CN-116151086-B - Hammer mill digital twin body construction method based on multidimensional fusion modeling

CN116151086BCN 116151086 BCN116151086 BCN 116151086BCN-116151086-B

Abstract

The invention provides a method for constructing a digital twin body of a hammer mill based on multi-dimensional fusion modeling, which comprises the steps of constructing a multi-dimensional model of the hammer mill; the multi-dimensional model comprises a geometric model, a physical model, a behavior model, a mechanism model and a data model, and the multi-dimensional model is fused to construct a digital twin body of the hammer mill. The structural attribute, the key physical quantity in the operation process, the raw material particle crushing process, the mapping relation of the key physical quantity and the equipment health index and the change rule of the crushing granularity in the production process of the hammer mill are respectively described by constructing a geometric model, a physical model, a behavior model, a mechanism model and a data model of the hammer mill, so that the performance and the crushing granularity of the mill are obtained on line in real time, and further, an important basis is provided for keeping the stable operation of the mill and the stability of the crushing granularity.

Inventors

LIN HAILONG
WANG MENG
WANG KAI
LIU XINYING
GAO LEI
ZHANG ZHILING
FAN XINLONG
SUN CHANGZHENG
ZHOU GUANGHUI
LIU JINSONG
ZHANG CHAO
TIAN XIAOJUN
WEI ZHIBO
DENG LIKANG
LIU XIAOFENG
SHAO YUBIN

Assignees

国投生物科技投资有限公司
西安交通大学
国投生物能源(铁岭)有限公司

Dates

Publication Date: 20260508
Application Date: 20211116

Claims (10)

1. The utility model provides a hammer mill digital twin body construction method based on multidimensional fusion modeling, which is characterized in that the method comprises the following steps: Constructing a multi-dimensional model of the hammer mill, wherein the multi-dimensional model comprises a geometric model, a physical model, a behavior model, a mechanism model and a data model; fusing the multidimensional models to construct a digital twin body of the hammer mill; the behavior model comprises a motion rule of raw materials in a crushing chamber and a deformation rule of the raw materials in the crushing chamber, and is established by the following method: Analyzing historical data based on the crushing granularity under different influencing factors, and carrying out normalization processing on each factor; carrying out importance sorting on all the factors after normalization processing, and taking the factor of the first six of the importance sorting as the factor influencing the crushing granularity; simulation analysis is carried out on factors influencing the crushing granularity through multi-body dynamics simulation software, so that a motion rule of the raw materials in a crushing chamber is obtained; And carrying out simulation analysis on factors influencing the crushing granularity by finite element analysis software to obtain the deformation rule of the raw material in the crushing chamber.
2. The method for constructing a digital twin body of a hammer mill based on multi-dimensional fusion modeling according to claim 1, wherein the method for constructing the digital twin body of the hammer mill by fusing the multi-dimensional models comprises the following steps: Loading a geometric model as a basis of the digital twin; The method comprises the steps of designing a data acquisition module, acquiring key physical quantities of the hammer mill and relating the key physical quantities to the geometric model by accessing a real-time data interface provided by the physical model; designing a behavior analysis module, integrating the behavior model into the digital twin body through data analysis and visualization software; and designing a data analysis module, adopting a visual chart library to perform the mechanism model and the data model to be curved and embedded into the digital twin body to obtain the digital twin body of the hammer mill.
3. The method for constructing a digital twin body of a hammer mill based on multi-dimensional fusion modeling according to claim 1, wherein the geometric model is constructed by the following method: Structural properties of the hammer mill are defined, formally as follows: ; ; Wherein: Representing a geometric model of the hammer mill; information indicating the components of the mill, at least including the base Variable frequency motor Bearing pedestal Rotor of pulverizer Hammer sheet A component; Representing geometry information; Representing the assembly relationship of the pulverizer; Indicating the relative movement of the shredder; And establishing a geometric model by using three-dimensional modeling software according to the structural attributes.
4. The method for constructing a digital twin body of a hammer mill based on multi-dimensional fusion modeling according to claim 3, wherein the method for constructing the geometric model further comprises: and carrying out light weight treatment and rendering treatment on the geometric model to obtain the geometric model with the same appearance as that of the hammer mill.
5. The method for constructing a digital twin body of a hammer mill based on multi-dimensional fusion modeling according to claim 1, wherein the physical model is constructed by the following method: A plurality of sensors are arranged on the hammer mill to monitor key physical quantities of the hammer mill, expressed as: ; Wherein: Real-time data set for key physical quantity; The current is the variable frequency motor current; the spindle rotation speed; The real-time vibration data set comprises 6 measuring points of the motor and the bearing; The real-time temperature data set comprises 6 measuring points of the motor and the bearing.
6. The method for constructing a digital twin body of a hammer mill based on multi-dimensional fusion modeling according to claim 1, wherein the factors influencing the crushing granularity are expressed as follows: ; Wherein: is the feed rate; Is the raw material type; is the water content of the raw materials, Is the mesh size, Is worn by a hammer, Is the spindle current.
7. The method for constructing a digital twin body of a hammer mill based on multi-dimensional fusion modeling according to claim 5, wherein the mechanism model is constructed by the following method: Defining the health index H of the equipment, wherein the value range is as follows ; Analyzing key physical quantity historical data and the state of the hammer mill; Constructing a nonlinear mapping relation between key physical quantity and equipment health index by using a support vector machine method: ; ; and constructing a mechanism model based on the nonlinear mapping relation between the key physical quantity and the equipment health index.
8. The method for constructing a digital twin body of a hammer mill based on multi-dimensional fusion modeling according to claim 1, wherein the data model is constructed by the following method: And constructing a LSTM-based crushing granularity prediction model as a data model according to the crushing granularity historical data.
9. The method for constructing a digital twin body of a hammer mill based on multi-dimensional fusion modeling according to claim 1, wherein the method further comprises: the following quaternion is defined for scientific evaluation of the digital twins: ; Wherein: Modeling accuracy for digital twins; the simulation confidence of the digital twin; Is virtual-real synchronous delay; Is the running stability of the digital twin.
10. An application method of the digital twin body of the hammer mill in production is characterized in that the digital twin body of the hammer mill is constructed by the construction method of the digital twin body of the hammer mill based on multi-dimensional fusion modeling, which is any one of claims 1 to 9, and comprises the following steps: the digital twin bodies of the hammer mill are deployed on a server of a production control center; acquiring key physical quantities in real time through a physical model in the digital twin body of the hammer mill; The motion rule of the raw materials in the crushing chamber and the deformation rule of the raw materials in the crushing chamber are obtained through real-time simulation according to key physical quantities by using a behavior model in the digital twin body of the hammer mill; Predicting the equipment performance of the hammer mill in real time according to the key physical quantity through a mechanism model in the digital twin body of the hammer mill; and predicting the crushing granularity of the material in real time according to the deformation rule of the material in the crushing chamber through a data model in the digital twin body of the hammer crusher.

Description

Hammer mill digital twin body construction method based on multidimensional fusion modeling Technical Field The invention relates to the technical field of manufacturing system automation, in particular to a method for constructing a digital twin body of a hammer mill based on multidimensional fusion modeling and an application method of the digital twin body of the hammer mill in production. Background The hammer mill is a key device of a degerming and crushing section of a fuel ethanol production line and is responsible for crushing crops such as corn, wheat, cassava and the like into particles. In the production process, the performance of the hammer mill is determined by various factors such as the performance of the variable frequency motor, the loading state of the main shaft, the abrasion degree of the hammer, and the like, and the performance of the hammer mill not only can influence the stability of the crushing granularity so as to carry out subsequent processes and cause fluctuation of the ethanol production quality, but also can cause equipment to stop when the performance is severely reduced, so that the production efficiency is reduced and larger economic loss is caused to enterprises. Therefore, it is necessary to monitor the performance of the hammer mill in real time while obtaining the milling particle size on line. However, the performance of the hammer mill at present is estimated by field personnel on the vibration amplitude and temperature of the variable frequency motor, then judgment is made according to experience, and the grinding granularity is obtained by a manual period sampling mode. The current method is difficult to accurately monitor the performance of the hammer mill in real time and cannot acquire the milling granularity in time, so that the production process is unstable, and a method for acquiring the performance and the milling granularity of the hammer mill on line in real time needs to be developed. The digital twin technology can construct a simulation model with multi-dimensional fusion, analyze the association relation between the historical data of the equipment and combine the real-time data of the sensor to map the actual state of the equipment by the twin body. Thus, in recent years, the technology has been continuously focused on by various industries, and has been continuously practiced in various fields such as aerospace, smart manufacturing, smart cities, and the like, and achievements brilliant have been achieved. However, on one hand, the digital twin technology is mainly applied to the demonstration of virtual and real synchronous motion, and has less application to the construction of equipment twin based on multi-dimensional fusion modeling, and on the other hand, the process industry, particularly the fuel ethanol preparation industry, is mainly used for variable frequency motors, pumps and fans, and the actual state of equipment is often required to be presented through multi-dimensional fusion modeling. Therefore, the digital twin technology is less applied in the fuel ethanol preparation industry. Disclosure of Invention The invention aims to provide a method for constructing a digital twin body of a hammer mill based on multidimensional fusion modeling, which is used for describing structural attributes, key physical quantities in the operation process, raw material particle crushing processes, mapping relations of key physical quantities and equipment health indexes and change rules of crushing granularity in the production process of the hammer mill respectively by constructing a geometric model, a physical model, a behavior model, a mechanism model and a data model of the hammer mill, and acquiring the performance and the crushing granularity of the mill on line in real time, so that important basis can be provided for keeping the mill stably operated and the stability of the crushing granularity. To achieve the above object, a first aspect of the present invention provides a method for constructing a digital twin body of a hammer mill based on multidimensional fusion modeling, the method comprising: Constructing a multi-dimensional model of the hammer mill, wherein the multi-dimensional model comprises a geometric model, a physical model, a behavior model, a mechanism model and a data model; And fusing the multidimensional models to construct a digital twin body of the hammer mill. Further, fusing the multidimensional models to construct a digital twin body of the hammer mill, comprising: Loading a geometric model as a basis of the digital twin; The method comprises the steps of designing a data acquisition module, acquiring key physical quantities of the hammer mill and relating the key physical quantities to the geometric model by accessing a real-time data interface provided by the physical model; designing a behavior analysis module, integrating the behavior model into a digital twin body through data analysis and visualization software; A