CN117424513A - Control method and system for realizing constant current control based on belt flow and wheel bucket current - Google Patents
Control method and system for realizing constant current control based on belt flow and wheel bucket current Download PDFInfo
- Publication number
- CN117424513A CN117424513A CN202311402453.2A CN202311402453A CN117424513A CN 117424513 A CN117424513 A CN 117424513A CN 202311402453 A CN202311402453 A CN 202311402453A CN 117424513 A CN117424513 A CN 117424513A
- Authority
- CN
- China
- Prior art keywords
- time sequence
- driving motor
- sequence
- coal flow
- motor current
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 239000013598 vector Substances 0.000 claims abstract description 242
- 239000003245 coal Substances 0.000 claims abstract description 222
- 230000004927 fusion Effects 0.000 claims abstract description 73
- 230000003993 interaction Effects 0.000 claims abstract description 43
- 230000003247 decreasing effect Effects 0.000 claims abstract description 12
- 230000002452 interceptive effect Effects 0.000 claims description 28
- 238000012937 correction Methods 0.000 claims description 25
- 238000011176 pooling Methods 0.000 claims description 15
- 238000012300 Sequence Analysis Methods 0.000 claims description 12
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 238000003062 neural network model Methods 0.000 claims description 3
- 230000011218 segmentation Effects 0.000 claims description 3
- 230000008859 change Effects 0.000 description 8
- 238000005303 weighing Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 7
- 238000009826 distribution Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 4
- 230000007547 defect Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000012544 monitoring process Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000002156 mixing Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000002457 bidirectional effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000007499 fusion processing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
- H02P23/00—Arrangements or methods for the control of AC motors characterised by a control method other than vector control
- H02P23/14—Estimation or adaptation of motor parameters, e.g. rotor time constant, flux, speed, current or voltage
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02P—CONTROL OR REGULATION OF ELECTRIC MOTORS, ELECTRIC GENERATORS OR DYNAMO-ELECTRIC CONVERTERS; CONTROLLING TRANSFORMERS, REACTORS OR CHOKE COILS
- H02P23/00—Arrangements or methods for the control of AC motors characterised by a control method other than vector control
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Control Of Electric Motors In General (AREA)
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
Technical Field
The invention relates to the field of intelligent control, in particular to a control method for realizing constant current control based on belt flow and wheel bucket current.
Background
The bucket wheel machine is an important device for coal exploitation and transportation, and consists of a large bucket wheel and a cantilever belt, and can carry out coal taking and coal unloading operations at different positions. The operation efficiency and safety of the bucket wheel machine are closely related to the control of the coal taking flow, so that an accurate, stable and reliable coal taking flow measuring and controlling method is needed
At present, the common coal taking flow measurement methods comprise an electronic belt weighing method and a laser scanning method, but both methods have certain defects and shortcomings. Specifically, the electronic belt weighing method is used for completing coal flow monitoring and control by arranging the electronic belt weighing device on the cantilever belt of the bucket wheel machine, but the belt weighing device has extremely poor precision in the actual use process due to continuous change of the pitching angle of the cantilever belt and lack of correction modes, and cannot be used as measurement data of the bucket wheel machine coal taking flow control. The laser scanning method is to install a laser scanner above the cantilever belt, calculate the volume by scanning the surface shape of the coal flow, add the estimation of the density and convert the volume into the flow. The method has the advantages of less error drift, relatively stability and less frequent correction, and has the defects that the density of the coal needs manual experience and the efficiency is lower; secondly, serious deviation of the cantilever belt can influence the calculation accuracy of the coal flow sectional area, and an effective deviation correcting device is needed to be additionally arranged. Accordingly, an optimized coal flow constant flow control scheme is desired.
Disclosure of Invention
In order to solve the technical problem, the intelligent operation level of the bucket wheel machine can be improved, the accurate control of the coal flow is realized, the belt overload is prevented, and the requirement of the coal blending proportion is met. A control method for realizing constant current control based on belt flow and wheel bucket current realizes constant current control on coal flow by introducing current parameters of a driving motor of a wheel bucket and belt coal flow data. Specifically, the belt coal flow value and the driving motor current value are monitored and collected in real time, and a data processing and analyzing algorithm is introduced into the rear end to perform time sequence collaborative analysis of the belt coal flow and the driving motor current, so that the real-time intelligent regulation of the driving motor current is realized by utilizing the relation between the belt flow and the driving motor current, and the purpose of constant current control is achieved.
The control method for realizing constant current control based on belt flow and wheel bucket current is characterized by comprising 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 belt coal flow rate values at a plurality of preset time points and driving motor current values at the preset time points into a belt coal flow time sequence input vector and a driving motor current time sequence input vector according to time dimensions respectively;
S3, carrying out vector local time sequence analysis on the belt coal flow time sequence input vector and the driving motor current time sequence input vector respectively to obtain a sequence of belt coal flow local time sequence characteristic vectors and a sequence of driving motor current local time sequence characteristic vectors;
s4, carrying out feature sequence interaction fusion on the sequence of the local time sequence feature vector of the belt coal flow and the sequence of the current local time sequence feature vector of the driving motor to obtain belt coal flow-driving motor current time sequence interaction fusion features;
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.
A control system for realizing constant current control based on belt flow and wheel bucket current comprises:
the data acquisition module is used for 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;
the arrangement module is used for arranging the belt coal flow rate values at the plurality of preset time points and the driving motor current values at the plurality of preset time points into a belt coal flow time sequence input vector and a driving motor current time sequence input vector according to the time dimension respectively;
The local time sequence analysis module is used for carrying out local time sequence analysis on the belt coal flow time sequence input vector and the driving motor current time sequence input vector respectively so as to obtain a sequence of belt coal flow local time sequence feature vectors and a sequence of driving motor current local time sequence feature vectors;
the characteristic sequence interactive fusion module is used for carrying out characteristic sequence interactive fusion on the sequence of the local time sequence characteristic vector of the belt coal flow and the sequence of the current local time sequence characteristic vector of the driving motor so as to obtain belt coal flow-driving motor current time sequence interactive fusion characteristics; and
and the current value control result generation module is used for determining that the current value of the driving motor at the current time point should be increased, kept or decreased based on the belt coal flow-driving motor current time sequence interaction fusion characteristic.
Compared with the prior art, the control method and the system for realizing constant current control based on the belt flow and the wheel bucket current realize constant current control on the coal flow by introducing the driving motor current parameter of the wheel bucket and the belt coal flow data. Specifically, the belt coal flow value and the driving motor current value are monitored and collected in real time, and a data processing and analyzing algorithm is introduced into the rear end to perform time sequence collaborative analysis of the belt coal flow and the driving motor current, so that the real-time intelligent regulation of the driving motor current is realized by utilizing the relation between the belt flow and the driving motor current, and the purpose of constant current control is achieved. Therefore, the intelligent operation level of the bucket wheel machine can be improved, the accurate control of the coal flow is realized, the belt overload is prevented, and the requirement of the coal blending proportion is met.
Drawings
The foregoing and other objects, features and advantages of the present application will become more apparent from the following more particular description of embodiments of the present application, as illustrated in the accompanying drawings. The accompanying drawings are included to provide a further understanding of embodiments of the application and are incorporated in and constitute a part of this specification, illustrate the application and not constitute a limitation to the application. In the drawings, like reference numerals generally refer to like parts or steps.
FIG. 1 is a flow chart of a control method for implementing constant current control based on belt flow and bucket current according to an embodiment of the present application;
FIG. 2 is a system architecture diagram of a control method for implementing constant current control based on belt flow and bucket current according to an embodiment of the present application;
FIG. 3 is a flowchart of substep S3 of a control method for implementing constant current control based on belt flow and bucket current in accordance with an embodiment of the present application;
FIG. 4 is a flowchart of substep S5 of a control method for implementing constant current control based on belt flow and bucket current in accordance with an embodiment of the present application;
FIG. 5 is a flowchart of substep S51 of a control method for implementing constant current control based on belt flow and bucket current according to an embodiment of the present application;
Fig. 6 is a block diagram of a control system implementing constant current control based on belt flow and bucket current in accordance with an embodiment of the present application.
Detailed Description
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
As used in this application and in the claims, the terms "a," "an," "the," and/or "the" are not specific to the singular, but may include the plural, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.
Although the present application makes various references to certain modules in a system according to embodiments of the present application, any number of different modules may be used and run on a user terminal and/or server. The modules are merely illustrative and different aspects of the systems and methods may use different modules.
Flowcharts are used in this application to describe the operations performed by systems according to embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed in order precisely. Rather, the various steps may be processed in reverse order or simultaneously, as desired. Also, other operations may be added to or removed from these processes.
Hereinafter, example embodiments according to the present application will be described in detail with reference to the accompanying drawings. It should be apparent that the described embodiments are only some of the embodiments of the present application and not all of the embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
The common coal taking flow measuring methods include an electronic belt weighing method and a laser scanning method, but both methods have certain defects and shortcomings. Specifically, the electronic belt weighing method is used for completing coal flow monitoring and control by arranging the electronic belt weighing device on the cantilever belt of the bucket wheel machine, but the belt weighing device has extremely poor precision in the actual use process due to continuous change of the pitching angle of the cantilever belt and lack of correction modes, and cannot be used as measurement data of the bucket wheel machine coal taking flow control. The laser scanning method is to install a laser scanner above the cantilever belt, calculate the volume by scanning the surface shape of the coal flow, add the estimation of the density and convert the volume into the flow. The method has the advantages of less error drift, relatively stability and less frequent correction, and has the defects that the density of the coal needs manual experience and the efficiency is lower; secondly, serious deviation of the cantilever belt can influence the calculation accuracy of the coal flow sectional area, and an effective deviation correcting device is needed to be additionally arranged. Accordingly, an optimized coal flow constant flow control scheme is desired.
As shown in fig. 1 and 2, a control method for realizing constant current control based on belt flow and wheel bucket current according to an embodiment of the application comprises the following steps:
s1, acquiring belt coal flow values at a plurality of preset time points and driving motor current values at a plurality of preset time points in a preset time period;
s2, arranging belt coal flow time sequence input vectors and driving motor current time sequence input vectors of a plurality of preset time points and driving motor current values of a plurality of preset time points according to time dimensions respectively;
s3, carrying out vector local time sequence analysis on the belt coal flow time sequence input vector and the driving motor current time sequence input vector respectively to obtain a sequence of belt coal flow local time sequence feature vectors and a sequence of driving motor current local time sequence feature vectors;
s4, carrying out feature sequence interaction fusion on the sequence of the local time sequence feature vector of the belt coal flow and the sequence of the current local time sequence feature vector of the driving motor to obtain a belt coal flow-driving motor current time sequence interaction fusion feature;
s5, determining that the current value of the driving motor at the current time point should be increased, kept or decreased based on the belt coal flow-driving motor current time sequence interaction fusion characteristic.
In S1, the belt coal flow is the flow of coal conveyed by a belt conveyor in the coal mine or coal treatment process, and is one of important indexes for measuring the coal conveying efficiency and the production capacity; the driving current value refers to the current consumed by the driving motor in the running process, and is one of important indexes for measuring the load and the working state of the driving motor. In one example, a belt coal flow value may be obtained by a coal flow sensor at a plurality of predetermined points in time over a predetermined period of time; and acquiring, by the current sensor, drive motor current values at a plurality of predetermined points in time.
It is noted that a coal flow sensor is a sensor device for measuring the flow of coal. It is typically mounted on a pipe or conveyor in a coal conveying system for real-time monitoring and measuring of the flow of coal through the pipe or conveyor. A current sensor is a sensor device for measuring the magnitude of a current. It is commonly used to monitor and measure the current in a circuit to obtain the current value in real time and to perform corresponding control and analysis.
S2, arranging the belt coal flow rate values at a plurality of preset time points and the driving motor current values at a plurality of preset time points into a belt coal flow time sequence input vector and a driving motor current time sequence input vector according to the time dimension respectively. Considering that the belt coal flow value and the driving motor current value can change with time in the time dimension, that is, the belt coal flow and the driving motor current have implicit time sequence change rules in time sequence, in order to be capable of carrying out real-time self-adaptive control on the driving motor current, the time sequence cooperative correlation characteristic distribution information focusing on the belt coal flow value and the driving motor current value is needed. Based on this, in the technical solution of the present application, it is necessary to arrange the belt coal flow values at a plurality of predetermined time points and the driving motor current values at a plurality of predetermined time points into a belt coal flow time sequence input vector and a driving motor current time sequence input vector according to the time dimension, so as to integrate the distribution information of the belt coal flow values and the driving motor current values in time sequence, respectively.
Step S3 includes the steps of:
s31, vector segmentation is carried out on the belt coal flow time sequence input vector and the driving motor current time sequence input vector respectively to obtain a sequence of the belt coal flow local time sequence input vector and a sequence of the driving motor current local time sequence input vector;
s32, carrying out feature extraction on the sequence of the local time sequence input vectors of the belt coal flow and the sequence of the local time sequence input vectors of the driving motor current through a time sequence feature extractor based on the deep neural network model to obtain the sequence of the local time sequence feature vectors of the belt coal flow and the sequence of the local time sequence feature vectors of the driving motor current.
In consideration of the fact that the belt coal flow data and the driving motor current data are continuously signals changing along with time in the process of monitoring and constant current control, various time sequence change modes and various time sequence change trends are displayed on the time dimension. Therefore, in order to analyze the time sequence change conditions of the belt coal flow value and the driving motor current value more fully, so as to capture finer granularity information and time sequence characteristics in time sequence data, and further accurately perform constant current control, in the technical scheme of the application, the belt coal flow time sequence input vector and the driving motor current time sequence input vector are further subjected to vector segmentation respectively to obtain a sequence of the belt coal flow local time sequence input vector and a sequence of the driving motor current local time sequence input vector.
Specifically, when step S32 is performed, for the belt coal flow value and the driving motor current value, they will show a certain change rule under each local time sequence, so as to effectively capture and describe each local time sequence feature of the belt coal flow value and the driving motor current value in the time dimension. More specifically, each layer using a one-dimensional convolution layer based timing feature extractor performs, in forward transfer of the layer, respectively, on input data: carrying out convolution processing on input data to obtain a convolution characteristic diagram; pooling the convolution feature images based on the feature matrix to obtain pooled feature images; performing nonlinear activation on the pooled feature map to obtain an activated feature map; the output of the last layer of the time sequence feature extractor based on the one-dimensional convolution layer is the sequence of the local time sequence feature vectors of the belt coal flow and the sequence of the local time sequence feature vectors of the driving motor current, and the input of the first layer of the time sequence feature extractor based on the one-dimensional convolution layer is the sequence of the local time sequence input vectors of the belt coal flow and the sequence of the local time sequence input vectors of the driving motor current.
It should be noted that the one-dimensional convolutional layer is a convolutional neural network layer commonly used in deep learning, and is used for processing sequence data. Unlike two-dimensional convolution layers, one-dimensional convolution layers perform a sliding window convolution operation in one dimension, and are typically used to process data having a sequential structure, such as time series, text, and the like. The input to the one-dimensional convolution layer is a one-dimensional tensor, e.g., time series data. It extracts features of the input data by defining a set of convolution kernels (or filters). Each convolution kernel is a small one-dimensional weight vector that performs element-by-element product-sum-and-sum operations 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 step and the filling mode. The convolution operation can capture the local pattern and characteristics of the input data, and multiple different characteristics can be extracted through the parallel operation of multiple convolution kernels. One-dimensional convolution layers are typically 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 then used to map the output of the convolutional layer to the final prediction or classification result.
It should be noted that, in other specific examples of the present application, the local time sequence analysis may be performed on the belt coal flow time sequence input vector and the driving motor current time sequence input vector by other manners to obtain a sequence of the belt coal flow local time sequence feature vector and a sequence of the driving motor current local time sequence feature vector, for example: determining the window size and step size of local time sequence analysis; the window size represents the number of time steps contained in each local timing feature vector, and the step size represents the interval between windows; local time sequence analysis is carried out on the belt coal flow time sequence input vector and the driving motor current time sequence input vector, for example: sequentially selecting continuous windows from the starting position of the time sequence by taking step length as an interval; extracting the characteristics of corresponding time steps in a belt coal flow time sequence input vector and a driving motor current time sequence input vector in each window; the extracted features are formed into a local time sequence feature vector; repeating the steps until the whole time sequence is covered, so as to obtain the sequence of the local time sequence characteristic vector of the belt coal flow and the sequence of the local time sequence characteristic vector of the driving motor current.
And S4, considering that the belt coal flow and the driving motor current are closely related, an implicit time sequence association relation exists between the belt coal flow and the driving motor current, and different time sequence association characteristics exist between the belt coal flow and the driving motor current in each local time period, and the local time sequence association characteristic information of the belt coal flow and the driving motor current has important significance for the real-time control of the driving motor current and the constant current control of the coal flow. Therefore, in the technical scheme of the application, the sequence of the local time sequence feature vector of the belt coal flow and the sequence of the current local time sequence feature vector of the driving motor are further processed through the feature sequence interactive fusion module, so that the correlation and the mutual influence between each local time sequence feature of the belt coal flow and the corresponding local time sequence feature of the current of the driving motor are captured, and the belt coal flow-driving motor current time sequence interactive fusion feature vector is obtained. It should be appreciated that the feature sequence interaction fusion module may separately weight the local timing feature vector of the belt coal flow and the local timing feature vector of the current of each driving motor by calculating the attention weight to model the importance between different feature sequences. Specifically, the module may assign a weight to each feature sequence based on a similarity and correlation between the sequence of belt coal flow local timing feature vectors and the sequence of drive motor current local timing feature vectors. Therefore, after the attention feature interactive fusion processing, the sequence of the local time sequence feature vectors of the belt coal flow and the sequence of the current local time sequence feature vectors of the driving motor can be mutually influenced and supplemented through the corresponding local time sequence feature vectors in the feature sequence, so that interactive cooperative feature distribution information about the belt coal flow and the current of the driving motor in each local time sequence is more fully captured, and the belt coal flow-current time sequence interactive fusion feature vectors of the driving motor are obtained. Specifically, the sequence of the local time sequence feature vectors of the belt coal flow and the sequence of the local time sequence feature vectors of the driving motor current are subjected to a feature sequence interactive fusion module to obtain the interactive fusion feature vectors of the belt coal flow and the driving motor current as the interactive fusion feature of the belt coal flow and the driving motor current, and the method comprises the following steps: calculating the correlation degree between any two characteristic vectors in the sequence of the local time sequence characteristic vectors of the belt coal flow and the sequence of the local time sequence characteristic vectors of the driving motor current to obtain the sequence of the local time sequence correlation characteristic matrix of the belt coal flow and the driving motor current; performing feature interaction attention coding on the sequence of the local time sequence feature vectors of the belt coal flow and the sequence of the local time sequence feature vectors of the driving motor based on the sequence of the local time sequence correlation feature matrix of the belt coal flow and the driving motor current to obtain the sequence of the local time sequence feature vectors of the attention-enhancing belt coal flow and the sequence of the local time sequence feature vectors of the attention-enhancing driving motor current; fusing the sequence of the local time sequence feature vectors of the belt coal flow and the feature vectors of the corresponding positions in the sequence of the local time sequence feature vectors of the attention-enhancing belt coal flow to obtain a sequence of the local time sequence feature vectors of the belt coal flow fusion, and fusing the sequence of the local time sequence feature vectors of the driving motor current and the feature vectors of the corresponding positions in the sequence of the local time sequence feature vectors of the attention-enhancing driving motor current to obtain a sequence of the local time sequence feature vectors of the driving motor current fusion; carrying out maximum value pooling treatment on the sequence of the local time sequence feature vectors fused with the belt coal flow to obtain a local time sequence maximum value pooling feature vector fused with the belt coal flow, and carrying out maximum value pooling treatment on the sequence of the local time sequence feature vectors fused with the driving motor current to obtain a local time sequence maximum value pooling feature vector fused with the driving motor current; and fusing the local time sequence maximum value pooling feature vector fused by the belt coal flow and the local time sequence maximum value pooling feature vector fused by the driving motor current to obtain the belt coal flow-driving motor current time sequence interaction fusion feature vector.
As shown in fig. 4, step S5 includes: s51, carrying out characteristic correction on the belt coal flow-driving motor current time sequence interaction fusion characteristic vector to obtain a corrected belt coal flow-driving motor current time sequence interaction fusion characteristic vector; and S52, the corrected belt coal flow and driving motor current time sequence interaction fusion feature vector is passed through a classifier to obtain a classification result, and the classification result is used for indicating that the current value of the driving motor at the current time point should be increased, should be kept or should be decreased.
S51, carrying out characteristic correction on the belt coal flow-driving motor current time sequence interaction fusion characteristic vector to obtain a corrected belt coal flow-driving motor current time sequence interaction fusion characteristic vector. In particular, in one specific example of the present application, as shown in fig. 5, S51 includes:
s511, cascading the sequence of the local time sequence feature vectors of the belt coal flow to obtain a time sequence feature vector of the full-time-domain belt coal flow, and cascading the sequence of the local time sequence feature vectors of the driving motor current to obtain a time sequence feature vector of the full-time-domain driving motor current;
s512, carrying out fusion correction on the full-time-domain belt coal flow time sequence feature vector and the full-time-domain driving motor current time sequence feature vector to obtain a correction feature vector;
And S513, fusing the corrected characteristic vector and the belt coal flow-driving motor current time sequence interactive fused characteristic vector to obtain the corrected belt coal flow-driving motor current time sequence interactive fused characteristic vector.
S511, cascading the sequence of the local time sequence feature vectors of the belt coal flow to obtain a time sequence feature vector of the full-time-domain belt coal flow, and cascading the sequence of the local time sequence feature vectors of the driving motor current to obtain a time sequence feature vector of the full-time-domain driving motor current. It should be appreciated that the dependency modeling capability can be enhanced by cascading and more flexible feature extraction supported, thereby improving the accuracy and robustness of the prediction of the drive motor current.
S512, fusion correction is carried out on the time sequence feature vector of the full-time-domain belt coal flow and the time sequence feature vector of the full-time-domain driving motor current to obtain a correction feature vector. Particularly, in the technical scheme of the application, the sequence of the local time sequence characteristic vector of the belt coal flow and the sequence of the local time sequence characteristic vector of the driving motor current are respectively used for expressing the sequence of the local neighborhood associated characteristic in the local time domain of the belt coal flow and the sequence of the local neighborhood associated characteristic in the local time domain of the driving motor current. By using the feature sequence interactive fusion module, bidirectional selective feature fusion based on an attention mechanism can be performed based on the relevance between each feature vector in the sequence of the local time sequence feature vectors of the belt coal flow and the sequence of the local time sequence feature vectors of the driving motor current so as to obtain the interactive fusion feature vector of the belt coal flow and the driving motor current time sequence, so that the interactive fusion of the time domain features of the belt flow and the driving motor current is realized. However, the applicant of the present application considers 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 driving motor current, and thus, when the interactive fusion feature vector of the belt coal flow-driving motor current is obtained through the feature sequence interactive fusion module, the unbalanced expression of the interactive fusion feature vector of the belt coal flow-driving motor current may be caused, and the expression effect of the interactive fusion feature vector of the belt coal flow-driving motor current is affected. Based on this, it is preferable that the time series characteristic vector of the full-time domain belt coal flow obtained by cascading the sequence of the local time series characteristic vector of the belt coal flow is, for example, denoted as V 1 And full time domain drive motor current timing feature directions derived from a sequential concatenation of drive motor current local timing feature vectorsThe amount being, for example, denoted as V 2 Fusion correction is performed to obtain corrected feature vectors, e.g. denoted as V c ：
Wherein V is 1 Is a time sequence characteristic vector of the full-time-domain belt coal flow, V 2 Is a full time domain drive motor current timing feature vector,and->Respectively representing the reciprocal of the global average value of the full-time-domain belt coal flow time sequence feature vector and the full-time-domain driving motor current time sequence feature vector, and I is a unit vector, and by-represents multiplication by position point by%>Representing addition by position>Representing difference in position, V c Is the correction feature vector. That is, the current time sequence characteristic vector V of the full-time-domain driving motor to be fused 2 Regarded as a time sequence characteristic vector V of the full-time-domain belt coal flow 1 Is possible to lose the full-time-domain belt coal flow time sequence characteristic vector V 1 Target distribution information of target features in a class space, resulting in loss of class regression objectives, so that feature enhancement and self-supervision balance of regression robustness can be realized during feature interpolation fusion by means of cross penalty of outlier distribution (outlierdism) of feature distribution relative to each other, so as to promote full-time domain belt coal flow time sequence feature vector V 1 And full time domain driving motor current time sequence characteristic vector V 2 Is a feature fusion effect of (1). In this way, the feature vector V will be corrected again c Alternating with the current time sequence of the belt coal flow-driving motorThe expression effect of the belt coal flow-driving motor current time sequence interaction fusion feature vector can be improved by fusion of the feature vectors, so that the accuracy of classification results obtained by the classifier is improved. Therefore, the real-time intelligent regulation of the current of the driving motor can be realized based on the belt flow and the bucket current, so that the purpose of constant current control is achieved.
More specifically, S513, the corrected feature vector and the belt coal flow-driving motor current timing sequence inter-fusion feature vector are fused to obtain a corrected belt coal flow-driving motor current timing sequence inter-fusion feature vector. It should be appreciated that the correction feature vector may contain correction information related to the drive motor current value, such as a correction factor or correction offset. The correction feature vector is fused with the belt coal flow-driving motor current time sequence interaction fusion feature vector, so that the capability of feature representation can be enhanced, and the model can better capture the complex relationship between the driving motor current and the belt coal flow.
It should be noted that, in other specific examples of the present application, the feature correction may be performed on the belt coal flow rate-driving motor current time sequence interaction feature vector in other manners to obtain a corrected belt coal flow rate-driving motor current time sequence interaction feature vector, for example: preprocessing the original data, including operations such as outlier removal, normalization and the like, so as to ensure the reliability and the processibility of the data; if the feature vector dimension is high, the feature selection method can be considered to select the most relevant feature subset so as to reduce the calculation amount and reduce the influence of noise; converting the feature vectors, e.g., reducing the dimension, mapping to new feature space, etc., to extract more useful information; selecting an appropriate feature correction method, common methods include statistical methods (e.g., mean correction, normalization), filtering methods (e.g., median filtering, gaussian filtering), machine learning methods (e.g., automatic encoder, generation of an countermeasure network), and the like; and correcting the feature vector according to the selected feature correction method.
Specifically, S52, the corrected belt coal flow-driving motor current time sequence interaction fusion feature vector is passed through a classifier to obtain a classification result, where the classification result is used to indicate that the current value of the driving motor at the current time point should be increased, should be kept or should be decreased. The method is characterized in that the classification processing is carried out by utilizing the interactive association fusion characteristic information between the local time sequence characteristics of the belt coal flow and the local time sequence characteristics of the driving motor current, so that the real-time self-adaptive adjustment of the driving motor current is realized by utilizing the time sequence association relation between the belt flow and the driving motor current, and the purpose of constant current control is achieved. More specifically, firstly, performing full-connection coding on corrected belt coal flow-driving motor current time sequence interaction fusion feature vectors by using a plurality of full-connection layers of a classifier to obtain coding classification feature vectors; the encoded classification feature vector is then passed through the Softmax classification function of the classifier to obtain a classification result.
It should be noted that, in other specific examples of the present application, the current value of the driving motor at the current time point may be determined to be increased, maintained or decreased based on the belt coal flow-driving motor current time sequence interaction and fusion feature in other manners, for example: collecting and preparing time sequence interaction fusion characteristic data of belt coal flow and driving motor current, wherein the time sequence interaction fusion characteristic data comprises characteristic vectors at the current time point and corresponding driving motor current values; extracting features related to the current time point from the time sequence interaction fusion feature data; analyzing the extracted characteristics, and observing the relation between the characteristics and the current of the driving motor; selecting a proper modeling method to establish a prediction model according to the result of the feature analysis; training a model by using historical data, and verifying and optimizing the model by using a verification set; predicting the characteristics of the current time point by using the trained model, and judging the variation trend of the current of the driving motor according to the prediction result; if the predicted value is higher than the current value, the current is increased; if the predicted value is similar to the current value, the current is indicated to be maintained; if the predicted value is lower than the current value, the current is reduced; and according to the judgment result, adjusting a control strategy to realize the increase, the maintenance or the reduction of the current. This may involve adjusting control parameters of the motor, increasing or decreasing the load, etc.
In summary, a control method for realizing constant-current control based on belt flow and wheel bucket current according to the embodiment of the application is explained, wherein constant-current control on coal flow is realized by introducing current parameters of a driving motor of a wheel bucket and belt coal flow data. Specifically, the belt coal flow value and the driving motor current value are monitored and collected in real time, and a data processing and analyzing algorithm is introduced into the rear end to perform time sequence collaborative analysis of the belt coal flow and the driving motor current, so that the real-time intelligent regulation of the driving motor current is realized by utilizing the relation between the belt flow and the driving motor current, and the purpose of constant current control is achieved. Therefore, the intelligent operation level of the bucket wheel machine can be improved, the accurate control of the coal flow is realized, the belt overload is prevented, and the requirement of the coal blending proportion is met.
Further, a control system for realizing constant current control based on the belt flow and the wheel bucket current is also provided.
Fig. 6 is a block diagram of a control system implementing constant current control based on belt flow and bucket current in accordance with an embodiment of the present application. As shown in fig. 6, a control system 300 for realizing constant current control based on belt flow and wheel bucket current according to an embodiment of the present application includes: a data acquisition module 310, configured to acquire belt coal flow values at a plurality of predetermined time points and driving motor current values at a plurality of predetermined time points within a predetermined time period; an arrangement module 320, configured to arrange the belt coal flow rate values at a plurality of predetermined time points and the driving motor current values at a plurality of predetermined time points into a belt coal flow rate time sequence input vector and a driving motor current time sequence input vector according to a time dimension, respectively; the local time sequence analysis module 330 is configured to perform local time sequence analysis on the belt coal flow time sequence input vector and the driving motor current time sequence input vector to obtain a sequence of belt coal flow local time sequence feature vectors and a sequence of driving motor current local time sequence feature vectors; the feature sequence interaction fusion module 340 is configured to perform feature sequence interaction fusion on the sequence of the local timing sequence feature vector of the belt coal flow and the sequence of the local timing sequence feature vector of the driving motor current to obtain a belt coal flow-driving motor current timing sequence interaction fusion feature; and a current value control result generation module 350, configured to determine, based on the belt coal flow-driving motor current timing sequence interaction fusion feature, that the current value of the driving motor at the current time point should be increased, should be maintained, or should be decreased.
As described above, the control system 300 for implementing constant current control based on the belt flow rate and the bucket current according to the embodiment of the present application may be implemented in various wireless terminals, for example, a server or the like having a control algorithm for implementing constant current control based on the belt flow rate and the bucket current. In one possible implementation, the control system 300 for implementing constant current control based on belt flow and wheel bucket current according to embodiments of the present application may be integrated into the wireless terminal as a software module and/or hardware module. For example, the control system 300 for implementing constant current control based on the belt flow and the wheel bucket current may be a software module in the operating system of the wireless terminal, or may be an application developed for the wireless terminal; of course, the control system 300 for implementing constant current control based on the belt flow and the bucket current can also be one of a plurality of hardware modules of the wireless terminal.
Alternatively, in another example, the control system 300 for implementing constant current control based on the belt flow and the bucket current may be a separate device from the wireless terminal, and the control system 300 for implementing constant current control based on the belt flow and the bucket current may be connected to the wireless terminal through a wired and/or wireless network and transmit interactive information according to an agreed data format.
The foregoing description of the embodiments of the present disclosure has been presented for purposes of illustration and description, and is not intended to be exhaustive or limited to the embodiments disclosed. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the various embodiments described. The terminology used herein was chosen in order to best explain the principles of the embodiments, the practical application, or the improvement of technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (9)
1. The control method for realizing constant current control based on the belt flow and the wheel bucket current is characterized by comprising the following steps:
s1, acquiring belt coal flow values at a plurality of preset time points and driving motor current values at a plurality of preset time points in a preset time period;
s2, respectively arranging the belt coal flow rate values at a plurality of preset time points and the driving motor current values at a plurality of preset time points into a belt coal flow time sequence input vector and a driving motor current time sequence input vector according to the time dimension;
s3, carrying out vector local time sequence analysis on the belt coal flow time sequence input vector and the driving motor current time sequence input vector respectively to obtain a sequence of belt coal flow local time sequence feature vectors and a sequence of driving motor current local time sequence feature vectors;
S4, carrying out feature sequence interaction fusion on the sequence of the local time sequence feature vector of the belt coal flow and the sequence of the current local time sequence feature vector of the driving motor to obtain belt coal flow-driving motor current time sequence interaction fusion features; and
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.
2. The control method for realizing constant current control based on belt flow and wheel bucket current according to claim 1, wherein step S3 comprises the steps of:
s31, vector segmentation is carried out on the belt coal flow time sequence input vector and the driving motor current time sequence input vector respectively to obtain a sequence of belt coal flow local time sequence input vectors and a sequence of driving motor current local time sequence input vectors;
s32, respectively carrying out feature extraction on the sequence of the local time sequence input vectors of the belt coal flow and the sequence of the local time sequence input vectors of the driving motor current through a time sequence feature extractor based on a deep neural network model so as to obtain the sequence of the local time sequence feature vectors of the belt coal flow and the sequence of the local time sequence feature vectors of the driving motor current.
3. The control method for realizing constant current control based on belt flow and wheel bucket current according to claim 2, wherein the control method is characterized by comprising the following steps: the time sequence feature extractor based on the deep neural network model is a time sequence 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, wherein step S4 is specifically: and the sequence of the local time sequence feature vectors of the belt coal flow and the sequence of the local time sequence feature vectors of the driving motor current pass through a feature sequence interactive fusion module to obtain the interactive fusion feature vector of the belt coal flow and the driving motor current time sequence as the interactive fusion feature of the belt coal flow and the driving motor current time sequence.
5. The control method for realizing constant current control based on belt flow and wheel bucket current according to claim 4, wherein the specific steps of step S4 include:
s41, calculating the correlation degree between any two characteristic vectors in the sequence of the local time sequence characteristic vectors of the belt coal flow and the sequence of the local time sequence characteristic vectors of the driving motor current to obtain a sequence of a local time sequence correlation characteristic matrix of the belt coal flow and the driving motor current;
S42, performing feature interaction attention coding on the sequence of the local time sequence feature vectors of the belt coal flow and the sequence of the local time sequence feature vectors of the driving motor based on the sequence of the local time sequence correlation feature matrix of the belt coal flow and the driving motor current to obtain a sequence of the local time sequence feature vectors of the attention-enhancing belt coal flow and a sequence of the local time sequence feature vectors of the attention-enhancing driving motor current;
s43, fusing the sequence of the local time sequence feature vectors of the belt coal flow and the feature vectors of the corresponding positions in the sequence of the local time sequence feature vectors of the attention-enhanced belt coal flow to obtain a sequence of the local time sequence feature vectors of the belt coal flow fusion, and fusing the sequence of the local time sequence feature vectors of the driving motor current and the feature vectors of the corresponding positions in the sequence of the local time sequence feature vectors of the attention-enhanced driving motor current to obtain a sequence of the local time sequence feature vectors of the driving motor current fusion;
s44, carrying out maximum value pooling treatment on the sequence of the local time sequence feature vectors fused with the belt coal flow to obtain a local time sequence maximum value pooling feature vector fused with the belt coal flow, and carrying out maximum value pooling treatment on the sequence of the local time sequence feature vectors fused with the driving motor current to obtain a local time sequence maximum value pooling feature vector fused with the driving motor current;
S45, fusing the local time sequence maximum value pooling feature vector fused by the belt coal flow and the local time sequence maximum value pooling feature vector fused by the driving motor current to obtain the belt coal flow-driving motor current time sequence interaction fused feature vector.
6. The control method for realizing constant current control based on belt flow and wheel bucket current according to claim 5, wherein step S5 comprises:
s51, carrying out characteristic correction on the belt coal flow-driving motor current time sequence interaction fusion characteristic vector to obtain a corrected belt coal flow-driving motor current time sequence interaction fusion characteristic vector;
and S52, the corrected belt coal flow and driving motor current time sequence interaction fusion feature vector is passed through a classifier to obtain a classification result, wherein the classification result is used for indicating that the current value of the driving motor at the current time point should be increased, should be kept or should be decreased.
7. The control method for realizing constant current control based on belt flow and wheel bucket current according to claim 6, wherein step 51 specifically comprises the steps of:
s511, cascading the sequence of the local time sequence feature vectors of the belt coal flow to obtain a time sequence feature vector of the full-time-domain belt coal flow, and cascading the sequence of the local time sequence feature vectors of the driving motor current to obtain a time sequence feature vector of the full-time-domain driving motor current;
S512, carrying out fusion correction on the time sequence feature vector of the full-time-domain belt coal flow and the time sequence feature vector of the full-time-domain driving motor current to obtain a correction feature vector; and
s513, fusing the correction feature vector and the belt coal flow-driving motor current time sequence interaction fusion feature vector to obtain the corrected belt coal flow-driving motor current time sequence interaction fusion feature vector.
8. The control method for realizing constant current control based on belt flow and wheel bucket current according to claim 7, wherein step S52 specifically comprises:
performing full connection coding on the corrected belt coal flow-driving motor current time sequence interaction fusion feature vector by using a plurality of full connection layers of the classifier to obtain a coding classification feature vector; and
and the coding classification feature vector is passed through a Softmax classification function of the classifier to obtain the classification result.
9. A control system for realizing constant current control based on belt flow and wheel bucket current is characterized by comprising:
the data acquisition module is used for 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;
The arrangement module is used for arranging the belt coal flow rate values at the plurality of preset time points and the driving motor current values at the plurality of preset time points into a belt coal flow time sequence input vector and a driving motor current time sequence input vector according to the time dimension respectively;
the local time sequence analysis module is used for carrying out local time sequence analysis on the belt coal flow time sequence input vector and the driving motor current time sequence input vector respectively so as to obtain a sequence of belt coal flow local time sequence feature vectors and a sequence of driving motor current local time sequence feature vectors;
the characteristic sequence interactive fusion module is used for carrying out characteristic sequence interactive fusion on the sequence of the local time sequence characteristic vector of the belt coal flow and the sequence of the current local time sequence characteristic vector of the driving motor so as to obtain belt coal flow-driving motor current time sequence interactive fusion characteristics; and
and the current value control result generation module is used for determining that the current value of the driving motor at the current time point should be increased, kept or decreased based on the belt coal flow-driving motor current time sequence interaction fusion characteristic.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311402453.2A CN117424513A (en) | 2023-10-26 | 2023-10-26 | Control method and system for realizing constant current control based on belt flow and wheel bucket current |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311402453.2A CN117424513A (en) | 2023-10-26 | 2023-10-26 | Control method and system for realizing constant current control based on belt flow and wheel bucket current |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117424513A true CN117424513A (en) | 2024-01-19 |
Family
ID=89529782
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311402453.2A Pending CN117424513A (en) | 2023-10-26 | 2023-10-26 | Control method and system for realizing constant current control based on belt flow and wheel bucket current |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117424513A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117892073A (en) * | 2024-03-14 | 2024-04-16 | 四川星海数创科技有限公司 | Irrigation area water metering system and water metering method |
-
2023
- 2023-10-26 CN CN202311402453.2A patent/CN117424513A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117892073A (en) * | 2024-03-14 | 2024-04-16 | 四川星海数创科技有限公司 | Irrigation area water metering system and water metering method |
| CN117892073B (en) * | 2024-03-14 | 2024-05-24 | 四川星海数创科技有限公司 | Irrigation area water metering system and water metering method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117424513A (en) | Control method and system for realizing constant current control based on belt flow and wheel bucket current | |
| CN108074015B (en) | Ultra-short-term prediction method and system for wind power | |
| CN106201849B (en) | Longevity prediction technique more than a kind of long-life component of finite data driving | |
| CN112288137A (en) | LSTM short-term load prediction method and device considering electricity price and Attention mechanism | |
| CN108174208A (en) | A kind of efficient video coding method of feature based classification | |
| CN115410150A (en) | Detection method and detection device for deviation of conveyor belt and processor | |
| CN110826624A (en) | Time series classification method based on deep reinforcement learning | |
| CN112149896A (en) | Attention mechanism-based mechanical equipment multi-working-condition fault prediction method | |
| CN118003961B (en) | Intelligent charging pile group control system and method | |
| CN117909881A (en) | Fault diagnosis method and device for multi-source data fusion pumping unit | |
| CN116518868B (en) | Deformation measurement method, device, equipment and storage medium based on artificial intelligence | |
| CN117485842A (en) | Method and system for monitoring attitude of wheel bucket cross beam of gate type bucket wheel machine in real time | |
| CN115661803A (en) | Image definition detection method, electronic device, and computer-readable storage medium | |
| CN113312587B (en) | Sensor acquisition data missing value processing method based on ARIMA prediction and regression prediction | |
| CN113971489A (en) | Method and system for predicting remaining service life based on hybrid neural network | |
| CN113077038A (en) | Industrial data feature selection method and device, computer equipment and storage medium | |
| CN111861798A (en) | Residential electricity data missing value interpolation method based on neighbor algorithm | |
| CN118378178B (en) | Transformer fault identification method and system based on residual map convolution neural network | |
| CN118420012B (en) | Urban sewage treatment aeration control system and method | |
| CN118049239B (en) | Data processing and tunnel construction quality control system for underground excavation engineering | |
| CN118567238B (en) | Flexible bus prefabrication construction method and system based on intelligent control system | |
| Ma et al. | Short term prediction of crowd density using v-SVR | |
| CN118734018A (en) | Intelligent monitoring management system for strength training based on data analysis | |
| CN118779524A (en) | Recommendation model based on cross-model denoising | |
| CN118567240A (en) | Aluminum smelting process parameter self-adaptive control method and system based on big data modeling |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |