CN116404186A - Power lithium-manganese battery production system - Google Patents
Power lithium-manganese battery production system Download PDFInfo
- Publication number
- CN116404186A CN116404186A CN202310670582.3A CN202310670582A CN116404186A CN 116404186 A CN116404186 A CN 116404186A CN 202310670582 A CN202310670582 A CN 202310670582A CN 116404186 A CN116404186 A CN 116404186A
- Authority
- CN
- China
- Prior art keywords
- lithium
- data
- manganese
- battery production
- manganese battery
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- KLARSDUHONHPRF-UHFFFAOYSA-N [Li].[Mn] Chemical compound [Li].[Mn] KLARSDUHONHPRF-UHFFFAOYSA-N 0.000 title claims abstract description 251
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 214
- 238000000034 method Methods 0.000 claims abstract description 61
- 230000002159 abnormal effect Effects 0.000 claims abstract description 50
- 230000000694 effects Effects 0.000 claims abstract description 39
- 238000011156 evaluation Methods 0.000 claims abstract description 35
- 238000012544 monitoring process Methods 0.000 claims abstract description 31
- 230000008569 process Effects 0.000 claims abstract description 30
- 230000005856 abnormality Effects 0.000 claims abstract description 14
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 9
- 238000013075 data extraction Methods 0.000 claims abstract description 8
- 238000001914 filtration Methods 0.000 claims abstract description 5
- 239000011159 matrix material Substances 0.000 claims description 15
- 238000010606 normalization Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 238000003064 k means clustering Methods 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 abstract description 2
- 230000001276 controlling effect Effects 0.000 abstract 1
- NUJOXMJBOLGQSY-UHFFFAOYSA-N manganese dioxide Chemical compound O=[Mn]=O NUJOXMJBOLGQSY-UHFFFAOYSA-N 0.000 description 4
- 239000000284 extract Substances 0.000 description 3
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 2
- WHXSMMKQMYFTQS-UHFFFAOYSA-N Lithium Chemical compound [Li] WHXSMMKQMYFTQS-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000001035 drying Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 229910052744 lithium Inorganic materials 0.000 description 2
- FBDMJGHBCPNRGF-UHFFFAOYSA-M [OH-].[Li+].[O-2].[Mn+2] Chemical compound [OH-].[Li+].[O-2].[Mn+2] FBDMJGHBCPNRGF-UHFFFAOYSA-M 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 239000008151 electrolyte solution Substances 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052757 nitrogen Inorganic materials 0.000 description 1
- 239000005486 organic electrolyte Substances 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000000243 solution Substances 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M6/00—Primary cells; Manufacture thereof
- H01M6/14—Cells with non-aqueous electrolyte
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M6/00—Primary cells; Manufacture thereof
- H01M6/005—Devices for making primary cells
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/10—Energy storage using batteries
Abstract
The invention relates to the field of lithium-manganese battery production, in particular to a power lithium-manganese battery production system, which comprises a multi-sensor device of the lithium-manganese battery production system, an abnormal data extraction device of the lithium-manganese battery production system and an early warning device of the lithium-manganese battery production system, wherein the multi-sensor device acquires relevant parameter data of a lithium-manganese battery production line and calculates neighborhood distribution indexes of all the data; obtaining the deviation degree of each data according to the neighborhood distribution index, extracting noise points and filtering; clustering the related parameter data sequentially through a clustering algorithm, obtaining a clustering effect evaluation coefficient according to the relation among the clustering clusters in the clustering process of the related parameter data, regulating and controlling the clustering process, obtaining an optimal clustering result, calculating the abnormality degree of the related parameters of the lithium-manganese battery production line, and further obtaining an abnormality early warning value of the lithium-manganese battery production system; and (5) monitoring a lithium-manganese battery production system. Therefore, the monitoring of a power lithium-manganese battery production system is realized, and the production efficiency of the lithium-manganese battery is improved.
Description
Technical Field
The application relates to the field of lithium-manganese battery production, in particular to a power lithium-manganese battery production system.
