CN117225091A - System and method for monitoring running state of bag-type dust collector - Google Patents
System and method for monitoring running state of bag-type dust collector Download PDFInfo
- Publication number
- CN117225091A CN117225091A CN202311438949.5A CN202311438949A CN117225091A CN 117225091 A CN117225091 A CN 117225091A CN 202311438949 A CN202311438949 A CN 202311438949A CN 117225091 A CN117225091 A CN 117225091A
- Authority
- CN
- China
- Prior art keywords
- classification
- matrix
- feature
- bag
- dust collector
- 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
- 239000000428 dust Substances 0.000 title claims abstract description 208
- 238000012544 monitoring process Methods 0.000 title claims abstract description 111
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000002159 abnormal effect Effects 0.000 claims abstract description 14
- 239000011159 matrix material Substances 0.000 claims description 149
- 239000013598 vector Substances 0.000 claims description 149
- 238000012545 processing Methods 0.000 claims description 35
- 238000003062 neural network model Methods 0.000 claims description 24
- 230000004913 activation Effects 0.000 claims description 21
- 238000011176 pooling Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 8
- 238000012546 transfer Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 11
- 238000012423 maintenance Methods 0.000 abstract description 6
- 238000010586 diagram Methods 0.000 description 11
- 238000003860 storage Methods 0.000 description 11
- 238000004590 computer program Methods 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000013527 convolutional neural network Methods 0.000 description 4
- 238000005457 optimization Methods 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000009776 industrial production Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 239000013618 particulate matter Substances 0.000 description 2
- 230000008859 change Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000003058 natural language processing Methods 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 239000012716 precipitator Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000003252 repetitive effect Effects 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
- 230000003245 working effect Effects 0.000 description 1
Landscapes
- Filtering Of Dispersed Particles In Gases (AREA)
Abstract
The application relates to the field of intelligent monitoring, and particularly discloses a system and a method for monitoring the running state of a bag-type dust collector. Therefore, the real-time monitoring of the running state can be realized, and when the abnormal running state is found, maintenance and adjustment measures are timely taken to ensure the normal running and the high-efficiency dust removing effect of the bag-type dust remover.
Description
Technical Field
The application relates to the field of intelligent monitoring, in particular to a system and a method for monitoring the running state of a bag-type dust collector.
Background
The bag-type dust collector is a key dust collecting device widely applied to industrial production. Dust and particulate generation is unavoidable during various manufacturing and processing processes, and these fine particulates can have serious impact on the working environment and product quality. To solve this problem, a bag-type dust collector is designed to efficiently remove dust and particulate matter in the air. In order to ensure the effective operation and performance of a bag-type dust collector, the operation state monitoring of the bag-type dust collector is crucial.
Therefore, there is a need for a bag house operating condition monitoring scheme.
Disclosure of Invention
The present application has been made to solve the above-mentioned technical problems. The embodiment of the application provides a system and a method for monitoring the running state of a bag-type dust collector, which are used for judging the running state of the bag-type dust collector by extracting the characteristics of inlet and outlet pressure differences and outlet dust concentration of the bag-type dust collector, correlating the extracted characteristics and classifying the extracted characteristics by a classifier. Therefore, the real-time monitoring of the running state can be realized, and when the abnormal running state is found, maintenance and adjustment measures are timely taken to ensure the normal running and the high-efficiency dust removing effect of the bag-type dust remover.
According to one aspect of the present application, there is provided an operation state monitoring system of a bag-type dust collector, comprising:
the operation data acquisition module is used for acquiring inlet and outlet pressure difference values and outlet dust concentration values of the bag-type dust collector at a plurality of preset time points in a preset time period;
the operation data structuring module is used for respectively arranging the inlet and outlet pressure difference values and the outlet dust concentration value of the plurality of preset time points into a pressure difference input vector and an outlet dust concentration input vector according to the time dimension;
The association module is used for associating the pressure difference input vector with the outlet dust concentration input vector to obtain an operation state monitoring parameter association matrix;
the running state data coding module is used for enabling the running state monitoring parameter association matrix to obtain a classification characteristic matrix through a convolution neural network model of which adjacent layers use convolution kernels which are transposed with each other;
the optimizing module is used for carrying out geometric order based on parameterization features on the classification feature matrix to obtain an optimized classification feature matrix;
and the running state result generation module is used for enabling the optimized classification feature matrix to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether the running state of the bag-type dust collector is normal or not.
In the operation state monitoring system of the bag-type dust collector, the association module is used for: calculating the operation state monitoring parameter correlation matrix between the pressure difference input vector and the outlet dust concentration input vector according to the following correlation coding formula; wherein, the association coding formula is:
wherein V is a Representing the input vector of the pressure difference,a transpose vector representing the pressure differential input vector, V b Representing the output dust concentration input vector, M representing the operating state monitoring parameter correlation matrix,>representing vector multiplication.
In the above-mentioned operation state monitoring system of the bag-type dust collector, the operation state data encoding module is configured to: each layer of the convolution neural network model, which uses convolution kernels transposed to each other, of the adjacent layers respectively performs input data in forward transfer of the layers: performing convolution processing, pooling processing and nonlinear processing on the input data based on a first two-dimensional convolution kernel to obtain a first activation feature map; performing convolution processing, pooling processing and nonlinear activation processing based on a second two-dimensional convolution kernel on the first activation feature map to obtain a second activation feature map, wherein the first two-dimensional convolution kernel and the second two-dimensional convolution kernel are transposed with each other; the input of the first layer of the convolution neural network model of which the adjacent layers use the convolution kernels which are transposed with each other is the running state monitoring parameter association matrix, and the output of the last layer of the convolution neural network model of which the adjacent layers use the convolution kernels which are transposed with each other is the classification feature matrix.
