Intelligent beam factory production simulation and optimization control system and method based on digital twinning

Abstract

The invention provides an intelligent beam factory production simulation and optimization control system and method based on digital twinning. A data collecting, analyzing and processing system is responsible for collecting, analyzing, processing and cleaning operation data of all process equipment in the whole production process of a high-speed precast beam; the digital twinning system constructs a whole-process digital twinning model of high-speed precast beam production based on operation data, and the simulation control system performs analogue simulation and testing on an actual production system based on the digital twinning model so as to optimize and enable the actual production process of the precast beam. Various possible production schemes are evaluated and compared before production, the optimal production scheduling plan is selected, the potential quality problem is solved, the product reject ratio is reduced, and the product quality and the customer satisfaction degree are improved. Based on the optimized production scheduling plan, the production process of the beam factory is monitored in real time, production tasks are adjusted and distributed, the equipment utilization rate is optimized, and the production cycle is shortened.

Description

Technical Field

[0001] The present invention belongs to the technical field of high-speed prefabricated beam factory manufacturing, and in particular relates to a production simulation and optimization control system and method for a smart beam factory based on digital twins. Background Art

[0002] In recent years, with the rapid development of infrastructure construction in my country, precast beams have been widely used in projects such as highways and bridges. Their production efficiency and quality have a significant impact on the progress and quality of highway construction. With the rapid development of technology, the concept of smart beam factories has emerged. However, in practice, it has been found that the precast beam production process, from raw material handling and equipment operation to production process monitoring, still requires a lot of manual intervention to ensure the smooth completion of each process. Product quality largely depends on the workers' experience in operating the equipment. Any operational errors will result in substandard quality of the corresponding precast beams.

[0003] Existing smart beam factories lack automated control systems and intelligent adjustment capabilities, resulting in poor integration between production processes. This can lead to problems such as delayed raw material supply and equipment failures requiring repair, extending production cycles and increasing costs. Furthermore, insufficient analysis and mining of production data prevents effective guidance for optimizing production processes and rationally allocating resources, impacting the overall efficiency of precast beam production. Summary of the Invention

[0004] In order to solve the problems existing in the prior art, the present invention aims to propose a production simulation and optimization control system and method for a smart beam factory based on digital twins, which solves the problem that the existing smart beam factory is insufficient in analysis and mining of production data, and is unable to optimize production processes and rationally allocate resources.

[0005] To achieve the above object, the technical solution of the present invention is achieved as follows: A digital twin-based intelligent beam plant production simulation and optimization control system, including: The data acquisition, analysis and processing system is used to collect, analyze, process and clean the operating data of each process equipment in the entire production process of the beam plant, and transmit the operating data to the digital twin system; Among them, the process equipment includes steel bar processing, steam curing and spraying, formwork vibration, concrete transportation and pouring, mobile trolley and tension grouting; A digital twin system, configured to construct a digital twin model of the beam plant and train the digital twin model based on the operating data; A simulation control system, including a simulation module and a control module. The simulation module uses a digital twin model to simulate the beam plant production process and formulate an optimized production scheduling plan; The control module is used to monitor the production process of the beam factory in real time based on the optimized production scheduling plan, and control and adjust the parameters of various process equipment.

[0006] Furthermore, the data acquisition, analysis and processing system includes an acquisition module, an analysis and processing module and a noise filtering module. The acquisition module is connected to the controller of each process equipment through a network, and the noise filtering module is used to clean the operation data; the analysis and processing unit is used to analyze and process the operation data and feed the results back to the digital twin system.

[0007] Furthermore, the analysis and processing module is divided into corresponding data analysis and processing units according to the device type, specifically including: Rebar processing data processing unit, used for order task data processing, production parameter control and issuance, production process monitoring and production result feedback; Steaming and spraying data processing unit, used for inputting production process parameters, controlling equipment start and stop, monitoring production process, and providing feedback on production results; The template vibration data processing unit is used for production plan task data processing, process parameter input, equipment start and stop control, production process monitoring and production result feedback; Concrete transportation and pouring data processing unit, used for production plan task data processing, process parameter input, equipment start and stop control, production process monitoring and production result feedback; The mobile trolley data processing unit is used for production process monitoring; The tensioning and grouting data processing unit is used for production process monitoring and result feedback.

[0008] Furthermore, the noise filtering module implements data cleaning through a dynamic threshold algorithm, the formula is:

[0009] in is the filtered data, t is the current time index, i is the sum index, x i is the original data value collected at the time of index i, n is the sliding window length, x t is the original data value collected at the current time t, is the window mean, is the window standard deviation, Dynamically adjust according to device status.

[0010] Furthermore, for rebar processing equipment, a dynamic threshold algorithm is used in combination with a process parameter mapping model for rebar processing equipment. The equipment calibration coefficient is optimized through historical data training to achieve accurate reverse inference and pre-compensation of the process parameters of rebar processing equipment. The process parameter mapping model is:

[0011] Where θ is the target process parameter, L is the length process parameter, d is the diameter process parameter, T is the temperature process parameter, K1 is the length calibration parameter, K2 is the diameter square calibration parameter, and K3 is the temperature calibration coefficient. is the systematic random error term.

[0012] Furthermore, when the data acquisition, analysis and processing system detects that the current signal fluctuation of the steel bar processing equipment exceeds 3 Automatically trigger Coefficient adjustment, adjustment step 0.1 ~ 0.5, signal-to-noise ratio D greater than or equal to 40%.

[0013] Furthermore, the simulation module establishes an objective function including production cycle, equipment waiting time, and equipment energy consumption, and solves the optimal production scheduling plan through a multi-objective optimization scheduling algorithm. The objective function is:

[0014] in For the production cycle, is the device waiting time, is the energy consumption of the equipment, is the production cycle weight coefficient, β is the waiting time weight coefficient, and γ is the energy consumption weight coefficient.

[0015] Furthermore, the control module integrates an adaptive PID control algorithm, combines fuzzy logic to dynamically adjust control parameters, and establishes a quality prediction neural network model to achieve real-time pre-control of the compressive strength of precast beams; The adaptive PID control algorithm formula is:

[0016] Where u(t) is the control output, e(t) is the real-time error, K p is the proportional gain coefficient, K i is the integral gain coefficient, is the error accumulation effect, K d is the differential gain coefficient, is the error change rate, is the fuzzy adaptive increment.

[0017] The quality prediction neural network model formula is:

[0018] Where X is the input feature vector, W1 is the weight of the input layer-hidden layer 1, b1 is the bias vector of the hidden layer 1, W2 is the weight of the hidden layer 2-hidden layer 2, b2 is the bias vector of the hidden layer 2, W3 is the weight of the hidden layer 2-output layer, b3 is the bias vector of the output layer, σ ( ) is the activation function, and f(X) is the predicted output result.

[0019] A digital twin-based intelligent beam plant production simulation and optimization control method includes: S1. Collect the operating data of each process equipment in the beam plant through the data acquisition, analysis and processing system, and classify, analyze and process the operating data and filter out noise; The operation data includes real-time production data, historical production data and historical configuration parameters, and the operation data types are divided into steel bar processing data, steaming data, spraying data, formwork vibration data, concrete transportation and pouring data, mobile trolley data and tensioning and grouting data; S2: Build a digital twin model of the beam factory through the digital twin system. The digital twin model is used to simulate the production process of the high-speed precast beam factory, and the digital twin model is trained based on the operating data obtained in S1. S3: Based on the digital twin model, the beam plant production process is simulated through the simulation module to simulate the effects and costs of different production plans, and an optimized production scheduling plan is formulated; S4: The control module remotely controls each process equipment and adjusts the production process according to the optimized production scheduling plan.

[0020] Furthermore, in S2, the digital twin model includes a physical model and a virtual model. The physical model is modeled based on the physical entity of the beam plant; the virtual model is modeled, simulated and optimized in a digital manner based on various characteristics of the physical model to create a virtual model.

[0021] Furthermore, a heat conduction dynamics equation was established for the temperature control of the steaming chamber of the steaming spray equipment, and the extended Kalman filter was used for state estimation to achieve a temperature control accuracy error of ≤±0.5°C. The heat conduction dynamics equation is:

[0022] Among them, T is the real-time temperature of the steaming chamber, is the temperature change rate, C is the heat melting in the steaming chamber, Q in Input heat power to the steaming chamber, Q out is the heat loss power, h is the surface convection heat transfer coefficient, A is the heat transfer surface area, T env is the external ambient temperature of the equipment; The extended Kalman filter formula is:

[0023] in The temperature of the steaming room is is the temperature value of the last acquisition period, Z t is the temperature sensor reading, K t is the Kalman gain matrix, H is the observation matrix, is the innovation residual.

[0024] Compared with the existing technology, the digital twin-based smart beam plant production simulation and optimization control system and method described in the present invention has the following advantages: Through data collection, analysis and processing, digital twin modeling, simulation optimization and precise control, the present invention effectively solves the problems of difficult product quality supervision and difficult production plan optimization in traditional precast beam production, improves production efficiency, reduces production costs, enhances the controllability and stability of the production process, and provides strong support for the intelligent production and management of precast beam factories.

[0025] The data acquisition, analysis and processing system collects, analyzes and processes the operating data of each process equipment in the entire production process of the beam plant in real time, and reflects the process parameters and equipment operating status in a timely and accurate manner, so that production management personnel can understand the production site situation in a timely manner and accurately control the production process, thereby improving production efficiency.

[0026] The simulation module uses a digital twin model to simulate the beam plant's production process. This allows for pre-production evaluation and comparison of various possible production options, selecting the optimal production schedule, addressing potential quality issues, reducing product defect rates, and improving product quality and customer satisfaction. Based on the optimized production schedule, the control module monitors the beam plant's production process in real time and remotely adjusts process equipment parameters, adjusting and allocating production tasks, optimizing equipment utilization, and shortening production cycles. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The accompanying drawings, which constitute part of the present invention, are provided to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are provided to explain the present invention and do not constitute an undue limitation of the present invention. In the accompanying drawings: Figure 1 The overall system architecture diagram provided by the embodiment of the present invention; Figure 2 This is a diagram of the architecture of each module in the system provided by an embodiment of the present invention; Figure 3 This is a diagram of the data acquisition, analysis, and processing system architecture provided by an embodiment of the present invention; Figure 4A floating window indicating the digital twin model steaming equipment provided in an embodiment of the present invention; Figure 5 A flow chart showing the control parameters of the steaming equipment control unit according to an embodiment of the present invention; Figure 6 The concrete placing boom equipment control unit Y-axis forward operation start-stop control process provided by the embodiment of the present invention; Figure 7 Flowchart of the algorithm of the adaptive noise filtering module provided by the embodiment of the present invention; Figure 8 A flowchart for solving the multi-objective optimization scheduling algorithm provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0028] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0029] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0030] like Figures 1 to 8 As shown in the figure, a digital twin-based intelligent beam plant production simulation and optimization control system includes: The data acquisition, analysis and processing system is used to collect, analyze, process and clean the operating data of each process equipment in the entire production process of the beam plant, and transmit the operating data to the digital twin system; The process equipment includes steel bar processing, steam curing and spraying, formwork vibration, concrete transportation and pouring, mobile trolley and tension grouting; A digital twin system, configured to construct a digital twin model of the beam plant and train the digital twin model based on the operating data; A simulation control system, comprising a simulation module and a control module, wherein the simulation module is used to simulate the production process of the beam plant using a digital twin model and formulate an optimized production scheduling plan; The control module is used to monitor the production process of the beam factory in real time based on the optimized production scheduling plan, and control and adjust the parameters of various process equipment.

[0031] In a preferred embodiment of the present invention, the data acquisition, analysis and processing system includes an acquisition module, an analysis and processing module and a noise filtering module. The acquisition module is connected to the controller of each process equipment through an industrial local area network, and the noise filtering module is used to clean the operation data; the analysis and processing module is provided with a corresponding data analysis and processing unit according to the operation data of each process equipment, and the data analysis and processing unit is used to analyze and process the operation data collected by the acquisition module, and feed the results back to the digital twin system.

[0032] In a preferred embodiment of the present invention, the analysis and processing module is divided into corresponding data analysis and processing units according to device type, specifically including: The steel bar processing data processing unit is responsible for processing order task data, controlling and issuing production parameters, monitoring the production process, and providing feedback on production results; The steaming and spraying data processing unit: production process parameter input, equipment start and stop control, production process monitoring and production result feedback; The template vibration data processing unit: production plan task data processing, process parameter input, equipment start and stop control, production process monitoring and production result feedback; The concrete transportation and pouring data processing unit is responsible for production plan task data processing, process parameter input, equipment start and stop control, production process monitoring, and production result feedback; The mobile trolley data processing unit: production process monitoring; The tensioning and grouting data processing unit: production process monitoring and result feedback.

[0033] By setting up a dedicated data processing unit for each device, it is possible to accurately process its specific data type and production needs, reduce data processing delays and errors, and enhance monitoring and feedback of the production process.

