CN117424513A - Control method and system for realizing constant current control based on belt flow and wheel bucket current - Google Patents

Abstract

The invention provides a control method and a control system for realizing constant current control based on belt flow and wheel bucket current. The method comprises the following steps: s1, acquiring belt coal flow values at a plurality of preset time points in a preset time period and driving motor current values at the preset time points; s2, arranging a belt coal flow time sequence input vector and a driving motor current time sequence input vector according to a time dimension; s3, analyzing to obtain a sequence of local time sequence feature vectors of the belt coal flow and a sequence of local time sequence feature vectors of the driving motor current; s4, obtaining the belt coal flow-driving motor current time sequence interaction fusion characteristic; s5, based on the belt coal flow-driving motor current time sequence interaction fusion characteristic, determining that the current value of the driving motor at the current time point should be increased, kept or decreased.

Description

Control method and system for constant current control based on belt flow and bucket current

Technical field

This application relates to the field of intelligent control, specifically to a control method for realizing constant current control based on belt flow and wheel bucket current. The invention also discloses a control system for realizing constant current control based on belt flow and wheel bucket current.

Background technique

Bucket wheel machine is an important equipment used for coal mining and transportation. It consists of a large wheel bucket and a cantilever belt, and can carry out coal picking and unloading operations at different locations. The operating efficiency and safety of the bucket wheel machine are closely related to the control of its coal flow. Therefore, an accurate, stable and reliable coal flow measurement and control method is needed.

At present, the commonly used coal flow measurement methods include electronic belt weighing method and laser scanning method, but both methods have certain defects and shortcomings. Specifically, the electronic belt weighing method completes coal flow monitoring and control by installing an electronic belt scale on the cantilever belt of the bucket wheel machine. However, due to the continuous changes in the pitch angle of the cantilever belt and the lack of correction methods, the belt scale has problems in actual use during actual use. The accuracy of the middle belt scale is extremely poor and cannot be used as measurement data for bucket wheel machine coal flow control. The laser scanning method is to install a laser scanner above the cantilever belt, use the method of scanning the surface shape of the coal flow to calculate the volume, plus estimate the density, and convert it into a flow rate. The advantage of this method is that there is less error drift, it is relatively stable, and it does not require frequent correction. Its disadvantage is that the density of coal requires manual experience and the efficiency is low; secondly, the serious deviation of the cantilever belt will affect the calculation accuracy of the coal flow cross-sectional area. An effective correction device needs to be installed. Therefore, an optimized constant flow control scheme for coal flow is desired.

Contents of the invention

In order to solve the above technical problems, this application is proposed, which can improve the intelligent operation level of the bucket wheel machine, achieve precise control of coal flow, prevent belt overload, and meet the requirements of coal blending ratio. A control method that realizes constant current control based on belt flow and wheel bucket current. It realizes constant current control of coal flow by introducing the driving motor current parameters of the wheel bucket and belt coal flow data. Specifically, the belt coal flow value and drive motor current value are collected through real-time monitoring, and data processing and analysis algorithms are introduced at the back end to perform timing collaborative analysis of the belt coal flow and drive motor current, thereby utilizing the belt flow and drive motor current values. The relationship between the currents is used to realize real-time intelligent adjustment of the drive motor current to achieve the purpose of constant current control.

A control method for realizing constant current control based on belt flow and bucket current, characterized in that it includes the following steps:

S1. Obtain belt coal flow values at multiple predetermined time points within a predetermined time period and drive motor current values at the multiple predetermined time points;

S2. Arrange the belt coal flow values at multiple predetermined time points and the driving motor current values at the multiple predetermined time points into a belt coal flow timing input vector and a driving motor current timing input vector respectively according to the time dimension;

S3. Perform local timing analysis on the belt coal flow timing input vector and the driving motor current timing input vector respectively to obtain the sequence of the belt coal flow local timing feature vector and the driving motor current local timing feature vector sequence;

S4. Perform feature sequence interactive fusion on the sequence of the local timing feature vectors of the belt coal flow and the sequence of the local timing feature vectors of the drive motor current to obtain the belt coal flow-drive motor current timing interactive fusion characteristics;

S5. Based on the belt coal flow-drive motor current timing interaction fusion characteristics, determine whether the current value of the drive motor at the current time point should be increased, maintained, or reduced.

A control system that realizes constant current control based on belt flow and wheel bucket current, which includes:

A data acquisition module, used to acquire belt coal flow values at multiple predetermined time points within a predetermined time period and drive motor current values at the multiple predetermined time points;

An arrangement module, configured to arrange the belt coal flow values at the plurality of predetermined time points and the driving motor current values at the plurality of predetermined time points into a belt coal flow timing input vector and a driving motor current timing input vector according to the time dimension. ;

A local timing analysis module, configured to perform local timing analysis on the belt coal flow timing input vector and the drive motor current timing input vector respectively to obtain the sequence of the belt coal flow local timing feature vector and the drive motor current local timing feature. sequence of vectors;

A feature sequence interactive fusion module is used to perform feature sequence interactive fusion on the sequence of the local timing feature vectors of the belt coal flow and the sequence of the local timing feature vectors of the drive motor current to obtain the belt coal flow-drive motor current timing interactive fusion features. ;as well as

The current value control result generation module is used to determine whether the current value of the drive motor at the current time point should be increased, maintained or reduced based on the belt coal flow-drive motor current timing interaction fusion characteristics.

Compared with the existing technology, this application provides a control method and system for realizing constant current control based on belt flow and wheel bucket current, which realizes coal control by introducing the driving motor current parameters of the wheel bucket and the belt coal flow data. Constant flow control of flow rate. Specifically, the belt coal flow value and drive motor current value are collected through real-time monitoring, and data processing and analysis algorithms are introduced at the back end to perform timing collaborative analysis of the belt coal flow and drive motor current, thereby utilizing the belt flow and drive motor current values. The relationship between the currents is used to realize real-time intelligent adjustment of the drive motor current to achieve the purpose of constant current control. In this way, the intelligent operation level of the bucket wheel machine can be improved, precise control of coal flow can be achieved, belt overload can be prevented, and coal blending ratio requirements can be met.

Description of the drawings

The above and other objects, features and advantages of the present application will become more apparent through a more detailed description of the embodiments of the present application in conjunction with the accompanying drawings. The drawings are used to provide further understanding of the embodiments of the present application, and constitute a part of the specification. They are used to explain the present application together with the embodiments of the present application, and do not constitute a limitation of the present application. In the drawings, like reference numbers generally represent like components or steps.

Figure 1 is a flow chart of a control method for realizing constant current control based on belt flow and wheel bucket current according to an embodiment of the present application;

Figure 2 is a system architecture diagram of a control method for realizing constant current control based on belt flow and wheel bucket current according to an embodiment of the present application;

Figure 3 is a flow chart of sub-step S3 of the control method for realizing constant current control based on belt flow and wheel bucket current according to an embodiment of the present application;

Figure 4 is a flow chart of sub-step S5 of the control method for realizing constant current control based on belt flow and wheel bucket current according to an embodiment of the present application;

Figure 5 is a flow chart of sub-step S51 of the control method for realizing constant current control based on belt flow and wheel bucket current according to an embodiment of the present application;

Figure 6 is a block diagram of a control system that implements constant current control based on belt flow and bucket current according to an embodiment of the present application.

Detailed ways

Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described here.

As shown in this application and claims, words such as "a", "an", "an" and/or "the" do not specifically refer to the singular and may include the plural unless the context clearly indicates an exception. Generally speaking, the terms "comprising" and "comprising" only imply the inclusion of clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or apparatus may also include other steps or elements.

Although this application makes various references to certain modules in systems according to embodiments of the application, any number of different modules may be used and run on user terminals and/or servers. The modules are illustrative only, and different modules may be used with different aspects of the system and methods.

Flowcharts are used in this application to illustrate operations performed by systems according to embodiments of this application. It should be understood that the preceding or following operations are not necessarily performed in exact order. Instead, the various steps can be processed in reverse order or simultaneously, as appropriate. At the same time, you can add other operations to these processes, or remove a step or steps from these processes.

Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the example embodiments described here.

Commonly used coal flow measurement methods include electronic belt weighing method and laser scanning method, but both methods have certain flaws and shortcomings. Specifically, the electronic belt weighing method completes coal flow monitoring and control by installing an electronic belt scale on the cantilever belt of the bucket wheel machine. However, due to the continuous changes in the pitch angle of the cantilever belt and the lack of correction methods, the belt scale has problems in actual use during actual use. The accuracy of the middle belt scale is extremely poor and cannot be used as measurement data for bucket wheel machine coal flow control. The laser scanning method is to install a laser scanner above the cantilever belt, use the method of scanning the surface shape of the coal flow to calculate the volume, plus estimate the density, and convert it into a flow rate. The advantage of this method is that there is less error drift, it is relatively stable, and it does not require frequent correction. Its disadvantage is that the density of coal requires manual experience and the efficiency is low; secondly, the serious deviation of the cantilever belt will affect the calculation accuracy of the coal flow cross-sectional area. An effective correction device needs to be installed. Therefore, an optimized constant flow control scheme for coal flow is desired.

A control method for realizing constant current control based on belt flow and wheel bucket current, as shown in Figure 1 and Figure 2. According to the embodiment of the present application, the control method for realizing constant current control based on belt flow and wheel bucket current includes the following step:

S1, obtain the belt coal flow values at multiple predetermined time points and the drive motor current values at multiple predetermined time points within a predetermined time period;

S2, arrange the belt coal flow values at multiple predetermined time points and the driving motor current values at multiple predetermined time points into a belt coal flow timing input vector and a driving motor current timing input vector according to the time dimension;

S3: Perform local timing analysis on the belt coal flow timing input vector and the driving motor current timing input vector to obtain the sequence of the belt coal flow local timing feature vector and the driving motor current local timing feature vector sequence;

S4. Perform feature sequence interactive fusion on the sequence of the belt coal flow local timing feature vector and the sequence of the drive motor current local timing feature vector to obtain the belt coal flow-drive motor current timing interactive fusion characteristics;

S5, based on the belt coal flow-drive motor current timing interaction fusion characteristics, determine whether the current value of the drive motor at the current time point should be increased, maintained or reduced.

In S1, the belt coal flow rate refers to the flow rate of coal transported by the belt conveyor in the coal mine or coal processing process. It is one of the important indicators to measure coal transportation efficiency and production capacity; the drive motor current value refers to the drive motor current value when the drive motor is running. The current consumed in the process is one of the important indicators to measure the load and working status of the drive motor. In one example, the coal flow sensor can be used to obtain the belt coal flow value at multiple predetermined time points within a predetermined time period; and the current sensor can be used to obtain the driving motor current value at multiple predetermined time points.

It is worth noting that the coal flow sensor is a sensor device used to measure coal flow. It is usually installed on the pipeline or conveyor belt in the coal transportation system and is used to monitor and measure the coal flow through the pipeline or conveyor belt in real time. A current sensor is a sensor device used to measure the magnitude of electrical current. It is usually used to monitor and measure the current in the circuit to obtain the current value in real time and perform corresponding control and analysis.

S2, arrange the belt coal flow values at multiple predetermined time points and the driving motor current values at multiple predetermined time points into a belt coal flow timing input vector and a driving motor current timing input vector respectively according to the time dimension. Considering that the belt coal flow value and the drive motor current value will change with time in the time dimension, that is to say, the belt coal flow rate and the drive motor current have implicit timing changes in timing, and , in order to perform real-time adaptive control of the current of the driving motor, it is necessary to focus on the time-series collaborative correlation feature distribution information of the belt coal flow value and the driving motor current value. Based on this, in the technical solution of this application, it is necessary to first arrange the belt coal flow values at multiple predetermined time points and the driving motor current values at multiple predetermined time points into the belt coal flow timing input vector and the driving motor respectively according to the time dimension. The current time series input vector is used to integrate the time series distribution information of the belt coal flow value and the drive motor current value respectively.

Step S3 includes the following steps:

S31, perform vector segmentation on the belt coal flow time series input vector and the drive motor current time series input vector respectively to obtain the sequence of the belt coal flow local time series input vector and the drive motor current local time series input vector sequence;

S32, use the temporal feature extractor based on the deep neural network model to perform feature extraction on the sequence of the local timing input vector of the belt coal flow and the sequence of the local timing input vector of the drive motor current to obtain the sequence and drive of the local timing feature vector of the belt coal flow. A sequence of local timing eigenvectors of the motor current.

Considering that in the actual monitoring and constant current control process of belt coal flow data and drive motor current data, the belt coal flow rate and drive motor current are continuous signals that change with time, and they show various temporal changes in the time dimension. patterns and various temporal trends. Therefore, in order to more fully analyze the timing changes of the belt coal flow value and the drive motor current value, in order to capture more fine-grained information and timing characteristics in the timing data, in order to perform constant current control more accurately , in the technical solution of this application, the vectors of the belt coal flow timing input vector and the driving motor current timing input vector are further divided to obtain the sequence of the belt coal flow local timing input vector and the driving motor current local timing input vector. sequence.

Specifically, during the operation of step S32, the belt coal flow value and the driving motor current value will show a certain change pattern in each local time sequence. In order to be able to change the belt coal flow value and the driving motor current value in time Each local timing feature in the dimension is effectively captured and characterized. In the technical solution of this application, the sequence of the belt coal flow local timing input vector and the sequence of the drive motor current local timing input vector are respectively passed through based on one-dimensional convolution. Feature mining is performed in the temporal feature extractor of the layer to extract the local temporal feature information of the belt coal flow value and the driving motor current value in the time dimension, thereby obtaining the sequence of the belt coal flow local timing feature vector and the driving motor current. A sequence of local temporal feature vectors. More specifically, each layer using a temporal feature extractor based on one-dimensional convolutional layers performs a convolution process on the input data in the forward pass of the layer to obtain a convolutional feature map; The map is pooled based on the feature matrix to obtain the pooled feature map; and, non-linear activation is performed on the pooled feature map to obtain the activation feature map; where, the last layer of the temporal feature extractor based on the one-dimensional convolution layer The output is the sequence of the local timing feature vectors of the belt coal flow and the sequence of the local timing feature vectors of the drive motor current. The input of the first layer of the timing feature extractor based on the one-dimensional convolution layer is the sequence sum of the local timing input vectors of the belt coal flow. A sequence of local timing input vectors that drive the motor current.

It is worth mentioning that the one-dimensional convolutional layer is a type of convolutional neural network layer commonly used in deep learning and is used to process sequence data. Different from the two-dimensional convolution layer, the one-dimensional convolution layer performs a sliding window convolution operation in one dimension and is usually used to process data with sequential structure such as time series and text. The input of a one-dimensional convolutional layer is a one-dimensional tensor, such as time series data. It extracts features of input data by defining a set of convolution kernels (or filters). Each convolution kernel is a small one-dimensional weight vector, which performs an element-by-element product and sum operation with the input data to obtain an element of the output feature map. In a one-dimensional convolution layer, the convolution kernel slides on the input data, and the size of the output feature map can be adjusted by changing the sliding stride and filling method. The convolution operation can capture the local patterns and features of the input data, and through the parallel operation of multiple convolution kernels, multiple different features can be extracted. One-dimensional convolutional layers are often used in combination with other types of layers, such as pooling layers and fully connected layers. The pooling layer can further reduce the dimension of the feature map and extract more abstract features. The fully connected layer is used to map the output of the convolutional layer to the final prediction or classification result.

It is worth mentioning that in other specific examples of this application, local timing analysis can be performed on the belt coal flow timing input vector and the drive motor current timing input vector in other ways to obtain the belt coal flow local timing feature vector. The sequence and the sequence of the local timing feature vectors of the drive motor current, for example: determine the window size and step size of the local timing analysis; the window size represents the number of time steps included in each local timing feature vector, and the step size represents the interval between windows; Perform local timing analysis on the belt coal flow timing input vector and the drive motor current timing input vector, for example: starting from the starting position of the time series, select consecutive windows at step intervals; within each window, extract the belt Characteristics of the corresponding time steps in the coal flow time series input vector and the drive motor current time series input vector; combine the extracted features into a local time series feature vector; repeat the above steps until the entire time series is covered to obtain the local time series feature vector of the belt coal flow The sequence of and the sequence of local timing eigenvectors of the drive motor current.

Step S4, considering that the belt coal flow and the drive motor current are closely related, there is an implicit timing relationship between them, and there are differences between the belt coal flow and the drive motor current in each local time period. The timing correlation characteristics of these local timing correlation characteristics of the belt coal flow and the driving motor current are of great significance for the real-time control of the driving motor current and the constant current control of the coal flow. Therefore, in the technical solution of this application, the sequence of the local timing feature vectors of the belt coal flow and the sequence of the local timing feature vectors of the drive motor current are further processed through the feature sequence interactive fusion module, so as to capture each local part of the belt coal flow. The correlation and mutual influence between the timing characteristics and the corresponding local timing characteristics of the drive motor current are used to obtain the belt coal flow-drive motor current timing interaction fusion feature vector. It should be understood that the feature sequence interactive fusion module can separately weight the local timing feature vectors of the belt coal flow and the local timing feature vectors of each drive motor current by calculating attention weights to model the importance between different feature sequences. . Specifically, the module can assign a weight to each feature sequence based on the similarity and correlation between the sequence of the belt coal flow local timing feature vector and the sequence of the drive motor current local timing feature vector through the feature sequences. Therefore, after interactive fusion processing of attention features, the sequence of local timing feature vectors of belt coal flow and the sequence of local timing feature vectors of driving motor current can interact and complement each other through the corresponding local timing feature vectors in the feature sequence, so as to achieve better results. In order to fully capture the interactive and collaborative feature distribution information about the belt coal flow and the drive motor current in each local time series, the belt coal flow-drive motor current time series interactive fusion feature vector is obtained. Specifically, the sequence of the belt coal flow local timing feature vector and the sequence of the drive motor current local timing feature vector are passed through the feature sequence interactive fusion module to obtain the belt coal flow-drive motor current timing interactive fusion feature vector as the belt coal flow-drive motor Current timing interactive fusion features include: calculating the correlation between any two feature vectors in the sequence of belt coal flow local timing feature vectors and the sequence of drive motor current local timing feature vectors to obtain the belt coal flow-drive motor current local timing sequence A sequence of correlation feature matrices; based on the sequence of belt coal flow-drive motor current local timing correlation feature matrices, feature interactive attention coding is performed on the sequence of belt coal flow local timing feature vectors and the sequence of drive motor current local timing feature vectors to obtain Attention enhances the sequence of local timing feature vectors of belt coal flow and attention enhances the sequence of local timing feature vectors of driving motor current; fuses the sequence of local timing feature vectors of belt coal flow and the sequence of attention enhanced belt coal flow local timing feature vectors The eigenvectors of the corresponding positions are obtained by merging the sequence of local timing eigenvectors of the belt coal flow, and fusing the eigenvectors of the corresponding positions in the sequence of the local timing eigenvectors of the driving motor current and the attention enhancement driving motor current local eigenvectors to obtain The driving motor current fuses the sequence of local timing feature vectors; the belt coal flow fusion local timing feature vector sequence is subjected to maximum pooling processing to obtain the belt coal flow fusion local timing maximum pooling feature vector, and the driving motor current fusion local The sequence of timing feature vectors is subjected to maximum pooling processing to obtain the driving motor current fusion local timing maximum pooling feature vector; and, the belt coal flow fusion local timing maximum pooling feature vector and the driving motor current fusion local timing maximum are The feature vector is pooled to obtain the belt coal flow-drive motor current time series interactive fusion feature vector.

As shown in Figure 4, step S5 includes: S51, performing feature correction on the belt coal flow-drive motor current timing interactive fusion eigenvector to obtain the corrected belt coal flow-drive motor current timing interactive fusion eigenvector; and, S52, The corrected belt coal flow-drive motor current timing interactive fusion feature vector is passed through the classifier to obtain the classification result. The classification result is used to indicate that the current value of the drive motor at the current time point should be increased, maintained or reduced.

S51. Perform feature correction on the belt coal flow-drive motor current timing interactive fusion feature vector to obtain the corrected belt coal flow-drive motor current timing interactive fusion feature vector. In particular, in a specific example of this application, as shown in Figure 5, S51 includes:

S511, cascade the sequence of the local timing feature vectors of the belt coal flow to obtain the full time domain belt coal flow timing feature vector, and cascade the sequence of the local timing feature vectors of the drive motor current to obtain the full time domain drive motor current timing. Feature vector;

S512, perform fusion correction on the full-time domain belt coal flow timing feature vector and the full-time domain drive motor current timing feature vector to obtain a correction feature vector;

And, S513, fuse the corrected feature vector and the belt coal flow-drive motor current timing interactive fusion feature vector to obtain the corrected belt coal flow-drive motor current timing interactive fusion feature vector.

S511, cascade the sequence of the local timing feature vectors of the belt coal flow to obtain the full time domain belt coal flow timing feature vector, and cascade the sequence of the local timing feature vectors of the drive motor current to obtain the full time domain drive motor current timing. Feature vector. It should be understood that cascading can enhance dependency modeling capabilities and support more flexible feature extraction, thereby improving the prediction accuracy and robustness of the drive motor current.

S512: Perform fusion correction on the full-time domain belt coal flow timing feature vector and the full-time domain drive motor current timing feature vector to obtain a correction feature vector. In particular, in the technical solution of the present application, the sequence of the local timing feature vectors of the belt coal flow and the sequence of the local timing feature vectors of the drive motor current are respectively used to express the sequence and drive of the local neighborhood correlation features in the local time domain of the belt coal flow. A sequence of local neighborhood correlation features within the local time domain of the motor current. By using the feature sequence interactive fusion module, bidirectional selective features based on the attention mechanism can be performed based on the correlation between each feature vector in the sequence of the belt coal flow local timing feature vector and the sequence of the drive motor current local timing feature vector. Fusion is used to obtain the belt coal flow-drive motor current time series interactive fusion feature vector, so that the time domain characteristics of the belt flow and drive motor current are interactively fused. However, the applicant of this application considered the difference between the sequence of the local timing feature vector of the belt coal flow and the sequence of the local timing feature vector of the drive motor current. Therefore, the belt coal flow-drive motor current was obtained through the feature sequence interactive fusion module. When time-series interactive fusion eigenvectors are used, it may lead to uneven expression of the belt coal flow-drive motor current time-series interactive fusion eigenvectors, affecting the expression effect of the belt coal flow-drive motor current time series interactive fusion eigenvectors. Based on this, preferably, for the full time domain belt coal flow timing feature vector obtained by the sequence cascade of the belt coal flow local timing feature vector, for example, recorded as V ₁ and obtained by the sequence cascade of the drive motor current local timing feature vector The full-time domain driving motor current timing feature vector, for example, recorded as V ₂ , is fused and corrected to obtain the corrected feature vector, for example, recorded as V _c :

Where V ₁ is the full time domain belt coal flow timing feature vector, V ₂ is the full time domain drive motor current timing feature vector, and/> Respectively represent the reciprocal of the global mean of the full-time domain belt coal flow timing feature vector and the full-time domain drive motor current timing feature vector, and I is the unit vector, ⊙ represents the point multiplication by position,/> means adding by position,/> Represents difference by position, V _c is the correction feature vector. That is to say, if the full-time domain drive motor current timing feature vector V ₂ to be fused is regarded as the strong feature timing enhancement input of the full-time belt coal flow timing feature vector V ₁ , the full-time belt coal flow timing feature vector may be lost. The target distribution information of the target feature of V ₁ in the class space leads to the loss of class regression purpose. Therefore, by cross-penalizing the outlier distribution (outlier distribution) of the feature distribution relative to each other, the feature can be realized during feature interpolation fusion. Robust self-supervised balancing is enhanced and regressed to improve the feature fusion effect of the full-time domain belt coal flow timing feature vector V ₁ and the full-time domain drive motor current timing feature vector V ₂ . In this way, by fusing the correction feature vector _Vc with the belt coal flow-drive motor current timing interactive fusion feature vector, the expression effect of the belt coal flow-drive motor current timing interactive fusion feature vector can be improved to improve the expression obtained through the classifier. the accuracy of the classification results. In this way, real-time intelligent adjustment of the drive motor current can be realized based on the belt flow and wheel bucket current, thereby achieving the purpose of constant current control. In this way, the intelligent operation level of the bucket wheel machine can be improved and accurate control of coal flow can be achieved. , thereby preventing the belt from being overloaded and meeting the requirements for the coal blending ratio.

More specifically, S513, fuse the corrected feature vector and the belt coal flow-drive motor current timing interactive fusion feature vector to obtain the corrected belt coal flow-drive motor current timing interactive fusion feature vector. It should be understood that the correction feature vector may contain correction information related to the drive motor current value, such as a correction factor or a correction deviation. Fusing the correction feature vector with the belt coal flow-drive motor current time series interaction fusion feature vector can enhance the feature representation capability and enable the model to better capture the complex relationship between the drive motor current and the belt coal flow.

It is worth mentioning that in other specific examples of this application, the characteristic vector of the belt coal flow-drive motor current timing interactive fusion can also be corrected in other ways to obtain the corrected belt coal flow-drive motor current timing interactive fusion. Feature vectors, for example: preprocess the original data, including removing outliers, normalization and other operations to ensure the reliability and processability of the data; if the feature vector has a high dimension, you can consider using feature selection methods to select the best Relevant feature subsets to reduce the amount of calculation and reduce the impact of noise; transform feature vectors, such as dimensionality reduction, mapping to new feature spaces, etc., to extract more useful information; select appropriate feature correction methods, common Methods include statistical methods (such as mean correction, standardization), filtering methods (such as median filtering, Gaussian filtering) and machine learning methods (such as autoencoders, generative adversarial networks), etc.; according to the selected feature correction method, the feature vector is Corrective operation.

Specifically, S52, the corrected belt coal flow-driving motor current timing interactive fusion feature vector is passed through the classifier to obtain a classification result. The classification result is used to indicate that the current value of the driving motor at the current time point should be increased, maintained, or should be decrease. That is to say, the interactive correlation and fusion feature information between the local timing characteristics of the belt coal flow and the local timing characteristics of the driving motor current are used for classification processing, and the timing correlation between the belt flow and the driving motor current is used to realize the classification of the driving motor current. Real-time adaptive adjustment to achieve the purpose of constant current control. More specifically, first, multiple fully connected layers of the classifier are used to perform fully connected encoding on the corrected belt coal flow-drive motor current timing interactive fusion feature vector to obtain the encoded classification feature vector; then, the encoded classification feature vector is classified through Softmax classification function of the processor to obtain the classification results.

It is worth mentioning that in other specific examples of this application, it can also be determined in other ways based on the belt coal flow-drive motor current timing interaction fusion characteristics that the current value of the drive motor at the current time point should be increased, maintained, or should be reduced, for example: collect and prepare the time series interactive fusion feature data of the belt coal flow and the drive motor current, including the feature vector of the current time point and the corresponding drive motor current value; extract the time series interaction fusion feature data with the current time point Relevant features; analyze the extracted features and observe the relationship between the features and the drive motor current; select an appropriate modeling method to establish a prediction model based on the results of feature analysis; use historical data to train the model and use verification Verify and tune the model collectively; use the trained model to predict the characteristics of the current time point, and judge the change trend of the drive motor current based on the prediction results; if the predicted value is higher than the current value, it means that the current should increase ; If the predicted value is similar to the current value, it means that the current should be maintained; if the predicted value is lower than the current value, it means that the current should be reduced; according to the judgment result, the control strategy is adjusted to achieve the increase, maintenance or decrease of the current. This may involve adjusting the control parameters of the motor, increasing or decreasing the load, etc.

In summary, according to the embodiment of the present application, the control method for realizing constant current control based on the belt flow rate and the wheel bucket current has been clarified. It realizes the constant current control of the coal flow rate by introducing the drive motor current parameters of the wheel bucket and the belt coal flow data. . Specifically, the belt coal flow value and drive motor current value are collected through real-time monitoring, and data processing and analysis algorithms are introduced at the back end to perform timing collaborative analysis of the belt coal flow and drive motor current, thereby utilizing the belt flow and drive motor current values. The relationship between the currents is used to realize real-time intelligent adjustment of the drive motor current to achieve the purpose of constant current control. In this way, the intelligent operation level of the bucket wheel machine can be improved, precise control of coal flow can be achieved, belt overload can be prevented, and coal blending ratio requirements can be met.

Furthermore, a control system for constant current control based on belt flow and wheel bucket current is also provided.

Figure 6 is a block diagram of a control system that implements constant current control based on belt flow and bucket current according to an embodiment of the present application. As shown in Figure 6, the control system 300 for realizing constant current control based on the belt flow rate and bucket current according to the embodiment of the present application includes: a data acquisition module 310 for acquiring the belt coal at multiple predetermined time points within a predetermined time period. The flow value and the drive motor current value at multiple predetermined time points; the arrangement module 320 is used to arrange the belt coal flow value at multiple predetermined time points and the drive motor current value at multiple predetermined time points into belt coal according to the time dimension. The flow timing input vector and the driving motor current timing input vector; the local timing analysis module 330 is used to perform local timing analysis on the belt coal flow timing input vector and the driving motor current timing input vector respectively to obtain the belt coal flow local timing feature vector. The sequence of the local timing feature vector of the drive motor current; the feature sequence interactive fusion module 340 is used to perform feature sequence interactive fusion on the sequence of the local timing feature vector of the belt coal flow and the sequence of the local timing feature vector of the drive motor current to obtain the belt The coal flow rate-drive motor current timing interactive fusion feature; and the current value control result generation module 350 is used to determine that the current value of the drive motor at the current time point should be increased based on the belt coal flow rate-drive motor current timing interactive fusion feature. should be maintained or should be reduced.

As mentioned above, the control system 300 for realizing constant current control based on the belt flow and bucket current according to the embodiment of the present application can be implemented in various wireless terminals, such as a server with a control algorithm for realizing constant current control based on the belt flow and bucket current. wait. In a possible implementation, the control system 300 for realizing constant current control based on the belt flow rate and bucket current according to the embodiment of the present application can be integrated into the wireless terminal as a software module and/or hardware module. For example, the control system 300 that implements constant current control based on the belt flow rate and wheel bucket current can be a software module in the operating system of the wireless terminal, or can be an application program developed for the wireless terminal; of course, the The control system 300 that implements constant current control based on the belt flow rate and the bucket current can also be one of the many hardware modules of the wireless terminal.

Alternatively, in another example, the control system 300 that implements constant current control based on the belt flow rate and the wheel bucket current and the wireless terminal can also be separate devices, and the control system 300 that implements the constant current control based on the belt flow rate and the wheel bucket current The control system 300 can be connected to the wireless terminal through a wired and/or wireless network, and transmit interactive information according to an agreed data format.

The embodiments of the present disclosure have been described above. The above description is illustrative, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen to best explain the principles, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims (9)

1. A control method based on belt flow and wheel bucket current to achieve constant current control, which is characterized by including the following steps: S1. Obtain belt coal flow values at multiple predetermined time points and drive motor current values at multiple predetermined time points within a predetermined time period; S2. Arrange the belt coal flow values at multiple predetermined time points and the driving motor current values at multiple predetermined time points into a belt coal flow timing input vector and a driving motor current timing input vector according to the time dimension; S3. Perform local timing analysis on the belt coal flow timing input vector and the driving motor current timing input vector to obtain the sequence of the belt coal flow local timing feature vector and the driving motor current local timing feature vector sequence; S4. Perform feature sequence interactive fusion on the sequence of the local timing feature vectors of the belt coal flow and the sequence of the local timing feature vectors of the drive motor current to obtain the belt coal flow-drive motor current timing interactive fusion characteristics; and S5. Based on the belt coal flow-drive motor current timing interaction fusion characteristics, determine whether the current value of the drive motor at the current time point should be increased, maintained, or reduced. 2. The control method for realizing constant current control based on belt flow and wheel bucket current according to claim 1, characterized in that step S3 includes the following steps: S31. Perform vector segmentation on the belt coal flow timing input vector and the driving motor current timing input vector respectively to obtain a sequence of the belt coal flow local timing input vector and a sequence of the driving motor current local timing input vector; S32. Use the temporal feature extractor based on the deep neural network model to perform feature extraction on the sequence of the local timing input vector of the belt coal flow and the sequence of the local timing input vector of the driving motor current to obtain the local timing of the belt coal flow. A sequence of eigenvectors and a sequence of local timing eigenvectors of the drive motor current. 3. The control method for constant current control based on belt flow and bucket current according to claim 2, characterized in that: the temporal feature extractor based on the deep neural network model is a temporal feature extractor based on a one-dimensional convolution layer. . 4. The control method for realizing constant current control based on belt flow and wheel bucket current according to claim 3, characterized in that step S4 specifically includes: combining the sequence of the local timing feature vector of the belt coal flow and the driving motor. The sequence of current local time series feature vectors is passed through the feature sequence interactive fusion module to obtain the belt coal flow-drive motor current time series interactive fusion feature vector as the belt coal flow-drive motor current time series interactive fusion feature. 5. The control method for constant current control based on belt flow and wheel bucket current according to claim 4, characterized in that the specific steps of step S4 include: S41. Calculate the correlation between any two feature vectors in the sequence of the local timing feature vectors of the belt coal flow and the sequence of the local timing feature vectors of the driving motor current to obtain the belt coal flow-drive motor current local timing correlation characteristics. sequence of matrices; S42. Based on the sequence of the belt coal flow-drive motor current local timing correlation feature matrix, perform feature interactive attention coding on the sequence of the belt coal flow local timing feature vectors and the sequence of the drive motor current local timing feature vectors. To obtain the sequence of local timing feature vectors of the attention-enhanced belt coal flow and the sequence of local timing feature vectors of the attention-enhanced drive motor current; S43. Fusion of the sequence of local timing feature vectors of the belt coal flow and the feature vectors at corresponding positions in the sequence of local timing feature vectors of the attention-enhanced belt coal flow to obtain a sequence of fused local timing feature vectors of the belt coal flow, and fuse The sequence of local timing feature vectors of the driving motor current and the feature vectors at corresponding positions in the sequence of local timing feature vectors of the driving motor current by the attention enhancement are used to obtain a sequence of local timing feature vectors of the driving motor current fusion; S44. Perform maximum pooling processing on the sequence of the belt coal flow fusion local timing feature vectors to obtain the belt coal flow fusion local timing maximum pooling feature vector, and fuse the sequence of local timing feature vectors on the drive motor current. Perform maximum pooling processing to obtain the local timing maximum pooling feature vector of the drive motor current fusion; S45. Fusion of the belt coal flow fusion local time series maximum pooling feature vector and the drive motor current fusion local time series maximum pooling feature vector to obtain the belt coal flow - drive motor current time series interactive fusion feature vector. 6. The control method for constant current control based on belt flow and wheel bucket current according to claim 5, characterized in that step S5 includes: S51. Perform feature correction on the belt coal flow-drive motor current timing interactive fusion feature vector to obtain the corrected belt coal flow-drive motor current timing interactive fusion feature vector; S52. Pass the corrected belt coal flow-drive motor current timing interactive fusion feature vector through a classifier to obtain a classification result. The classification result is used to indicate that the current value of the drive motor at the current time point should be increased, maintained, or should be reduced. 7. The control method for realizing constant current control based on belt flow and wheel bucket current according to claim 6, characterized in that step 51 specifically includes the following steps: S511. Concatenate the sequence of the local timing feature vectors of the belt coal flow to obtain the full time domain belt coal flow timing feature vector, and concatenate the sequence of the local timing feature vectors of the drive motor current to obtain the full time domain. Drive motor current timing characteristic vector; S512. Perform fusion correction on the full-time domain belt coal flow timing feature vector and the full-time domain drive motor current timing feature vector to obtain a correction feature vector; and S513. Fusion of the corrected feature vector and the belt coal flow-drive motor current timing interactive fusion feature vector to obtain the corrected belt coal flow-drive motor current timing interactive fusion feature vector. 8. The control method for realizing constant current control based on belt flow and wheel bucket current according to claim 7, characterized in that step S52 specifically includes: Use multiple fully connected layers of the classifier to perform fully connected encoding on the corrected belt coal flow-drive motor current timing interactive fusion feature vector to obtain a coded classification feature vector; and The encoded classification feature vector is passed through the Softmax classification function of the classifier to obtain the classification result. 9. A control system that realizes constant current control based on belt flow and bucket current, which is characterized by including: A data acquisition module, used to acquire belt coal flow values at multiple predetermined time points within a predetermined time period and drive motor current values at the multiple predetermined time points; An arrangement module, configured to arrange the belt coal flow values at the plurality of predetermined time points and the driving motor current values at the plurality of predetermined time points into a belt coal flow timing input vector and a driving motor current timing input vector according to the time dimension. ; A local timing analysis module, configured to perform local timing analysis on the belt coal flow timing input vector and the drive motor current timing input vector respectively to obtain the sequence of the belt coal flow local timing feature vector and the drive motor current local timing feature. sequence of vectors; A feature sequence interactive fusion module is used to perform feature sequence interactive fusion on the sequence of the local timing feature vectors of the belt coal flow and the sequence of the local timing feature vectors of the drive motor current to obtain the belt coal flow-drive motor current timing interactive fusion features. ;as well as The current value control result generation module is used to determine whether the current value of the drive motor at the current time point should be increased, maintained or reduced based on the belt coal flow-drive motor current timing interaction fusion characteristics.