In the above-mentioned operation state monitoring system of the bag-type dust collector, the optimization module includes: a parameterized coding vector construction unit, configured to construct parameterized coding vectors of each position in the classification feature matrix to obtain a plurality of pixel position parameterized coding vectors, where the parameterized coding vectors include coordinates, gradient values along an X-axis direction, gradient values along a Y-axis direction, and feature values; a parameterized feature extraction unit, configured to pass the plurality of pixel position parameterized encoding vectors through a full-connection layer-based parameterized feature extractor to obtain a plurality of pixel position parameterized encoding feature vectors; the cosine similarity calculation unit is used for calculating cosine similarity between any two pixel position parameterized coding feature vectors in the plurality of pixel position parameterized coding feature vectors to obtain an ordered geometric topology matrix; a geometric topological feature extraction unit, which is used for passing the ordered geometric topological matrix through a geometric topological feature extractor based on a convolution layer to obtain an ordered geometric topological feature matrix; and the fusion unit is used for fusing the classification characteristic matrix and the ordered geometric topological characteristic matrix to obtain the optimized classification characteristic matrix.
In the above-mentioned operation state monitoring system of the bag-type dust collector, the operation state result generating module includes: the unfolding unit is used for unfolding the optimized classification feature matrix into classification feature vectors according to row vectors or column vectors; the full-connection unit is used for carrying out full-connection coding on the classification feature vectors by using a full-connection layer of the classifier so as to obtain full-connection coding feature vectors; the probability unit is used for inputting the fully-connected coding feature vector into a Softmax classification function of the classifier to obtain probability values of the classification feature matrix belonging to various classification labels, wherein the classification labels comprise a rule for indicating that the running state of the bag-type dust collector is normal and a rule for indicating that the running state of the bag-type dust collector is abnormal; and the classification unit is used for determining the classification label corresponding to the maximum probability value as the classification result.
According to another aspect of the present application, there is provided an operation state monitoring method of a bag-type dust collector, comprising:
acquiring inlet and outlet pressure difference values and outlet dust concentration values of the bag-type dust collector at a plurality of preset time points in a preset time period;
arranging the inlet and outlet pressure difference values and the outlet dust concentration value of the plurality of preset time points into a pressure difference input vector and an outlet dust concentration input vector according to the time dimension respectively;
Correlating the pressure difference input vector with the outlet dust concentration input vector to obtain an operation state monitoring parameter correlation matrix;
the operation state monitoring parameter association matrix is subjected to a convolution neural network model of which the adjacent layers use convolution kernels which are transposed to obtain a classification characteristic matrix;
performing geometric order based on parameterization features on the classification feature matrix to obtain an optimized classification feature matrix;
and the optimized classification characteristic matrix passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the running state of the bag-type dust collector is normal or not.
In the above method for monitoring an operation state of a bag-type dust collector, the associating the pressure difference input vector with the outlet dust concentration input vector to obtain an operation state monitoring parameter association matrix includes: calculating the operation state monitoring parameter correlation matrix between the pressure difference input vector and the outlet dust concentration input vector according to the following correlation coding formula; wherein, the association coding formula is:
wherein V is a Representing the input vector of the pressure difference,a transpose vector representing the pressure differential input vector, V b Representing the output dust concentration input vector, M representing the operating state monitoring parameter correlation matrix,>representing vector multiplication.
In the above method for monitoring the operation state of a bag-type dust collector, the step of obtaining the classification feature matrix by using a convolution neural network model of mutually transposed convolution kernels through adjacent layers includes: each layer of the convolution neural network model, which uses convolution kernels transposed to each other, of the adjacent layers respectively performs input data in forward transfer of the layers: performing convolution processing, pooling processing and nonlinear processing on the input data based on a first two-dimensional convolution kernel to obtain a first activation feature map; performing convolution processing, pooling processing and nonlinear activation processing based on a second two-dimensional convolution kernel on the first activation feature map to obtain a second activation feature map, wherein the first two-dimensional convolution kernel and the second two-dimensional convolution kernel are transposed with each other; the input of the first layer of the convolution neural network model of which the adjacent layers use the convolution kernels which are transposed with each other is the running state monitoring parameter association matrix, and the output of the last layer of the convolution neural network model of which the adjacent layers use the convolution kernels which are transposed with each other is the classification feature matrix.
In the above method for monitoring an operation state of a bag-type dust collector, the performing geometric order based on parameterized features on the classification feature matrix to obtain an optimized classification feature matrix includes: constructing parameterized coding vectors of all positions in the classification feature matrix to obtain a plurality of pixel position parameterized coding vectors, wherein the parameterized coding vectors comprise coordinates, gradient values along the X-axis direction, gradient values along the Y-axis direction and feature values; passing the plurality of pixel position parameterized encoding vectors through a full-connection layer-based parameterized feature extractor to obtain a plurality of pixel position parameterized encoding feature vectors; calculating cosine similarity between any two pixel position parameterized coding feature vectors in the plurality of pixel position parameterized coding feature vectors to obtain an ordered geometric topology matrix; passing the ordered geometric topological matrix through a geometric topological feature extractor based on a convolution layer to obtain an ordered geometric topological feature matrix; and fusing the classification characteristic matrix and the ordered geometric topological characteristic matrix to obtain the optimized classification characteristic matrix.
In the above method for monitoring the operation state of a bag-type dust collector, the step of passing the optimized classification feature matrix through a classifier to obtain a classification result, where the classification result is used to indicate whether the operation state of the bag-type dust collector is normal, includes: expanding the optimized classification feature matrix into classification feature vectors according to row vectors or column vectors; performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain full-connection coding feature vectors; inputting the fully-connected coding feature vector into a Softmax classification function of the classifier to obtain probability values of the classification feature matrix belonging to various classification labels, wherein the classification labels comprise a rule for indicating that the running state of the bag-type dust collector is normal and a rule for indicating that the running state of the bag-type dust collector is abnormal; and determining the classification label corresponding to the maximum probability value as the classification result.
