Cadmium telluride production line control method, device and equipment based on digital twinning
Through digital twin technology, the model of cadmium telluride production line equipment is established, the operating parameters are optimized and abnormal responses are automatically solved, and the problems of manual monitoring and data islands of cadmium telluride production line are solved, improving the working efficiency and stability of the equipment.
Patent Information
- Application Number
- CN202411168902.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-23
- Publication Date
- 2024-11-26
AI Technical Summary
The cadmium telluride production lines rely on manual monitoring and dispersed data management, resulting in low efficiency, data silos, high maintenance costs, unstable product quality, high failure rate, and low working efficiency and stability.
The control method based on digital twin is adopted to establish a device model by obtaining sensor data, simulating the operating status under different operating parameters, optimizing the equipment performance parameters, monitoring and automatically responding to abnormal situations in real time, and generating control strategies to improve the operating efficiency and stability of the equipment.
Through digital twin technology, the operation status of cadmium telluride production line equipment is simulated and optimized, real-time monitoring and automated response are achieved, the work efficiency and stability of the equipment are improved, and the failure rate and maintenance costs are reduced.
Smart Images

Figure CN119024796A_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the field of automation control technology, and specifically relates to a cadmium telluride production line control method, device and equipment based on digital twin. Background Art
[0002] Current cadmium telluride production line management technology relies on manual monitoring, decentralized data management, and passive maintenance, which has problems such as low efficiency, data silos, high maintenance costs, and unstable product quality. Manual operations are prone to errors, data dispersion hinders comprehensive optimization, and passive maintenance leads to high failure rates and downtime losses. Therefore, the current cadmium telluride production line equipment has relatively low efficiency and stability. Summary of the invention
[0003] The object of the present invention is to provide a cadmium telluride production line control method, device and equipment based on digital twin, which can improve the working efficiency and stability of the cadmium telluride production line equipment.
[0004] The first aspect of the present invention discloses a cadmium telluride production line control method based on digital twin, comprising:
[0005] Obtain the historical operation data of each device on the cadmium telluride production line collected by sensors;
[0006] Build a digital twin model of each device based on its historical operating data;
[0007] Use the digital twin model of each device to simulate the operating status of each device under different operating parameter conditions and obtain the performance indicators of each device under different operating parameter conditions;
[0008] According to the performance indicators of each device under different operating parameter conditions, the constructed device performance optimization model of each device is optimized to obtain the optimal solution as the first operating parameter of each device;
[0009] In the process of controlling each device to operate with the first operating parameter corresponding to each device, obtaining real-time operating data of each device;
[0010] When the real-time operating data of any device exceeds the preset abnormal warning threshold, it is determined to be an abnormal device and an alarm message is issued for the abnormal device.
[0011] In some embodiments, after issuing an alarm message for the abnormal device, the method further includes:
[0012] Automatically activate the response system corresponding to the abnormal device;
[0013] The real-time operation data of the abnormal equipment and the operation status of its response system are analyzed to obtain data analysis results.
[0014] In some embodiments, after analyzing the real-time operation data of the abnormal device and the operation status of its response system and obtaining the data analysis results, the method further includes:
[0015] According to the data analysis result, optimizing the first operating parameter of the abnormal device to obtain a second operating parameter;
[0016] The abnormal device is controlled to operate with the second operating parameter.
[0017] In some embodiments, after analyzing the real-time operation data of the abnormal device and the operation status of its response system and obtaining the data analysis results, the method further includes:
[0018] Generating a control strategy for a response system to the abnormal device according to the data analysis result;
[0019] The response system of the abnormal device is controlled according to the control strategy.
[0020] In some embodiments, a digital twin model of each device is established based on the historical operation data of each device, including:
[0021] Extract geometric features from the CAD drawings of each device, and extract design parameters from the 3D design models of each device;
[0022] Establish the geometric model of the equipment according to the geometric features and design parameters;
[0023] Clean the historical operation data of each device to obtain clean operation data;
[0024] Using multi-body dynamics and computational fluid dynamics, a digital twin model of each device is established based on the cleaning operation data.
[0025] The second aspect of the present invention discloses a cadmium telluride production line control device based on digital twin, comprising:
[0026] An acquisition unit, used to acquire historical operation data of each device on the cadmium telluride production line collected by sensors;
[0027] An establishment unit is used to establish a digital twin model of each device based on the historical operation data of each device;
[0028] A simulation unit is used to use the digital twin model of each device to simulate the operating state of each device under different operating parameter conditions, and obtain the performance indicators of each device under different operating parameter conditions;
[0029] A first optimization unit is used to optimize the constructed equipment performance optimization model of each equipment according to the performance index of each equipment under different operating parameter conditions, and obtain an optimal solution as the first operating parameter of each equipment;
[0030] A monitoring unit, used to obtain real-time operation data of each device during the process of controlling each device to operate with the first operating parameter corresponding to each device;
[0031] The early warning unit is used to determine any device as an abnormal device when the real-time operating data of the device exceeds a preset abnormal early warning threshold, and to send an alarm message to the abnormal device.
[0032] In some embodiments, it also includes:
[0033] A starting unit, configured to automatically start a response system corresponding to the abnormal device after the early warning unit issues an alarm message for the abnormal device;
[0034] The analysis unit is used to analyze the real-time operation data of the abnormal equipment and the operation status of its response system to obtain data analysis results.
[0035] In some embodiments, it also includes:
[0036] a second optimization unit, configured to optimize the first operating parameter of the abnormal device to obtain a second operating parameter according to the data analysis result after the analysis unit analyzes the real-time operating data of the abnormal device and the operating conditions of the response system thereof to obtain a data analysis result;
[0037] The first control unit is used to control the abnormal device to operate with the second operating parameter.
[0038] In some embodiments, it also includes:
[0039] A generating unit, configured to generate a control strategy for the response system of the abnormal device according to the data analysis result after the analyzing unit analyzes the real-time operation data of the abnormal device and the operation status of the response system thereof to obtain the data analysis result;
[0040] The second control unit is used to control the response system of the abnormal equipment according to the control strategy.
[0041] The third aspect of the present invention discloses an electronic device, comprising a memory storing executable program code and a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the digital twin-based cadmium telluride production line control method disclosed in the first aspect.
[0042] The fourth aspect of the present invention discloses a computer-readable storage medium, which stores a computer program, wherein the computer program enables a computer to execute the cadmium telluride production line control method based on digital twin disclosed in the first aspect.
[0043] The beneficial effect of the present invention lies in that by acquiring the historical operating data of each device on the cadmium telluride production line collected by the sensor, a digital twin model of each device is established, and the digital twin model is used to simulate the operating status of each device under different operating parameter conditions to obtain the performance indicators of each device; the constructed equipment performance optimization model of each device is optimized according to the performance indicators to obtain the first operating parameters of each device; in the process of controlling each device to operate with its own first operating parameter, the real-time operating data of each device is obtained, and when the real-time operating data of any device exceeds the preset abnormal warning threshold, it is determined to be an abnormal device and an alarm message is issued, so that the operating status of each device on the cadmium telluride production line under different operating parameter conditions can be simulated based on the digital twin technology, so as to obtain the performance indicators of each device under different operating parameter conditions, optimize the equipment operating parameters with the performance indicators as the target, and apply the optimization scheme to the actual production environment, monitor the equipment operating status in real time, ensure the effectiveness and stability of the optimization scheme, and thus improve the working efficiency and stability of the cadmium telluride production line equipment. BRIEF DESCRIPTION OF THE DRAWINGS
[0044] The accompanying drawings herein show specific examples of the technical solutions described in the present invention, and together with the specific implementation methods, constitute a part of the specification, and are used to explain the technical solutions, principles and effects of the present invention.
[0045] Unless otherwise specified or defined, the same reference numerals in different drawings represent the same or similar technical features, and the same or similar technical features may also be represented by different reference numerals.
[0046] Figure 1 It is a flow chart of a cadmium telluride production line control method based on digital twin disclosed in an embodiment of the present invention;
[0047] Figure 2 It is a structural schematic diagram of a cadmium telluride production line control device based on digital twin disclosed in an embodiment of the present invention;
[0048] Figure 3 It is a structural schematic diagram of an electronic device disclosed in an embodiment of the present invention.
[0049] Description of reference numerals:
[0050] 201, acquisition unit; 202, establishment unit; 203, simulation unit; 204, first optimization unit; 205, monitoring unit; 206, early warning unit; 301, memory; 302, processor. DETAILED DESCRIPTION
[0051] Unless otherwise specified or defined, all technical and scientific terms used herein have the same meaning as those generally understood by those skilled in the art. In the case of combining the technical solution of the present invention with realistic scenarios, all technical and scientific terms used herein may also have meanings corresponding to the purpose of implementing the technical solution of the present invention. The "first, second..." used herein is only used to distinguish the names and does not represent a specific quantity or order. The term "and / or" used herein includes any and all combinations of one or more related listed items.
[0052] It should be noted that when a component is considered to be "fixed to" another component, it can be directly fixed to the other component or there can be a central component; when an component is considered to be "connected to" another component, it can be directly connected to the other component or there can be a central component at the same time; when an component is considered to be "installed on" another component, it can be directly installed on the other component or there can be a central component at the same time. When an component is considered to be "set on" another component, it can be directly set on the other component or there can be a central component at the same time.
[0053] Unless otherwise specified or defined, the "said" and "the" used in this document refer to the technical features or technical contents mentioned or described before the corresponding position, and the technical features or technical contents may be the same as or similar to the technical features or technical contents mentioned therein. In addition, the terms "including" and "having" and any variations thereof used in this document are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.
[0054] The embodiment of the present invention discloses a cadmium telluride production line control method based on digital twin, which can be implemented by computer programming. The execution subject of the method can be an electronic device such as a computer, a laptop, a tablet computer, or a cadmium telluride production line control device based on digital twin embedded in the electronic device, and the present invention is not limited to this. In order to facilitate the understanding of the present invention, the specific embodiments of the present invention will be described in more detail below with reference to the drawings of the specification.
[0055] like Figure 1As shown, the cadmium telluride production line control method based on digital twin includes the following steps 110 to 160:
[0056] 110. Obtain the historical operating data of each device on the cadmium telluride production line collected by sensors.
[0057] The equipment related to the cadmium telluride production line includes three types of equipment, namely material processing equipment, material storage equipment and material conveying equipment. Among them, material processing equipment includes homogenizer, sintering furnace, crusher, grinder and screening machine; material storage equipment includes various silos, such as mixed feeding silo, screen storage silo, storage silo and grinding material feeding silo; material conveying equipment includes screw feeder, screw elevator, bucket elevator, variable frequency rotary valve, vibrating feeder, filling machine, vacuum machine, sealing machine and labeling inkjet printer.
[0058] For material processing equipment, temperature, vibration and pressure sensors are installed on each device. The temperature sensor is used to monitor the internal temperature of the equipment to prevent overheating; the vibration sensor is used to monitor the vibration of the equipment during operation to prevent equipment failure; the pressure sensor is used to monitor the internal pressure of the equipment to ensure the safety of the processing process.
[0059] For material storage equipment, material level, humidity and weight sensors are installed on each device. The material level sensor is used to monitor the height of the material in the silo to prevent it from being overfull or too little; the humidity sensor is used to monitor the humidity in the silo to prevent the material from being dampened by steam; the weight sensor is used to monitor the weight of the material in the silo to ensure the accuracy of the feeding.
[0060] For material conveying equipment, flow, temperature and acceleration sensors are installed on each device. The flow sensor is used to monitor the material conveying flow rate to ensure the stability of transportation; the temperature sensor is used to monitor the temperature changes of the conveying equipment to prevent equipment failure caused by friction heat; the acceleration sensor is used to monitor the operating speed of the conveying equipment to prevent material overflow or blockage.
[0061] These sensors are installed on equipment related to the cadmium telluride production line to ensure that the operating data of the equipment can be collected in real time, and then the operating data collected by the sensors is transmitted through the Internet of Things gateway. The operating data specifically includes the temperature, vibration and pressure sensing data of each material processing equipment, the material level, humidity and weight sensing data of each material storage equipment, and the flow, temperature and acceleration sensing data of each material conveying equipment.
[0062] Historical operation data refers to the operation data of each device within a specified historical time period (such as the past week or month).
[0063] 120. Establish a digital twin model for each device based on its historical operating data.
[0064] The digital twin model of each device can simulate the operating status of each device under different conditions. Specifically, the specific implementation method of establishing the digital twin model of each device includes the following steps 1201 to 1204 (not shown):
[0065] 1201. Extract geometric features from the CAD drawings of each device, and extract design parameters from the 3D design models of each device.
[0066] 1202. Establish a geometric model of the equipment based on geometric features and design parameters.
[0067] 1203. Clean the historical operation data of each device to obtain clean operation data.
[0068] Among them, the cleaning process includes operations such as removing noise and outliers.
[0069] 1204. Utilize multi-body dynamics and computational fluid dynamics to build digital twin models of each device based on clean operation data.
[0070] Specifically, the implementation of step 1204 includes the following steps S11 to S12 (not shown):
[0071] S11. Modeling and network partitioning:
[0072] Modeling: Through multi-body dynamics (MBD) technology, for example, using multi-body dynamics software (such as Simpack, Adams), according to CAD drawings, establish multi-rigid body models of each device, including parameter definitions such as joints, links, mass, and inertia.
[0073] Meshing: According to the collective shape of each device, the fluid domain is divided into fine mesh units (such as tetrahedral or hexahedral meshes) by using computational fluid dynamics (CFD) technology, such as using computational fluid dynamics software (such as ANSYS Fluent) for spatial discretization.
[0074] S12. Combined action simulation: including dynamics simulation, fluid dynamics simulation, and coupling analysis;
[0075] Dynamic simulation: The MBD module is established through MBD simulation. The MBD module is used to analyze the mechanical motion behavior of each device under different operating conditions and obtain the mechanical motion data such as displacement, velocity, acceleration, etc. of each component.
[0076] Fluid dynamics simulation: CFD module is established through CFD simulation. The CFD module is used to simulate the flow behavior of materials inside the equipment according to the boundary conditions such as temperature, pressure, flow rate, etc. of the materials, and calculate key parameters such as the material temperature distribution and the gradient of the force (such as pressure and shear force) exerted by the materials on the mechanical components.
[0077] Coupling analysis: Set a unified time step so that the MBD module and the CFD module are synchronized in each time step. The mechanical motion data calculated by the MBD module will be passed to the CFD module, and the CFD module will update the boundary conditions of the fluid domain based on these mechanical motion data. The CFD module calculates key parameters such as the material temperature distribution and the force gradient of the material on the mechanical components, and feeds these key parameters back to the MBD module to affect the next movement state of the equipment.
[0078] 130. Use the digital twin model of each device to simulate the operating status of each device under different operating parameter conditions and obtain the performance indicators of each device under different operating parameter conditions.
[0079] Among them, the performance indicators specifically include the following 7 indicators:
[0080] Production efficiency: refers to the production rate under different operating parameters;
[0081] Energy consumption analysis: refers to the energy consumption data under different operating parameters (electricity consumption, heat energy consumption per unit time, etc.);
[0082] Temperature distribution: refers to the temperature distribution of each area inside the equipment and the trend of temperature changes over time;
[0083] Material state change: refers to the material's degree distribution, temperature, density, etc.;
[0084] Equipment load: refers to the load of each key component of the equipment (such as bearing load, transmission load, etc.) and load trend changes;
[0085] Production quality: refers to the quality indicators of the product (such as purity, particle size, surface finish, etc.) and the evaluation of the consistency and stability of product quality.
[0086] Fault prediction: probability of equipment failure under different operating parameters, and life prediction of key components.
[0087] 140. According to the performance indicators of each device under different operating parameter conditions, the constructed equipment performance optimization model of each device is optimized to obtain the optimal solution as the first operating parameter of each device.
[0088] In the present invention, the equipment performance optimization model is defined as: a mathematical or computer model used to improve the equipment's operating efficiency, stability and life. It helps operators determine the best equipment operating conditions by modeling and optimizing the equipment's operating parameters (such as speed, temperature, load, etc.).
[0089] The implementation method of constructing the device performance optimization model for each device specifically includes the following steps S21 to S24 not shown in the figure:
[0090] S21. Obtain sensor parameters of each device during operation.
[0091] Among them, high-precision sensors are used to collect various sensor parameters during equipment operation, including temperature, vibration, material flow rate, energy consumption, etc. The distributed data processing framework Apache Kafka can be used to collect, store and pre-process these sensor parameters in real time.
[0092] S22, performing denoising and normalization processing on the sensing parameters to obtain processed sensing data.
[0093] First, filtering technology (such as Kalman filter) is used to remove noise in the sensor parameters to improve the accuracy of the sensor parameters. Secondly, through normalization processing, the sensor parameters of different dimensions are adjusted to the same scale to facilitate subsequent model training and optimization.
[0094] S23. Perform principal component analysis on the processed sensor data to extract key features from the sensor data.
[0095] For example, principal component analysis (PCA) is used to extract key features from processed sensor data, which can reduce the dimension of the data and the complexity of model calculation.
[0096] S24. Determine the model type corresponding to each device according to the key features and preset optimization goals of each device, and build a device performance optimization model for each device according to the model type.
[0097] For different devices, choose the appropriate model type. Multiple candidate types include multivariate linear regression model, support vector machine, neural network or deep learning model, genetic algorithm or particle swarm optimization algorithm, etc.
[0098] Among them, the multivariate linear regression model is suitable for simple linear relationship modeling; the support vector machine is suitable for classification and regression problems, especially for high-dimensional data; the neural network or deep learning model is suitable for complex nonlinear relationship modeling and for dealing with the joint influence of multiple equipment parameters and environmental variables; the genetic algorithm or particle swarm optimization algorithm is suitable for the global optimization of model parameters to help find the optimal solution.
[0099] Therefore, the specific method for determining the model type corresponding to each device can be: if the key characteristics of the device and the preset optimization goals are a simple linear relationship, then the multivariate linear regression model is selected as its model type; if the key characteristics of the device and the preset optimization goals are a complex nonlinear relationship, then the deep learning model is selected as its model type.
[0100] Optionally, the structure of the deep learning model includes an input layer, a first hidden layer, a second hidden layer, a third hidden layer and an output layer connected in sequence, wherein:
[0101] Input layer: The dimension of the input layer is equal to the number of key features of the input;
[0102] The first hidden layer: contains 128 neurons and uses the ReLU activation function. This layer is responsible for capturing the nonlinear relationship between the key features of the input.
[0103] The second hidden layer contains 64 neurons and uses the ReLU activation function. This layer further abstracts features and captures more complex relationships.
[0104] The third hidden layer: contains 32 neurons and uses the ReLU activation function. It is used to more finely extract features related to the preset optimization target.
[0105] Output layer: The output layer contains 1 neuron, uses a linear activation function, and outputs the preset optimization target.
[0106] In the above model architecture, the three hidden layers use the ReLU activation function (Rectified Linear Unit). This is because ReLU can effectively solve the gradient vanishing problem and ensure that the model can still converge quickly when the depth is large. The formula of ReLU is: f(x) = max(0, x).
[0107] In the output layer, the present invention adopts a linear activation function because the preset optimization target of the output is a continuous value and does not need to be normalized or compressed to a certain range.
[0108] As an optional implementation, during the training process of the above deep learning model:
[0109] First, data preparation: standardize all key features of the input (such as zero mean and unit variance) to ensure that the numerical ranges of different features are similar and prevent a certain key feature from dominating the model training.
[0110] Second, the loss function selection: select mean-square error (MSE) as the loss function. MSE is used to measure the difference between the model prediction value and the true value. Its formula is: where y i is the true value, is the model's predicted value.
[0111] Then, the optimization algorithm is selected: use the Adam optimizer, which is an optimization algorithm based on gradient descent, which can adaptively adjust the learning rate and has good convergence speed and stability. The update formula of the Adam optimizer is as follows:
[0112] m t =β1m t-1 +(1-β1)g t
[0113]
[0114]
[0115]
[0116] Among them, m t and v t They represent the exponential moving average of the momentum and mean square value of the gradient respectively; β1 and β2 represent the estimated decay rate of the gradient, which are usually set to 0.9 or 0.99; g t Represents the gradient of the current time step t, that is, the gradient of the objective function with respect to the model parameter θ; and are the estimated values after deviation correction respectively; α is the learning rate, which controls the step size of each parameter update; ∈ is the smoothing term, which prevents division by zero and is usually set to a smaller value; θ t Represents model parameters.
[0117] Based on this, the training process of the above deep learning model includes steps S31 to S35 (not shown):
[0118] S31, Model initialization: Randomly initialize model parameters (such as weights and biases).
[0119] S32, forward propagation: input key features through the input layer, hidden layer to the output layer, calculate the predicted value.
[0120] S33. Calculate loss: Calculate the difference between the model prediction value and the true value through the loss function (MSE).
[0121] S34, Back propagation: Use Adam optimizer for back propagation to update model parameters and reduce losses.
[0122] S35, iterative training: repeat the above process until the loss converges to a preset threshold or reaches the maximum number of training rounds.
[0123] Through the trained model, the current equipment operation data can be input in real time to output the optimized parameters. This optimized parameter will help the equipment maintain optimal performance under different working conditions and extend the service life of the equipment.
[0124] For example, assuming that the key characteristics of the screw elevator are material flow rate, material friction, ambient temperature, etc., the preset optimization target is the equipment temperature of the screw elevator. The equipment temperature of the screw elevator is affected by factors such as material flow rate, material friction, ambient temperature, etc., and is a linear relationship. Then the following multivariate linear regression model can be established:
[0125] T=β0+β1·v+β2·F+β3·T env +∈
[0126] Where T is the predicted equipment temperature, v is the material flow rate, F is the material friction, T env is the ambient temperature, ∈ is the error term. In addition, β0 is the intercept term, which means that when all independent variables V, F, T env When both are 0, the predicted value of the dependent variable T, which usually reflects the baseline level of the model. β1 is the regression coefficient of the material flow rate V, which indicates the degree of influence of the flow rate on the equipment temperature T. The larger the value of β1, the more significant the influence of the flow rate on the temperature; β2 is the regression coefficient of the material friction force F, which quantifies the influence of the friction force on the equipment temperature T. If β2 is positive, an increase in friction will lead to an increase in temperature, and vice versa; β3 is the ambient temperature T env The regression coefficient represents the impact of ambient temperature changes on the device temperature T. A higher β3 value means that the ambient temperature has a greater impact on the device temperature.
[0127] For another example, assuming that the key features of the spiral elevator are the current speed, load, ambient temperature, material particle size, features of historical operation data, etc., and the preset optimization target is the speed and load of the spiral elevator, which are nonlinear relationships, then the above-mentioned deep learning model can be established: including the input layer, the first hidden layer, the second hidden layer, the third hidden layer and the output layer connected in sequence. Since there are 5 key features in this example, including the current speed (RPM), load (Load), ambient temperature (Temp), material particle size (Particle Size), features of historical operation data (such as the speed and temperature of the previous few hours, etc.); therefore, the dimension of the input layer is 5. The deep learning model is trained using the training method of the above steps S31 to S35 to obtain the equipment performance optimization model of the spiral elevator.
[0128] Through the trained equipment performance optimization model, the current screw elevator operation data can be input in real time to output the optimized optimal speed recommendation. This optimization parameter will help the screw elevator maintain the best performance under different working conditions, reduce the generation of friction heat, reduce energy consumption, and extend the service life of the screw elevator.
[0129] 150. While controlling each device to operate with its corresponding first operating parameter, obtain real-time operating data of each device.
[0130] The optimized first operating parameters are applied in actual production, and during operation, the real-time operating data of each device is monitored in real time to ensure that the device operates in the best operating state.
[0131] 160. When the real-time operating data of any device exceeds the preset abnormal warning threshold, it is determined to be an abnormal device and an alarm message is issued for the abnormal device.
[0132] The real-time operation data of the equipment is monitored by setting an abnormal warning threshold. The alarm message may be sent by pushing the alarm message to the bound mobile terminal through the mobile office communication service software so that the mobile terminal holder can find the abnormal warning in time.
[0133] As an optional implementation, after an alarm message is issued for an abnormal device, the corresponding response system of the abnormal device, such as a cooling system, a deceleration system, etc., can also be automatically enabled to ensure the safety of the equipment and materials. In addition, the real-time operating data of the abnormal device and the operating status of the response system are analyzed to obtain data analysis results. Among them, the data analysis results mainly include summarizing the optimization effect and the operating status of the response system to form a data analysis report. Specifically, after step 160, the following steps 161 to 162 (not shown) can be executed:
[0134] 161. Automatically activate the response system corresponding to abnormal equipment.
[0135] 162. Analyze the real-time operating data of abnormal equipment and the operating status of its response system to obtain data analysis results.
[0136] The real-time operation data of abnormal equipment and the operation status of the response system are analyzed, including but not limited to one or more of the following analysis methods:
[0137] Statistical analysis: Use descriptive statistical indicators (such as mean, median, standard deviation, variance) to summarize the real-time operation data of the equipment, compare the historical operation data and real-time operation data before and after optimization, and test the significance of the difference through statistical methods such as t-test or ANOVA;
[0138] Trend analysis: Use time series analysis methods (such as moving average and exponential smoothing) to observe the changing trend of data over time, identify trend change points, and evaluate the sustainability of optimization effects;
[0139] Correlation analysis: Pearson correlation coefficient or Spearman rank correlation coefficient is calculated to evaluate the linear or nonlinear correlation between the first operating parameter and the performance index;
[0140] Regression analysis: construct a multivariate regression model to quantify the impact of the first operating parameter on the performance index, and determine the key influencing factors through the significance test of the regression coefficient;
[0141] Fault analysis: Use Fault Tree Analysis (FTA) or Failure Mode and Effect Analysis (FMEA) methods to identify possible causes of failures, calculate the changes in failure rates before and after optimization, and evaluate the effectiveness of optimization measures.
[0142] Optionally, the operating parameters of the abnormal equipment and the control strategy of the response system can be further optimized according to the data analysis results to form a closed-loop optimization management. Specifically, after executing step 162, the following steps 163 to 164 (not shown) can be executed:
[0143] 163. According to the data analysis result, the first operating parameter of the abnormal device is optimized to obtain the second operating parameter.
[0144] 164. Control the abnormal device to operate with a second operating parameter.
[0145] Among them, the implementation method of step 163 is specifically as follows: extract key conclusions and suggestions from the data analysis results, determine the impact of the first operating parameter on the equipment performance and the optimization potential; determine the specific optimization goals (such as improving efficiency, reducing energy consumption, reducing failures, etc.) according to the data analysis results combined with actual production needs and quality standards; then, select a suitable optimization algorithm (such as genetic algorithm, ion group optimization, simulated annealing, etc.) to further optimize the first operating parameter and obtain the second operating parameter (including the set value of the key parameter, adjustment frequency and operation guidance). In the process of optimizing the first operating parameter of the abnormal equipment, the parameters are adjusted in combination with the production iteration, and gradually adjusted to the optimal solution as the second operating parameter.
[0146] Further optionally, after executing step 162, the following steps 165 to 166 (not shown) may be executed:
[0147] 165. Based on the data analysis results, generate control strategies for the response system of abnormal equipment.
[0148] 166. Control the response system of abnormal equipment according to the control strategy.
[0149] The control strategy for the system should adopt any one or more of the adaptive control strategy, predictive control strategy, optimal scheduling strategy and energy management strategy, among which:
[0150] Adaptive control strategy: implement equipment operating parameters and dynamically adjust parameter settings according to the current operating status and optimization goals; use feedback control systems to ensure that the equipment can maintain the optimal state under different operating conditions;
[0151] Predictive control strategy: Based on historical data and prediction models, adjust operating parameters in advance to avoid potential problems;
[0152] Optimize scheduling strategy: Based on the applause prediction model, take preventive measures in advance to avoid equipment failure;
[0153] Energy management strategy: Optimize energy consumption management, dynamically adjust equipment operating parameters and reduce energy consumption based on real-time energy consumption data and optimization goals.
[0154] Through the above implementation, the operating status of the equipment is detected in real time under the optimized first operating parameter condition, abnormal equipment is identified in time, and the control strategy of the response system of the abnormal equipment is updated to ensure that the response system can automatically adjust the operating parameters to maintain the optimal state. According to the results of real-time detection and data analysis, a continuous improvement and optimization cycle system is formed through feedback and adjustment, and closed-loop management can be achieved. This facilitates regular maintenance and inspection of the equipment, and continuously adjusts and optimizes the operating parameters and response system according to the actual operating conditions to ensure long-term stable operation of the equipment. According to the optimization results and operating experience of each device, the digital twin model of each device is updated to improve the accuracy and applicability of the model.
[0155] In summary, by implementing the embodiments of the present invention, by creating digital copies of physical objects and combining the data collected by sensors, functions such as virtual simulation, real-time monitoring, data analysis, and prediction and early warning are realized, thereby optimizing the production process, improving product quality, and ultimately achieving cost reduction and efficiency improvement. The collected real-time data can not only fully and in real time reflect the current status and future operating trends of the production line, but also warn and evaluate the risks that may arise in the equipment, and provide scientific and reasonable suggestions. Managers can respond and make decisions quickly based on these real-time feedbacks, effectively reduce equipment failures and downtime, and improve production efficiency and product quality.
[0156] In addition, the system also has intelligent decision-making support functions. Through in-depth analysis and mining of data, it helps managers optimize production processes, reduce operating costs, and realize intelligent and refined management of production lines. Overall, the application of this invention will significantly improve the timeliness and accuracy of production line monitoring and management, help managers make more scientific and reasonable decisions, and comprehensively enhance the competitiveness and market responsiveness of enterprises.
[0157] like Figure 2 As shown, the embodiment of the present invention discloses a cadmium telluride production line control device based on digital twin, including an acquisition unit 201, an establishment unit 202, a simulation unit 203, a first optimization unit 204, a monitoring unit 205, and an early warning unit 206, wherein:
[0158] An acquisition unit 201 is used to acquire historical operation data of each device on the cadmium telluride production line collected by a sensor;
[0159] An establishing unit 202 is used to establish a digital twin model of each device based on the historical operation data of each device;
[0160] The simulation unit 203 is used to use the digital twin model of each device to simulate the operating state of each device under different operating parameter conditions, and obtain the performance index of each device under different operating parameter conditions;
[0161] The first optimization unit 204 is used to optimize the constructed device performance optimization model of each device according to the performance index of each device under different operating parameter conditions, and obtain the optimal solution as the first operating parameter of each device;
[0162] The monitoring unit 205 is used to obtain real-time operation data of each device during the process of controlling each device to operate with the first operating parameters corresponding to each device;
[0163] The early warning unit 206 is used to determine any device as an abnormal device when the real-time operation data of the device exceeds a preset abnormal early warning threshold, and to issue an alarm message for the abnormal device.
[0164] As an optional implementation, the above device further includes the following units not shown in the figure:
[0165] A start-up unit, used to automatically start a response system corresponding to the abnormal device after the early warning unit issues an alarm message for the abnormal device;
[0166] The analysis unit is used to analyze the real-time operation data of the abnormal equipment and the operation status of its response system to obtain data analysis results.
[0167] As an optional implementation, the above device further includes the following units not shown in the figure:
[0168] A second optimization unit is used to optimize the first operating parameter of the abnormal device to obtain a second operating parameter according to the data analysis result after the analysis unit analyzes the real-time operating data of the abnormal device and the operating conditions of the response system to obtain the data analysis result;
[0169] The first control unit is used to control the abnormal device to operate with a second operating parameter.
[0170] As an optional implementation, the above device further includes the following units not shown in the figure:
[0171] A generating unit, configured to generate a control strategy for the response system of the abnormal device according to the data analysis result after the analyzing unit analyzes the real-time operation data of the abnormal device and the operation status of the response system thereof to obtain the data analysis result;
[0172] The second control unit is used to control the response system of the abnormal equipment according to the control strategy.
[0173] As an optional implementation, the establishment unit 202 includes the following subunits (not shown):
[0174] An extraction subunit, used to extract geometric features according to the CAD drawings of each device, and to extract design parameters according to the 3D design model of each device;
[0175] A first modeling subunit is used to establish a geometric model of the device according to geometric features and design parameters;
[0176] The processing subunit is used to clean the historical operation data of each device to obtain clean operation data;
[0177] The second modeling subunit is used to establish a digital twin model of each equipment based on the cleaning operation data by using multi-body dynamics and computational fluid dynamics.
[0178] like Figure 3 As shown, an embodiment of the present invention discloses an electronic device, including a memory 301 storing executable program codes and a processor 302 coupled to the memory 301;
[0179] Among them, the processor 302 calls the executable program code stored in the memory 301 to execute the cadmium telluride production line control method based on digital twin described in the above embodiments.
[0180] An embodiment of the present invention further discloses a computer-readable storage medium storing a computer program, wherein the computer program enables a computer to execute the cadmium telluride production line control method based on digital twin described in the above embodiments.
[0181] The purpose of the above embodiments is to exemplarily reproduce and deduce the technical solution of the present invention, and to fully describe the technical solution, purpose and effect of the present invention. Its purpose is to make the public understand the disclosed content of the present invention more thoroughly and comprehensively, and it does not limit the scope of protection of the present invention.
[0182] The above embodiments are not exhaustive enumerations of the present invention, and there may be multiple other implementations not listed. Any replacement and improvement made without violating the concept of the present invention shall fall within the protection scope of the present invention.
Claims
1. A cadmium telluride production line control method based on digital twin, characterized in that: include: Obtain the historical operation data of each device on the cadmium telluride production line collected by sensors; Build a digital twin model of each device based on its historical operating data; Use the digital twin model of each device to simulate the operating status of each device under different operating parameter conditions and obtain the performance indicators of each device under different operating parameter conditions; According to the performance indicators of each device under different operating parameter conditions, the constructed device performance optimization model of each device is optimized to obtain the optimal solution as the first operating parameter of each device; In the process of controlling each device to operate with the first operating parameter corresponding to each device, obtaining real-time operating data of each device; When the real-time operating data of any device exceeds the preset abnormal warning threshold, it is determined to be an abnormal device and an alarm message is issued for the abnormal device.
2. The cadmium telluride production line control method based on digital twin according to claim 1, characterized in that: After issuing an alarm message for the abnormal device, the method further includes: Automatically activate the response system corresponding to the abnormal device; The real-time operation data of the abnormal equipment and the operation status of its response system are analyzed to obtain data analysis results.
3. The cadmium telluride production line control method based on digital twin according to claim 2, characterized in that: Analyze the real-time operation data of the abnormal equipment and the operation status of the response system, and after obtaining the data analysis results, further include: According to the data analysis result, optimizing the first operating parameter of the abnormal device to obtain a second operating parameter; The abnormal device is controlled to operate with the second operating parameter.
4. The cadmium telluride production line control method based on digital twin according to claim 2, characterized in that: Analyze the real-time operation data of the abnormal equipment and the operation status of the response system, and after obtaining the data analysis results, further include: Generating a control strategy for a response system to the abnormal device according to the data analysis result; The response system of the abnormal device is controlled according to the control strategy.
5. The cadmium telluride production line control method based on digital twinning according to any one of claims 1 to 4, characterized in that: Based on the historical operation data of each device, a digital twin model of each device is established, including: Extract geometric features from the CAD drawings of each device, and extract design parameters from the 3D design models of each device; Establish the geometric model of the equipment according to the geometric features and design parameters; Clean the historical operation data of each device to obtain clean operation data; Using multi-body dynamics and computational fluid dynamics, a digital twin model of each device is established based on the cleaning operation data.
6. A cadmium telluride production line control device based on digital twin, characterized in that: include: An acquisition unit, used to acquire historical operation data of each device on the cadmium telluride production line collected by sensors; An establishment unit is used to establish a digital twin model of each device based on the historical operation data of each device; A simulation unit is used to use the digital twin model of each device to simulate the operating state of each device under different operating parameter conditions, and obtain the performance indicators of each device under different operating parameter conditions; A first optimization unit is used to optimize the constructed equipment performance optimization model of each equipment according to the performance index of each equipment under different operating parameter conditions, and obtain the optimal solution as the first operating parameter of each equipment; A monitoring unit, used to obtain real-time operation data of each device during the process of controlling each device to operate with the first operating parameter corresponding to each device; The early warning unit is used to determine any device as an abnormal device when the real-time operating data of the device exceeds a preset abnormal early warning threshold, and to send an alarm message to the abnormal device.
7. The digital twin-based cadmium telluride production line control device according to claim 6, characterized in that: Also includes: A starting unit, configured to automatically start a response system corresponding to the abnormal device after the early warning unit issues an alarm message for the abnormal device; The analysis unit is used to analyze the real-time operation data of the abnormal equipment and the operation status of its response system to obtain data analysis results.
8. The digital twin-based cadmium telluride production line control device according to claim 7, characterized in that: Also includes: a second optimization unit, configured to optimize the first operating parameter of the abnormal device to obtain a second operating parameter according to the data analysis result after the analysis unit analyzes the real-time operating data of the abnormal device and the operating conditions of the response system thereof to obtain a data analysis result; The first control unit is used to control the abnormal device to operate with the second operating parameter.
9. The digital twin-based cadmium telluride production line control device according to claim 7, characterized in that: Also includes: A generating unit, configured to generate a control strategy for the response system of the abnormal device according to the data analysis result after the analyzing unit analyzes the real-time operation data of the abnormal device and the operation status of the response system thereof to obtain the data analysis result; The second control unit is used to control the response system of the abnormal equipment according to the control strategy.
10. An electronic device, characterized in that: It includes a memory storing executable program code and a processor coupled to the memory; the processor calls the executable program code stored in the memory to execute the digital twin-based cadmium telluride production line control method according to any one of claims 1 to 5.
Citation Information
Patent Citations
Operation optimization method and system of digital twin factory
CN116880372A
Automatic production line operation monitoring system based on digital twinning technology
CN116894662A
Digital twin system parameter control method and system
CN117572771A
Cited By
Manufacturing unit innovation platform building method based on digital twin industrial robot
CN119328809A
Automatic control system and control method for producing lithium carbonate
CN120508059A
Porous biological ceramic artificial bone additive manufacturing method and system
CN120816583A
Filling machine parameter control method and device, electronic equipment and storage medium
CN122110681A