[0034] In a preferred embodiment of the present invention, the noise filtering module implements data cleaning through a dynamic threshold algorithm, and the formula is:

[0035] in is the filtered data, t is the current time index, i is the sum index, x i is the original data value collected at the time of index i, n is the sliding window length, x t is the original data value collected at the current time t, is the window mean, is the window standard deviation, Dynamically adjust according to device status.

[0036] The noise filtering module uses a dynamic threshold algorithm to clean the collected operating data, effectively removing noise and interference information in the data, improving the accuracy and reliability of the data, and enabling subsequent analysis and processing to be carried out in a purer data environment, thereby improving the overall performance of the system and the scientific nature of decision-making.

[0037] In a preferred embodiment of the present invention, a dynamic threshold algorithm is used to filter out industrial noise for rebar processing equipment. Combined with a process parameter mapping model for the rebar processing equipment, the equipment calibration coefficient is optimized through historical data training to achieve accurate inference and pre-compensation of the process parameters of the rebar processing equipment. The process parameter mapping model is:

[0038] Where θ is the target process parameter, L is the length process parameter, d is the diameter process parameter, T is the temperature process parameter, K1 is the length calibration parameter, K2 is the diameter square calibration parameter, and K3 is the temperature calibration coefficient. is the systematic random error term.

[0039] When the acquisition module detects that the current signal fluctuation of the steel bar processing equipment exceeds Automatically trigger The coefficient is adjusted with a step size of 0.1 to 0.5, which improves the signal-to-noise ratio by more than 40% and ensures the reliability of subsequent data analysis.

[0040] When equipment parameters shift due to long-term use or environmental changes, precise back-calculation and pre-compensation functions can be used to adjust parameters in a timely manner to restore the equipment to its optimal operating state, reducing the risk of equipment failure and production interruption.

[0041] In a preferred embodiment of the present invention, the digital twin system includes a visualization display unit for displaying and analyzing the data of the data analysis and processing system in the form of models, graphics, and charts, and developing a visualization display system so that users can intuitively understand the various data and status of the entire production process of the high-speed prefabricated beam factory, and promptly discover potential problems and regular change trends.

[0042] In a preferred embodiment of the present invention, the simulation module establishes an objective function including production cycle, equipment waiting time, and equipment energy consumption, and solves the optimal production scheduling plan through a multi-objective optimization scheduling algorithm (NSGA-II algorithm). The objective function is:

[0043] in For the production cycle, is the device waiting time, is the energy consumption of the equipment, is the production cycle weight coefficient, β is the waiting time weight coefficient, and γ is the energy consumption weight coefficient.

[0044] Goal to achieve: Minimize Improve production efficiency and minimize Improve equipment utilization and minimize Reduce energy costs.

[0045] In the actual application of a beam factory, 、 、 The algorithm converged after 200 iterations, achieving an 18% reduction in production cycle time (from 48 hours to 39.36 hours), a 22% reduction in energy consumption (from 120 kWh to 93.6 kWh per beam), and a 25% reduction in equipment waiting time, validating its engineering practicality. By simulating the effectiveness and costs of different production plans, it provides decision-makers with a scientific basis for developing optimized production scheduling plans, improving production efficiency and quality, and ultimately enhancing a company's competitiveness and market share.

[0046] In a preferred embodiment of the present invention, the control module integrates an adaptive PID control algorithm and dynamically adjusts the control parameters in combination with fuzzy logic to ensure the optimal match between the vibration equipment frequency and the slump of the concrete. At the same time, a quality prediction neural network model is established to achieve real-time pre-control of the compressive strength of the precast beam; The adaptive PID control algorithm formula is:

[0047] Where u(t) is the control output, e(t) is the real-time error, K p is the proportional gain coefficient, K i is the integral gain coefficient, is the error accumulation effect, K d is the differential gain coefficient, is the error change rate, is the fuzzy adaptive increment.

[0048] The quality prediction neural network model formula is: .

[0049] Where X is the input feature vector, W1 is the weight of the input layer-hidden layer 1, b1 is the bias vector of the hidden layer 1, W2 is the weight of the hidden layer 2-hidden layer 2, b2 is the bias vector of the hidden layer 2, W3 is the weight of the hidden layer 2-output layer, b3 is the bias vector of the output layer, σ ( ) is the activation function, and f(X) is the predicted output result.