According to still another aspect of the present application, there is provided an electronic apparatus including: a processor; and a memory in which computer program instructions are stored which, when executed by the processor, cause the processor to perform the method of monitoring the operational status of a bag-type dust collector as described above.
According to a further aspect of the present application there is provided a computer readable medium having stored thereon computer program instructions which, when executed by a processor, cause the processor to perform the method of monitoring the operational status of a bag house dust collector as described above.
Compared with the prior art, the running state monitoring system and method of the bag-type dust collector provided by the application are used for judging the running state of the bag-type dust collector by extracting the characteristics of the inlet and outlet pressure differences and the outlet dust concentration of the bag-type dust collector, correlating the extracted characteristics and classifying the extracted characteristics through the classifier. Therefore, the real-time monitoring of the running state can be realized, and when the abnormal running state is found, maintenance and adjustment measures are timely taken to ensure the normal running and the high-efficiency dust removing effect of the bag-type dust remover.
Drawings
The above and other objects, features and advantages of the present application will become more apparent by describing embodiments of the present application in more detail with reference to the attached 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 together with the embodiments of the application, do not limit the application. In the drawings, like reference numerals generally refer to like parts or steps.
Fig. 1 is a system block diagram of an operational status monitoring system of a bag-type dust collector according to an embodiment of the application.
Fig. 2 is a block diagram of an operation state monitoring system of a bag-type dust collector according to an embodiment of the present application.
Fig. 3 is a block diagram of an optimization module in a system for monitoring the operational status of a bag-type dust collector according to an embodiment of the application.
Fig. 4 is a block diagram of an operation state result generation module in the operation state monitoring system of the bag-type dust collector according to the embodiment of the present application.
Fig. 5 is a flowchart of a method of monitoring an operational status of a bag-type dust collector according to an embodiment of the present application.
Fig. 6 is a block diagram of an electronic device according to an embodiment of the application.
Detailed Description
Hereinafter, exemplary 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 embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.
Exemplary System
Fig. 1 is a system block diagram of an operational status monitoring system of a bag-type dust collector according to an embodiment of the application. As shown in fig. 1, in an operation state monitoring system 100 of a bag-type dust collector, it includes: an operation data obtaining module 110, configured to obtain inlet and outlet pressure differences and outlet dust concentration values of the bag-type dust collector at a plurality of predetermined time points within a predetermined time period; an operation data structuring module 120, configured to arrange the inlet and outlet pressure differences and the outlet dust concentration values at the plurality of predetermined time points into a pressure difference input vector and an outlet dust concentration input vector according to a time dimension, respectively; the correlation module 130 is configured to correlate the pressure difference input vector and the outlet dust concentration input vector to obtain an operation state monitoring parameter correlation matrix; the running state data coding module 140 is configured to obtain a classification feature matrix by using a convolutional neural network model of a mutually transposed convolutional kernel through an adjacent layer by using the running state monitoring parameter association matrix; an optimization module 150, configured to perform geometric order based on parameterized features on the classification feature matrix to obtain an optimized classification feature matrix; and the running state result generating module 160 is configured to pass the optimized classification feature matrix through a classifier to obtain a classification result, where the classification result is used to indicate whether the running state of the bag-type dust collector is normal.
Fig. 2 is a block diagram of an operation state monitoring system of a bag-type dust collector according to an embodiment of the present application. In this configuration, as shown in fig. 2, first, inlet and outlet pressure differences and outlet dust concentration values of the bag house at a plurality of predetermined time points within a predetermined period of time are acquired. And then, arranging the inlet and outlet pressure difference values and the outlet dust concentration value of the plurality of preset time points into a pressure difference input vector and an outlet dust concentration input vector according to the time dimension respectively. And then, correlating the pressure difference input vector with the outlet dust concentration input vector to obtain an operation state monitoring parameter correlation matrix. And further, the operation state monitoring parameter association matrix is obtained through a convolution neural network model of which adjacent layers use convolution kernels which are transposed with each other. Then, the classification feature matrix is subjected to geometric order based on parameterized features to obtain an optimized classification feature matrix. And finally, the optimized classification characteristic matrix passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the running state of the bag-type dust collector is normal or not.
In the operation state monitoring system 100 of the bag-type dust collector, the operation data acquisition module 110 is configured to acquire inlet and outlet pressure differences and outlet dust concentration values of the bag-type dust collector at a plurality of predetermined time points within a predetermined time period.
As described above in the background art, the bag-type dust collector is a key dust removing device commonly used in industrial production, and is used for efficiently removing dust and particulate matters in air. Dust and particulate matter may have serious effects on the working environment and product quality, and thus dust removal-related operations are required. In order to ensure the effective operation and performance of the bag-type dust collector, the operation state monitoring of the bag-type dust collector is important. Therefore, an operational status monitoring scheme for a bag house is desired.
In recent years, deep learning and neural networks have been widely used in the fields of computer vision, natural language processing, text signal processing, and the like. In addition, deep learning and neural networks have also shown levels approaching and even exceeding humans in the fields of image classification, object detection, semantic segmentation, text translation, and the like. The development of deep learning and neural networks provides a new solution idea and scheme for monitoring the running state of the bag-type dust collector.
