Automatic centering control system and method based on multi-level detection

Abstract

This application relates to the field of intelligent control, specifically disclosing an automatic alignment control system and method based on multi-level detection. It employs deep learning-based artificial intelligence control technology to obtain initial distance measurement values ​​using the flight time of the base station and each communication tag. Furthermore, it optimizes the feature representation of the global implicit features of each signal strength by fusing the global implicit correlation features of the signal strengths between the base station and each communication tag with the topological correlation features between the communication tags, utilizing the topological features of each communication tag. This enables two-stage alignment of the material inlet and the material receiving outlet based on multiple distance correction values, improving the alignment accuracy of the material inlet and the material receiving outlet, thereby increasing operational efficiency.

Description

Technical Field

[0001] This application relates to the field of intelligent control, and more specifically, to an automatic centering control system and method based on multi-level detection. Background Technology

[0002] After coal is mined from underground and transferred to the surface, it needs to be crushed and ground into pulverized coal before being transferred to cable hopper cars. Currently, self-propelled crushers are used to crush coal lumps and grind them into pulverized coal. As one of the key electromechanical equipment in coal production enterprises, the crusher is an important production device to ensure efficient and safe production in coal mines. Furthermore, transfer conveyors are used to transfer the crushed pulverized coal to cable hopper cars to achieve automated operation. During this process, the self-propelled crusher, transfer conveyor, and cable hopper cars need to be aligned and controlled to prevent coal leakage, thus ensuring efficiency while avoiding waste of coal resources.

[0003] Existing self-propelled crushers, transfer conveyors, and cable hopper trolleys often deviate from their intended direction of travel during operation, requiring manual adjustments to align the individual devices with adjacent equipment and achieve centering control of the material inlet and outlet. However, constant manual adjustments increase operating time, resulting in poor maneuverability and flexibility. Furthermore, manual adjustments cannot guarantee precise alignment of the material inlet and outlet, severely impacting the overall system efficiency during mining, crushing, and transportation, increasing costs, and wasting resources.

[0004] Therefore, there is a need for an optimized automated operation control scheme for self-propelled crushers, transfer machines, and cable hopper trucks. Summary of the Invention

[0005] To address the aforementioned technical problems, this application is proposed. Embodiments of this application provide an automatic alignment control system and method based on multi-level detection. This system employs deep learning-based artificial intelligence control technology to obtain initial distance measurement values ​​using the flight times of the base station and each communication tag. Furthermore, it optimizes the feature representation of the global implicit features of each signal strength by fusing the global implicit correlation features of the signal strengths between the base station and each communication tag with the topological correlation features between the communication tags, utilizing the topological features of each communication tag. In this way, based on the multiple distance correction values, two-stage alignment can be performed on the material discharge port and the material receiving port to improve the alignment accuracy of the material discharge port and the material receiving port, thereby improving operational efficiency.

[0006] According to one aspect of this application, an automatic alignment control system based on multi-level detection is provided, comprising:

[0007] The first alignment module is used to perform primary alignment of the material inlet and the material receiving inlet based on the GPS positioning module.

[0008] The second alignment module is used to perform secondary alignment of the material discharge port and the material receiving port based on communication between the base station and the communication tag; and

[0009] The third alignment module is used to perform three-level alignment between the discharge port and the receiving port based on multiple lidars deployed at the receiving port.

[0010] In the above-mentioned automatic alignment control system based on multi-level detection, the first alignment module includes: a positioning unit, used to obtain the absolute coordinates of the receiving port based on the GPS positioning module; an alignment target unit, used to determine the absolute coordinates that the discharge port should reach based on the absolute coordinates of the receiving port; and an alignment completion module, used to determine that the first-level alignment is completed in response to the absolute coordinates of the discharge port being the absolute coordinates that the discharge port should reach.

[0011] In the aforementioned automatic alignment control system based on multi-level detection, the second alignment module includes: a communication data receiving unit, used to receive communication data between the base station and each of the communication tags from the base station, the communication data including flight time and signal strength values; a distance initial value calculation unit, used to determine multiple initial distance measurement values ​​based on the flight time in the communication data; a signal strength semantic encoding unit, used to pass the signal strength values ​​in the communication data through a context encoder containing a one-hot encoding layer to obtain multiple signal strength context semantic feature vectors; a topology matrix construction unit, used to obtain a topology matrix of the multiple communication tags, where the values ​​at each off-diagonal position in the topology matrix are the distances between corresponding two communication tags, and the values ​​at each diagonal position in the topology matrix are the distances between the corresponding base station and the communication tag; and a topology feature extraction unit, used to pass the topology matrix through a convolutional neural network model as a feature extractor to obtain a communication space topology matrix. The system comprises: an encoding unit for passing the communication space topology matrix and the signal strength global correlation matrix obtained by arranging the plurality of signal strength context semantic feature vectors in a two-dimensional manner through a graph neural network model to obtain a communication topology signal strength global correlation matrix; a feature distribution optimization unit for optimizing the feature distribution of the communication topology signal strength global correlation matrix to obtain an optimized communication topology signal strength global correlation matrix; a query unit for calculating the product between each row vector in the optimized communication topology signal strength global correlation matrix and the optimized communication topology signal strength global correlation matrix to obtain a plurality of decoded feature vectors; a decoding unit for passing the plurality of decoded feature vectors through a decoder to obtain a plurality of decoded values ​​representing distance compensation values; a correction unit for correcting the plurality of initial distance measurement values ​​based on the plurality of decoded values ​​to obtain a plurality of distance correction values; and a secondary detection unit for performing secondary alignment of the discharge port and the receiving port based on the plurality of distance correction values.

[0012] In the above-mentioned automatic alignment control system based on multi-level detection, the signal strength semantic encoding unit is further configured to: a one-hot encoding subunit, configured to encode the signal strength values ​​in the communication data one-hot to obtain multiple signal strength feature vectors; and a global context encoding subunit, configured to use the context encoder to perform global context semantic encoding on the multiple signal strength feature vectors to obtain multiple signal strength context semantic feature vectors.

[0013] In the aforementioned automatic alignment control system based on multi-level detection, the global context encoding subunit includes: a query vector construction subunit, used to arrange the multiple signal strength feature vectors in one dimension to obtain a global signal strength feature vector; a self-attention subunit, used to calculate the product between the global signal strength feature vector and the transpose of each of the multiple signal strength feature vectors to obtain multiple self-attention association matrices; a standardization subunit, used to standardize each of the multiple self-attention association matrices to obtain multiple standardized self-attention association matrices; an attention calculation subunit, used to pass each of the multiple standardized self-attention association matrices through a Softmax classification function to obtain multiple probability values; and an attention application subunit, used to weight each of the multiple signal strength feature vectors using each probability value as a weight to obtain multiple signal strength context semantic feature vectors.

[0014] In the aforementioned automatic alignment control system based on multi-level detection, the topology feature extraction unit is further configured to: use each layer of the convolutional neural network model serving as the feature extractor to perform the following on the input data during the forward propagation of the layer: convolution processing on the input data to obtain a convolutional feature map; pooling along the channel dimension of the convolutional feature map to obtain a pooled feature map; and nonlinear activation on the pooled feature map to obtain an activation feature map; wherein the output of the last layer of the convolutional neural network serving as the feature extractor is the communication space topology matrix, and the input of the first layer of the convolutional neural network serving as the feature extractor is the topology matrix.

[0015] In the aforementioned automatic alignment control system based on multi-level detection, the feature distribution optimization unit is further configured to: perform feature distribution optimization on the global correlation matrix of the communication topology signal strength using the following formula to obtain the optimized global correlation matrix of the communication topology signal strength; wherein, the formula is:

[0016]

[0017] Where μ and δ are the mean and standard deviation of the eigenvalue set at each location in the global correlation matrix of the signal strength of the communication topology, respectively, and m i，j It is the eigenvalue at position (i, j) of the global correlation matrix of the signal strength of the communication topology.

[0018] In the aforementioned automatic alignment control system based on multi-level detection, the decoding unit is further configured to: use the decoder to pass the plurality of decoded feature vectors through the decoder to obtain a plurality of decoded values ​​representing the distance compensation value using the following formula; wherein, the formula is: Where X represents the plurality of decoded feature vectors, Y is the plurality of decoded values, and W is the weight matrix. This represents matrix multiplication.

[0019] In the above-mentioned automatic centering control system based on multi-level detection, the correction unit is further used to calculate the sum of the decoded value and the initial distance measurement value to obtain the plurality of distance correction values.

[0020] According to another aspect of this application, an automatic centering control method based on multi-level detection is provided, comprising:

[0021] Based on the GPS positioning module, the material inlet and the receiving inlet are aligned in one stage;

[0022] Based on the communication between the base station and the communication tag, a two-stage alignment is performed between the material inlet and the material receiving inlet; and

[0023] Based on multiple lidar sensors deployed at the receiving port, the discharge port and the receiving port are aligned in three stages.

[0024] According to another aspect of this application, an electronic device is provided, comprising: a processor; and a memory storing computer program instructions, which, when executed by the processor, cause the processor to perform the automatic centering control method based on multi-level detection as described above.

[0025] According to another aspect of this application, a computer-readable medium is provided having computer program instructions stored thereon, which, when executed by a processor, cause the processor to perform the automatic centering control method based on multi-level detection as described above.

[0026] Compared with existing technologies, this application provides an automatic alignment control system and method based on multi-level detection. It employs deep learning-based artificial intelligence control technology to obtain initial distance measurement values ​​using the flight time of the base station and each communication tag. Furthermore, it optimizes the feature representation of the global implicit features of each signal strength by fusing the global implicit correlation features of each signal strength between the base station and each communication tag with the topological correlation features between the communication tags, utilizing the topological features of each communication tag. This enables two-stage alignment of the material inlet and the material receiving outlet based on multiple distance correction values, improving the alignment accuracy of the material inlet and the material receiving outlet, thereby increasing operational efficiency. Attached Figure Description

[0027] The above and other objects, features, and advantages of this application will become more apparent from the more detailed description of the embodiments of this application in conjunction with the accompanying drawings. The drawings are provided to further illustrate the embodiments of this application and form part of the specification. They are used together with the embodiments of this application to explain this application and do not constitute a limitation thereof. In the drawings, the same reference numerals generally represent the same components or steps.

[0028] Figure 1 This is an application scenario diagram of an automatic alignment control system based on multi-level detection according to an embodiment of this application;

[0029] Figure 2 This is a block diagram of an automatic alignment control system based on multi-level detection according to an embodiment of this application;

[0030] Figure 3 This is a system architecture diagram of an automatic alignment control system based on multi-level detection according to an embodiment of this application;

[0031] Figure 4 This is a block diagram of the first alignment module in the automatic alignment control system based on multi-level detection according to an embodiment of this application;

[0032] Figure 5 This is a block diagram of the second alignment module in the automatic alignment control system based on multi-level detection according to an embodiment of this application;

[0033] Figure 6 This is a flowchart of the convolutional neural network encoding in the automatic alignment control system based on multi-level detection according to an embodiment of this application;

[0034] Figure 7 This is a flowchart of an automatic centering control method based on multi-level detection according to an embodiment of this application;

[0035] Figure 8 This is a block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0036] Hereinafter, exemplary embodiments according to this application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of this application, and not all embodiments of this application. It should be understood that this application is not limited to the exemplary embodiments described herein.

[0037] Scene Overview

[0038] As mentioned in the background section, after coal is mined from underground and transferred to the surface, it needs to be crushed and ground into pulverized coal before being transferred to a hopper car. Currently, self-propelled crushers are used to crush coal lumps and grind them into pulverized coal. As one of the key electromechanical equipment in coal production enterprises, the crusher is an important production device to ensure efficient and safe production in coal mines. Furthermore, transfer conveyors are used to transfer the crushed pulverized coal to cable hopper cars to achieve automated operation. During this process, the self-propelled crusher, transfer conveyor, and cable hopper cars need to be aligned and controlled to prevent coal leakage, thus ensuring efficiency while avoiding waste of coal resources.

[0039] Existing self-propelled crushers, transfer conveyors, and cable hopper trolleys often deviate from their intended direction of travel during operation, requiring manual adjustments to align the individual devices with adjacent equipment and achieve centering control of the material inlet and outlet. However, constant manual adjustments increase operating time, result in poor maneuverability and flexibility, and cannot guarantee precise alignment of the material inlet and outlet. This severely impacts the efficiency of the entire system during mining, crushing, and transportation, increases investment costs, and wastes resources. Therefore, an optimized automated operation control scheme for self-propelled crushers, transfer conveyors, and cable hopper trolleys is desired.

[0040] Specifically, in the technical solution of this application, the automatic alignment control scheme for the material drop port and the material receiving port is as follows: GPS high-precision positioning (using the absolute coordinates of the lower-level material receiving point as a reference to calculate the absolute coordinate values ​​that the upper-level material drop point should reach); wireless ranging (installing several wireless ranging tags around the material receiving port and a base station at the material drop port to measure the real-time distance between the base station and the tags; when the distance to each tag is equal, the initial automatic alignment is completed); and radar measurement (considering the accuracy of the wireless ranging device, installing four radar ranging units around the material receiving port to measure the real-time distance to the material receiving port; when the distance to each tag is equal, the automatic alignment is completed, and this also has the function of preventing collisions between the material drop port and the material receiving port). Using the above three levels of detection, the calculation of the automatic alignment position and the position detection during the alignment process can be completed.

[0041] Accordingly, considering that in the secondary detection based on wireless ranging, several wireless ranging tags are installed around the receiving port, and a base station is installed at the discharge port, and the distance between the base station and each tag is obtained based on the communication between the base station and the tags, the measurement accuracy will decrease due to signal interference when conducting distance testing based on communication because multiple tags are installed around the receiving port, resulting in low initial alignment accuracy. Therefore, it is expected that the accuracy of distance measurement between the base station and each tag will be optimized to improve the alignment accuracy of the discharge port and the receiving port.

[0042] Specifically, in the technical solution of this application, deep learning-based artificial intelligence control technology is employed to obtain initial distance measurement values ​​through the flight time of the base station and each communication tag. Furthermore, by fusing the global implicit correlation features of each signal strength between the base station and each communication tag with the topological correlation features between the communication tags, the feature representation of the global implicit features of each signal strength is optimized using the topological features of each communication tag. Further, the optimized implicit features of each signal strength between the base station and each communication tag are corrected based on the query of the global signal strength correlation features to extract interference feature information between the global implicit correlation features of each signal strength. This information is then used for decoding and regression to obtain distance compensation values ​​to correct each distance. In this way, based on the multiple distance correction values, secondary alignment of the material discharge port and the material receiving port can be performed to improve the alignment accuracy of the material discharge port and the material receiving port, thereby improving operational efficiency.

[0043] More specifically, in the technical solution of this application, firstly, communication data between the base station and each of the communication tags is received from the base station, the communication data including time of flight and signal strength values. Then, multiple initial distance measurement values ​​can be determined based on the time of flight in the communication data. For example, multiple initial distance measurement values ​​between the base station and each of the communication tags can be obtained by multiplying the time of flight in the communication data by the speed of light c.

[0044] Next, considering the correlation between the signal strength of the base station and each communication tag, a context encoder containing a one-hot coding layer is further used to encode each signal strength value in the communication data to extract a global high-dimensional semantic feature between the signal strength of the base station and each communication tag, which is more suitable for characterizing the essential features of communication distance, thereby obtaining multiple signal strength context semantic feature vectors.

[0045] Furthermore, when determining the distance between a base station and each tag through communication between the base station and the tag, signal interference can reduce measurement accuracy, resulting in low initial alignment accuracy. That is, considering the mutual interference of signal strengths in spatial locations when the various communication tags communicate with the base station, utilizing the spatial topological features of each communication tag to enhance the expression of the implicit correlation features of each signal strength can obviously improve the accuracy of distance measurement. Therefore, in the technical solution of this application, a topology matrix of the multiple communication tags is further obtained. Here, the values ​​at each off-diagonal position in the topology matrix represent the distance between two corresponding communication tags, and the values ​​at each diagonal position in the topology matrix represent the distance between the corresponding base station and the communication tag. Next, the topology matrix is ​​used to extract features through a convolutional neural network model acting as a feature extractor to extract the spatial topological features of each communication tag, thereby obtaining a communication spatial topology matrix.

[0046] Then, using each of the multiple signal strength context semantic feature vectors as the feature representation of a node, and the communication space topology matrix as the feature representation of the edges between nodes, the global correlation matrix of signal strength obtained by arranging the multiple signal strength context semantic feature vectors in two dimensions and the communication space topology matrix are processed through a graph neural network model to obtain a global correlation matrix of communication topology signal strength. Specifically, the graph neural network model uses learnable neural network parameters to perform graph structure data encoding on the communication space topology matrix and the global correlation matrix of signal strength to obtain a global correlation matrix of communication topology signal strength containing irregular spatial topological features and global hidden correlation feature information of each signal strength. In this way, by fusing the features of the global correlation matrix of signal strength and the communication space topology matrix, the feature expression of the global hidden correlation features of each signal strength can be optimized using the spatial topological features of each communication tag, thereby improving the accuracy of distance compensation.

[0047] Furthermore, considering that the global correlation matrix of the communication topology signal strength contains the communication interference information between the base station and each tag, in order to accurately compensate for each distance value, the product between each row vector in the global correlation matrix of the communication topology signal strength and the global correlation matrix of the communication topology signal strength is further calculated to extract the influence of the interference features between the global implicit correlation features of each signal strength on the communication distance measurement, thereby obtaining multiple decoding feature vectors.

[0048] Then, the multiple decoded feature vectors are decoded and regressed using a decoder to obtain multiple decoded values ​​representing the distance compensation values ​​for each distance measurement. Based on these multiple decoded values, the initial values ​​of the multiple distance measurements are corrected to obtain multiple distance correction values. Subsequently, based on these multiple distance correction values, secondary alignment can be performed on the discharge port and the receiving port. This improves the alignment accuracy of the discharge port and the receiving port.

[0049] Specifically, in the technical solution of this application, for the communication topology signal strength global correlation matrix obtained by using a graph neural network model, since each row vector corresponds to the spatial topological representation of the contextual signal strength features between the base station and a single tag, the clustering effect of the feature distribution of the communication topology signal strength global correlation matrix as a whole deteriorates. Therefore, when calculating the product between each row vector in the communication topology signal strength global correlation matrix and the communication topology signal strength global correlation matrix, the feature distribution of the obtained decoded feature vector may not be dense enough, affecting the accuracy of the decoded value.

[0050] Here, the applicant of this application considers that in the global correlation matrix of signal strength of the communication topology, the relationship between the feature distributions of each row vector follows a Gaussian distribution under natural conditions. That is, the average degree of correlation between each row vector as an individual feature distribution and the global feature distribution has the highest probability density, while higher and lower degrees of correlation both have lower probability densities. Therefore, based on this high-frequency distribution characteristic following a Gaussian point distribution, feature clustering defocusing fuzzy optimization can be performed on the global correlation matrix of signal strength of the communication topology, expressed as:

[0051]

[0052] μ and δ are respectively the feature set m i，j The mean and standard deviation of ∈M, and m i，j It is the eigenvalue at the (i, j)th position of the global correlation matrix M of the signal strength of the communication topology.

[0053] The defocusing fuzziness optimization of feature clustering compensates for the dependency similarity between the high-frequency distribution features following a Gaussian point distribution and the uniform representation of the overall feature distribution, by using a statistical information-based feature clustering index for the focus stack representation used to estimate clustering metrics. This avoids focus fuzziness in the overall feature distribution caused by low dependency similarity, thus improving the clustering effect of the feature distribution of the global correlation matrix of the communication topology signal strength, thereby improving the accuracy of the decoded feature vector values. This improves the alignment accuracy of the material inlet and outlet, thereby increasing operational efficiency.

[0054] Based on this, this application proposes an automatic alignment control system based on multi-level detection, which includes: a first alignment module for performing first-level alignment of the material discharge port and the material receiving port based on a GPS positioning module; a second alignment module for performing second-level alignment of the material discharge port and the material receiving port based on communication between a base station and a communication tag; and a third alignment module for performing third-level alignment of the material discharge port and the material receiving port based on multiple lidars deployed at the material receiving port.

[0055] Figure 1 This is an application scenario diagram of an automatic alignment control system based on multi-level detection according to an embodiment of this application. For example... Figure 1 As shown, in this application scenario, high-precision GPS positioning (e.g., as...) is used. Figure 1 As shown in G), the coordinates of the receiving point are obtained (e.g., as shown in G). Figure 1 As shown in C); several wireless ranging tags are installed around the receiving port (e.g., such as...). Figure 1 The L1-Ln shown in the diagram) and the base station installed at the material discharge port (e.g., as shown in the diagram) Figure 1 As shown in B), to measure the real-time distance between the base station and the tag (e.g., as shown in B). Figure 1 (d1-dn as shown); and, by means of 4 radars deployed around the receiving port (e.g., such as...) Figure 1 The R1-R4 shown in the diagram respectively measure the real-time distance to the receiving port (e.g., as shown in the diagram). Figure 1 (D1-D4 as shown in the diagram). Next, the above data is input to a server deployed with an automatic centering control algorithm based on multi-level detection (e.g., Figure 1 In the S), the server is able to process the input data using the multi-level detection-based automatic alignment control algorithm to generate alignment control instructions.

[0056] After introducing the basic principles of this application, various non-limiting embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0057] Exemplary System

[0058] Figure 2 This is a block diagram of an automatic alignment control system based on multi-level detection according to an embodiment of this application. Figure 2 As shown, the automatic centering control system 300 based on multi-level detection according to an embodiment of this application includes: a first centering module 310; a second centering module 320; and a third centering module 330.

[0059] The first alignment module 310 is used to perform primary alignment of the material discharge port and the material receiving port based on the GPS positioning module; the second alignment module 320 is used to perform secondary alignment of the material discharge port and the material receiving port based on the communication between the base station and the communication tag; and the third alignment module 330 is used to perform tertiary alignment of the material discharge port and the material receiving port based on multiple lidars deployed at the material receiving port.

[0060] Figure 3 This is a system architecture diagram of an automatic alignment control system based on multi-level detection according to an embodiment of this application. Figure 3 As shown, in the system architecture of the multi-level detection-based automatic alignment control system 300, the first alignment module 310 first performs primary alignment of the material discharge port and the material receiving port based on the GPS positioning module. Next, the second alignment module 320 performs secondary alignment of the material discharge port and the material receiving port based on communication between the base station and the communication tag. Then, the third alignment module 330 performs tertiary alignment of the material discharge port and the material receiving port based on multiple lidar sensors deployed at the material receiving port.

[0061] Specifically, during the operation of the multi-level detection-based automatic alignment control system 300, the first alignment module 310 is used to perform primary alignment of the material inlet and the material receiving inlet based on the GPS positioning module. In the technical solution of this application, the absolute coordinates of the lower-level material receiving point are obtained through high-precision GPS positioning to calculate the absolute coordinate value that the upper-level material inlet should reach. This allows for precise value-based alignment control of the material inlet and the material receiving inlet. Responding to the absolute coordinates of the material inlet being the absolute coordinates that the material inlet should reach, the completion of the primary alignment is determined.

[0062] Figure 4 This is a block diagram of the first alignment module in an automatic alignment control system based on multi-level detection according to an embodiment of this application. Figure 4 As shown, the first alignment module 310 includes: a positioning unit 3110, used to obtain the absolute coordinates of the receiving port based on the GPS positioning module; an alignment target unit 3120, used to determine the absolute coordinates that the discharge port should reach based on the absolute coordinates of the receiving port; and an alignment completion module 3130, used to determine that the first-level alignment is completed in response to the absolute coordinates of the discharge port being the absolute coordinates that the discharge port should reach.

[0063] Specifically, during the operation of the multi-level detection-based automatic alignment control system 300, the second alignment module 320 is used to perform secondary alignment of the material discharge port and the material receiving port based on communication between the base station and the communication tag. In the technical solution of this application, the alignment control of the material discharge port and the material receiving port is achieved through wireless ranging. Specifically, several wireless ranging tags are installed around the material receiving port, and a base station is installed at the material discharge port. The real-time distance between the base station and the tags is measured. In response to the fact that the various distance correction values ​​are equal or the differences between the various distance correction values ​​are within a predetermined fluctuation range, the secondary alignment is determined to be completed.

[0064] Figure 5 This is a block diagram of the second alignment module in an automatic alignment control system based on multi-level detection according to an embodiment of this application. Figure 5 As shown, the second alignment module 320 includes: a communication data receiving unit 3210, used to receive communication data between the base station and each of the communication tags from the base station, the communication data including flight time and signal strength values; a distance initial value calculation unit 3220, used to determine multiple distance measurement initial values ​​based on the flight time in the communication data; a signal strength semantic encoding unit 3230, used to pass the signal strength values ​​in the communication data through a context encoder containing a one-hot encoding layer to obtain multiple signal strength context semantic feature vectors; a topology matrix construction unit 3240, used to obtain a topology matrix of the multiple communication tags, where the values ​​at each off-diagonal position in the topology matrix are the distances between corresponding two communication tags, and the values ​​at each diagonal position in the topology matrix are the distances between the corresponding base station and the communication tag; a topology feature extraction unit 3250, used to pass the topology matrix through a convolutional neural network model as a feature extractor to obtain a communication space topology matrix; and a graph neural encoding unit 3260. The system comprises: a communication topology matrix and a signal strength global correlation matrix obtained by arranging the multiple signal strength context semantic feature vectors in a two-dimensional manner; a graph neural network model to obtain a communication topology signal strength global correlation matrix; a feature distribution optimization unit 3270 to optimize the feature distribution of the communication topology signal strength global correlation matrix to obtain an optimized communication topology signal strength global correlation matrix; a query unit 3280 to calculate the product between each row vector in the optimized communication topology signal strength global correlation matrix and the optimized communication topology signal strength global correlation matrix to obtain multiple decoded feature vectors; a decoding unit 3290 to pass the multiple decoded feature vectors through a decoder to obtain multiple decoded values ​​representing distance compensation values; a correction unit 3300 to correct the multiple initial distance measurement values ​​based on the multiple decoded values ​​to obtain multiple distance correction values; and a secondary detection unit 3310 to perform secondary alignment of the discharge port and the receiving port based on the multiple distance correction values.

[0065] More specifically, in the second alignment module 320, the communication data receiving unit 3210 is used to receive communication data between the base station and each of the communication tags from the base station. The communication data includes flight time and signal strength values. Considering that in secondary detection based on wireless ranging, several wireless ranging tags are installed around the receiving port, and a base station is installed at the discharge port, and the distance between the base station and each tag is obtained based on the communication between the base station and the tags, the measurement accuracy will decrease due to signal interference during communication-based distance testing because multiple tags are installed around the receiving port. This results in low initial alignment accuracy. Therefore, it is desirable to optimize the accuracy of distance measurement between the base station and each tag to improve the alignment accuracy of the discharge port and the receiving port. Therefore, in the technical solution of this application, artificial intelligence control technology based on deep learning is adopted to obtain the initial value of distance measurement through the flight time of the base station and each communication tag. Furthermore, by fusing the global implicit correlation features of each signal strength between the base station and each communication tag and the topological correlation features between each communication tag, the feature expression of the global implicit features of each signal strength is optimized by utilizing the topological features of each communication tag. Thus, in a specific example of this application, communication data between the base station and each of the communication tags is received from the base station, and the communication data includes flight time and signal strength values.

[0066] More specifically, in the second alignment module 320, the initial distance value calculation unit 3220 is used to determine multiple initial distance measurement values ​​based on the time of flight in the communication data. That is, multiple initial distance measurement values ​​are determined based on the time of flight in the communication data. In a specific example of this application, multiple initial distance measurement values ​​between the base station and each of the communication tags can be obtained by multiplying the time of flight in the communication data by the speed of light c.

[0067] More specifically, in the second pairing module 320, the signal strength semantic encoding unit 3230 is used to pass the signal strength values ​​in the communication data through a context encoder containing a one-hot encoding layer to obtain multiple signal strength context semantic feature vectors. Considering the correlation between the signal strengths of the base station and the various communication tags, a context encoder containing a one-hot encoding layer is further used to encode each signal strength value in the communication data to extract global high-dimensional semantic features between the signal strengths of the base station and the various communication tags, which are more suitable for characterizing the essential features of communication distance, thereby obtaining multiple signal strength context semantic feature vectors. Specifically, the signal strength values ​​in the communication data are one-hot encoded to obtain multiple signal strength feature vectors; the context encoder is used to perform global context semantic encoding on the multiple signal strength feature vectors to obtain multiple signal strength context semantic feature vectors. More specifically, the context encoder is used to perform global context semantic encoding on the plurality of signal strength feature vectors to obtain a plurality of signal strength context semantic feature vectors, including: arranging the plurality of signal strength feature vectors in one dimension to obtain a global signal strength feature vector; calculating the product between the global signal strength feature vector and the transpose of each of the plurality of signal strength feature vectors to obtain a plurality of self-attention association matrices; then standardizing each of the plurality of self-attention association matrices to obtain a plurality of standardized self-attention association matrices; passing each of the plurality of standardized self-attention association matrices through a Softmax classification function to obtain a plurality of probability values; and then weighting each of the plurality of signal strength feature vectors using each of the plurality of probability values ​​as a weight to obtain the plurality of signal strength context semantic feature vectors.

[0068] More specifically, in the second alignment module 320, the topology matrix construction unit 3240 is used to obtain the topology matrix of the plurality of communication tags. The values ​​at each off-diagonal position in the topology matrix represent the distance between two corresponding communication tags, and the values ​​at each diagonal position represent the distance between the corresponding base station and the communication tag. It should be understood that when obtaining the distance between a base station and each tag through communication between the base station and the tag, signal interference can lead to a decrease in measurement accuracy, resulting in low initial alignment accuracy. That is, considering that the signal strengths of the various communication tags interfere with each other spatially when communicating with the base station, if the spatial topological features of the various communication tags can be used to enhance the expression of the implicit correlation features of the various signal strengths, the accuracy of distance measurement can obviously be improved. Therefore, in the technical solution of this application, the topology matrix of the plurality of communication tags is further obtained. Here, the values ​​at each off-diagonal position in the topology matrix represent the distance between two corresponding communication tags, and the values ​​at each diagonal position in the topology matrix represent the distance between the corresponding base station and the communication tag.

[0069] More specifically, in the second pairing module 320, the topology feature extraction unit 3250 is used to pass the topology matrix through a convolutional neural network model acting as a feature extractor to obtain a communication space topology matrix. That is, the topology matrix is ​​processed through the convolutional neural network model acting as a feature extractor to extract the spatial topology features of each communication tag, thereby obtaining the communication space topology matrix. In a specific example, the convolutional neural network includes multiple cascaded neural network layers, each of which includes a convolutional layer, a pooling layer, and an activation layer. During the encoding process of the convolutional neural network, each layer performs kernel-based convolution processing on the input data during the forward propagation process, performs pooling processing on the convolutional feature map output by the convolutional layer using the pooling layer, and performs activation processing on the pooled feature map output by the pooling layer using the activation layer. The input data of the first layer of the convolutional neural network is the topology matrix; the output data of the last layer of the convolutional neural network is the communication space topology matrix. More specifically, each layer of the convolutional neural network model, which is used as a feature extractor, performs the following on the input data during the forward propagation of the layer: convolution processing on the input data to obtain a convolutional feature map, pooling the convolutional feature map along the channel dimension to obtain a pooled feature map, and non-linear activation on the pooled feature map to obtain an activation feature map.

[0070] Figure 6 This is a flowchart illustrating the convolutional neural network encoding in an automatic alignment control system based on multi-level detection according to an embodiment of this application. Figure 6 As shown, the encoding process of the convolutional neural network includes: using each layer of the convolutional neural network model as a feature extractor to process the input data in the forward propagation of the layer: S210, performing convolution processing on the input data to obtain a convolutional feature map; S220, performing pooling along the channel dimension on the convolutional feature map to obtain a pooled feature map; and S230, performing non-linear activation on the pooled feature map to obtain an activation feature map.

[0071] More specifically, in the second pairing module 320, the graph neural coding unit 3260 is used to pass the communication space topology matrix and the signal strength global correlation matrix obtained by two-dimensional arrangement of the plurality of signal strength context semantic feature vectors through a graph neural network model to obtain the communication topology signal strength global correlation matrix. In the technical solution of this application, each signal strength context semantic feature vector in the plurality of signal strength context semantic feature vectors is used as the feature representation of a node, and the communication space topology matrix is ​​used as the feature representation of the edges between nodes. The signal strength global correlation matrix obtained by two-dimensional arrangement of the plurality of signal strength context semantic feature vectors and the communication space topology matrix are passed through a graph neural network model to obtain the communication topology signal strength global correlation matrix. Specifically, the graph neural network model performs graph structure data encoding on the communication space topology matrix and the signal strength global correlation matrix through learnable neural network parameters to obtain the communication topology signal strength global correlation matrix containing irregular spatial topology features and global hidden correlation feature information of each signal strength. In this way, by fusing features of the global correlation matrix of signal strength and the communication spatial topology matrix, the feature expression of the global implicit correlation features of each signal strength can be optimized by utilizing the spatial topology features of each communication tag, thereby improving the accuracy of distance compensation.

[0072] More specifically, in the second alignment module 320, the feature distribution optimization unit 3270 is used to optimize the feature distribution of the global correlation matrix of communication topology signal strength to obtain an optimized global correlation matrix of communication topology signal strength. In particular, in the technical solution of this application, for the global correlation matrix of communication topology signal strength obtained by using a graph neural network model from the communication spatial topology matrix and the global correlation matrix of signal strength, since each row vector corresponds to the spatial topological representation of the contextual signal strength features between the base station and a single tag, the clustering effect of the feature distribution of the global correlation matrix of communication topology signal strength as a whole deteriorates. Therefore, when calculating the product between each row vector in the global correlation matrix of communication topology signal strength and the global correlation matrix of communication topology signal strength, the feature distribution of the obtained decoded feature vector may not be dense enough, affecting the accuracy of the decoded value.

[0073] Here, the applicant of this application considers that in the global correlation matrix of signal strength of the communication topology, the relationship between the feature distributions of each row vector follows a Gaussian distribution under natural conditions. That is, the average degree of correlation between each row vector as an individual feature distribution and the global feature distribution has the highest probability density, while higher and lower degrees of correlation both have lower probability densities. Therefore, based on this high-frequency distribution characteristic following a Gaussian point distribution, feature clustering defocusing fuzzy optimization can be performed on the global correlation matrix of signal strength of the communication topology, expressed as:

[0074]

[0075] Where μ and δ are the mean and standard deviation of the eigenvalue set at each location in the global correlation matrix of the signal strength of the communication topology, respectively, and m i，j This is the eigenvalue at position (i, j) of the global correlation matrix of the communication topology signal strength. The defocusing fuzziness optimization of feature clustering compensates for the dependency similarity between the high-frequency distribution features following a Gaussian point distribution and the uniform representation of the overall feature distribution, by using a statistically based feature clustering index for the focus stack representation used to estimate the clustering metric. This avoids focus fuzziness in the overall feature distribution caused by low dependency similarity, thus improving the clustering effect of the feature distribution of the global correlation matrix of the communication topology signal strength, thereby improving the accuracy of the decoded feature vector values. This improves the alignment accuracy of the material inlet and outlet, thereby increasing operational efficiency.

[0076] More specifically, in the second pairing module 320, the query unit 3280 is used to calculate the product between each row vector in the global correlation matrix of the optimized communication topology signal strength and the global correlation matrix of the optimized communication topology signal strength to obtain multiple decoded feature vectors. Considering that the global correlation matrix of the communication topology signal strength contains communication interference information between the base station and each tag, in order to accurately compensate for each distance value, the product between each row vector in the global correlation matrix of the communication topology signal strength and the global correlation matrix of the communication topology signal strength is further calculated to extract the influence of interference features between the global implicit correlation features of each signal strength on the communication distance measurement, thereby obtaining multiple decoded feature vectors. In a specific example of this application, the decoder is used to pass the multiple decoded feature vectors through the decoder to obtain multiple decoded values ​​representing the distance compensation value using the following formula; wherein, the formula is: Where X represents the plurality of decoded feature vectors, Y is the plurality of decoded values, and W is the weight matrix. This represents matrix multiplication.

[0077] More specifically, in the second alignment module 320, the decoding unit 3290 and the correction unit 3300 are configured to pass the plurality of decoded feature vectors through a decoder to obtain a plurality of decoded values ​​representing distance compensation values, and to correct the plurality of initial distance measurement values ​​based on the plurality of decoded values ​​to obtain a plurality of distance correction values. In a specific example of this application, the plurality of distance correction values ​​can be obtained by calculating the sum between the decoded values ​​and the initial distance measurement values ​​respectively.

[0078] More specifically, in the second alignment module 320, the secondary detection unit 3310 is used to perform secondary alignment of the material discharge port and the material receiving port based on the plurality of distance correction values. That is, the material discharge port and the material receiving port are aligned in a secondary manner based on the plurality of distance correction values. This improves the alignment accuracy of the material discharge port and the material receiving port. In a specific example of this application, secondary alignment is considered complete when the various distance correction values ​​are equal or the differences between the various distance correction values ​​are within a predetermined fluctuation range.

[0079] Specifically, during the operation of the multi-level detection-based automatic alignment control system 300, the third alignment module 330 is used to perform three-level alignment between the material discharge port and the material receiving port based on multiple lidars deployed at the material receiving port. It should be understood that during the three-level alignment process, four wireless ranging-based lidars are installed around the material receiving port. The real-time distance from each lidar to the material receiving port is measured in decibels. When the distances from each lidar to the material receiving port are equal or the distances differ within a specified standard range, automatic alignment is completed. This ensures precise alignment between the material discharge port and the material receiving port, while also preventing collisions between them, thus improving the safety of equipment operation.

[0080] In summary, the automatic alignment control system 300 based on multi-level detection according to the embodiments of this application is explained. It employs deep learning-based artificial intelligence control technology to obtain initial distance measurement values ​​using the flight times of the base station and each communication tag. Furthermore, it optimizes the feature representation of the global implicit features of each signal strength by fusing the global implicit correlation features of each signal strength between the base station and each communication tag with the topological correlation features between the communication tags, utilizing the topological features of each communication tag. Thus, based on the multiple distance correction values, secondary alignment of the material discharge port and the material receiving port can be performed to improve the alignment accuracy of the material discharge port and the material receiving port, thereby improving operational efficiency.

[0081] As described above, the automatic alignment control system based on multi-level detection according to the embodiments of this application can be implemented in various terminal devices. In one example, the automatic alignment control system 300 based on multi-level detection according to the embodiments of this application can be integrated into the terminal device as a software module and / or a hardware module. For example, the automatic alignment control system 300 based on multi-level detection can be a software module in the operating system of the terminal device, or it can be an application developed for the terminal device; of course, the automatic alignment control system 300 based on multi-level detection can also be one of many hardware modules of the terminal device.

[0082] Alternatively, in another example, the multi-level detection-based automatic alignment control system 300 and the terminal device can also be separate devices, and the multi-level detection-based automatic alignment control system 300 can be connected to the terminal device via wired and / or wireless networks, and transmit interactive information in accordance with an agreed data format.

[0083] Exemplary methods

[0084] Figure 7 This is a flowchart of an automatic centering control method based on multi-level detection according to an embodiment of this application. Figure 7 As shown, the automatic alignment control method based on multi-level detection according to an embodiment of this application includes the following steps: S110, performing first-level alignment of the material discharge port and the material receiving port based on a GPS positioning module; S120, performing second-level alignment of the material discharge port and the material receiving port based on communication between a base station and a communication tag; and S130, performing third-level alignment of the material discharge port and the material receiving port based on multiple lidars deployed at the material receiving port.

[0085] In one example, in the above-described automatic alignment control method based on multi-level detection, step S110 includes: obtaining the absolute coordinates of the receiving port based on the GPS positioning module; using the absolute coordinates of the receiving port as a reference, determining the absolute coordinates that the discharge port should reach; and determining that the first-level alignment is completed in response to the absolute coordinates of the discharge port being the absolute coordinates that the discharge port should reach.

[0086] In one example, in the above-described automatic alignment control method based on multi-level detection, step S120 includes: receiving communication data between the base station and each of the communication tags, the communication data including flight time and signal strength values; determining multiple initial distance measurement values ​​based on the flight time in the communication data; passing the signal strength values ​​in the communication data through a context encoder containing a one-hot coding layer to obtain multiple signal strength context semantic feature vectors; obtaining a topology matrix of the multiple communication tags, where the values ​​at each off-diagonal position in the topology matrix represent the distance between two corresponding communication tags, and the values ​​at each diagonal position in the topology matrix represent the distance between the corresponding base station and the communication tag; passing the topology matrix through a convolutional neural network model as a feature extractor to obtain a communication space topology matrix; and then... The communication space topology matrix and the global correlation matrix of signal strength obtained by arranging the multiple signal strength context semantic feature vectors in a two-dimensional manner are used to obtain the global correlation matrix of communication topology signal strength through a graph neural network model; the feature distribution of the global correlation matrix of communication topology signal strength is optimized to obtain an optimized global correlation matrix of communication topology signal strength; the product between each row vector in the optimized global correlation matrix of communication topology signal strength and the optimized global correlation matrix of communication topology signal strength is calculated to obtain multiple decoded feature vectors; the multiple decoded feature vectors are respectively passed through a decoder to obtain multiple decoded values ​​for representing distance compensation values; based on the multiple decoded values, the multiple initial values ​​of distance measurement are corrected to obtain multiple distance correction values; and based on the multiple distance correction values, a two-level alignment is performed on the discharge port and the receiving port.

[0087] In summary, the automatic alignment control method based on multi-level detection according to the embodiments of this application is explained. It employs deep learning-based artificial intelligence control technology to obtain initial distance measurement values ​​using the flight time of the base station and each communication tag. Furthermore, it optimizes the feature representation of the global implicit features of each signal strength by fusing the global implicit correlation features of each signal strength between the base station and each communication tag with the topological correlation features between the communication tags, utilizing the topological features of each communication tag. Thus, based on the multiple distance correction values, two-stage alignment can be performed on the material discharge port and the material receiving port to improve the alignment accuracy of the material discharge port and the material receiving port, thereby improving operational efficiency.

[0088] Exemplary electronic devices

[0089] Below, for reference Figure 8 This describes an electronic device according to embodiments of the present application.

[0090] Figure 8 A block diagram of an electronic device according to an embodiment of this application is illustrated.

[0091] like Figure 8 As shown, the electronic device 10 includes one or more processors 11 and memory 12.

[0092] The processor 11 may be a central processing unit (CPU) or other form of processing unit with data processing capabilities and / or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.

[0093] The memory 12 may include one or more computer program products, which may include various forms of computer-readable storage media, such as volatile memory and / or non-volatile memory. The volatile memory may include, for example, random access memory (RAM) and / or cache memory. The non-volatile memory may include, for example, read-only memory (ROM), hard disk, flash memory, etc. One or more computer program instructions may be stored on the computer-readable storage medium, and the processor 11 may execute the program instructions to implement the functions and / or other desired functions in the multi-level detection-based automatic alignment control system of the various embodiments of this application described above. Various contents, such as distance correction values, may also be stored in the computer-readable storage medium.

[0094] In one example, the electronic device 10 may also include an input device 13 and an output device 14, which are interconnected via a bus system and / or other forms of connection mechanism (not shown).

[0095] The input device 13 may include, for example, a keyboard, a mouse, etc.

[0096] The output device 14 can output various information to the outside, including decoded values. The output device 14 may include, for example, a display, a speaker, a printer, and a communication network and its connected remote output devices, etc.

[0097] Of course, for the sake of simplicity, Figure 8 Only some of the components of the electronic device 10 relevant to this application are shown in this illustration; components such as buses, input / output interfaces, etc., are omitted. In addition, the electronic device 10 may include any other suitable components depending on the specific application.

Claims

1. An automatic alignment control system based on multi-level detection, characterized in that, include: The first alignment module is used to perform primary alignment of the material inlet and the material receiving inlet based on the GPS positioning module. The second alignment module is used to perform secondary alignment of the material discharge port and the material receiving port based on the communication between the base station and the communication tag. as well as The third alignment module is used to perform three-level alignment between the discharge port and the receiving port based on multiple lidars deployed at the receiving port; The second centering module includes: A communication data receiving unit is configured to receive communication data between the base station and each of the communication tags from the base station, the communication data including flight time and signal strength values; The distance initial value calculation unit is used to determine multiple initial values ​​for distance measurement based on the flight time in the communication data; The signal strength semantic coding unit is used to pass the signal strength values ​​in the communication data through a context encoder containing a one-hot coding layer to obtain multiple signal strength context semantic feature vectors. A topology matrix construction unit is used to obtain the topology matrix of the plurality of communication tags, wherein the value of each position on the off-diagonal side of the topology matrix is ​​the distance between two corresponding communication tags, and the value of each position on the diagonal side of the topology matrix is ​​the distance between the corresponding base station and the communication tag. A topology feature extraction unit is used to pass the topology matrix through a convolutional neural network model as a feature extractor to obtain a communication space topology matrix. The graph neural coding unit is used to pass the communication space topology matrix and the signal strength global correlation matrix obtained by two-dimensional arrangement of the plurality of signal strength context semantic feature vectors through a graph neural network model to obtain the communication topology signal strength global correlation matrix; The feature distribution optimization unit is used to perform feature distribution optimization on the global correlation matrix of the communication topology signal strength to obtain an optimized global correlation matrix of the communication topology signal strength. The query unit is used to calculate the product between each row vector in the global correlation matrix of the signal strength of the optimized communication topology and the global correlation matrix of the signal strength of the optimized communication topology to obtain multiple decoded feature vectors; A decoding unit is used to pass the plurality of decoded feature vectors through a decoder to obtain a plurality of decoded values ​​representing distance compensation values; A correction unit is used to correct the multiple initial distance measurement values ​​based on the multiple decoded values ​​to obtain multiple corrected distance values; The secondary detection unit is used to perform secondary alignment of the material discharge port and the material receiving port based on the multiple distance correction values.

2. The automatic alignment control system based on multi-level detection according to claim 1, characterized in that, The first centering module includes: A positioning unit is used to obtain the absolute coordinates of the receiving port based on the GPS positioning module; The target unit is used to determine the absolute coordinates that the discharge port should reach, based on the absolute coordinates of the receiving port. The centering completion module is used to determine the completion of the first-level centering in response to the absolute coordinates of the material discharge port being the absolute coordinates that the material discharge port should reach.

3. The automatic alignment control system based on multi-level detection according to claim 2, characterized in that, The signal strength semantic coding unit is further used for: One-hot coding subunit is used to encode the signal strength values ​​in the communication data one-hot to obtain multiple signal strength feature vectors; A global context encoding subunit is used to perform global context semantic encoding on the plurality of signal strength feature vectors using the context encoder to obtain a plurality of signal strength context semantic feature vectors.

4. The automatic alignment control system based on multi-level detection according to claim 3, characterized in that, The global context coding subunit includes: The query vector constructs a second-level sub-unit, which is used to arrange the multiple signal strength feature vectors in one dimension to obtain a global signal strength feature vector; The self-attention second-level subunit is used to calculate the product between the global signal intensity feature vector and the transpose of each of the multiple signal intensity feature vectors to obtain multiple self-attention correlation matrices; The standardized second-level subunit is used to standardize each of the multiple self-attention association matrices to obtain multiple standardized self-attention association matrices. The attention calculation subunit is used to obtain multiple probability values ​​by passing each of the multiple standardized self-attention association matrices through the Softmax classification function. The attention-applying second-level subunit is used to weight each of the multiple signal intensity feature vectors with each probability value among the multiple probability values ​​as a weight to obtain the multiple signal intensity context semantic feature vectors.

5. The automatic alignment control system based on multi-level detection according to claim 4, characterized in that, The topological feature extraction unit is further configured to: use each layer of the convolutional neural network model, which serves as the feature extractor, to process the input data during the forward propagation of the layer. The input data is processed by convolution to obtain a convolutional feature map; The convolutional feature map is pooled along the channel dimension to obtain a pooled feature map; as well as The pooled feature map is nonlinearly activated to obtain an activated feature map; The output of the last layer of the convolutional neural network, which serves as the feature extractor, is the communication space topology matrix, and the input of the first layer of the convolutional neural network, which serves as the feature extractor, is the topology matrix.

6. The automatic alignment control system based on multi-level detection according to claim 5, characterized in that, The feature distribution optimization unit is further configured to: perform feature distribution optimization on the global correlation matrix of the communication topology signal strength using the following formula to obtain the optimized global correlation matrix of the communication topology signal strength; The formula is as follows: Where μ and δ are the mean and standard deviation of the eigenvalue set at each location in the global correlation matrix of the signal strength of the communication topology, respectively, and m i,j It is the eigenvalue at position (i,j) of the global correlation matrix of the signal strength of the communication topology.

7. The automatic alignment control system based on multi-level detection according to claim 6, characterized in that, The decoding unit is further configured to: use the decoder to pass the plurality of decoded feature vectors through the decoder respectively to obtain a plurality of decoded values ​​representing the distance compensation value; wherein the formula is: Where X represents the plurality of decoded feature vectors, Y is the plurality of decoded values, and W is the weight matrix. This represents matrix multiplication.

8. The automatic alignment control system based on multi-level detection according to claim 7, characterized in that, The correction unit is further configured to calculate the sum between the decoded value and the initial distance measurement value to obtain the plurality of distance correction values.

9. An automatic alignment control method based on multi-level detection, using the automatic alignment control system based on multi-level detection as described in claim 1, characterized in that, include: Based on the GPS positioning module, the material inlet and the receiving inlet are aligned in one stage. Based on the communication between the base station and the communication tag, the material discharge port and the material receiving port are aligned in two stages. as well as Based on multiple lidar sensors deployed at the receiving port, the discharge port and the receiving port are aligned in three stages.

Images