CN113945569A - Ion membrane fault detection method and device - Google Patents
Ion membrane fault detection method and device Download PDFInfo
- Publication number
- CN113945569A CN113945569A CN202111163342.1A CN202111163342A CN113945569A CN 113945569 A CN113945569 A CN 113945569A CN 202111163342 A CN202111163342 A CN 202111163342A CN 113945569 A CN113945569 A CN 113945569A
- Authority
- CN
- China
- Prior art keywords
- model
- ionic membrane
- image
- membrane
- training
- 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.)
- Granted
Links
- 239000012528 membrane Substances 0.000 title claims abstract description 255
- 238000001514 detection method Methods 0.000 title claims abstract description 123
- 238000012549 training Methods 0.000 claims abstract description 95
- 238000000034 method Methods 0.000 claims abstract description 47
- 239000001257 hydrogen Substances 0.000 claims abstract description 37
- 229910052739 hydrogen Inorganic materials 0.000 claims abstract description 37
- 238000004519 manufacturing process Methods 0.000 claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 37
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 claims abstract description 36
- 238000012360 testing method Methods 0.000 claims abstract description 34
- 238000012795 verification Methods 0.000 claims abstract description 34
- 238000002372 labelling Methods 0.000 claims abstract description 25
- 238000013508 migration Methods 0.000 claims abstract description 13
- 230000005012 migration Effects 0.000 claims abstract description 13
- 238000003062 neural network model Methods 0.000 claims abstract description 10
- 230000006870 function Effects 0.000 claims description 28
- 230000004913 activation Effects 0.000 claims description 21
- 238000010606 normalization Methods 0.000 claims description 20
- 238000003860 storage Methods 0.000 claims description 20
- 238000013526 transfer learning Methods 0.000 claims description 20
- 238000007781 pre-processing Methods 0.000 claims description 12
- 239000013598 vector Substances 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 5
- 230000007797 corrosion Effects 0.000 claims description 5
- 238000005260 corrosion Methods 0.000 claims description 5
- 238000005336 cracking Methods 0.000 claims description 5
- 230000008021 deposition Effects 0.000 claims description 5
- 230000035515 penetration Effects 0.000 claims description 5
- 238000013527 convolutional neural network Methods 0.000 abstract description 16
- 150000002500 ions Chemical class 0.000 description 98
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 230000008569 process Effects 0.000 description 7
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 3
- 230000008901 benefit Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 239000001301 oxygen Substances 0.000 description 3
- 229910052760 oxygen Inorganic materials 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000005034 decoration Methods 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000005868 electrolysis reaction Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 150000001450 anions Chemical class 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 238000005341 cation exchange Methods 0.000 description 1
- 150000001768 cations Chemical class 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 230000007850 degeneration Effects 0.000 description 1
- 238000006731 degradation reaction Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 150000002431 hydrogen Chemical class 0.000 description 1
- 239000003014 ion exchange membrane Substances 0.000 description 1
- 238000012821 model calculation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 229910001868 water Inorganic materials 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Chemical & Material Sciences (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Separation Using Semi-Permeable Membranes (AREA)
Abstract
The invention discloses a fault detection method and device for an ionic membrane. Wherein, the method comprises the following steps: acquiring an ionic membrane image set, wherein the ionic membrane image set comprises a plurality of ionic membranes with different fault categories; labeling the ion membrane image set based on the fault category to obtain a labeled data set, wherein the labeled data set comprises: a training set, a verification set and a test set; training a target residual error network model by adopting the labeled data set to obtain an ionic membrane fault detection model, wherein the target residual error network model is a neural network model obtained by natural image characteristic migration; and detecting whether the ionic membrane of the hydrogen production equipment breaks down or not by adopting the ionic membrane fault detection model to obtain a fault detection result. The invention solves the technical problems that the existing ion membrane fault detection method based on the convolutional neural network model is easy to generate overfitting and cannot give consideration to both the detection processing speed and the detection accuracy rate in the prior art.
Description
Technical Field
The invention relates to the field of ionic membrane detection, in particular to a fault detection method and device for an ionic membrane.
Background
The membrane cell electrolysis method is a method of separating an electrolysis product by dividing a cell into an anode chamber and a cathode chamber by a cation exchange membrane. The ion exchange membrane has the characteristic of selective permeation to anions and cations, ions with one charge are allowed to pass through, and ions with the opposite charge are limited to pass through, so that the purpose of separating hydrogen, oxygen and water is achieved, but in the actual production process, the early warning is given when the oxygen content in hydrogen production storage exceeds 2%, and explosion occurs when the oxygen content exceeds 4%, so that purposefully, the ion membrane fault detection is an important link.
In the prior art, fault detection is performed on an ionic membrane, usually by acquiring the real-time state of the ionic membrane of a hydrogen production device, extracting video frames from a historical detection image library and a shot video to form an image set, and preprocessing the image set, however, the above prior solutions have the following problems in the process of using the prior deep learning based on a convolutional neural network: 1) as shown in table 1 below, due to too many model parameters, it is easy to generate overfitting if the training data set is limited; the larger the network is, the more the parameters are, the higher the calculation complexity is, and the difficulty in application is high; the deeper the network is, the more the gradient dispersion problem is easy to occur (i.e. the more backward the gradient is, the more the gradient is easy to disappear), and the model is difficult to optimize.
TABLE 1
2) The ion membrane images of the hydrogen production equipment have various failure modes, the differences among the ion membrane images are sometimes quite obvious, the differences among some failures are not quite large, especially for a diagnostic image shot by the same image means, the failure image combination mode is not spliced completely in a symmetrical mode, the image intervals are different after splicing, in addition, the acquisition of a data set is difficult, and professionals are required to label the acquired data. Therefore, the labeling cost of the data set of the multi-label learning task is high, and the labeled data size is too small, so that overfitting is easily caused by the huge parameters of the feature learning model, and the advantage of feature learning cannot be fully exerted.
In view of the above problems, no effective solution has been proposed.
Disclosure of Invention
The embodiment of the invention provides a fault detection method and device for an ionic membrane, and at least solves the technical problems that in the prior art, an existing ionic membrane fault detection method based on a convolutional neural network model is easy to generate overfitting, and the detection processing speed and the detection accuracy rate cannot be taken into consideration.
According to an aspect of an embodiment of the present invention, there is provided a method of detecting a failure of an ionic membrane, including: acquiring an ionic membrane image set, wherein the ionic membrane image set comprises a plurality of ionic membranes with different fault categories; labeling the ion membrane image set based on the fault category to obtain a labeled data set, wherein the labeled data set comprises: a training set, a verification set and a test set; training a target residual error network model by adopting the labeled data set to obtain an ionic membrane fault detection model, wherein the target residual error network model is a neural network model obtained by natural image characteristic migration; and detecting whether the ionic membrane of the hydrogen production equipment breaks down or not by adopting the ionic membrane fault detection model to obtain a fault detection result.
Optionally, acquiring an ionic membrane image set, comprising: acquiring a historical ionic membrane image and a current ionic membrane image, wherein the historical ionic membrane image is an ionic membrane image in a historical detection image library, and the current ionic membrane image is an ionic membrane image obtained by currently shooting an ionic membrane in the hydrogen production equipment; and obtaining the ionic membrane image set based on the historical ionic membrane image and the current ionic membrane image.
Optionally, before performing labeling processing on the ion membrane image set based on the fault category to obtain a labeled data set, the method further includes: scaling all the ion membrane images in the ion membrane image set to obtain all the adjusted ion membrane images; adding a category label to all of the adjusted ion membrane images, wherein the category label is used for indicating the fault category, and the fault category includes at least one of the following: deformation, shedding, cracking, waviness, corrosion, deposition, fouling, penetration, foreign body piercing.
Optionally, before performing labeling processing on the ion membrane image set based on the fault category to obtain a labeled data set, the method further includes: performing data preprocessing on all the ion membrane images in the ion membrane image set to obtain preprocessed ion membrane images; wherein, the data preprocessing is used for processing missing values and abnormal values in the ion membrane image; and extracting an image characteristic value from the preprocessed ion membrane image to obtain an image characteristic vector.
Optionally, after performing labeling processing on the ion membrane image set based on the fault category to obtain a labeled data set, the method further includes: acquiring the data processing requirement of the target residual error network model; based on the data processing requirement, the labeled data set of a first scale is used as the training set, the labeled data set of a second scale is used as the verification set, and the labeled data set of a third scale is used as the test set, wherein the first scale is larger than the second scale and the third scale.
Optionally, before training the target residual error network model by using the labeled data set to obtain the ion membrane fault detection model, the method further includes: building an initial residual error network model; and transferring the natural image features of the natural image set training model to the initial residual error network model to obtain the target residual error network model.
Optionally, the network structure of the initial residual error network model is vector convolution Conv1-Batch Normalization algorithm-linear rectification ReLU1 activation function and Conv2-Batch Normalization algorithm-ReLU 2 activation function; the convolution layer of the target residual error network model adopts 3 × 3 convolution kernels, the network structure of the target residual error network model is Conv1-Batch Normalization algorithm-ReLU 1 activation function and Conv2-Batch Normalization algorithm-ReLU 2 activation function, in addition, Conv3-Batch Normalization algorithm-ReLU 3 activation function is added at the shortcut connection position in the target residual error network model, the output of the previous layer in the target residual error network model is used as the input of the convolution layer at the shortcut connection position, and the first output of the Conv1, the second output of the Conv2 and the third output of the Conv3 are used as the input of the next training stage.
Optionally, the number of convolution kernels in the Conv1-10 convolution layer in the target residual error network model is 64, the number of convolution kernels in the Conv11-22 convolution layer is 128, the number of convolution kernels in the Conv23-34 convolution layer is 256, and the number of convolution kernels in the Conv35-40 convolution layer is 512.
Optionally, training the target residual error network model by using the labeled data set to obtain an ionic membrane fault detection model includes: inputting all image data in the labeled data set to the target residual error network model for learning to obtain a transfer learning model; importing the training set into the transfer learning model for training so as to update model parameters of the transfer learning model to obtain a training model; importing the verification set into the training model for training so as to adjust model parameters of the training model to obtain a verification model; and importing the test set into the verification model for testing to obtain the ionic membrane fault detection model.
Optionally, the ion membrane fault detection module is used to detect whether the ion membrane of the hydrogen production equipment has a fault, so as to obtain a fault detection result, and the fault detection result includes: and detecting the test set by adopting the ionic membrane fault detection model to determine whether the ionic membrane of the hydrogen production equipment has a fault or not and obtain the fault detection result.
According to another aspect of the embodiments of the present invention, there is also provided an apparatus for detecting a failure of an ionic membrane, including: the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring an ionic membrane image set, and the ionic membrane image set comprises a plurality of ionic membranes with different fault types; a labeling module, configured to perform labeling processing on the ionic membrane image set based on the fault category to obtain a labeled data set, where the labeled data set includes: a training set, a verification set and a test set; the training module is used for training a target residual error network model by adopting the labeled data set to obtain an ionic membrane fault detection model, wherein the target residual error network model is a neural network model obtained by natural image characteristic migration; and the detection module is used for detecting whether the ionic membrane of the hydrogen production equipment fails by adopting the ionic membrane fault detection model to obtain a fault detection result.
According to another aspect of the embodiments of the present invention, there is also provided a non-volatile storage medium, wherein the non-volatile storage medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor and executing any one of the above ion membrane fault detection methods.
According to another aspect of the embodiments of the present invention, there is also provided an electronic device, including a memory and a processor, where the memory stores a computer program, and the processor is configured to execute the computer program to perform any one of the above-mentioned ion membrane fault detection methods.
According to another aspect of the embodiments of the present invention, there is also provided a processor, configured to execute a program, where the program is configured to execute any one of the above-mentioned ion membrane fault detection methods when executed.
In the embodiment of the invention, an ion membrane image set is obtained, wherein the ion membrane image set comprises a plurality of ion membranes with different fault types; labeling the ion membrane image set based on the fault category to obtain a labeled data set, wherein the labeled data set comprises: a training set, a verification set and a test set; training a target residual error network model by adopting the labeled data set to obtain an ionic membrane fault detection model, wherein the target residual error network model is a neural network model obtained by natural image characteristic migration; whether the ionic membrane of the hydrogen production equipment breaks down or not is detected by adopting the ionic membrane fault detection model, a fault detection result is obtained, the technical effects of avoiding the over-fitting phenomenon in the ionic membrane fault detection process and considering the detection processing speed and the detection accuracy are achieved, so that the accurate prevention and control management of the hydrogen production equipment in the hydrogen production process is guaranteed, and the technical problems that the over-fitting is easily generated and the detection processing speed and the detection accuracy cannot be considered by using the existing ionic membrane fault detection method based on the convolutional neural network model in the prior art are solved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this application, illustrate embodiment(s) of the invention and together with the description serve to explain the invention without limiting the invention. In the drawings:
FIG. 1 is a flow chart of a method of fault detection of an ionic membrane according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a residual block structure of an alternative initial residual network model according to an embodiment of the present invention;
FIG. 3 is a block diagram of an alternative target residual network model according to an embodiment of the present invention;
FIG. 4 is a schematic diagram of a network structure of an alternative target residual network model according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a fault detection device for an ionic membrane according to an embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
First, in order to facilitate understanding of the embodiments of the present invention, some terms or nouns referred to in the present invention will be explained as follows:
the Convolutional Neural Network (CNN) is a kind of feedforward Neural Network containing convolution calculation and having a deep structure, is one of representative algorithms for deep learning, has a characteristic learning capability, can automatically learn the feature expression of pixel data of an original image in a large number of training samples, does not depend on manual design features, and can obtain a feature description better than the original data expression capability. A new CNN image classification model with high classification precision and good robustness needs a data set with rich classes and large sample size to train the model. Because the network weight parameters of the pre-trained CNN model are fully trained on a large data set, the migration learning method can discover the characteristics and the structure of the two regions which are related to each other and different from each other and have no change in the field, and the data of the target domain is directly migrated and multiplexed by using the rich label data which are different in the auxiliary domain and related.
The residual network ResNet, the structure of which is proposed by Microsoft research institute, has extremely high accuracy of computer vision detection, and has lower parameter number than VGGNet and GoogleNet, and the effect is very outstanding. The ResNet structure can accelerate the training of the neural network very fast, the accuracy of the model is greatly improved, and the ResNet model is superior to a common network structure in the aspects of convergence performance, classification performance, network correspondence and the like. The main innovation of the ResNet model is that the model 'degeneration' problem is found, a residual structure is introduced according to the problem, the residual structure directly transmits the result of the previous layer to the next layer of network, so that after the model is further deepened, the error at least needs to be kept consistent and cannot be increased continuously, and the ResNet model can have more model layers and higher accuracy.
With the increase of the depth of the model, the difference between the model precision and the common network is gradually opened, the problem of model performance degradation under the depth condition is solved to a certain extent, and the performance of each task in the computer vision field is greatly improved in the later development.
Example 1
In accordance with an embodiment of the present invention, there is provided an embodiment of a method for fault detection of an ionic membrane, where the steps illustrated in the flowchart of the figure may be performed in a computer system, such as a set of computer executable instructions, and where a logical order is illustrated in the flowchart, in some cases the steps illustrated or described may be performed in an order different than that presented herein.
Fig. 1 is a flowchart of a method for detecting a failure of an ionic membrane according to an embodiment of the present invention, as shown in fig. 1, the method including the steps of:
step S102, an ion membrane image set is obtained, wherein the ion membrane image set comprises a plurality of ion membranes with different fault types;
step S104, performing labeling processing on the ionic membrane image set based on the fault type to obtain a labeled data set, wherein the labeled data set comprises: a training set, a verification set and a test set;
step S106, training a target residual error network model by adopting the labeled data set to obtain an ionic membrane fault detection model, wherein the target residual error network model is a neural network model obtained by natural image characteristic migration;
and S108, detecting whether the ionic membrane of the hydrogen production equipment fails by adopting the ionic membrane fault detection model to obtain a fault detection result.
In the embodiment of the invention, an ion membrane image set is obtained, wherein the ion membrane image set comprises a plurality of ion membranes with different fault types; labeling the ion membrane image set based on the fault category to obtain a labeled data set, wherein the labeled data set comprises: a training set, a verification set and a test set; training a target residual error network model by adopting the labeled data set to obtain an ionic membrane fault detection model, wherein the target residual error network model is a neural network model obtained by natural image characteristic migration; whether the ionic membrane of the hydrogen production equipment breaks down or not is detected by adopting the ionic membrane fault detection model, a fault detection result is obtained, the technical effects of avoiding the over-fitting phenomenon in the ionic membrane fault detection process and considering the detection processing speed and the detection accuracy are achieved, so that the accurate prevention and control management of the hydrogen production equipment in the hydrogen production process is guaranteed, and the technical problems that the over-fitting is easily generated and the detection processing speed and the detection accuracy cannot be considered by using the existing ionic membrane fault detection method based on the convolutional neural network model in the prior art are solved.
In the embodiment of the application, on the basis of the existing residual error network ResNet structure, the hydrogen production equipment ionic membrane fault detection method based on the ResNet structure with the improved staggered block structure and the transfer learning method is provided, and the method has important significance for accurate prevention and control management in the hydrogen production process.
It should be noted that, in the embodiment of the present application, the target residual error network model learns general features of the images in the general field by using a migration learning method, and can alleviate the problem of model overfitting caused by the too small scale of the field of the ion membrane images of the hydrogen production equipment. For example, the initial residual error network model is trained by using a large-scale natural image, general features (such as color, texture, shape and the like) of the natural image are transferred to the field of the hydrogen production equipment ion membrane to obtain a target residual error network model, and the multi-label classification performance can be effectively improved by using local information of labeled object classes in the image.
Optionally, in the embodiment of the present application, an ion membrane image set may be generated based on a historical detection image library and a real-time taken high-definition photograph, and a label is added to the ion membrane image set according to a detection report of the ion membrane; for example, the detection report of the ionic membrane is classified into fault detection, and different fault categories are counted as the labeled data set B.
After the image preprocessing is completed, dividing an annotation data set B into a training set B1, a verification set B2 and a test set B3 according to the data processing requirements of a target residual network model (namely, an improved ResNet CNN structure); inputting all image data in the labeled data set B into a target residual error network model for learning to obtain a target residual error network model, namely a transfer learning model M; importing the training set B1 into the transfer learning model M for training so as to update the model parameters of the transfer learning model to obtain a training model M1; introducing the verification set B2 into the training model for training to adjust model parameters of the training model M1 to obtain a verification model M2; the test set M3 is introduced into the verification model M2 for testing to obtain the ion membrane fault detection model, and the ion membrane fault detection model M2 can be used for fault detection of the ion membrane.
Optionally, in this embodiment of the present application, the target residual network model ResNet uses a 3 × 3 convolution kernel mode, and a large convolution kernel is replaced with a plurality of small convolution kernels, so that model parameters can be reduced, the number of nonlinear activation functions is increased, and the model calculation amount is reduced. However, small stacking of convolution kernels increases the depth of the model, makes training of the model difficult, and increases training time. The embodiment of the application provides an improved ResNet structure model, combines a characteristic diagram in a network structure, reduces the layer number of the network, removes redundant connection, simplifies the network structure, and accordingly reduces the training time of the network; adding convolution layers in the quick connection to form a new type of residual block, combining different types of residual blocks and improving the learning capacity of the whole network structure; the number of convolution kernels in part of convolution layers is increased, and the capability of extracting features of the network structure is improved.
In the embodiment of the application, the idea of transfer learning is adopted, and the problem of overfitting of a small sample is converted into the problem of training and adjusting parameters of the existing model through transferring a mature ResNet model, so that the speed of image recognition is greatly increased. In an alternative embodiment of the present application, the experimental results shown in the following tables 2 and 3 indicate that the improved ResNet model of the present application is a compact and efficient network structure, and has the advantage of simple training on the premise of completing the detection task, that is, the average accuracy of fault detection is higher and the average time consumption is less.
TABLE 2
TABLE 3
In an alternative embodiment, acquiring a set of ion membrane images comprises:
step S202, acquiring a historical ionic membrane image and a current ionic membrane image;
and step S204, obtaining the ion membrane image set based on the historical ion membrane image and the current ion membrane image.
In the embodiment of the present application, the historical ion membrane image is an ion membrane image in a historical detection image library, and the current ion membrane image is an ion membrane image obtained by currently shooting an ion membrane in the hydrogen production equipment. The ion membrane image set can be obtained by acquiring a historical ion membrane image in a historical detection image library and a current ion membrane image shot in real time.
In an optional embodiment, before performing labeling processing on the set of ion membrane images based on the fault category to obtain a labeled data set, the method further includes:
step S302, scaling all the ion membrane images in the ion membrane image set to obtain all the adjusted ion membrane images;
step S304, adding a category label to all the adjusted ion membrane images, wherein the category label is used for indicating the fault category, and the fault category includes at least one of the following: deformation, shedding, cracking, waviness, corrosion, deposition, fouling, penetration, foreign body piercing.
In the embodiment of the present application, the picture size of the ion membrane image in the obtained ion membrane image set is adjusted, for example, all the ion membrane images are scaled to have a shortest side length of 1024 pixels, so as to obtain an adjusted ion membrane image. Adding a category label to all the adjusted ion membrane images, wherein the category label is used for indicating the fault category, and the fault category includes at least one of the following: deformation, shedding, cracking, waviness, corrosion, deposition, fouling, penetration, foreign body piercing.
As an optional embodiment, after class labels are added to the adjusted ion membrane images, the ion membrane image sets to which the labels are added to the target residual error network model, the adjusted ion membrane images are read and converted into Python voice numpy arrays, and the Python voice numpy arrays and the corresponding class labels thereof are fed into the target residual error network model.
In an optional embodiment, before performing labeling processing on the set of ion membrane images based on the fault category to obtain a labeled data set, the method further includes:
step S402, performing data preprocessing on all the ion membrane images in the ion membrane image set to obtain preprocessed ion membrane images; wherein, the data preprocessing is used for processing missing values and abnormal values in the ion membrane image;
and S404, extracting an image characteristic value from the preprocessed ionic membrane image to obtain an image characteristic vector.
Optionally, by performing data preprocessing on all the ion membrane images in the ion membrane image set, missing values and abnormal values of the ion membrane images can be processed, and image characteristic values and characteristic vectors are extracted.
In an optional embodiment, after performing labeling processing on the set of ion membrane images based on the fault category to obtain a labeled data set, the method further includes:
step S502, acquiring the data processing requirement of the target residual error network model;
step S504 is performed to use the labeled data set with a first ratio as the training set, the labeled data set with a second ratio as the verification set, and the labeled data set with a third ratio as the test set based on the data processing requirement, wherein the first ratio is greater than the second ratio and the third ratio.
Optionally, in the embodiment of the present application, 70% of the labeled data set B may be randomly used as the training set B1, 15% of the labeled data set B may be used as the verification set B2, and the remaining 15% of the labeled data set B may be used as the test set B3.
In an optional embodiment, before training the target residual error network model using the labeled data set to obtain an ionic membrane fault detection model, the method further includes:
step S602, building an initial residual error network model;
and step S604, transferring the natural image features of the natural image set training model to the initial residual error network model to obtain the target residual error network model.
In the above optional embodiment, the target residual error network model is obtained by building an initial residual error network model, and migrating the natural image features of the natural image set training model to the initial residual error network model, i.e., training the initial residual error network model using large-scale natural images.
Through the embodiments of the application, general features (such as color, texture, shape and the like) of a natural image are transferred to the field of the hydrogen production equipment ion membrane to obtain a target residual error network model, and the multi-label classification performance can be effectively improved by using local information of labeled object classes in the image.
In an alternative embodiment, the network structure of the initial residual network model is vector convolution Conv1-Batch Normalization algorithm-linear rectification ReLU1 activation function and Conv2-Batch Normalization algorithm-ReLU 2 activation function; the convolution layer of the target residual error network model adopts 3 × 3 convolution kernels, the network structure of the target residual error network model is Conv1-Batch Normalization algorithm-ReLU 1 activation function and Conv2-Batch Normalization algorithm-ReLU 2 activation function, in addition, Conv3-Batch Normalization algorithm-ReLU 3 activation function is added at the shortcut connection position in the target residual error network model, the output of the previous layer in the target residual error network model is used as the input of the convolution layer at the shortcut connection position, and the first output of the Conv1, the second output of the Conv2 and the third output of the Conv3 are used as the input of the next training stage.
As shown in fig. 2 and fig. 3, the network structure of the initial residual network model (original ResNet parameter block model) is Conv1-Batch Normalization algorithm-ReLU 1 activation function-Conv 2-Batch Normalization algorithm-ReLU 2 activation function, the network structure of the target residual network model (improved ResNet parameter block model) is Conv1-Batch Normalization algorithm-ReLU 1 activation function-Conv 2-Batch Normalization algorithm-ReLU 2 activation function, and the Conv3-Batch Normalization algorithm-ReLU 3 activation function is added at the shortcut connection, the output of the previous layer is used as the input of the convolution layer at the shortcut connection, and the output of Conv1 and Conv2 and the output of the connection line shortcut Conv3 are used as the input of the next stage.
By the embodiment of the application, the technical problems of too few samples, long time consumption for model training, low model precision and the like in ionic membrane research of hydrogen production equipment can be solved, an improved ResNet CNN structure is used, the improved ResNet CNN model combines an original residual block and an improved residual block, and the whole improved ResNet CNN structure does not need more data volume and preprocessing process and can also have higher detection accuracy and higher processing speed.
Compared with an original ResNet CNN structure, the convolutional neural network has the advantages that the structural design is important, and intuitively, the deeper the hierarchical structure of the convolutional neural network is, the more nodes are, and the stronger feature expression capability is realized. The individual detection is carried out by using the network structures such as AlexNet and GoogleNet with less network layers, and the accuracy is relatively low. The ResNet model with a large number of network layers is used for detection, the training time is long, and therefore a balance needs to be made between the detection accuracy and the training time.
The idea of the improved model in the embodiment of the application is that the number of layers of the network is reduced by combining the characteristic diagram in the network structure, redundant connection is removed, the network structure is simplified, and therefore the training time of the network is reduced; adding convolution layers in the quick connection to form a new type of residual block, combining different types of residual blocks and improving the learning capacity of the whole network structure; the number of convolution kernels in part of convolution layers is increased, and the capability of extracting features of the network structure is improved.
In an alternative embodiment, the number of convolution kernels in the Conv1-10 convolutional layers in the target residual network model is 64, the number of convolution kernels in the Conv11-22 convolutional layers is 128, the number of convolution kernels in the Conv23-34 convolutional layers is 256, and the number of convolution kernels in the Conv35-40 convolutional layers is 512.
As shown in fig. 4, in the embodiment of the present application, 7 improved ResNet models and 9 original ResNet models are used. In order to enhance the feature expression capability of the improved ResNet model, the number of convolution kernels in a part of convolution layers is increased. The number of convolution kernels in the Conv1-10 convolutional layers was 64, the number of convolution kernels in the Conv11-22 convolutional layers was increased to 128, the number of convolution kernels in the Conv23-34 convolutional layers was increased to 256, and the number of convolution kernels in the Conv35-40 convolutional layers was increased to 512.
Utilize improved generation ResNet parameter block to increase swift connection through this application embodiment, make up out a neotype parameter block structure, let the gradient grow, avoid the gradient disappearance problem to produce, the gradient grow means that the study convergence speed is fast moreover, can accelerate training speed greatly, has improved ionic membrane fault detection efficiency.
In an alternative embodiment, training the target residual error network model using the labeled data set to obtain an ionic membrane fault detection model includes:
step S702, inputting all image data in the labeled data set into the target residual error network model for learning to obtain a transfer learning model;
step S704, importing the training set into the transfer learning model for training so as to update model parameters of the transfer learning model to obtain a training model;
step S706, importing the verification set into the training model for training so as to adjust model parameters of the training model to obtain a verification model;
step S708, importing the test set into the verification model for testing to obtain the ion membrane fault detection model.
In the above embodiment of the present application, all image data in the labeled data set B are input to the initial residual error network model for learning, so as to obtain the target residual error network model, i.e. a migration learning model M; importing the training set B1 into the transfer learning model M for training so as to update the model parameters of the transfer learning model to obtain a training model M1; introducing the verification set B2 into the training model for training to adjust model parameters of the training model M1 to obtain a verification model M2; the test set M3 is introduced into the verification model M2 for testing to obtain the ion membrane fault detection model, and the ion membrane fault detection model M2 can be used for fault detection of the ion membrane.
In an alternative embodiment, the detecting module for detecting ion membrane failure of hydrogen production equipment using ion membrane failure described above is used to obtain a failure detection result, and includes:
and S802, detecting the test set by adopting the ionic membrane fault detection model to determine whether the ionic membrane of the hydrogen production equipment has a fault or not, and obtaining the fault detection result.
In the embodiment of the application, the ionic membrane fault detection result of the hydrogen production equipment can be obtained by testing the test set B3 by using the ionic membrane fault detection model M2.
According to the embodiment of the application, the improved ResNet model learning is carried out by utilizing the image set of ImageNet, the learning result is transferred to the ion membrane image recognition process of the hydrogen production equipment, the problem of small samples which are difficult to sample is solved by using the transfer learning concept, and the efficiency of the improved ResNet model is greatly improved.
Example 2
According to an embodiment of the present invention, there is also provided an embodiment of an apparatus for implementing the method for detecting a failure of an ionic membrane, fig. 5 is a schematic structural diagram of an apparatus for detecting a failure of an ionic membrane according to an embodiment of the present invention, and as shown in fig. 5, the apparatus for detecting a failure of an ionic membrane includes: an acquisition module 50, an annotation module 52, a training module 54, and a detection module 56, wherein:
an obtaining module 50, configured to obtain an ionic membrane image set, where the ionic membrane image set includes a plurality of ionic membranes with different fault categories; a labeling module 52, configured to perform labeling processing on the ionic membrane image set based on the fault category to obtain a labeled data set, where the labeled data set includes: a training set, a verification set and a test set; a training module 54, configured to train a target residual error network model by using the labeled data set to obtain an ionic membrane fault detection model, where the target residual error network model is a neural network model obtained by performing natural image feature migration; and the detection module 56 is used for detecting whether the ionic membrane of the hydrogen production equipment fails by adopting the ionic membrane fault detection model to obtain a fault detection result.
It should be noted that the above modules may be implemented by software or hardware, for example, for the latter, the following may be implemented: the modules can be located in the same processor; alternatively, the modules may be located in different processors in any combination.
It should be noted that the acquiring module 50, the labeling module 52, the training module 54, and the detecting module 56 correspond to steps S102 to S108 in embodiment 1, and the modules are the same as the corresponding steps in the implementation example and the application scenario, but are not limited to the disclosure in embodiment 1. It should be noted that the modules described above may be implemented in a computer terminal as part of an apparatus.
It should be noted that, reference may be made to the relevant description in embodiment 1 for alternative or preferred embodiments of this embodiment, and details are not described here again.
The above-mentioned fault detection device for ionic membrane may further include a processor and a memory, and the above-mentioned obtaining module 50, the labeling module 52, the training module 54, the detection module 56, and the like are all stored in the memory as program units, and the processor executes the above-mentioned program units stored in the memory to implement the corresponding functions.
The processor comprises a kernel, and the kernel calls a corresponding program unit from the memory, wherein one or more than one kernel can be arranged. The memory may include volatile memory in a computer readable medium, Random Access Memory (RAM) and/or nonvolatile memory such as Read Only Memory (ROM) or flash memory (flash RAM), and the memory includes at least one memory chip.
According to an embodiment of the present application, there is also provided an embodiment of a non-volatile storage medium. Optionally, in this embodiment, the nonvolatile storage medium includes a stored program, and the apparatus in which the nonvolatile storage medium is located is controlled to execute the any one of the ion membrane fault detection methods when the program runs.
Optionally, in this embodiment, the nonvolatile storage medium may be located in any one of a group of computer terminals in a computer network, or in any one of a group of mobile terminals, and the nonvolatile storage medium includes a stored program.
Optionally, the apparatus in which the non-volatile storage medium is controlled to perform the following functions when the program is executed: acquiring an ionic membrane image set, wherein the ionic membrane image set comprises a plurality of ionic membranes with different fault categories; labeling the ion membrane image set based on the fault category to obtain a labeled data set, wherein the labeled data set comprises: a training set, a verification set and a test set; training a target residual error network model by adopting the labeled data set to obtain an ionic membrane fault detection model, wherein the target residual error network model is a neural network model obtained by natural image characteristic migration; and detecting whether the ionic membrane of the hydrogen production equipment breaks down or not by adopting the ionic membrane fault detection model to obtain a fault detection result.
Optionally, the apparatus in which the non-volatile storage medium is controlled to perform the following functions when the program is executed: acquiring a historical ionic membrane image and a current ionic membrane image, wherein the historical ionic membrane image is an ionic membrane image in a historical detection image library, and the current ionic membrane image is an ionic membrane image obtained by currently shooting an ionic membrane in the hydrogen production equipment; and obtaining the ionic membrane image set based on the historical ionic membrane image and the current ionic membrane image.
Optionally, the apparatus in which the non-volatile storage medium is controlled to perform the following functions when the program is executed: scaling all the ion membrane images in the ion membrane image set to obtain all the adjusted ion membrane images; adding a category label to all of the adjusted ion membrane images, wherein the category label is used for indicating the fault category, and the fault category includes at least one of the following: deformation, shedding, cracking, waviness, corrosion, deposition, fouling, penetration, foreign body piercing.
Optionally, the apparatus in which the non-volatile storage medium is controlled to perform the following functions when the program is executed: performing data preprocessing on all the ion membrane images in the ion membrane image set to obtain preprocessed ion membrane images; wherein, the data preprocessing is used for processing missing values and abnormal values in the ion membrane image; and extracting an image characteristic value from the preprocessed ion membrane image to obtain an image characteristic vector.
Optionally, the apparatus in which the non-volatile storage medium is controlled to perform the following functions when the program is executed: acquiring the data processing requirement of the target residual error network model; based on the data processing requirement, the labeled data set of a first scale is used as the training set, the labeled data set of a second scale is used as the verification set, and the labeled data set of a third scale is used as the test set, wherein the first scale is larger than the second scale and the third scale.
Optionally, the apparatus in which the non-volatile storage medium is controlled to perform the following functions when the program is executed: building an initial residual error network model; and transferring the natural image features of the natural image set training model to the initial residual error network model to obtain the target residual error network model.
Optionally, the apparatus in which the non-volatile storage medium is controlled to perform the following functions when the program is executed: inputting all image data in the labeled data set to the target residual error network model for learning to obtain a transfer learning model; importing the training set into the transfer learning model for training so as to update model parameters of the transfer learning model to obtain a training model; importing the verification set into the training model for training so as to adjust model parameters of the training model to obtain a verification model; and importing the test set into the verification model for testing to obtain the ionic membrane fault detection model.
Optionally, the apparatus in which the non-volatile storage medium is controlled to perform the following functions when the program is executed: and detecting the test set by adopting the ionic membrane fault detection model to determine whether the ionic membrane of the hydrogen production equipment has a fault or not and obtain the fault detection result.
According to an embodiment of the present application, there is also provided an embodiment of a processor. Optionally, in this embodiment, the processor is configured to execute a program, where the program executes the method for detecting a fault of an ionic membrane.
According to an embodiment of the present application, there is further provided an embodiment of an electronic device, including a memory and a processor, where the memory stores a computer program, and the processor is configured to execute the computer program to perform any one of the above-mentioned ion membrane fault detection methods.
There is also provided, in accordance with an embodiment of the present application, an embodiment of a computer program product, which, when executed on a data processing device, is adapted to execute a program initializing a fault detection method step of an ionic membrane having any of the above.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the units may be a logical division, and in actual implementation, there may be another division, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable non-volatile storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a non-volatile storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned nonvolatile storage medium includes: a U-disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a removable hard disk, a magnetic or optical disk, and other various media capable of storing program codes.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that, for those skilled in the art, various modifications and decorations can be made without departing from the principle of the present invention, and these modifications and decorations should also be regarded as the protection scope of the present invention.
Claims (13)
1. A method of detecting a failure of an ionic membrane, comprising:
acquiring an ionic membrane image set, wherein the ionic membrane image set comprises a plurality of ionic membranes with different fault categories;
labeling the ion membrane image set based on the fault category to obtain a labeled data set, wherein the labeled data set comprises: a training set, a verification set and a test set;
training a target residual error network model by adopting the labeled data set to obtain an ionic membrane fault detection model, wherein the target residual error network model is a neural network model obtained by natural image characteristic migration;
and detecting whether the ionic membrane of the hydrogen production equipment breaks down or not by adopting the ionic membrane fault detection model to obtain a fault detection result.
2. The method of claim 1, wherein acquiring a set of ion membrane images comprises:
acquiring a historical ionic membrane image and a current ionic membrane image, wherein the historical ionic membrane image is an ionic membrane image in a historical detection image library, and the current ionic membrane image is an ionic membrane image obtained by currently shooting an ionic membrane in the hydrogen production equipment;
and obtaining the ionic membrane image set based on the historical ionic membrane image and the current ionic membrane image.
3. The method of claim 1, wherein prior to performing labeling processing on the set of ion membrane images based on the failure category to obtain a labeled data set, the method further comprises:
scaling all the ion membrane images in the ion membrane image set to obtain all the adjusted ion membrane images;
adding a class label to all of the adjusted ion membrane images, wherein the class label is used for indicating the fault class, and the fault class comprises at least one of the following: deformation, shedding, cracking, waviness, corrosion, deposition, fouling, penetration, foreign body piercing.
4. The method of claim 1, wherein prior to performing labeling processing on the set of ion membrane images based on the failure category to obtain a labeled data set, the method further comprises:
performing data preprocessing on all the ion membrane images in the ion membrane image set to obtain preprocessed ion membrane images; wherein the data preprocessing is used for processing missing values and abnormal values in the ion membrane image;
and extracting an image characteristic value from the preprocessed ion membrane image to obtain an image characteristic vector.
5. The method of claim 1, wherein after labeling the set of ion membrane images based on the failure category to obtain a labeled data set, the method further comprises:
acquiring the data processing requirement of the target residual error network model;
based on the data processing requirements, using a first proportion of the labeled data sets as the training set, a second proportion of the labeled data sets as the verification set, and a third proportion of the labeled data sets as the test set, wherein the first proportion is greater than the second proportion and the third proportion.
6. The method of claim 1, wherein prior to training a target residual network model using the annotated data set to arrive at an ionic membrane fault detection model, the method further comprises:
building an initial residual error network model;
and transferring the natural image characteristics of the natural image set training model to the initial residual error network model to obtain the target residual error network model.
7. The method of claim 6, wherein the network structure of the initial residual network model is vector convolution Conv1-Batch Normalization algorithm-linear rectification ReLU1 activation function and Conv2-Batch Normalization algorithm-ReLU 2 activation function; the convolution layer of the target residual error network model adopts 3-3 convolution kernels, the network structure of the target residual error network model is Conv1-Batch Normalization algorithm-ReLU 1 activation function and Conv2-Batch Normalization algorithm-ReLU 2 activation function, a Conv3-Batch Normalization algorithm-ReLU 3 activation function is added at a shortcut connection in the target residual error network model, the output of the previous layer in the target residual error network model is used as the input of the convolution layer at the shortcut connection, and the first output of the Conv1, the second output of the Conv2 and the third output of the Conv3 are used as the input of the next training stage.
8. The method of claim 6, wherein the number of convolution kernels in Conv1-10 convolutional layers, the number of convolution kernels in Conv11-22 convolutional layers, the number of convolution kernels in Conv23-34 convolutional layers, and the number of convolution kernels in Conv35-40 convolutional layers in the target residual network model is 64, 128, and 512.
9. The method of claim 1, wherein training a target residual network model using the annotated data set to obtain an ionic membrane fault detection model comprises:
inputting all image data in the labeled data set into the target residual error network model for learning to obtain a transfer learning model;
importing the training set into the transfer learning model for training so as to update model parameters of the transfer learning model to obtain a training model;
importing the verification set into the training model for training so as to adjust model parameters of the training model to obtain a verification model;
and importing the test set into the verification model for testing to obtain the ionic membrane fault detection model.
10. The method of claim 9, wherein the detecting whether the ionic membrane of the hydrogen production equipment has a fault by using the ionic membrane fault detection model to obtain a fault detection result comprises:
and detecting the test set by adopting the ionic membrane fault detection model to determine whether the ionic membrane of the hydrogen production equipment has a fault or not and obtain a fault detection result.
11. An apparatus for detecting a failure of an ionic membrane, comprising:
the system comprises an acquisition module, a processing module and a processing module, wherein the acquisition module is used for acquiring an ionic membrane image set, and the ionic membrane image set comprises a plurality of ionic membranes with different fault categories;
a labeling module, configured to label the ion membrane image set based on the fault category to obtain a labeled data set, where the labeled data set includes: a training set, a verification set and a test set;
the training module is used for training a target residual error network model by adopting the labeling data set to obtain an ionic membrane fault detection model, wherein the target residual error network model is a neural network model obtained by natural image characteristic migration;
and the detection module is used for detecting whether the ionic membrane of the hydrogen production equipment fails by adopting the ionic membrane fault detection model to obtain a fault detection result.
12. A non-volatile storage medium storing a plurality of instructions adapted to be loaded by a processor and to perform the method of ion membrane fault detection according to any one of claims 1 to 10.
13. An electronic device comprising a memory and a processor, wherein the memory has stored therein a computer program, and the processor is configured to execute the computer program to perform the method for detecting a failure of an ionic membrane according to any one of claims 1 to 10.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111163342.1A CN113945569B (en) | 2021-09-30 | 2021-09-30 | Fault detection method and device for ion membrane |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111163342.1A CN113945569B (en) | 2021-09-30 | 2021-09-30 | Fault detection method and device for ion membrane |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113945569A true CN113945569A (en) | 2022-01-18 |
| CN113945569B CN113945569B (en) | 2023-12-26 |
Family
ID=79329764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111163342.1A Active CN113945569B (en) | 2021-09-30 | 2021-09-30 | Fault detection method and device for ion membrane |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113945569B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108388890A (en) * | 2018-03-26 | 2018-08-10 | 南京邮电大学 | A kind of neonatal pain degree assessment method and system based on human facial expression recognition |
