CN113298750A - Detection method for wheel falling of circular cooler - Google Patents
Detection method for wheel falling of circular cooler Download PDFInfo
- Publication number
- CN113298750A CN113298750A CN202011050388.8A CN202011050388A CN113298750A CN 113298750 A CN113298750 A CN 113298750A CN 202011050388 A CN202011050388 A CN 202011050388A CN 113298750 A CN113298750 A CN 113298750A
- Authority
- CN
- China
- Prior art keywords
- circular cooler
- wheel
- neural network
- network model
- residual error
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- 238000003062 neural network model Methods 0.000 claims abstract description 54
- 238000012549 training Methods 0.000 claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 31
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000002372 labelling Methods 0.000 claims abstract description 3
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 claims description 21
- 238000001816 cooling Methods 0.000 claims description 21
- 238000012795 verification Methods 0.000 claims description 20
- 238000011176 pooling Methods 0.000 claims description 9
- 239000011159 matrix material Substances 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 abstract description 8
- 238000007689 inspection Methods 0.000 abstract description 3
- 230000008569 process Effects 0.000 description 13
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 6
- 238000005245 sintering Methods 0.000 description 5
- 238000009851 ferrous metallurgy Methods 0.000 description 3
- 238000009434 installation Methods 0.000 description 3
- 229910052742 iron Inorganic materials 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000001035 drying Methods 0.000 description 2
- 239000000446 fuel Substances 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000002156 mixing Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 239000000843 powder Substances 0.000 description 2
- 230000003321 amplification Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000004907 flux Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 238000007711 solidification Methods 0.000 description 1
- 230000008023 solidification Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/90—Dynamic range modification of images or parts thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biomedical Technology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The application discloses a method for detecting wheel falling of a circular cooler, which comprises the following steps: cameras are arranged on two sides of the circular cooler; collecting running images of a plurality of ring coolers within a period of time; processing a plurality of running images; labeling the processed running image to obtain a labeled image set; the labels comprise a wheeled label and a non-wheeled label; constructing a circular cooler turn-off identification residual error neural network model, and training and verifying the circular cooler turn-off identification residual error neural network model by using a marked image set; inputting a running image collected according to a fixed frequency into a trained and verified circular cooler wheel drop recognition residual error neural network model, detecting whether the circular cooler wheel drops or not, and outputting a detection result; and the detection result comprises that the wheel falls off when the circular cooler is used and the wheel does not fall off when the circular cooler is used. The problem that the operation condition of the circular cooler is regularly checked by adopting a manual inspection mode in the current factory, and the production loss and the like can not be found in time if the condition of wheel falling is generated can be solved.
Description
Technical Field
The application relates to the technical field of image processing, in particular to a method for detecting wheel falling of a circular cooler.
Background
In the ferrous metallurgy industry, sintering is an important pre-process. For example, before blast furnace iron making, iron-containing powder, fuel and flux are mixed according to the process proportion, and the iron-containing powder is bonded into block sintered ore by using a small amount of molten mass generated by the combustion heat of the fuel and a solidification reaction. The sintering process generally includes batching, primary mixing and distributing, secondary mixing and distributing, ignition sintering, dust removal and air draft, crushing and cooling.
Among them, the ring cooler is called a ring cooler for short, and is generally used for cooling a sintering process flow, and is one of important devices in ferrous metallurgy. The circular cooler is a bearing for cooling in the sintering process and is one of important devices in ferrous metallurgy. The rough operation condition of the ring cooling machine can cause the bearing of the trolley wheel to deform and wear, so that the wheel falls off from the axle, the production efficiency is seriously influenced, and the safety of personnel is threatened. Therefore, the wheel falling condition of the circular cooler is detected in time, and the dangerous working condition caused by the falling of the wheels can be effectively avoided.
However, at present, the operation condition of the circular cooler is regularly checked by adopting a manual inspection mode in a factory, and if the condition of wheel falling occurs, the condition can not be found in time, so that the production loss is easily caused.
Disclosure of Invention
The application provides a detection method that cold machine of ring falls round to solve present mill and all adopt the artifical mode of patrolling and examining to regularly inspect the operation condition of cold machine of ring, if take place to fall the circumstances of round, unable in time discover, cause production loss scheduling problem easily.
A method for detecting wheel drop of a circular cooler comprises the following steps:
cameras are arranged on two sides of the circular cooler;
collecting running images of a plurality of ring coolers within a period of time;
processing a plurality of running images;
labeling the processed running image to obtain a labeled image set; the labels comprise a wheeled label and a non-wheeled label;
constructing a circular cooler turn-off identification residual error neural network model, and training and verifying the circular cooler turn-off identification residual error neural network model by using the marked image set;
inputting the running image collected according to a fixed frequency into the trained and verified circular cooler wheel drop recognition residual neural network model, detecting whether the circular cooler wheel drops or not, and outputting a detection result; and the detection result comprises that the wheel falls when the circular cooler is used and the wheel does not fall when the circular cooler is used.
The application provides a detection method that cold machine of ring falls round, through at cold machine both sides installation camera of ring, and construct the cold machine of ring and fall round discernment residual error neural network model, the cold machine running image of ring that gathers with the camera is input into the cold machine of ring and fall round discernment residual error neural network model, whether the condition of falling round in service to the cold machine of ring is monitored, through this kind of on-line monitoring, can in time discover the cold machine of ring fall round the condition, can in time handle the condition of falling round, avoid bringing the hysteresis quality because artifical patrolling and examining, and then avoid causing the production loss.
Drawings
In order to more clearly explain the technical solution of the present application, the drawings needed to be used in the embodiments will be briefly described below, and it is obvious to those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a top view of the ring cooler;
FIG. 2 is a front view of the trolley of FIG. 1;
fig. 3 is a flowchart of a method for detecting a wheel drop of a circular cooler according to an embodiment of the present application;
FIG. 4 is a schematic view of a camera mounting location;
FIG. 5 is a diagram of a circular cooler wheel drop identification residual error neural network model architecture corresponding to the circular cooler wheel drop detection method shown in FIG. 3;
FIG. 6 is a flowchart illustrating training and verification of a first circular cooler round-trip recognition residual neural network model shown in FIG. 3;
fig. 7 is a flowchart of training and verifying the second circular cooling machine round-trip recognition residual neural network model shown in fig. 3.
Detailed Description
The technical solutions in the embodiments of the present application will be described clearly and completely with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.
FIG. 1 is a top view of the ring cooler; fig. 2 is a front view of the trolley of fig. 1. Referring to fig. 1 and 2, the trolley 11 of the circular cooler 1 moves circularly by the wheels 111 on both sides. Because the rough operating condition of the ring cooling machine 1 can lead to the bearing of the wheel 111 of the trolley 11 to deform and wear, the wheel 111 falls off from the axle, the operating condition of the ring cooling machine 1 is checked regularly by adopting a manual inspection mode in the current factory, and the problem of production loss and the like can not be found in time if the condition of wheel falling occurs.
Fig. 3 is a flowchart of a method for detecting a broken wheel of a circular cooler according to an embodiment of the present application. As shown in fig. 3, the present application provides a method for detecting a wheel drop of a circular cooler, including the following steps:
s1: cameras are arranged on two sides of the circular cooler. Fig. 4 is a schematic view of a camera mounting position. As shown in fig. 4, cameras 2 are respectively installed on two sides of the circular cooler 1, and the cameras 2 need to be aligned to wheels of the trolley to take pictures and record the running conditions of the wheels. The number of the cameras shown in fig. 4 is 2, one side of each of two sides of the circular cooler 1 can be set more according to actual conditions, the types of the cameras can be various, related debugging is needed after the installation of the cameras is completed, and the method is not specifically limited in the application.
S2: collecting running images of the multiple ring coolers within a period of time. The running speed of the trolley can be obtained by utilizing a PLC (programmable Logic controller), the running position of wheels of the trolley is calculated according to the speed, when the wheels of the trolley run to the visual field range of the camera, the camera is started to shoot, the running image in a period of time is collected, and in the period of time, the normal image of the wheels and the image in the wheel falling process are required to ensure that the collected running image can cover all running conditions of the wheels of the trolley.
After the running image is acquired, the step S3 is executed: and processing a plurality of running images. The specific treatment mode may include the following:
adjusting the size of the running image to a set pixel size; the set pixel size may be 1024 pixels by 1024 pixels.
Adjusting the brightness of the running image; the running image may be adjusted in brightness according to the following equation:
g(x,y)＝a*f(x,y)+b，0＜a＜3，
wherein g (x, y) is a three-channel numerical value of red, green and blue of an output target image x row and y columns of pixel points, f (x, y) is an input running image x row, a is an amplification coefficient, b is an offset coefficient, a is a positive number, and the value can be between 0 and 3, without specific limitation.
Carrying out smooth denoising processing on the adjusted running image; the resized and brightened running image may be linearly filtered according to the following equation:
wherein, g (i, j) is the pixel value of the output target image, (i, j) is the pixel coordinate value of the target image, (f (i + k, j + l) is the pixel value of the input running image, (k, l) is the pixel coordinate value of the running image, and h (k, l) is the weighting coefficient of the filter. The process of linear filtering is the process of smoothing and drying.
The above specific modes of the resizing, the brightness adjustment, and the smooth drying process are only illustrative, and the present application is not limited to the specific modes.
After the running image processing is completed, the process proceeds to step S4: and marking labels on the processed running images to obtain a marked image set, wherein the labels comprise wheel labels and non-wheel labels. For example, a label with a wheel may be denoted by 1, a label without a wheel may be denoted by 0, and a label may be marked in an image attribute of a live image, which is not particularly limited in the present application.
After the labeled image set is formed, the labeled image set may be divided into a training set and a verification set, and then the step S5 is continuously executed: and constructing a circular cooler turn-off identification residual error neural network model, and training and verifying the circular cooler turn-off identification residual error neural network model by using the marked image set. Specifically, the training set is used for training the circular cooler wheel drop identification residual error neural network model, and the verification set is used for verifying the circular cooler wheel drop identification residual error neural network model. Because the training of the circular cooler round-trip recognition residual error neural network model is a process of repeatedly learning the model, the required data volume is large, and relatively speaking, the verification process of the model does not need excessive data volume, so that the number of the marked images in the training set can be larger than that of the marked images in the verification set. For example, 80% of the labeled images in the labeled image set may be used as the training set, and the remaining 20% of the labeled images may be used as the verification set.
Fig. 5 is an architecture diagram of a circular-cooling machine wheel-drop recognition residual error neural network model corresponding to the detection method for the circular-cooling machine wheel-drop shown in fig. 3, fig. 6 is a flow chart of training and verification of the first circular-cooling machine wheel-drop recognition residual error neural network model shown in fig. 3, and fig. 7 is a flow chart of training and verification of the second circular-cooling machine wheel-drop recognition residual error neural network model shown in fig. 3. In detail, with reference to fig. 5 to 7, step S5 may include the following steps:
s51: and constructing a circular cooler wheel drop identification residual error neural network model, wherein the circular cooler wheel drop identification residual error neural network model comprises an input layer, a plurality of residual error blocks, a full connection layer, a classifier and an output layer. The residual block may include a convolutional layer and a pooling layer; the output of the convolution layer is used as the input of the pooling layer, and the output of the pooling layer is used as the output of the residual block; the convolution layer is used for carrying out standardized operation and regularization operation on the input marked image and outputting image operation data; the pooling layer is used for performing dimension reduction processing on the image operation data output by the convolution layer. The dimensions of each residual block may be different from each other, and the dimensions of each residual block are determined by the convolutional layer and the pooling layer. The dimension of the convolution layer may be set to 32 dimensions, the step size may be 1, and convolution is performed by 3 × 3, which is not particularly limited in the present application.
S52: parameters in the residual block are initialized. The equation of the convolutional layer may be a linear equation, and the parameter of the convolutional layer is a parameter of the linear equation, and specifically may include a weight value and a bias value, and the parameter may further include a batch normalization scale factor. In the subsequent model training process, the weight values and the bias values are mainly trained. Since the parameter update of the front layer training will cause the change of the input data distribution of the back layer in the model training process, the input data distribution of each layer is changed all the time, therefore, batch standardization algorithm can be set for the convolution layer and the full connection layer to keep the same input data distribution. The individual layers may also be set with batch normalization scale factors, which also serve to normalize for each input sample.
S53: inputting the marked images in the training set into a residual block through an input layer, and outputting image operation data after performing standardized operation and regularization operation; and the image operation data output by each residual block is used as the input data of the next residual block, and all the residual blocks are traversed.
S54: and inputting the image operation data output by the last residual block into the full-connection layer, and outputting the multi-dimensional characteristic matrix after carrying out standardized operation.
S55: and inputting the multi-dimensional feature matrix into a classifier for classification, and outputting a detection result through an output layer. The classifier can adopt a softmax classifier and is used for carrying out feature classification on the multi-dimensional feature matrix to finally obtain a detection result, and the detection result can be represented in the same form with the label of the marked image so as to facilitate subsequent comparison.
S56: comparing the detection result with the label of the marked image to obtain a comparison result; and comparing the detection result with the label of the marked image to compare whether the detection result is the same as the label.
S57: according to the comparison result, correcting the parameters of the residual block until all the marked images in the training set are used up, and finishing the training; if the comparison result is that the detection result is the same as the label, the parameter does not need to be corrected, and if the comparison result is that the detection result is different from the label, the parameter needs to be corrected correspondingly. When all the labeled images in the training set have undergone the steps S53-S57, the model training is finished.
S58: and inputting all marked images of the verification set into the trained circular cooler turn-off identification residual error neural network model, and verifying the circular cooler turn-off identification residual error neural network model.
As shown in fig. 6, step S58 may specifically include the following steps:
s581: and inputting all the marked images of the verification set into the trained circular cooler turn-off recognition residual error neural network model, and outputting a detection result.
S582: and inputting the detection result into a loss function to obtain the loss rate.
The formula for the loss function is as follows:
wherein L is the loss rate, ynFor the input n-th label of the label image, yn' is the corresponding detection result outputted, and N is the total number of the marker images.
S583: judging whether the loss rate is less than or equal to a target loss value; the target loss value of the loss rate may be set to 0.01.
S584: and if the loss rate is greater than the target loss value, continuing training the circular cooler off-round recognition residual error neural network model until the loss rate is less than or equal to the target loss value, and stopping training. And if the loss rate is less than or equal to the target loss value, the fact that the circular cooler turn-off identification residual error neural network model passes verification is shown, and a final circular cooler turn-off identification residual error neural network model is obtained.
As shown in fig. 7, in another embodiment, step S58 may include the following steps:
s581': and inputting all the marked images of the verification set into the trained circular cooler turn-off identification residual error neural network model, and outputting a detection result.
S582': and comparing the detection result with the label of the corresponding marked image to obtain a comparison result.
S583': and counting the error rate of the comparison result, wherein the error rate can be obtained by dividing the error quantity by the total input quantity.
S584': and if the error rate is greater than the error threshold, continuing training the circular cooler turn-off recognition residual error neural network model until the error rate is less than or equal to the error threshold, and stopping training. The error threshold may be set according to actual conditions, and the application is not particularly limited. And if the error rate is less than or equal to the error threshold, the ring cooling machine turn-off identification residual error neural network model is verified to obtain a final ring cooling machine turn-off identification residual error neural network model. After the final circular cooler turn-off identification residual error neural network model is obtained, the circular cooler turn-off identification residual error neural network model can be packaged, and the packaged model is an executable program file.
S6: inputting a running image collected according to a fixed frequency into a trained and verified circular cooler wheel drop recognition residual error neural network model, detecting whether the circular cooler wheel drops or not, and outputting a detection result; and the detection result comprises that the wheel falls off when the circular cooler is used and the wheel does not fall off when the circular cooler is used. The fixed frequency may be one frame of image collected per second, or one frame of image collected per two seconds, and may be set according to actual needs, which is not specifically limited in the present application.
And when the detection result is that the circular cooler has wheel falling, the wheel falling alarm is carried out. Maintenance personnel can in time carry out the maintenance of wheel to the cold machine of ring, and furthest's reduction is to the influence of production.
The application provides a detection method that cold machine of ring falls round, through at cold machine both sides installation camera of ring, and construct the cold machine of ring and fall round discernment residual error neural network model, the cold machine running image of ring that gathers with the camera is input into the cold machine of ring and fall round discernment residual error neural network model, whether the condition of falling round in service to the cold machine of ring is monitored, through this kind of on-line monitoring, can in time discover the cold machine of ring fall round the condition, can in time handle the condition of falling round, avoid bringing the hysteresis quality because artifical patrolling and examining, and then avoid causing the production loss.
The same and similar parts in the various embodiments in this specification may be referred to each other.
Claims (10)
1. A method for detecting wheel drop of a circular cooler is characterized by comprising the following steps:
cameras are arranged on two sides of the circular cooler;
collecting running images of a plurality of ring coolers within a period of time;
processing a plurality of running images;
labeling the processed running image to obtain a labeled image set; the labels comprise a wheeled label and a non-wheeled label;
constructing a circular cooler turn-off identification residual error neural network model, and training and verifying the circular cooler turn-off identification residual error neural network model by using the marked image set;
inputting the running image collected according to a fixed frequency into the trained and verified circular cooler wheel drop recognition residual neural network model, detecting whether the circular cooler wheel drops or not, and outputting a detection result; and the detection result comprises that the wheel falls when the circular cooler is used and the wheel does not fall when the circular cooler is used.
2. The method for detecting a ring cooling machine broken wheel according to claim 1, wherein the processing in the step of processing a plurality of running images comprises:
adjusting the size of the running image to a set pixel size;
adjusting the brightness of the running image;
and carrying out smooth denoising processing on the adjusted running image.
3. The method for detecting the wheel drop of the circular cooler according to claim 1, wherein when the detection result is that the wheel drop of the circular cooler occurs, a wheel drop alarm is given.
4. The method for detecting the ring cooling machine wheel slip according to claim 1, wherein the set of labeled images is divided into a training set and a verification set;
the method comprises the following steps of constructing a circular cooler turn-off identification residual error neural network model, and training and verifying the circular cooler turn-off identification residual error neural network model by using a marked image set, wherein the steps comprise:
constructing a circular cooler wheel-falling identification residual error neural network model, wherein the circular cooler wheel-falling identification residual error neural network model comprises an input layer, a plurality of residual error blocks, a full connection layer, a classifier and an output layer;
initializing parameters in the residual block;
inputting all the marked images in the training set into the residual block through an input layer, and outputting image operation data after performing standardized operation and regularization operation; the image operation data output by each residual block is used as the input data of the next residual block, and all the residual blocks are traversed;
inputting the image operation data output by the last residual block into the full-connection layer, and outputting a multi-dimensional feature matrix after carrying out standardized operation;
inputting the multi-dimensional feature matrix into the classifier for classification, and outputting a detection result through the output layer;
comparing the detection result with the label of the marked image to obtain a comparison result;
correcting the parameters of the residual block according to the comparison result until all the marked images in the training set are used up, and finishing the training;
inputting all the marked images of the verification set into the trained circular cooler turn-off identification residual error neural network model, and verifying the circular cooler turn-off identification residual error neural network model;
and if the verification is passed, obtaining the trained and verified circular cooler off-turn recognition residual error neural network model.
5. The method for detecting the circular cooler broken wheel according to claim 4, wherein the residual block comprises a convolution layer and a pooling layer; the output of the convolutional layer is used as the input of the pooling layer, and the output of the pooling layer is used as the output of the residual block; the convolution layer is used for carrying out standardization operation and regularization operation on the input marked image and outputting the image operation data; the pooling layer is used for performing dimensionality reduction processing on the image operation data output by the convolution layer.
6. The method for detecting the ring cooling machine dropped wheel according to claim 5, wherein the step of inputting all the labeled images of the verification set into the trained ring cooling machine dropped wheel recognition residual error neural network model and verifying the ring cooling machine dropped wheel recognition residual error neural network model comprises:
inputting all the marked images of the verification set into the trained circular cooler turn-off recognition residual error neural network model, and outputting the detection result;
inputting the detection result into a loss function to obtain a loss rate;
judging whether the loss rate is less than or equal to a target loss value;
if the loss rate is larger than a target loss value, continuing to train the circular cooler turn-off recognition residual error neural network model;
and stopping training if the loss rate is less than or equal to the target loss value.
7. The method for detecting the ring cooling machine dropped wheel according to claim 5, wherein the step of inputting all the labeled images of the verification set into the trained ring cooling machine dropped wheel recognition residual error neural network model and verifying the ring cooling machine dropped wheel recognition residual error neural network model comprises:
inputting all the marked images of the verification set into the trained circular cooler turn-off recognition residual error neural network model, and outputting the detection result;
comparing the detection result with the corresponding label of the marked image to obtain a comparison result;
counting the error rate of the comparison result;
if the error rate is larger than an error threshold value, continuing to train the circular cooler off-round recognition residual error neural network model;
stopping training if the error rate is less than or equal to the error threshold.
8. The method for detecting the cold ring wheel falling of the circular cooler according to claim 6 or 7, wherein the number of the labeled images in the training set is greater than the number of the labeled images in the verification set.
9. The method for detecting the circular cooler broken wheel according to claim 5, wherein the dimensions of each of the residual blocks are different from each other.
10. The method for detecting the circular cooler broken wheel according to claim 5, wherein the convolution layer and the full connection layer are provided with a batch standardization algorithm for keeping the input data in the same distribution.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011050388.8A CN113298750A (en) | 2020-09-29 | 2020-09-29 | Detection method for wheel falling of circular cooler |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011050388.8A CN113298750A (en) | 2020-09-29 | 2020-09-29 | Detection method for wheel falling of circular cooler |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113298750A true CN113298750A (en) | 2021-08-24 |
Family
ID=77318305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011050388.8A Pending CN113298750A (en) | 2020-09-29 | 2020-09-29 | Detection method for wheel falling of circular cooler |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113298750A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA3045333A1 (en) * | 2016-12-01 | 2018-06-07 | Berkeley Lights, Inc. | Automated detection and repositioning of micro-objects in microfluidic devices |
| CN108510488A (en) * | 2018-03-30 | 2018-09-07 | 安徽理工大学 | Four kinds of damage detecting methods of conveyer belt based on residual error network |
| CN109376792A (en) * | 2018-11-07 | 2019-02-22 | 河北工业大学 | Photovoltaic cell open defect classification method based on multichannel residual error neural network |
| CN110059751A (en) * | 2019-04-19 | 2019-07-26 | 南京链和科技有限公司 | A kind of tire code and tire condition recognition methods based on machine learning |
| CN110057198A (en) * | 2019-05-17 | 2019-07-26 | 天津市三特电子有限公司 | Wheel of sintering trolley working state detecting method and detection device |
| CN110246132A (en) * | 2019-06-23 | 2019-09-17 | 中车青岛四方车辆研究所有限公司 | Rail vehicle bolt looseness detection method and system |
| 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 |
-
2020
- 2020-09-29 CN CN202011050388.8A patent/CN113298750A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA3045333A1 (en) * | 2016-12-01 | 2018-06-07 | Berkeley Lights, Inc. | Automated detection and repositioning of micro-objects in microfluidic devices |
| CN108510488A (en) * | 2018-03-30 | 2018-09-07 | 安徽理工大学 | Four kinds of damage detecting methods of conveyer belt based on residual error network |
| CN109376792A (en) * | 2018-11-07 | 2019-02-22 | 河北工业大学 | Photovoltaic cell open defect classification method based on multichannel residual error neural network |
| CN110059751A (en) * | 2019-04-19 | 2019-07-26 | 南京链和科技有限公司 | A kind of tire code and tire condition recognition methods based on machine learning |
| CN110057198A (en) * | 2019-05-17 | 2019-07-26 | 天津市三特电子有限公司 | Wheel of sintering trolley working state detecting method and detection device |
| CN110246132A (en) * | 2019-06-23 | 2019-09-17 | 中车青岛四方车辆研究所有限公司 | Rail vehicle bolt looseness detection method and system |
| 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 |
Non-Patent Citations (3)
| Title |
|---|
| ZHEMING TONG,ET AL.: "A convolutional neural network approach for visual recognition in wheel production lines", 《INTERNATIONAL JOURNAL OF ADVANCED ROBOTIC SYSTEMS》 * |
| 张成林: "环冷机打滑和掉轮故障的在线检测方法", 《工业技术》 * |
| 陈翔: "基于机器视觉的环冷机台车车轮状态监测***", 《硕士论文电子期刊工程科技Ⅰ辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110902315B (en) | Belt deviation state detection method and system | |
| CN113297885A (en) | Belt conveyor surface state detection method and device based on convolutional neural network | |
| CN110120155A (en) | A kind of chemical industry plant area vehicle overload overload intelligent monitoring and alarming system | |
| CN109598200B (en) | Intelligent image identification system and method for molten iron tank number | |
| CN111768390B (en) | Image recognition-based grate cooler red river recognition method | |
| CN111179236A (en) | Raw ball granularity analysis method and device for pelletizer | |
| CN111476712B (en) | Trolley grate image shooting and detecting method and system of sintering machine | |
| CN113298750A (en) | Detection method for wheel falling of circular cooler | |
| CN114708532A (en) | Monitoring video quality evaluation method, system and storage medium | |
| CN111223094B (en) | Trolley grate spacing detection method and system for sintering machine | |
| CN113077423B (en) | Laser selective melting pool image analysis system based on convolutional neural network | |
| CN111223098B (en) | Trolley grate inclination angle detection method and system of sintering machine | |
| CN113298751A (en) | Detection method for auxiliary door blockage | |
| CN112634179A (en) | Transformer equipment image change detection method and system for preventing camera shake | |
| CN116977299A (en) | Automated control system for casting and method thereof | |
| CN116258680A (en) | Processing method of abnormal monitoring image of blanking of sintering belt | |
| O’Donovan et al. | Ladle pouring process parameter and quality estimation using Mask R-CNN and contrast-limited adaptive histogram equalisation | |
| CN114663365A (en) | Defect detection method, device and computer storage medium | |
| CN113963291A (en) | Coal-fired working condition identification method based on video image quality and model modeling method thereof | |
| Xie et al. | Tobacco plant recognizing and counting based on svm | |
| CN109214390B (en) | Fence state detection method and system based on machine vision principle | |
| CN114091250A (en) | Method, device and equipment for adjusting temperature of die and storage medium | |
| CN111223095B (en) | Trolley grate spacing detection method and system for sintering machine | |
| Chen et al. | Deep learning for hot rolled steel surface rust defects detection | |
| TW202040428A (en) | Workpiece recognition and tracking system of 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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210824 |