A production and processing system based on digital twin

Abstract

The present invention discloses a production and processing system based on digital twins, and relates to the field of digital twin technology. The system includes a data acquisition unit, a digital twin unit, and a data analysis and processing unit; the digital twin unit is used for simulation modeling to obtain a digital twin model of the production and processing system; the data acquisition unit is used for collecting equipment operating parameters of processing equipment in the system; the data analysis and processing unit is used for combining the equipment operating parameters of upstream and downstream processing equipment with the equipment operating parameters to obtain a parameter sequence when the equipment operating parameters continuously exceed the corresponding parameter threshold range, and the parameter sequence is used as an input to an anomaly detection model for operation to obtain an anomaly detection result; when the anomaly detection result indicates the existence of an anomaly, the corresponding equipment model in the digital twin model is rendered and displayed by the digital twin unit. The system disclosed by the present invention can avoid misdetection of equipment and ensure the accuracy of the state of the equipment model displayed in the digital twin model.

Description

Technical Field

[0001] The present invention belongs to the technical field of digital twins, and in particular relates to a production and processing system based on digital twins. Background Art

[0002] Digital twins make full use of physical models, sensor updates, operation history and other data, integrate multi-disciplinary, multi-physical quantity, multi-scale, and multi-probability simulation processes, complete mapping in virtual space, and thus reflect the entire life cycle of the corresponding physical equipment.

[0003] At present, digital twin technology is widely used in enterprise production and processing systems. It can determine whether there is an abnormality in the equipment in each system based on the equipment operating parameters of each physical device detected by sensors, and visualize it in the digital twin model of the production and processing system so that staff can promptly discover equipment failures in the production and processing system. However, in the production and processing system, there may be mutual influence between adjacent equipment. For example, the operating temperature of a processing equipment in a certain process or the vibration of the equipment during operation may affect the equipment parameters detected by the sensors of the equipment in the adjacent process, resulting in misjudgment.

[0004] Therefore, how to provide an effective solution to avoid misdetection of equipment in the digital twin production and processing system has become a difficult problem that needs to be solved urgently in the prior art. Summary of the invention

[0005] The purpose of the present invention is to provide a production and processing system based on digital twins to solve the above-mentioned problems existing in the prior art.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a production and processing system based on digital twins, comprising: a plurality of data acquisition units, a digital twin unit, and a data analysis and processing unit;

[0008] The digital twin unit is used to simulate and model the physical equipment of the production and processing system, obtain a digital twin model of the production and processing system, and visualize the digital twin model;

[0009] The multiple data acquisition units are respectively used to collect equipment operating parameters of multiple processing equipment in the production and processing system;

[0010] The data analysis and processing unit is used for combining the equipment operating parameters of the upstream and downstream processing equipments whose processing procedures are adjacent to the processing procedures of the any processing equipment with the equipment operating parameters of the any processing equipment to obtain a parameter sequence corresponding to the any processing equipment when the equipment operating parameters of any processing equipment continuously exceed the parameter threshold range corresponding to the any processing equipment;

[0011] Using the parameter sequence corresponding to any one of the processing equipment as the input of the anomaly detection model corresponding to any one of the processing equipment to perform calculations to obtain an anomaly detection result of any one of the processing equipment; and

[0012] When the abnormality detection result of any of the processing equipment indicates that any of the processing equipment is abnormal, an abnormality prompt message is sent to the digital twin unit, so that the digital twin unit renders and displays the device model corresponding to any of the processing equipment in the digital twin model;

[0013] Among them, the anomaly detection model corresponding to any processing equipment is trained by combining the historical equipment operating parameters of the upstream and downstream processing equipment whose processing procedures are adjacent to the processing procedures of any processing equipment with the historical equipment operating parameters of any processing equipment to obtain a historical parameter sequence as sample input, and the historical anomaly discrimination results of any processing equipment and the same period as the historical equipment operating parameters as sample output.

