Equipment protection system and method for bucket wheel excavators

Abstract

This application relates to the field of intelligent monitoring, specifically disclosing an equipment protection system and method for bucket wheel excavators. It employs a deep learning-based neural network model to monitor the temperature of multiple components of the bucket wheel excavator and constructs a spatial topology matrix between these components to represent the thermal influence between them. This more accurately and reasonably represents the temperature distribution characteristics of the bucket wheel excavator. Furthermore, based on these temperature distribution characteristics, it determines whether an over-temperature protection alert should be issued. This approach takes into account the synergy between multiple components in the equipment, thereby improving the intelligence and rationality of the over-temperature protection.

Description

Technical Field

[0001] This application relates to the field of intelligent monitoring, and more specifically, to an equipment protection system and method for bucket wheel excavators. Background Technology

[0002] In recent years, with the development of intelligent equipment, stacker-reclaimers such as bucket wheel excavators are also moving towards unmanned operation. Safety technology is essential for achieving intelligent and unmanned operation of stacker-reclaimers, as this eliminates the need for constant human monitoring.

[0003] Among various protection methods, over-temperature protection is a type of equipment protection technology. Existing over-temperature protection schemes for equipment typically monitor the equipment's temperature and determine whether to activate over-temperature protection based on a comparison between a predetermined threshold and the real-time temperature. However, this protection scheme ignores the fact that the equipment is an organic whole. The temperature value at one location cannot characterize the temperature distribution of the entire equipment, and temperature transfer and thermal effects occur between multiple components of a device. Ignoring the coordination between multiple components of the equipment will reduce the intelligence and rationality of the over-temperature protection.

[0004] Therefore, an optimized equipment protection scheme for bucket wheel excavators is needed. Summary of the Invention

[0005] To address the aforementioned technical problems, this application is proposed. Embodiments of this application provide an equipment protection system and method for a bucket wheel excavator. This system employs a deep learning-based neural network model to monitor the temperature of multiple components of the bucket wheel excavator and constructs a spatial topology matrix between these components to represent the thermal influence between them. This more accurately and reasonably represents the temperature distribution characteristics of the bucket wheel excavator. Furthermore, based on these temperature distribution characteristics, it determines whether an over-temperature protection alert should be issued. This approach takes into account the coordination between multiple components in the equipment, thereby improving the intelligence and rationality of the over-temperature protection.

[0006] According to one aspect of this application, a device protection system for a bucket wheel excavator is provided, comprising:

[0007] The temperature monitoring module is used to acquire the temperature values ​​of multiple components of the bucket wheel excavator at multiple predetermined time points within a predetermined time period.

[0008] The temperature time series feature extraction module is used to arrange the temperature values ​​of each component at multiple predetermined time points within a predetermined time period into temperature input vectors according to the time dimension, and then use a first convolutional neural network model with a one-dimensional convolutional kernel to obtain multiple temperature feature vectors.

[0009] A spatial topology construction module is used to construct a spatial topology matrix between the multiple components, wherein the values ​​at each position on the non-diagonal side of the spatial topology matrix are the distances between the corresponding two components.

[0010] A spatial topology feature extraction module is used to pass the spatial topology matrix through a second convolutional neural network model, which acts as a feature extractor, to obtain a spatial topology feature matrix.

[0011] A globalization module is used to arrange the multiple temperature feature vectors in a two-dimensional manner to obtain a global temperature feature matrix.

[0012] The graph feature extraction module is used to obtain the topological global temperature feature matrix by passing the global temperature feature matrix and the spatial topological feature matrix through a graph neural network model.

[0013] The feature distribution enhancement module is used to enhance the consistency of feature distribution between vectors in the topological global temperature feature matrix to obtain optimized classification feature vectors; and

[0014] The protection result generation module is used to pass the optimized classification feature vector through a classifier to obtain a classification result, which is used to indicate whether an over-temperature protection reminder is issued.

[0015] In the aforementioned equipment protection system for bucket wheel excavators, the temperature time-series feature extraction module is further configured to: use each layer of the first convolutional neural network model using a one-dimensional convolutional kernel to perform the following operations on the input data during the forward propagation of the layer: convolution processing the input data to obtain a convolutional feature map; pooling the convolutional feature map based on the feature matrix to obtain a pooled feature map; and nonlinear activation of the pooled feature map to obtain an activation feature map; wherein the output of the last layer of the first convolutional neural network using a one-dimensional convolutional kernel is the temperature feature vector, and the input of the first layer of the first convolutional neural network using a one-dimensional convolutional kernel is the temperature input vector.

[0016] In the aforementioned equipment protection system for bucket wheel excavators, the spatial topology feature extraction module is further configured to: use each layer of the second convolutional neural network model, which serves 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 second convolutional neural network, which serves as the feature extractor, is the spatial topology feature matrix, and the input of the first layer of the second convolutional neural network, which serves as the feature extractor, is the spatial topology matrix.

[0017] In the aforementioned equipment protection system for bucket wheel excavators, the second convolutional neural network model, which serves as the feature extractor, is a deep residual network model.

[0018] In the aforementioned equipment protection system for bucket wheel excavators, the graph feature extraction module is further configured to use the graph neural network model to encode the global temperature feature matrix and the spatial topology feature matrix with learnable neural network parameters to obtain the topological global temperature feature matrix containing irregular spatial topology features and high-dimensional temperature distribution temporal features.

[0019] In the aforementioned equipment protection system for bucket wheel excavators, the feature distribution enhancement module is further configured to: perform vector norming and Hilbert probability spacerization on the classification feature vector using the following formula to obtain the optimized classification feature vector; wherein, the formula is:

[0020]

[0021] Where V is the classification feature vector, and ||V||² represents the L2 norm of the classification feature vector. v represents the squared 2-norm of the classification feature vector, i.e., the inner product of the classification feature vector itself. i It is the i-th feature value of the classification feature vector, exp(·) represents the vector exponentiation operation, which means calculating the natural exponent function value raised to the power of each feature value in the vector, and v i ′ is the i-th feature value of the optimized classification feature vector.

[0022] In the aforementioned equipment protection system for bucket wheel excavators, the protection result generation module includes: a fully connected encoding unit, used to perform fully connected encoding on the optimized classification feature vector using multiple fully connected layers of the classifier to obtain an encoded classification feature vector; and a classification result generation unit, used to pass the encoded classification feature vector through the Softmax classification function of the classifier to obtain the classification result.

[0023] According to another aspect of this application, a method for protecting equipment for a bucket wheel excavator is provided, comprising:

[0024] The temperature values ​​of multiple components of the bucket wheel excavator at multiple predetermined time points within a predetermined time period are obtained.

[0025] The temperature values ​​of each component at multiple predetermined time points within a predetermined time period are arranged into temperature input vectors according to the time dimension, and then multiple temperature feature vectors are obtained by using a first convolutional neural network model with a one-dimensional convolutional kernel.

[0026] Construct a spatial topology matrix between the multiple components, wherein the values ​​at each off-diagonal position in the spatial topology matrix are the distances between the corresponding two components;

[0027] The spatial topology matrix is ​​passed through a second convolutional neural network model, which acts as a feature extractor, to obtain a spatial topology feature matrix.

[0028] The multiple temperature feature vectors are arranged in a two-dimensional manner to obtain a global temperature feature matrix;

[0029] The global temperature feature matrix and the spatial topology feature matrix are used through a graph neural network model to obtain the topological global temperature feature matrix;

[0030] The topological global temperature feature matrix is ​​subjected to vector feature distribution consistency enhancement to obtain optimized classification feature vectors; and

[0031] The optimized classification feature vector is passed through a classifier to obtain a classification result, which is used to indicate whether an over-temperature protection alert is issued.

[0032] According to another aspect of this application, an electronic device is provided, comprising: a processor; and a memory storing computer program instructions that, when executed by the processor, cause the processor to perform the device protection method for a bucket wheel machine as described above.

[0033] 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 equipment protection method for a bucket wheel excavator as described above.

[0034] Compared with existing technologies, this application provides an equipment protection system and method for bucket wheel excavators. By employing a deep learning-based neural network model, it monitors the temperature of multiple components of the bucket wheel excavator and constructs a spatial topology matrix between these components to represent the thermal influence between them. This more accurately and reasonably represents the temperature distribution characteristics of the bucket wheel excavator. Furthermore, based on these temperature distribution characteristics, it determines whether an over-temperature protection alert should be issued. In this way, it can take into account the synergy between multiple components in the equipment, thereby improving the intelligence and rationality of the over-temperature protection. Attached Figure Description

[0035] 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.

[0036] Figure 1 This is an application scenario diagram of an equipment protection system for a bucket wheel excavator according to an embodiment of this application;

[0037] Figure 2 This is a block diagram of an equipment protection system for a bucket wheel excavator according to an embodiment of this application;

[0038] Figure 3 This is a system architecture diagram of an equipment protection system for a bucket wheel excavator according to an embodiment of this application;

[0039] Figure 4 This is a flowchart of the first convolutional neural network encoding in the equipment protection system for a bucket wheel excavator according to an embodiment of this application;

[0040] Figure 5 This is a flowchart of the second convolutional neural network encoding in the equipment protection system for a bucket wheel excavator according to an embodiment of this application;

[0041] Figure 6 This is a block diagram of a protection result generation module in an equipment protection system for a bucket wheel excavator according to an embodiment of this application;

[0042] Figure 7 This is a flowchart of a device protection method for a bucket wheel excavator according to an embodiment of this application;

[0043] Figure 8 This is a block diagram of an electronic device according to an embodiment of this application. Detailed Implementation

[0044] 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.

[0045] Application Overview

[0046] As mentioned in the background technology, over-temperature protection is an important aspect of equipment protection for bucket wheel excavators. However, existing over-temperature protection schemes neglect the fact that the equipment is an organic whole. The temperature value at one location cannot characterize the temperature distribution of the entire equipment. Furthermore, temperature transmission and thermal effects occur between multiple components of the equipment. Ignoring the coordination between these components will reduce the intelligence and rationality of the over-temperature protection.

[0047] To address the aforementioned issues, the technical solution of this application involves monitoring the temperature of multiple components of the bucket wheel excavator during over-temperature protection. A spatial topology matrix between these components is used to represent the thermal influence between them, thereby more accurately and reasonably representing the temperature distribution characteristics of the bucket wheel excavator. Based on these temperature distribution characteristics, it is then determined whether an over-temperature protection alert should be issued.

[0048] Specifically, firstly, the temperature values ​​of multiple components of the bucket wheel excavator at multiple predetermined time points within a predetermined time period are acquired. That is, temperature sensors are used to monitor the temperature of multiple components of the bucket wheel excavator to collect discrete data on the temporal distribution of the temperature of each component. Next, the temperature values ​​of each component at multiple predetermined time points within the predetermined time period are arranged into temperature input vectors according to the time dimension, and then a first convolutional neural network model with a one-dimensional convolutional kernel is used to obtain multiple temperature feature vectors. In other words, after vectorizing the temperature distribution of each component of the bucket wheel excavator, the temperature input vector is subjected to one-dimensional convolutional encoding using the first convolutional neural network model with a one-dimensional convolutional kernel to capture the correlation pattern features between temperature distributions within local time windows in the temperature input vector, i.e., the multiple temperature feature vectors.

[0049] Furthermore, considering that the spatial distance between components is a crucial factor in temperature transmission and thermal effect analysis, the technical solution of this application uses a spatial topology matrix between the multiple components. In this matrix, the values ​​at each off-diagonal position represent the distance between the corresponding two components, while the values ​​at each diagonal position are zero. Here, the distance between the center points of two components is used as the distance between them.

[0050] Next, the spatial topology matrix is ​​processed by a second convolutional neural network model, which acts as a feature extractor, to obtain a spatial topology feature matrix. That is, a convolutional neural network model, which excels in local feature extraction, is used as a feature extractor to perform kernel-based local spatial domain feature filtering on the spatial topology matrix to capture the high-dimensional implicit features of the spatial distribution contained within the matrix. The convolutional kernel has learnable neural network parameters. In a specific example of this application, the second convolutional neural network model acting as the feature extractor is a deep residual network model.

[0051] Specifically, in the technical solution of this application, the temperature feature vectors of each component of the bucket wheel excavator are represented by high-dimensional features relative to the nodes, while the spatial topological feature matrix is ​​used to represent the high-dimensional feature representation of the edges between nodes. That is, the spatial topological feature matrix and the multiple temperature feature vectors form high-dimensional graph data. Based on this, in the technical solution of this application, a graph neural network model is used to encode the high-dimensional graph data formed by the spatial topological feature matrix and the multiple temperature feature vectors to obtain a feature distribution containing irregular spatial topological features and high-dimensional temperature distribution temporal features.

[0052] Specifically, the multiple temperature feature vectors are first arranged in a two-dimensional manner to obtain a global temperature feature matrix. Then, the global temperature feature matrix and the spatial topology feature matrix are processed by a graph neural network model to obtain a topological global temperature feature matrix. The graph neural network model encodes the global temperature feature matrix and the spatial topology feature matrix with learnable neural network parameters to obtain the topological global temperature feature matrix containing irregular spatial topology features and high-dimensional temperature distribution temporal features.

[0053] After obtaining the topological global temperature feature matrix, the matrix is ​​processed by a classifier to obtain a classification result. This classification result indicates whether an over-temperature protection alert should be issued. In other words, after obtaining the global temperature distribution features of the bucket wheel excavator, the classifier is used to classify and determine these features to obtain a classification result indicating whether an over-temperature protection alert should be issued.

[0054] Specifically, in the technical solution of this application, when obtaining the topological global temperature feature matrix by passing the global temperature feature matrix and the spatial topological feature matrix through a graph neural network model, each topological global temperature feature vector of the topological global temperature feature matrix, such as a row vector, expresses the correlation features of the temperature time series distribution of a single component under the spatial topology of multiple components. The feature distribution of each topological global temperature feature vector will be inconsistent, which leads to a special cross-vector anomaly distribution in the topological global temperature feature matrix obtained by directly arranging the topological global temperature feature vectors. When classifying by a classifier, the dependence on a single classification result is poor, affecting the accuracy of the classification result.

[0055] Therefore, the classification feature vector obtained after expanding the topological global temperature feature matrix is ​​subjected to Hilbert probability space normalization, specifically expressed as follows:

[0056]

[0057] V is the classification feature vector, and ||V||² represents the L2 norm of the classification feature vector. It represents its square, that is, the inner product of the classification feature vectors themselves, v i It is the i-th feature value of the classification feature vector V, and v i ′ is the i-th feature value of the optimized classification feature vector V′.

[0058] Here, the normed Hilbert probability spaceization of the vector is used to perform a probabilistic interpretation of the classification feature vector V within a Hilbert space that defines the vector inner product. This reduces the hidden perturbation of the class representation of the specific local distribution of the classification feature vector V to the class representation of the overall Hilbert space topology, thereby improving the robustness of the feature distribution of the classification feature vector V converging to the classification regression with a predetermined classification probability. Simultaneously, the establishment of a metric-induced probability space structure enhances the long-range dependence of the feature distribution of the classification feature vector V on the classification result across classifiers. Thus, directly classifying the optimized classification feature vector V′ through a classifier improves the dependence of the topological global temperature feature matrix on the classification result when classified by the classifier, thereby improving the accuracy of the classification result.

[0059] Based on this, this application proposes an equipment protection system for a bucket wheel excavator, comprising: a temperature monitoring module for acquiring temperature values ​​of multiple components of the bucket wheel excavator at multiple predetermined time points within a predetermined time period; a temperature time-series feature extraction module for arranging the temperature values ​​of each component at multiple predetermined time points within the predetermined time period into temperature input vectors according to the time dimension, and then obtaining multiple temperature feature vectors using a first convolutional neural network model with a one-dimensional convolutional kernel; a spatial topology construction module for constructing a spatial topology matrix between the multiple components, wherein the value at each position on the non-diagonal side of the spatial topology matrix is ​​the distance between the corresponding two components; and a spatial topology feature extraction module for extracting the spatial topology features. The system employs a first convolutional neural network model, which acts as a feature extractor, to obtain a spatial topological feature matrix. A globalization module arranges the multiple temperature feature vectors in a two-dimensional manner to obtain a global temperature feature matrix. A graph feature extraction module processes the global temperature feature matrix and the spatial topological feature matrix through a graph neural network model to obtain a topological global temperature feature matrix. A feature distribution enhancement module strengthens the consistency of feature distribution between vectors in the topological global temperature feature matrix to obtain optimized classification feature vectors. Finally, a protection result generation module processes the optimized classification feature vectors through a classifier to obtain a classification result, which indicates whether an over-temperature protection alert is issued.

[0060] Figure 1 This is an application scenario diagram of an equipment protection system for a bucket wheel excavator according to an embodiment of this application. For example... Figure 1 As shown, in this application scenario, a temperature sensor (e.g., such as...) is used... Figure 1 The illustrated T) acquires temperature values ​​of multiple components of the bucket wheel excavator at multiple predetermined time points within a predetermined time period. Then, the above data is input to a server deployed with equipment protection algorithms for the bucket wheel excavator (e.g., Figure 1 In S), the server is able to process the input data using the equipment protection algorithm for the bucket wheel machine to generate a classification result indicating whether an over-temperature protection alert has been issued.

[0061] 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.

[0062] Exemplary System

[0063] Figure 2 This is a block diagram of a device protection system for a bucket wheel excavator according to an embodiment of this application. Figure 2As shown, the equipment protection system 300 for a bucket wheel excavator according to an embodiment of this application includes: a temperature monitoring module 310; a temperature time series feature extraction module 320; a spatial topology construction module 330; a spatial topology feature extraction module 340; a globalization module 350; a graph feature extraction module 360; a feature distribution enhancement module 370; and a protection result generation module 380.

[0064] The temperature monitoring module 310 is used to acquire the temperature values ​​of multiple components of the bucket wheel excavator at multiple predetermined time points within a predetermined time period. The temperature time-series feature extraction module 320 is used to arrange the temperature values ​​of each component at multiple predetermined time points within the predetermined time period into temperature input vectors according to the time dimension, and then obtain multiple temperature feature vectors by using a first convolutional neural network model with a one-dimensional convolutional kernel. The spatial topology construction module 330 is used to construct a spatial topology matrix between the multiple components, wherein the value of each position on the non-diagonal part of the spatial topology matrix is ​​the distance between the corresponding two components. The spatial topology feature extraction module 340 is used to extract the spatial topology matrix using a feature extractor. The second convolutional neural network model is used to obtain the spatial topology feature matrix; the globalization module 350 is used to arrange the multiple temperature feature vectors in two dimensions to obtain the global temperature feature matrix; the graph feature extraction module 360 ​​is used to pass the global temperature feature matrix and the spatial topology feature matrix through a graph neural network model to obtain the topological global temperature feature matrix; the feature distribution enhancement module 370 is used to enhance the consistency of feature distribution between vectors of the topological global temperature feature matrix to obtain optimized classification feature vectors; and the protection result generation module 380 is used to pass the optimized classification feature vectors through a classifier to obtain classification results, the classification results being used to indicate whether an over-temperature protection reminder is issued.

[0065] Figure 3 This is a system architecture diagram of an equipment protection system for a bucket wheel excavator according to an embodiment of this application. Figure 3As shown, in this network architecture, the temperature monitoring module 310 first acquires the temperature values ​​of multiple components of the bucket wheel excavator at multiple predetermined time points within a predetermined time period. Then, the temperature time-series feature extraction module 320 arranges the temperature values ​​of each component acquired by the temperature monitoring module 310 at multiple predetermined time points within the predetermined time period into temperature input vectors according to the time dimension, and then uses a first convolutional neural network model with a one-dimensional convolutional kernel to obtain multiple temperature feature vectors. The spatial topology construction module 330 constructs a spatial topology matrix between the multiple components, where the value at each off-diagonal position in the spatial topology matrix is ​​the distance between the corresponding two components. Finally, the spatial topology feature extraction module 340 processes the spatial topology matrix constructed by the spatial topology construction module 330 through a second convolutional neural network model, which acts as a feature extractor. The network model is used to obtain a spatial topology feature matrix; the globalization module 350 arranges multiple temperature feature vectors obtained by the temperature time series feature extraction module 320 in a two-dimensional manner to obtain a global temperature feature matrix; then, the graph feature extraction module 360 ​​uses a graph neural network model to obtain a topological global temperature feature matrix through the global temperature feature matrix obtained by the globalization module 350 and the spatial topology feature matrix obtained by the spatial topology feature extraction module 340; the feature distribution enhancement module 370 enhances the consistency of feature distribution between vectors in the topological global temperature feature matrix obtained by the graph feature extraction module 360 ​​to obtain an optimized classification feature vector; furthermore, the protection result generation module 380 uses a classifier to obtain a classification result, which is used to indicate whether an over-temperature protection reminder is issued.

[0066] Specifically, during the operation of the equipment protection system 300 for the bucket wheel excavator, the temperature monitoring module 310 is used to acquire the temperature values ​​of multiple components of the bucket wheel excavator at multiple predetermined time points within a predetermined time period. It should be understood that when performing over-temperature protection on the bucket wheel excavator, it is necessary to monitor the temperature of multiple components of the bucket wheel excavator. Therefore, in a specific example of this application, temperature sensors can be used to acquire the temperature values ​​of multiple components of the bucket wheel excavator at multiple predetermined time points within a predetermined time period; that is, temperature sensors are used to monitor the temperature of multiple components of the bucket wheel excavator to collect discrete data on the time-series temperature distribution of each component.

[0067] Specifically, during the operation of the equipment protection system 300 for the bucket wheel excavator, the temperature time-series feature extraction module 320 is used to arrange the temperature values ​​of each component at multiple predetermined time points within a predetermined time period into temperature input vectors according to the time dimension, and then obtain multiple temperature feature vectors using a first convolutional neural network model with a one-dimensional convolutional kernel. In the technical solution of this application, the temperature values ​​of each component at multiple predetermined time points within a predetermined time period are arranged into temperature input vectors according to the time dimension, and then multiple temperature feature vectors are obtained using a first convolutional neural network model with a one-dimensional convolutional kernel. That is, after vectorizing the temperature distribution of each component of the bucket wheel excavator, the temperature input vector is subjected to one-dimensional convolutional encoding using the first convolutional neural network model with a one-dimensional convolutional kernel to capture the correlation pattern features between temperature distributions within a local time window in the temperature input vector, i.e., the multiple temperature feature vectors. In a specific example, the first convolutional neural network includes multiple cascaded neural network layers, where each neural network layer includes a convolutional layer, a pooling layer, and an activation layer. In the encoding process of the first convolutional neural network, each layer of the first convolutional neural network performs kernel-based convolution processing on the input data during the forward propagation of the layer, 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.

[0068] Figure 4 This is a flowchart illustrating the encoding of a first convolutional neural network in an equipment protection system for a bucket wheel excavator according to an embodiment of this application. Figure 4 As shown, the encoding process of the first convolutional neural network includes: each layer of the first convolutional neural network model using a one-dimensional convolutional kernel performs the following operations on the input data during the forward propagation of the layer: S210, performing convolution processing on the input data to obtain a convolutional feature map; S220, performing pooling based on the feature matrix on the convolutional feature map to obtain a pooled feature map; and S230, performing nonlinear activation on the pooled feature map to obtain an activation feature map; wherein, the output of the last layer of the first convolutional neural network using a one-dimensional convolutional kernel is the temperature feature vector, and the input of the first layer of the first convolutional neural network using a one-dimensional convolutional kernel is the temperature input vector.

[0069] Specifically, during the operation of the equipment protection system 300 for the bucket wheel excavator, the spatial topology construction module 330 is used to construct a spatial topology matrix between the multiple components. The values ​​at each off-diagonal position in the spatial topology matrix represent the distance between the corresponding two components. Considering that the spatial distance between components is a crucial factor in temperature transmission and thermal effect analysis, in the technical solution of this application, the spatial topology matrix between the multiple components contains values ​​at each off-diagonal position representing the distance between the corresponding two components, and values ​​at each diagonal position representing zero. Here, the distance between the center points of two components is used as the distance between the two components.

[0070] Specifically, during the operation of the equipment protection system 300 for the bucket wheel excavator, the spatial topology feature extraction module 340 is used to pass the spatial topology matrix through a second convolutional neural network model, which acts as a feature extractor, to obtain a spatial topology feature matrix. That is, a convolutional neural network model with excellent performance in local feature extraction is used as a feature extractor to perform kernel-based local spatial domain feature filtering on the spatial topology matrix to capture the high-dimensional implicit features of the spatial distribution contained in the spatial topology matrix. The convolutional kernel has learnable neural network parameters. In a specific example of this application, the second convolutional neural network model acting as the feature extractor is a deep residual network model.

[0071] Figure 5 This is a flowchart illustrating the second convolutional neural network encoding in an equipment protection system for a bucket wheel excavator according to an embodiment of this application. Figure 5 As shown, the encoding process of the second convolutional neural network includes: each layer of the second convolutional neural network model, which serves as a feature extractor, performs the following operations on the input data during the forward propagation of the layer: S310, performing convolution processing on the input data to obtain a convolutional feature map; S320, performing pooling along the channel dimension on the convolutional feature map to obtain a pooled feature map; and S330, performing nonlinear activation on the pooled feature map to obtain an activation feature map; wherein, the output of the last layer of the second convolutional neural network serving as a feature extractor is the spatial topological feature matrix, and the input of the first layer of the second convolutional neural network serving as a feature extractor is the spatial topological matrix.

[0072] Specifically, during the operation of the equipment protection system 300 for the bucket wheel excavator, the globalization module 350 and the graph feature extraction module 360 ​​are used to arrange the multiple temperature feature vectors in a two-dimensional manner to obtain a global temperature feature matrix, and to pass the global temperature feature matrix and the spatial topology feature matrix through a graph neural network model to obtain a topological global temperature feature matrix. In particular, in the technical solution of this application, the temperature feature vectors of each component of the bucket wheel excavator are represented by high-dimensional features relative to nodes, while the spatial topology feature matrix is ​​used to represent the high-dimensional feature representation of the edges between nodes. That is, the spatial topology feature matrix and the multiple temperature feature vectors form high-dimensional graph data. Based on this, in the technical solution of this application, a graph neural network model is used to encode the high-dimensional graph data formed by the spatial topology feature matrix and the multiple temperature feature vectors to obtain a feature distribution containing irregular spatial topology features and high-dimensional temperature distribution temporal features. Specifically, the multiple temperature feature vectors are first arranged in a two-dimensional manner to obtain a global temperature feature matrix. Then, the global temperature feature matrix and the spatial topology feature matrix are processed by a graph neural network model to obtain a topological global temperature feature matrix. The graph neural network model encodes the global temperature feature matrix and the spatial topology feature matrix with learnable neural network parameters to obtain the topological global temperature feature matrix containing irregular spatial topology features and high-dimensional temperature distribution temporal features.

[0073] Specifically, during the operation of the equipment protection system 300 for the bucket wheel excavator, the feature distribution enhancement module 370 is used to enhance the consistency of feature distribution between vectors in the topological global temperature feature matrix to obtain optimized classification feature vectors. In particular, in the technical solution of this application, when obtaining the topological global temperature feature matrix by passing the global temperature feature matrix and the spatial topological feature matrix through a graph neural network model, each topological global temperature feature vector of the topological global temperature feature matrix, for example, a row vector expressing the correlation features of the temperature time series distribution of a single component under the spatial topology of multiple components, will have inconsistent feature distributions. This results in a special cross-vector anomaly distribution in the topological global temperature feature matrix obtained by directly arranging the various topological global temperature feature vectors. When classifying using a classifier, the dependency on a single classification result is poor, affecting the accuracy of the classification result. Therefore, the classification feature vector obtained after expanding the topological global temperature feature matrix is ​​subjected to Hilbert probability space normalization, specifically expressed as:

[0074]

[0075] Where V is the classification feature vector, and ||V||² represents the L2 norm of the classification feature vector. v represents the squared 2-norm of the classification feature vector, i.e., the inner product of the classification feature vector itself. i It is the i-th feature value of the classification feature vector, exp(·) represents the vector exponentiation operation, which means calculating the natural exponent function value raised to the power of each feature value in the vector, and v i ' is the i-th eigenvalue of the optimized classification feature vector. Here, the normed Hilbert probability spaceization of the vector is used to perform a probabilistic interpretation of the classification feature vector V in a Hilbert space defined by the norming of the classification feature vector V itself. This reduces the hidden perturbation of the class representation of the special local distribution of the classification feature vector V to the class representation of the overall Hilbert space topology, thereby improving the robustness of the feature distribution of the classification feature vector V converging to the classification regression with a predetermined classification probability. At the same time, the establishment of the metric-induced probability space structure enhances the long-range dependence of the feature distribution of the classification feature vector V on the classification result across classifiers. Thus, directly classifying the optimized classification feature vector V' through the classifier improves the dependence of the topological global temperature feature matrix on the classification result when classified by the classifier, thereby improving the accuracy of the classification result.

[0076] Specifically, during the operation of the equipment protection system 300 for the bucket wheel excavator, the protection result generation module 380 is used to pass the optimized classification feature vector through a classifier to obtain a classification result, which indicates whether an over-temperature protection alert is issued. That is, the optimized classification feature vector is passed through a classifier to obtain a classification result, which indicates whether an over-temperature protection alert is issued. In a specific example of this application, passing the optimized classification feature vector through a classifier to obtain a classification result includes: processing the optimized classification feature vector using the classifier with the following formula to obtain a classification result, wherein the formula is:

[0077] O = softmax{(W n B n ):…:(W1,B1)|X}, where W1 to W n The weight matrix is ​​B1 to B1. nLet X be the bias vector and X be the optimized classification feature vector. Specifically, the classifier includes multiple fully connected layers and a Softmax layer cascaded with the last fully connected layer of the multiple fully connected layers. In the classification process of the classifier, the optimized classification feature vector is fully encoded multiple times using the multiple fully connected layers of the classifier to obtain an encoded classification feature vector. Then, the encoded classification feature vector is input into the Softmax layer of the classifier, that is, the Softmax classification function is used to classify the encoded classification feature vector to obtain a first probability value indicating that an over-temperature protection alert will be issued at the current time point and a second probability value indicating that an over-temperature protection alert will not be issued at the current time point. Subsequently, the label corresponding to the larger of the first probability value and the second probability value is determined as the classification result. That is, after obtaining the global temperature distribution features of the bucket wheel excavator, the classifier is used to classify and judge the global temperature distribution features to obtain the classification result indicating whether an over-temperature protection alert will be issued.

[0078] Figure 6 This is a block diagram of a protection result generation module in a device protection system for a bucket wheel excavator according to an embodiment of this application. Figure 6 As shown, the protection result generation module 380 includes: a fully connected encoding unit 381, used to perform fully connected encoding on the optimized classification feature vector using multiple fully connected layers of the classifier to obtain an encoded classification feature vector; and a classification result generation unit 382, ​​used to pass the encoded classification feature vector through the Softmax classification function of the classifier to obtain the classification result.

[0079] In summary, the equipment protection system 300 for a bucket wheel excavator according to the embodiments of this application is explained. It adopts a deep learning-based neural network model to monitor the temperature of multiple components of the bucket wheel excavator and constructs a spatial topology matrix between the multiple components to represent the thermal influence between each component. This more accurately and reasonably represents the temperature distribution characteristics of the bucket wheel excavator. Furthermore, based on the temperature distribution characteristics, it determines whether an over-temperature protection alert is generated. In this way, the coordination between multiple components in the equipment can be taken into account, thereby improving the intelligence and rationality of the equipment over-temperature protection.

[0080] As described above, the equipment protection system for bucket wheel excavators according to embodiments of this application can be implemented in various terminal devices. In one example, the equipment protection system 300 for bucket wheel excavators according to embodiments of this application can be integrated into a terminal device as a software module and / or a hardware module. For example, the equipment protection system 300 for bucket wheel excavators 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 equipment protection system 300 for bucket wheel excavators can also be one of many hardware modules of the terminal device.

[0081] Alternatively, in another example, the equipment protection system 300 for the bucket wheel excavator and the terminal device can also be separate devices, and the equipment protection system 300 for the bucket wheel excavator can be connected to the terminal device via wired and / or wireless networks, and transmit interactive information in accordance with an agreed data format.

[0082] Exemplary methods

[0083] Figure 7 This is a flowchart of a device protection method for a bucket wheel excavator according to an embodiment of this application. Figure 7 As shown, the equipment protection method for a bucket wheel excavator according to an embodiment of this application includes the following steps: S110, acquiring temperature values ​​of multiple components of the bucket wheel excavator at multiple predetermined time points within a predetermined time period; S120, arranging the temperature values ​​of each component at multiple predetermined time points within the predetermined time period into temperature input vectors according to the time dimension, and then obtaining multiple temperature feature vectors by using a first convolutional neural network model with a one-dimensional convolutional kernel; S130, constructing a spatial topology matrix between the multiple components, wherein the value at each position on the non-diagonal side of the spatial topology matrix is ​​the distance between the corresponding two components; S140, converting the spatial topology matrix into a single-dimensional convolutional neural network model; The system obtains a spatial topological feature matrix by using a second convolutional neural network model as a feature extractor; S150, the multiple temperature feature vectors are arranged in two dimensions to obtain a global temperature feature matrix; S160, the global temperature feature matrix and the spatial topological feature matrix are processed by a graph neural network model to obtain a topological global temperature feature matrix; S170, the topological global temperature feature matrix is ​​enhanced with vector feature distribution consistency enhancement to obtain an optimized classification feature vector; and S180, the optimized classification feature vector is processed by a classifier to obtain a classification result, which is used to indicate whether an over-temperature protection reminder is issued.

[0084] In one example, in the above-described equipment protection method for bucket wheel excavators, step S120 includes: using each layer of the first convolutional neural network model using one-dimensional convolutional kernels to perform the following on the input data during the forward propagation of the layers: performing convolution processing on the input data to obtain a convolutional feature map; performing pooling based on the feature matrix on the convolutional feature map to obtain a pooled feature map; and performing nonlinear activation on the pooled feature map to obtain an activation feature map; wherein the output of the last layer of the first convolutional neural network using one-dimensional convolutional kernels is the temperature feature vector, and the input of the first layer of the first convolutional neural network using one-dimensional convolutional kernels is the temperature input vector.

[0085] In one example, in the above-described equipment protection method for bucket wheel excavators, step S140 includes: using each layer of the second convolutional neural network model, which serves as a feature extractor, to process the input data in the forward pass of the layer as follows: performing convolution processing on the input data to obtain a convolutional feature map; performing pooling along the channel dimension on the convolutional feature map to obtain a pooled feature map; and performing nonlinear activation on the pooled feature map to obtain an activation feature map; wherein the output of the last layer of the second convolutional neural network serving as a feature extractor is the spatial topology feature matrix, and the input of the first layer of the second convolutional neural network serving as a feature extractor is the spatial topology matrix. The second convolutional neural network model serving as a feature extractor is a deep residual network model.

[0086] In one example, in the above-described equipment protection method for bucket wheel excavators, step S160 includes: using the graph neural network model to encode the global temperature feature matrix and the spatial topology feature matrix with learnable neural network parameters to obtain the topological global temperature feature matrix containing irregular spatial topology features and high-dimensional temperature distribution temporal features.

[0087] In one example, in the above-described equipment protection method for bucket wheel excavators, step S170 includes: performing vector norming Hilbert probability spaceization on the classification feature vector using the following formula to obtain the optimized classification feature vector; wherein, the formula is:

[0088]

[0089] Where V is the classification feature vector, and ||V||² represents the L2 norm of the classification feature vector. v represents the squared 2-norm of the classification feature vector, i.e., the inner product of the classification feature vector itself. iIt is the i-th feature value of the classification feature vector, exp(·) represents the vector exponentiation operation, which means calculating the natural exponent function value raised to the power of each feature value in the vector, and v i ′ is the i-th feature value of the optimized classification feature vector.

[0090] In one example, in the above-described equipment protection method for bucket wheel excavators, step S180 includes: using multiple fully connected layers of the classifier to perform fully connected encoding on the optimized classification feature vector to obtain an encoded classification feature vector; and passing the encoded classification feature vector through the Softmax classification function of the classifier to obtain the classification result.

[0091] In summary, the equipment protection method for a bucket wheel excavator according to the embodiments of this application is explained. It employs a deep learning-based neural network model to monitor the temperature of multiple components of the bucket wheel excavator and constructs a spatial topology matrix between the multiple components to represent the thermal influence between each component. This more accurately and reasonably represents the temperature distribution characteristics of the bucket wheel excavator. Furthermore, based on the temperature distribution characteristics, it determines whether an over-temperature protection alert is generated. In this way, the coordination between multiple components in the equipment can be taken into account, thereby improving the intelligence and rationality of the equipment over-temperature protection.

[0092] Exemplary electronic devices

[0093] Below, for reference Figure 8 This describes an electronic device according to embodiments of the present application.

[0094] Figure 8 A block diagram of an electronic device according to an embodiment of this application is illustrated.

[0095] like Figure 8 As shown, the electronic device 10 includes one or more processors 11 and memory 12.

[0096] 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.

[0097] 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 of the parking space-level dynamic shared intelligent management and control system of the various embodiments of this application described above, and / or other desired functions. Various contents, such as optimized classification feature vectors, may also be stored in the computer-readable storage medium.

[0098] 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).

[0099] The input device 13 may include, for example, a keyboard, a mouse, etc.

[0100] The output device 14 can output various information to the outside, including classification results. 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.

[0101] 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.

[0102] Exemplary computer program products and computer-readable storage media

[0103] In addition to the methods and devices described above, embodiments of this application may also be computer program products, which include computer program instructions that, when executed by a processor, cause the processor to perform the steps of the functions in the device protection method for a bucket wheel excavator according to various embodiments of this application as described in the "Exemplary Systems" section above.

[0104] The computer program product can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computing device, partially on the user's computing device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0105] Furthermore, embodiments of this application may also be computer-readable storage media storing computer program instructions that, when executed by a processor, cause the processor to perform steps of the functions in the device protection method for a bucket wheel excavator according to various embodiments of this application as described in the "Exemplary System" section above.

[0106] The computer-readable storage medium may be any combination of one or more readable media. A readable medium may be a readable signal medium or a readable storage medium. A readable storage medium may, for example, include, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or devices, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: electrical connections having one or more wires, portable disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0107] The basic principles of this application have been described above with reference to specific embodiments. However, it should be noted that the advantages, benefits, and effects mentioned in this application are merely examples and not limitations, and should not be considered as essential features of each embodiment of this application. Furthermore, the specific details disclosed above are for illustrative and facilitative purposes only, and are not limitations. These details do not limit the application to the necessity of employing the aforementioned specific details for implementation.

[0108] The block diagrams of devices, apparatuses, devices, and systems involved in this application are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, or configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, devices, and systems can be connected, arranged, and configured in any manner. Words such as “comprising,” “including,” “having,” etc., are open-ended terms meaning “including but not limited to,” and are used interchangeably with them. The terms “or” and “and” as used herein refer to the terms “and / or,” and are used interchangeably with them unless the context clearly indicates otherwise. The term “such as” as used herein refers to the phrase “such as but not limited to,” and is used interchangeably with it.

[0109] It should also be noted that in the apparatus, equipment, and methods of this application, the components or steps can be disassembled and / or recombined. These disassemblies and / or recombinations should be considered as equivalent solutions of this application.

[0110] The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use this application. Various modifications to these aspects will be readily apparent to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of this application. Therefore, this application is not intended to be limited to the aspects shown herein, but rather to be accorded the widest scope consistent with the principles and novel features disclosed herein.

[0111] The above description has been given for purposes of illustration and description. Furthermore, this description is not intended to limit the embodiments of this application to the forms disclosed herein. Although numerous exemplary aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, alterations, additions, and sub-combinations thereof.

Claims

1. A device protection system for a bucket wheel excavator, characterized in that, include: The temperature monitoring module is used to acquire the temperature values ​​of multiple components of the bucket wheel excavator at multiple predetermined time points within a predetermined time period. The temperature time series feature extraction module is used to arrange the temperature values ​​of each component at multiple predetermined time points within a predetermined time period into temperature input vectors according to the time dimension, and then use a first convolutional neural network model with a one-dimensional convolutional kernel to obtain multiple temperature feature vectors. A spatial topology construction module is used to construct a spatial topology matrix between the multiple components, wherein the values ​​at each position on the non-diagonal side of the spatial topology matrix are the distances between the corresponding two components. A spatial topology feature extraction module is used to pass the spatial topology matrix through a second convolutional neural network model, which acts as a feature extractor, to obtain a spatial topology feature matrix. A globalization module is used to arrange the multiple temperature feature vectors in a two-dimensional manner to obtain a global temperature feature matrix. The graph feature extraction module is used to encode the global temperature feature matrix and the spatial topology feature matrix with learnable neural network parameters using a graph neural network model to obtain a topological global temperature feature matrix containing irregular spatial topology features and high-dimensional temperature distribution temporal features. The feature distribution enhancement module is used to enhance the consistency of feature distribution between vectors of the topological global temperature feature matrix to obtain an optimized classification feature vector. Specifically, the classification feature vector after the topological global temperature feature matrix is ​​expanded is subjected to Hilbert probability spacer with vector norming using the following formula to obtain the optimized classification feature vector. The formula is as follows: Where V is the classification feature vector, and ||V||2 represents the L2 norm of the classification feature vector. v represents the squared 2-norm of the classification feature vector, i.e., the inner product of the classification feature vector itself. i It is the i-th feature value of the classification feature vector, exp(·) represents the vector exponentiation operation, which means calculating the natural exponent function value raised to the power of each feature value in the vector, and v i ' is the i-th feature value of the optimized classification feature vector; The protection result generation module is used to pass the optimized classification feature vector through a classifier to obtain a classification result, which is used to indicate whether an over-temperature protection reminder is issued.

2. The equipment protection system for a bucket wheel excavator according to claim 1, characterized in that, The temperature time-series feature extraction module is further configured to: use each layer of the first convolutional neural network model using one-dimensional convolutional kernels to process the input data during the forward propagation of the layers: The input data is processed by convolution to obtain a convolutional feature map; The convolutional feature map is pooled based on the feature matrix to obtain a pooled feature map; as well as The pooled feature map is nonlinearly activated to obtain an activated feature map; Wherein, the output of the last layer of the first convolutional neural network using a one-dimensional convolutional kernel is the temperature feature vector, and the input of the first layer of the first convolutional neural network using a one-dimensional convolutional kernel is the temperature input vector.

3. The equipment protection system for a bucket wheel excavator according to claim 2, characterized in that, The spatial topology feature extraction module is further configured to: use each layer of the second 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; Wherein, the output of the last layer of the second convolutional neural network, which serves as the feature extractor, is the spatial topological feature matrix, and the input of the first layer of the second convolutional neural network, which serves as the feature extractor, is the spatial topological matrix.

4. The equipment protection system for a bucket wheel excavator according to claim 3, characterized in that, The second convolutional neural network model used as the feature extractor is a deep residual network model.

5. The equipment protection system for a bucket wheel excavator according to claim 4, characterized in that, The protection result generation module includes: A fully connected encoding unit is configured to perform fully connected encoding on the optimized classification feature vector using multiple fully connected layers of the classifier to obtain an encoded classification feature vector; and The classification result generation unit is used to pass the encoded classification feature vector through the Softmax classification function of the classifier to obtain the classification result.

6. A method for protecting equipment used in bucket wheel excavators, characterized in that, include: The temperature values ​​of multiple components of the bucket wheel excavator at multiple predetermined time points within a predetermined time period are obtained. The temperature values ​​of each component at multiple predetermined time points within a predetermined time period are arranged into temperature input vectors according to the time dimension, and then multiple temperature feature vectors are obtained by using a first convolutional neural network model with a one-dimensional convolutional kernel. Construct a spatial topology matrix between the multiple components, wherein the values ​​at each off-diagonal position in the spatial topology matrix are the distances between the corresponding two components; The spatial topology matrix is ​​passed through a second convolutional neural network model, which acts as a feature extractor, to obtain a spatial topology feature matrix. The multiple temperature feature vectors are arranged in a two-dimensional manner to obtain a global temperature feature matrix; The global temperature feature matrix and the spatial topology feature matrix are encoded with learnable neural network parameters using a graph neural network model to obtain a topological global temperature feature matrix containing irregular spatial topology features and high-dimensional temperature distribution temporal features. The topological global temperature feature matrix is ​​enhanced with vector feature distribution consistency enhancement to obtain optimized classification feature vectors. Specifically, the classification feature vectors after the topological global temperature feature matrix is ​​expanded are subjected to Hilbert probability spacerization with vector norming using the following formula to obtain the optimized classification feature vectors. The formula is as follows: Where V is the classification feature vector, and ||V||2 represents the L2 norm of the classification feature vector. v represents the squared 2-norm of the classification feature vector, i.e., the inner product of the classification feature vector itself. i It is the i-th feature value of the classification feature vector, exp(·) represents the vector exponentiation operation, which means calculating the natural exponent function value raised to the power of each feature value in the vector, and v i ' is the i-th feature value of the optimized classification feature vector; The optimized classification feature vector is passed through a classifier to obtain a classification result, which is used to indicate whether an over-temperature protection alert is issued.

7. The equipment protection method for a bucket wheel excavator according to claim 6, characterized in that, The optimized classification feature vector is passed through a classifier to obtain a classification result, which is used to indicate whether an over-temperature protection alert is issued, including: The optimized classification feature vector is fully encoded using multiple fully connected layers of the classifier to obtain the encoded classification feature vector; and The encoded classification feature vector is passed through the Softmax classification function of the classifier to obtain the classification result.

Images