A bucket wheel excavator control method and system based on UWB positioning

Abstract

The present invention provides a bucket wheel machine control method and system based on UWB positioning, which relates to the field of bucket wheel machine control technology, including obtaining historical operation control information, bucket wheel machine location information, operation environment image information, cargo quantity information and operation parameter information. Then, by clustering the historical operation control information, a set of operation routes of the bucket wheel machine is obtained, and a bucket wheel machine operation simulation model is established. Next, the operation route of the bucket wheel machine is analyzed in real time using a neural network model to obtain real-time operation route information. Then, combined with the real-time operation route information and the comprehensive analysis results of the operation area, the first and second optimizations are performed to meet the real-time operation requirements of the bucket wheel machine. The present invention combines multi-source information acquisition and intelligent optimization scheduling to achieve dynamic optimization and real-time adjustment of the bucket wheel machine transportation process, improve transportation efficiency, enhance transportation flexibility, optimize operation control strategies, and enhance transportation safety.

Description

Technical Field

[0001] The present invention relates to the technical field of bucket wheel machine control, and in particular to a bucket wheel machine control method and system based on UWB positioning. Background Art

[0002] At present, bucket wheel excavators are increasingly used in the fields of logistics and warehousing. However, there are some challenges and limitations in the traditional bucket wheel excavator control methods. Traditional methods are usually based on fixed operation routes and simple control strategies, which cannot adapt to complex working environments and dynamic transportation needs. In addition, traditional methods often lack accurate perception of the bucket wheel excavator's location, cargo location, and operating environment, resulting in inefficiency in the transportation process and incomplete transportation tasks.

[0003] The existing methods lack comprehensive consideration of factors such as the operating environment, cargo quantity, and real-time status of the bucket wheel excavator in the selection and optimization of the control route, resulting in less than ideal control effects.

[0004] Therefore, the prior art requires a more efficient and intelligent bucket wheel machine control method to achieve precise control and optimization of bucket wheel machine operation. Summary of the invention

[0005] The purpose of the present invention is to provide a bucket wheel machine control method and system based on UWB positioning to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0006] In a first aspect, the present application provides a bucket wheel machine control method based on UWB positioning, comprising:

[0007] Acquire first information, second information, third information and fourth information, wherein the first information includes historical operation control information, the second information includes location information of the bucket wheel machine and cargo location information, the third information includes operating environment image information of the bucket wheel machine, and the fourth information includes cargo quantity information and operating parameter information of the bucket wheel machine;

[0008] Clustering the first information to obtain an operation control route set, wherein the operation control route set includes an operation route of at least one bucket wheel machine and its corresponding operation time information;

[0009] Establishing a bucket wheel machine operation simulation model based on the second information and the operation control route set, wherein the bucket wheel machine operation simulation model includes at least two operation routes of the bucket wheel machine, and the operation route includes at least two nodes and one edge, wherein the node is a working node of the bucket wheel machine, and the edge represents an operation path of the bucket wheel machine between the nodes;

[0010] The operation routes of all bucket wheel machines are sent to a preset neural network model for route analysis, wherein the operation routes of all bucket wheel machines are analyzed in real time to obtain real-time operation route information of the bucket wheel machines;

[0011] Performing a comprehensive analysis of the operation area of ​​the third information and the real-time operation route information of the bucket wheel machine, and performing a first optimization on the real-time operation route of the bucket wheel machine in the operation area obtained based on the analysis, to obtain the real-time operation route information after the first optimization;

[0012] The fourth information and the real-time operation route information after the first optimization are subjected to operation demand analysis, the optimized real-time operation route information is optimized for a second time according to the operation demand obtained by the analysis, and the bucket wheel machine is controlled based on the real-time operation route information of the bucket wheel machine obtained by the second optimization.

[0013] In a second aspect, the present application also provides a bucket wheel machine control system based on UWB positioning, including:

[0014] an acquisition unit, configured to acquire first information, second information, third information, and fourth information, wherein the first information includes historical operation control information, the second information includes location information of the bucket wheel machine and cargo location information, the third information includes operating environment image information of the bucket wheel machine, and the fourth information includes cargo quantity information and operating parameter information of the bucket wheel machine;

[0015] A first processing unit is used to cluster the first information to obtain an operation control route set, wherein the operation control route set includes an operation route of at least one bucket wheel machine and its corresponding operation time information;

[0016] a second processing unit, configured to establish a bucket wheel machine operation simulation model based on the second information and the operation control route set, wherein the bucket wheel machine operation simulation model includes at least two operation routes of the bucket wheel machine, and the operation route includes at least two nodes and one edge, wherein the node is a working node of the bucket wheel machine, and the edge represents an operation path of the bucket wheel machine between the nodes;

[0017] A first analysis unit is used to send the operation routes of all bucket wheel machines to a preset neural network model for route analysis, wherein the operation routes of all bucket wheel machines are analyzed in real time to obtain real-time operation route information of the bucket wheel machines;

[0018] A second analysis unit is used to perform a comprehensive analysis of the operation area of ​​the third information and the real-time operation route information of the bucket wheel machine, and perform a first optimization on the real-time operation route of the bucket wheel machine in the operation area obtained based on the analysis, to obtain the real-time operation route information after the first optimization;

[0019] The third analysis unit is used to perform operation demand analysis on the fourth information and the real-time operation route information after the first optimization, perform a second optimization on the optimized real-time operation route information according to the operation demand obtained by the analysis, and control the bucket wheel machine based on the real-time operation route information of the bucket wheel machine obtained by the second optimization.

[0020] The beneficial effects of the present invention are:

[0021] The present invention uses UWB positioning technology to achieve high-precision positioning of bucket wheel machines and cargo positions, combines multi-source information acquisition and intelligent optimization scheduling, realizes dynamic optimization and real-time adjustment of bucket wheel machine transportation process, improves transportation efficiency, enhances transportation flexibility, optimizes operation control strategy, improves transportation safety, and realizes intelligent transportation management. The production of these effects makes the transportation process of bucket wheel machines more efficient, flexible and safe, thereby improving the operating efficiency and competitiveness of the entire logistics and warehousing system.

[0022] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or be understood by implementing the embodiments of the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the written description, claims, and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0024] Figure 1 It is a schematic flow chart of a bucket wheel excavator control method based on UWB positioning described in an embodiment of the present invention;

[0025] Figure 2 It is a schematic diagram of the topological structure of the bucket wheel excavator control system based on UWB positioning described in an embodiment of the present invention.

[0026] In the figure: 701, acquisition unit; 702, first processing unit; 703, second processing unit; 704, first analysis unit; 705, second analysis unit; 706, third analysis unit. DETAILED DESCRIPTION

[0027] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0028] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0029] Embodiment 1:

[0030] This embodiment provides a bucket wheel excavator control method based on UWB positioning.

[0031] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3, step S4, and step S5.

[0032] Step S1, acquiring first information, second information, third information and fourth information, wherein the first information includes historical operation control information, the second information includes location information of the bucket wheel machine and cargo location information, the third information includes operating environment image information of the bucket wheel machine, and the fourth information includes cargo quantity information and operating parameter information of the bucket wheel machine;

[0033] It can be understood that the historical operation control information in this step includes data such as the operation trajectory, operation speed, and completion status of the transportation task of the bucket wheel machine in the past. This information can be used to analyze the operation characteristics and behavior rules of the bucket wheel machine, and provide a reference for subsequent control optimization. The location information of the bucket wheel machine and the cargo location information are the basis for realizing the transportation task of the bucket wheel machine. Accurately obtaining the location information of the bucket wheel machine and the cargo helps the system to monitor and track the transportation process in real time, thereby adjusting the transportation route and task allocation. The operating environment image information of the bucket wheel machine is environmental image data obtained by devices such as sensors or cameras, which is used to detect obstacles on the transportation route, identify safety hazards, and evaluate road conditions, etc., so as to ensure the safety and stability of transportation.

[0034] Finally, the cargo quantity information and bucket wheel machine operating parameter information are to better understand the actual needs of the transportation task and the operating status of the bucket wheel machine. By monitoring the cargo quantity and bucket wheel machine operating parameters, the transportation strategy can be adjusted in time to ensure the smooth progress of the transportation process.

[0035] This step can obtain a variety of information to fully understand the bucket wheel machine's operating status, transportation task requirements and environmental conditions, providing sufficient data support for subsequent control and optimization. This helps to achieve intelligent management and optimized scheduling of the bucket wheel machine transportation process, and improves transportation efficiency and safety.

[0036] Step S2, clustering the first information to obtain an operation control route set, wherein the operation control route set includes an operation route of at least one bucket wheel machine and its corresponding operation time information;

[0037] It can be understood that this step obtains a plurality of representative operation control route sets by clustering the historical operation control information, which includes different types of bucket wheel machine operation routes and corresponding operation time information. This helps the system to better understand and analyze the operation characteristics and laws of the bucket wheel machine, and provides basic data for subsequent simulation modeling and route analysis, thereby realizing intelligent control and optimization of the bucket wheel machine transportation process. In this step, step S2 includes step S21, step S22 and step S23.

[0038] Step S21, preprocessing the first information to obtain an operation route set, wherein the first information includes an operation route of at least one bucket wheel machine and its corresponding operation time information, and the preprocessing method includes deduplication processing, outlier processing and normalization processing;

[0039] It can be understood that this step can effectively improve the quality and accuracy of the operation route data used through deduplication, outlier processing and normalization processing, ensuring that subsequent clustering analysis can be carried out based on reliable data, thereby obtaining a more accurate set of operation control routes.

[0040] Step S22: performing cluster analysis on the operation route set based on the K-means algorithm to obtain at least two clusters, each of which includes an operation route of at least one bucket wheel machine and its corresponding operation time;

[0041] It can be understood that this step uses the K-means algorithm to perform cluster analysis on the operation route set, which can divide the data points into several clusters, each of which has similar operation characteristics, so as to better understand the operation behavior of the bucket wheel machine. This helps to identify different types of operation routes, provides basic data for subsequent operation simulation and route analysis, and then realizes intelligent control and optimization of the bucket wheel machine transportation process.

[0042] Step S23, calculating the threshold range corresponding to the running time in each cluster according to the Laida criterion, and screening to obtain at least two main clusters based on the preset running time threshold, and using the main clusters as the running control route set of the bucket wheel excavator.

[0043] It can be understood that this step can effectively identify stable and reliable operation routes by calculating the operation time threshold range based on the Laida criterion and screening the main clusters as the operation control route set of the bucket wheel machine, thereby improving the operation safety and stability of the bucket wheel machine. This helps to reduce the risk and accident rate during transportation and improve the operation efficiency and reliability of the entire logistics and warehousing system.

[0044] Step S3, establishing a bucket wheel machine operation simulation model based on the second information and the operation control route set, wherein the bucket wheel machine operation simulation model includes at least two operation routes of the bucket wheel machine, and the operation route includes at least two nodes and one edge, wherein the node is a working node of the bucket wheel machine, and the edge represents an operation path of the bucket wheel machine between the nodes;

[0045] It can be understood that this step can simulate the operation of the bucket wheel machine in the actual working environment by establishing a bucket wheel machine operation simulation model, including behaviors in terms of path selection and speed control. By establishing a bucket wheel machine operation simulation model, the operation behavior and working path of the bucket wheel machine can be better understood, providing a reliable basis for subsequent optimization scheduling and control strategies. In this step, step S3 includes step S31, step S32 and step S33.

[0046] Step S31, performing feature extraction on the operation control route set and the second information to obtain working position data of the bucket wheel machine and path data between the working positions, and taking the working position data of the bucket wheel machine as a node and taking the path data between the working positions as an edge;

[0047] It can be understood that this step can accurately describe the working position and transportation path of the bucket wheel machine by extracting features and establishing node and edge models, providing a reliable data basis for the bucket wheel machine operation simulation model. This helps to simulate the operation of the bucket wheel machine in the actual working environment and provide support for optimizing scheduling and control strategies. Among them, feature extraction is to extract necessary feature data from the operation control route set and the second information. For the operation control route set, the features include the working position data of the bucket wheel machine and the path data between the working positions. For the second information, the features include the position information and working position information of the bucket wheel machine.

[0048] Step S32, sending the working position data of the bucket wheel machine and the path data between the working positions to the trained convolutional neural network to generate simulation information of the bucket wheel machine's running trajectory;

[0049] It can be understood that this step can use deep learning technology to more accurately simulate the operation of bucket wheel machine in complex environment by sending the working position data and path data of bucket wheel machine to convolution neural network model and generating simulation information of bucket wheel machine running track, so as to provide support for optimizing the transportation path of bucket wheel machine and improving transportation efficiency. Among them, by using convolution neural network model to generate simulation information of bucket wheel machine running track, the operation of bucket wheel machine in actual working environment can be more accurately simulated, including behavioral characteristics in terms of path selection, transportation time, etc., wherein the trained convolution neural network sends the historical working position data of bucket wheel machine and the path data between working positions to the pre-trained convolution neural network model. The convolution neural network model receives input data and processes and analyzes the input data through multi-layer convolution, pooling and full connection operations. After being processed by the convolution neural network model, the simulation information of bucket wheel machine running track is generated. Then the trained convolution neural network model is obtained. Since convolution neural network is a prior art, it will not be described in detail here.

[0050] Step S33: constructing a bucket wheel machine operation simulation model based on the simulation information of the bucket wheel machine operation trajectory.

[0051] It can be understood that this step can simulate the operation of the bucket wheel machine in the actual working environment by constructing a bucket wheel machine operation simulation model, including the behavior characteristics in terms of path selection, transportation time, behavior changes, etc. This helps to improve the accuracy and reliability of the bucket wheel machine transportation process and provide support for subsequent optimization scheduling and control strategies.

[0052] Step S4, sending the operation routes of all bucket wheel machines to a preset neural network model for route analysis, wherein the operation routes of all bucket wheel machines are analyzed in real time to obtain real-time operation route information of the bucket wheel machines;

[0053] It can be understood that this step can achieve rapid prediction and adjustment of the bucket wheel machine's running route by sending the bucket wheel machine's running route to the neural network model for real-time analysis, thereby improving the efficiency and accuracy of operation control. In this step, step S4 includes step S41, step S42, step S43 and step S44.

[0054] Step S41: semantically extract the running route of the bucket wheel machine and the preset historical running speed of the bucket wheel machine based on natural language processing technology to obtain keyword information, wherein the keyword information includes historical time consumption information of the bucket wheel machine running to each node;

[0055] It can be understood that this step uses natural language processing technology to perform semantic extraction on the bucket wheel machine's operating route and historical operating speed, and obtains keyword information and historical consumption time information, which can help understand and analyze the operation of the bucket wheel machine and provide data support for subsequent route analysis and optimization.

[0056] Step S42: constructing a running route prediction model based on a feedforward neural network algorithm;

[0057] It can be understood that the structure of the feedforward neural network in this step includes an input layer, several hidden layers and an output layer. The number of nodes in the input layer depends on the dimension of the feature, and the number of nodes in the output layer is usually the same as the dimension of the prediction target. The neural network is trained using a preset training set, wherein the back propagation algorithm and the Adam optimizer are used to minimize the mean square error between the predicted value and the true value for training. The weights and biases of the neural network are adjusted so that the model can more accurately predict the operation route of the bucket wheel machine. Finally, model evaluation and hyperparameter adjustment are performed to obtain the operation route prediction model. The operation route prediction model constructed based on the feedforward neural network algorithm can accurately predict the operation route of the bucket wheel machine, providing an important reference for subsequent route analysis and optimization scheduling.

[0058] Step S43, obtaining an operation route prediction result of the bucket wheel machine according to the keyword information and the operation route prediction model;

[0059] It can be understood that this step can accurately predict the operation route of the bucket wheel excavator by combining keyword information and the operation route prediction model, providing a reliable prediction basis for real-time route analysis and optimized scheduling, thereby improving transportation efficiency and resource utilization.

[0060] Step S44, regularly updating the operation route prediction model and outputting the latest operation route prediction result of the bucket wheel machine.

[0061] It can be understood that this step regularly updates and outputs the latest bucket wheel machine operation route prediction results, which can maintain the timeliness and accuracy of the prediction model and provide reliable support for real-time route analysis and optimized scheduling.

[0062] Step S5, performing a comprehensive analysis of the operation area on the third information and the real-time operation route information of the bucket wheel machine, and performing a first optimization on the real-time operation route of the bucket wheel machine in the operation area obtained based on the analysis, to obtain the real-time operation route information after the first optimization;

[0063] It can be understood that this step can adjust and optimize the bucket wheel machine's operating route according to the real-time operating environment through comprehensive analysis and first optimization of the operating area, so as to ensure that the bucket wheel machine can complete the task safely and efficiently. In this step, step S5 includes step S51, step S52 and step S53.

[0064] Step S51, performing image processing on the third information, wherein the operating environment images of all bucket wheel machines are matched with the operating routes of the bucket wheel machines, and it is determined whether the operating routes of the bucket wheel machines are passable, so as to obtain the passability assessment result of the operating routes of the bucket wheel machines;

[0065] It is understood that this step matches the position of the bucket wheel machine in the image with the running route. This can be done by marking the position of the bucket wheel machine on the image and matching it with the running route on the map to determine the current position of the bucket wheel machine and the path it is about to pass. It is determined whether there are obstacles, construction areas or other inaccessible situations in the running route of the bucket wheel machine. This can be done by identifying and analyzing objects in the image through image analysis algorithms, such as target detection, semantic segmentation, etc., to determine the traffic capacity of the bucket wheel machine.

[0066] Step S52, performing correlation analysis on the operation route information of all bucket wheel machines and the work tasks of the workers, and obtaining the correlation value between the operation route information of each bucket wheel machine and the work tasks of the workers;

[0067] It is understandable that this step associates and analyzes the running route information of the bucket wheel machine with the work tasks of the workers, which can more accurately assign the work tasks of the workers to the bucket wheel machine, reduce conflicts and duplications between tasks, and improve the efficiency and accuracy of task execution.

[0068] Step S53: adjusting the real-time operation route information of the bucket wheel machine based on the capacity evaluation result and the correlation value of the operation route of the bucket wheel machine to obtain the real-time operation route information after the first optimization.

[0069] It can be understood that the real-time operation route information after the first optimization in this step can better adapt to the actual operation environment and work task requirements, and improve the safety and efficiency of bucket wheel machine transportation. In this step, step S53 includes step S531, step S532 and step S533.

[0070] Step S531: According to the traffic capacity evaluation result, the bucket wheel machine operation routes are classified according to the traffic capacity, and the route with the best traffic grade is selected as the first adjusted route based on the Dijkstra algorithm;

[0071] It can be understood that this step selects the route with the best capacity based on the capacity evaluation results, thereby improving the transportation efficiency and safety of the bucket wheel machine. At the same time, the application of the Dijkstra algorithm ensures that the selected route is reasonably optimized, so that the bucket wheel machine can reach the destination in the shortest way. The Dijkstra algorithm is a classic algorithm for finding the single-source shortest path in a weighted graph. In this scenario, we regard the operation route of the bucket wheel machine as a graph, and the capacity of each path is used as the weight of the edge. By applying the Dijkstra algorithm, we can find the best passage path between each area, thereby ensuring that the route selected by the bucket wheel machine during operation has the best capacity.

[0072] Step S532: judging the correlation value between the operation route information of each bucket wheel machine and the work task of the worker, and determining the operation route information of the bucket wheel machine corresponding to each worker's work task;

[0073] It can be understood that in this step, for each worker's work task, the operation route information of the corresponding bucket wheel machine is determined according to its correlation value. If a worker's work task has a high correlation with multiple bucket wheel machines, it can be considered to select the nearest bucket wheel machine or the bucket wheel machine with the best traffic capacity to perform the task. Through this step, we can reasonably allocate tasks and determine the operation route information of the bucket wheel machine according to the needs of the worker's work tasks and the operation of the bucket wheel machine, thereby improving the efficiency and accuracy of task execution.

[0074] Step S533: Based on the greedy algorithm, the preset worker task sorting table is used to make a second adjustment to the route after the first adjustment to obtain the real-time operation route information of the bucket wheel excavator after the second adjustment.

[0075] It can be understood that the preset worker work task sorting table in this step records the work tasks of each worker and the order in which they are executed. The greedy algorithm is an algorithm that achieves global optimality based on local optimal selection. We can use the greedy algorithm to sort the task sorting table so that the bucket wheel machine's running route can be arranged more effectively. When sorting, we can consider factors such as the urgency and distance of the work tasks, and give priority to tasks with short distances and high urgency. According to the task sorting results obtained by the greedy algorithm, we make a second adjustment to the bucket wheel machine route after the first adjustment. This may involve rearranging the driving order of the bucket wheel machine to ensure that urgent tasks are given priority while minimizing the driving distance and time. This can better meet the execution requirements of the tasks, improve the efficiency of the bucket wheel machine and the accuracy of task execution.

[0076] Step S6: perform an operation demand analysis on the fourth information and the real-time operation route information after the first optimization, perform a second optimization on the optimized real-time operation route information according to the operation demand obtained by the analysis, and control the bucket wheel machine based on the real-time operation route information of the bucket wheel machine obtained by the second optimization.

[0077] It can be understood that first, we analyze the fourth information (cargo quantity information and bucket wheel machine operating parameter information) to understand the current operation requirements of the construction site. This may involve information such as the quantity of cargo, the real-time situation of the construction site, and the operating parameters of the bucket wheel machine. According to the operation requirements, we can determine the tasks that need to be prioritized, the emergency situation of the construction site, and the operating parameter settings of the bucket wheel machine. Then perform a second optimization. Through the operation requirements and the second optimization, we can better adapt to the real-time demand changes of the construction site and improve the task execution efficiency and flexibility of the bucket wheel machine. At the same time, the real-time control of the bucket wheel machine can ensure the accurate execution of the task and improve the overall efficiency of the construction site operation. In this step, step S6 includes step S61, step S62, step S63, step S64 and step S65.

[0078] Step S61, performing feature extraction and normalization processing according to preset bucket wheel machine working task information, the cargo quantity information and bucket wheel machine operating parameter information to obtain a bucket wheel machine working feature matrix;

[0079] It can be understood that we extract relevant features from the preset bucket wheel machine work task information, which includes task type, task priority, task execution time, etc. Secondly, we extract features from the cargo quantity information, such as the size and type of cargo quantity. Finally, we extract features from the bucket wheel machine's operating parameter information, such as the bucket wheel machine's speed, load capacity, energy consumption, etc. After obtaining each feature, we normalize these features, and then combine the extracted and normalized features into a feature matrix, in which each row represents a work task or a working state, and each column represents a feature. Through the construction of the bucket wheel machine's working feature matrix, we can effectively integrate and represent the bucket wheel machine's work task information, cargo quantity information, and operating parameter information, providing basic data for subsequent data analysis and optimization.

[0080] Step S62: Perform weighted evaluation processing according to the preset historical operation route of the bucket wheel machine, the historical cargo change quantity and the historical task completion progress to obtain the real-time comprehensive score of each bucket wheel machine;

[0081] It can be understood that this step can comprehensively consider factors such as the bucket wheel machine's working efficiency, load conditions and task execution capabilities by performing weighted evaluation on the bucket wheel machine's historical operating routes, historical cargo changes and historical task completion progress, providing an important reference for subsequent optimization and adjustment.

[0082] Step S63, matching the bucket wheel machine working characteristic matrix with the real-time working comprehensive score of each bucket wheel machine to obtain a matching result, wherein the matching result is the real-time working comprehensive score of the bucket wheel machine working characteristic;

[0083] It can be understood that this step matches the working characteristics of the bucket wheel machine with the real-time comprehensive working score, which provides a basis for the next step of route optimization adjustment. Through the matching results, we can more accurately understand the working status of each bucket wheel machine, so as to make targeted optimization adjustments.

[0084] Step S64, sending the matching result and the first optimized real-time running route to the BP neural network for comprehensive score prediction, to obtain comprehensive score information of the first optimized real-time running route;

[0085] It is understood that this step uses the BP neural network to predict the comprehensive score of the matching results and the real-time operation route, so as to quantitatively evaluate the comprehensive performance of the real-time operation route after the first optimization. This helps to evaluate the effect of route optimization and guide the subsequent control and adjustment of the bucket wheel machine. It is understood that this step uses the comprehensive scores corresponding to the historical matching results and the real-time operation route after the first optimization as the training set to train the trained BP neural network, and then predicts the comprehensive score information of the real-time operation route after the first optimization based on the trained BP neural network, wherein the BP neural network is trained by the back propagation algorithm.

[0086] Step S65: If the comprehensive score information of the real-time running route after the first optimization is less than the preset threshold, the matching result and the real-time running route after the first optimization are sent to the preset route optimization neural network for optimization adjustment until the comprehensive score value of the real-time running route obtained by the second optimization reaches the preset threshold.

[0087] It can be understood that this step uses the route optimization neural network to further adjust the real-time operation route after the first optimization to improve the comprehensive performance of the route. Through multiple iterations of optimization, the score of the real-time operation route can reach a preset threshold, thereby improving the operation efficiency and performance of the bucket wheel machine. In this step, step S65 includes step S651 and step S652.

[0088] Step S651, sorting and numbering the real-time running routes after the first optimization according to the driving paths, and associating all the numbers with their corresponding comprehensive real-time scores to obtain the initial parameters of the particle swarm optimization algorithm;

[0089] It can be understood that this step provides an initial population for the particle swarm optimization algorithm, so that the algorithm can start searching for the optimal solution from a suitable starting point. By associating the ranking and scoring of the routes, the optimization process is effectively initialized, which helps to improve the convergence speed and search efficiency of the algorithm.

[0090] Step S652: Optimize the initial parameters of the particle swarm optimization algorithm based on the particle swarm optimization algorithm, wherein the driving route with the highest comprehensive real-time score is selected as a replacement for the real-time operation route after the first optimization through a preset fitness function, and determine whether the replaced driving route can be run in real time. If it can be run in real time, the real-time operation route after the second optimization is obtained.

[0091] It can be understood that the preset fitness function formula in this step is as follows:

[0092]

[0093] Among them, F(x) represents the fitness value, w1 represents the weight of the comprehensive real-time score, a represents the comprehensive real-time score, w2 represents the weight of the route feasibility, and b represents the route feasibility, which is 1 if the route is feasible, otherwise it is 0.

[0094] In this step, the initial parameters are iteratively optimized through the particle swarm optimization algorithm to select the driving route with the highest comprehensive real-time score, and its safety is ensured through real-time inspection to obtain the real-time operation route after the second optimization. Such an optimization process can better meet the actual bucket wheel machine operation requirements and improve the efficiency and performance of the system. During the optimization process, the algorithm will continuously update the position and speed of the particles to find the optimal solution. We select the driving route with the highest comprehensive real-time score as a replacement for the real-time operation route after the first optimization through the fitness function.

[0095] Embodiment 2:

[0096] like Figure 2 As shown, this embodiment provides a bucket wheel machine control system based on UWB positioning, see Figure 2 The system includes an acquisition unit 701 , a first processing unit 702 , a second processing unit 703 , a first analysis unit 704 and a second analysis unit 705 .

[0097] The acquisition unit 701 is used to acquire first information, second information, third information and fourth information, wherein the first information includes historical operation control information, the second information includes location information of the bucket wheel machine and cargo location information, the third information includes operating environment image information of the bucket wheel machine, and the fourth information includes cargo quantity information and operating parameter information of the bucket wheel machine;

[0098] A first processing unit 702 is used to cluster the first information to obtain an operation control route set, where the operation control route set includes an operation route of at least one bucket wheel machine and its corresponding operation time information;

[0099] The second processing unit 703 is used to establish a bucket wheel machine operation simulation model based on the second information and the operation control route set, wherein the bucket wheel machine operation simulation model includes at least two operation routes of the bucket wheel machine, and the operation route includes at least two nodes and one edge, wherein the node is a working node of the bucket wheel machine, and the edge represents an operation path of the bucket wheel machine between the nodes;

[0100] The first analysis unit 704 is used to send the operation routes of all bucket wheel machines to a preset neural network model for route analysis, wherein the operation routes of all bucket wheel machines are analyzed in real time to obtain real-time operation route information of the bucket wheel machines;

[0101] The second analysis unit 705 is used to perform a comprehensive analysis of the operation area on the third information and the real-time operation route information of the bucket wheel machine, and perform a first optimization on the real-time operation route of the bucket wheel machine in the operation area obtained based on the analysis, to obtain the real-time operation route information after the first optimization;

[0102] The third analysis unit is used to perform operation demand analysis on the fourth information and the real-time operation route information after the first optimization, perform a second optimization on the optimized real-time operation route information according to the operation demand obtained by the analysis, and control the bucket wheel machine based on the real-time operation route information of the bucket wheel machine obtained by the second optimization.

[0103] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0104] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0105] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A bucket wheel excavator control method based on UWB positioning, characterized in that: include: Acquire first information, second information, third information and fourth information, wherein the first information includes historical operation control information, the second information includes location information of the bucket wheel machine and cargo location information, the third information includes operating environment image information of the bucket wheel machine, and the fourth information includes cargo quantity information and operating parameter information of the bucket wheel machine; Clustering the first information to obtain an operation control route set, wherein the operation control route set includes an operation route of at least one bucket wheel machine and its corresponding operation time information; Establishing a bucket wheel machine operation simulation model based on the second information and the operation control route set, wherein the bucket wheel machine operation simulation model includes at least two operation routes of the bucket wheel machine, and the operation route includes at least two nodes and one edge, wherein the node is a working node of the bucket wheel machine, and the edge represents an operation path of the bucket wheel machine between the nodes; The operation routes of all bucket wheel machines are sent to a preset neural network model for route analysis, wherein the operation routes of all bucket wheel machines are analyzed in real time to obtain real-time operation route information of the bucket wheel machines; Performing a comprehensive analysis of the operation area of ​​the third information and the real-time operation route information of the bucket wheel machine, and performing a first optimization on the real-time operation route of the bucket wheel machine in the operation area obtained based on the analysis, to obtain the real-time operation route information after the first optimization; The fourth information and the real-time operation route information after the first optimization are subjected to operation demand analysis, the optimized real-time operation route information is optimized for a second time according to the operation demand obtained by the analysis, and the bucket wheel machine is controlled based on the real-time operation route information of the bucket wheel machine obtained by the second optimization.

2. The bucket wheel excavator control method based on UWB positioning according to claim 1 is characterized in that , clustering the first information to obtain an operation control route set, wherein the operation control route set includes an operation route of at least one bucket wheel machine and its corresponding operation time information, including: Preprocessing the first information to obtain an operation route set, wherein the first information includes an operation route of at least one bucket wheel machine and its corresponding operation time information, and the preprocessing method includes deduplication processing, outlier processing and normalization processing; Performing cluster analysis on the operation route set based on K-means algorithm to obtain at least two clusters, each of which includes an operation route of at least one bucket wheel machine and its corresponding operation time; The threshold range corresponding to the running time in each cluster is calculated according to the Laida criterion, and at least two main clusters are obtained based on the preset running time threshold, and the main clusters are used as the running control route set of the bucket wheel excavator.

3. The bucket wheel excavator control method based on UWB positioning according to claim 1 is characterized in that , establishing a bucket wheel machine operation simulation model based on the second information and the operation control route set, including: Performing feature extraction on the operation control route set and the second information to obtain working position data of the bucket wheel machine and path data between the working positions, and taking the working position data of the bucket wheel machine as a node and the path data between the working positions as an edge; Sending the working position data of the bucket wheel machine and the path data between the working positions to the trained convolutional neural network to generate simulation information of the bucket wheel machine's running trajectory; A bucket wheel machine operation simulation model is constructed based on the simulation information of the bucket wheel machine operation trajectory.

4. The bucket wheel machine control method based on UWB positioning according to claim 1 is characterized in that ,The operation routes of all bucket wheel machines are sent to the preset neural network model for route analysis, including: Based on natural language processing technology, semantic extraction is performed on the bucket wheel machine's running route and the preset historical running speed of the bucket wheel machine to obtain keyword information, wherein the keyword information includes historical time consumption information of the bucket wheel machine running to each node; The operation route prediction model is constructed based on the feedforward neural network algorithm; Obtaining an operation route prediction result of a bucket wheel machine according to the keyword information and the operation route prediction model; The operation route prediction model is regularly updated and the latest operation route prediction result of the bucket wheel machine is output.

5. The bucket wheel excavator control method based on UWB positioning according to claim 1 is characterized in that , performing a comprehensive analysis of the operation area using the third information and the real-time operation route information of the bucket wheel machine, including: The third information is subjected to image processing, wherein the operating environment images of all bucket wheel machines are matched with the operating routes of the bucket wheel machines, and it is determined whether the operating routes of the bucket wheel machines are passable, so as to obtain a passability assessment result of the operating routes of the bucket wheel machines; Perform correlation analysis on the operation route information of all bucket wheel machines and the work tasks of the workers, and obtain the correlation value between the operation route information of each bucket wheel machine and the work tasks of the workers; Based on the capacity evaluation result and the correlation value of the bucket wheel machine's operating route, the real-time operating route information of the bucket wheel machine is adjusted to obtain the real-time operating route information after the first optimization.

6. The bucket wheel excavator control method based on UWB positioning according to claim 5 is characterized in that , based on the capacity evaluation result and the correlation value of the bucket wheel machine's operation route, the real-time operation route information of the bucket wheel machine is adjusted, including: According to the traffic capacity evaluation result, the bucket wheel machine operation route is classified according to the traffic capacity, and the route with the best traffic grade is selected as the first adjusted route based on the Dijkstra algorithm; The operation route information of each bucket wheel machine and the correlation value of the worker's work task are judged to determine the operation route information of the bucket wheel machine corresponding to each worker's work task; Based on the greedy algorithm, the preset worker work task sorting table is used to make a second adjustment to the route after the first adjustment, so as to obtain the real-time operation route information of the bucket wheel excavator after the second adjustment.

7. The bucket wheel excavator control method based on UWB positioning according to claim 1 is characterized in that , performing operation demand analysis on the fourth information and the real-time operation route information after the first optimization, including: Performing feature extraction and normalization processing according to preset bucket wheel machine working task information, the cargo quantity information and bucket wheel machine operating parameter information to obtain a bucket wheel machine working feature matrix; A weighted evaluation is performed based on the preset bucket wheel machine's historical operation route, historical cargo change quantity, and historical task completion progress to obtain a comprehensive real-time working score for each bucket wheel machine. Matching the bucket wheel machine working characteristic matrix with the real-time working comprehensive score of each bucket wheel machine to obtain a matching result, wherein the matching result is the real-time working comprehensive score of the bucket wheel machine working characteristic matrix; Sending the matching result and the first optimized real-time operation route to a BP neural network for comprehensive score prediction to obtain comprehensive score information of the first optimized real-time operation route; If the comprehensive score information of the real-time running route after the first optimization is less than the preset threshold, the matching result and the real-time running route after the first optimization are sent to the preset route optimization neural network for optimization and adjustment until the comprehensive score value of the real-time running route obtained by the second optimization reaches the preset threshold.

8. The bucket wheel excavator control method based on UWB positioning according to claim 7 is characterized in that If the comprehensive score information of the first optimized real-time running route is less than the preset threshold, the matching result and the first optimized real-time running route are sent to the preset route optimization neural network for optimization adjustment, including: The real-time operation routes after the first optimization are sorted and numbered according to the driving paths, and all the numbers are associated with their corresponding comprehensive real-time scores to obtain initial parameters of the particle swarm optimization algorithm; The initial parameters of the particle swarm optimization algorithm are optimized based on the particle swarm optimization algorithm, wherein the driving route with the highest comprehensive real-time score is selected as a replacement for the real-time operation route after the first optimization through a preset fitness function, and it is determined whether the replaced driving route can be run in real time. If it can be run in real time, the real-time operation route after the second optimization is obtained.

9. The bucket wheel excavator control method based on UWB positioning according to claim 8 is characterized in that ,The formula of the fitness function includes: Among them, F(x) represents the fitness value, w1 represents the weight of the comprehensive real-time score, a represents the comprehensive real-time score, w2 represents the weight of the route feasibility, and b represents the route feasibility, which is 1 if the route is feasible, otherwise it is 0.

10. A bucket wheel excavator control system based on UWB positioning, characterized in that: include: an acquisition unit, configured to acquire first information, second information, third information, and fourth information, wherein the first information includes historical operation control information, the second information includes location information of the bucket wheel machine and cargo location information, the third information includes operating environment image information of the bucket wheel machine, and the fourth information includes cargo quantity information and operating parameter information of the bucket wheel machine; A first processing unit is used to cluster the first information to obtain an operation control route set, wherein the operation control route set includes an operation route of at least one bucket wheel machine and its corresponding operation time information; a second processing unit, configured to establish a bucket wheel machine operation simulation model based on the second information and the operation control route set, wherein the bucket wheel machine operation simulation model includes at least two operation routes of the bucket wheel machine, and the operation route includes at least two nodes and one edge, wherein the node is a working node of the bucket wheel machine, and the edge represents an operation path of the bucket wheel machine between the nodes; A first analysis unit is used to send the operation routes of all bucket wheel machines to a preset neural network model for route analysis, wherein the operation routes of all bucket wheel machines are analyzed in real time to obtain real-time operation route information of the bucket wheel machines; A second analysis unit is used to perform a comprehensive analysis of the operation area of ​​the third information and the real-time operation route information of the bucket wheel machine, and perform a first optimization on the real-time operation route of the bucket wheel machine in the operation area obtained based on the analysis, to obtain the real-time operation route information after the first optimization; The third analysis unit is used to perform operation demand analysis on the fourth information and the real-time operation route information after the first optimization, perform a second optimization on the optimized real-time operation route information according to the operation demand obtained by the analysis, and control the bucket wheel machine based on the real-time operation route information of the bucket wheel machine obtained by the second optimization.

Images