[0050] The adaptive PID control algorithm automatically adjusts control parameters based on the system's real-time status. Combined with fuzzy logic, it can better handle system uncertainty and complexity, making control parameter adjustment more flexible and precise. The quality prediction neural network model, based on historical data and real-time monitoring data, establishes the inherent relationship between the compressive strength of precast beams and various process parameters through learning and training. During the production process, the compressive strength of precast beams can be predicted in real time, and production parameters can be adjusted accordingly, achieving real-time quality control.

[0051] In a preferred embodiment of the present invention, the control module is equipped with corresponding control units for each process equipment, specifically including a rebar processing equipment control unit, a steam curing and spraying equipment control unit, a formwork vibrating equipment control unit, a concrete transport and pouring equipment control unit, a mobile trolley data equipment control unit, and a tensioning and grouting data equipment control unit. The steam curing and spraying data equipment control unit includes a steam curing equipment control unit and a spraying equipment control unit, the formwork vibrating data equipment control unit includes a formwork equipment control unit and a vibrating equipment control unit, and the concrete transport and pouring equipment control unit includes a torpedo tank control unit and a concrete placing boom control unit.

[0052] The functions of the control unit of the steel bar processing equipment include: issuing equipment processing parameters, equipment start, stop and equipment emergency stop, etc. The functions of the control unit of steaming equipment and spraying equipment include: issuing equipment process parameters, equipment start and stop, etc. The functions of the template equipment control unit include: issuing equipment process parameters, oil pump startup, mold opening and closing state selection, one-button mold opening and closing control, and equipment emergency stop, etc. The functions of the vibration equipment control unit include: issuing equipment process parameters, single vibrator selection control, equipment start, stop and equipment emergency stop, etc. The functions of the torpedo tank control unit include: forward and reverse travel control of the equipment, one-button access to the loading position and one-button access to different unloading positions, etc. The functions of the concrete placing boom control unit include: issuing equipment process parameters, one-button placing control, X-axis and Y-axis forward and reverse travel control, and position selection control.

[0053] The production simulation and optimization control method of the smart beam factory based on digital twin includes: S1. The data acquisition, analysis, and processing system collects operational data from various process equipment in the beam plant, and classifies, analyzes, processes, and filters noise from the operational data. The operational data types are specifically classified into rebar processing data, steaming and spraying data, formwork vibration data, concrete transportation and pouring data, mobile trolley data, and tensioning and grouting data. S2: Build a digital twin model of the beam factory, which is used to simulate the production process of the high-speed precast beam factory and is trained based on the operating data obtained in S1; S3: Based on the digital twin model, the beam plant production process is simulated through the simulation module to simulate the effects and costs of different production plans and formulate an optimal production scheduling plan; S4: The control module interacts with each process equipment according to the optimal production scheduling plan to remotely control the production process.

[0054] In a preferred embodiment of the present invention, in S2, the digital twin model includes a physical model and a virtual model. The physical model is based on the physical entity of the beam factory, and models various factors such as various process equipment in the production workshop, high-speed box beams and the environment to construct a physical model; the virtual model is based on the various characteristics of the physical model (such as structure, performance, movement and state, etc.) in a digital way. Modeling, simulation and optimization are performed to create a virtual model to achieve comprehensive digital management of the production process of the high-speed prefabricated beam factory.

[0055] Based on the real-time production data, historical production data and historical configuration parameters of each process equipment, the digital twin of the entire production process of each high-speed precast beam is trained.

[0056] In a preferred embodiment of the present invention, in S2, the equipment dynamics state space equation is introduced when constructing the digital twin model, and a heat conduction dynamics equation is established for the temperature control of the steaming chamber of the steaming spray equipment. The extended Kalman filter is combined with state estimation to achieve a temperature control accuracy error of ≤±0.5°C; The heat conduction dynamics equation is:

[0057] Where T is the real-time temperature of the steaming chamber, is the temperature change rate, C is the heat melting in the steaming chamber, Q in Input heat power to the steaming chamber, Q out is the heat loss power, h is the surface convection heat transfer coefficient, A is the heat transfer surface area, T env is the external ambient temperature of the device.

[0058] The extended Kalman filter formula is: .

[0059] in The temperature of the steaming room is is the temperature value of the last acquisition period, Z t is the temperature sensor reading, K t is the Kalman gain matrix, H is the observation matrix, is the innovation residual.

[0060] Specifically, taking the steaming room as an example, the digital twin constructed based on the heat conduction dynamics equation uses the extended Kalman filter (EKF) algorithm to estimate the state of temperature data. In a continuous 72-hour test, the root mean square error (RMSE) between the predicted and measured temperature values ​​was 0.32°C, which is 60% higher than the accuracy of the traditional PID control solution. The specific parameters are as follows: heat capacity C = 1200kJ / °C, convection heat transfer coefficient h15 = W / (m^2·°C), heat dissipation area A = 80m 2 .

[0061] A floating label is set above each process equipment model to distinguish the equipment status by color, such as gray for stop, green for operation, and red for equipment failure, etc. Different status colors can also be added according to other needs.

[0062] Click on the floating label above the steaming room in the twin model to pop up Figure 4 The floating window shown includes key equipment status information such as the steaming room equipment number, operating status, temperature and humidity, and operating time.

[0063] The implementation process of the data acquisition, analysis and processing system: (1) System architecture deployment: A star-shaped data transmission industrial LAN is deployed in the production workshop and the digital twin center of the digital twin system, and an industrial wireless LAN is deployed within the operating range of some equipment. Specifically, the controllers of the steel bar processing equipment, steam curing and spraying equipment, formwork vibrating equipment, and mobile trolley equipment are all connected to the industrial LAN via network cables; the equipment controllers of the torpedo tank and concrete placing machine of the concrete transport and pouring equipment are all connected to the industrial LAN via wireless means; and the controller of the tensioning and grouting equipment is connected to the Internet via a 4G smart gateway.

[0064] (2) Establishing a communication connection: The digital twin center deploys a server and connects it to the industrial LAN. KepServer data acquisition software is installed on the server to provide an OPC server for the acquisition module. The OPC server and each process equipment controller use the Modbus TCP communication protocol. KepServer software configures channel, equipment and other parameters to establish real-time communication with each process equipment in the production workshop. Based on the data acquisition and control requirements of each process equipment, the communication address information table is determined, and the corresponding communication address information is configured for the equipment in KepServer software.

[0065] (3) Develop communication services: Configure the operating environment of the data acquisition, analysis, and processing service on the server, and deploy the developed and tested data acquisition, analysis, and processing service on the server. The data acquisition, analysis, and processing service uses the object-oriented programming language C# to develop an efficient OPC communication service, establish a connection with the OPC server of the KepServer software, and collect and subscribe to the operating data of each process equipment in the production process in real time.

[0066] The data acquisition, analysis and processing service is a software service used to perform specific data acquisition and processing tasks in the data acquisition, analysis and processing system.

[0067] The data acquisition, analysis and processing system collects equipment data such as steel bar processing, steaming and spraying, formwork vibration and concrete transportation and pouring through the ModbusTcp communication protocol; the tensioning and grouting equipment pushes the operating data to the data acquisition, analysis and processing system through the HTTP communication protocol.

[0068] (4) Data Storage: Deploy a MySql database and an IOTDB database on the server. Establish a configuration information table for each process equipment in the MySql database, recording the equipment name, equipment number, equipment communication information, and equipment communication address configuration. Real-time collected process equipment operation data is first recorded in the server memory as status information per second, and then periodically (the period configured in this embodiment is 5 minutes) stored in the IOTDB database. After storage is completed, the data records in the memory are cleared simultaneously.

[0069] (5) Alarm information: The data acquisition, analysis and processing service subscribes to the alarm information of each process equipment in real time through the OPC communication service, and stores the code, name, start time and end time of the alarm information in the MySql database.

[0070] (6) Periodically check the connection status: The data acquisition, analysis and processing service periodically checks the connection status with the OPC server of the KepServer software. If the connection is disconnected, it will automatically reconnect to ensure a persistent connection status.

[0071] (7) Data display and interface opening: The data acquisition, analysis and processing system opens a data interface for the centralized control interface by developing a RESTful-style HTTP request method program. The centralized control interface periodically accesses the data interface and captures the information of each production process equipment in the current interface for display, including the equipment's online / offline status, the feedback status of each equipment sensor, and the process parameters set by the equipment production.

[0072] The centralized control interface refers to the centralized control interface of the control module.

[0073] The control module, while ensuring safe equipment operation and controllable conditions, triggers the control address points of each process equipment one by one through the QC online monitoring interface of the KepServer data acquisition software. This module verifies the start / stop and parameter distribution control functions of each type of process equipment, as well as position selection, travel control, and other control functions for some equipment.

[0074] The control module is customized and developed for each control unit using a Restful-style HTTP request method program. Operator authority verification and control operation security passwords are added to the centralized control interface to ensure basic security. To ensure stable and reliable device control, an anti-accidental touch function is added to each operation button on the centralized control interface. A filter is added to the HTTP request interface of each control unit. The filter uniquely binds the server IP and MAC address of the control operation to ensure that remote control is performed on a unique server, thereby ensuring the control security of each control unit in the control system. Through on-site debugging and verification work, each control module unit is fully verified to ensure the normal, stable, and safe operation of the remote control module.

[0075] Take the control process of the steaming equipment control unit for example. Figure 5 As shown in the figure, in the centralized control interface, click the Edit button to modify the production process parameters of the steaming equipment, such as the heating temperature, heating time, and cooling time of each section. Then click the Send button. The control module receives the steaming equipment number and parameter information sent. The OPC service determines the device to which the parameters are sent based on the device number and sends the parameter information to the OPC server of KepServer. At the same time, it feeds back the parameter sending completion feedback to the centralized control interface. The OPC server writes the parameter information into the bound PLC (process equipment controller) variable to complete the parameter sending control.

[0076] Take the Y-axis forward operation start-stop control process of the concrete placing boom equipment control unit as an example. Figure 6 As shown, in this embodiment, the Y axis is the forward traveling direction of the trolley of the concrete placing boom.

[0077] In the centralized control interface, click the Y-axis forward movement button to send the device number and control command to the control module. The control module determines whether it is currently in remote control mode. If not, it directly reports a control failure to the centralized control interface. If it is in remote control mode, it again determines whether the concrete placing boom is in the start or stop state. If it is in the stop state, the control command is converted to a start command; if it is in the starting state, the control command is converted to a stop command. The OPC service determines the communication address of the controlled device based on the device number and control command type and sends it to the KepServer OPC server. At the same time, it reports a control success response to the centralized control interface. The OPC server writes the control command to the corresponding address of the PLC, completing the travel start and stop control of the concrete placing boom.

[0078] The control system has the control recording function of each control module, and can record the log of each control operation in real time in the MySql database.

[0079] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A digital twin-based intelligent beam plant production simulation and optimization control system, characterized by: include: The data acquisition, analysis and processing system is used to collect, analyze, process and clean the operating data of each process equipment in the entire production process of the beam plant, and transmit the operating data to the digital twin system; Among them, each process includes steel bar processing, steam curing and spraying, formwork vibration, concrete transportation and pouring, mobile trolley and tension grouting; A digital twin system, configured to construct a digital twin model of the beam plant and train the digital twin model based on the operating data; A simulation control system, including a simulation module and a control module. The simulation module uses a digital twin model to simulate the beam plant production process and formulate an optimized production scheduling plan; The control module is used to monitor the production process of the beam factory in real time based on the optimized production scheduling plan, and control and adjust the parameters of various process equipment.

2. The digital twin-based intelligent beam plant production simulation and optimization control system according to claim 1 is characterized by: The data acquisition, analysis and processing system includes an acquisition module, an analysis and processing module and a noise filtering module. The acquisition module is connected to the controller of each process equipment through a network. The noise filtering module is used to clean the operating data; the analysis and processing unit is used to analyze and process the operating data and feed the results back to the digital twin system.

3. The digital twin-based intelligent beam plant production simulation and optimization control system according to claim 2 is characterized by: The analysis and processing module is divided into corresponding data analysis and processing units according to the device type, specifically including: Rebar processing data processing unit, used for order task data processing, production parameter control and issuance, production process monitoring and production result feedback; Steaming and spraying data processing unit, used for inputting production process parameters, controlling equipment start and stop, monitoring production process, and providing feedback on production results; The template vibration data processing unit is used for production plan task data processing, process parameter input, equipment start and stop control, production process monitoring and production result feedback; Concrete transportation and pouring data processing unit, used for production plan task data processing, process parameter input, equipment start and stop control, production process monitoring and production result feedback; Mobile trolley data processing unit for production process monitoring; The tensioning and grouting data processing unit is used for production process monitoring and result feedback.

4. The digital twin-based intelligent beam plant production simulation and optimization control system according to claim 2 is characterized by: The noise filtering module implements data cleaning through a dynamic threshold algorithm, the formula is: in, is the filtered data, t is the current time index, i is the sum index, is the original data value collected at the moment of index i, n is the sliding window length, is the original data value collected at the current time t, is the window mean, is the window standard deviation, Dynamically adjust according to device status.

5. The digital twin-based intelligent beam plant production simulation and optimization control system according to claim 4 is characterized by: For rebar processing equipment, a dynamic threshold algorithm is used in combination with a process parameter mapping model for rebar processing equipment. The equipment calibration coefficient is optimized through historical data training to achieve accurate reverse inference and pre-compensation of the process parameters of rebar processing equipment. The process parameter mapping model is: Among them, θ is the target process parameter, L is the length process parameter, d is the diameter process parameter, T is the temperature process parameter, K1 is the length calibration parameter, K2 is the diameter square calibration parameter, and K3 is the temperature calibration coefficient. is the systematic random error term.

6. The digital twin-based intelligent beam plant production simulation and optimization control system according to claim 5 is characterized by: When the data acquisition, analysis and processing system detects that the current signal fluctuation of the steel bar processing equipment exceeds 3 Automatically trigger Coefficient adjustment, adjustment step 0.1 ~ 0.5, signal-to-noise ratio greater than or equal to 40%.

7. The digital twin-based intelligent beam plant production simulation and optimization control system according to claim 1 is characterized by: The beam plant simulation module establishes an objective function including production cycle, equipment waiting time, and equipment energy consumption, and solves the optimal production scheduling plan through a multi-objective optimization scheduling algorithm. The objective function is: in, For the production cycle, is the device waiting time, is the energy consumption of the equipment, is the production cycle weight coefficient, β is the waiting time weight coefficient, and γ is the energy consumption weight coefficient.

8. The digital twin-based intelligent beam plant production simulation and optimization control system according to claim 1 is characterized by: The control module integrates an adaptive PID control algorithm, combines fuzzy logic to dynamically adjust control parameters, and establishes a quality prediction neural network model to achieve real-time pre-control of the compressive strength of precast beams; The adaptive PID control algorithm formula is: Among them, u(t) is the control output, e(t) is the real-time error, K p is the proportional gain coefficient, K i is the integral gain coefficient, is the error accumulation effect, K d is the differential gain coefficient, is the error change rate, is the fuzzy adaptive increment; The quality prediction neural network model formula is: Where X is the input feature vector, W1 is the weight of the input layer-hidden layer 1, b1 is the bias vector of the hidden layer 1, W2 is the weight of the hidden layer 2-hidden layer 2, b2 is the bias vector of the hidden layer 2, W3 is the weight of the hidden layer 2-output layer, b3 is the bias vector of the output layer, σ ( ) is the activation function, and f(X) is the predicted output result.

9. A digital twin-based intelligent beam plant production simulation and optimization control method, characterized in that: include: S1. Collect the operating data of each process equipment in the beam plant through the data acquisition, analysis and processing system, and classify, analyze and process the operating data and filter out noise; The operating data includes real-time production data, historical production data and historical configuration parameters; S2: Build a digital twin model of the beam factory through the digital twin system. The digital twin model is used to simulate the production process of the high-speed precast beam factory, and the digital twin model is trained based on the operating data obtained in S1. S3: Based on the digital twin model, the beam plant production process is simulated through the simulation module to simulate the effects and costs of different production plans, and an optimized production scheduling plan is formulated; S4: The control module remotely controls each process equipment and adjusts the production process according to the optimized production scheduling plan.

10. The method for production simulation and optimization control of a smart beam plant based on digital twins according to claim 9 is characterized in that: In S2, the digital twin model includes a physical model and a virtual model. The physical model is modeled based on the physical entity of the beam plant; the virtual model is modeled, simulated and optimized in a digital way based on the various characteristics of the physical model to create a virtual model.

11. The method for production simulation and optimization control of a smart beam plant based on digital twins according to claim 10 is characterized in that: For the temperature control of the steaming chamber of the steaming spray equipment, a heat conduction dynamics equation is established, and the extended Kalman filter is used for state estimation to achieve a temperature control accuracy error of ≤±0.5℃; The heat conduction dynamics equation is: Among them, T is the real-time temperature of the steaming chamber, is the temperature change rate, C is the heat melting in the steaming chamber, Q in Input heat power to the steaming chamber, Q out is the heat loss power, h is the surface convection heat transfer coefficient, A is the heat transfer surface area, T env is the external ambient temperature of the equipment; The extended Kalman filter formula is: in, The temperature of the steaming room is is the temperature value of the last acquisition cycle, is the temperature sensor reading, K t is the Kalman gain matrix, H is the observation matrix, is the innovation residual.

Images