CN113191366A - Method and system for monitoring abnormality of electrolytic process - Google Patents
Method and system for monitoring abnormality of electrolytic process Download PDFInfo
- Publication number
- CN113191366A CN113191366A CN202110560557.0A CN202110560557A CN113191366A CN 113191366 A CN113191366 A CN 113191366A CN 202110560557 A CN202110560557 A CN 202110560557A CN 113191366 A CN113191366 A CN 113191366A
- Authority
- CN
- China
- Prior art keywords
- electrolytic
- electrolytic cell
- polar plate
- monitoring
- thermal image
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 108
- 238000012544 monitoring process Methods 0.000 title claims abstract description 61
- 230000008569 process Effects 0.000 title claims abstract description 54
- 230000005856 abnormality Effects 0.000 title claims abstract description 31
- 230000002159 abnormal effect Effects 0.000 claims abstract description 30
- 230000011218 segmentation Effects 0.000 claims abstract description 30
- 238000005868 electrolysis reaction Methods 0.000 claims abstract description 24
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 238000001931 thermography Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims abstract description 6
- 238000004364 calculation method Methods 0.000 claims description 15
- 239000003792 electrolyte Substances 0.000 claims description 13
- 238000003860 storage Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 7
- 238000011176 pooling Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000005096 rolling process Methods 0.000 claims description 3
- 230000009191 jumping Effects 0.000 claims description 2
- 238000007689 inspection Methods 0.000 abstract description 16
- 238000001514 detection method Methods 0.000 abstract description 14
- 239000002184 metal Substances 0.000 abstract description 11
- 238000004519 manufacturing process Methods 0.000 abstract description 10
- 230000006378 damage Effects 0.000 abstract description 7
- 210000004027 cell Anatomy 0.000 description 72
- 238000010586 diagram Methods 0.000 description 9
- 238000004891 communication Methods 0.000 description 5
- 238000003745 diagnosis Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 5
- CWYNVVGOOAEACU-UHFFFAOYSA-N Fe2+ Chemical compound [Fe+2] CWYNVVGOOAEACU-UHFFFAOYSA-N 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000007423 decrease Effects 0.000 description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 238000007726 management method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000001681 protective effect Effects 0.000 description 2
- 210000002421 cell wall Anatomy 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 230000003247 decreasing effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000010339 dilation Effects 0.000 description 1
- 238000011143 downstream manufacturing Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 238000011031 large-scale manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000011112 process operation Methods 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002588 toxic effect Effects 0.000 description 1
- 239000002341 toxic gas Substances 0.000 description 1
- 231100000563 toxic property Toxicity 0.000 description 1
- 231100000419 toxicity Toxicity 0.000 description 1
- 230000001988 toxicity Effects 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Investigating Or Analyzing Materials Using Thermal Means (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention provides a method and a system for monitoring electrolysis process abnormity, wherein the method comprises the following steps: obtaining a thermal image of the electrolytic cell; identifying the electrolytic cell and the polar plate in the thermal image based on a semantic segmentation network model, and carrying out temperature marking and position marking on the electrolytic cell and the polar plate; determining a polar plate with abnormal temperature in the electrolytic cell based on a target identification algorithm; the semantic segmentation network model is obtained by training a thermography sample of an electrolytic cell with a determined semantic label. The method and the system for monitoring the abnormality of the electrolytic process can realize automatic inspection of the abnormal condition of the electrode plate in the electrolytic production process, have high detection speed and high accuracy, realize complete machine automation of the abnormality monitoring of the electrolytic process, and greatly reduce the damage of manual inspection work to human bodies during metal electrolysis.
Description
Technical Field
The invention relates to the technical field of metal electrolysis, in particular to a method and a system for monitoring electrolysis process abnormity.
Background
In the non-ferrous metal electrolysis (refining) industry, in the metal electrolysis process, due to the influences of process operation conditions, physical specifications of a cathode and an anode and other factors, abnormal conditions such as short circuit or open circuit exist, so that the electric energy consumption is overlarge, the current efficiency is reduced, the yield and the quality are influenced, and the waste of electric power, manpower and time is caused.
In order to monitor the abnormity of short circuit, open circuit and the like, manual detection is generally adopted in the industry, namely manual detection is carried out one by using a handheld inspection instrument. However, manual detection is adopted, so that the detection and obstacle removal speed is low, the accuracy is low, the manual labor intensity is high, and the toxicity, the corrosivity and the like of the electrolyte can also hurt the human health. In addition, when the inspection is carried out manually, the detection accuracy, efficiency and the like are greatly influenced by the difference of working attitude, working state, working capacity and the like of workers.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a method and a system for monitoring the abnormality of an electrolysis process.
In a first aspect, the present invention provides a method for monitoring an abnormality in an electrolytic process, comprising:
obtaining a thermal image of the electrolytic cell;
identifying the electrolytic cell and the polar plate in the thermal image based on a semantic segmentation network model, and carrying out temperature marking and position marking on the electrolytic cell and the polar plate;
determining a polar plate with abnormal temperature in the electrolytic cell based on a target identification algorithm;
the semantic segmentation network model is obtained by training a thermography sample of an electrolytic cell with a determined semantic label.
Optionally, the semantic segmentation network model comprises an encoder, a decoder and a connection layer between the encoder and the decoder;
the encoder comprises 8 convolution layers, wherein each two convolution layers are a convolution block, the total number of the convolution blocks is 4, 1 multiplied by 5 convolution kernels are used in the convolution layers, the convolution blocks are connected through dense blocks, and downsampling is completed through a maximum pooling layer after the dense blocks;
the decoder comprises 4 rolling blocks, the up-sampling result is connected with the output of the sub-module with the same resolution in the encoder through jumping connection and is used as the input of the next sub-module in the decoder, and the output resolution of each sub-module in the decoder is sequentially increased through up-sampling operation until the output resolution is consistent with the resolution of the input image.
Optionally, the temperature marking and position marking of the electrolytic cell and the polar plate comprises:
and after the identified electrolytic bath and the identified polar plate are subjected to inclination compensation, temperature marking and position marking are carried out on the electrolytic bath and the polar plate.
Optionally, after the temperature marking and the position marking are carried out on the electrolytic bath and the polar plate, the method further comprises the following steps:
acquiring temperature values of different polar plate positions in each electrolytic tank;
and inputting the temperature values of different polar plate positions in each electrolytic tank and data monitored by the sensors into a state monitoring and early warning model, monitoring the electrolytic process in real time, and performing abnormal warning on the electrolytic process according to a warning rule.
Optionally, the sensors include an electrolyte wall side wall temperature sensor and an electrolyte level measurement sensor.
Optionally, the obtaining a thermography of the electrolytic cell comprises:
and acquiring a thermal image of the electrolytic cell acquired by the camera, wherein the camera is arranged on a fixed support or a movable slide rail above the electrolytic cell.
In a second aspect, the present invention further provides a system for monitoring abnormality of an electrolytic process, comprising: the system comprises a plurality of edge computing modules and a cloud server;
the edge calculation module comprises a camera, a sensor, an edge calculation host and a gateway, and is connected with the cloud server through the gateway;
wherein, the edge calculation host is used for acquiring the thermal image of the electrolytic cell collected by the camera and the data monitored by the sensor, and executing the step of the monitoring method for the electrolytic process abnormity in the first aspect; alternatively, the first and second electrodes may be,
the cloud server is configured to receive the thermal image of the electrolytic cell collected by the camera and data monitored by the sensor, which are transmitted by each edge computing host, and execute the step of the monitoring method for electrolytic process abnormality according to the first aspect.
In a third aspect, the present invention further provides an apparatus for monitoring abnormality of an electrolytic process, comprising:
the acquisition unit is used for acquiring a thermal image of the electrolytic cell;
the identification unit is used for identifying the electrolytic cell and the polar plate in the thermal image based on the semantic segmentation network model and marking the temperature and the position of the electrolytic cell and the polar plate;
and the determining unit is used for determining the polar plate with abnormal temperature in the electrolytic tank based on the target recognition algorithm.
In a fourth aspect, the present invention further provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the steps of the method for monitoring an abnormality in an electrolysis process according to the first aspect.
In a fifth aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method for monitoring an electrolysis process for abnormalities as described in the first aspect above.
According to the method and the system for monitoring the abnormality of the electrolytic process, provided by the invention, the thermal image data of the electrolytic cell area is analyzed through a machine vision related algorithm, the automatic inspection of the abnormal condition of the electrode plate in the electrolytic production process can be realized, the detection speed is high, the accuracy is high, the complete machine automation of the abnormality monitoring of the electrolytic process is realized, and the damage of manual inspection work to a human body during metal electrolysis can be greatly reduced.
Drawings
In order to more clearly illustrate the technical solutions of the present invention or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a schematic flow diagram of a method for monitoring an abnormality in an electrolytic process according to the present invention;
FIG. 2 is one of the schematic diagrams of the camera fixing method provided by the present invention;
FIG. 3 is a second schematic view of a camera fixing method according to the present invention;
FIG. 4 is a schematic structural diagram of a semantic segmentation network model provided by the present invention;
FIG. 5 is a schematic structural diagram of an abnormality monitoring system for an electrolytic process according to the present invention;
FIG. 6 is a schematic structural view of an apparatus for monitoring abnormality in an electrolytic process according to the present invention;
fig. 7 is a schematic structural diagram of an electronic device provided by the present invention.
Detailed Description
The term "and/or" in the present invention describes an association relationship of associated objects, and means that there may be three relationships, for example, a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.
The term "plurality" as used herein means two or more, and other terms are analogous.
The technical solutions in the present invention will be described clearly and completely with reference to the accompanying drawings, and it is obvious that the described embodiments are only some embodiments of the present invention, and not all 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.
In order to monitor the abnormity of short circuit, open circuit and the like, a manual inspection method is generally adopted in the industry. However, the method has the advantages of low detection and obstacle removal speed, low accuracy, high manual labor intensity, toxic property, corrosivity and the like of the electrolyte, and harm to human health. In addition, when the inspection is carried out manually, the detection accuracy, efficiency and the like are greatly influenced by the difference of working attitude, working state, working capacity and the like of workers.
Meanwhile, the manual inspection method can only confirm abnormal conditions, but cannot monitor the real-time state of the electrolysis process. When the abnormality occurs, the damage is already generated, and if the electrolysis process can be monitored in real time, the production efficiency can be greatly improved, and the electrolysis energy consumption can be reduced.
Therefore, in order to solve the defects and shortcomings of manual inspection during non-ferrous metal electrolysis, the embodiments of the invention provide a solution, which can realize real-time state monitoring during electrolysis production and automatic inspection of abnormal conditions of a polar plate, has high detection speed and high accuracy, not only realizes complete machine automation of electrolysis process state monitoring and fault diagnosis, but also can greatly reduce the damage of manual inspection work to human bodies during metal electrolysis.
Fig. 1 is a schematic flow chart of a method for monitoring an abnormality of an electrolytic process, as shown in fig. 1, the method includes the following steps:
specifically, in order to realize real-time state monitoring in the electrolytic production process and automatic inspection of abnormal conditions of a polar plate, the thermal image data of the electrolytic cell area is analyzed by adopting a machine vision related algorithm, a thermal image of the electrolytic cell is firstly acquired, the optional thermal image can be a thermal image picture shot by a camera, the camera is positioned to a shooting position and an angle which are set by a program above the electrolytic cell by a positioning device (such as a fixed support or a movable slide rail), and then the camera shoots the electrolytic cell area according to parameters set by the program, so that the thermal image of the electrolytic cell is acquired.
Fig. 2 is a schematic view of a camera fixing manner provided by the present invention, and as shown in fig. 2, the camera 200 may be fixed on a fixing bracket above the electrolytic cell 210, and the fixing bracket uses an electric pan-tilt 220 to adjust the position and angle of the camera 200. Fig. 3 is a schematic view of another camera fixing manner provided by the present invention, and as shown in fig. 3, the camera 200 may also be fixed on a movable slide rail 300 above the electrolytic cell 210, and the movable slide rail 300 uses a fixed pan-tilt to realize detection of different electrolysis areas by means of the movement of the slide rail. By the camera fixing mode shown in fig. 2 and 3, the large-scale production monitoring can be realized with less capital investment.
Optionally, in order to avoid the influence of rotation error, a positioning module can be further arranged, and the holder can be calibrated in real time through the positioning module, so that the positioning error is eliminated to the maximum extent.
specifically, the semantic segmentation network model in the embodiment of the invention is trained according to the thermographic sample of the electrolytic cell with the determined semantic label, so that accurate image semantic segmentation can be realized. After obtaining the thermal image of the electrolytic cell, obtaining the result of semantic segmentation through the trained semantic segmentation network model, thereby identifying the electrolytic cell and the polar plate in the thermal image, and carrying out temperature marking and position marking on the electrolytic cell and the polar plate.
And 102, determining the polar plate with abnormal temperature in the electrolytic cell based on a target identification algorithm.
Specifically, after identifying the electrolytic cell and the polar plate in the thermal image based on the semantic segmentation network model and marking the temperature and the position of the electrolytic cell and the polar plate, the temperature abnormal area in the thermal image can be detected through a target identification algorithm based on deep learning, and the temperature abnormal polar plate in the electrolytic cell can be determined according to the polar plate position mark corresponding to the temperature abnormal area, so that the temperature abnormal polar plate can be marked and positioned. The target recognition algorithm can be implemented by using a traditional target recognition algorithm for flaw detection.
According to the monitoring method for the electrode process abnormity, provided by the invention, the thermal image data of the electrolytic cell area is analyzed through a machine vision related algorithm, the automatic inspection of the abnormal condition of the electrode plate in the electrolytic production process can be realized, the detection speed is high, the accuracy is high, the complete machine automation of the electrolytic process abnormity monitoring is realized, and the damage of manual inspection work to a human body during metal electrolysis can be greatly reduced.
Optionally, in this embodiment of the present invention, the semantic segmentation network model may be constructed based on an Unet network model, and the convolutional layers in the Unet backbone network are reconstructed into a DenseBlock (dense block) structure, as shown in the following formula, each layer is overlapped with the outputs of all layers in front of it by a dense connection manner, and each layer is connected with each layer in a feed-forward manner, where x is0，x1，…，xe-1Referring to the output results at level 0, 1, …, e-1, multiple He (·) inputs are concatenated into a tensor, due to its dense connectivity.
xe＝He([x0，x1，…，xe-1])
Where Xe is the final output featuremap, He is a nonlinear transfer function, which is a combinatorial operation that may include a series of BN (Batch Normalization), ReLU (Rectified Linear Unit), Pooling (Pooling), and Conv (convolution) operations.
Fig. 4 is a schematic structural diagram of a semantic segmentation network model provided by the present invention, and as shown in fig. 4, the semantic segmentation network model includes an encoder, a decoder, and a connection layer between the encoder and the decoder.
The encoder (also called a shrinking encoder) includes 8 convolutional layers, and each two convolutional layers are one convolutional block, which is 4 convolutional blocks. Considering that most of the electrolytic cells are rectangular and have relatively large length-width ratios, 1 × 5 convolution kernels are used in the convolution layers to replace original 3 × 3 convolution kernels, every convolution block is connected through dense blocks, 6 cascade connections are formed in the convolution layers, and downsampling is completed through a largest pooling layer after the dense blocks are connected.
Alternatively, the resolution of the input image is 512 × 512, eventually down-sampled to 32 × 32. Correspondingly, the size of the originally collected picture (namely the obtained thermal image of the electrolytic cell) can be scaled and normalized and unified into 512 x 512 dimensions so as to meet the input requirement of a semantic segmentation model, and the centralized processing is realized by the mean value removal of each pixel point, so that the image generalization effect is enhanced.
The decoder (which may also be referred to as a dilation decoder) also contains 4 convolutional blocks, connects the upsampled result to the output of the sub-module with the same resolution in the encoder by a skip connection, and uses the output resolution of each sub-module in the decoder sequentially increased by the upsampling operation until the output resolution matches the resolution of the input image.
Optionally, the temperature marking and position marking of the electrolytic cell and the polar plate comprises:
and after the identified electrolytic bath and the identified polar plate are subjected to inclination compensation, temperature marking and position marking are carried out on the electrolytic bath and the polar plate.
Specifically, after the electrolytic cell segmentation result is obtained based on the semantic segmentation network model, that is, after the electrolytic cell and the polar plate in the thermal image are identified, the electrolytic cell and the polar plate can be subjected to temperature marking and position marking after the inclination compensation is performed on the electrolytic cell and the polar plate in consideration of the fact that the thermal image possibly has a certain inclination due to the shooting angle and the like.
For example, the edge coordinates of the electrolyzer area can be obtained by taking the matrix as a reference, and the minimum circumscribed rectangle with the direction angle, including the center point coordinates, the width and the height and the rotation angle, can be obtained for the edge coordinate point. And calculating the distance from the coordinate point to the upper edge and the lower edge, sequencing the coordinates of the minimum circumscribed rectangle to meet the one-to-one correspondence of perspective transformation coordinates, and performing nearest interpolation and boundary compensation to finally obtain the electrolysis bath after the inclination compensation. And then, coding positions of a workshop, an electrolytic cell and the cathode and anode plates, detecting short-circuit and open-circuit areas in the thermal image data by adopting a target identification algorithm based on deep learning, mapping an abnormal area identification result with the codes of the cathode and anode plates, and outputting a judgment result.
Optionally, after the temperature marking and the position marking are carried out on the electrolytic bath and the polar plate, the method further comprises the following steps:
acquiring temperature values of different polar plate positions in each electrolytic tank;
and inputting the temperature values of different polar plate positions in each electrolytic tank and data monitored by the sensors into a state monitoring and early warning model, monitoring the electrolytic process in real time, and performing abnormal warning on the electrolytic process according to warning rules.
Specifically, after the temperature marking and the position marking are carried out on the electrolytic bath and the polar plate, the temperature values of different polar plate positions in each electrolytic bath can be obtained, so that the state of the electrolytic process can be monitored in real time by adopting a state monitoring and early warning model according to the temperature values and data monitored by various other sensors, and the abnormal warning of the electrolytic process can be carried out according to the warning rules.
Alternatively, the sensors may include an electrolyte tank wall side wall temperature sensor and an electrolyte level measuring sensor.
Alternatively, the early warning rules in the state monitoring and early warning model may be determined by service personnel, for example, the temperature of a certain electrolytic cell electrode plate continuously and monotonically increases or monotonically decreases in a certain time period, or the wall temperature at a specific position of the electrolytic cell monotonically increases or monotonically decreases, so as to determine the temperature of the electrolytic cell, the wall temperature, the electrolyte level and the like according to the early warning rules determined by the service personnel, output the determination result, and perform early warning prompt when the early warning rules are satisfied.
The monitoring method for the abnormality of the electrolytic process provided by the invention can realize real-time state monitoring in the electrolytic production process and early warning of the abnormal condition of the polar plate by adopting the state monitoring and early warning model to carry out real-time monitoring, judgment and early warning on the electrolytic process, not only realizes complete machine automation of state monitoring and fault diagnosis of the electrolytic process, but also can greatly reduce the damage of manual inspection work to human bodies during metal electrolysis.
The method and the device provided by the embodiments of the invention are based on the same inventive concept, and because the principles of solving the problems of the method and the device are similar, the implementation of the device and the method can be mutually referred, and repeated parts are not repeated.
Fig. 5 is a schematic structural diagram of an abnormal monitoring system for an electrolytic process provided by the present invention, as shown in fig. 5, the system includes:
a plurality of edge computing modules 500 and a cloud server 510;
the edge calculation module 500 comprises a camera 200, a sensor 501, an edge calculation host 502 and a gateway 503, and the edge calculation module 500 is connected with a cloud server 510 through the gateway 503;
wherein, the camera 200 is used for collecting the thermal image of the electrolytic cell; the sensor 501 is used for monitoring the process data of the electrolytic cell, such as the wall temperature of the electrolytic cell, the level height of electrolyte and the like, and transmitting signals to the edge calculation host 502 in a wireless or wired mode; the edge calculation host 502 is used for acquiring the thermal image of the electrolytic cell collected by the camera 200 and the data monitored by the sensor 501, and executing any one of the methods provided by the above embodiments.
For example, in the edge calculation host 502, the machine vision algorithm is used for marking and positioning the electrode plate with abnormal temperature of the electrolytic cell, judging the data of the electrolytic cell wall temperature sensor and the electrolyte level sensor according to a set threshold value, and alarming according to the identification and judgment result. For the polar plate with a normal state, temperature recording and statistics are carried out, and if the temperature is monotonously increased and decreased within a period of time, early warning prompt is carried out; similarly, the state of the wall temperature data of the electrolytic bath, the level height data of the electrolyte and the like is monitored, and if the data monotonically rises or falls within a period of time, the early warning prompt is given.
Optionally, the edge computing hosts 502 may transmit raw data, processed data, and the like to the cloud server 510 through the gateway 503 in a wired or wireless manner, for example, the cloud server 510 may receive the thermal image of the electrolytic cell collected by the camera 200 and the data monitored by the sensor 501 transmitted by each edge computing host 502, and perform any one of the methods provided in the embodiments above.
Optionally, the edge computing host 502 has a data storage function to prevent data loss due to network abnormality and the like; the edge calculation host 502 can set the acquisition frequency, data accuracy and the like of the camera 200 and the sensor 501; the edge calculation host 502 can set thermal image acquisition positions, angles and the like of the electric holder and the movable slide rail; the edge calculation host 502 may set an algorithm for data analysis and processing to implement functions such as fault alarm and early fault diagnosis.
Optionally, the cloud server 510 may collect data of each edge computing host 502, and combine upstream and downstream process data and production management data to implement real-time production monitoring, production management, and process optimization functions.
Optionally, the system may include a display module for displaying the temperature of the electrolytic cell in the picture or playing back a historical picture in real time.
Optionally, in order to prevent the equipment from being damaged by corrosive gas in a workshop or the like, the camera 200, the sensor 501, the edge computing host 502, the gateway 503, and the like are all covered with a protective cover or other protective devices.
Compared with the prior art, the monitoring system for the abnormality of the electrolysis process has the advantages that: the complete automatic diagnosis of the abnormal state of the non-ferrous metal electrolytic polar plate and the real-time monitoring of the non-ferrous metal electrolytic state are realized; the influence of toxic gas on the health of workers during manual detection is reduced, and potential safety hazards are avoided; the accuracy and efficiency of the abnormality diagnosis of the electrolytic polar plate are greatly improved; the state monitoring and early warning of the electrolytic cell are realized, the failure rate of the electrolytic cell is greatly reduced, and the economic and safety benefits are improved; the early warning rule configuration of the fault can be carried out according to the service requirement, and the adaptability is high.
It should be noted that, the monitoring system for monitoring abnormality of electrolytic process provided by the present invention can implement all the method steps implemented by the above method embodiment, and can achieve the same technical effect, and detailed descriptions of the same parts and beneficial effects as those of the method embodiment in this embodiment are not repeated herein.
Fig. 6 is a schematic structural diagram of an apparatus for monitoring an abnormality in an electrolytic process according to the present invention, as shown in fig. 6, the apparatus includes:
an acquisition unit 600 for acquiring a thermograph of the electrolytic cell;
the identification unit 610 is used for identifying the electrolytic cell and the polar plate in the thermal image based on the semantic segmentation network model, and marking the temperature and the position of the electrolytic cell and the polar plate;
and the determining unit 620 is used for determining the polar plate with abnormal temperature in the electrolytic cell based on the target identification algorithm.
Optionally, the semantic segmentation network model comprises an encoder, a decoder and a connection layer between the encoder and the decoder; the encoder comprises 8 convolution layers, wherein every two convolution layers are a convolution block, the total number of the convolution blocks is 4, 1 x 5 convolution kernels are used in the convolution layers, the convolution blocks are connected through dense blocks, and downsampling is completed through a maximum pooling layer after the dense blocks; the decoder comprises 4 rolling blocks, the up-sampling result is connected with the output of the sub-module with the same resolution in the encoder through jump connection and is used as the input of the next sub-module in the decoder, and the output resolution of each sub-module in the decoder is sequentially increased through the up-sampling operation until the output resolution is consistent with the resolution of the input image.
Optionally, the identifying unit 610 is configured to: and after the identified electrolytic bath and the identified polar plate are subjected to inclination compensation, temperature marking and position marking are carried out on the electrolytic bath and the polar plate.
Optionally, the apparatus further comprises:
the monitoring and early warning unit 630 is used for acquiring temperature values of different polar plate positions in each electrolytic cell; and inputting the temperature values of different polar plate positions in each electrolytic tank and data monitored by the sensors into a state monitoring and early warning model, monitoring the electrolytic process in real time, and performing abnormal warning on the electrolytic process according to warning rules.
Optionally, the sensors include an electrolyte wall side wall temperature sensor and an electrolyte level measurement sensor.
Optionally, the obtaining unit 600 is configured to: and acquiring a thermal image of the electrolytic cell acquired by the camera, wherein the camera is arranged on a fixed support or a movable slide rail above the electrolytic cell.
It should be noted that the division of the unit in the embodiment of the present invention is schematic, and is only a logic function division, and there may be another division manner in actual implementation. 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 as a software functional unit and sold or used as a stand-alone product, may be stored in a processor readable 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 storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, a network device, or the like) or a processor (processor) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
It should be noted that, the apparatus provided in the embodiment of the present invention can implement all the method steps implemented by the method embodiment and achieve the same technical effect, and detailed descriptions of the same parts and beneficial effects as the method embodiment in this embodiment are omitted here.
Fig. 7 is a schematic structural diagram of an electronic device provided in the present invention, and as shown in fig. 7, the electronic device may include: a processor (processor)710, a communication Interface (Communications Interface)720, a memory (memory)730, and a communication bus 740, wherein the processor 710, the communication Interface 720, and the memory 730 communicate with each other via the communication bus 740. Processor 710 may invoke logic instructions in memory 730 to perform a method of monitoring for an electrolysis process anomaly, the method comprising: obtaining a thermal image of the electrolytic cell; identifying an electrolytic cell and a polar plate in a thermal image based on a semantic segmentation network model, and carrying out temperature marking and position marking on the electrolytic cell and the polar plate; determining a polar plate with abnormal temperature in the electrolytic cell based on a target identification algorithm; the semantic segmentation network model is obtained by training a thermography sample of an electrolytic cell with a determined semantic label.
In addition, the logic instructions in the memory 730 can be implemented in the form of software functional units and stored in a computer readable storage medium when the software functional units are sold or used as independent products. 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 storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, the present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, is implemented to perform the above-mentioned methods for monitoring an abnormality of an electrolytic process, the method comprising: obtaining a thermal image of the electrolytic cell; identifying an electrolytic cell and a polar plate in a thermal image based on a semantic segmentation network model, and carrying out temperature marking and position marking on the electrolytic cell and the polar plate; determining a polar plate with abnormal temperature in the electrolytic cell based on a target identification algorithm; the semantic segmentation network model is obtained by training a thermography sample of an electrolytic cell with a determined semantic label.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for monitoring abnormality of an electrolytic process, comprising:
obtaining a thermal image of the electrolytic cell;
identifying the electrolytic cell and the polar plate in the thermal image based on a semantic segmentation network model, and carrying out temperature marking and position marking on the electrolytic cell and the polar plate;
determining a polar plate with abnormal temperature in the electrolytic cell based on a target identification algorithm;
the semantic segmentation network model is obtained by training a thermography sample of an electrolytic cell with a determined semantic label.
2. The method of claim 1, wherein the semantic segmentation network model comprises an encoder, a decoder, and a connection layer between the encoder and the decoder;
the encoder comprises 8 convolution layers, wherein each two convolution layers are a convolution block, the total number of the convolution blocks is 4, 1 multiplied by 5 convolution kernels are used in the convolution layers, the convolution blocks are connected through dense blocks, and downsampling is completed through a maximum pooling layer after the dense blocks;
the decoder comprises 4 rolling blocks, the up-sampling result is connected with the output of the sub-module with the same resolution in the encoder through jumping connection and is used as the input of the next sub-module in the decoder, and the output resolution of each sub-module in the decoder is sequentially increased through up-sampling operation until the output resolution is consistent with the resolution of the input image.
3. The method for monitoring abnormality of electrolytic process according to claim 1, wherein said temperature marking and position marking of the electrolytic bath and the electrode plate comprises:
and after the identified electrolytic bath and the identified polar plate are subjected to inclination compensation, temperature marking and position marking are carried out on the electrolytic bath and the polar plate.
4. The method for monitoring abnormality of electrolytic process according to claim 1 or 3, characterized in that after said temperature marking and position marking of the electrolytic bath and the plate, the method further comprises:
acquiring temperature values of different polar plate positions in each electrolytic tank;
and inputting the temperature values of different polar plate positions in each electrolytic tank and data monitored by the sensors into a state monitoring and early warning model, monitoring the electrolytic process in real time, and performing abnormal warning on the electrolytic process according to a warning rule.
5. The method of claim 4, wherein the sensors comprise a bath wall temperature sensor and an electrolyte level measuring sensor.
6. The method for monitoring abnormality of electrolytic process according to claim 1, wherein said obtaining a thermograph of an electrolytic cell comprises:
and acquiring a thermal image of the electrolytic cell acquired by the camera, wherein the camera is arranged on a fixed support or a movable slide rail above the electrolytic cell.
7. An electrolytic process anomaly monitoring system, comprising: the system comprises a plurality of edge computing modules and a cloud server;
the edge calculation module comprises a camera, a sensor, an edge calculation host and a gateway, and is connected with the cloud server through the gateway;
wherein the edge calculation host is used for acquiring the thermal image of the electrolytic cell collected by the camera and the data monitored by the sensor and executing the method of any one of claims 1 to 6; alternatively, the first and second electrodes may be,
the cloud server is used for receiving the electrolytic bath thermal image collected by the camera and the data monitored by the sensor and transmitted by each edge computing host, and executing the method of any one of claims 1 to 6.
8. An apparatus for monitoring an electrolysis process anomaly, comprising:
the acquisition unit is used for acquiring a thermal image of the electrolytic cell;
the identification unit is used for identifying the electrolytic cell and the polar plate in the thermal image based on the semantic segmentation network model and marking the temperature and the position of the electrolytic cell and the polar plate;
and the determining unit is used for determining the polar plate with abnormal temperature in the electrolytic tank based on the target recognition algorithm.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method for monitoring an abnormality of an electrolytic process according to any one of claims 1 to 6.
10. A non-transitory computer readable storage medium, on which a computer program is stored, wherein the computer program, when being executed by a processor, implements the steps of the method for monitoring an abnormality of an electrolytic process according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110560557.0A CN113191366A (en) | 2021-05-21 | 2021-05-21 | Method and system for monitoring abnormality of electrolytic process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110560557.0A CN113191366A (en) | 2021-05-21 | 2021-05-21 | Method and system for monitoring abnormality of electrolytic process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113191366A true CN113191366A (en) | 2021-07-30 |
Family
ID=76984627
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110560557.0A Pending CN113191366A (en) | 2021-05-21 | 2021-05-21 | Method and system for monitoring abnormality of electrolytic process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113191366A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106835201A (en) * | 2015-12-03 | 2017-06-13 | 中国科学院青海盐湖研究所 | Aluminium cell control method based on fuzzy clustering algorithm |
| CN107767360A (en) * | 2017-08-17 | 2018-03-06 | 中南大学 | A kind of method for early warning and detection means for electrolytic bath electrode plate failure |
| CN110689544A (en) * | 2019-09-06 | 2020-01-14 | 哈尔滨工程大学 | Method for segmenting delicate target of remote sensing image |
| WO2020107687A1 (en) * | 2018-11-27 | 2020-06-04 | 邦鼓思电子科技（上海）有限公司 | Vision-based working area boundary detection system and method, and machine equipment |
| CN111321429A (en) * | 2019-05-13 | 2020-06-23 | 杭州海康威视系统技术有限公司 | Method and device for detecting temperature of electrode plate of electrolytic cell |
-
2021
- 2021-05-21 CN CN202110560557.0A patent/CN113191366A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106835201A (en) * | 2015-12-03 | 2017-06-13 | 中国科学院青海盐湖研究所 | Aluminium cell control method based on fuzzy clustering algorithm |
| CN107767360A (en) * | 2017-08-17 | 2018-03-06 | 中南大学 | A kind of method for early warning and detection means for electrolytic bath electrode plate failure |
| WO2020107687A1 (en) * | 2018-11-27 | 2020-06-04 | 邦鼓思电子科技（上海）有限公司 | Vision-based working area boundary detection system and method, and machine equipment |
| CN111321429A (en) * | 2019-05-13 | 2020-06-23 | 杭州海康威视系统技术有限公司 | Method and device for detecting temperature of electrode plate of electrolytic cell |
| CN110689544A (en) * | 2019-09-06 | 2020-01-14 | 哈尔滨工程大学 | Method for segmenting delicate target of remote sensing image |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108537154B (en) | Power transmission line bird nest identification method based on HOG characteristics and machine learning | |
| CN110310261B (en) | Contact net dropper defect detection model training method and defect detection method | |
| CN108257114A (en) | A kind of transmission facility defect inspection method based on deep learning | |
| CN111737909B (en) | Structural health monitoring data anomaly identification method based on space-time graph convolutional network | |
| CN111321429B (en) | Method and device for detecting temperature of electrode plate of electrolytic cell | |
| CN111723821A (en) | Detection and identification method and device for power plant instrument image | |
| CN115526515B (en) | Safety monitoring system of gate for water conservancy and hydropower | |
| CN115171361B (en) | Dangerous behavior intelligent detection and early warning method based on computer vision | |
| CN114707970B (en) | Electrolytic production parameter determining method | |
| CN114898523A (en) | Power transmission line image monitoring method and device with distance measuring function | |
| CN114460227B (en) | Electrolyte abnormality monitoring method and system | |
| CN112989703A (en) | Feature fusion metal additive manufacturing fusion state real-time prediction method based on deep learning | |
| CN116704733A (en) | Aging early warning method and system for aluminum alloy cable | |
| US11521120B2 (en) | Inspection apparatus and machine learning method | |
| US11682112B2 (en) | Inspection device and machine learning method | |
| CN112183555B (en) | Method and system for detecting welding quality, electronic device and storage medium | |
| CN113191366A (en) | Method and system for monitoring abnormality of electrolytic process | |
| CN108898187A (en) | A kind of method and device of automatic identification power distribution room indicating equipment image | |
| CN114192583B (en) | Scada platform-based strip steel rolling process quality monitoring method and system | |
| CN111678438B (en) | Scale body displacement early warning method and system | |
| CN114119662A (en) | Image processing method and system in fish detection visual system | |
| CN114549453A (en) | Contact line pull-out lead height value detection method and system | |
| CN113516091A (en) | Method for identifying electric spark image of transformer substation | |
| CN114719784B (en) | Device and method for detecting inclination angle of cylindrical weighing sensor | |
| CN116385429B (en) | Intelligent management method and system for backstroke departure device production line |
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 |