Intelligent in-transit material supervision system and method based on Unity3D engine

Abstract

The invention discloses an intelligent in-transit material supervision system and method based on a Unity 3D engine, the system comprises a front-end visualization layer, a middle-end business logic layer, a rear-end data processing layer and an Internet of Things data acquisition layer, the system deeply combines a U3D technology with specific logistics business, and through constructing a three-dimensional virtual scene, the real-time performance of the system is improved, and the real-time performance of the system is improved. The state, the position and the environment change of the materials in the transportation process are accurately reflected in real time, the transportation path is optimized, the transportation time is predicted and the transportation risk is evaluated by applying an intelligent algorithm and a calculation formula, and the purposes of improving the intelligent level of logistics supervision, guaranteeing the safety of the materials and improving the transportation efficiency are achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of logistics supervision, and in particular relates to an intelligent in-transit materials supervision system and method based on the Unity3D engine. Background Art

[0002] With the deepening development of global economic integration, the importance of the logistics industry as a key link connecting production and consumption has become increasingly prominent. However, the traditional way of supervising in-transit materials often relies on manual tracking, paper records and post-analysis, which has problems such as information lag, many blind spots in supervision and low efficiency. With the rapid development of the Internet of Things, big data, cloud computing and 3D visualization technology, new opportunities for change have been brought to logistics supervision.

[0003] As a cross-platform twin development engine, Unity3D has gradually been applied to non-game fields, such as industrial design, education and training, and urban planning, due to its powerful 3D rendering capabilities, flexible scalability, and broad user base. In the field of logistics supervision, U3D technology can be used to build a 3D logistics visualization platform to achieve intuitive display and dynamic monitoring of the material transportation process. However, there are currently few systems or methods on the market that deeply combine U3D technology with specific logistics business to comprehensively optimize the supervision of in-transit materials by intelligent means. Summary of the invention

[0004] In order to solve the problems existing in the prior art, the present invention proposes an intelligent in-transit materials supervision system and method based on the Unity3D engine.

[0005] The technical solution of the present invention is as follows: An intelligent in-transit material supervision system based on the Unity3D engine, including a front-end visualization layer, a mid-end business logic layer, a back-end data processing layer and an Internet of Things data collection layer; The front-end visualization layer is used to display the real-time location, status, environmental information and key data including transportation route planning results, estimated arrival time and safety risk level of the materials during transportation; The middle-end business logic layer is used to call the data generated by the back-end data processing layer and return the processing results to the front-end visualization layer for display; The back-end data processing layer is responsible for storing the monitoring data collected by the IoT data collection layer and generating key data such as the real-time location, status, and environmental information of the materials during transportation, as well as the transportation route planning results, the estimated arrival time, and the safety risk level. It also provides an API interface for the mid-end business logic layer to call, and monitors the monitoring data for abnormal conditions in real time for abnormal processing and feedback. The IoT data collection layer includes IoT devices composed of various sensors, RFID tags, and GPS locators installed on transport vehicles, material packaging or transportation routes, which are used to collect monitoring data related to position data, speed data, temperature data, humidity data and vibration data during material transportation in real time, and transmit them to the back-end data processing layer wirelessly.

[0006] An intelligent in-transit materials supervision method based on Unity3D engine includes the following specific steps: Step 1) Initialization: construct and render a 3D logistics scene model with road network, transport vehicles, and material model elements in the Unity3D engine; at the same time, configure the backend data processing layer; Step 2) IoT data collection: Start IoT devices installed on transport vehicles, material packaging or transport routes to collect real-time monitoring data related to location data, speed data, temperature data, humidity data and vibration data during material transportation, and transmit them to the back-end data processing layer wirelessly; Step 3) Data processing and analysis: After receiving IoT data, the back-end data processing layer first cleans and preprocesses the monitoring data to remove noise data and redundant information. Then, based on the real-time location, status, and environmental information of the materials during transportation collected by the monitoring data, the monitoring data is processed and analyzed according to the preset location tracking algorithm, path planning algorithm, and risk assessment model to generate key data including transportation path planning results, estimated arrival time, and safety risk level. Step 4) Front-end display and interaction: The mid-end business logic layer transmits the key data generated by the back-end data processing layer and the real-time location, status, and environmental information of the material transportation process to the front-end visualization layer for display; Step 5) Exception handling and feedback: During the transportation of materials, the back-end data processing layer monitors the monitoring data for abnormal conditions in real time. If an abnormal condition is detected, the alarm mechanism is triggered immediately, and an early warning is issued through the interface of the front-end visualization layer and the supervisor control platform.

[0007] Furthermore, the rendering includes rendering related to vehicle models, road textures and weather effects.

[0008] Furthermore, the IoT device includes an RFID tag and reader for identifying material ID information, a GPS module for obtaining location data and speed data in the monitoring data, a temperature sensor for obtaining temperature data in the monitoring data, a humidity sensor for obtaining humidity data in the monitoring data, and a vibration sensor for obtaining vibration data in the monitoring data.

[0009] Furthermore, the position tracking algorithm specifically comprises the following steps: 3-1) Position tracking algorithm, based on the speed data in the monitoring data, uses the particle filter algorithm to accurately track the location of the material; at the initial moment t =0, from the initial probability distribution p ( x 0) randomly selects N samples: x0(i)∼p(x0), i=1,2,…,N; where x0(i) represents the state of the i-th sample at the initial moment; For each sample, prediction is made according to the state transition equation of the system to obtain the predicted particle set: xt(i)∼p(xt|xt−1(i)), i=1,2,…,N; xt(i) represents the state of the i-th sample at time t; p(xt|xt−1(i)) represents the probability distribution of the current time step xt given the state xt−1(i) of the i-th particle at the previous time step (t-1); The position coordinates are obtained through the particle set weights, thereby achieving position tracking.

[0010] The specific steps of the path planning algorithm include: 3-2) For the path planning process, RRT-STAR is used to plan the optimal transportation path for materials based on multi-dimensional factors such as real-time road conditions, traffic rules, transportation costs and material characteristics. In RRT-STAR, each node q has an associated cost c(q), which represents the minimum known path cost from the starting point q_start to the node q. The cost calculation formula is: c(q)=c(parent(q))+distance(parent(q),q)]; Where parent(q) is the parent node of node q, and distance(parent(q),q) is the Euclidean distance from the parent node to node q; The method for constructing the risk assessment model includes: 3-3) Establish a risk assessment model based on the real-time collected temperature data, humidity data, and vibration data; the risk assessment model formula is specifically expressed as: Y=beta_0+beta_1X_1+beta_2X_2+beta_3X_3+epsilon; Among them, Y is the risk assessment result, beta_0 is the constant term, X_1 is the mileage, X_2 is the number of deliveries, X_3 is the traffic congestion condition, beta_1, beta_2, beta_3 are the regression coefficients corresponding to the mileage, number of deliveries and traffic congestion condition respectively, and epsilon is the random error term.

[0011] Compared with the prior art, the present invention has the following beneficial effects: The present invention proposes an intelligent in-transit material supervision system and method based on the Unity3D engine. The system and method deeply combine U3D technology with specific logistics business, and reflect the status, location and environmental changes of materials in the transportation process in real time and accurately by constructing a three-dimensional virtual scene. Intelligent algorithms and calculation formulas are used to optimize transportation routes, predict transportation time, and evaluate transportation risks. The purpose is to enhance the intelligence level of logistics supervision, ensure material safety, and improve transportation efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0012] Figure 1 It is a block diagram of an intelligent in-transit material supervision system based on the Unity3D engine in the embodiment; Figure 2 The figure is a flow chart of the intelligent in-transit materials supervision method based on the Unity3D engine in the embodiment. DETAILED DESCRIPTION

[0013] The present invention is further explained below in conjunction with the accompanying drawings and specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not used to limit the scope of the present invention. After reading the present invention, various equivalent modifications of the present invention by those skilled in the art all fall within the scope defined by the claims attached to this application.

[0014] Example: The present invention provides an intelligent in-transit material supervision system based on Unity3D engine, such as Figure 1 As shown, it includes the front-end visualization layer, the mid-end business logic layer, the back-end data processing layer and the Internet of Things data collection layer; The front-end visualization layer is a three-dimensional virtual scene built based on the Unity3D engine, which is used to display the real-time location, status, environmental information, and key data including transportation route planning results, estimated arrival time, and safety risk level during the transportation process; The middle-end business logic layer is used to receive requests sent by the front-end, call the data generated by the back-end data processing layer and return the processing results to the front-end visualization layer for display; The back-end data processing layer, including infrastructure such as database servers, computing servers and cloud service platforms, is responsible for storing the monitoring data collected by the IoT data collection layer and generating key data such as the real-time location, status, and environmental information of materials during transportation, as well as transportation route planning results, estimated arrival time, and safety risk level. It also provides an API interface for the mid-end business logic layer to call, and monitors abnormal conditions of the monitoring data in real time for abnormal processing and feedback. The IoT data collection layer includes IoT devices consisting of various sensors, RFID tags, and GPS locators installed on transport vehicles, material packaging, or transportation routes. It is used to collect real-time monitoring data related to location data, speed data, temperature data, humidity data, and vibration data during the material transportation process, and transmit it wirelessly to the back-end data processing layer.

[0015] The present invention provides an intelligent in-transit materials supervision method based on Unity3D engine, such as Figure 2 As shown, the specific steps are as follows: Step 1) Initialization: Build and render a 3D logistics scene model with road network, transport vehicles, and material model elements in the Unity3D engine; at the same time, configure the back-end data processing layer related to the database server, computing server, and cloud service platform to ensure the stability and reliability of data storage and computing services; Step 2) IoT data collection: Start IoT devices installed on transport vehicles, material packaging or transport routes to collect real-time monitoring data related to location data, speed data, temperature data, humidity data and vibration data during material transportation, and transmit them to the back-end data processing layer wirelessly; Step 3) Data processing and analysis: After the back-end data processing layer receives the IoT data, it first cleans and preprocesses the monitoring data to remove noise data and redundant information. Then, based on the real-time location, status, and environmental information of the materials during transportation collected by the monitoring data, the monitoring data is processed and analyzed according to the preset location tracking algorithm, path planning algorithm, and risk assessment model to generate key data including transportation path planning results, estimated arrival time, and safety risk level. Specifically, the distributed database system MongoDB is used to store a large amount of real-time data and support high concurrent access. Data cleaning and compression algorithms are used to improve the efficiency of data transmission and storage.

[0016] Step 4) Front-end display and interaction: The mid-end business logic layer transmits the key data generated by the back-end data processing layer and the real-time location, status, and environmental information during the material transportation process to the front-end visualization layer for display; users can access the three-dimensional logistics scene through devices such as PC, tablet or mobile phone, and view the location, status, environmental information and path planning results of the material transportation process in real time. At the same time, the system provides interactive functions, allowing users to adjust the path, query historical data, receive alarm information, etc.

[0017] Step 5) Exception handling and feedback: During the transportation of materials, the back-end data processing layer monitors the monitoring data for abnormal conditions in real time. If an abnormal condition is detected, such as excessive temperature or abnormal humidity, the alarm mechanism is triggered immediately, and an early warning is issued through the interface of the front-end visualization layer and the supervisor control platform. Supervisors are also notified through SMS, email and other methods. Supervisors can respond quickly based on the alarm information and take corresponding measures to ensure the safety and timeliness of materials. The judgment of abnormal conditions adopts the method of comparing the real-time monitoring data with the set threshold range. If the real-time monitoring data exceeds the set threshold, it is considered that an abnormal condition has occurred.

[0018] Furthermore, rendering can be performed using HDRP, an advanced rendering function of the Unity3D engine, and the rendering includes rendering related to vehicle models, road textures, and weather effects.

[0019] Furthermore, the IoT device includes an RFID tag and reader for identifying material ID information, a GPS module for obtaining location data and speed data in the monitoring data, a temperature sensor for obtaining temperature data in the monitoring data, a humidity sensor for obtaining humidity data in the monitoring data, and a vibration sensor for obtaining vibration data in the monitoring data.

[0020] Furthermore, the specific steps of the location tracking algorithm include: 3-1) Position tracking algorithm, based on GPS positioning data in monitoring data and auxiliary information of IoT sensors: with directional speed data, particle filter algorithm is used to accurately track the location of materials; at the initial moment t =0, from the initial probability distribution p ( x 0) randomly selects N samples: x0(i)∼p(x0), i=1,2,…,N; where x0(i) represents the state of the i-th sample at the initial moment; For each sample, prediction is made according to the state transition equation of the system to obtain the predicted particle set: xt(i)∼p(xt|xt−1(i)), i=1,2,…,N; xt(i) represents the state of the i-th sample at time t; p(xt|xt−1(i)) represents the probability distribution of the current time step xt given the state xt−1(i) of the i-th particle at the previous time step (t-1); The position coordinates are obtained through the particle set weights, thereby achieving position tracking.

[0021] The specific steps of the path planning algorithm include: 3-2) For the path planning process, RRT-STAR is used to plan the optimal transportation path for materials based on multi-dimensional factors such as real-time road conditions, traffic rules, transportation costs and material characteristics. In RRT-STAR, each node q has an associated cost c(q), which represents the minimum known path cost from the starting point q_start to the node q. The cost calculation formula is: c(q)=c(parent(q))+distance(parent(q),q)]; Where parent(q) is the parent node of node q, and distance(parent(q),q) is the Euclidean distance from the parent node to node q; The methods for constructing risk assessment models include: 3-3) Establish a risk assessment model based on the real-time collected temperature data, humidity data, vibration data and the characteristics of perishable, flammable, explosive and other materials; the risk assessment model formula is specifically expressed as: Y=beta_0+beta_1X_1+beta_2X_2+beta_3X_3+epsilon; Among them, Y is the risk assessment result, beta_0 is the constant term, X_1 is the mileage, X_2 is the number of deliveries, X_3 is the traffic congestion condition, beta_1, beta_2, beta_3 are the regression coefficients corresponding to the mileage, number of deliveries and traffic congestion condition, respectively, indicating the degree of influence, and epsilon is the random error term.

[0022] The above description is only a specific implementation of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by a technician familiar with the technical field within the technical scope disclosed by the present invention should be covered by the protection scope of the present invention.

Claims

1. An intelligent in-transit material supervision system based on Unity3D engine, characterized in that: It includes the front-end visualization layer, the mid-end business logic layer, the back-end data processing layer and the IoT data collection layer; The front-end visualization layer is used to display the real-time location, status, environmental information and key data including transportation route planning results, estimated arrival time and safety risk level of the materials during transportation; The middle-end business logic layer is used to call the data generated by the back-end data processing layer and return the processing results to the front-end visualization layer for display; The back-end data processing layer is responsible for storing the monitoring data collected by the IoT data collection layer and generating key data such as the real-time location, status, and environmental information of the materials during transportation, as well as the transportation route planning results, the estimated arrival time, and the safety risk level. It also provides an API interface for the mid-end business logic layer to call, and monitors the monitoring data for abnormal conditions in real time for abnormal processing and feedback. The IoT data collection layer includes IoT devices composed of various sensors, RFID tags, and GPS locators installed on transport vehicles, material packaging or transportation routes, which are used to collect monitoring data related to position data, speed data, temperature data, humidity data and vibration data during material transportation in real time, and transmit them to the back-end data processing layer wirelessly.

2. An intelligent in-transit goods supervision method based on Unity3D engine, characterized in that: The specific steps include: Step 1) Initialization: construct and render a 3D logistics scene model with road network, transport vehicles, and material model elements in the Unity3D engine; at the same time, configure the backend data processing layer; Step 2) IoT data collection: Start IoT devices installed on transport vehicles, material packaging or transport routes to collect real-time monitoring data related to location data, speed data, temperature data, humidity data and vibration data during material transportation, and transmit them to the back-end data processing layer wirelessly; Step 3) Data processing and analysis: After receiving IoT data, the back-end data processing layer first cleans and preprocesses the monitoring data to remove noise data and redundant information. Then, based on the real-time location, status, and environmental information of the materials during transportation collected by the monitoring data, the monitoring data is processed and analyzed according to the preset location tracking algorithm, path planning algorithm, and risk assessment model to generate key data including transportation path planning results, estimated arrival time, and safety risk level. Step 4) Front-end display and interaction: The mid-end business logic layer transmits the key data generated by the back-end data processing layer and the real-time location, status, and environmental information of the material transportation process to the front-end visualization layer for display; Step 5) Exception handling and feedback: During the transportation of materials, the back-end data processing layer monitors the monitoring data for abnormal conditions in real time. If an abnormal condition is detected, the alarm mechanism is triggered immediately, and an early warning is issued through the interface of the front-end visualization layer and the supervisor control platform.

3. The intelligent in-transit goods supervision method based on Unity3D engine according to claim 2 is characterized in that: The rendering includes rendering related to vehicle models, road textures and weather effects.

4. The intelligent in-transit goods supervision method based on Unity3D engine according to claim 3 is characterized in that: The IoT device includes an RFID tag and reader for identifying material ID information, a GPS module for obtaining location data and speed data in the monitoring data, a temperature sensor for obtaining temperature data in the monitoring data, a humidity sensor for obtaining humidity data in the monitoring data, and a vibration sensor for obtaining vibration data in the monitoring data.

5. The intelligent in-transit goods supervision method based on Unity3D engine according to claim 4 is characterized in that: The specific steps of the position tracking algorithm include: 3-1) Position tracking algorithm, based on the speed data in the monitoring data, uses the particle filter algorithm to accurately track the location of the material; at the initial moment t =0, from the initial probability distribution p ( x 0) randomly selects N samples: x0(i)∼p(x0), i=1,2,…,N; where x0(i) represents the state of the i-th sample at the initial moment; For each sample, prediction is made according to the state transition equation of the system to obtain the predicted particle set: xt(i)∼p(xt|xt−1(i)), i=1,2,…,N; xt(i) represents the state of the i-th sample at time t; p(xt|xt−1(i)) represents the probability distribution of the current time step xt given the state xt−1(i) of the i-th particle at the previous time step (t-1); The position coordinates are obtained through the particle set weights, thereby achieving position tracking; The specific steps of the path planning algorithm include: 3-2) For the path planning process, RRT-STAR is used to plan the optimal transportation path for materials based on multi-dimensional factors such as real-time road conditions, traffic rules, transportation costs and material characteristics. In RRT-STAR, each node q has an associated cost c(q), which represents the minimum known path cost from the starting point q_start to the node q. The cost calculation formula is: c(q)=c(parent(q))+distance(parent(q),q)]; Where parent(q) is the parent node of node q, and distance(parent(q),q) is the Euclidean distance from the parent node to node q; The method for constructing the risk assessment model includes: 3-3) Establish a risk assessment model based on the real-time collected temperature data, humidity data, and vibration data; the risk assessment model formula is specifically expressed as: Y=beta_0+beta_1X_1+beta_2X_2+beta_3X_3+epsilon; Among them, Y is the risk assessment result, beta_0 is the constant term, X_1 is the mileage, X_2 is the number of deliveries, X_3 is the traffic congestion condition, beta_1, beta_2, beta_3 are the regression coefficients corresponding to the mileage, number of deliveries and traffic congestion condition respectively, and epsilon is the random error term.

Images