Specifically, in the technical scheme of the application, firstly, inlet and outlet pressure difference values and outlet dust concentration values of the bag-type dust collector at a plurality of preset time points in a preset time period are obtained. It should be appreciated that the inlet-outlet pressure differential is an important indicator of the performance of a bag house. The working principle of the bag-type dust collector is that dust particles are deposited through the flowing of air flow, and the pressure difference is an index for measuring the resistance of the air flow passing through the bag-type dust collector. If the pressure difference is too large, the situation that the bag-type dust collector is blocked may be indicated, and the working effect of the dust collector is affected. Thus, monitoring inlet-outlet pressure differences may provide information regarding the operational anomalies of the precipitator. The outlet dust concentration value is an index for evaluating the dust removing effect of the dust remover. The lower the outlet dust concentration value is, the better the dust removing effect of the dust remover is. Through monitoring the outlet dust concentration value, whether the dust removal effect of the dust remover reaches the requirement can be judged, so that the dust remover is helped to judge whether the operation of the dust remover is abnormal. The inlet and outlet pressure difference values of the bag-type dust collector at a plurality of preset time points in a preset time period can be obtained by collecting data through pressure sensors arranged at the inlet and the outlet of the bag-type dust collector and performing difference operation, and the outlet dust concentration values of the bag-type dust collector at a plurality of preset time points in the preset time period can be obtained by collecting data through dust concentration sensors.
In the operation state monitoring system 100 of the bag-type dust collector, the operation data structuring module 120 is configured to arrange the inlet-outlet pressure differences and the outlet dust concentration values at the plurality of predetermined time points into a pressure difference input vector and an outlet dust concentration input vector according to a time dimension, respectively. The operation state of the bag-type dust collector is usually changed along with time, and the inlet and outlet pressure difference values and the outlet dust concentration values at different time points can reflect different operation states. By arranging these data in the time dimension, they can be input into the model as part of a time series. The arrangement of the time series data may provide information about the pattern and trend of the operating state over time. For example, if the bag house is operating normally, the inlet and outlet pressure differences may fluctuate over a relatively stable range, while the outlet dust concentration value may be kept low. In contrast, if the operating conditions of the bag house are abnormal, abnormal fluctuations or significant increases in inlet and outlet pressure differences and outlet dust concentration values may occur.
In the operation state monitoring system 100 of the bag-type dust collector, the correlation module 130 is configured to correlate the pressure difference input vector with the outlet dust concentration input vector to obtain an operation state monitoring parameter correlation matrix. The pressure difference and the outlet dust concentration are two important indexes in the monitoring of the running state of the bag-type dust collector. The pressure difference reflects the air flow condition inside the dust remover, and the concentration of the outlet dust reflects the dust removing effect. There may be a certain correlation between these two indicators, for example, when the pressure difference increases, the outlet dust concentration may increase, indicating that the performance of the dust collector decreases. By correlating the pressure differential input vector with the outlet dust concentration input vector, their information can be combined to form a more comprehensive operating condition monitoring parameter correlation matrix. The matrix can reflect the relation and the change trend among different parameters, so that a more comprehensive operation state monitoring result is provided.
Specifically, in the operation state monitoring system 100 of the bag-type dust collector, the association module 130 is configured to: calculating the operation state monitoring parameter correlation matrix between the pressure difference input vector and the outlet dust concentration input vector according to the following correlation coding formula; wherein, the association coding formula is:
wherein V is a Representing the input vector of the pressure difference,a transpose vector representing the pressure differential input vector, V b Representing the output dust concentration input vector, M representing the operating state monitoring parameter correlation matrix,>representing vector multiplication.
In the operation state monitoring system 100 of the bag-type dust collector, the operation state data encoding module 140 is configured to obtain the classification feature matrix by using a convolution neural network model with mutually transposed convolution kernels through adjacent layers. It should be appreciated by those of ordinary skill in the art that convolutional neural networks perform well in feature extraction. The convolution layer is one of the most important layers of the convolution neural network, local characteristics of input data are extracted by carrying out convolution operation on the input data and a group of learnable convolution kernels, and the convolution operation is carried out on the input data in a sliding window mode to generate a series of characteristic diagrams; the pooling layer is used for downsampling the feature map, so that the dimension of the feature map is reduced and main features can be reserved; the activation function is an important component in convolutional neural networks, and by introducing nonlinear transformation, the expression capacity of the network and the capacity of fitting complex functions are enhanced. The method can effectively extract local features through convolution operation, and performs feature dimension reduction and abstraction through pooling operation. While the transpose operation of the convolution kernel may be used to upsample the input to achieve feature expansion and refinement. In the operation state monitoring of the bag-type dust collector, the operation state monitoring parameter association matrix is input into a convolutional neural network model, so that the local feature extraction can be performed on the matrix by using convolutional operation. By using mutually transposed convolution kernels, features can be expanded and refined at different levels, thereby extracting a richer and distinguishable representation of the features.
Specifically, in the operation state monitoring system 100 of the bag-type dust collector, the operation state data encoding module 140 is configured to: each layer of the convolution neural network model, which uses convolution kernels transposed to each other, of the adjacent layers respectively performs input data in forward transfer of the layers: performing convolution processing, pooling processing and nonlinear processing on the input data based on a first two-dimensional convolution kernel to obtain a first activation feature map; performing convolution processing, pooling processing and nonlinear activation processing based on a second two-dimensional convolution kernel on the first activation feature map to obtain a second activation feature map, wherein the first two-dimensional convolution kernel and the second two-dimensional convolution kernel are transposed with each other; the input of the first layer of the convolution neural network model of which the adjacent layers use the convolution kernels which are transposed with each other is the running state monitoring parameter association matrix, and the output of the last layer of the convolution neural network model of which the adjacent layers use the convolution kernels which are transposed with each other is the classification feature matrix.
In the technical scheme of the application, because the classification characteristic matrix is obtained through a specific coding mode, a specific data structure and an internal rule exist in the data structure of the classification characteristic matrix, namely, the parameterized characteristics of the classification characteristic matrix form an ordered structure according to a certain rule. Thus, if the geometric ordering of the parameterized features of the classification feature matrix can be exploited, the feature representation of the classification feature matrix can be optimized.
In the system 100 for monitoring the operation state of a bag-type dust collector, the optimizing module 150 is configured to perform geometric order based on parameterized features on the classification feature matrix to obtain an optimized classification feature matrix.
Fig. 3 is a block diagram of an optimization module in a system for monitoring the operational status of a bag-type dust collector according to an embodiment of the application. As shown in fig. 3, the optimizing module 150 includes: a parameterized encoding vector construction unit 151 configured to construct parameterized encoding vectors of respective positions in the classification feature matrix to obtain a plurality of pixel position parameterized encoding vectors, where the parameterized encoding vectors include coordinates, gradient values along an X-axis direction, gradient values along a Y-axis direction, and feature values; a parameterized feature extraction unit 152, configured to pass the plurality of pixel location parameterized encoding vectors through a full-link layer-based parameterized feature extractor to obtain a plurality of pixel location parameterized encoding feature vectors; a cosine similarity calculating unit 153, configured to calculate cosine similarity between any two pixel position parameterized encoding feature vectors in the plurality of pixel position parameterized encoding feature vectors to obtain an ordered geometric topology matrix; a geometric feature extraction unit 154 for passing the ordered geometric feature matrix through a convolution layer based geometric feature extractor to obtain an ordered geometric feature matrix; and a fusion unit 155, configured to fuse the classification feature matrix and the ordered geometric topology feature matrix to obtain the optimized classification feature matrix.
It should be understood that in the technical solution of the present application, the parameterized encoding vector of each position in the classification feature matrix is configured to obtain a plurality of pixel position parameterized encoding vectors, where the parameterized encoding vectors include coordinates, gradient values along the X-axis direction, gradient values along the Y-axis direction, and feature values. The plurality of pixel position parameterized encoding vectors are then passed through a full-link layer based parameterized feature extractor to obtain a plurality of pixel position parameterized encoding feature vectors, i.e., full-link encoding is utilized to capture implicit information of the parametric features at each position in the classification feature matrix. Further, the cosine similarity between any two pixel position parameterized encoding feature vectors in the plurality of pixel position parameterized encoding feature vectors is calculated to obtain an ordered geometric topology matrix, that is, the geometric ordered feature value of the parameterized feature is represented by the cosine similarity between the pixel position parameterized encoding feature vectors. Further, the ordered geometric topology matrix is passed through a convolutional layer-based geometric topology feature extractor to obtain an ordered geometric topology feature matrix, i.e., the ordered geometric topology features implied in the ordered geometric topology matrix are captured with convolutional encoding. And fusing the classification feature matrix and the ordered geometric feature matrix to obtain the optimized classification feature matrix, for example, multiplying the ordered geometric feature matrix and the classification feature matrix by a matrix, and mapping the classification feature matrix into a feature space of the ordered geometric feature matrix to obtain the optimized classification feature matrix.
In this way, the classification feature matrix is subjected to geometric order based on parameterization features so as to arrange the classification feature matrix into an ordered structure according to a certain rule, so that the expression capacity and classification effect of the classification feature matrix are improved. Meanwhile, the classification feature matrix can be more compact and effective through geometric order based on parameterization features, and the accuracy and the efficiency of classification tasks are improved.
In the operation state monitoring system 100 of the bag-type dust collector, the operation state result generating module 160 is configured to pass the optimized classification feature matrix through a classifier to obtain a classification result, where the classification result is used to indicate whether the operation state of the bag-type dust collector is normal. The classifier is used as a machine learning model, and can be analyzed and judged according to input data, and the classifier is mapped to different categories. And inputting the optimized classification characteristic matrix into the trained classifier to obtain a classification result for indicating whether the running state of the bag-type dust collector is normal. Based on the classification result, the operation state of the bag-type dust collector can be quickly known. Therefore, the bag-type dust collector can be monitored in real time, and when the abnormal operation of the bag-type dust collector is found, maintenance and cleaning measures are timely taken so as to ensure the normal operation and efficient operation of the bag-type dust collector.
Fig. 4 is a block diagram of an operation state result generation module in the operation state monitoring system of the bag-type dust collector according to the embodiment of the present application. As shown in fig. 4, the operation state result generating module 160 includes: a developing unit 161, configured to develop the optimized classification feature matrix into classification feature vectors according to row vectors or column vectors; a full-connection unit 162, configured to perform full-connection encoding on the classification feature vector by using a full-connection layer of the classifier to obtain a full-connection encoded feature vector; a probability unit 163, configured to input the fully-connected encoding feature vector into a Softmax classification function of the classifier to obtain probability values of the classification feature matrix belonging to each classification label, where the classification labels include a rule for indicating that the operation state of the bag-type dust collector is normal and a rule for indicating that the operation state of the bag-type dust collector is abnormal; and a classification unit 164, configured to determine a classification label corresponding to the largest probability value as the classification result.
In summary, the operation state monitoring system 100 of the bag-type dust collector according to the embodiment of the application is illustrated, and the operation state of the bag-type dust collector is determined by extracting features of the inlet-outlet pressure difference and the outlet dust concentration of the bag-type dust collector, correlating the extracted features and classifying the features by a classifier. Therefore, the real-time monitoring of the running state can be realized, and when the abnormal running state is found, maintenance and adjustment measures are timely taken to ensure the normal running and the high-efficiency dust removing effect of the bag-type dust remover.
As described above, the operation state monitoring system 100 of the bag-type dust collector according to the embodiment of the present application may be implemented in various terminal devices, for example, a server for operation state monitoring of the bag-type dust collector, or the like. In one example, the operational status monitoring system 100 of a bag house according to an embodiment of the present application may be integrated into the terminal device as a software module and/or a hardware module. For example, the operational status monitoring system 100 of the bag house may be a software module in the operating system of the terminal device or may be an application developed for the terminal device; of course, the bag house operation status monitoring system 100 may also be one of a plurality of hardware modules of the terminal device.
Alternatively, in another example, the operation state monitoring system 100 of the bag-type dust collector and the terminal device may be separate devices, and the operation state monitoring system 100 of the bag-type dust collector may be connected to the terminal device through a wired and/or wireless network and transmit the interactive information in a agreed data format.
Exemplary method
Fig. 5 is a flowchart of a method of monitoring an operational status of a bag-type dust collector according to an embodiment of the present application. As shown in fig. 5, in the method for monitoring the operation state of the bag-type dust collector, the method includes: s110, acquiring inlet and outlet pressure difference values and outlet dust concentration values of the bag-type dust collector at a plurality of preset time points in a preset time period; s120, arranging inlet and outlet pressure difference values and outlet dust concentration values of the plurality of preset time points into a pressure difference input vector and an outlet dust concentration input vector according to time dimensions respectively; s130, correlating the pressure difference input vector with the outlet dust concentration input vector to obtain an operation state monitoring parameter correlation matrix; s140, the operation state monitoring parameter association matrix is obtained through a convolution neural network model of which adjacent layers use convolution kernels which are transposed with each other; s150, carrying out geometric order based on parameterization features on the classification feature matrix to obtain an optimized classification feature matrix; and S160, the optimized classification feature matrix passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the running state of the bag-type dust collector is normal or not.
Here, it will be understood by those skilled in the art that the specific operations of the respective steps in the above-described operation state monitoring method of the bag-type dust collector have been described in detail in the above description of the operation state monitoring system of the bag-type dust collector with reference to fig. 1 to 4, and thus, repetitive descriptions thereof will be omitted.
In summary, the method for monitoring the operation state of the bag-type dust collector according to the embodiment of the application is explained, wherein the operation state of the bag-type dust collector is judged by extracting the characteristics of the inlet-outlet pressure difference and the outlet dust concentration of the bag-type dust collector, correlating the extracted characteristics and classifying the extracted characteristics by a classifier. Therefore, the real-time monitoring of the running state can be realized, and when the abnormal running state is found, maintenance and adjustment measures are timely taken to ensure the normal running and the high-efficiency dust removing effect of the bag-type dust remover.
Exemplary electronic device
Next, an electronic device according to an embodiment of the present application is described with reference to fig. 6.
Fig. 6 is a block diagram of an electronic device according to an embodiment of the application.
As shown in fig. 6, the electronic device 10 includes one or more processors 11 and a memory 12.
The processor 11 may be a Central Processing Unit (CPU) or other form of processing unit having data processing and/or instruction execution capabilities, and may control other components in the electronic device 10 to perform desired functions.
Memory 12 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, random Access Memory (RAM) and/or cache memory (cache), and the like. The non-volatile memory may include, for example, read Only Memory (ROM), hard disk, flash memory, and the like. One or more computer program instructions may be stored on the computer readable storage medium that may be executed by the processor 11 to implement the method of monitoring the operational status of a bag house and/or other desired functions of the various embodiments of the present application described above. Various contents such as inlet and outlet pressure differences and outlet dust concentration values of the bag-type dust collector at a plurality of predetermined time points within a predetermined period of time may also be stored in the computer-readable storage medium.
In one example, the electronic device 10 may further include: an input device 13 and an output device 14, which are interconnected by a bus system and/or other forms of connection mechanisms (not shown).
The input means 13 may comprise, for example, a keyboard, a mouse, etc.
The output device 14 can output various information to the outside, including a result of judging whether the operation state of the bag-type dust collector is normal or not, and the like. The output means 14 may include, for example, a display, speakers, a printer, and a communication network and remote output devices connected thereto, etc.
Of course, only some of the components of the electronic device 10 that are relevant to the present application are shown in fig. 6 for simplicity, components such as buses, input/output interfaces, etc. are omitted. In addition, the electronic device 10 may include any other suitable components depending on the particular application.
Exemplary computer program product and computer readable storage Medium
In addition to the methods and apparatus described above, embodiments of the application may also be a computer program product comprising computer program instructions which, when executed by a processor, cause the processor to perform the steps in the method of monitoring the operational status of a bag-type dust collector according to various embodiments of the application described in the "exemplary methods" section of this specification.
The computer program product may write program code for performing operations of embodiments of the present application in any combination of one or more programming languages, including an object oriented programming language such as Java, C++ or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computing device, partly on the user's device, as a stand-alone software package, partly on the user's computing device, partly on a remote computing device, or entirely on the remote computing device or server.
Furthermore, embodiments of the present application may also be a computer-readable storage medium, having stored thereon computer program instructions, which when executed by a processor, cause the processor to perform the steps in the method for monitoring the operation status of a bag-type dust collector according to various embodiments of the present application described in the "exemplary method" section of the present specification.
The computer readable storage medium may employ any combination of one or more readable media. The readable medium may be a readable signal medium or a readable storage medium. The readable storage medium may include, for example, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or a combination of any of the foregoing. More specific examples (a non-exhaustive list) of the readable storage medium would include the following: an electrical connection having one or more wires, a portable disk, a hard disk, random Access Memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
Claims (10)
1. An operational status monitoring system for a bag-type dust collector, comprising:
The operation data acquisition module is used for acquiring inlet and outlet pressure difference values and outlet dust concentration values of the bag-type dust collector at a plurality of preset time points in a preset time period;
the operation data structuring module is used for respectively arranging the inlet and outlet pressure difference values and the outlet dust concentration value of the plurality of preset time points into a pressure difference input vector and an outlet dust concentration input vector according to the time dimension;
the association module is used for associating the pressure difference input vector with the outlet dust concentration input vector to obtain an operation state monitoring parameter association matrix;
the running state data coding module is used for enabling the running state monitoring parameter association matrix to obtain a classification characteristic matrix through a convolution neural network model of which adjacent layers use convolution kernels which are transposed with each other;
the optimizing module is used for carrying out geometric order based on parameterization features on the classification feature matrix to obtain an optimized classification feature matrix;
and the running state result generation module is used for enabling the optimized classification feature matrix to pass through a classifier to obtain a classification result, and the classification result is used for indicating whether the running state of the bag-type dust collector is normal or not.
