Intelligent temperature control system of aluminum alloy plate punch forming die

Abstract

The invention discloses an intelligent temperature control system of an aluminum alloy plate punch forming die, which relates to the field of aluminum alloy plate processing and comprises a temperature acquisition module, a data transmission module, an analysis processing module, a control decision module and a heating and cooling execution module. Various sensors and self-adaptive layout are used for temperature acquisition, so that data accuracy is guaranteed; data transmission is combined with multiple technologies and block chain authentication to ensure stability; analyzing and processing introduced quantum neural network and causal analysis mining features; the control decision is combined with multiple algorithms and multiple parameters are considered, so that intelligent decision making is realized; a novel device and a phase-change material are adopted for heating and cooling, and the temperature is accurately controlled by combining an advanced control strategy. According to the invention, accurate temperature acquisition, multi-technology guarantee data transmission and quantum calculation are realized to improve the analysis decision ability, and accurate temperature control is realized by the novel device and the control strategy; the die state can be monitored, faults can be diagnosed, stamping quality and efficiency are improved, the service life of the die is prolonged, and cost is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of aluminum alloy plate processing, and in particular to an intelligent temperature control system for an aluminum alloy plate stamping forming die. Background Art

[0002] Aluminum alloy sheets have been widely used in aerospace, automobile manufacturing, electronic equipment and many other fields due to their excellent properties such as low density, high strength and corrosion resistance. Stamping is an important process for processing aluminum alloy sheets, which can efficiently process aluminum alloy sheets into various complex shapes of parts. However, the mold temperature control in the process of aluminum alloy sheet stamping has always been a key factor restricting stamping quality and production efficiency.

[0003] In the traditional stamping process of aluminum alloy sheets, the mold temperature is mainly controlled by the operator's experience and a simple temperature control device. This method has many disadvantages. First, the operator's experience is limited, and it is difficult to accurately grasp the optimal temperature of the mold in different stamping stages and under different working conditions. Moreover, manual adjustment has a slow response speed and cannot respond to the rapid changes in mold temperature in time, which easily leads to large fluctuations in mold temperature. When the mold temperature is too high, the aluminum alloy sheet may be over-softened, resulting in decreased dimensional accuracy of the molded part, poor surface quality, and even defects such as cracks; when the mold temperature is too low, the plasticity of the aluminum alloy sheet is reduced, the stamping difficulty increases, and it is easy to cause increased mold wear and reduce the service life of the mold.

[0004] Secondly, traditional temperature control devices have a single function and limited adjustment accuracy. For example, some heating devices can only provide fixed heating power and cannot be dynamically adjusted according to the actual temperature requirements of the mold; the coolant flow and temperature of the cooling device are also difficult to accurately control, and cannot achieve accurate adjustment of the mold temperature. In addition, the traditional temperature acquisition method mainly uses a few thermocouple sensors, which can only obtain local temperature information of the mold and cannot fully and accurately reflect the overall temperature distribution of the mold, resulting in a lack of sufficient basis for temperature control decisions.

[0005] With the development of industrial automation and intelligence, although some advanced temperature control technologies have been gradually applied to aluminum alloy sheet stamping dies, there are still some problems. The existing intelligent temperature control system needs to be improved in data processing and analysis capabilities, and cannot fully explore the potential information behind the temperature data, making it difficult to accurately predict and intelligently control the mold temperature. At the same time, these systems lack sufficient adaptability and flexibility when dealing with complex and changeable stamping conditions and mold states, and cannot adjust the control strategy in time to meet production needs.

[0006] In addition, the mold will be worn, cracked and other faults during long-term use, which will not only affect the temperature distribution of the mold, but also reduce the quality and efficiency of stamping. However, the existing temperature control system often lacks the real-time monitoring and fault diagnosis functions of the mold status, and cannot detect potential problems of the mold in time and provide early warning and repair, which increases the uncertainty and cost of the production process.

[0007] Therefore, it is of great practical significance to develop an intelligent temperature control system for aluminum alloy sheet stamping dies. The system needs to be able to collect die temperature information in real time and accurately, efficiently process and analyze data, achieve precise control of die temperature, and have die status monitoring and fault diagnosis and early warning functions to improve the quality and production efficiency of aluminum alloy sheet stamping and reduce production costs. Summary of the invention

[0008] The intelligent temperature control system of the aluminum alloy sheet stamping die proposed in the present invention solves the problems mentioned in the above-mentioned prior art.

[0009] In order to achieve the above object, the present invention adopts the following technical scheme: an intelligent temperature control system for an aluminum alloy sheet stamping die, comprising: Temperature acquisition module: Thermocouple sensors and fiber Bragg grating sensors are evenly distributed in key parts of the mold, and the distribution position of the sensors is dynamically adjusted using an adaptive layout algorithm; the temperature uniformity evaluation formula is used Evaluate the uniformity of mold temperature distribution, It is The temperature collected by the sensor, is the average temperature, n is the number of sensors, is the weight determined according to the location and importance of the sensor; Data transmission module: Using 5G communication technology and industrial Ethernet, adopting a blockchain-based data transmission authentication mechanism, and using the data transmission stability evaluation formula Evaluate data transmission stability, is the amount of data transmitted correctly, is the total amount of data transferred, is the time of the jth transmission interruption, T is the total transmission time; Data analysis and processing module: Use the noise reduction algorithm to denoise the collected data, introduce quantum neural network for feature extraction; use the data feature validity evaluation formula Evaluate the effectiveness of features, is the weight of the jth feature, is the contribution rate of the jth feature, is the causal association strength between the jth feature and the mold temperature control target, and m is the number of features; Control decision module: Adopt intelligent decision model based on fuzzy logic control and particle swarm optimization algorithm to adjust the working parameters of heating and cooling execution modules according to the real-time status of the mold and the dynamic changes of the stamping process; establish a multi-parameter coupling control decision model and adopt decision accuracy evaluation formula Evaluate the accuracy of decisions, is the number of correct decisions, is the total number of decisions, is the deviation between the mold temperature and the target temperature after the kth decision, and L is the total number of decisions; Heating and cooling execution module: equipped with electromagnetic induction heating device and microchannel liquid cooling device, introducing intelligent phase change material. When the mold temperature is too high, the phase change material absorbs heat and undergoes phase change. When the temperature drops, the phase change material releases heat to maintain the stability of the mold temperature.

[0010] Furthermore, it also includes: Mold status detection module: monitor the pressure changes during the stamping process through pressure sensors, monitor the vibration of the mold using vibration sensors, adopt anomaly detection algorithm based on wavelet transform, and introduce quantum entanglement state anomaly perception technology; use multi-sensor data fusion algorithm to fuse the pressure, vibration and quantum entanglement state perception data; use anomaly detection accuracy evaluation formula Evaluate the anomaly detection performance, is the number of correctly detected anomalies, is the actual number of anomalies, It is The delay time of anomaly detection, is the total monitoring time.

[0011] Furthermore, it also includes: Fault diagnosis and early warning module: Use fault tree analysis and Bayesian network to analyze the operating data of each module, introduce deep learning autoencoder to extract fault features; adopt fault reasoning mechanism based on knowledge graph to structure and associate fault knowledge to achieve fault diagnosis and reasoning; when potential fault is detected, use virtual reality and augmented reality technology to show the fault location and maintenance instructions to the operator; use fault prediction accuracy evaluation formula Evaluate the effectiveness of fault prediction, is the number of correctly predicted failures, is the actual number of failures that occurred, is the deviation between the predicted time of the jth fault and the actual time of the fault occurrence, is the total fault monitoring time.

[0012] Furthermore, the temperature acquisition module uses self-calibration technology to calibrate the sensor regularly, uses a calibration algorithm based on Kalman filtering, and introduces quantum calibration technology; uses a calibration method based on quantum bit error correction code to correct quantum noise and errors in the sensor measurement process; uses an adaptive calibration strategy to dynamically adjust the calibration cycle and calibration parameters according to the sensor's usage time and working environment factors; and uses the calibration error evaluation formula Evaluate the calibration effect, is the true temperature value, is the temperature value measured by the sensor, is the number of calibrations, It is a weight determined according to the calibration time and environmental conditions.

[0013] Furthermore, the data transmission module introduces data encryption technology to encrypt the transmitted data, using a quantum encryption algorithm combined with homomorphic encryption technology; a hybrid encryption mechanism based on blockchain and quantum key distribution is adopted, combining the distributed ledger of blockchain with the unbreakable nature of quantum keys, and using the data encryption security evaluation formula Evaluate the security of data encryption, is the amount of data safely transmitted, is the total amount of data, It is The probability of encrypted data being cracked. is the total number of encrypted data transmissions.

[0014] Furthermore, the data analysis and processing module introduces transfer learning technology, and uses the temperature data and processing experience of the mold to introduce cross-domain transfer learning; the temperature control data and processing methods in the aerospace and automobile manufacturing fields are transferred to the temperature control system of the aluminum alloy sheet stamping mold to broaden the data source and processing ideas; the meta-learning-based transfer learning method is used to learn the characteristics and processing modes of data in different fields; the transfer learning effect evaluation formula is used Evaluate the effectiveness of transfer learning. After transfer learning The improvement value of data analysis indicators, It is the first The value of the data analysis indicator, n is the number of data analysis indicators, It is the weight determined according to the importance of the indicator.

[0015] Furthermore, the control decision module adopts a multi-objective optimization algorithm to ensure the stability of the mold temperature and take into account the quality and production efficiency of stamping; uses a non-dominated sorting genetic algorithm for optimization and introduces a quantum multi-objective optimization algorithm; considers the service life and energy consumption of the mold, establishes a multi-objective collaborative optimization model, and uses a multi-objective optimization effect evaluation formula Evaluate the performance of multi-objective optimization. is the weight of the jth target, is the optimization effect index of the jth objective, is the synergistic correlation strength between the jth target and other targets, and m is the number of targets.

[0016] Furthermore, the heating and cooling execution module adopts intelligent flow control valve and variable frequency heating power supply to realize the control of coolant flow and heating power; adopts the traditional PID control algorithm, introduces the model predictive control algorithm, and combines the adaptive control strategy to automatically adjust the parameters of the control algorithm according to the real-time status of the mold and environmental changes; through the control accuracy evaluation formula Evaluate the accuracy of control, is the set control parameter value, is the actual control parameter value, is the control frequency, It is a weight determined based on control time and importance.

[0017] Furthermore, the mold status detection module uses machine learning algorithms to classify and predict pressure and vibration data, and uses a combination of support vector machines and neural networks to introduce deep learning convolutional neural networks and recurrent neural networks; it uses an ensemble learning-based method to fuse the results of multiple machine learning algorithms and evaluate the classification accuracy through the formula Evaluate the accuracy of classification, TP is the number of true positive examples, TN is the number of true negative examples, FP is the number of false positive examples, and FN is the number of false negative examples. It is The confidence deviation of the sub-classification, is the total number of classifications.

[0018] Furthermore, the fault diagnosis and early warning module uses a combination of expert system and machine learning to perform fault diagnosis. The expert system performs preliminary diagnosis based on pre-set rules and experience, and the machine learning algorithm learns and analyzes fault data. The knowledge graph deep learning fault diagnosis model is introduced, and a case-based reasoning fault diagnosis method is adopted. Historical fault cases are used for analogical reasoning to locate and solve new faults. The fault diagnosis accuracy evaluation formula is used. Evaluate the effectiveness of fault diagnosis, is the number of faults correctly diagnosed, is the total number of diagnoses, is the deviation between the jth fault diagnosis time and the actual fault occurrence time, is the total fault diagnosis time.

[0019] Compared with the prior art, the present invention has the following beneficial effects: In terms of temperature acquisition, the system uses a variety of advanced sensors, including quantum dot temperature sensors, which can capture mold temperature changes in an all-round and high-precision manner. The adaptive layout algorithm can dynamically adjust the sensor position according to the mold characteristics. The improved evaluation formula can more accurately evaluate temperature uniformity and provide an accurate data basis for subsequent temperature control.

[0020] In terms of data transmission, 5G, industrial Ethernet and terahertz communication technologies are combined to ensure fast and stable data transmission, and the blockchain authentication mechanism ensures data integrity and traceability. The optimized evaluation formula comprehensively considers transmission interruptions to make data transmission more reliable.

[0021] The data analysis and processing module introduces quantum neural networks and causal analysis methods, which can mine deep features and find key causal relationships. Cross-domain transfer learning and meta-learning methods broaden the data processing ideas, and the improved evaluation formula scientifically evaluates the transfer learning effect, improving the efficiency and accuracy of data analysis.

[0022] The control decision module combines fuzzy logic, particle swarm optimization and reinforcement learning algorithms, takes into account multi-parameter coupling, and can quickly adjust control parameters according to the real-time status of the mold and process changes. The quantum multi-objective optimization algorithm can quickly find the global optimal solution, taking into account multiple objectives, and the improved evaluation formula comprehensively evaluates the optimization effect, achieving accurate temperature control decisions.

[0023] The heating and cooling execution module adopts new heating and cooling devices, such as bionic microchannel liquid cooling devices and intelligent phase change materials, which can efficiently adjust the mold temperature. The model predictive control algorithm and adaptive control strategy improve the control accuracy and response speed, and the improved evaluation formula reasonably evaluates the control effect.

[0024] In addition, the mold status monitoring module introduces quantum entanglement state perception technology and multi-sensor data fusion algorithm, which can detect minor damage to the mold in advance. The improved evaluation formula comprehensively considers the detection delay and improves the accuracy of abnormal detection. The fault diagnosis and early warning module combines deep learning and knowledge graphs, provides maintenance guidance through VR and AR technology, and the improved evaluation formula accurately evaluates the fault prediction effect, which can detect and solve potential faults in time.

[0025] In general, this system improves the quality and production efficiency of aluminum alloy sheet stamping, prolongs the service life of the mold, reduces the production cost, and has good application prospects and economic value. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 A schematic block diagram of an intelligent temperature control system for an aluminum alloy sheet stamping die proposed by the present invention; DETAILED DESCRIPTION

[0027] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0028] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0029] In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined. In addition, the terms "installed", "connected" and "connected" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, and it can be the internal connection of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. The present invention will be further described in detail below in conjunction with the accompanying drawings.

[0030] Reference Figure 1 : An intelligent temperature control system for an aluminum alloy sheet stamping die, comprising: Temperature acquisition module: The temperature acquisition module plays a key role in the temperature monitoring and control of the mold. In addition to the uniformly distributed high-precision thermocouple sensors and fiber Bragg grating sensors in the key parts of the mold, quantum dot temperature sensors are also innovatively introduced. Thermocouple sensors are based on the Seebeck effect. When the two ends of two conductors of different materials are connected into a loop and there is a temperature difference between the two ends, a thermoelectric potential will be generated in the loop. The temperature can be obtained by measuring the electromotive force. The fiber Bragg grating sensor uses the reflection characteristics of the grating in the optical fiber to light of a specific wavelength. When the temperature changes, the period and effective refractive index of the grating change, resulting in the central wavelength drift of the reflected light. The temperature can be determined by detecting the wavelength drift. The working principle of the quantum dot temperature sensor is based on the fluorescence characteristics of quantum dots. Quantum dots are a nano-scale semiconductor material that emits fluorescence when excited by light, and its fluorescence emission wavelength and intensity change with temperature. By accurately measuring this fluorescence characteristic, ultra-high precision perception of temperature can be achieved. Its unique advantage is that it can capture temperature changes in tiny areas of the mold, which is difficult for traditional sensors to achieve. Moreover, its response speed is several times faster than that of traditional sensors, which means that temperature information can be obtained in a more timely manner. In terms of sensor layout, an adaptive layout algorithm is adopted. The algorithm will first accurately model the shape and size of the mold, and use computer-aided design (CAD) and computer-aided engineering (CAE) technology to simulate the temperature field distribution in the mold under different stamping processes. Then, based on the simulation results and combined with the stamping process requirements, such as stamping speed, pressure, material properties and other factors, the distribution position of the sensor is dynamically adjusted. For example, in stress concentration areas of the mold or areas where the temperature changes drastically, the number of sensors will be appropriately increased to ensure that the temperature data can be accurately collected to achieve the best temperature collection effect. In order to more accurately evaluate the uniformity of the mold temperature distribution, an improved temperature uniformity evaluation formula is adopted. (in It is The temperature collected by the sensor, is the average temperature, n is the number of sensors, is a weight determined by the sensor location and importance) to more accurately evaluate the uniformity of mold temperature distribution.

[0031] Data transmission module: The data transmission module is an important part to ensure accurate and stable transmission of key data such as mold temperature. Based on the use of 5G communication technology and industrial Ethernet, terahertz communication technology is introduced as a backup communication link. Based on technologies such as millimeter wave frequency bands and massive MIMO (multiple input multiple output), 5G communication technology can provide peak data rates of up to tens of Gbps, ultra-low latency in milliseconds, and millions of connections per square kilometer. Industrial Ethernet adopts the IEEE802.3 standard, which has the characteristics of openness, low cost, and high reliability. It is widely used in industrial environments to achieve high-speed data transmission between devices. Terahertz communication technology operates in the frequency band of 0.1-10THz and has the characteristics of extremely high transmission rate and strong anti-interference ability. Its extremely high bandwidth enables it to transmit a large amount of data in a short time, such as when the mold temperature data suddenly increases. In addition, terahertz waves are highly directional and are not easily interfered by signals in other frequency bands. When 5G and industrial Ethernet fail, such as electromagnetic interference, network congestion or physical damage, the terahertz communication system can switch quickly. It monitors the status of the main communication link in real time through the intelligent monitoring module. Once an abnormality is detected, the terahertz communication link will be started in a very short time (nanosecond level) to ensure uninterrupted data transmission. In order to ensure the integrity and source traceability of the data, a data transmission authentication mechanism based on blockchain is adopted. Blockchain is a decentralized distributed ledger technology that divides data into multiple data blocks, each of which contains all data transaction records within a certain period of time. During the data transmission process, a unique digital signature is added to each data transmission package. This digital signature is generated by an asymmetric encryption algorithm. The sender uses its own private key to sign the data, and the receiver uses the sender's public key for verification. At the same time, each block in the blockchain contains the hash value of the previous block to form a chain structure. Once the data is tampered with during the transmission process, the receiver can detect the abnormality by verifying the digital signature and hash value, thereby ensuring the integrity of the data. In addition, through the distributed ledger of the blockchain, the source and transmission path of the data can be traced to ensure the source traceability of the data. In terms of evaluating the stability of data transmission, an optimized data transmission stability evaluation formula is used (in is the amount of data transmitted correctly, is the total amount of data transferred, is the time of the jth transmission interruption, T is the total transmission time), and the transmission interruption situation is comprehensively considered to evaluate the data transmission stability more comprehensively.

[0032] Data analysis and processing module: The data analysis and processing module undertakes the key data processing and feature extraction tasks in the entire mold temperature management system. First, the collected data is denoised using a deep learning-based denoising algorithm. Deep learning algorithms rely on multi-layer neural network structures, such as common convolutional neural networks (CNNs) or recurrent neural networks (RNNs) and their variants (such as LSTM, GRU, etc.). When processing temperature data, for CNN, the temperature data can be structured in the time and space dimensions to make it similar to image data. The local and global features in the data are automatically extracted through components such as convolution layers and pooling layers. The convolution kernel is used to slide convolution on the data to capture the patterns and regularities in the data and remove noise interference. For RNN and its variants, since temperature data has time series characteristics, they can effectively process this sequence data, capture the long-term dependencies in the data through memory units, identify the differences between noise signals and true temperature signals, and then filter and remove noise. At the same time, quantum neural networks are introduced for feature extraction. Quantum neural networks use the superposition and entanglement characteristics of quantum bits. Unlike traditional bits, which have only two states, 0 and 1, quantum bits (qubits) can be in a superposition state of 0 and 1 at the same time, which enables quantum neural networks to have the ability to parallelize calculations when processing data and can process multiple data states at the same time. The entanglement property allows a special connection between quantum bits. Even if they are separated in space, the state change of one quantum bit will instantly affect other entangled quantum bits. When processing complex temperature data, quantum neural networks can more efficiently explore the high-dimensional space of data and dig out deep-level features hidden in the data, such as the subtle change pattern of mold temperature under complex working conditions. In terms of feature screening, a feature screening method based on causal analysis is used. This method combines domain knowledge and data mining technology. Domain knowledge includes professional knowledge such as mold material characteristics and stamping process principles. For example, the difference in thermal conductivity of different mold materials will affect the temperature distribution, and the parameters such as stamping speed and pressure in the stamping process are closely related to temperature changes. Data mining technology uses algorithms to discover potential patterns and laws from large amounts of data. In causal analysis, methods such as Granger causality test are used to determine the causal relationship between different features and between features and mold temperature. For example, by analyzing and judging whether the feature of the mold surface coating thickness is the Granger cause that affects the mold temperature change, the key features that have a direct causal relationship with the mold temperature control can be found. When evaluating the effectiveness of the features, the improved data feature effectiveness evaluation formula is used (in is the weight of the jth feature, is the contribution rate of the jth feature, is the causal relationship strength between the jth feature and the mold temperature control target, and m is the number of features), which can more accurately evaluate the effectiveness of the features.

[0033] Control decision module: The control decision module is the core component of precise control of mold temperature. It uses a variety of advanced algorithms and models to achieve efficient and intelligent control decisions. This module adopts an intelligent decision model based on fuzzy logic control and particle swarm optimization algorithm, and introduces reinforcement learning algorithm on this basis. Fuzzy logic control is a control method that imitates human thinking. It converts precise input data into fuzzy sets through membership functions, such as converting the precise value of mold temperature into fuzzy concepts such as "low temperature", "medium temperature" and "high temperature". Then, according to the pre-set fuzzy rules, such as "if the mold temperature is low temperature and the temperature change rate is small, then increase the heating power appropriately", fuzzy reasoning is performed, and finally the fuzzy output is converted into a precise control quantity, such as a specific heating power adjustment value, through defuzzification operations. Particle swarm optimization algorithm (PSO) is an optimization algorithm based on swarm intelligence. In the mold temperature control scenario, each particle represents a set of possible control parameters (such as heating power, cooling flow, etc.), and the particles fly in the solution space and find the optimal solution by constantly updating their own positions. The particle position update is based on its own historical optimal position and the global optimal position of the group. Through iterative search, it gradually converges to the optimal control parameter combination to achieve optimal control of the mold temperature. The reinforcement learning algorithm continuously learns the optimal control strategy by interacting with the environment. In mold temperature control, the environment is the mold and its stamping process system. The reinforcement learning algorithm takes the real-time state of the mold (such as current temperature, temperature change trend, stamping process stage, etc.) as input and outputs the corresponding control action (such as adjusting the working parameters of the heating or cooling equipment). After each control action is executed, the system will give a reward or penalty signal according to the change of the mold temperature. The algorithm continuously tries different control actions and adjusts the strategy according to the reward feedback, gradually learning the optimal control strategy under different states, so that it can quickly adjust the working parameters of the heating and cooling execution modules according to the real-time state of the mold and the dynamic changes of the stamping process. At the same time, considering the thermal properties of the mold material (such as thermal conductivity, specific heat capacity, etc.), the material and thickness of the aluminum alloy sheet, and other factors, a multi-parameter coupled control decision model is established. The thermal conductivity of the mold material determines the speed at which heat is conducted inside the mold, and the specific heat capacity affects the ease with which the mold temperature changes. Different materials of aluminum alloy plates have different heat dissipation and deformation characteristics during the stamping process, and the thickness affects the heat exchange efficiency between the plate and the mold. Through comprehensive analysis and modeling of these parameters, finite element analysis and other methods are used to simulate the changes in mold temperature under different parameter combinations, and a control decision model that can accurately reflect the multi-parameter coupling relationship is constructed, providing a more comprehensive and accurate basis for control decisions. In terms of evaluating decision accuracy, an improved decision accuracy evaluation formula is used. (in is the number of correct decisions, is the total number of decisions, is the deviation between the mold temperature and the target temperature after the kth decision, and L is the total number of decisions). The temperature deviation after the decision is comprehensively considered to evaluate the decision accuracy more scientifically.

[0034] Heating and cooling execution module: As the direct executor of mold temperature control, the heating and cooling execution module is equipped with an electromagnetic induction heating device and a microchannel liquid cooling device, which ensures precise control of mold temperature through a variety of advanced technologies. The electromagnetic induction heating device adopts a new type of high-frequency induction coil material and topological structure. In terms of materials, special alloy materials with high magnetic permeability, low hysteresis loss and low eddy current loss are selected. This material can efficiently generate induced current under high-frequency alternating magnetic field, thereby converting electrical energy into thermal energy, significantly improving heating efficiency. For example, some ferrite-metal composite materials have a much higher magnetic permeability than traditional copper coil materials. Under the same electromagnetic excitation, they can generate a stronger induced magnetic field, thereby increasing heating power. In terms of topological structure, an optimized multi-turn spiral or array design is adopted. The multi-turn spiral structure can form a relatively uniform magnetic field distribution on the mold surface, so that all parts of the mold are heated more evenly. The array structure can flexibly adjust the position and parameters of each induction unit according to the shape of the mold and heating requirements, so as to achieve precise heating of local areas of the mold. Through precise electromagnetic field simulation and experimental optimization, the optimal number of coil turns, spacing and arrangement are determined, further improving the uniformity and efficiency of heating. The microchannel liquid cooling device adopts a bionic microchannel design. This design imitates the vascular network in the body and constructs a complex and delicate microchannel structure. These microchannels have extremely small inner diameters, usually between tens and hundreds of microns, which greatly increases the contact area between the coolant and the inner wall of the mold. When the coolant flows in the microchannel, it can more effectively take away the heat inside the mold. At the same time, the branching structure of the microchannel is similar to the branching of biological blood vessels, which can make the coolant evenly distributed in various areas inside the mold, avoiding the problems of local overheating or uneven cooling that may occur in traditional cooling methods. Through reasonable fluid mechanics design, the shape, size and layout of the microchannel are optimized to ensure that the flow resistance of the coolant in the microchannel is minimized and the best cooling effect is achieved. In addition, the module introduces intelligent phase change materials. This phase change material has a specific phase change temperature range. When the mold temperature is too high, the phase change material absorbs heat and changes from solid to liquid or other phases, and a phase change process occurs. In this process, the phase change material absorbs a large amount of latent heat, plays a role in buffering and regulating temperature, and prevents the mold temperature from rising sharply. For example, some organic polymer phase change materials can absorb a large amount of heat while keeping their own temperature relatively stable when the temperature reaches its phase change point. When the temperature drops, the phase change material will change from liquid to solid, release the stored heat, and maintain the stability of the mold temperature. By precisely controlling the addition amount and distribution position of the phase change material, it can play the best role in mold temperature control, further improving the stability and accuracy of mold temperature control.

[0035] The present invention also includes the following modules: Mold status detection module, which plays a vital role in mold status monitoring, ensures accurate control of mold status through a variety of advanced technical means. First, the module monitors the pressure changes during the stamping process through a pressure sensor. The pressure sensor adopts a high-precision piezoresistive or piezoelectric principle. Piezoresistive pressure sensors are based on the piezoresistive effect. When subjected to pressure, the internal resistance value will change. The pressure can be accurately obtained by measuring the change in resistance value. Piezoelectric pressure sensors use the characteristic of piezoelectric materials generating charges when subjected to pressure to determine the pressure by measuring the size of the charge. These pressure sensors are precisely installed at the key stress-bearing parts of the mold, and can capture the dynamic changes of pressure during the stamping process in real time and accurately, providing basic data for analyzing the stress state of the mold. At the same time, vibration sensors are used to monitor the vibration of the mold. Vibration sensors mostly use accelerometers or displacement sensors. Accelerometers can measure the acceleration changes of the mold in all directions. By analyzing the acceleration signal, the frequency, amplitude and other characteristics of the mold vibration can be understood. Displacement sensors can accurately measure the displacement of mold components, thereby determining whether the mold is loose or abnormally displaced. These vibration sensors are distributed at different positions of the mold to monitor the vibration state of the mold in all directions. In addition to the anomaly detection algorithm based on wavelet transform, an anomaly perception technology based on quantum entanglement is also introduced. Quantum entanglement is a quantum mechanical phenomenon. For a quantum system in an entangled state, even if it is separated from each other in space, the state change of one quantum will instantly affect the state of another quantum. In mold monitoring, quantum entanglement is extremely sensitive to tiny physical changes. For example, tiny damage or defects inside the mold will cause extremely tiny changes in local stress, strain and other physical properties. These changes will affect the quantum system in the entangled state through the surrounding physical field. Quantum sensors can capture these extremely weak change signals, thereby sensing tiny damage and defects inside the mold in advance, providing an important basis for preventive maintenance of the mold. In order to improve the accuracy and reliability of anomaly detection, a multi-sensor data fusion algorithm is adopted. The algorithm first pre-processes the data of pressure, vibration and quantum entanglement perception, including data cleaning, filtering and other operations to remove noise and interference signals. Then, data fusion technology, such as data fusion method based on Bayesian network, is used to fuse the data of different sensors. The Bayesian network can comprehensively judge the state of the mold based on the probabilistic relationship between different sensor data. For example, when the pressure sensor detects an abnormal increase in pressure, the vibration sensor detects an abnormal vibration frequency, and the quantum entangled state senses a slight change inside the mold, the Bayesian network's reasoning calculation can more accurately determine whether the mold has an abnormality and the type and location of the abnormality. In terms of evaluating the anomaly detection effect, an improved anomaly detection accuracy evaluation formula is used (in is the number of correctly detected anomalies, is the actual number of anomalies, It is The delay time of anomaly detection, is the total monitoring time), comprehensively considers the detection delay, and more reasonably evaluates the anomaly detection effect.

[0036] Fault diagnosis and early warning module: This module plays a key role in ensuring the stable operation of the system. It uses a variety of advanced technical means to accurately diagnose and warn system faults. The module uses fault tree analysis and Bayesian network to analyze the operating data of each module of the system. Fault tree analysis is a graphical deductive method. It takes the major faults (top events) that the system does not want to happen as the starting point, and gradually analyzes the various direct and indirect causes (intermediate events and bottom events) that lead to the top events. These events are connected through logic gates (such as AND gates, OR gates, etc.) to construct an inverted tree-like logical causal relationship diagram. For example, if the mold temperature is out of control as the top event, then the possible causes of the event include intermediate events such as heating and cooling execution module failures and data analysis and processing module errors. Further analysis can also find bottom events such as sensor failures and control algorithm errors. Through this method, the causal relationship of system failures can be clearly sorted out, providing clues for troubleshooting. Bayesian network is a graphical network model based on probabilistic reasoning. It uses nodes to represent variables (such as the operating parameters of each module) and uses directed edges to represent the probabilistic dependencies between variables. By learning and analyzing historical operation data, the conditional probability distribution between nodes is determined. In fault diagnosis, the probability of each fault is calculated using the Bayesian formula based on the currently observed operation data, so as to determine the most likely fault type of the system. On this basis, the deep learning autoencoder is introduced to extract fault features. The autoencoder is a special neural network structure consisting of an encoder and a decoder. The encoder compresses the input high-dimensional operation data into a low-dimensional feature representation, and the decoder attempts to restore these feature representations to the original data. During the training process, the autoencoder learns the intrinsic characteristics of the data by minimizing the reconstruction error. When a system fails, the characteristics of the operation data will change, and the autoencoder can capture these changes and discover potential fault modes. For example, by training data such as temperature and pressure under normal operation and fault conditions, the autoencoder can identify abnormal changes in data characteristics during failure, thereby extracting fault features. A fault reasoning mechanism based on knowledge graph is used to structure and associate fault knowledge. The knowledge graph is a semantic network that stores knowledge in the form of entity-relationship-entity triples. In the mold intelligent temperature control system, various fault types, fault causes, fault manifestations, and maintenance methods are taken as entities, and the causal relationships and correlations between them are taken as relationships to construct a fault knowledge graph. When an abnormality is detected in the system, the cause and solution of the fault can be quickly determined by reasoning and querying in the knowledge graph, achieving more accurate fault diagnosis and reasoning. When a potential fault is detected, the fault location and maintenance instructions are displayed to the operator through virtual reality (VR) and augmented reality (AR) technology.VR technology creates a completely virtual environment. Operators can wear VR equipment to view the structure and fault location of the mold in all directions in the virtual environment, and obtain detailed maintenance steps and operation instructions. AR technology superimposes virtual information on the real scene. Operators can use AR glasses and other equipment to see the marks of the fault location and maintenance prompts on the actual mold, and perform troubleshooting and maintenance more intuitively. In terms of evaluating the effect of fault prediction, an improved fault prediction accuracy evaluation formula is used. (in is the number of correctly predicted failures, is the actual number of failures that occurred, is the deviation between the predicted time of the jth fault and the actual time of the fault occurrence, is the total fault monitoring time), comprehensively considers the prediction time deviation, and evaluates the fault prediction effect more accurately.

[0037] In the present invention, the temperature acquisition module uses self-calibration technology to periodically calibrate the sensor. In addition to using the calibration algorithm based on Kalman filtering, quantum calibration technology is introduced. Quantum calibration technology uses the stability and repeatability of quantum states to provide a high-precision calibration benchmark for the sensor. The calibration method based on quantum bit error correction code can effectively correct quantum noise and errors in the sensor measurement process. Adopt an adaptive calibration strategy to dynamically adjust the calibration cycle and calibration parameters according to factors such as the sensor's usage time and working environment. Use an improved calibration error evaluation formula (in is the true temperature value, is the temperature value measured by the sensor, is the number of calibrations, is a weight determined according to the calibration time and environmental conditions) to more reasonably evaluate the calibration effect.

[0038] In the present invention, the data transmission module introduces data encryption technology to encrypt the transmitted data. In addition to using an algorithm based on quantum encryption, it also combines homomorphic encryption technology. Homomorphic encryption allows calculations to be performed directly on encrypted data without decryption, ensuring the security of the data during processing. A hybrid encryption mechanism based on blockchain and quantum key distribution is adopted, combining the distributed ledger of blockchain and the unbreakable nature of quantum keys to further improve the security of data encryption. An improved data encryption security evaluation formula is adopted (in is the amount of data safely transmitted, is the total amount of data, It is The probability of encrypted data being cracked. is the total number of encrypted data transmissions), comprehensively considers the risk of encrypted data being cracked, and more comprehensively evaluates the security of data encryption.

[0039] In the present invention, the data analysis and processing module introduces transfer learning technology. In addition to using the temperature data and processing experience of other similar molds, cross-domain transfer learning is introduced. The temperature control data and processing methods in the fields of aerospace, automobile manufacturing, etc. are transferred to the temperature control system of aluminum alloy sheet stamping forming molds to broaden the data source and processing ideas. The meta-learning-based transfer learning method is used to quickly learn the characteristics and processing modes of data in different fields, thereby improving the efficiency and effect of transfer learning. The improved transfer learning effect evaluation formula is used (in After transfer learning The improvement value of data analysis indicators, It is the first The value of the data analysis indicator, n is the number of data analysis indicators, is a weight determined according to the importance of the indicator) to more scientifically evaluate the effect of transfer learning.

[0040] In the present invention, the control decision module adopts a multi-objective optimization algorithm to ensure the temperature stability of the mold while taking into account the quality and production efficiency of stamping. In addition to using the non-dominated sorting genetic algorithm (NSGA-II) for optimization, a quantum multi-objective optimization algorithm is introduced. The quantum multi-objective optimization algorithm uses the superposition and entanglement characteristics of quantum bits to search for the global optimal solution more quickly. Considering more objectives such as the service life of the mold and energy consumption, a multi-objective collaborative optimization model is established. The improved multi-objective optimization effect evaluation formula is adopted (in is the weight of the jth target, is the optimization effect index of the jth objective, is the synergistic correlation strength between the jth objective and other objectives, and m is the number of objectives), to more comprehensively evaluate the effect of multi-objective optimization.

[0041] In the present invention, the heating and cooling execution modules use intelligent flow control valves and variable frequency heating power supplies to achieve precise control of coolant flow and heating power. In addition to the traditional PID control algorithm, the model predictive control (MPC) algorithm is introduced. The MPC algorithm can predict and adjust the control parameters in advance according to the temperature model of the mold and future process requirements, thereby improving the control accuracy and response speed. Adopt an adaptive control strategy to automatically adjust the parameters of the control algorithm according to the real-time status of the mold and environmental changes. Use an improved control accuracy evaluation formula (in is the set control parameter value, is the actual control parameter value, is the control frequency, is a weight determined according to control time and importance) to more reasonably evaluate the accuracy of control.

[0042] In the present invention, the mold state detection module uses a machine learning algorithm to classify and predict pressure and vibration data. In addition to using a method that combines support vector machines (SVM) and neural networks, deep learning convolutional neural networks (CNN) and recurrent neural networks (RNN) are introduced. CNN can automatically extract the spatial features of data, and RNN can process the temporal features of sequence data to improve the accuracy of classification and prediction. The results of multiple machine learning algorithms are integrated based on an ensemble learning method to further enhance the reliability of classification and prediction. The improved classification accuracy evaluation formula is used. (TP is the number of true positive examples, TN is the number of true negative examples, FP is the number of false positive examples, and FN is the number of false negative examples, It is The confidence deviation of the sub-classification, is the total number of classifications), and the classification confidence deviation is comprehensively considered to more accurately evaluate the accuracy of classification.

[0043] In the present invention, the fault diagnosis and early warning module uses a method that combines expert systems and machine learning to perform fault diagnosis. In addition to the expert system performing preliminary diagnosis based on pre-set rules and experience, and the machine learning algorithm learning and analyzing a large amount of fault data, a deep learning fault diagnosis model enhanced by knowledge graphs is introduced. The knowledge graph can provide rich domain knowledge for the deep learning model and improve the accuracy and interpretability of fault diagnosis. A case-based reasoning fault diagnosis method is used, and analogical reasoning is performed using historical fault cases to quickly locate and resolve new faults. An improved fault diagnosis accuracy evaluation formula is used (in is the number of faults correctly diagnosed, is the total number of diagnoses, is the deviation between the jth fault diagnosis time and the actual fault occurrence time, is the total fault diagnosis time), comprehensively considering the diagnosis time deviation to more accurately evaluate the effect of fault diagnosis.

[0044] The above are only preferred specific implementation modes of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical solutions and inventive concepts of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. An intelligent temperature control system for aluminum alloy sheet stamping die, characterized in that: include: Temperature acquisition module: Thermocouple sensors and fiber Bragg grating sensors are evenly distributed in the mold, and the distribution position of the sensors is dynamically adjusted using an adaptive layout algorithm; Temperature uniformity evaluation formula Evaluate the uniformity of mold temperature distribution, It is The temperature collected by the sensor, is the average temperature, n is the number of sensors, is the weight determined according to the location and importance of the sensor; Data transmission module: Using 5G communication technology and industrial Ethernet, adopting a blockchain-based data transmission authentication mechanism, and using the data transmission stability evaluation formula Evaluate data transmission stability, is the amount of data transmitted correctly, is the total amount of data transferred, is the time of the jth transmission interruption, T is the total transmission time; Data analysis and processing module: Use the noise reduction algorithm to denoise the collected data, introduce quantum neural network for feature extraction; use the data feature validity evaluation formula Evaluate the effectiveness of features, is the weight of the jth feature, is the contribution rate of the jth feature, is the causal association strength between the jth feature and the mold temperature control target, and m is the number of features; Control decision module: Adopt intelligent decision model based on fuzzy logic control and particle swarm optimization algorithm to adjust the working parameters of heating and cooling execution modules according to the real-time status of the mold and the dynamic changes of the stamping process; establish a multi-parameter coupling control decision model and adopt decision accuracy evaluation formula Evaluate the accuracy of decisions, is the number of correct decisions, is the total number of decisions, is the deviation between the mold temperature and the target temperature after the kth decision, and L is the total number of decisions; Heating and cooling execution module: equipped with electromagnetic induction heating device and microchannel liquid cooling device, introducing intelligent phase change material. When the mold temperature exceeds the threshold, the phase change material absorbs heat and undergoes phase change. When the temperature is lower than the threshold, the phase change material releases heat.

2. The intelligent temperature control system for aluminum alloy sheet stamping die according to claim 1, characterized in that: Also includes: Mold status detection module: monitors the pressure changes during the stamping process through pressure sensors, monitors the vibration of the mold using vibration sensors, adopts anomaly detection algorithm based on wavelet transform, and introduces quantum entangled state anomaly perception technology; uses multi-sensor data fusion algorithm to fuse the pressure, vibration and quantum entangled state perception data; Adopt anomaly detection accuracy evaluation formula Evaluate the anomaly detection performance, is the number of correctly detected anomalies, is the actual number of anomalies, It is The delay time of anomaly detection, is the total monitoring time.

3. The intelligent temperature control system for aluminum alloy sheet stamping die according to claim 1, characterized in that: Also includes: Fault diagnosis and early warning module: Use fault tree analysis and Bayesian network to analyze the operating data of each module, introduce deep learning autoencoder to extract fault features; adopt fault reasoning mechanism based on knowledge graph to structure and associate fault knowledge to achieve fault diagnosis and reasoning; when potential fault is detected, use virtual reality and augmented reality technology to show the fault location and maintenance instructions to the operator; use fault prediction accuracy evaluation formula Evaluate the effectiveness of fault prediction, is the number of correctly predicted failures, is the actual number of failures that occurred, is the deviation between the predicted time of the jth fault and the actual time of the fault occurrence, is the total fault monitoring time.

4. The intelligent temperature control system for aluminum alloy sheet stamping die according to claim 1, characterized in that: In the temperature acquisition module, the self-calibration technology is used to calibrate the sensor regularly. The calibration algorithm based on Kalman filtering is used to introduce quantum calibration technology. The calibration method based on quantum bit error correction code is used to correct the quantum noise and error in the sensor measurement process. The adaptive calibration strategy is used to dynamically adjust the calibration cycle and calibration parameters according to the sensor's usage time and working environment factors. The calibration error evaluation formula is used. Evaluate the calibration effect, is the true temperature value, is the temperature value measured by the sensor, is the number of calibrations, It is a weight determined according to the calibration time and environmental conditions.

5. The intelligent temperature control system for aluminum alloy sheet stamping die according to claim 1, characterized in that: In the data transmission module, data encryption technology is introduced to encrypt the transmitted data. The quantum encryption algorithm is combined with homomorphic encryption technology. A hybrid encryption mechanism based on blockchain and quantum key distribution is adopted to combine the distributed ledger of blockchain and the unbreakable nature of quantum keys. The data encryption security evaluation formula is used to evaluate the security of the data. Evaluate the security of data encryption, is the amount of data safely transmitted, is the total amount of data, It is The probability of encrypted data being cracked. is the total number of encrypted data transmissions.

6. The intelligent temperature control system for aluminum alloy sheet stamping die according to claim 1, characterized in that: In the data analysis and processing module, transfer learning technology is introduced, and cross-domain transfer learning is introduced using the temperature data and processing experience of the mold; the temperature control data and processing methods in the aerospace and automobile manufacturing fields are transferred to the temperature control system of the aluminum alloy sheet stamping forming mold to broaden the data source and processing ideas; a transfer learning method based on meta-learning is used to learn the characteristics and processing modes of data in different fields; and a transfer learning effect evaluation formula is used Evaluate the effectiveness of transfer learning. After transfer learning The improvement value of data analysis indicators, It is the first The value of the data analysis indicator, n is the number of data analysis indicators, It is the weight determined according to the importance of the indicator.

7. The intelligent temperature control system for aluminum alloy sheet stamping forming dies according to claim 1, characterized in that: In the control decision module, a multi-objective optimization algorithm is used to ensure the stability of the mold temperature and take into account the quality and production efficiency of stamping. The non-dominated sorting genetic algorithm is used for optimization, and the quantum multi-objective optimization algorithm is introduced. Considering the service life and energy consumption of the mold, a multi-objective collaborative optimization model is established, and a multi-objective optimization effect evaluation formula is used. Evaluate the performance of multi-objective optimization. is the weight of the jth target, is the optimization effect index of the jth objective, is the synergistic correlation strength between the jth target and other targets, and m is the number of targets.

8. The intelligent temperature control system for aluminum alloy sheet stamping die according to claim 1, characterized in that: In the heating and cooling execution module, intelligent flow control valve and variable frequency heating power supply are used to control the coolant flow and heating power; the traditional PID control algorithm is adopted, the model predictive control algorithm is introduced, and the adaptive control strategy is combined to automatically adjust the parameters of the control algorithm according to the real-time status of the mold and environmental changes; the control accuracy evaluation formula is used Evaluate the accuracy of control, is the set control parameter value, is the actual control parameter value, is the control frequency, It is a weight determined based on control time and importance.

9. The intelligent temperature control system for aluminum alloy sheet stamping die according to claim 2, characterized in that: In the mold state detection module, a machine learning algorithm is used to classify and predict pressure and vibration data. The method of combining support vector machine and neural network is used to introduce deep learning convolutional neural network and recurrent neural network. The method based on ensemble learning is used to integrate the results of multiple machine learning algorithms and evaluate the classification accuracy through the formula. Evaluate the accuracy of classification, TP is the number of true positive examples, TN is the number of true negative examples, FP is the number of false positive examples, and FN is the number of false negative examples. It is The confidence deviation of the sub-classification, is the total number of classifications.

10. The intelligent temperature control system for aluminum alloy sheet stamping die according to claim 3, characterized in that: In the fault diagnosis and early warning module, a combination of expert system and machine learning is used for fault diagnosis. The expert system performs preliminary diagnosis based on pre-set rules and experience, and the machine learning algorithm learns and analyzes fault data. A knowledge graph deep learning fault diagnosis model is introduced, and a case-based reasoning fault diagnosis method is adopted. Historical fault cases are used for analogical reasoning to locate and solve new faults. The fault diagnosis accuracy evaluation formula is used Evaluate the effectiveness of fault diagnosis, is the number of faults correctly diagnosed, is the total number of diagnoses, is the deviation between the jth fault diagnosis time and the actual fault occurrence time, is the total fault diagnosis time.

Images