Cotton digital processing system and method based on digital twinning

Abstract

The invention discloses a cotton digital processing system and method based on digital twinning, and relates to the field of digital twinning and cotton processing.In the system, a physical entity layer collects equipment operation parameters and cotton quality data of all physical equipment in the cotton processing link; the virtual-real mapping layer obtains equipment operation parameters and cotton quality data and uploads the equipment operation parameters and the cotton quality data to the service application layer, and a digital twinborn model is driven according to the equipment operation parameters; the service application layer is used for determining the optimal operation parameter of each physical device based on the cotton quality parameter, determining a consistency evaluation result based on the device operation parameter and the optimal operation parameter of each physical device, and determining an instruction according to the optimal operation parameter of each physical device when the consistency is inconsistent; performing visual display on the digital twin model driven by the equipment operation parameters; and the physical entity layer is also used for controlling each physical device to work according to the instruction. The intelligent level of cotton processing can be improved, resource loss is reduced, and the cotton quality is guaranteed.

Description

Technical Field

[0001] This application relates to the field of digital twins and cotton processing, and in particular to a digital cotton processing system and method based on digital twins. Background Technology

[0002] Currently, although cotton processing equipment has achieved a high degree of mechanization in the cotton processing industry, the coverage of related digital processing equipment is insufficient and the standards are not uniform. The lack of safety also affects the overall efficiency of cotton processing management and control. There is an urgent need for a mature and usable digital cotton processing system. Summary of the Invention

[0003] The purpose of this application is to provide a cotton digital processing system and method based on digital twins, forming a digital solution covering the entire life cycle of cotton processing, and providing innovative technical support for improving the intelligence level of cotton processing, reducing resource consumption, and ensuring cotton quality.

[0004] To achieve the above objectives, this application provides the following solution: In the first aspect, this application provides a cotton digital processing system based on digital twins, including a physical entity layer, a virtual-physical mapping layer and a service application layer; The physical entity layer is used to: collect equipment operating parameters and cotton quality data of various physical devices in the cotton processing process; The virtual-real mapping layer is used to: acquire the equipment operating parameters and the cotton quality data, and upload them to the service application layer; drive the digital twin model based on the equipment operating parameters; The service application layer is used to: determine the optimal operating parameters of each physical device based on the cotton quality parameters; determine the consistency evaluation result based on the device operating parameters and the optimal operating parameters of each physical device; when the consistency evaluation result is inconsistent, determine the instruction based on the optimal operating parameters of each physical device; and visualize the digital twin model driven by the device operating parameters. The physical entity layer is also used to: receive instructions issued by the service application layer, and control each physical device to work according to the instructions.

[0005] Secondly, this application provides a cotton digital processing method based on digital twins, including: The equipment operation parameters and cotton quality data of various physical devices in the cotton processing process are collected through the physical entity layer. The device operating parameters and cotton quality data are obtained through the virtual-real mapping layer and uploaded to the service application layer; The digital twin model is driven by the virtual-real mapping layer based on the device operating parameters; The service application layer determines the optimal operating parameters of each physical device based on the cotton quality parameters, and determines the consistency evaluation result based on the device operating parameters and the optimal operating parameters of each physical device; when the consistency evaluation result is inconsistent, an instruction is determined based on the optimal operating parameters of each physical device; and the digital twin model driven by the device operating parameters is visualized. The physical entity layer controls the operation of each physical device according to the instructions.

[0006] According to the specific embodiments provided in this application, the following technical effects are disclosed: This application collects equipment operating parameters and cotton quality data of various physical devices in the cotton processing stage through the physical entity layer, and then uploads them to the service application layer through the virtual-physical mapping layer. Simultaneously, the virtual-physical mapping layer drives a digital twin model based on the equipment operating parameters, realizing the virtual model of the cotton processing process and the virtual-physical mapping of the physical entities. Finally, at the service application layer, the optimal operating parameters of each physical device are determined based on the cotton quality parameters, and a consistency evaluation result is determined based on the equipment operating parameters and the optimal operating parameters of each physical device. When the consistency evaluation results are inconsistent, instructions are determined based on the optimal operating parameters of each physical device. Thus, this application integrates multi-source data such as equipment operating parameters and cotton quality data, and visualizes the digital twin model driven by the equipment operating parameters, supporting real-time monitoring and interactive operation of the entire processing process. The physical entity layer then receives instructions from the service application layer and controls each physical device to operate according to the instructions, achieving intuitive control of the cotton processing process and significantly improving production transparency and management efficiency.