[0014] Based on the above disclosed content, the present invention sets up multiple data acquisition units, digital twin units and data analysis and processing units; the digital twin unit is used to simulate and model the physical equipment of the production and processing system, obtain the digital twin model of the production and processing system, and visualize the digital twin model; multiple data acquisition units are respectively used to collect equipment operating parameters of multiple processing equipment in the production and processing system; the data analysis and processing unit is used to combine the equipment operating parameters of upstream and downstream processing equipment adjacent to the processing process of any processing equipment with the equipment operating parameters of any processing equipment when the equipment operating parameters of any processing equipment continuously exceed the parameter threshold range corresponding to any processing equipment, so as to obtain a parameter sequence corresponding to any processing equipment; the parameter sequence corresponding to any processing equipment is used as the input of the anomaly detection model corresponding to any processing equipment for calculation, so as to obtain the anomaly detection result of any processing equipment; and when the anomaly detection result of any processing equipment indicates that any processing equipment has an anomaly, an abnormal prompt information is sent to the digital twin unit, so that the digital twin unit renders and displays the equipment model corresponding to any processing equipment in the digital twin model. In this way, when determining whether there is an abnormality in the processing equipment in the production and processing system, in addition to considering the equipment operating parameters of the processing equipment, the influence of the processing process and the upstream and downstream processing equipment adjacent to the processing process is also considered to avoid misdetection of equipment in the digital twin production and processing system, prevent misjudgment, and ensure the accuracy of the status of the equipment model displayed in the digital twin model.

[0015] In a possible design, the digital twin-based production and processing system further includes an image acquisition unit, which is used to acquire an image of an area where a physical device of the production and processing system is located;

[0016] The data analysis and processing unit is further used to perform person recognition and entity device recognition on the image, and after recognizing the person and the entity device, determine the coordinates of the recognized person and the entity device in the pixel coordinate system;

[0017] Determine the target coordinates in the digital twin model corresponding to the pixel coordinates of the identified person based on the coordinates of the identified person in the pixel coordinate system, the coordinates of the physical device in the pixel coordinate system, the coordinates of the physical device in the digital twin model, and the conversion relationship between the pixel coordinates and the coordinates in the digital twin model; and

[0018] Add a character model at the target coordinates in the digital twin model.

[0019] In a possible design, the data analysis and processing unit is also used to perform face recognition on the identified person after identifying the person, obtain the person information of the identified person, and annotate the person model with annotation information, wherein the annotation information includes the person information.

[0020] In a possible design, when the data analysis and processing unit is used to perform face recognition on a recognized person and obtain the person information of the recognized person, it is specifically used to:

[0021] Extracting the facial image of the person to be identified;

[0022] Identify key points in the face image, wherein the key points include left eye key points, right eye key points and lip key points;

[0023] Scaling the face image so that the size of a rectangular area determined based on the left eye key point, the right eye key point and the lip key point reaches a first preset size, wherein the left eye key point and the right eye key point are located at two end points of a side of the rectangular area, and the lip key point is located on the opposite side of the side where the left eye key point and the right eye key point are located in the rectangular area;

[0024] Taking the center point of the rectangular area as the center, extracting a rectangular image of a second preset size from the face image to obtain a partial face image;

[0025] Extracting the LBP feature value of each pixel in the partial face image to obtain an LBP feature gradient map of the partial face image of the identified person;

[0026] The LBP feature gradient map of the partial face image of the person to be identified is compared with the LBP feature gradient maps of partial face images of multiple users with known person information acquired in advance, and the person information of the person to be identified is determined based on the comparison result.

[0027] In a possible design, the data analysis and processing unit is also used to filter the partial face image.

[0028] In one possible design, the digital twin unit is used to simulate and model the physical device according to material parameters and geometric parameters of the physical device to obtain the digital twin model.

[0029] In a possible design, the multiple data acquisition units include a temperature sensor, a speed sensor, a vibration sensor and / or a rotation speed sensor.

[0030] In one possible design, the anomaly detection model is a convolutional neural network model.

[0031] In a second aspect, the present invention provides a method for detecting an abnormality of an equipment, which is applied to a production and processing system based on a digital twin. The production and processing system based on a digital twin includes a plurality of data acquisition units, a digital twin unit, and a data analysis and processing unit. The method for detecting an abnormality of an equipment includes:

[0032] The physical equipment of the production and processing system is simulated and modeled by the digital twin unit to obtain a digital twin model of the production and processing system, and the digital twin model is visually displayed;

[0033] The equipment operation parameters of multiple processing equipment in the production and processing system are collected respectively by multiple data collection units;

[0034] When the equipment operation parameters of any processing equipment continuously exceed the parameter threshold range corresponding to the any processing equipment, the equipment operation parameters of the upstream and downstream processing equipment whose processing procedures are adjacent to the processing procedure of the any processing equipment are combined with the equipment operation parameters of the any processing equipment through the data analysis processing unit to obtain a parameter sequence corresponding to the any processing equipment; and

[0035] Using the parameter sequence corresponding to any one of the processing equipment as the input of the anomaly detection model corresponding to any one of the processing equipment to perform calculations to obtain an anomaly detection result of any one of the processing equipment;

[0036] When the abnormality detection result of any of the processing equipment indicates that any of the processing equipment is abnormal, an abnormality prompt information is sent to the digital twin unit through the data analysis and processing unit, so that the digital twin unit renders and displays the device model corresponding to any of the processing equipment in the digital twin model;

[0037] Among them, the anomaly detection model corresponding to any processing equipment is trained by combining the historical equipment operating parameters of the upstream and downstream processing equipment whose processing procedures are adjacent to the processing procedures of any processing equipment with the historical equipment operating parameters of any processing equipment to obtain a historical parameter sequence as sample input, and the historical anomaly discrimination results of any processing equipment and the same period as the historical equipment operating parameters as sample output.

[0038] In a possible design, the multiple data acquisition units include a temperature sensor, a speed sensor, a vibration sensor and / or a rotation speed sensor.

[0039] Beneficial effects:

[0040] The digital twin-based production and processing system provided by the present application, when determining whether there is an abnormality in the processing equipment in the production and processing system, not only considers the equipment operating parameters of the processing equipment, but also considers the influence of the processing procedure and the upstream and downstream processing equipment adjacent to the processing procedure, so as to avoid misdetection of equipment in the digital twin production and processing system, prevent misjudgment, and ensure the accuracy of the status of the equipment model displayed in the digital twin model. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1A schematic block diagram of a production and processing system based on digital twins provided in an embodiment of the present application;

[0042] Figure 2 A flowchart of a device anomaly detection method provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in combination with the drawings and the description of the embodiments or the prior art. Obviously, the following description of the structure of the drawings is only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention.

[0044] It should be understood that although the terms first, second, etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another unit. For example, a first unit can be referred to as a second unit, and similarly, a second unit can be referred to as a first unit without departing from the scope of the exemplary embodiments of the present invention.

[0045] It should be understood that the term "and / or" that may appear in this article is merely a description of the association relationship between associated objects, indicating that three relationships may exist. For example, A and / or B can represent three situations: A exists alone, B exists alone, and A and B exist at the same time. The term " / and" that may appear in this article describes another type of association object relationship, indicating that two relationships may exist. For example, A / and B can represent two situations: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this article generally indicates that the previous and next associated objects are in an "or" relationship.

[0046] like Figure 1 As shown, the first aspect of an embodiment of the present application provides a production and processing system based on digital twins, which includes multiple data acquisition units, digital twin units and data analysis and processing units, and the data analysis and processing units are respectively communicated with the multiple data acquisition units and the digital twin units.

[0047] The digital twin unit is used to simulate and model the physical equipment of the production and processing system. Specifically, the digital twin unit can simulate and model the physical equipment according to the material parameters and geometric parameters (such as length, width, height, etc.) of the physical equipment to obtain a digital twin model of the production and processing system.

[0048] The multiple data acquisition units are used to respectively acquire the equipment operation parameters of the multiple processing equipment in the production and processing system, and the multiple data acquisition units may include, but are not limited to, temperature sensors, speed sensors, vibration sensors and / or rotation speed sensors, etc. The equipment operation parameters of the multiple processing equipment may include, but are not limited to, parameters such as temperature, speed, vibration amplitude and / or rotation speed.

[0049] The data analysis and processing unit is used to combine the equipment operating parameters of the upstream and downstream processing equipment adjacent to the processing process of any processing equipment with the equipment operating parameters of any processing equipment when the equipment operating parameters of any processing equipment continue to exceed the parameter threshold range corresponding to any processing equipment, so as to obtain a parameter sequence corresponding to any processing equipment.

[0050] Among them, the parameter threshold range corresponding to any processing equipment may refer to the parameter range when any processing equipment works normally alone. In the process of production and processing through the production and processing system, the processing procedures of multiple processing equipment are different. For example, in the process of production and processing of a certain equipment, processing equipment A needs to perform processing procedure A1 first, then processing equipment B performs processing procedure B1, then processing equipment C performs processing procedure C1, and finally processing equipment D performs processing procedure D1. Then processing procedure B1 is the downstream processing procedure of processing procedure A1, and it is also the upstream processing procedure of processing procedure C1. Processing equipment B is the downstream processing equipment whose processing procedure is adjacent to processing procedure A1 of processing equipment A, and processing equipment B is also the upstream processing equipment whose processing procedure is adjacent to processing procedure C1 of processing equipment C.

[0051] The data analysis and processing unit is also used to use the parameter sequence corresponding to any processing equipment as the input of the anomaly detection model corresponding to any processing equipment to perform operations, and obtain the anomaly detection result of any processing equipment. In the embodiment of the present application, an anomaly detection model for processing equipment anomaly detection is pre-trained, and the anomaly detection model corresponding to any processing equipment can be a historical parameter sequence obtained by combining the historical equipment operating parameters of upstream and downstream processing equipment whose processing procedures are adjacent to the processing procedures of any processing equipment with the historical equipment operating parameters of any processing equipment as sample input, and the historical anomaly discrimination results of any processing equipment that are concurrent with the historical equipment operating parameters as sample output for training.

[0052] The anomaly detection model may be, but is not limited to, a convolutional neural network (CNN) model or a recurrent neural network (RNN) model, which is not specifically limited in the embodiments of the present application.

[0053] The data analysis and processing unit is also used to send abnormal prompt information to the digital twin unit when the abnormal detection result of any processing equipment indicates that any processing equipment has an abnormality, so that the digital twin unit can render and display the device model corresponding to any processing equipment in the digital twin model, for example, the device model corresponding to any processing equipment can be rendered into a specified color for display. In this way, it is convenient for relevant staff to promptly discover the abnormality of the processing equipment through the digital twin model, so as to take corresponding measures in time to ensure the normal operation of the production and processing system.

[0054] See also Figure 1 The digital twin-based production and processing system also includes an image acquisition unit, which is communicatively connected to the data analysis and processing unit. The image acquisition unit can be a monitoring camera and can obtain images of the area where the physical equipment of the production and processing system is located.

[0055] The data analysis and processing unit is also used to perform person identification and entity device identification on the image, and after identifying the person and the entity device, determine the coordinates of the identified person and the entity device in the pixel coordinate system; based on the coordinates of the identified person in the pixel coordinate system, the coordinates of the entity device in the pixel coordinate system, the coordinates of the entity device in the digital twin model, and the conversion relationship between the pixel coordinates and the coordinates in the digital twin model, determine the target coordinates in the digital twin model corresponding to the pixel coordinates of the identified person; and add a person model at the target coordinates in the digital twin model.

[0056] In one or more embodiments, the data analysis and processing unit is further used to perform face recognition on the identified person after identifying the person, obtain the person information of the identified person, and annotate the person model with annotation information, the annotation information includes person information, and the person information may be but is not limited to the person name, work number and / or contact number, etc. In this way, the person located in the area where the production and processing system is located can be identified based on the person information annotated on the person model in the digital twin model, so that when the processing equipment in the production and processing system is abnormal, the on-site personnel can be contacted in time for viewing and confirmation.

[0057] In one or more embodiments, the data analysis and processing unit performs face recognition on the identified person to obtain the person information of the identified person, which may include but is not limited to the following steps S101-S106.

[0058] Step S101: Extract the facial image of the person to be identified

[0059] Step S102: Identify key points in the face image.

[0060] Among them, the key points in the face image include the left eye key point, the right eye key point and the lip key point.

[0061] Step S103: scaling the face image so that the size of the rectangular area determined based on the left eye key point, the right eye key point and the lip key point reaches a first preset size.

[0062] Among them, the first preset size can be set according to actual conditions, the left eye key point and the right eye key point are located at the two end points of an edge of the rectangular area, and the lip key point is located on the opposite side of the edge where the left eye key point and the right eye key point are located in the rectangular area.

[0063] Step S104: extracting a rectangular image of a second preset size from the face image with the center point of the rectangular area as the center, to obtain a partial face image.

[0064] The second preset size can be set according to actual conditions.

[0065] The face image is scaled so that the size of the rectangular area determined based on the left eye key point, the right eye key point and the lip key point reaches a first preset size, and then a rectangular image of a second preset size is extracted from the face image with the center point of the rectangular area as the center to obtain a partial face image. In this way, the position and size of the face area corresponding to the partial face image extracted each time can be kept consistent, thereby ensuring the accuracy of subsequent face recognition.

[0066] In one or more embodiments, filtering processing may also be performed on the partial face image.

[0067] Step S105: extract the LBP feature value of each pixel in the partial face image to obtain the LBP feature gradient map of the partial face image of the identified person.

[0068] Step S106. Compare the LBP feature gradient map of the partial face image of the identified person with the LBP feature gradient maps of the partial face images of multiple users with known character information acquired in advance, and determine the character information of the identified person based on the comparison result.

[0069] In an embodiment of the present application, the known person information corresponding to the LBP feature gradient map (of the partial face image of a user with known person information) that has the highest similarity with the LBP feature gradient map of the partial face image of the identified person and whose similarity is higher than a preset threshold can be used as the person information of the identified person.

[0070] The digital twin-based production and processing system provided by the present invention is provided with multiple data acquisition units, digital twin units and data analysis and processing units; the digital twin unit is used to simulate and model the physical equipment of the production and processing system, obtain the digital twin model of the production and processing system, and visualize the digital twin model; the multiple data acquisition units are respectively used to collect the equipment operating parameters of multiple processing equipment in the production and processing system; the data analysis and processing unit is used to combine the equipment operating parameters of the upstream and downstream processing equipment adjacent to the processing procedure of any processing equipment with the equipment operating parameters of any processing equipment when the equipment operating parameters of any processing equipment continuously exceed the parameter threshold range corresponding to any processing equipment, so as to obtain a parameter sequence corresponding to any processing equipment; the parameter sequence corresponding to any processing equipment is used as the input of the anomaly detection model corresponding to any processing equipment for calculation, so as to obtain the anomaly detection result of any processing equipment; and when the anomaly detection result of any processing equipment indicates that any processing equipment has an anomaly, an abnormal prompt information is sent to the digital twin unit, so that the digital twin unit renders and displays the equipment model corresponding to any processing equipment in the digital twin model. In this way, when determining whether the processing equipment in the production and processing system is abnormal, in addition to considering the equipment operating parameters of the processing equipment, the influence of the processing process and the upstream and downstream processing equipment adjacent to the processing process is also considered to avoid the misdetection of the equipment in the production and processing system of the digital twin, prevent the occurrence of misjudgment, and ensure the accuracy of the state of the equipment model displayed in the digital twin model. At the same time, character recognition and face recognition can be performed, and a character model can be added to the digital twin model and the character model can be annotated with annotation information. In this way, the personnel located in the area where the production and processing system is located can be identified according to the information annotated on the character model in the digital twin model, so that when the processing equipment in the production and processing system is abnormal, the on-site personnel can be contacted in time for viewing and confirmation. In addition, when recognizing faces, the face image is scaled so that the size of the rectangular area determined based on the left eye key point, the right eye key point and the lip key point reaches the first preset size, and then the rectangular image of the second preset size is extracted from the face image with the center point of the rectangular area as the center to obtain a partial face image, so that the position and size of the face area corresponding to each partial face image extracted can be kept consistent, thereby ensuring the accuracy of subsequent face recognition.

[0071] See also Figure 2 The second aspect of the present application embodiment provides a device abnormality detection method, which is applied to Figure 1 In the digital twin-based production and processing system shown, the equipment abnormality detection method may include but is not limited to the following steps S201-S205.

[0072] Step S201. Use the digital twin unit to simulate and model the physical equipment of the production and processing system to obtain a digital twin model of the production and processing system, and visualize the digital twin model.

[0073] Step S202: using a plurality of data acquisition units to respectively acquire equipment operating parameters of a plurality of processing equipment in the production and processing system.

[0074] The multiple data acquisition units may include, but are not limited to, a temperature sensor, a speed sensor, a vibration sensor and / or a rotation speed sensor.

[0075] Step S203. When the equipment operating parameters of any processing equipment continue to exceed the parameter threshold range corresponding to any processing equipment, the equipment operating parameters of the upstream and downstream processing equipment whose processing procedures are adjacent to the processing procedures of any processing equipment are combined with the equipment operating parameters of any processing equipment through the data analysis and processing unit to obtain a parameter sequence corresponding to any processing equipment.

[0076] Step S204. Taking the parameter sequence corresponding to any processing equipment as the input of the anomaly detection model corresponding to any processing equipment to perform calculations, and obtaining an anomaly detection result of any processing equipment;

[0077] Step S205. When the abnormal detection result of any processing equipment indicates that any processing equipment has an abnormality, an abnormal prompt information is sent to the digital twin unit through the data analysis and processing unit, so that the digital twin unit renders and displays the device model corresponding to any processing equipment in the digital twin model.

[0078] Among them, the anomaly detection model corresponding to any processing equipment is trained by combining the historical equipment operating parameters of the upstream and downstream processing equipment whose processing procedures are adjacent to the processing procedures of any processing equipment with the historical equipment operating parameters of any processing equipment to obtain a historical parameter sequence as sample input, and the historical anomaly discrimination results of any processing equipment and the same period as the historical equipment operating parameters as sample output.

[0079] The working process, working details and technical effects of the method provided in the second aspect of this embodiment can be found in the first aspect of the embodiment and will not be described in detail here.

[0080] Finally, it should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the protection scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A production and processing system based on digital twins, characterized in that: include: Multiple data acquisition units, digital twin units, and data analysis and processing units; The digital twin unit is used to simulate and model the physical equipment of the production and processing system, obtain a digital twin model of the production and processing system, and visualize the digital twin model; The multiple data acquisition units are respectively used to collect equipment operating parameters of multiple processing equipment in the production and processing system; The data analysis and processing unit is used for combining the equipment operating parameters of the upstream and downstream processing equipments whose processing procedures are adjacent to the processing procedures of the any processing equipment with the equipment operating parameters of the any processing equipment to obtain a parameter sequence corresponding to the any processing equipment when the equipment operating parameters of any processing equipment continuously exceed the parameter threshold range corresponding to the any processing equipment; Using the parameter sequence corresponding to any one of the processing equipment as the input of the anomaly detection model corresponding to any one of the processing equipment to perform calculations to obtain an anomaly detection result of any one of the processing equipment; as well as When the abnormality detection result of any of the processing equipment indicates that any of the processing equipment is abnormal, an abnormality prompt message is sent to the digital twin unit, so that the digital twin unit renders and displays the device model corresponding to any of the processing equipment in the digital twin model; Among them, the anomaly detection model corresponding to any processing equipment is trained by combining the historical equipment operating parameters of the upstream and downstream processing equipment whose processing procedures are adjacent to the processing procedures of any processing equipment with the historical equipment operating parameters of any processing equipment to obtain a historical parameter sequence as sample input, and the historical anomaly discrimination results of any processing equipment and the same period as the historical equipment operating parameters as sample output.

2. The production and processing system based on digital twin according to claim 1 is characterized in that: It also includes an image acquisition unit, which is used to acquire images of the area where the physical equipment of the production and processing system is located; The data analysis and processing unit is further used to perform person recognition and entity device recognition on the image, and after recognizing the person and the entity device, determine the coordinates of the recognized person and the entity device in the pixel coordinate system; Determine the target coordinates in the digital twin model corresponding to the pixel coordinates of the identified person based on the coordinates of the identified person in the pixel coordinate system, the coordinates of the physical device in the pixel coordinate system, the coordinates of the physical device in the digital twin model, and the conversion relationship between the pixel coordinates and the coordinates in the digital twin model; as well as Add a character model at the target coordinates in the digital twin model.

3. The production and processing system based on digital twin according to claim 2 is characterized in that: The data analysis and processing unit is also used to perform face recognition on the identified person after identifying the person, obtain the person information of the identified person, and annotate the person model with annotation information, wherein the annotation information includes the person information.

4. The production and processing system based on digital twin according to claim 3 is characterized in that: When the data analysis and processing unit is used to perform face recognition on a person to be identified and obtain person information of the person to be identified, it is specifically used to: Extracting the facial image of the person to be identified; Identify key points in the face image, wherein the key points include left eye key points, right eye key points and lip key points; Scaling the face image so that the size of a rectangular area determined based on the left eye key point, the right eye key point and the lip key point reaches a first preset size, wherein the left eye key point and the right eye key point are located at two end points of a side of the rectangular area, and the lip key point is located on the opposite side of the side where the left eye key point and the right eye key point are located in the rectangular area; Taking the center point of the rectangular area as the center, extracting a rectangular image of a second preset size from the face image to obtain a partial face image; Extracting the LBP feature value of each pixel in the partial face image to obtain an LBP feature gradient map of the partial face image of the identified person; The LBP feature gradient map of the partial face image of the person to be identified is compared with the LBP feature gradient maps of partial face images of multiple users with known person information acquired in advance, and the person information of the person to be identified is determined based on the comparison result.

5. The production and processing system based on digital twin according to claim 4 is characterized in that: The data analysis and processing unit is also used to filter the partial face image.

6. The production and processing system based on digital twin according to claim 1 is characterized in that: The digital twin unit is used to simulate and model the physical device according to the material parameters and geometric parameters of the physical device to obtain the digital twin model.

7. The production and processing system based on digital twin according to claim 1 is characterized in that: The multiple data acquisition units include a temperature sensor, a speed sensor, a vibration sensor and / or a rotation speed sensor.

8. The production and processing system based on digital twin according to claim 1, characterized in that: The anomaly detection model is a convolutional neural network model.

9. A method for detecting equipment anomalies, applied to a production and processing system based on digital twins, wherein the production and processing system based on digital twins comprises a plurality of data acquisition units, a digital twin unit and a data analysis and processing unit, characterized in that: The device abnormality detection method comprises: The physical equipment of the production and processing system is simulated and modeled by the digital twin unit to obtain a digital twin model of the production and processing system, and the digital twin model is visually displayed; The equipment operation parameters of multiple processing equipment in the production and processing system are collected respectively by multiple data collection units; When the equipment operation parameters of any processing equipment continuously exceed the parameter threshold range corresponding to the any processing equipment, the equipment operation parameters of the upstream and downstream processing equipment whose processing procedures are adjacent to the processing procedure of the any processing equipment are combined with the equipment operation parameters of the any processing equipment through the data analysis processing unit to obtain a parameter sequence corresponding to the any processing equipment; and Using the parameter sequence corresponding to any one of the processing equipment as the input of the anomaly detection model corresponding to any one of the processing equipment to perform calculations to obtain an anomaly detection result of any one of the processing equipment; When the abnormality detection result of any of the processing equipment indicates that any of the processing equipment is abnormal, an abnormality prompt information is sent to the digital twin unit through the data analysis and processing unit, so that the digital twin unit renders and displays the device model corresponding to any of the processing equipment in the digital twin model; Among them, the anomaly detection model corresponding to any processing equipment is trained by combining the historical equipment operating parameters of the upstream and downstream processing equipment whose processing procedures are adjacent to the processing procedures of any processing equipment with the historical equipment operating parameters of any processing equipment to obtain a historical parameter sequence as sample input, and the historical anomaly discrimination results of any processing equipment and the same period as the historical equipment operating parameters as sample output.

10. The device abnormality detection method according to claim 9, characterized in that: The multiple data acquisition units include a temperature sensor, a speed sensor, a vibration sensor and / or a rotation speed sensor.

Images