CN110659697A - Quality abnormity monitoring and diagnosing method and system in plate coating process - Google Patents
Quality abnormity monitoring and diagnosing method and system in plate coating process Download PDFInfo
- Publication number
- CN110659697A CN110659697A CN201910934173.3A CN201910934173A CN110659697A CN 110659697 A CN110659697 A CN 110659697A CN 201910934173 A CN201910934173 A CN 201910934173A CN 110659697 A CN110659697 A CN 110659697A
- Authority
- CN
- China
- Prior art keywords
- plate
- quality image
- network model
- deep learning
- quality
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/02—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring length, width, or thickness
- G01B21/08—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring length, width, or thickness for measuring thickness
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a quality abnormity monitoring and diagnosing method and system in a plate coating process, wherein the monitoring and diagnosing method comprises the following steps: establishing a deep learning network model for representing the mapping relation between the quality image and the abnormal category; the deep learning network model comprises a first convolution layer, a first pooling layer, a second convolution layer, a second pooling layer and a full-connection layer; obtaining a quality image sample of the polar plate, and training the deep learning network model by adopting the quality image of the polar plate to obtain a trained deep learning network model; detecting the thickness of the polar plate in the plate coating process, and obtaining a quality image of the polar plate according to the thickness of the polar plate; and then, inputting the quality image of the pole plate into the trained deep learning network model to obtain the abnormal category of the pole plate. The technical scheme provided by the invention can identify the abnormal category of the plate through the thickness change of the plate when monitoring the quality of the plate coating process.
Description
Technical Field
The invention belongs to the technical field of quality detection in a plate coating process of a polar plate, and particularly relates to a quality abnormity monitoring and diagnosing method and system in the plate coating process.
Background
The plate coating process is a process of forming a polar plate by lead plaster and a grid, the formed polar plate is a main part of electrochemical reaction of the lead-acid storage battery, and the quality of the polar plate directly influences the service life and the electric capacity of the battery. The thickness is a key quality characteristic in the plate coating process, and the uneven coating thickness in the plate coating process can have an important influence on the matching rate of the plates, so that the performance of the battery is influenced.
At present, a quality abnormity monitoring and diagnosing method in a lead-acid storage battery plate coating process is generally monitored by using a control chart firstly. If the alarm is controlled, the operator intervenes to search the alarm reason again and eliminate the alarm reason. The hysteresis of control chart alarms makes it difficult to use in an automated production line.
The invention discloses an on-line monitoring device for a plate coating process, which is disclosed in Chinese patent with the publication number of CN207263278U, and comprises an electronic scale, a display screen and a main computer, wherein each plate is weighed, and data is transmitted to the screen and the main computer. When the main computer finds that the weight of the pole plate is close to or exceeds the tolerance limit, an alarm is triggered, the monitored weight value can be displayed on a screen, and an operator needs to adjust the parameters of the plate coating machine. The disadvantages of this method are: the plate coating process has the characteristic of high corrosion, most of electronic scales are in contact type, and the corrosion of strong acid can cause the damage of the electronic scales and further cause the unreliability of weighing results. And this detection method is difficult to use in an automated plate coating line. The automatic plate coating line can produce 150 polar plates at 120-. The coating process itself is not very accurate, and the method only concerns whether the measured value of a single plate exceeds the tolerance limit, and once the tolerance limit is exceeded, the coating adjustment may cause over-adjustment, thereby causing instability of the process.
The chinese patent of invention with the publication number of CN201607195U discloses a device for measuring the thickness of a polar plate, which can conveniently and effectively measure the height and thickness of the polar plate stack, and overcomes the disadvantages of the vernier caliper. Although the device has low cost, the quality of the polar plate can be detected only by a sampling mode, and the device cannot meet the production line with increasingly improved automation degree.
The replacement of the online monitoring and diagnosing device is mostly completed in the plate coating process, but an advanced monitoring and diagnosing method is not used as a complete set at present, and the real production intellectualization is difficult to realize. The control chart method can only identify the normality and abnormality of the process, can not identify the abnormality type and is difficult to diagnose in the next step.
In summary, the problem that the abnormal category cannot be identified exists when the quality of the plate coating process is monitored in the prior art.
Disclosure of Invention
The invention aims to provide a quality abnormity monitoring and diagnosing method and system in a plate coating process, which aim to solve the problem that the abnormity category cannot be identified when the quality of the plate coating process is monitored in the prior art.
In order to achieve the purpose, the invention adopts the following technical scheme:
a quality abnormity monitoring and diagnosing method for a plate coating process is characterized by comprising the following steps:
(1) establishing a deep learning network model for representing the mapping relation between the quality image and the abnormal category; the deep learning network model comprises a first convolution layer, a first pooling layer, a second convolution layer, a second pooling layer and a full-connection layer;
(2) obtaining a quality image sample of the polar plate, and training the deep learning network model by adopting the quality image of the polar plate to obtain a trained deep learning network model;
(3) detecting the thickness of the polar plate in the plate coating process, and obtaining a quality image of the polar plate according to the thickness of the polar plate; and then, inputting the quality image of the pole plate into the trained deep learning network model to obtain the abnormal category of the pole plate.
Further, the method for obtaining the quality image sample of the polar plate comprises the following steps:
obtaining thickness data samples of the electrode plate from historical data;
carrying out normalization processing on the thickness data samples, and carrying out cluster analysis on the thickness data samples after the normalization processing;
and mapping the thickness data sample of the polar plate after the clustering analysis to the gray level image to obtain a quality image sample of the polar plate.
Further, multiplying the thickness data sample after the cluster analysis by 255 and then rounding to obtain a quality image sample of the pole plate.
Further, after the quality image of the pole plate is input into the trained deep learning network model, the probability that the quality image of the pole plate belongs to each abnormal class is obtained, and the abnormal class with the maximum probability is used as the abnormal class corresponding to the quality image.
A quality anomaly monitoring and diagnosis system for a sheet coating process includes a processor and a memory having stored thereon a computer program for execution on the processor; when the processor executes the computer program, the following steps are realized:
(1) establishing a deep learning network model for representing the mapping relation between the quality image and the abnormal category; the deep learning network model comprises a first convolution layer, a first pooling layer, a second convolution layer, a second pooling layer and a full-connection layer;
(2) obtaining a quality image sample of the polar plate, and training the deep learning network model by adopting the quality image of the polar plate to obtain a trained deep learning network model;
(3) detecting the thickness of the polar plate in the plate coating process, and obtaining a quality image of the polar plate according to the thickness of the polar plate; and then, inputting the quality image of the pole plate into the trained deep learning network model to obtain the abnormal category of the pole plate.
Further, the method for obtaining the quality image sample of the polar plate comprises the following steps:
obtaining thickness data samples of the electrode plate from historical data;
carrying out normalization processing on the thickness data samples, and carrying out cluster analysis on the thickness data samples after the normalization processing;
and mapping the thickness data sample of the polar plate after the clustering analysis to the gray level image to obtain a quality image sample of the polar plate.
Further, multiplying the thickness data sample after the cluster analysis by 255 and then rounding to obtain a quality image sample of the pole plate.
Further, after the quality image of the pole plate is input into the trained deep learning network model, the probability that the quality image of the pole plate belongs to each abnormal class is obtained, and the abnormal class with the maximum probability is used as the abnormal class corresponding to the quality image.
The invention has the beneficial effects that: according to the technical scheme provided by the invention, a deep learning network model used for representing the mapping relation between the quality image and the abnormal category is established, then the thickness of the polar plate in the plate coating process is detected, the quality image of the polar plate is obtained according to the thickness of the polar plate, and finally the abnormal category of the coated plate is obtained by combining the deep learning network model. The technical scheme provided by the invention can identify the abnormal category of the plate through the thickness of the plate when monitoring the quality of the plate coating process.
Drawings
FIG. 1 is a schematic structural view of a coating process production line in an embodiment of the method of the present invention;
FIG. 2 is a flow chart of a quality anomaly monitoring and diagnosis method of a plating process in an embodiment of the method of the present invention.
Detailed Description
The method comprises the following steps:
the embodiment provides a quality abnormity monitoring and diagnosing method in a plate coating process, which is used for solving the problem of poor monitoring effect on the plate coating process in the prior art.
In the method for monitoring and diagnosing quality abnormality of a plate coating process provided by the embodiment, a plate coating process production line is shown in fig. 1, and a coating machine 1, an acid spraying nozzle 2, a laser thickness gauge 4 and a surface dryer 5 are installed on the production line. The grid 7 is placed on the conveyor belt, the lead paste 6 is output from the plate coating machine 1 and coated on the grid 7 on the conveyor belt to form the polar plate 3, the acid spraying nozzle 2 sprays acid on the polar plate 3, and the laser thickness gauge 4 detects the thickness of the polar plate 3 on the conveyor belt. The conveyor belt transports the plates 3 into a surface dryer 5 for drying.
The flow of the quality anomaly monitoring and diagnosing method for the plate coating process provided by the embodiment is shown in fig. 1, and the method comprises the following steps:
(1) and establishing a deep learning network model for representing the mapping relation between the pole plate quality image and the abnormal category.
The deep learning network model established in the embodiment is a convolutional neural network model, and the structure of the deep learning network model comprises a first convolutional layer, a first pooling layer, a second convolutional layer, a second pooling layer and a full-link layer, wherein the deep learning network model inputs a quality image of a polar plate and outputs an abnormal category to which the quality image belongs. Wherein, the number of convolution kernels of the first convolution layer is set to be 25, and the size of the convolution kernels is 3 multiplied by 3; the pooling function of the first pooling layer is maximum pooling; the number of convolution kernels of the second convolution layer is set to be 50, and the size of the convolution kernels is 3 multiplied by 3; the pooling function of the second pooling layer is maximum pooling; the number of nodes of the fully connected layer is 200.
(2) Obtaining a thickness data sample of the pole plate, obtaining a quality image sample of the pole plate according to the thickness data sample of the pole plate, and training the established deep learning network model by adopting the quality image sample to obtain the trained deep learning network model.
In the embodiment, the thickness data sample of the plate is obtained by adopting the laser thickness gauge in the time period T1Wherein the plate coating machine produces a plate at each moment, wherein in the time interval T1＝{t1,t2,...,tn}. The laser thickness gauge collects the thickness of the polar plates, wherein each polar plate carries out thickness measurement on different positions to obtain test data.
The thickness data obtained at time T1 were:
the thickness data obtained at time T2 were:
if the server has historical thickness data at S moments, the historical thickness data are divided into S-29 data arrays which are respectively { X1,X2,...,Xs-29}。
Will { X1,X2,...,Xs-29Normalizing each matrix sample in the data matrix respectively to obtain normalized historical data (X)1’,X2’,...,Xs-29' }, and then performing clustering analysis on the samples by adopting a Kmeans clustering algorithm:
k central points are selected, and K can be determined according to the operation experience of workers or the number of abnormal reason types in historical data;
traversing S-29 analysis samples, and dividing each sample to the nearest central point to obtain K clusters;
calculating the average value of each cluster, and taking the average value as a new central point;
the above process is repeated until the center point of each cluster is no longer changed.
So that K quality abnormal modes and corresponding sample sets can be obtained, and the category y of each sample is marked to form a sample set { (X)1,y1),(X2,y2),...,(XS-29,yS-29)}. Each abnormal mode corresponds to a specific abnormal reason of the plate coating process.
Respectively mapping the normalized sample sets to a gray-scale image, namely multiplying each element by 255 and then rounding to obtain a process picture, wherein the calculation formula is as follows:
Gi＝round(X'i×255)
(3) and training the established deep learning network model by using the process map to obtain the trained deep learning network model.
Firstly, randomly initializing a weight w and a bias value b in a deep learning network model, and initializing a random number with a value of (0, 1), wherein an existing sample set is defined as a training set and is input into the deep learning network model in batches, the sample amount of each batch is 30, the output probability P j of the deep learning network model of each sample is obtained, a Loss function corresponding to each sample is calculated according to an expected output probability Pj, and if the sample Loss is Loss, the calculation formula is as follows:
and calculating the partial derivatives of the weights and the bias by a back propagation algorithm and updating, wherein the calculation formula is as follows:
wherein wtAnd wt-1Weights for the t-th and t-1 updates, respectively, btAnd bt-1The offset values are respectively at the t-th and t-1 updates.
When all training samples are input into the deep learning network model, one cycle is completed. And training the network for a plurality of periods, and stopping until the performance reaches the optimal value. And storing the deep learning network model corresponding to the optimal network parameter for subsequent anomaly monitoring and diagnosis.
(4) And detecting the thickness of the pole plate in the plate coating process, obtaining a pole plate map according to the thickness of the pole plate, and inputting the pole plate map into a trained deep learning network model to obtain the abnormal type of the pole plate.
The embodiment of the system is as follows:
the embodiment provides a quality abnormity monitoring and diagnosing system for a plate coating process, which comprises a processor and a memory, wherein the memory is stored with a computer program for being executed on the processor, and when the processor executes the computer program, the quality abnormity monitoring and diagnosing method for the plate coating process provided in the embodiment of the method is realized.
Claims (8)
1. A quality abnormity monitoring and diagnosing method for a plate coating process is characterized by comprising the following steps:
(1) establishing a deep learning network model for representing the mapping relation between the quality image and the abnormal category; the deep learning network model comprises a first convolution layer, a first pooling layer, a second convolution layer, a second pooling layer and a full-connection layer;
(2) obtaining a quality image sample of the polar plate, and training the deep learning network model by adopting the quality image of the polar plate to obtain a trained deep learning network model;
(3) detecting the thickness of the polar plate in the plate coating process, and obtaining a quality image of the polar plate according to the thickness of the polar plate; and then, inputting the quality image of the pole plate into the trained deep learning network model to obtain the abnormal category of the pole plate.
2. The method for monitoring and diagnosing the quality abnormality in the plate coating process according to claim 1, wherein the method for acquiring the quality image sample of the plate comprises the following steps:
obtaining thickness data samples of the electrode plate from historical data;
carrying out normalization processing on the thickness data samples, and carrying out cluster analysis on the thickness data samples after the normalization processing;
and mapping the thickness data sample of the polar plate after the clustering analysis to the gray level image to obtain a quality image sample of the polar plate.
3. The method for monitoring and diagnosing the quality abnormality in the plate coating process according to claim 2, wherein the thickness data samples after the cluster analysis are multiplied by 255 and then rounded to obtain quality image samples of the plate.
4. The quality anomaly monitoring and diagnosis method in the plate coating process according to claim 1, wherein the probability that the plate quality image belongs to each anomaly class is obtained after the quality image of the plate is input into the trained deep learning network model, and the anomaly class with the highest probability is used as the anomaly class corresponding to the quality image.
5. A quality anomaly monitoring and diagnosis system for a sheet coating process includes a processor and a memory having stored thereon a computer program for execution on the processor; wherein the processor, when executing the computer program, implements the steps of:
(1) establishing a deep learning network model for representing the mapping relation between the quality image and the abnormal category; the deep learning network model comprises a first convolution layer, a first pooling layer, a second convolution layer, a second pooling layer and a full-connection layer;
(2) obtaining a quality image sample of the polar plate, and training the deep learning network model by adopting the quality image of the polar plate to obtain a trained deep learning network model;
(3) detecting the thickness of the polar plate in the plate coating process, and obtaining a quality image of the polar plate according to the thickness of the polar plate; and then, inputting the quality image of the pole plate into the trained deep learning network model to obtain the abnormal category of the pole plate.
6. A quality anomaly monitoring and diagnosis system in a coating process according to claim 5, wherein the method for obtaining quality image samples of the pole plate comprises the following steps:
obtaining thickness data samples of the electrode plate from historical data;
carrying out normalization processing on the thickness data samples, and carrying out cluster analysis on the thickness data samples after the normalization processing;
and mapping the thickness data sample of the polar plate after the clustering analysis to the gray level image to obtain a quality image sample of the polar plate.
7. The system for monitoring and diagnosing quality abnormality in a plate coating process according to claim 2, wherein the thickness data samples after the cluster analysis are multiplied by 255 and then rounded to obtain quality image samples of the plate.
8. The system for monitoring and diagnosing quality abnormality in a plate coating process according to claim 1, wherein the probability that the quality image of the plate belongs to each abnormal class is obtained after the quality image of the plate is input into the trained deep learning network model, and the abnormal class with the highest probability is used as the abnormal class corresponding to the quality image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910934173.3A CN110659697A (en) | 2019-09-29 | 2019-09-29 | Quality abnormity monitoring and diagnosing method and system in plate coating process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910934173.3A CN110659697A (en) | 2019-09-29 | 2019-09-29 | Quality abnormity monitoring and diagnosing method and system in plate coating process |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110659697A true CN110659697A (en) | 2020-01-07 |
Family
ID=69039866
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910934173.3A Pending CN110659697A (en) | 2019-09-29 | 2019-09-29 | Quality abnormity monitoring and diagnosing method and system in plate coating process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110659697A (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001232265A (en) * | 2000-02-21 | 2001-08-28 | Nippon Steel Corp | Method for deciding coating condition and apparatus for monitoring coating quality |
| CN202956623U (en) * | 2012-11-23 | 2013-05-29 | 凯迈（江苏）机电有限公司 | Pole piece coating production line and pole piece coating quality online marking device |
| CN204214404U (en) * | 2014-11-24 | 2015-03-18 | 天津力神电池股份有限公司 | The detection system of the slurry coating width of electrodes of lithium-ion batteries |
| CN107507330A (en) * | 2017-08-17 | 2017-12-22 | 深圳怡化电脑股份有限公司 | Detection method, detection means and the terminal device of banknote thickness abnormity |
| CN109212617A (en) * | 2018-08-24 | 2019-01-15 | 中国石油天然气股份有限公司 | Automatic identification method and device for electric imaging logging phase |
| CN109724984A (en) * | 2018-12-07 | 2019-05-07 | 上海交通大学 | A kind of defects detection identification device and method based on deep learning algorithm |
| CN110196021A (en) * | 2019-01-16 | 2019-09-03 | 苏州大学 | Coating layer thickness and its application are measured based on Optical coherence tomography technology |
-
2019
- 2019-09-29 CN CN201910934173.3A patent/CN110659697A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2001232265A (en) * | 2000-02-21 | 2001-08-28 | Nippon Steel Corp | Method for deciding coating condition and apparatus for monitoring coating quality |
| CN202956623U (en) * | 2012-11-23 | 2013-05-29 | 凯迈（江苏）机电有限公司 | Pole piece coating production line and pole piece coating quality online marking device |
| CN204214404U (en) * | 2014-11-24 | 2015-03-18 | 天津力神电池股份有限公司 | The detection system of the slurry coating width of electrodes of lithium-ion batteries |
| CN107507330A (en) * | 2017-08-17 | 2017-12-22 | 深圳怡化电脑股份有限公司 | Detection method, detection means and the terminal device of banknote thickness abnormity |
| CN109212617A (en) * | 2018-08-24 | 2019-01-15 | 中国石油天然气股份有限公司 | Automatic identification method and device for electric imaging logging phase |
| CN109724984A (en) * | 2018-12-07 | 2019-05-07 | 上海交通大学 | A kind of defects detection identification device and method based on deep learning algorithm |
| CN110196021A (en) * | 2019-01-16 | 2019-09-03 | 苏州大学 | Coating layer thickness and its application are measured based on Optical coherence tomography technology |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111461555B (en) | Production line quality monitoring method, device and system | |
| CN109389145B (en) | Electric energy meter manufacturer evaluation method based on metering big data clustering model | |
| CN106886213B (en) | A kind of batch process fault detection method based on core similarity Support Vector data description | |
| CN113447828B (en) | Lithium battery temperature estimation method and system based on Bayesian neural network | |
| CN107679715A (en) | A kind of electric energy meter comprehensive error process merit rating method and evaluation system based on SPC | |
| CN117932501B (en) | Electric energy meter running state management method and system | |
| US20220243347A1 (en) | Determination method and determination apparatus for conversion efficiency of hydrogen production by wind-solar hybrid electrolysis of water | |
| CN117330963B (en) | Energy storage power station fault detection method, system and equipment | |
| CN103279030B (en) | Dynamic soft measuring modeling method and device based on Bayesian frame | |
| CN110659697A (en) | Quality abnormity monitoring and diagnosing method and system in plate coating process | |
| CN116502526A (en) | Improved PSO-GRNN neural network-based weighing sensor fault diagnosis method | |
| CN116581883A (en) | Power distribution network line loss assessment method and device based on neural network | |
| CN109614758A (en) | The monitoring method of circular shape error with spatial coherence | |
| CN106952842A (en) | Sample measurement system and its sampling method for measurement | |
| CN109493065A (en) | A kind of fraudulent trading detection method of Behavior-based control incremental update | |
| CN109858699B (en) | Water quality quantitative simulation method and device, electronic equipment and storage medium | |
| CN106093329B (en) | Method for improving reliability of water quality monitoring data with controllable error correction capability | |
| CN109931987A (en) | A kind of intelligent vegetable planting machine environment based on cloud precisely monitors system and method | |
| CN113095340B (en) | Abnormality early warning method of production machine and mass production method of objects | |
| CN117685879B (en) | Full-automatic image measuring instrument detecting system | |
| CN118261451B (en) | Intelligent motor production monitoring method and system based on data feedback | |
| CN117590242B (en) | Method and device for detecting consistency of galvanic pile, storage medium and electronic device | |
| CN112240979B (en) | Method for detecting voltage critical point of lithium ion battery, electronic terminal and storage medium | |
| CN117525491A (en) | Dimension reduction simplifying method, device, equipment and medium for fuel cell stack model | |
| CN117521522A (en) | Voltage sag economic loss assessment method, device and equipment |
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 |
Application publication date: 20200107 |
|
| RJ01 | Rejection of invention patent application after publication |