Smart material yard distribution, storage and transportation control system and method based on data analysis
Through technologies such as the Internet of Things, edge computing and deep reinforcement learning, an intelligent material field management system is built, which solves the problems of data silos, insufficient intelligence and insufficient emergency response capabilities of traditional material field management systems, and realizes the storage and transportation management of material field Efficient intelligence and automation.
Patent Information
- Application Number
- CN202411240260.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-05
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-09-05
AI Technical Summary
The traditional material yard management system lacks a unified data platform, resulting in data silos, cumbersome operations, high error rates, unable to respond to market changes and production demands in real time, and insufficient data analysis and prediction capabilities, weak intelligence and automation, and system integration and The scalability is limited, the emergency response and collaborative operation capabilities are insufficient, and the visualization effect is poor.
Through the Internet of Things and sensors, real-time monitoring of material data in the material field, combining three-dimensional laser scanning and augmented reality to build dynamic models, edge computing and preprocessing data, use intelligent adaptive prediction strategies to optimize replenishment strategies and perform blockchain storage, and build multi-dimensional composites Indicator and statistical anomaly detection mechanism, use deep reinforcement learning to plan the optimal distribution path, establish an intelligent scheduling system and emergency response platform, introduce intelligent collaborative operations, and realize real-time data sharing and efficient emergency response.
Improve the intelligence, automation and emergency response capabilities of material yard storage and transportation management, simplify operational processes, reduce operational risks, improve response speed and flexibility, ensure the safety and traceability of adaptive prediction strategies, and enhance Visualization effect.
Smart Images

Figure CN118761699B_ABST
Abstract
Description
Technical Field
[0001] The present invention belongs to the technical field of data monitoring, and more specifically to a smart material yard distribution, storage and transportation management and control system and method based on data analysis. Background Art
[0002] In the field of modern industry and logistics, with the expansion of enterprise scale and the complexity of business, the material yard is a key link in the storage and transfer of raw materials and finished products. Its management efficiency directly affects the smooth operation and cost control of the entire production chain. Traditional material yard management systems often lack a unified data platform, and information is not shared between departments, resulting in serious data islands and difficulty in forming global decision support; manual scheduling, recording and management lead to cumbersome operations, high error rates, and inability to respond to market changes and production needs in real time; inventory backlogs and low cargo turnover rates cause capital occupation and waste of storage space. Therefore, the traditional material yard distribution, storage and transportation management model has been difficult to meet the needs of efficiency, accuracy and intelligence.
[0003] For example, the patent with the authorization announcement number CN110019623B discloses an intelligent monitoring system for fuel storage and transportation in a steel raw material yard, including: a yard information module, an inventory management module, a yard three-dimensional simulation module and a report management module; the yard information module includes a yard database unit, a yard real-time transceiver unit, and a yard electronic map unit; the inventory management module includes a laser data acquisition and point cloud data processing unit, a volume model calculation unit, a inventory management unit, and an inventory query and correction unit; the three-dimensional simulation module includes a scene three-dimensional model unit, a virtual guide unit, and a real-time on-site dynamic visualization unit. This invention comprehensively uses information networks, automatic control, 3D scanning, mobile Internet, GIS geographic space information, intelligent identification, precise positioning, and cloud computing technology to build an integrated smart yard, which can reduce labor intensity, optimize the labor environment, improve labor efficiency, and reduce labor costs, helping enterprises to improve profitability and gain competitive advantages.
[0004] The above existing technologies all have the following problems: 1) Insufficient data analysis and prediction capabilities; 2) Weak intelligence and automation; 3) Limited system integration and scalability; 4) Insufficient emergency response and collaborative work capabilities; 5) Poor visualization effect. Summary of the invention
[0005] In view of the shortcomings of the existing technology, the present invention proposes a smart material yard distribution, storage and transportation management and control system and method based on data analysis. The material yard material data is monitored in real time through the Internet of Things and sensors, and a dynamic model is built by combining three-dimensional laser scanning and augmented reality. Edge computing pre-processes data to generate a storage and transportation data set; based on the data set, an intelligent adaptive prediction strategy is adopted to optimize the replenishment strategy and store it on the blockchain; a multi-dimensional composite indicator and statistical anomaly detection mechanism are constructed to realize automatic identification and dynamic adjustment of anomalies, and deep reinforcement learning is used to plan the optimal distribution path; an intelligent scheduling system and emergency response platform are constructed to integrate resources and plans, and introduce intelligent collaborative operations to realize real-time data sharing and efficient emergency response, and comprehensively improve the intelligence, automation and emergency handling capabilities of material storage and transportation management.
[0006] To achieve the above object, the present invention provides the following technical solutions:
[0007] The intelligent material yard distribution, storage and transportation control method based on data analysis includes:
[0008] Step S1: Real-time monitoring of material storage and transportation data in the material yard through the Internet of Things and sensors, and three-dimensional dynamic modeling of the material yard using three-dimensional laser scanning and augmented reality. At the same time, at the source of data collection, edge computing methods are used for preliminary processing and integration to obtain material storage and transportation data sets;
[0009] Step S2: Based on the material storage and transportation data set, use the intelligent adaptive forecasting strategy to predict the changing trends of material demand, inventory level and transportation efficiency. According to the forecast results and current inventory status, formulate an adaptive replenishment strategy, optimize the replenishment strategy and store it on the blockchain;
[0010] Step S3: Construct a multi-dimensional composite indicator system, use a statistical anomaly detection algorithm to perform real-time detection on material storage and transportation data to determine whether it falls within the abnormal range. If an abnormality is detected, start the adaptive dynamic adjustment mechanism, and use the deep reinforcement learning strategy to generate the optimal distribution path based on the adjusted material storage and transportation data;
[0011] Step S4: Build an intelligent scheduling system based on reinforcement learning, establish an intelligent emergency response platform based on big data and AI, integrate a variety of emergency resources and plans, introduce an intelligent collaborative operation system, and update and share material storage and transportation data, distribution routes, and emergency response information in real time.
[0012] Specifically, the specific implementation steps of step S2 include:
[0013] S2.1: Receive material storage and transportation data set , select the adaptive prediction model based on machine learning algorithm combined with time series analysis, and use the material storage and transportation data set The adaptive prediction model is trained and the optimal adaptive prediction model is selected by cross-validation method, where: Indicates the nth material storage and transportation data, where n indicates the number of material storage and transportation data;
[0014] S2.2: Analyze the material demand, inventory level and transportation efficiency trends predicted by the optimal adaptive forecasting model, identify the supply and demand gap, and formulate an adaptive replenishment strategy based on the forecast results and current inventory levels. At the same time, use a multi-objective optimization algorithm to optimize the replenishment strategy combination;
[0015] S2.3: Write a smart contract based on the optimal replenishment strategy combination and deploy the smart contract on the blockchain.
[0016] Specifically, the specific steps of S2.2 include:
[0017] S2.21: Extract the prediction value of the optimal adaptive prediction model , and compare the predicted material demand with the current and future inventory levels to calculate the supply-demand gap, where: It represents the forecast value of the storage and transportation data of the nth material. The calculation formula of the supply-demand gap is:
[0018]
[0019] in, represents the supply-demand gap value at time t, represents the forecast value of material demand at time t, represents the current inventory at time t, represents the delay rate at time t, represents the expected arrival quantity at time t, represents the safety stock at time t, represents the replacement rate at time t, represents the substitutable inventory at time t, represents the backlog of orders at time t;
[0020] S2.22: Preliminarily set the parameters of the replenishment strategy based on the supply-demand gap and current inventory levels.
[0021] Specifically, the specific steps of S2.2 also include:
[0022] S2.23: Set the goal of replenishment strategy optimization and generate multi-objective function;
[0023] S2.24: Set the parameters of the multi-objective optimization algorithm, and use the parameters of the replenishment strategy as optimization variables and input them into the multi-objective optimization algorithm;
[0024] S2.25: Run the multi-objective optimization algorithm to iteratively search for the optimal replenishment strategy combination. In each iteration, evaluate the performance of the current replenishment strategy combination, calculate its corresponding objective function value, and adjust the parameters of the replenishment strategy according to the update rule of the optimization algorithm;
[0025] S2.26: Based on the output of the multi-objective optimization algorithm, select a set of optimal replenishment strategy combinations and deploy the optimal replenishment strategy combination, monitor the difference between the actual situation and the predicted results during the replenishment process, and adjust the strategy in time to adapt to changes.
[0026] Specifically, the specific formula of the multi-objective function in S2.23 is:
[0027]
[0028] in, represents the total resource consumption, Indicates the resource consumption for each replenishment, A binary variable indicating whether replenishment is performed at time t. 1 means replenishment, 0 means no replenishment. Indicates the resources held per unit of time and per unit of inventory. represents the replenishment quantity at time t, represents the length of time t, Indicates that the unit is out of stock of resources. express The out-of-stock change function at time, Indicates the quality of resources, represents the weight of time t, B t represents the out-of-stock quantity at time t, It represents the transport efficiency, represents the unit transportation resource consumption from supply source j to time t, represents the replenishment quantity from supply source j at time t, C represents the multi-objective optimization problem function, T represents the set of time periods, and J represents the set of supply sources or transportation routes.
[0029] Specifically, the specific steps of step S3 include:
[0030] S3.1: According to the characteristics of material storage and transportation data, determine the monitoring dimension indicators, including inventory volume, inventory turnover rate, transportation time, transportation resources, and loss rate, and assign weights to each monitoring dimension indicator, construct weighted composite indicators, and obtain a multi-dimensional composite indicator system;
[0031] S3.2: Load the trained anomaly detection model and input the material storage and transportation data into the anomaly detection model for anomaly detection;
[0032] S3.3: Analyze and compare the output results of the anomaly detection model with the weighted composite indicators in the multi-dimensional composite indicator system to determine whether the material storage and transportation data falls within the abnormal range;
[0033] S3.4: If an anomaly is detected, the adaptive dynamic adjustment mechanism is initiated according to the preset rules, and the multi-dimensional composite indicator system and anomaly detection model are re-evaluated and adjusted based on the adjusted material storage and transportation data.
[0034] Specifically, the specific steps of step S3 also include:
[0035] S3.5: Load the pre-trained distribution path optimization model and abstract the material storage and transportation distribution problem into a reinforcement learning environment;
[0036] S3.6: Use deep reinforcement learning algorithms to train the delivery path optimization model and find the optimal delivery path through trial and error and iterative optimization;
[0037] S3.7: Input the adjusted material storage and transportation data into the trained distribution path optimization model to generate the optimal distribution path.
[0038] The intelligent material yard distribution, storage and transportation management and control system based on data analysis includes: intelligent prediction module, risk assessment module and intelligent scheduling module;
[0039] The intelligent prediction module includes an intelligent prediction unit, in which an intelligent adaptive prediction strategy is configured, and the intelligent adaptive prediction strategy is used to predict the changing trends of material demand, inventory level and transportation efficiency, and generate replenishment suggestions accordingly;
[0040] The risk assessment module includes a risk assessment unit and an anomaly detection unit. The risk assessment unit is configured with a multi-dimensional composite indicator system, which is used to conduct a comprehensive quantitative assessment of risk factors in the storage and transportation process of the material field. The anomaly detection unit is configured with a statistical anomaly detection algorithm, which is used to perform anomaly detection on the storage and transportation data of the material field, and to determine whether the data belongs to the abnormal range by calculating the statistics of the data and comparing it with the preset threshold value;
[0041] The intelligent scheduling module includes a scheduling algorithm unit and a path planning unit. The scheduling algorithm unit is configured with a scheduling strategy, which is used to intelligently schedule and optimize the storage and transportation resources of the material yard. The path planning unit is used to plan the optimal driving path for the transport vehicle.
[0042] Specifically, an electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a smart material yard distribution, storage and transportation management and control method based on data analysis are implemented.
[0043] Specifically, a computer-readable storage medium stores computer instructions, which, when executed, execute the steps of a smart material yard distribution, storage and transportation control method based on data analysis.
[0044] Compared with the prior art, the present invention has the following beneficial effects:
[0045] 1. The present invention proposes a smart material yard distribution, storage and transportation management and control system based on data analysis, and optimizes and improves the architecture, operation steps and processes. The system has the advantages of simple process, low investment and operation costs, and low production work costs.
[0046] 2. The present invention proposes a smart material yard distribution, storage and transportation management and control method based on data analysis, constructs a multi-dimensional composite indicator system, and uses a statistical anomaly detection algorithm to perform real-time detection of material storage and transportation data, which can promptly discover and handle abnormal situations and reduce operational risks; the introduction of an adaptive dynamic adjustment mechanism enables the system to automatically adjust the distribution path and inventory management strategy according to real-time data, thereby improving response speed and flexibility; the application of blockchain technology ensures the security and traceability of the adaptive prediction strategy, and improves the transparency and reliability of the execution of the adaptive prediction strategy.
[0047] 3. The present invention proposes a smart material yard distribution, storage and transportation management and control method based on data analysis, constructs an intelligent scheduling system, an intelligent emergency response platform and an intelligent collaborative operation system based on reinforcement learning, and realizes intelligence and automation; through three-dimensional dynamic modeling and real-time on-site dynamic visualization technology, the visualization effect is enhanced. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] Figure 1 It is a schematic diagram of the intelligent material yard distribution, storage and transportation control method based on data analysis of the present invention;
[0049] Figure 2 This is a principle flow chart of the intelligent material yard distribution, storage and transportation control method based on data analysis of the present invention;
[0050] Figure 3 This is a flow chart for implementing the adaptive prediction strategy of the intelligent material yard distribution, storage and transportation control method based on data analysis of the present invention;
[0051] Figure 4 This is an architecture diagram of the smart material yard distribution, storage and transportation management and control system based on data analysis in the present invention. DETAILED DESCRIPTION
[0052] Example 1
[0053] See also Figure 1-Figure 3 The present invention provides an embodiment: a smart material yard distribution storage and transportation control method based on data analysis, comprising:
[0054] Step S1: Real-time monitoring of material storage and transportation data in the material yard through the Internet of Things and sensors, and three-dimensional dynamic modeling of the material yard using three-dimensional laser scanning and augmented reality. At the same time, at the source of data collection, edge computing methods are used for preliminary processing and integration to obtain material storage and transportation data sets, where: Indicates the nth material storage and transportation data, where n indicates the number of material storage and transportation data;
[0055] Furthermore, the specific steps of step S1 include:
[0056] (1) IoT and sensor deployment: According to the actual needs of the material yard, weight sensors, position sensors, temperature sensors, and humidity sensors are installed at key locations of the material yard, such as material stacking areas, conveyor belts, and storage warehouses, and ensure that the sensors can work stably and transmit data in real time;
[0057] (2) Data collection and transmission: IoT sensors collect material storage and transportation data in real time, and transmit the data to the data collection system or edge computing node wirelessly or wiredly to ensure the real-time and accuracy of the data;
[0058] (3) 3D laser scanning modeling: Design a scanning plan based on the specific conditions and needs of the material yard, including scanning path, scanning point setting, and scanning time. Use a 3D laser scanner to scan the material yard to obtain 3D point cloud data of the material pile. At the same time, pre-process the 3D point cloud data obtained by scanning, including denoising, filtering, and registration, to improve data quality.
[0059] (4) Augmented reality fusion: Use 3D modeling software to convert the processed point cloud data into a 3D model, combine the 3D model with augmented reality technology, and use AR devices such as AR glasses and tablets to display the 3D dynamic model of the material pile in the real environment to achieve virtual-real fusion;
[0060] (5) Preliminary processing of edge computing: Deploy edge computing nodes at or near the source of data collection, and use the computing power of edge computing nodes to perform preliminary processing and integration of the collected data, such as data compression, feature extraction, and feature analysis, to reduce the amount of data transmission and improve the efficiency of subsequent processing.
[0061] Step S2: Based on the material storage and transportation data set, use the intelligent adaptive forecasting strategy to predict the changing trends of material demand, inventory level and transportation efficiency. According to the forecast results and current inventory status, formulate an adaptive replenishment strategy, optimize the replenishment strategy and store it on the blockchain;
[0062] Step S3: Construct a multi-dimensional composite indicator system, use a statistical anomaly detection algorithm to perform real-time detection on material storage and transportation data to determine whether it falls within the abnormal range. If an abnormality is detected, start the adaptive dynamic adjustment mechanism, and use the deep reinforcement learning strategy to generate the optimal distribution path based on the adjusted material storage and transportation data;
[0063] Step S4: Build an intelligent scheduling system based on reinforcement learning, establish an intelligent emergency response platform based on big data and AI, integrate a variety of emergency resources and plans, introduce an intelligent collaborative operation system, and update and share material storage and transportation data, distribution routes, and emergency response information in real time.
[0064] The specific implementation steps of step S2 include:
[0065] S2.1: Receive material storage and transportation data set , select the adaptive prediction model based on machine learning algorithm combined with time series analysis, and use the material storage and transportation data set The adaptive prediction model is trained and the optimal adaptive prediction model is selected by cross-validation method;
[0066] Furthermore, the specific implementation steps of S2.1 include:
[0067] (1) Data preparation: collecting, cleaning, and preprocessing material storage and transportation data sets;
[0068] (2) Algorithm selection: Select machine learning algorithms and adaptive prediction models based on the characteristics of the data set;
[0069] (3) Divide the data set: divide the data set into training set, validation set and test set;
[0070] (4) Model training: Use training set data to train the adaptive prediction model;
[0071] (5) Cross-validation: Evaluate the performance of the adaptive prediction model through cross-validation and adjust the parameters of the adaptive prediction model;
[0072] (6) Model selection: Select the optimal adaptive prediction model based on the cross-validation results;
[0073] (7) Model evaluation: Use the test set to evaluate the performance of the final adaptive prediction model.
[0074] S2.2: Analyze the material demand, inventory level and transportation efficiency trends predicted by the optimal adaptive forecasting model, identify the supply and demand gap, and formulate an adaptive replenishment strategy based on the forecast results and current inventory levels. At the same time, use a multi-objective optimization algorithm to optimize the replenishment strategy combination;
[0075] S2.3: Write a smart contract based on the optimal replenishment strategy combination and deploy the smart contract on the blockchain.
[0076] The specific steps of S2.2 include:
[0077] S2.21: Extract the prediction value of the optimal adaptive prediction model , and compare the predicted material demand with the current and future inventory levels to calculate the supply-demand gap, where: It represents the forecast value of the storage and transportation data of the nth material. The calculation formula of the supply-demand gap is:
[0078]
[0079] in, represents the supply-demand gap value at time t, represents the forecast value of material demand at time t, represents the current inventory at time t, represents the delay rate at time t, represents the expected arrival quantity at time t, represents the safety stock at time t, represents the replacement rate at time t, represents the substitutable inventory at time t, represents the backlog of orders at time t;
[0080] S2.22: Preliminarily set the parameters of the replenishment strategy based on the supply-demand gap and current inventory levels;
[0081] S2.23: Set the goal of replenishment strategy optimization and generate a multi-objective function. The specific formula of the multi-objective function is:
[0082]
[0083] in, represents the total resource consumption, Indicates the resource consumption for each replenishment, A binary variable indicating whether replenishment is performed at time t. 1 means replenishment, 0 means no replenishment. Indicates the resources held per unit of inventory per unit of time, represents the replenishment quantity at time t, represents the length of time t, Indicates that the unit is out of stock of resources. express The out-of-stock change function at time arrive Continuous changes in inventory status within a time period, Indicates the quality of resources, represents the weight of time t, B t Represents the out-of-stock quantity at time t, which is a state value at a discrete time point t and a specific value. It represents the transport efficiency, represents the unit transportation resource consumption from supply source j to time t, represents the replenishment quantity from supply source j at time t, C represents the multi-objective optimization problem function, T represents the set of time periods, and J represents the set of supply sources or transportation routes;
[0084] S2.24: Set the parameters of the multi-objective optimization algorithm, and use the parameters of the replenishment strategy as optimization variables and input them into the multi-objective optimization algorithm;
[0085] S2.25: Run the multi-objective optimization algorithm to iteratively search for the optimal replenishment strategy combination. In each iteration, evaluate the performance of the current replenishment strategy combination, calculate its corresponding objective function value, and adjust the parameters of the replenishment strategy according to the update rule of the optimization algorithm;
[0086] Furthermore, the specific steps of S2.25 include:
[0087] (1) Problem definition and modeling
[0088] Identify multiple goals for optimizing replenishment strategies , , , define decision variables, such as replenishment quantity, replenishment time, and replenishment frequency, and establish objective functions and constraints to transform practical problems into mathematical models;
[0089] (2) Selecting a multi-objective optimization algorithm
[0090] Select a suitable multi-objective optimization algorithm according to the characteristics and requirements of the problem. The present invention selects a particle swarm optimization algorithm combined with a genetic algorithm;
[0091] (3) Algorithm initialization
[0092] Initialize the multi-objective optimization algorithm parameters, such as population size, number of iterations, crossover rate, and mutation rate, to generate an initial solution set, i.e., an initial replenishment strategy combination;
[0093] (4) Evaluate the performance of the solution
[0094] Evaluate the performance of the replenishment strategy combination and use the evaluation function to calculate the corresponding objective function value;
[0095] (5) Iterative Optimization
[0096] Generate new replenishment strategy combinations based on the update rules of the multi-objective optimization algorithm, such as selection, crossover, and mutation, evaluate the performance of the new replenishment strategy combinations, and compare them with the old replenishment strategy combinations. Select the solution with better performance to enter the next generation of iteration based on the comparison results.
[0097] (6) Convergence judgment
[0098] Check whether the convergence conditions are met, such as reaching the maximum number of iterations. If the convergence conditions are met, output the optimal replenishment strategy combination, otherwise, continue iterative optimization.
[0099] S2.26: Based on the output of the multi-objective optimization algorithm, select a set of optimal replenishment strategy combinations and deploy the optimal replenishment strategy combination, monitor the difference between the actual situation and the predicted results during the replenishment process, and adjust the strategy in time to adapt to changes.
[0100] The specific steps of step S3 include:
[0101] S3.1: According to the characteristics of material storage and transportation data, determine the monitoring dimension indicators, including inventory volume, inventory turnover rate, transportation time, transportation resources, and loss rate, and assign weights to each monitoring dimension indicator, construct weighted composite indicators, and obtain a multi-dimensional composite indicator system;
[0102] S3.2: Load the trained anomaly detection model and input the material storage and transportation data into the anomaly detection model for anomaly detection;
[0103] S3.3: Analyze and compare the output results of the anomaly detection model with the weighted composite indicators in the multi-dimensional composite indicator system to determine whether the material storage and transportation data falls within the abnormal range;
[0104] S3.4: If an anomaly is detected, the adaptive dynamic adjustment mechanism is activated according to the preset rules, and the multi-dimensional composite indicator system and anomaly detection model are re-evaluated and adjusted based on the adjusted material storage and transportation data;
[0105] S3.5: Load the pre-trained distribution path optimization model, and abstract the distribution problem of material storage and transportation into an environment in reinforcement learning, wherein the training process of the optimization model is the prior art content in this field, and is not the inventive solution of this application, and will not be described in detail here;
[0106] S3.6: Use a deep reinforcement learning algorithm to train the delivery path optimization model, and find the optimal delivery path through continuous trial and error and iterative optimization. The deep reinforcement learning algorithm is a prior art content in this field, and is not an inventive solution of this application, and will not be described in detail here;
[0107] S3.7: Input the adjusted material storage and transportation data into the trained distribution path optimization model to generate the optimal distribution path.
[0108] Example 2
[0109] See also Figure 4 , another embodiment provided by the present invention: a smart material yard distribution storage and transportation management and control system based on data analysis, including: a data acquisition module, an intelligent prediction module, a risk assessment module, an intelligent scheduling module, and a decision support module;
[0110] The data acquisition module is used to monitor the material storage and transportation data from different sources in real time through the Internet of Things method and sensor deployment, and to model it based on 3D laser scanning technology. The different sources refer to the data accessed from various modes of transportation such as trucks, trains, and ship terminals. The material storage and transportation data include: the in and out of the warehouse of materials, inventory status, location of transportation vehicles, equipment operation status and environmental parameters.
[0111] Intelligent forecasting module, which uses machine learning and statistical analysis methods to predict supply and demand trends, inventory requirements, and equipment maintenance requirements. By analyzing historical data patterns, the module can identify potential inventory shortages or surpluses, as well as the possibility of equipment failures in advance, thereby supporting more accurate resource planning and preventive maintenance plans;
[0112] Risk assessment module, which is used to evaluate risks in stockyard operations, including supply chain disruptions, safety compliance, environmental impacts, equipment failures, identify risk factors and quantify their potential impacts, and propose countermeasures;
[0113] Intelligent scheduling module, which is used to automatically optimize the path, time and resource allocation of material handling, storage and distribution based on real-time data and risk prediction results. It can dynamically adjust task priorities to ensure maximum operation efficiency while taking into account cost control, energy conservation and emission reduction factors. For example, it can arrange the best stacking and reclaiming sequence and transportation route through algorithms to reduce idle operation and waiting time.
[0114] The decision support module is used to summarize the analysis results of the previous modules, visualize them through data visualization, reports and dashboards, and assist managers in making decisions, including adjusting inventory levels, optimizing material storage and transportation networks, adjusting transportation plans, and implementing cost-saving measures.
[0115] The data acquisition module includes: a data acquisition unit, a state monitoring unit, and a three-dimensional laser scanning unit;
[0116] Data collection unit, used to collect material storage and transportation data in the material yard in real time;
[0117] The status monitoring unit is used to monitor the equipment, vehicles and goods in the storage and transportation process of the material yard in real time and obtain their operating status and location information;
[0118] The 3D laser scanning unit is used to obtain the 3D spatial information of the material yard through 3D laser scanning technology, and is used to build a digital twin model to realize the visualization and simulation of the material yard storage and transportation scene;
[0119] The intelligent prediction module includes: intelligent prediction unit, replenishment suggestion generation unit, and blockchain recording unit;
[0120] Intelligent forecasting unit, used to forecast the storage and transportation demand, inventory level and transportation time of material yards using intelligent adaptive forecasting strategies;
[0121] Replenishment suggestion generation unit, used to generate specific replenishment suggestions based on the results of intelligent prediction, reducing inventory backlog and out-of-stock risks;
[0122] The blockchain recording unit is used to use blockchain technology to record information on the storage and transportation process of the material yard, such as transaction records and inventory changes, to ensure the data is tamper-proof and traceable.
[0123] The risk assessment module includes: risk assessment unit, anomaly detection unit, and early warning unit;
[0124] The risk assessment unit is used to construct a multi-dimensional composite indicator system, and based on this, identify, evaluate and manage various risks in the storage and transportation process of the material yard, and determine the possibility and impact of the risk;
[0125] The abnormality detection unit is used to monitor abnormal conditions in the storage and transportation process of the material yard in real time, such as equipment failure and transportation delay, and issue early warnings in a timely manner;
[0126] The early warning unit is used to send early warning information to staff based on the results of abnormal detection so that timely measures can be taken to deal with risks.
[0127] The intelligent scheduling module includes: scheduling algorithm unit, path planning unit, inventory control unit;
[0128] The scheduling algorithm unit is used to intelligently schedule and optimize the storage and transportation resources of the material yard based on real-time data and prediction results and using scheduling strategies;
[0129] The route planning unit is used to plan the optimal route for transport vehicles using GIS technology and intelligent algorithms to reduce travel time and cost;
[0130] Inventory control unit to manage inventory based on stock levels and replenishment recommendations, ensuring that stock levels remain within thresholds.
[0131] The decision support module includes: database unit, report generation unit, and decision analysis unit;
[0132] Database unit, used to store and manage various data in the system, including raw data, processed data, and analysis results;
[0133] The report generation unit is used to generate various reports and charts based on the data in the database, such as inventory reports, transportation reports, and sales reports, to help managers intuitively understand the storage and transportation status of the material yard;
[0134] The decision analysis unit is used to conduct in-depth analysis of the data in the report and provide decision-making suggestions and support to managers.
[0135] The specific workflows of the data acquisition module, intelligent prediction module, risk assessment module, intelligent scheduling module, decision support module and their corresponding units include:
[0136] The data acquisition unit of the data acquisition module collects the material storage and transportation data in the material yard in real time. The material storage and transportation data includes but is not limited to the type, quantity, location, temperature, humidity of the materials, and the operating status and energy consumption of the transportation equipment. The collected data is transmitted to the database of the system center by wired or wireless means; the status monitoring unit continuously monitors the operating status of each equipment and facility in the material yard, such as the speed of the conveyor belt, the position of the stacker, and the temperature and humidity of the warehouse. The monitored status information is also transmitted to the database of the system center and compared with the preset threshold value. Once an abnormality is found, the risk assessment module is notified immediately; the three-dimensional laser scanning unit performs high-precision scanning of the material yard and generates a three-dimensional model for accurately grasping the distribution and location information of the materials. At the same time, the scanned three-dimensional data is processed and transmitted to the system center for synchronization with the digital twin model;
[0137] The intelligent prediction unit in the intelligent prediction module uses intelligent adaptive prediction strategies to mine and analyze historical data, predict the demand and flow trend of materials in the future, and transmit the prediction results to the replenishment suggestion generation unit and the inventory control unit; the replenishment suggestion generation unit automatically generates a replenishment plan based on the prediction results of the intelligent prediction unit, including replenishment time, quantity, and type, and transmits the replenishment plan to the procurement system and the inventory control unit to guide the actual replenishment operation; the blockchain recording unit uses blockchain technology to record and trace the entire process of materials from warehousing to delivery. At the same time, the data on the blockchain can be accessed by the data acquisition module, intelligent prediction module, risk assessment module, intelligent scheduling module, decision support module and their corresponding units in the system;
[0138] The risk assessment module receives data from the data acquisition module and the status monitoring unit through the risk assessment unit, combines historical data and expert knowledge base, conducts quantitative assessment of risks in the logistics process, and transmits the assessment results to the anomaly detection unit and the early warning unit to provide a basis for anomaly detection and early warning; the anomaly detection unit uses a statistical anomaly detection algorithm to monitor and analyze real-time data, identify abnormal patterns that are significantly different from normal patterns, and transmit the abnormal information to the early warning unit and the intelligent scheduling module so that timely measures can be taken to deal with them; the early warning unit generates early warning information based on the information provided by the anomaly detection unit and the assessment results of the risk assessment unit, and notifies the staff through SMS, email or system pop-up windows, and transmits the early warning information to the intelligent scheduling module and the decision support module at the same time;
[0139] The scheduling algorithm unit in the intelligent scheduling module uses the optimization algorithm to generate the optimal scheduling plan based on the actual material demand, inventory status, and transportation capacity factors, and transmits the scheduling plan to the path planning unit and the inventory control unit to guide the actual scheduling operation; the path planning unit plans the optimal transportation route based on the scheduling plan provided by the scheduling algorithm unit, combined with real-time traffic information and weather conditions, and transmits the planned path information to the transportation system to guide the actual driving of the transportation vehicles or equipment; the inventory control unit dynamically adjusts and optimizes the inventory based on the replenishment plan provided by the replenishment suggestion generation unit and the prediction results of the intelligent prediction unit, and transmits the inventory adjustment information to the inventory management system and procurement system to guide the actual inventory operation;
[0140] The database unit in the decision support module is responsible for storing and managing the data within the system, including real-time data, historical data, and analysis results, while the report generation unit automatically generates reports and charts based on the data in the database.
[0141] Example 3
[0142] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the steps of a smart material yard distribution, storage and transportation control method based on data analysis are implemented. For details, please refer to the above method embodiment, which will not be repeated here.
[0143] A computer-readable storage medium stores computer instructions, which, when executed, execute the steps of a smart material yard distribution, storage and transportation control method based on data analysis, wherein the storage medium may be a volatile or non-volatile computer-readable storage medium.
[0144] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in the field may also change, modify, replace and modify the above-mentioned embodiments without departing from the purpose and scope of protection of the present invention, and all of these are within the protection of the present invention.
Claims
1. A smart material yard distribution, storage and transportation control method based on data analysis, characterized in that: include: Step S1: Real-time monitoring of material storage and transportation data in the material yard through the Internet of Things and sensors, and three-dimensional dynamic modeling of the material yard using three-dimensional laser scanning and augmented reality. At the same time, at the source of data collection, edge computing methods are used for preliminary processing and integration to obtain material storage and transportation data sets; Step S2: Based on the material storage and transportation data set, use the adaptive prediction model to predict the changing trends of material demand, inventory level and transportation efficiency. According to the prediction results and current inventory status, formulate an adaptive replenishment strategy, optimize the replenishment strategy and store it on the blockchain; Step S3: Construct a multi-dimensional composite indicator system, use an anomaly detection model to perform real-time detection on material storage and transportation data to determine whether it falls within the abnormal range. If an abnormality is detected, start the adaptive dynamic adjustment mechanism, and use the deep reinforcement learning strategy to generate the optimal distribution path based on the adjusted material storage and transportation data; Step S4: Build an intelligent dispatching system based on reinforcement learning, establish an intelligent emergency response platform based on big data and AI, integrate multiple emergency resources and plans, introduce an intelligent collaborative operation system, and update and share material storage and transportation data, distribution routes, and emergency response information in real time; The edge computing method is to deploy edge computing nodes at or near the data collection source, and use the computing power of the edge computing nodes to perform preliminary processing and integration of the collected data; The specific implementation steps of step S2 include: S2.1: Receive material storage and transportation data set , select the adaptive prediction model based on machine learning algorithm combined with time series analysis, and use the material storage and transportation data set The adaptive prediction model is trained and the optimal adaptive prediction model is selected by cross-validation method, where: Indicates the nth material storage and transportation data, where n indicates the number of material storage and transportation data; S2.2: Analyze the material demand, inventory level and transportation efficiency trends predicted by the optimal adaptive forecasting model, identify the supply and demand gap, and formulate an adaptive replenishment strategy based on the forecast results and current inventory levels. At the same time, use a multi-objective optimization algorithm to optimize the replenishment strategy combination; S2.3: Write a smart contract based on the optimal replenishment strategy combination and deploy the smart contract on the blockchain; The specific steps of step S3 include: S3.1: According to the characteristics of material storage and transportation data, determine the monitoring dimension indicators, including inventory volume, inventory turnover rate, transportation time, transportation resources, and loss rate, and assign weights to each monitoring dimension indicator, construct weighted composite indicators, and obtain a multi-dimensional composite indicator system; S3.2: Load the trained anomaly detection model and input the material storage and transportation data into the anomaly detection model for anomaly detection; S3.3: Analyze and compare the output results of the anomaly detection model with the weighted composite indicators in the multi-dimensional composite indicator system to determine whether the material storage and transportation data falls within the abnormal range; S3.4: If an anomaly is detected, the adaptive dynamic adjustment mechanism is activated according to the preset rules, and the multi-dimensional composite indicator system and anomaly detection model are re-evaluated and adjusted based on the adjusted material storage and transportation data; The specific steps of step S3 also include: S3.5: Load the pre-trained distribution path optimization model and abstract the material storage and transportation distribution problem into a reinforcement learning environment; S3.6: Use deep reinforcement learning algorithms to train the delivery path optimization model and find the optimal delivery path through trial and error and iterative optimization; S3.7: Input the adjusted material storage and transportation data into the trained distribution path optimization model to generate the optimal distribution path.
2. The method for controlling and managing intelligent material yard distribution, storage and transportation based on data analysis according to claim 1, characterized in that: The specific steps of S2.2 include: S2.21: Extract the prediction value of the optimal adaptive prediction model , and compare the predicted material demand with the current and future inventory levels to calculate the supply-demand gap, where: It represents the forecast value of the storage and transportation data of the nth material. The calculation formula of the supply-demand gap is: , in, represents the supply-demand gap value at time t, represents the forecast value of material demand at time t, represents the current inventory at time t, The delay rate at time t reflects the proportion of delay that may occur in the expected arrival. represents the expected arrival quantity at time t, represents the safety stock at time t, represents the replacement rate at time t, represents the substitutable inventory at time t, represents the backlog of orders at time t; S2.22: Preliminarily set the parameters of the replenishment strategy based on the supply-demand gap and current inventory levels.
3. The method for controlling and managing intelligent material yard distribution, storage and transportation based on data analysis according to claim 2, characterized in that: The specific steps of S2.2 also include: S2.23: Set the goal of replenishment strategy optimization and generate multi-objective function; S2.24: Set the parameters of the multi-objective optimization algorithm, and use the parameters of the replenishment strategy as optimization variables and input them into the multi-objective optimization algorithm; S2.25: Run the multi-objective optimization algorithm to iteratively search for the optimal replenishment strategy combination. In each iteration, evaluate the performance of the current replenishment strategy combination, calculate its corresponding objective function value, and adjust the parameters of the replenishment strategy according to the update rule of the optimization algorithm; S2.26: Based on the output of the multi-objective optimization algorithm, select a set of optimal replenishment strategy combinations and deploy the optimal replenishment strategy combination, monitor the difference between the actual situation and the predicted results during the replenishment process, and adjust the strategy in time to adapt to changes.
4. The method for controlling and managing intelligent material yard distribution, storage and transportation based on data analysis according to claim 3 is characterized in that: The specific formula of the multi-objective function in S2.23 is: , in, represents the total resource consumption, Indicates the resource consumption for each replenishment, A binary variable indicating whether replenishment is performed at time t. 1 means replenishment, 0 means no replenishment. Indicates the resources held per unit of time and per unit of inventory. represents the replenishment quantity at time t, represents the length of time t, Indicates that the unit is out of stock of resources. express The out-of-stock change function at time, Indicates the quality of resources, represents the weight of time t, B t represents the out-of-stock quantity at time t, It represents the transport efficiency, represents the unit transportation resource consumption from supply source j to time t, represents the replenishment quantity from supply source j at time t, C represents the multi-objective optimization problem function, T represents the set of time periods, and J represents the set of supply sources or transportation routes.
5. A smart material yard distribution, storage and transportation control system based on data analysis, which is used to implement the smart material yard distribution, storage and transportation control method based on data analysis described in claims 1-4, characterized in that: include: Intelligent prediction module, risk assessment module, and intelligent scheduling module; The intelligent prediction module includes an intelligent prediction unit, in which an intelligent adaptive prediction strategy is configured, and the intelligent adaptive prediction strategy is used to predict the changing trends of material demand, inventory level and transportation efficiency, and generate replenishment suggestions accordingly; The risk assessment module includes a risk assessment unit and an anomaly detection unit. The risk assessment unit is configured with a multi-dimensional composite indicator system, which is used to conduct a comprehensive quantitative assessment of risk factors in the storage and transportation process of the material yard. The anomaly detection unit is configured with a statistical anomaly detection algorithm, which is used to perform anomaly detection on material storage and transportation data, and to determine whether the material storage and transportation data belongs to an abnormal range by calculating the statistical quantity of the material storage and transportation data and comparing it with a preset threshold value; The intelligent scheduling module includes a scheduling algorithm unit and a path planning unit. The scheduling algorithm unit is configured with a scheduling strategy, which is used to intelligently schedule and optimize the storage and transportation resources of the material yard. The path planning unit is used to plan the optimal driving path for the transport vehicle.
6. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the smart material yard distribution, storage and transportation management and control method based on data analysis as described in any one of claims 1-4 are implemented.
7. A computer-readable storage medium, characterized in that: Computer instructions are stored thereon, and when the computer instructions are executed, the steps of the smart material yard distribution, storage and transportation control method based on data analysis as described in any one of claims 1-4 are executed.
Citation Information
Patent Citations
A smart monitoring system for fuel storage and transportation in steel raw material yards
CN110019623B
Management method and system for cloud computing data center
CN108075906A
DQN-based real-time optimization method for material delivery in uncertain workshop environment
CN113128770A
Point group position data processor, point group position data processing method, point group position data processing system, and point group position data processing program
JP2012057960A
Cloud-based fleet and asset management for edge computing of machine learning and artificial intelligence workloads
US12014219B1