2. The system for monitoring the operation state of a bag-type dust collector according to claim 1, wherein the association module is configured to: calculating the operation state monitoring parameter correlation matrix between the pressure difference input vector and the outlet dust concentration input vector according to the following correlation coding formula;
Wherein, the association coding formula is:
wherein V is a Representing the input vector of the pressure difference,a transpose vector representing the pressure differential input vector, V b Representing the output dust concentration input vector, M representing the operating state monitoring parameter correlation matrix,>representing vector multiplication.
3. The system for monitoring the operation state of the bag-type dust collector according to claim 2, wherein the operation state data encoding module is configured to: each layer of the convolution neural network model, which uses convolution kernels transposed to each other, of the adjacent layers respectively performs input data in forward transfer of the layers:
performing convolution processing, pooling processing and nonlinear processing on the input data based on a first two-dimensional convolution kernel to obtain a first activation feature map;
performing convolution processing, pooling processing and nonlinear activation processing based on a second two-dimensional convolution kernel on the first activation feature map to obtain a second activation feature map, wherein the first two-dimensional convolution kernel and the second two-dimensional convolution kernel are transposed with each other;
the input of the first layer of the convolution neural network model of which the adjacent layers use the convolution kernels which are transposed with each other is the running state monitoring parameter association matrix, and the output of the last layer of the convolution neural network model of which the adjacent layers use the convolution kernels which are transposed with each other is the classification feature matrix.
4. The system for monitoring the operation state of a bag-type dust collector according to claim 3, wherein the optimizing module comprises:
a parameterized coding vector construction unit, configured to construct parameterized coding vectors of each position in the classification feature matrix to obtain a plurality of pixel position parameterized coding vectors, where the parameterized coding vectors include coordinates, gradient values along an X-axis direction, gradient values along a Y-axis direction, and feature values;
a parameterized feature extraction unit, configured to pass the plurality of pixel position parameterized encoding vectors through a full-connection layer-based parameterized feature extractor to obtain a plurality of pixel position parameterized encoding feature vectors;
the cosine similarity calculation unit is used for calculating cosine similarity between any two pixel position parameterized coding feature vectors in the plurality of pixel position parameterized coding feature vectors to obtain an ordered geometric topology matrix;
a geometric topological feature extraction unit, which is used for passing the ordered geometric topological matrix through a geometric topological feature extractor based on a convolution layer to obtain an ordered geometric topological feature matrix;
and the fusion unit is used for fusing the classification characteristic matrix and the ordered geometric topological characteristic matrix to obtain the optimized classification characteristic matrix.
5. The system for monitoring the operation state of the bag-type dust collector according to claim 4, wherein the operation state result generating module comprises:
the unfolding unit is used for unfolding the optimized classification feature matrix into classification feature vectors according to row vectors or column vectors;
the full-connection unit is used for carrying out full-connection coding on the classification feature vectors by using a full-connection layer of the classifier so as to obtain full-connection coding feature vectors;
the probability unit is used for inputting the fully-connected coding feature vector into a Softmax classification function of the classifier to obtain probability values of the classification feature matrix belonging to various classification labels, wherein the classification labels comprise a rule for indicating that the running state of the bag-type dust collector is normal and a rule for indicating that the running state of the bag-type dust collector is abnormal;
and the classification unit is used for determining the classification label corresponding to the maximum probability value as the classification result.
6. The method for monitoring the running state of the bag-type dust collector is characterized by comprising the following steps of:
acquiring inlet and outlet pressure difference values and outlet dust concentration values of the bag-type dust collector at a plurality of preset time points in a preset time period;
arranging the inlet and outlet pressure difference values and the outlet dust concentration value of the plurality of preset time points into a pressure difference input vector and an outlet dust concentration input vector according to the time dimension respectively;
Correlating the pressure difference input vector with the outlet dust concentration input vector to obtain an operation state monitoring parameter correlation matrix;
the operation state monitoring parameter association matrix is subjected to a convolution neural network model of which the adjacent layers use convolution kernels which are transposed to obtain a classification characteristic matrix;
performing geometric order based on parameterization features on the classification feature matrix to obtain an optimized classification feature matrix;
and the optimized classification characteristic matrix passes through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the running state of the bag-type dust collector is normal or not.
7. The method of claim 6, wherein correlating the pressure differential input vector and the outlet dust concentration input vector to obtain an operational status monitoring parameter correlation matrix comprises: calculating the operation state monitoring parameter correlation matrix between the pressure difference input vector and the outlet dust concentration input vector according to the following correlation coding formula;
wherein, the association coding formula is:
wherein V is a Representing the input vector of the pressure difference,a transpose vector representing the pressure differential input vector, V b Representing the output dust concentration input vector, M representing the operating state monitoring parameter correlation matrix,>representing vector multiplication.
8. The method for monitoring the operation state of the bag-type dust collector according to claim 7, wherein the step of obtaining the classification feature matrix by using the convolution neural network model of the mutually transposed convolution kernels through the adjacent layers comprises the steps of: each layer of the convolution neural network model, which uses convolution kernels transposed to each other, of the adjacent layers respectively performs input data in forward transfer of the layers:
performing convolution processing, pooling processing and nonlinear processing on the input data based on a first two-dimensional convolution kernel to obtain a first activation feature map;
performing convolution processing, pooling processing and nonlinear activation processing based on a second two-dimensional convolution kernel on the first activation feature map to obtain a second activation feature map, wherein the first two-dimensional convolution kernel and the second two-dimensional convolution kernel are transposed with each other;
the input of the first layer of the convolution neural network model of which the adjacent layers use the convolution kernels which are transposed with each other is the running state monitoring parameter association matrix, and the output of the last layer of the convolution neural network model of which the adjacent layers use the convolution kernels which are transposed with each other is the classification feature matrix.
9. The method of claim 8, wherein the classifying feature matrix is geometrically ordered based on parameterized features to obtain an optimized classifying feature matrix, comprising:
constructing parameterized coding vectors of all positions in the classification feature matrix to obtain a plurality of pixel position parameterized coding vectors, wherein the parameterized coding vectors comprise coordinates, gradient values along the X-axis direction, gradient values along the Y-axis direction and feature values;
passing the plurality of pixel position parameterized encoding vectors through a full-connection layer-based parameterized feature extractor to obtain a plurality of pixel position parameterized encoding feature vectors;
calculating cosine similarity between any two pixel position parameterized coding feature vectors in the plurality of pixel position parameterized coding feature vectors to obtain an ordered geometric topology matrix;
passing the ordered geometric topological matrix through a geometric topological feature extractor based on a convolution layer to obtain an ordered geometric topological feature matrix;
and fusing the classification characteristic matrix and the ordered geometric topological characteristic matrix to obtain the optimized classification characteristic matrix.
10. The method for monitoring the operation state of the bag-type dust collector according to claim 9, wherein the step of passing the optimized classification feature matrix through a classifier to obtain a classification result, wherein the classification result is used for indicating whether the operation state of the bag-type dust collector is normal or not comprises the steps of:
expanding the optimized classification feature matrix into classification feature vectors according to row vectors or column vectors;
performing full-connection coding on the classification feature vectors by using a full-connection layer of the classifier to obtain full-connection coding feature vectors;
inputting the fully-connected coding feature vector into a Softmax classification function of the classifier to obtain probability values of the classification feature matrix belonging to various classification labels, wherein the classification labels comprise a rule for indicating that the running state of the bag-type dust collector is normal and a rule for indicating that the running state of the bag-type dust collector is abnormal;
and determining the classification label corresponding to the maximum probability value as the classification result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311438949.5A CN117225091A (en) | 2023-10-30 | 2023-10-30 | System and method for monitoring running state of bag-type dust collector |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311438949.5A CN117225091A (en) | 2023-10-30 | 2023-10-30 | System and method for monitoring running state of bag-type dust collector |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117225091A true CN117225091A (en) | 2023-12-15 |
Family
ID=89092948
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311438949.5A Pending CN117225091A (en) | 2023-10-30 | 2023-10-30 | System and method for monitoring running state of bag-type dust collector |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117225091A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117848713A (en) * | 2024-01-05 | 2024-04-09 | 湖州槐坎南方水泥有限公司 | System and method for monitoring running state of pulse valve of bag-type dust collector |
| CN117848713B (en) * | 2024-01-05 | 2024-07-09 | 湖州槐坎南方水泥有限公司 | System and method for monitoring running state of pulse valve of bag-type dust collector |
-
2023
- 2023-10-30 CN CN202311438949.5A patent/CN117225091A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117848713A (en) * | 2024-01-05 | 2024-04-09 | 湖州槐坎南方水泥有限公司 | System and method for monitoring running state of pulse valve of bag-type dust collector |
| CN117848713B (en) * | 2024-01-05 | 2024-07-09 | 湖州槐坎南方水泥有限公司 | System and method for monitoring running state of pulse valve of bag-type dust collector |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Choi et al. | Graph neural controlled differential equations for traffic forecasting | |
| US10996664B2 (en) | Predictive classification of future operations | |
| CN116247824B (en) | Control method and system for power equipment | |
| CN115834433B (en) | Data processing method and system based on Internet of things technology | |
| CN112036435A (en) | Brushless direct current motor sensor fault detection method based on convolutional neural network | |
| CN115783923A (en) | Elevator fault mode identification system based on big data | |
| CN116797533B (en) | Appearance defect detection method and system for power adapter | |
| CN117156442B (en) | Cloud data security protection method and system based on 5G network | |
| CN116992226A (en) | Water pump motor fault detection method and system | |
| CN115324843A (en) | Wind generating set fault diagnosis system and method based on monitoring data | |
| CN117061322A (en) | Internet of things flow pool management method and system | |
| CN117269644A (en) | Line fault monitoring system and method for current transformer | |
| CN117784710B (en) | Remote state monitoring system and method for numerical control machine tool | |
| CN115731513A (en) | Intelligent park management system based on digital twin | |
| CN117104377A (en) | Intelligent management system and method for electric bicycle | |
| Li et al. | NDNet: Spacewise multiscale representation learning via neighbor decoupling for real-time driving scene parsing | |
| CN116402777B (en) | Power equipment detection method and system based on machine vision | |
| CN116844088A (en) | Online dust remover control system and method thereof | |
| Zhang et al. | Novel dynamic enhanced robust principal subspace discriminant analysis for high-dimensional process fault diagnosis with industrial applications | |
| CN117168861A (en) | Abnormality monitoring method and abnormality monitoring system for sewage treatment equipment | |
| CN117274689A (en) | Detection method and system for detecting defects of packaging box | |
| CN117225091A (en) | System and method for monitoring running state of bag-type dust collector | |
| CN111340139A (en) | Method and device for judging complexity of image content | |
| CN115143128B (en) | Fault diagnosis method and system for small-sized submersible electric pump | |
| CN116205927A (en) | Image segmentation method based on boundary enhancement |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication |