A smart factory personnel positioning and scheduling system based on three-dimensional modeling

Abstract

The application discloses a kind of personnel positioning and scheduling systems of wisdom factory based on three-dimensional modeling, it is related to wisdom factory personnel positioning and scheduling technical neighborhood, including wisdom factory data acquisition module, pre-processing module, three-dimensional positioning module, environment monitoring module, model fusion module and personnel scheduling module, the wisdom factory data acquisition module, with acquisition equipment, collect wisdom factory environment data, wisdom factory's point cloud data and wisdom factory personnel data;The three-dimensional positioning module updates wisdom factory personnel real-time three-dimensional positioning coordinates, constructs wisdom factory three-dimensional model, obtains wisdom factory personnel real-time three-dimensional positioning data, data acquisition technology in the system described in the application, positioning error calculation technique, three-dimensional modeling technique, model construction technique and model fusion technique are closely combined with modern information technology, and the intelligent degree in the personnel positioning and scheduling process of wisdom factory based on three-dimensional modeling is significantly enhanced.

Description

[0001] The present application relates to the technical field of smart factory personnel positioning and scheduling, and particularly relates to a smart factory personnel positioning and scheduling system based on three-dimensional modeling. BACKGROUND

[0002] In the context of the rapid development of modern manufacturing, smart factories have become a key trend for improving production efficiency and optimizing management patterns. Traditional factories face many challenges in personnel management and are unable to meet the needs of efficient production. On the one hand, personnel are widely distributed and have complex working states in a factory. Relying solely on manual recording and experience-based scheduling cannot accurately grasp the real-time positions and working progress of personnel, leading to unreasonable task allocation and seriously affecting production efficiency. On the other hand, when a factory faces an emergency, it is unable to quickly locate relevant personnel, resulting in delayed emergency response and losses for the factory. Meanwhile, three-dimensional modeling technology and advanced personnel positioning technology are constantly maturing. In this context, a smart factory personnel positioning and scheduling system based on three-dimensional modeling has emerged, aiming to break through the limitations of traditional personnel management by utilizing advanced technology to provide efficient and accurate personnel positioning and scientifically reasonable scheduling solutions for factories, thereby improving overall production efficiency and enhancing the ability of factories to respond to unexpected situations, and promoting the intelligentization and high efficiency of the manufacturing industry.

[0003] Although existing technologies have made great progress in the direction of smart factory personnel positioning and scheduling, there are still some problems to be optimized. Existing technologies are unable to combine environmental factors of smart factories to monitor the interference of various environmental factors on smart factory personnel positioning, affecting the accuracy of real-time positioning of smart factory personnel, and leading to unreasonable scheduling of smart factory personnel. SUMMARY

[0004] The present application aims to provide a smart factory personnel positioning and scheduling system based on three-dimensional modeling to solve the problems raised in the background.

[0005] To solve the above technical problems, the technical solution adopted by the present application is as follows: a smart factory personnel positioning and scheduling system based on three-dimensional modeling, comprising a smart factory data acquisition module, a preprocessing module, a three-dimensional positioning module, an environment monitoring module, a model fusion module, and a personnel scheduling module, wherein the modules are communicatively connected.

[0006] The smart factory data acquisition module uses acquisition equipment to acquire smart factory environment data, smart factory point cloud data, and smart factory personnel data, providing data support for the implementation of the functions of the subsequent modules.

[0007] The preprocessing module performs data cleaning, data calibration, data standardization, and time synchronization processing on the acquired data.

[0008] The three-dimensional positioning module obtains real-time positioning errors of the personnel in the intelligent factory according to a Euclidean distance formula, constructs a positioning error monitoring model, and provides a data basis for the accurate real-time three-dimensional positioning coordinates of the personnel in the intelligent factory and the construction of a dust concentration monitoring model and an electromagnetic noise monitoring model; the positioning error monitoring model is combined to update the real-time three-dimensional positioning coordinates of the personnel in the intelligent factory, the point cloud data of the intelligent factory is utilized to construct a three-dimensional model of the intelligent factory, and real-time three-dimensional positioning data of the personnel in the intelligent factory are obtained;

[0009] The environment monitoring module respectively constructs a dust concentration monitoring model and an electromagnetic noise monitoring model through a linear regression algorithm.

[0010] The model fusion module fuses the dust concentration monitoring model and the electromagnetic noise monitoring model by using a neural network algorithm to obtain an environment monitoring model.

[0011] The personnel scheduling module combines the three-dimensional model of the intelligent factory and the environment monitoring model to obtain the positioning of abnormal environment data, schedules the personnel in the intelligent factory to take corresponding measures according to the real-time three-dimensional positioning data of the personnel in the intelligent factory, and solves the problem that the prior art is difficult to combine the environmental factors of the intelligent factory to monitor the interference of various environmental factors on the positioning of the personnel in the intelligent factory, thereby leading to unreasonable scheduling of the personnel in the intelligent factory.

[0012] Further improvement of the technical scheme of the present application is that the intelligent factory data acquisition module utilizes acquisition equipment to acquire intelligent factory environment data and point cloud data of the intelligent factory, and the process includes:

[0013] The acquisition equipment is a dust concentration sensor, an electromagnetic interference measuring instrument, a three-dimensional laser scanner, a UWB positioning device, an inertial navigation positioning device and a laser tracker, the intelligent factory environment data includes dust concentration of the intelligent factory environment and electromagnetic noise of the intelligent factory environment, and the personnel data of the intelligent factory includes real-time three-dimensional positioning coordinates of the personnel in the intelligent factory and reference three-dimensional positioning coordinates of the personnel in the intelligent factory;

[0014] The dust concentration sensor is used to acquire the dust concentration of the intelligent factory environment based on the light scattering principle;

[0015] The electromagnetic interference measuring instrument is used to acquire the electromagnetic noise of the intelligent factory environment based on the electromagnetic induction principle;

[0016] A scanning site in the intelligent factory is selected, the three-dimensional laser scanner is fixed on the scanning site in the intelligent factory, scanning parameters are set, the position and attitude information of the three-dimensional laser scanner are obtained, the three-dimensional laser scanner measures the time of laser from emission to reflection back to the three-dimensional laser scanner by emitting a laser beam, the distance between the measured point and the three-dimensional laser scanner is calculated in combination with the position and attitude information of the three-dimensional laser scanner, and the point cloud data of the intelligent factory are obtained.

[0017] The UWB positioning device is composed of a UWB tag, a UWB base station and a positioning engine, the UWB tag is worn on the body of the intelligent factory personnel, the UWB base station is arranged at a central position of the intelligent factory, receives a UWB pulse signal, the positioning engine measures the distance between the UWB tag and the UWB base station based on a ToF ranging principle, and through a multi-variable positioning algorithm, real-time three-dimensional positioning coordinates of the intelligent factory personnel are obtained.

[0018] The three-dimensional initial positioning coordinates of the intelligent factory personnel are collected by using a laser tracker based on a triangulation principle, and the inertial navigation positioning device is composed of an inertial measurement unit and a data processing unit, wherein the inertial measurement unit is used to measure the real-time acceleration of the intelligent factory personnel in the three-dimensional space and the real-time angular velocity of the intelligent factory personnel in the three-dimensional space, the data processing unit is used to receive the real-time acceleration and the real-time angular velocity of the intelligent factory personnel in the three-dimensional space, the received data is integrated to obtain the displacement of the intelligent factory personnel in the three-dimensional space, and the sum of the three-dimensional initial positioning coordinates of the intelligent factory personnel and the displacement of the intelligent factory personnel in the three-dimensional space is calculated to obtain the reference three-dimensional positioning coordinates of the intelligent factory personnel.

[0019] Further improvement of the technical scheme of the present application is that the process of data cleaning, data calibration, data standardization and time synchronization processing of the collected data in the preprocessing module comprises:

[0020] The dust concentration of the intelligent factory environment, the electromagnetic noise of the intelligent factory environment, the real-time three-dimensional positioning coordinates of the intelligent factory personnel, the reference three-dimensional positioning coordinates of the intelligent factory personnel and the point cloud data of the intelligent factory are subjected to data cleaning, data calibration and data standardization processing to remove repeated values and abnormal values.

[0021] A time stamp is added to the collected dust concentration of the intelligent factory environment, electromagnetic noise of the intelligent factory environment, real-time three-dimensional positioning coordinates of the intelligent factory personnel and point cloud data of the intelligent factory, the collection time of the dust concentration of the intelligent factory environment, real-time three-dimensional positioning coordinates of the intelligent factory personnel, reference three-dimensional positioning coordinates of the intelligent factory personnel and point cloud data of the intelligent factory is synchronized according to the time stamp, and the collection time of the electromagnetic noise of the intelligent factory environment, real-time three-dimensional positioning coordinates of the intelligent factory personnel, reference three-dimensional positioning coordinates of the intelligent factory personnel and point cloud data of the intelligent factory is synchronized.

[0022] Further improvement of the technical scheme of the present application is that the three-dimensional positioning module uses the Euclidean distance formula to obtain the real-time positioning error of the intelligent factory personnel, and the process comprises:

[0023] The real-time positioning error of the intelligent factory personnel is divided into the real-time positioning error of the intelligent factory personnel caused by the dust concentration and the real-time positioning error of the intelligent factory personnel caused by the electromagnetic noise.

[0024] extracting the real-time three-dimensional positioning coordinates of the smart factory personnel corresponding to the collection timestamp of the dust concentration in the smart factory environment and the reference three-dimensional positioning coordinates of the smart factory personnel, and calculating the real-time positioning error of the smart factory personnel caused by the dust concentration by using the Euclidean distance formula;

[0025] extracting the real-time three-dimensional positioning coordinates of the smart factory personnel corresponding to the collection timestamp of the electromagnetic noise in the smart factory environment and the reference three-dimensional positioning coordinates of the smart factory personnel, and calculating the real-time positioning error of the smart factory personnel caused by the electromagnetic noise by using the Euclidean distance formula.

[0026] Further improvement of the technical scheme of the present application is that the process of constructing the positioning error monitoring model by the three-dimensional positioning module includes:

[0027] The random forest model is constructed by using the random forest algorithm, the dust concentration in the smart factory environment, the electromagnetic noise in the smart factory environment, the real-time positioning error of the smart factory personnel caused by the dust concentration and the real-time positioning error of the smart factory personnel caused by the electromagnetic noise are used as a data set, the data set is divided into a training set and a test set according to a 7:3 ratio, the random forest model is trained using the training set data, the nonlinear relationship between the dust concentration in the smart factory environment and the real-time positioning error of the smart factory personnel caused by the dust concentration and the nonlinear relationship between the electromagnetic noise in the smart factory environment and the real-time positioning error of the smart factory personnel caused by the electromagnetic noise are learned, and a trained random forest model is obtained; the trained random forest is evaluated using the test set data, the random forest model parameters are adjusted, the random forest model is optimized, the optimized random forest model is deployed in a three-dimensional modeling-based smart factory personnel positioning and scheduling system, and a positioning error monitoring model is obtained.

[0028] Further improvement of the technical scheme of the present application is that the three-dimensional positioning module, in combination with the positioning error monitoring model, updates the real-time positioning of the smart factory personnel, constructs a smart factory three-dimensional model, and the process of obtaining real-time three-dimensional positioning data of the smart factory personnel includes:

[0029] The dust concentration in the smart factory environment and the electromagnetic noise in the smart factory environment are input into the positioning error monitoring model, and the positioning error monitoring model outputs the real-time positioning error of the smart factory personnel caused by the dust concentration and the real-time positioning error of the smart factory personnel caused by the electromagnetic noise, respectively;

[0030] According to the real-time positioning error of the smart factory personnel caused by the dust concentration and the real-time positioning error of the smart factory personnel caused by the electromagnetic noise, the real-time positioning coordinates of the smart factory personnel are updated;

[0031] The neighborhood points of each point in the point cloud data of the smart factory are extracted, the covariance matrix of each neighborhood point is calculated by using a principal component analysis method, the eigenvalues and eigenvectors are obtained by performing feature decomposition on the covariance matrix of each neighborhood point, and the planar features in the point cloud data of the smart factory are extracted through the eigenvalues and eigenvectors; the normal vector of each point in the point cloud data of the smart factory is calculated, and the edge features in the point cloud data of the smart factory are extracted according to the included angle between the normal vector of each point in the point cloud data of the smart factory and the normal vectors of adjacent points; and the Harris corner point detection algorithm is used to extract the corner point features in the point cloud data of the smart factory.

[0032] Based on the extracted planar features, edge features and corner point features, a Delaunay triangulation algorithm is used to perform Delaunay triangulation on the point cloud data of the smart factory, discrete points in each point cloud data of the smart factory are connected into triangular patches, and a three-dimensional model of the smart factory is constructed.

[0033] The updated real-time three-dimensional positioning coordinates of the personnel in the smart factory are mapped into the three-dimensional model of the smart factory, and real-time three-dimensional positioning data of the personnel in the smart factory are obtained.

[0034] Further improvement of the technical scheme of the present application is that the process of constructing the dust concentration monitoring model by the environmental monitoring module through the linear regression algorithm includes:

[0035] The real-time positioning error of the personnel in the smart factory caused by the dust concentration is taken as an input variable, the influence index of the dust concentration on the positioning of the personnel in the smart factory is taken as an output variable, a linear regression model is constructed by using the linear regression algorithm, and the expression of the linear regression model is , wherein is the influence index of the dust concentration on the positioning of the personnel in the smart factory, is the real-time positioning error of the personnel in the smart factory caused by the dust concentration, is the intercept when the real-time positioning error of the personnel in the smart factory caused by the dust concentration is 0, is the slope, is an error term, and and are estimated by using the least square method to obtain the dust concentration monitoring model.

[0036] Further improvement of the technical scheme of the present application is that the process of constructing the electromagnetic noise monitoring model by the environmental monitoring module through the linear regression algorithm includes:

[0037] The real-time positioning error of the personnel in the smart factory caused by the electromagnetic noise is taken as an input variable, the influence index of the electromagnetic noise on the positioning of the personnel in the smart factory is taken as an output variable, a linear regression model is constructed by using the linear regression algorithm, and the expression of the linear regression model is wherein is an index of the influence of electromagnetic noise on the real-time positioning error of the smart factory personnel, is a real-time positioning error of the smart factory personnel caused by electromagnetic noise, is an intercept when the real-time positioning error of the smart factory personnel caused by electromagnetic noise is 0, is a slope, is an error term, estimated using a least squares method and obtain an electromagnetic noise monitoring model.

[0038] Further improvements of the technical solution of the present application are that the model fusion module fuses the dust concentration monitoring model and the electromagnetic noise monitoring model using a neural network algorithm, and the process of obtaining the environment monitoring model includes:

[0039] input the real-time positioning error of the smart factory personnel caused by the dust concentration into the dust concentration monitoring model to obtain an index of the influence of the dust concentration on the positioning of the smart factory personnel; input the real-time positioning error of the smart factory personnel caused by the electromagnetic noise into the electromagnetic noise monitoring model to obtain an index of the influence of the electromagnetic noise on the positioning of the smart factory personnel;

[0040] use a neural network algorithm to construct a neural network model, use the real-time positioning error of the smart factory personnel caused by the dust concentration, the real-time positioning error of the smart factory personnel caused by the electromagnetic noise, the index of the influence of the dust concentration on the positioning of the smart factory personnel, and the index of the influence of the electromagnetic noise on the positioning of the smart factory personnel as a data set, divide the data set into a training set and a test set according to a ratio of 7:3, select MLP as the neural network structure, the input layer includes two neurons to receive the real-time positioning error of the smart factory personnel caused by the dust concentration and the real-time positioning error of the smart factory personnel caused by the electromagnetic noise, the hidden layer is configured with an MSE function, and the output layer includes two neurons to output the index of the influence of the dust concentration on the positioning of the smart factory personnel and the index of the influence of the electromagnetic noise on the positioning of the smart factory personnel;

[0041] input the training set data into the neural network model, set the learning rate to 0.01 and the number of iterations to 1000, and the training process includes forward propagation and back propagation, wherein the forward propagation is used to calculate the predicted output data, and the back propagation is used to update the weights and biases of the model, through repeated iteration training, the nonlinear relationship between the real-time positioning error of the smart factory personnel caused by the dust concentration and the index of the influence of the dust concentration on the positioning of the smart factory personnel and the nonlinear relationship between the real-time positioning error of the smart factory personnel caused by the electromagnetic noise and the index of the influence of the electromagnetic noise on the positioning of the smart factory personnel are learned until the set number of iterations is reached, and a trained neural network model is obtained;

[0042] The test set data is input into the trained neural network model, the error between the output value of the neural network model and the actual value is evaluated by using the MSE function, the parameters of the neural network model are adjusted according to the evaluation result, and an environment monitoring model is obtained.

[0043] Further improvement of the technical scheme of the present application is that the process of the personnel scheduling module scheduling the smart factory personnel to take corresponding measures includes:

[0044] The real-time positioning error of the smart factory personnel caused by the dust concentration and the real-time positioning error of the smart factory personnel caused by the electromagnetic noise are input into the environment monitoring model, and the environment monitoring model outputs an influence index of the dust concentration on the positioning of the smart factory personnel and an influence index of the electromagnetic noise on the positioning of the smart factory personnel.

[0045] When the influence index of the dust concentration on the positioning of the smart factory personnel is lower than 0.4, the influence of the dust concentration on the positioning of the smart factory personnel is small; when the influence index of the dust concentration on the positioning of the smart factory personnel is higher than 0.4, it indicates that the dust concentration is abnormal and has a great influence on the positioning of the smart factory personnel, the three-dimensional positioning coordinates of the abnormal dust concentration are extracted from the three-dimensional model of the smart factory, the distance between the three-dimensional positioning coordinates of the abnormal dust concentration and the three-dimensional positioning data of the smart factory personnel is obtained through the Euclidean formula according to the real-time three-dimensional positioning data of the smart factory personnel, the smart factory personnel corresponding to the minimum distance value is extracted, and the smart factory personnel is scheduled to cope with the interference of the dust concentration.

[0046] When the influence index of the electromagnetic noise on the positioning of the smart factory personnel is lower than 0.3, the influence of the electromagnetic noise on the positioning of the smart factory personnel is small; when the influence index of the electromagnetic noise on the positioning of the smart factory personnel is higher than 0.3, it indicates that the electromagnetic noise is abnormal and has a great influence on the positioning of the smart factory personnel, the three-dimensional positioning coordinates of the abnormal electromagnetic noise are extracted from the three-dimensional model of the smart factory, the distance between the three-dimensional positioning coordinates of the abnormal electromagnetic noise and the three-dimensional positioning data of the smart factory personnel is obtained through the Euclidean formula according to the real-time three-dimensional positioning data of the smart factory personnel, the smart factory personnel corresponding to the minimum distance value is extracted, and the smart factory personnel is scheduled to cope with the interference of the electromagnetic noise.

[0047] The beneficial effects of the present application are: compared with the traditional three-dimensional modeling-based intelligent factory personnel positioning and scheduling system, the data acquisition technology, positioning error calculation technology, three-dimensional modeling technology, model construction technology and model fusion technology in the system of the present application are closely combined with modern information technology, the intelligent factory environment data, intelligent factory personnel data and intelligent factory point cloud data are accurately captured, and the real-time positioning error of the intelligent factory personnel, the intelligent factory three-dimensional model and the intelligent factory personnel real-time three-dimensional positioning data are obtained, the dust concentration monitoring model and the electromagnetic noise monitoring model are constructed by using the linear regression algorithm, the dust concentration monitoring model and the electromagnetic noise monitoring model are fused by using the neural network algorithm, the environment monitoring model is obtained, the real-time and comprehensive monitoring of the intelligent factory personnel positioning and the environment condition is achieved, the problem that the positioning of the intelligent factory personnel is disturbed by the difficult-to-monitor environmental factors is solved, the problem of low intelligent factory personnel positioning accuracy and unreasonable intelligent factory personnel scheduling is solved, and it is ensured that the system in the present application can refine the dynamic monitoring standard of the intelligent factory personnel positioning and scheduling system in a more accurate range, so that the monitored data becomes a more accurate index under the same conditions, and the research and application of this method significantly enhances the intelligent degree in the process of the three-dimensional modeling-based intelligent factory personnel positioning and scheduling. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments described in the present application, and other drawings can also be obtained by those skilled in the art based on these drawings.

[0049] Figure 1 The block diagram of the three-dimensional modeling-based intelligent factory personnel positioning and scheduling system of the present application. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor fall within the scope of protection of the present application.

[0051] As Figure 1As shown, the present application provides a three-dimensional modeling-based intelligent factory personnel positioning and scheduling system, which comprises an intelligent factory data acquisition module, a preprocessing module, a three-dimensional positioning module, an environment monitoring module, a model fusion module and a personnel scheduling module, wherein the modules are communicatively connected;

[0052] The intelligent factory data acquisition module uses acquisition equipment to acquire intelligent factory environment data, intelligent factory point cloud data and intelligent factory personnel data, which provides data support for the implementation of the subsequent module functions;

[0053] The preprocessing module performs data cleaning, data calibration, data standardization and time synchronization processing on the acquired data;

[0054] The three-dimensional positioning module acquires the real-time positioning error of the intelligent factory personnel according to the Euclidean distance formula, constructs a positioning error monitoring model, provides a data basis for the construction of the dust concentration monitoring model and the electromagnetic noise monitoring model for the accurate real-time three-dimensional positioning coordinates of the intelligent factory personnel, updates the real-time three-dimensional positioning coordinates of the intelligent factory personnel in combination with the positioning error monitoring model, constructs an intelligent factory three-dimensional model using the intelligent factory point cloud data, and acquires real-time three-dimensional positioning data of the intelligent factory personnel;

[0055] The environment monitoring module constructs a dust concentration monitoring model and an electromagnetic noise monitoring model respectively through a linear regression algorithm;

[0056] The model fusion module fuses the dust concentration monitoring model and the electromagnetic noise monitoring model using a neural network algorithm to obtain an environment monitoring model;

[0057] The personnel scheduling module combines the intelligent factory three-dimensional model and the environment monitoring model to obtain the positioning of abnormal environment data, and schedules the intelligent factory personnel to take corresponding measures according to the real-time three-dimensional positioning data of the intelligent factory personnel, thereby solving the problem that the prior art cannot combine the environmental factors of the intelligent factory to monitor the interference of various environmental factors on the positioning of the intelligent factory personnel, resulting in unreasonable scheduling of the intelligent factory personnel.

[0058] Preferably, the process of acquiring intelligent factory environment data and intelligent factory point cloud data by the intelligent factory data acquisition module using acquisition equipment comprises:

[0059] The acquisition equipment is a dust concentration sensor, an electromagnetic interference measuring instrument, a three-dimensional laser scanner, a UWB positioning device, an inertial navigation positioning device and a laser tracker, the intelligent factory environment data includes the dust concentration of the intelligent factory environment and the electromagnetic noise of the intelligent factory environment, and the intelligent factory personnel data includes real-time three-dimensional positioning coordinates of the intelligent factory personnel and reference three-dimensional positioning coordinates of the intelligent factory personnel;

[0060] The dust concentration sensor is used to collect the dust concentration of the smart factory environment based on the light scattering principle.

[0061] The electromagnetic interference measuring instrument is used to collect the electromagnetic noise of the smart factory environment based on the electromagnetic induction principle.

[0062] The scanning station in the smart factory is selected, the three-dimensional laser scanner is fixed on the scanning station in the smart factory, the scanning parameters are set, the position and attitude information of the three-dimensional laser scanner are obtained, the three-dimensional laser scanner measures the time from the emission of the laser beam to the reflection back to the three-dimensional laser scanner, and the distance between the measured point and the three-dimensional laser scanner is calculated based on the position and attitude information of the three-dimensional laser scanner to obtain the point cloud data of the smart factory.

[0063] The UWB positioning device is composed of a UWB tag, a UWB base station and a positioning engine, the UWB tag is worn on the body of the smart factory personnel, the UWB base station is deployed at the center position of the smart factory to receive the UWB pulse signal, the positioning engine measures the distance between the UWB tag and the UWB base station based on the ToF ranging principle, and the real-time three-dimensional positioning coordinates of the smart factory personnel are obtained through a variable positioning algorithm.

[0064] The laser tracker is used to collect the three-dimensional initial positioning coordinates of the smart factory personnel based on the triangulation principle, and the inertial navigation positioning device is composed of an inertial measurement unit and a data processing unit, wherein the inertial measurement unit is used to measure the real-time acceleration of the smart factory personnel in the three-dimensional space and the real-time angular velocity of the smart factory personnel in the three-dimensional space, the data processing unit receives the real-time acceleration and real-time angular velocity of the smart factory personnel in the three-dimensional space, integrates the received data to obtain the displacement of the smart factory personnel in the three-dimensional space, and calculates the sum of the three-dimensional initial positioning coordinates of the smart factory personnel and the displacement of the smart factory personnel in the three-dimensional space to obtain the reference three-dimensional positioning coordinates of the smart factory personnel.

[0065] Preferably, the preprocessing module includes the processes of data cleaning, data calibration, data standardization and time synchronization of the collected data.

[0066] The dust concentration of the smart factory environment, the electromagnetic noise of the smart factory environment, the real-time three-dimensional positioning coordinates of the smart factory personnel, the reference three-dimensional positioning coordinates of the smart factory personnel and the point cloud data of the smart factory are subjected to data cleaning, data calibration and data standardization processing to remove duplicate values and abnormal values.

[0067] The time stamps are added to the collected dust concentration of the smart factory environment, electromagnetic noise of the smart factory environment, real-time three-dimensional positioning coordinates of the smart factory personnel, and point cloud data of the smart factory. According to the time stamps, the collection times of the dust concentration of the smart factory environment, the real-time three-dimensional positioning coordinates of the smart factory personnel, the reference three-dimensional positioning coordinates of the smart factory personnel, and the point cloud data of the smart factory are synchronized. The collection times of the electromagnetic noise of the smart factory environment, the real-time three-dimensional positioning coordinates of the smart factory personnel, the reference three-dimensional positioning coordinates of the smart factory personnel, and the point cloud data of the smart factory are synchronized.

[0068] Preferably, the three-dimensional positioning module obtains the real-time positioning error of the smart factory personnel by using the Euclidean distance formula, and the process includes:

[0069] The real-time positioning error of the smart factory personnel is divided into a real-time positioning error of the smart factory personnel caused by the dust concentration and a real-time positioning error of the smart factory personnel caused by the electromagnetic noise.

[0070] The real-time positioning error of the smart factory personnel caused by the dust concentration is obtained by extracting the real-time three-dimensional positioning coordinates of the smart factory personnel and the reference three-dimensional positioning coordinates of the smart factory personnel corresponding to the collection time stamp of the dust concentration of the smart factory environment and using the Euclidean distance formula.

[0071] The real-time positioning error of the smart factory personnel caused by the electromagnetic noise is obtained by extracting the real-time three-dimensional positioning coordinates of the smart factory personnel and the reference three-dimensional positioning coordinates of the smart factory personnel corresponding to the collection time stamp of the electromagnetic noise of the smart factory environment and using the Euclidean distance formula.

[0072] Preferably, the three-dimensional positioning module constructs the positioning error monitoring model, and the process includes:

[0073] The random forest model is constructed by using the random forest algorithm, the dust concentration of the smart factory environment, the electromagnetic noise of the smart factory environment, the real-time positioning error of the smart factory personnel caused by the dust concentration, and the real-time positioning error of the smart factory personnel caused by the electromagnetic noise are used as a data set, the data set is divided into a training set and a test set according to a 7:3 ratio, the training set data is used to train the random forest model, the nonlinear relationship between the dust concentration of the smart factory environment and the real-time positioning error of the smart factory personnel caused by the dust concentration and the nonlinear relationship between the electromagnetic noise of the smart factory environment and the real-time positioning error of the smart factory personnel caused by the electromagnetic noise are learned, and a trained random forest model is obtained. The trained random forest is evaluated using the test set data, the random forest model parameters are adjusted, the random forest model is optimized, the optimized random forest model is deployed in a three-dimensional modeling-based smart factory personnel positioning and scheduling system, and a positioning error monitoring model is obtained.

[0074] Preferably, the three-dimensional positioning module, in combination with the positioning error monitoring model, updates the real-time positioning of the smart factory personnel, constructs a three-dimensional model of the smart factory, and obtains the process of real-time three-dimensional positioning data of the smart factory personnel includes:

[0075] The dust concentration of the smart factory environment and the electromagnetic noise of the smart factory environment are input into the positioning error monitoring model, and the positioning error monitoring model outputs the real-time positioning error of the smart factory personnel caused by the dust concentration and the real-time positioning error of the smart factory personnel caused by the electromagnetic noise.

[0076] According to the real-time positioning error of the smart factory personnel caused by the dust concentration and the real-time positioning error of the smart factory personnel caused by the electromagnetic noise, the real-time positioning coordinates of the smart factory personnel are updated.

[0077] Extract the neighborhood points of each point in the point cloud data of the smart factory, calculate the covariance matrix of each neighborhood point using principal component analysis method, obtain the eigenvalues and eigenvectors by performing eigenvalue decomposition on the covariance matrix of each neighborhood point, and extract the plane features in the point cloud data of the smart factory through the eigenvalues and eigenvectors; calculate the normal vector of each point in the point cloud data of the smart factory, and extract the edge features in the point cloud data of the smart factory according to the included angle between the normal vector of each point in the point cloud data of the smart factory and the normal vector of its adjacent point; and use Harris corner detection algorithm to extract the corner features in the point cloud data of the smart factory.

[0078] Based on the extracted plane features, edge features and corner features, a Delaunay triangulation algorithm is used to perform Delaunay triangulation on the point cloud data of the smart factory, connect the discrete points in each point cloud data of the smart factory into triangular patches, and construct a three-dimensional model of the smart factory.

[0079] Map the updated real-time three-dimensional positioning coordinates of the smart factory personnel to the three-dimensional model of the smart factory to obtain real-time three-dimensional positioning data of the smart factory personnel.

[0080] Preferably, the environment monitoring module, through a linear regression algorithm, constructs a dust concentration monitoring model, the process includes:

[0081] The real-time positioning error of the smart factory personnel caused by the dust concentration is taken as an input variable, and the influence index of the dust concentration on the positioning of the smart factory personnel is taken as an output variable. A linear regression model is constructed using a linear regression algorithm, and the expression of the linear regression model is , wherein is the influence index of the dust concentration on the positioning of the smart factory personnel, is the real-time positioning error of the smart factory personnel caused by the dust concentration, is the intercept when the real-time positioning error of the smart factory personnel caused by the dust concentration is 0. is a slope, is an error term, estimated using least squares and obtain a dust concentration monitoring model.

[0082] Preferably, the environment monitoring module, in the process of constructing the electromagnetic noise monitoring model by the linear regression algorithm, comprises:

[0083] taking the real-time positioning error of the smart factory personnel caused by the electromagnetic noise as an input variable, taking the influence index of the electromagnetic noise on the positioning of the smart factory personnel as an output variable, and constructing a linear regression model by using a linear regression algorithm, the expression of the linear regression model being , wherein is the influence index of the electromagnetic noise on the positioning of the smart factory personnel, is the real-time positioning error of the smart factory personnel caused by the electromagnetic noise, is an intercept when the real-time positioning error of the smart factory personnel caused by the electromagnetic noise is 0, is a slope, is an error term, estimated using least squares and obtain an electromagnetic noise monitoring model.

[0084] Preferably, the model fusion module, in the process of fusing the dust concentration monitoring model and the electromagnetic noise monitoring model by using a neural network algorithm to obtain an environment monitoring model, comprises:

[0085] inputting the real-time positioning error of the smart factory personnel caused by the dust concentration into the dust concentration monitoring model to obtain the influence index of the dust concentration on the positioning of the smart factory personnel, and inputting the real-time positioning error of the smart factory personnel caused by the electromagnetic noise into the electromagnetic noise monitoring model to obtain the influence index of the electromagnetic noise on the positioning of the smart factory personnel;

[0086] constructing a neural network model by using a neural network algorithm, taking the real-time positioning error of the smart factory personnel caused by the dust concentration, the real-time positioning error of the smart factory personnel caused by the electromagnetic noise, the influence index of the dust concentration on the positioning of the smart factory personnel, and the influence index of the electromagnetic noise on the positioning of the smart factory personnel as a data set, dividing the data set into a training set and a test set according to a ratio of 7:3, selecting MLP as a neural network structure, taking the input layer to include two neurons to receive the real-time positioning error of the smart factory personnel caused by the dust concentration and the real-time positioning error of the smart factory personnel caused by the electromagnetic noise, configuring the hidden layer with an MSE function, and taking the output layer to include two neurons to output the influence index of the dust concentration on the positioning of the smart factory personnel and the influence index of the electromagnetic noise on the positioning of the smart factory personnel;

[0087] The training set data is input into the neural network model, the learning rate is set to 0.01, the number of iterations is 1000, and the training process includes forward propagation and back propagation, wherein the forward propagation is used to calculate the predicted output data, and the back propagation is used to update the weights and biases of the model. Through repeated iteration training, the nonlinear relationship between the real-time positioning error of the smart factory personnel caused by the dust concentration and the influence index of the dust concentration on the positioning of the smart factory personnel, and the nonlinear relationship between the real-time positioning error of the smart factory personnel caused by the electromagnetic noise and the influence index of the electromagnetic noise on the positioning of the smart factory personnel are learned, until the set number of iterations is reached, and the trained neural network model is obtained.

[0088] The test set data is input into the trained neural network model, the MSE function is used to evaluate the error between the output value and the actual value of the neural network model, the parameters of the neural network model are adjusted according to the evaluation result, and the environment monitoring model is obtained.

[0089] Preferably, the process of scheduling the smart factory personnel to take corresponding measures includes:

[0090] The real-time positioning error of the smart factory personnel caused by the dust concentration and the real-time positioning error of the smart factory personnel caused by the electromagnetic noise are input into the environment monitoring model, and the environment monitoring model outputs the influence index of the dust concentration on the positioning of the smart factory personnel and the influence index of the electromagnetic noise on the positioning of the smart factory personnel.

[0091] When the influence index of the dust concentration on the positioning of the smart factory personnel is less than 0.4, the influence of the dust concentration on the positioning of the smart factory personnel is small; when the influence index of the dust concentration on the positioning of the smart factory personnel is greater than 0.4, it indicates that the dust concentration is abnormal and has a large influence on the positioning of the smart factory personnel. The three-dimensional positioning coordinates of the dust concentration anomaly are extracted from the three-dimensional model of the smart factory, the distance between the three-dimensional positioning coordinates of the dust concentration anomaly and the three-dimensional positioning data of the smart factory personnel is obtained through the Euclidean formula according to the real-time three-dimensional positioning data of the smart factory personnel, and the smart factory personnel corresponding to the minimum distance value is extracted. The smart factory personnel should be scheduled to deal with the interference of the dust concentration;

[0092] When the influence index of the electromagnetic noise on the positioning of the smart factory personnel is less than 0.3, the influence of the electromagnetic noise on the positioning of the smart factory personnel is small; when the influence index of the electromagnetic noise on the positioning of the smart factory personnel is greater than 0.3, it indicates that the electromagnetic noise is abnormal and has a large influence on the positioning of the smart factory personnel. The three-dimensional positioning coordinates of the electromagnetic noise anomaly are extracted from the three-dimensional model of the smart factory, the distance between the three-dimensional positioning coordinates of the electromagnetic noise anomaly and the three-dimensional positioning data of the smart factory personnel is obtained through the Euclidean formula according to the real-time three-dimensional positioning data of the smart factory personnel, and the smart factory personnel corresponding to the minimum distance value is extracted. The smart factory personnel should be scheduled to deal with the interference of the electromagnetic noise.

[0093] Firstly, the dust concentration of the smart factory environment is collected using a dust concentration sensor, the electromagnetic noise of the smart factory environment is collected through an electromagnetic interference measuring instrument, the real-time three-dimensional positioning coordinates of the smart factory personnel are collected using a UWB positioning device, the reference three-dimensional positioning coordinates of the smart factory personnel are collected using an inertial navigation positioning device and a laser tracker, and the point cloud data of the smart factory is collected through a three-dimensional laser scanner. Time stamps are added to the collected data, and the synchronization of data collection is realized according to the time stamps. Then, the collected data is preprocessed, the real-time positioning error of the smart factory personnel is calculated using the Euclidean distance formula, and the positioning error monitoring model is constructed using the random forest algorithm. Next, the real-time positioning coordinates of the smart factory personnel are updated in combination with the positioning error monitoring model, the three-dimensional model of the smart factory is constructed, the updated real-time three-dimensional positioning coordinates of the smart factory personnel are mapped into the three-dimensional model of the smart factory, and the real-time three-dimensional positioning data of the smart factory personnel are obtained. Then, the dust concentration monitoring model and the electromagnetic noise monitoring model are constructed through a linear regression algorithm, the environmental monitoring model is obtained by fusing the dust concentration monitoring model and the electromagnetic noise monitoring model using a neural network algorithm. Finally, the positioning of abnormal environmental data is obtained in combination with the three-dimensional model of the smart factory and the environmental monitoring model, and the smart factory personnel are dispatched to take corresponding measures according to the real-time three-dimensional positioning data of the smart factory personnel.

[0094] The above is only a specific embodiment of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily think of changes or replacements within the technical scope disclosed in the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A smart factory personnel positioning and scheduling system based on 3D modeling, comprising a smart factory data acquisition module, a preprocessing module, a 3D positioning module, an environmental monitoring module, a model fusion module, and a personnel scheduling module, wherein, The communication connections between the modules are characterized by: The smart factory data acquisition module uses acquisition equipment to collect smart factory environmental data, smart factory point cloud data, and smart factory personnel data. The preprocessing module performs data cleaning, data calibration, data standardization, and time synchronization on the collected data. The three-dimensional positioning module obtains the real-time positioning error of personnel in the smart factory according to the Euclidean distance formula, constructs a positioning error monitoring model, updates the real-time three-dimensional positioning coordinates of personnel in the smart factory in combination with the positioning error monitoring model, constructs a three-dimensional model of the smart factory using the point cloud data of the smart factory, and obtains real-time three-dimensional positioning data of personnel in the smart factory. The environmental monitoring module constructs a dust concentration monitoring model and an electromagnetic noise monitoring model using a linear regression algorithm. Specifically, it uses the real-time positioning error of personnel in the smart factory caused by dust concentration as an input variable, and the impact index of dust concentration on personnel positioning in the smart factory as an output variable. A linear regression model is then constructed using this model, and its expression is as follows: ,in This represents the impact index of dust concentration on personnel positioning in smart factories. The real-time positioning error of personnel in a smart factory caused by dust concentration. The intercept when the real-time positioning error of personnel in a smart factory due to dust concentration is 0. The slope The error term is estimated using the least squares method. and To obtain a dust concentration monitoring model; Using the real-time positioning error of personnel in a smart factory caused by electromagnetic noise as the input variable and the impact index of electromagnetic noise on personnel positioning as the output variable, a linear regression model is constructed using a linear regression algorithm. The expression of this linear regression model is as follows: ,in This represents the impact index of electromagnetic noise on personnel positioning in smart factories. The real-time positioning error of personnel in smart factories caused by electromagnetic noise. The intercept when the real-time positioning error of personnel in a smart factory caused by electromagnetic noise is 0. The slope The error term is estimated using the least squares method. and To obtain an electromagnetic noise monitoring model; The model fusion module utilizes a neural network algorithm to fuse a dust concentration monitoring model and an electromagnetic noise monitoring model to obtain an environmental monitoring model. Specifically, it includes: inputting the real-time positioning error of smart factory personnel caused by dust concentration into the dust concentration monitoring model to obtain the impact index of dust concentration on the positioning of smart factory personnel; and inputting the real-time positioning error of smart factory personnel caused by electromagnetic noise into the electromagnetic noise monitoring model to obtain the impact index of electromagnetic noise on the positioning of smart factory personnel. Using neural network algorithms, a neural network model is constructed. The real-time positioning errors of smart factory personnel caused by dust concentration, the real-time positioning errors of smart factory personnel caused by electromagnetic noise, the influence index of dust concentration on the positioning of smart factory personnel, and the influence index of electromagnetic noise on the positioning of smart factory personnel are used as datasets. The datasets are divided into training and testing sets in a 7:3 ratio. MLP is selected as the neural network structure. The input layer includes two neurons, which receive the real-time positioning errors of smart factory personnel caused by dust concentration and the real-time positioning errors of smart factory personnel caused by electromagnetic noise. The hidden layer is configured with the MSE function. The output layer includes two neurons, which output the influence index of dust concentration on the positioning of smart factory personnel and the influence index of electromagnetic noise on the positioning of smart factory personnel. The training set data is input into the neural network model, the learning rate is set to 0.01, and the number of training iterations is 1000. The training process includes forward propagation and back propagation. Forward propagation is used to calculate the predicted output data, and back propagation is used to update the model's weights and biases. Through repeated iterative training, the nonlinear relationship between the real-time positioning error of smart factory personnel caused by dust concentration and the influence index of dust concentration on the positioning of smart factory personnel, as well as the nonlinear relationship between the real-time positioning error of smart factory personnel caused by electromagnetic noise and the influence index of electromagnetic noise on the positioning of smart factory personnel, is learned until the set number of training iterations is reached, and the trained neural network model is obtained. The test set data is input into the trained neural network model. The MSE function is used to evaluate the error between the output value of the neural network model and the actual value. The parameters of the neural network model are adjusted according to the evaluation results to obtain the environmental monitoring model. The personnel scheduling module combines the smart factory 3D model and the environmental monitoring model to obtain the location of abnormal environmental data. Based on the real-time 3D positioning data of smart factory personnel, it schedules smart factory personnel to take corresponding measures. Specifically, it inputs the real-time positioning error of smart factory personnel caused by dust concentration and the real-time positioning error of smart factory personnel caused by electromagnetic noise into the environmental monitoring model. The environmental monitoring model outputs the influence index of dust concentration on the positioning of smart factory personnel and the influence index of electromagnetic noise on the positioning of smart factory personnel. When the impact index of dust concentration on personnel positioning in the smart factory is below 0.4, the impact of dust concentration on personnel positioning in the smart factory is small; when the impact index of dust concentration on personnel positioning in the smart factory is above 0.4, it indicates that the dust concentration is abnormal and has a large impact on personnel positioning in the smart factory. The three-dimensional positioning coordinates of the abnormal dust concentration are extracted from the three-dimensional model of the smart factory. Based on the real-time three-dimensional positioning data of the smart factory personnel, the distance between the three-dimensional positioning coordinates of the abnormal dust concentration and the three-dimensional positioning data of the smart factory personnel is obtained through the Euclidean formula. The smart factory personnel corresponding to the minimum distance value are extracted, and the smart factory personnel are dispatched to deal with the interference of dust concentration. When the impact index of electromagnetic noise on personnel positioning in a smart factory is below 0.3, the impact of electromagnetic noise on personnel positioning in a smart factory is small; when the impact index of electromagnetic noise on personnel positioning in a smart factory is above 0.3, it indicates that the electromagnetic noise is abnormal and has a large impact on personnel positioning in a smart factory. The three-dimensional positioning coordinates of the abnormal electromagnetic noise are extracted from the three-dimensional model of the smart factory. Based on the real-time three-dimensional positioning data of the smart factory personnel, the distance between the three-dimensional positioning coordinates of the abnormal electromagnetic noise and the three-dimensional positioning data of the smart factory personnel is obtained through the Euclidean formula. The smart factory personnel corresponding to the minimum distance value are extracted, and the personnel of the smart factory are dispatched to deal with the interference of electromagnetic noise.

2. The intelligent factory personnel positioning and scheduling system based on 3D modeling according to claim 1, characterized in that: The smart factory data acquisition module, using acquisition equipment, collects smart factory environmental data and point cloud data, including the following process: The data acquisition equipment includes a dust concentration sensor, an electromagnetic interference measuring instrument, a 3D laser scanner, a UWB positioning device, an inertial navigation positioning device, and a laser tracker. The smart factory environment data includes the dust concentration and electromagnetic noise of the smart factory environment. The smart factory personnel data includes the real-time 3D positioning coordinates of smart factory personnel and the reference 3D positioning coordinates of smart factory personnel. Using a dust concentration sensor based on the principle of light scattering, the dust concentration in the smart factory environment is collected; An electromagnetic interference measuring instrument is used to collect electromagnetic noise in the smart factory environment based on the principle of electromagnetic induction. Select a scanning station in the smart factory, fix the 3D laser scanner at the scanning station, set the scanning parameters, and obtain the position and attitude information of the 3D laser scanner. The 3D laser scanner emits a laser beam, and the time from the laser beam to its reflection back to the 3D laser scanner is measured. Combined with the position and attitude information of the 3D laser scanner, the distance between the measured point and the 3D laser scanner is calculated to obtain the point cloud data of the smart factory. UWB positioning devices consist of UWB tags, UWB base stations, and positioning engines. UWB tags are worn by personnel in smart factories, and UWB base stations are deployed in the center of the smart factory to receive UWB pulse signals. The positioning engine measures the distance between the UWB tag and the UWB base station based on the ToF ranging principle. Through a variable positioning algorithm, the real-time three-dimensional positioning coordinates of personnel in the smart factory are obtained. Using a laser tracker and based on the principle of triangulation, the initial three-dimensional positioning coordinates of personnel in the smart factory are collected. The inertial navigation and positioning equipment consists of an inertial measurement unit and a data processing unit. The inertial measurement unit measures the real-time acceleration and angular velocity of the personnel in three-dimensional space. The data processing unit receives the real-time acceleration and angular velocity of the personnel in three-dimensional space, performs integration on the received data to obtain the displacement of the personnel in three-dimensional space, and calculates the sum of the initial three-dimensional positioning coordinates and the displacement of the personnel in three-dimensional space to obtain the reference three-dimensional positioning coordinates of the personnel.

3. The intelligent factory personnel positioning and scheduling system based on 3D modeling according to claim 2, characterized in that: The preprocessing module performs data cleaning, data calibration, data standardization, and time synchronization on the collected data, including the following processes: Data cleaning, calibration, and standardization are performed on the dust concentration, electromagnetic noise, real-time 3D positioning coordinates of personnel, reference 3D positioning coordinates of personnel, and point cloud data of the smart factory environment to remove duplicate and outlier values. Timestamps are added to the collected data on dust concentration, electromagnetic noise, real-time 3D positioning coordinates of personnel, and point cloud data of the smart factory environment. Based on these timestamps, the acquisition time of the dust concentration, electromagnetic noise, real-time 3D positioning coordinates, reference 3D positioning coordinates, and point cloud data of the smart factory environment is synchronized.

4. The intelligent factory personnel positioning and scheduling system based on 3D modeling according to claim 3, characterized in that: The three-dimensional positioning module, using the Euclidean distance formula, obtains the real-time positioning error of personnel in the smart factory through the following process: The real-time positioning error of personnel in the smart factory is divided into the real-time positioning error caused by dust concentration and the real-time positioning error caused by electromagnetic noise. Extract the real-time 3D positioning coordinates and reference 3D positioning coordinates of smart factory personnel corresponding to the timestamp of dust concentration collection in the smart factory environment. Use the Euclidean distance formula to calculate the real-time positioning error of smart factory personnel caused by dust concentration. Extract the real-time 3D positioning coordinates and reference 3D positioning coordinates of smart factory personnel corresponding to the timestamp of electromagnetic noise collection in the smart factory environment. Use the Euclidean distance formula to calculate the real-time positioning error of smart factory personnel caused by electromagnetic noise.

5. The intelligent factory personnel positioning and scheduling system based on 3D modeling according to claim 4, characterized in that: The process of constructing the positioning error monitoring model by the three-dimensional positioning module includes: A random forest model was constructed using the random forest algorithm. The dataset consisted of dust concentration, electromagnetic noise, and real-time positioning errors of personnel caused by dust and electromagnetic noise in a smart factory environment. These datasets were divided into training and testing sets in a 7:3 ratio. The training set was used to train the random forest model, learning the nonlinear relationships between dust concentration and the resulting real-time positioning errors, as well as between electromagnetic noise and its effects. The trained random forest model was then evaluated using the testing set data. The model parameters were adjusted to optimize it. Finally, the optimized random forest model was deployed in a 3D modeling-based smart factory personnel positioning and scheduling system to obtain a positioning error monitoring model.

6. The intelligent factory personnel positioning and scheduling system based on 3D modeling according to claim 5, characterized in that: The process by which the three-dimensional positioning module, in conjunction with the positioning error monitoring model, updates the real-time positioning of personnel in the smart factory, constructs a three-dimensional model of the smart factory, and obtains real-time three-dimensional positioning data of personnel in the smart factory includes: The dust concentration and electromagnetic noise of the smart factory environment are input into the positioning error monitoring model. The positioning error monitoring model outputs the real-time positioning error of the smart factory personnel caused by dust concentration and the real-time positioning error of the smart factory personnel caused by electromagnetic noise, respectively. The real-time positioning coordinates of smart factory personnel are updated based on the real-time positioning errors caused by dust concentration and electromagnetic noise. The process involves extracting neighborhood points from the point cloud data of a smart factory, calculating the covariance matrix of each neighborhood point using principal component analysis, performing eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and eigenvectors, and extracting planar features from the point cloud data using these eigenvalues ​​and eigenvectors. The process also includes calculating the normal vector of each point in the point cloud data, extracting edge features based on the angle between the normal vector of each point and the normal vectors of its neighbors, and finally using the Harris corner detection algorithm to extract corner features from the point cloud data. Based on the extracted planar features, edge features, and corner features, the Delaunay triangulation algorithm is used to perform Delaunay triangulation on the point cloud data of the smart factory, connecting the discrete points in the point cloud data of each smart factory into triangular patches to construct a three-dimensional model of the smart factory. The updated real-time 3D positioning coordinates of personnel in the smart factory are mapped onto the 3D model of the smart factory to obtain real-time 3D positioning data of personnel in the smart factory.

Images