[0007] Furthermore, by making intelligent decisions at the service application layer, using digital twin models to achieve dynamic optimization and control of processing parameters, predictive maintenance of equipment status, and real-time collection of equipment operation data through sensor technology, combined with cotton processing quality prediction models to continuously optimize processing technology, a digital solution covering the entire life cycle of cotton processing is formed, providing innovative technical support for improving the level of intelligence and digitalization of cotton processing, reducing resource consumption, and ensuring cotton quality. Attached Figure Description

[0008] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0009] Figure 1 This is a schematic diagram of a cotton digital processing system based on digital twins in one embodiment of this application.

[0010] Figure 2 This is a schematic diagram of the cotton processing steps corresponding to the physical equipment group for cotton processing.

[0011] Figure 3 This is a schematic diagram of a cotton digital processing method based on digital twins in one embodiment of this application. Detailed Implementation

[0012] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0013] This application combines digital twin technology to achieve full lifecycle management of various equipment in the cotton processing production line, realizes the digital and information-based upgrade of the cotton processing production line, and effectively avoids economic losses caused by sudden equipment failures through predictive maintenance. It has the characteristics of high timeliness, high level of digitalization, simple operation, high security, short time, and traceable historical data.

[0014] To make the above-mentioned objectives, features and advantages of this application more apparent and understandable, the application will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0015] In one exemplary embodiment, such as Figure 1 As shown, a digital cotton processing system based on digital twins is provided, including a physical entity layer, a virtual-physical mapping layer, and a service application layer.

[0016] The physical entity layer is used to collect equipment operating parameters and cotton quality data from various physical devices in the cotton processing stage. Specifically, for example... Figure 1 As shown, the physical entity layer includes a cotton processing physical equipment group, data acquisition equipment, and a control system.

[0017] Among them, such as Figure 2 As shown, the cotton processing physical equipment group includes an automatic cotton bale opening and feeding device, a seed cotton heavy and impurity separator, a seed cotton foreign fiber separator, a seed cotton online monitoring system, a seed cotton drying tower, a seed cotton cleaning machine, a cotton gin, a lint cleaning machine, a lint online monitoring system, a cotton collector, a lint baler, and an automatic bundling machine.

[0018] The data acquisition device is used to collect the equipment operating parameters and cotton quality data of each physical device in the cotton processing equipment group during the cotton processing stage. The cotton quality data includes the seed cotton quality before seed cotton cleaning and the lint cotton quality after lint cotton cleaning, which are obtained through the seed cotton online monitoring system and the lint cotton online monitoring system, respectively. The data acquisition device includes a speed sensor, an electric field sensor, a voltage sensor, a current sensor, a power meter, a temperature sensor, a humidity sensor, a moisture regain sensor, an tilt sensor, a torque sensor, a displacement sensor, a pressure sensor, a cotton flow sensor, a high-speed camera, and a PLC.

[0019] The physical equipment in the cotton processing equipment group includes: Automatic cotton bale opening and feeding equipment collects pressure and speed data via pressure and speed sensors; the seed cotton heavy and impurity separator collects speed data via a speed sensor; the seed cotton foreign fiber separator collects torque, electric field, and speed data via torque, electric field, and speed sensors; the seed cotton drying tower collects internal temperature, humidity, and seed cotton moisture regain data via temperature, humidity, and moisture regain sensors; the seed cotton cleaning machine collects tilt angle, torque, displacement, voltage, and current data via tilt angle, torque, displacement, voltage, and current sensors; the cotton gin collects speed, voltage, and current data via speed, voltage, and current sensors; the lint baling machine collects pressure and speed data via pressure and speed sensors; the automatic baling machine collects pressure and speed data via pressure and speed sensors; and voltage, current, and power meters collect data on the total electrical energy consumed and power generated during production.

[0020] The control system is used to receive instructions issued by the service application layer and control each physical device in the cotton processing physical equipment group to work according to the instructions.

[0021] The virtual-real mapping layer is used to: acquire the equipment operating parameters and the cotton quality data, and upload them to the service application layer; drive the digital twin model based on the equipment operating parameters; specifically, as follows: Figure 1 As shown, the virtual-real mapping layer includes a data transmission module, a data analysis module, a twin model module, and a data storage module.

[0022] The data transmission module is used to: acquire the equipment operating parameters and cotton quality data, and upload them to the service application layer; that is, to transmit relevant parameters collected by the data acquisition device from the physical device to the host computer, and to transmit cotton-related quality data detected by the seed cotton online monitoring system and the lint cotton online monitoring system. The data analysis module is used to: preprocess the equipment operating parameters. The data storage module is used to: store the preprocessed equipment operating parameters. The digital twin model module is used to: drive the digital twin model based on the preprocessed equipment operating parameters; the equipment configuration of the digital twin model is consistent with the equipment configuration in the physical entity layer, and the digital twin model performs virtual-real mapping of each physical device in the cotton processing stage in virtual space.

[0023] The service application layer is used to: determine the optimal operating parameters of each physical device based on the cotton quality parameters; determine the consistency evaluation result based on the device operating parameters and the optimal operating parameters of each physical device; when the consistency evaluation result is inconsistent, determine the instruction based on the optimal operating parameters of each physical device; and visualize the digital twin model driven by the device operating parameters.

[0024] Specifically, such as Figure 1 As shown, the service application layer is either a PC terminal or a mobile terminal of the digital platform. In other words, the service application layer exists simultaneously on both the PC and mobile terminals in the form of a digital platform, thereby monitoring the operating status of each piece of equipment in the cotton processing process and the quality of cotton at each stage in real time, and performing intelligent control.

[0025] The physical entity layer is also used to: receive instructions issued by the service application layer, and control each physical device to work according to the instructions.

[0026] Based on the same inventive concept, this application also provides a method for implementing the system described above. The solution provided by this method is similar to the implementation scheme described in the system above; therefore, the specific limitations in one or more method embodiments provided below can be found in the system limitations above, and will not be repeated here.

[0027] In one exemplary embodiment, a digital cotton processing method based on digital twins is provided, including the following steps 100-500: Step 100 involves collecting equipment operating parameters and cotton quality data from various physical devices in the cotton processing stage through the physical entity layer. Specifically, after the cotton processing production line starts, the data acquisition devices in the physical entity layer begin collecting the equipment operating parameters of each physical device to obtain the real-time operating status of each device. As cotton begins processing on the production line, the quality of seed cotton before seed cotton cleaning and the quality of lint cotton after lint cotton cleaning are acquired in real time. These two parameters are detected by two physical devices: the seed cotton online monitoring system and the lint cotton online monitoring system.

[0028] Step 200: Obtain the device operating parameters and cotton quality data through the virtual-real mapping layer, and upload them to the service application layer. Specifically, data transmission is implemented through the data transmission module in the virtual-real mapping layer.

[0029] Step 300: Drive the digital twin model through the virtual-real mapping layer based on the device operating parameters.

[0030] Step 400: The service application layer determines the optimal operating parameters of each physical device based on the cotton quality parameters, and determines the consistency evaluation result based on the device operating parameters and the optimal operating parameters of each physical device; when the consistency evaluation result indicates inconsistency, an instruction is determined based on the optimal operating parameters of each physical device; and the digital twin model driven by the device operating parameters is visualized.

[0031] In a practical application, within the service application layer, determining the optimal operating parameters for each physical device based on the cotton quality parameters includes: constructing a cotton processing quality prediction model; wherein the cotton processing quality prediction model is a BP neural network model; and inputting the cotton quality parameters into the cotton processing quality prediction model to obtain the optimal operating parameters for each physical device. The optimal operating parameters include information such as the optimal power of the corresponding physical device (e.g., seed cotton cleaner, ginning machine, lint cleaner, drying tower, etc.).

[0032] Specifically, firstly, code was written in C# to read and retrieve seed cotton quality data and lint quality data, obtaining the quality of seed cotton before cleaning and the quality of lint after cleaning. Then, code for a cotton processing quality prediction model was written in Python. Next, the acquired seed cotton and lint quality data were input into the cotton processing quality prediction model, and the optimal operating parameters for the seed cotton cleaner and lint cleaner were calculated to obtain an optimal adjustment plan. Finally, a visualization interface was written in C# to visualize the calculated optimal adjustment plan in real time.

[0033] In a practical application, within the service application layer, determining the consistency evaluation result based on the device operating parameters and the optimal operating parameters of each physical device includes: obtaining the device operating parameters and the optimal operating parameters of each physical device; constructing a parameter prediction-actual comparison evaluation model; the parameter prediction-actual comparison evaluation model is a Siamese neural network model; inputting the device operating parameters and the optimal operating parameters of each physical device into the parameter prediction-actual comparison evaluation model to obtain a 0-1 value, which serves as the consistency evaluation result; wherein, a 0 value indicates that the consistency evaluation result is consistent, and a 1 value indicates that the consistency evaluation result is inconsistent.

[0034] The operating parameters of the equipment and the optimal operating parameters of each physical device are not one-dimensional data, but multi-dimensional data. Taking the operating parameters of a cotton cleaning machine as an example, these include the speed of the spiked roller, the gap between the grid strips, the inclination angle of the cleaning section, the data acquisition time, and the internal temperature and humidity of the equipment. A parameter prediction-actual comparison evaluation model can calculate the similarity between the equipment operating parameters and the optimal operating parameters of each physical device, thereby determining whether the two are consistent. If they are inconsistent, a process recommendation window can pop up, providing equipment parameter adjustment schemes and issuing adjustment commands to the control system.

[0035] Specifically, firstly, C# code was used to obtain the data collected by each sensor in the data acquisition module and the final optimal adjustment scheme of the cotton processing quality prediction model. Then, Python code was used to write the parameter prediction-actual comparison and evaluation model code. Next, the equipment operating parameters and the predicted optimal adjustment scheme data were input into the model. If an error occurred, the model output 1; if no error occurred, the model output 0. Finally, when the model outputs 1, its predicted optimal adjustment scheme was sent to the control system, and the control system adjusted the equipment operating parameters.

[0036] In another practical application, the method further includes fault prediction through the service application layer, specifically including the following steps: constructing a fault dataset based on extensive experiments and the practical experience of factory workers; training a convolutional neural network model using the fault dataset to obtain a fault prediction model (the principle is: comparing the fault dataset with the real-time operating parameters of the actual equipment; if the actual operating parameters of a certain equipment are the same or similar to those in the fault database, it will output which part of which equipment is faulty); inputting the equipment operating parameters into the fault prediction model to obtain equipment fault information, which can provide detailed information on which specific part is faulty; visualizing the equipment fault information in the digital twin model, and displaying a pop-up window accompanied by a warning sound when displaying the equipment fault information.

[0037] Specifically, the first step is to quantify the faults occurring in each piece of equipment on the cotton processing production line and predict the trends of these faults. Then, C# code is used to acquire data from various sensors in the data acquisition module. Next, Python code is used to write the fault prediction model. Afterward, the acquired data from each sensor is input into the fault prediction model to predict the specific faults of each piece of equipment. Finally, a visual pop-up window accompanied by an audible warning is created using C# to visually alert the user to the predicted equipment faults.

[0038] Step 500: The physical entity layer controls each physical device to operate according to the instructions. Specifically, the control system in the physical entity layer controls the movement of each physical device.

[0039] In practical applications, the method further includes: visually displaying the equipment operating parameters of each physical device, the cotton quality data, the optimal operating parameters of each device, and the instructions in the digital twin model through the service application layer. Specifically, on-site personnel in the cotton processing workshop can log in to the cotton processing digital platform via mobile devices to observe the relevant cotton quality, abnormal equipment status, and equipment parameter adjustment plans in real time; off-site operators can log in to the cotton processing digital platform via PC to monitor the internal operating status, historical operating data, and current workshop conditions of each device in the entire cotton production line in real time.

[0040] As an optional implementation method, such as Figure 3 As shown, the method of this application includes the following steps: After the cotton processing production line is started, the data acquisition equipment begins to collect data to obtain the real-time operating status of each physical device, and cotton processing begins; the quality of seed cotton before seed cotton cleaning and the quality of lint cotton after lint cleaning are obtained, and the optimal operating parameters of each physical device are calculated using a cotton processing quality prediction model; at the same time, equipment failures are predicted through a fault prediction model, and a fault warning window pops up; after obtaining the optimal operating parameters of each physical device, the predicted equipment operating parameters are evaluated against the actual equipment operating parameters using an operating parameter prediction-actual comparison evaluation model; if they are consistent, subsequent processing continues without adjustment; if they are inconsistent, an equipment parameter adjustment plan is provided, and an adjustment command is sent to the control system; the control system receives the adjustment command and begins to execute the corresponding equipment adjustment; the mobile terminal logs into the cotton processing digital platform to observe the relevant cotton quality, abnormal equipment status, and equipment parameter adjustment plan in real time; the PC terminal logs into the cotton processing digital platform to monitor the internal operating status, historical operating data, and current status of each device in the entire cotton production line in real time.

[0041] In summary, this application utilizes a digital twin-based cotton digital processing system to achieve real-time display of seed cotton and lint quality, status monitoring of various equipment, alarm prompts for equipment anomalies, planning of equipment adjustment strategies, and intelligent control. By employing a fault prediction model, the system monitors equipment operating status in real time, predicts equipment faults, and displays a fault warning window on the cotton processing digital platform.

[0042] Compared with existing technologies, this application has the following advantages: (1) A digital twin model of the entire cotton processing process is constructed using digital twin technology to achieve real-time data interaction and dynamic mapping between the physical production line and the twin model. Compared with the existing processing mode, its advantage lies in the modular architecture that supports multi-dimensional visualization monitoring of process parameters, equipment status and cotton quality. Users can intuitively control the processing process through the digital cotton processing platform, which significantly improves production transparency and management efficiency.

[0043] (2) Based on the parameter prediction-actual comparison evaluation model, this application can dynamically optimize and control the operating parameters of each piece of equipment and realize predictive maintenance of equipment failure. Compared with the traditional method that relies on experience judgment, this system uses digital twin technology and machine learning to mine the correlation between process parameters and cotton quality, automatically generate the best processing plan, and reduce resource waste and quality fluctuations caused by human intervention.

[0044] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0045] This document uses specific examples to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the methods and core ideas of this application. Furthermore, those skilled in the art will recognize that, based on the ideas of this application, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. A cotton digital processing system based on digital twinning, characterized in that, The system comprises a physical entity layer, a virtual-real mapping layer and a service application layer; The physical entity layer is configured to collect device operation parameters and cotton quality data of each physical device in the cotton processing link; The virtual-real mapping layer is configured to obtain the device operation parameters and the cotton quality data, and upload them to the service application layer; and drive a digital twin model according to the device operation parameters; The service application layer is configured to determine optimal operation parameters of each physical device based on the cotton quality parameters, determine a consistency evaluation result based on the device operation parameters and the optimal operation parameters of each physical device, determine an instruction according to the optimal operation parameters of each physical device when the consistency evaluation result represents inconsistency, and visually display the digital twin model driven by the device operation parameters; The physical entity layer is further configured to receive the instruction issued by the service application layer, and control each physical device to work according to the instruction.

2. The digital twin-based cotton digital processing system according to claim 1, wherein, The physical entity layer comprises a cotton processing physical device group, a data acquisition device and a control system; The cotton processing physical device group comprises cotton bale automatic opening and feeding equipment, seed cotton heavy impurity separation equipment, seed cotton foreign fiber separation equipment, a seed cotton online monitoring system, a seed cotton drying tower, a seed cotton cleaning machine, a gin, a lint cleaning machine, a lint online monitoring system, a cotton collector, a lint packer and an automatic bale packing machine; The data acquisition device is configured to collect device operation parameters and cotton quality data of each physical device in the cotton processing link in the cotton processing physical device group; the cotton quality data comprises seed cotton quality before seed cotton cleaning and lint quality after lint cleaning, and is obtained by the seed cotton online monitoring system and the lint online monitoring system, respectively; The control system is configured to receive the instruction issued by the service application layer, and control each physical device in the cotton processing physical device group to work according to the instruction.

3. The digital twin-based cotton digital processing system of claim 1, wherein, The virtual-real mapping layer comprises a data transmission module, a data analysis module, a twin model module and a data storage module; The data transmission module is configured to obtain the device operation parameters and the cotton quality data, and upload them to the service application layer; The data analysis module is configured to pre-process the device operation parameters; The data storage module is configured to store the pre-processed device operation parameters; The twin model module is configured to drive a digital twin model according to the pre-processed device operation parameters; the device composition of the digital twin model is consistent with that of the physical entity layer.

4. The digital-twin-based cotton digital processing system of claim 1, wherein, The service application layer is a digital platform PC end or a digital platform mobile end.

5. The digital twin-based cotton digital processing system of claim 2, wherein, The data acquisition device comprises a rotational speed sensor, an electric field sensor, a voltage sensor, a current sensor, a power meter, a temperature sensor, a humidity sensor, a moisture regain sensor, an inclination sensor, a torque sensor, a displacement sensor, a pressure sensor, a cotton flow sensor, a high-speed camera and a PLC.

6. A cotton digital processing method based on digital twinning, characterized in that, The method comprises: collecting device operation parameters and cotton quality data of each physical device in the cotton processing link through a physical entity layer; The device operation parameters and the cotton quality data are acquired through the virtual-real mapping layer and uploaded to the service application layer; The digital twin model is driven according to the device operation parameters through the virtual-real mapping layer; The optimal operation parameters of each physical device are determined based on the cotton quality parameters through the service application layer, the consistency evaluation result is determined based on the device operation parameters and the optimal operation parameters of each physical device, and when the consistency evaluation result represents inconsistency, the instruction is determined according to the optimal operation parameters of each physical device; the digital twin model driven by the device operation parameters is visually displayed; Each physical device is controlled to work according to the instruction through the physical entity layer.

7. The cotton digital processing method based on digital twinning according to claim 6, wherein, The method further comprises fault prediction through the service application layer, specifically including the following steps: A fault data set is constructed; The convolutional neural network model is trained using the fault data set to obtain a fault prediction model; The device operation parameters are input into the fault prediction model to obtain device fault information; The device fault information is visually displayed in the digital twin model, and a pop-up window is displayed when the device fault information is displayed, accompanied by a warning sound.

8. The cotton digital processing method based on digital twinning according to claim 6, wherein, In the service application layer, the optimal operation parameters of each physical device are determined based on the cotton quality parameters, including: A cotton processing quality prediction model is constructed; wherein the cotton processing quality prediction model is a BP neural network model; The cotton quality parameters are input into the cotton processing quality prediction model to obtain the optimal operation parameters of each physical device.

9. The cotton digital processing method based on digital twinning according to claim 6, wherein, In the service application layer, the consistency evaluation result is determined based on the device operation parameters and the optimal operation parameters of each physical device, including: The device operation parameters and the optimal operation parameters of each physical device are obtained; A parameter prediction-actual comparison evaluation model is constructed; the parameter prediction-actual comparison evaluation model is a twin neural network model; The device operation parameters and the optimal operation parameters of each physical device are input into the parameter prediction-actual comparison evaluation model to obtain a 0-1 value as the consistency evaluation result; wherein 0 value represents consistent consistency evaluation result, and 1 value represents inconsistent consistency evaluation result.

10. The cotton digital processing method based on digital twinning according to claim 6, wherein, The method further comprises: Through the service application layer, the device operation parameters of each physical device, the cotton quality data, the optimal operation parameters of each device and the instruction are visually displayed in the digital twin model.

Images