| CN108564123A (en) * | 2018-04-10 | 2018-09-21 | 复旦大学附属肿瘤医院 | A kind of Thyroid Neoplasms smear image classification method and its device |
| CN109299705A (en) * | 2018-10-24 | 2019-02-01 | 电子科技大学 | Rotary machinery fault diagnosis method based on one-dimensional depth residual error convolutional neural networks |
| CN109840593A (en) * | 2019-01-28 | 2019-06-04 | 华中科技大学鄂州工业技术研究院 | Diagnose the method and apparatus of solid oxide fuel battery system failure |
| CN110031226A (en) * | 2019-04-12 | 2019-07-19 | 佛山科学技术学院 | A kind of diagnostic method and device of bearing fault |
| CN110188720A (en) * | 2019-06-05 | 2019-08-30 | 上海云绅智能科技有限公司 | A kind of object detection method and system based on convolutional neural networks |
| CN110263692A (en) * | 2019-06-13 | 2019-09-20 | 北京数智源科技有限公司 | Container switch gate state identification method under large scene |
| CN110503154A (en) * | 2019-08-27 | 2019-11-26 | 携程计算机技术（上海）有限公司 | Method, system, electronic equipment and the storage medium of image classification |
| WO2019232830A1 (en) * | 2018-06-06 | 2019-12-12 | 平安科技（深圳）有限公司 | Method and device for detecting foreign object debris at airport, computer apparatus, and storage medium |
| CN110728654A (en) * | 2019-09-06 | 2020-01-24 | 台州学院 | Automatic pipeline detection and classification method based on deep residual error neural network |
| CN111310862A (en) * | 2020-03-27 | 2020-06-19 | 西安电子科技大学 | Deep neural network license plate positioning method based on image enhancement in complex environment |
| CN112418328A (en) * | 2020-11-25 | 2021-02-26 | 哈尔滨市科佳通用机电股份有限公司 | Deep learning-based drain outlet cover plate non-closing in-place fault detection method |
| CN113095420A (en) * | 2021-04-20 | 2021-07-09 | 池州学院 | Insulator fault detection method based on improved YOLOv3 |
-
2021
- 2021-09-30 CN CN202111163342.1A patent/CN113945569B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108388890A (en) * | 2018-03-26 | 2018-08-10 | 南京邮电大学 | A kind of neonatal pain degree assessment method and system based on human facial expression recognition |
| CN108564123A (en) * | 2018-04-10 | 2018-09-21 | 复旦大学附属肿瘤医院 | A kind of Thyroid Neoplasms smear image classification method and its device |
| WO2019232830A1 (en) * | 2018-06-06 | 2019-12-12 | 平安科技（深圳）有限公司 | Method and device for detecting foreign object debris at airport, computer apparatus, and storage medium |
| CN109299705A (en) * | 2018-10-24 | 2019-02-01 | 电子科技大学 | Rotary machinery fault diagnosis method based on one-dimensional depth residual error convolutional neural networks |
| CN109840593A (en) * | 2019-01-28 | 2019-06-04 | 华中科技大学鄂州工业技术研究院 | Diagnose the method and apparatus of solid oxide fuel battery system failure |
| CN110031226A (en) * | 2019-04-12 | 2019-07-19 | 佛山科学技术学院 | A kind of diagnostic method and device of bearing fault |
| CN110188720A (en) * | 2019-06-05 | 2019-08-30 | 上海云绅智能科技有限公司 | A kind of object detection method and system based on convolutional neural networks |
| CN110263692A (en) * | 2019-06-13 | 2019-09-20 | 北京数智源科技有限公司 | Container switch gate state identification method under large scene |
| CN110503154A (en) * | 2019-08-27 | 2019-11-26 | 携程计算机技术（上海）有限公司 | Method, system, electronic equipment and the storage medium of image classification |
| CN110728654A (en) * | 2019-09-06 | 2020-01-24 | 台州学院 | Automatic pipeline detection and classification method based on deep residual error neural network |
| CN111310862A (en) * | 2020-03-27 | 2020-06-19 | 西安电子科技大学 | Deep neural network license plate positioning method based on image enhancement in complex environment |
| CN112418328A (en) * | 2020-11-25 | 2021-02-26 | 哈尔滨市科佳通用机电股份有限公司 | Deep learning-based drain outlet cover plate non-closing in-place fault detection method |
| CN113095420A (en) * | 2021-04-20 | 2021-07-09 | 池州学院 | Insulator fault detection method based on improved YOLOv3 |
Non-Patent Citations (6)
| Title |
|---|
| 张涛,胡宁,胡友谱,李为民: "制氢工艺水碳比神经网络模型研究", 石油与天然气化工, no. 06 * |
| 成回中;: "基于数据融和的制氢设备故障诊断和监控系统", 实验室研究与探索, no. 12 * |
| 李玉峰;顾曼璇;赵亮;: "采用改进Faster R-CNN的遥感图像目标检测方法", 信号处理, no. 08 * |
| 毛冠通;洪流;王景霖;: "基于迁移学习的滚动轴承在线故障诊断", 航空科学技术, no. 01 * |
| 汪鹏;张奥帆;王利琴;董永峰;: "基于迁移学习与多标签平滑策略的图像自动标注", 计算机应用, no. 11 * |
| 董浩,钱积新,武培筠: "在线优化在离子膜氯碱生产中的应用", 化工学报, no. 01, pages 42 - 43 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113945569B (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110569721B (en) | Recognition model training method, image recognition method, device, equipment and medium | |
| CN110569814B (en) | Video category identification method, device, computer equipment and computer storage medium | |
| CN111091109B (en) | Method, system and equipment for predicting age and gender based on face image | |
| CN110163211B (en) | Image recognition method, device and storage medium | |
| CN111046550B (en) | Fuel cell voltage prediction system based on space-time characteristics | |
| CN107209864A (en) | Face identification method and system | |
| CN111079739A (en) | Multi-scale attention feature detection method | |
| CN113435269A (en) | Improved water surface floating object detection and identification method and system based on YOLOv3 | |
| CN116760583B (en) | Enhanced graph node behavior characterization and abnormal graph node detection method | |
| CN109271957B (en) | Face gender identification method and device | |
| CN114330499A (en) | Method, device, equipment, storage medium and program product for training classification model | |
| CN112148997B (en) | Training method and device for multi-modal countermeasure model for disaster event detection | |
| CN115390164A (en) | Radar echo extrapolation forecasting method and system | |
| CN114663392A (en) | Knowledge distillation-based industrial image defect detection method | |
| CN110363072A (en) | Tongue image recognition method, apparatus, computer equipment and computer readable storage medium | |
| CN112861659A (en) | Image model training method and device, electronic equipment and storage medium | |
| CN115240259A (en) | Face detection method and face detection system based on YOLO deep network in classroom environment | |
| CN114612414A (en) | Image processing method, model training method, device, equipment and storage medium | |
| CN113945569A (en) | Ion membrane fault detection method and device | |
| CN113327238A (en) | Gastroscope image classification model construction method and gastroscope image classification method | |
| CN108496174A (en) | method and system for face recognition | |
| CN115797291A (en) | Circuit terminal identification method and device, computer equipment and storage medium | |
| CN114596445A (en) | Method for improving fault diagnosis precision of oil production machine | |
| CN113537398A (en) | Color value evaluation model training method and component, and color value evaluation method and component | |
| CN112560599A (en) | Text recognition method and device, computer equipment and storage medium |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |