto front; S302. Incorporate the empirical parameter range based on the equipment historical data into the crossover operator, and limit the search space within the safe operating range of the hydraulic system; S303. Adopt a dynamic mutation probability adjustment strategy. When the optimal solution has not been updated for 5 consecutive generations, increase the mutation probability from 0.1 to 0.

3.

5. A method for optimizing the mold opening and closing parameters of an injection molding machine for energy conservation and efficiency improvement, characterized in that, The specific content of S4 includes: S401. Collect the feedback data of the hydraulic cylinder displacement sensor at intervals of 0.5 seconds, and calculate the root mean square error RMSE between the actual mold opening trajectory and the theoretical trajectory; S402. When RMSE exceeds 0.15 mm, use the recursive least squares method with a forgetting factor to update the speed-pressure compensation model; S403. After the calibration is completed, recalculate the matching degree of DECC and PSI. If the decrease in DECC is less than 5% and the increase in PSI is less than 8%, roll back to the previous generation of parameter sets.

6. An injection molding machine mold opening and closing parameter optimization system for energy conservation and efficiency improvement, characterized in that, Including: Multi-source data acquisition module, including an embedded temperature sensor array, a high-frequency pressure transmitter, and a vibration accelerometer; Composite optimization calculation module, equipped with an FPGA accelerator for real-time solving the coupling relationship between DECC and PSI; Dynamic parameter injection module, performing two-way data interaction with the injection molding machine PLC controller through the industrial Ethernet protocol; Closed-loop feedback control module, integrating an abnormal condition identification unit and a parameter version management database.

7. An optimization system for the mold opening and closing parameters of an injection molding machine for energy conservation and efficiency improvement according to claim 6, characterized in that, The multi-source data acquisition module includes: The temperature sensor array adopts an 8×8 matrix layout, covering the surface of the mold cavity and key nodes of the hot runner; the sampling frequency of the high-frequency pressure transmitter is not less than 2 kHz, and the measurement range covers 0 - 250 MPa; the number of vibration accelerometers is not less than 4, which are respectively installed at the four corners of the moving template, and the frequency response range is 5 - 2000 Hz.

8. The injection molding machine mold opening and closing parameter optimization system for energy conservation and efficiency improvement according to claim 6, wherein, The composite optimization calculation module includes: A process feature extraction unit based on time series analysis, used to generate the first derivative spectrum of the pressure-time waveform; an energy consumption efficiency prediction unit, which uses an LSTM neural network to establish a non-linear mapping relationship between DECC and injection speed; a stability evaluation unit, which uses the wavelet packet decomposition algorithm to extract the pressure fluctuation characteristics required for PSI calculation.

9. The injection molding machine mold opening and closing parameter optimization system for energy conservation and efficiency improvement according to claim 6, characterized in that, The dynamic parameter injection module includes: During the parameter switching process, maintain the pressure fluctuation of the hydraulic system not exceeding ±1.5 MPa; preview the equipment behavior after parameter adjustment through the digital twin model. If the predicted clamping force deviation exceeds 2%, suspend the injection and issue an alarm; record the timestamp, operator ID, and equipment status snapshot of each parameter adjustment.

10. The injection molding machine mold opening and closing parameter optimization system for energy conservation and efficiency improvement according to claim 6, characterized in that, The closed-loop feedback control module includes: An abnormal condition identification unit, which uses the isolation forest algorithm to detect the abnormal deviation combination mode of DECC and PSI; a parameter version management database, which stores at least 100 sets of historical optimization parameter sets and their corresponding material grades and environmental temperature and humidity combinations; a self-learning unit, when a new material grade is detected, initialize the optimization parameter set based on the transfer learning algorithm.

Images