Background
Lithium-manganese batteries are typically referred to as lithium manganese dioxide batteries, which are a typical class of organic electrolyte lithium batteries that use lithium as the negative electrode and manganese dioxide as the positive electrode. The manganese dioxide battery has good low-rate and medium-rate discharge performance, low price, good safety performance and stronger competitiveness compared with the conventional battery.
With the progress of technology and the development of society, the demand of society for lithium-manganese batteries is increasing, and therefore, improving the yield of lithium-manganese batteries is an important problem. The production efficiency of the production line is improved through monitoring and analysis of the lithium-manganese battery production line, so that the social requirement of the lithium-manganese battery can be relieved to a certain extent. The operation condition of each data of the production line on the production site is monitored, so that the production condition of the lithium-manganese battery is monitored.
In summary, the present invention provides a power type lithium-manganese battery production system, wherein a plurality of sensors are deployed in the production of the power type lithium-manganese battery, the production line of the lithium-manganese battery is monitored, the production status of each parameter data in the production of the lithium-manganese battery is analyzed, and each parameter data is analyzed, so as to monitor the production process of the lithium-manganese battery, and improve the production efficiency of the lithium-manganese battery.
Disclosure of Invention
In order to solve the technical problems, the invention provides a power lithium-manganese battery production system, which comprises:
the system comprises a multi-sensor device of a manganese lithium battery production system, an abnormal data extraction device of the manganese lithium battery production system and an early warning device of the manganese lithium battery production system;
a multi-sensor device of a manganese lithium battery production system: the sensor collects related parameter data of the manganese lithium battery production line and constructs a manganese lithium battery production line monitoring matrix;
abnormal data extraction device of manganese lithium battery production system: obtaining neighborhood distribution indexes of each data according to the data distribution conditions in each data neighborhood range; obtaining the deviation degree of each data according to the neighborhood distribution index of each data; taking the data with the deviation degree higher than the deviation threshold value as noise points and filtering; selecting a clustering center point of each manganese lithium battery production line related parameter data cluster, and obtaining a clustering distance according to the relation between the data of each manganese lithium battery production line related parameter and the clustering center point; carrying out cluster analysis on the data of the relevant parameters of each manganese lithium battery in sequence by combining the cluster distance and a K-means clustering algorithm, and obtaining a clustering effect evaluation coefficient of the relevant parameters of the manganese lithium battery according to the relation among the clusters of the relevant parameter data of the manganese lithium battery; obtaining the optimal clustering division result of the relevant parameters of each manganese lithium battery according to the clustering effect evaluation coefficient of the relevant parameters of each manganese lithium battery; obtaining the abnormality degree of the relevant parameters of each lithium-manganese battery production line according to the relation among the clustering clusters corresponding to the relevant parameters of each lithium-manganese battery production line;
early warning device of manganese lithium battery production system: obtaining abnormal early warning values of the lithium-manganese battery production system according to the abnormal degree of the related parameters of each lithium-manganese battery production line; and monitoring results of the lithium-manganese battery production system are obtained according to the abnormal early warning value of the lithium-manganese battery production system.
Preferably, the neighborhood distribution index of each data is obtained according to the data distribution condition in each data neighborhood range, and the expression is:
in the method, in the process of the invention,for data->Domain distribution index of>Representing a functional relationship->For all data sets of the relevant parameters p of the lithium-manganese battery production line,/for the lithium-manganese battery production line>Respectively corresponding data of relevant parameters p of the lithium-manganese battery production line at data acquisition time a and data acquisition time b, < + >>For data->Absolute value of difference between>A data difference cutoff distance.
Preferably, the deviation degree of each data is obtained according to the neighborhood distribution index of each data, and the expression is:
in the method, in the process of the invention,for data->Degree of deviation of->For data->Domain distribution index of>To avoid minima with denominator zero, < ->A threshold is distributed for the neighborhood.
Preferably, the clustering distance is obtained according to the relation between the data of the related parameters of each manganese lithium battery production line and the clustering center point, and the expression is:
in the method, in the process of the invention,for clustering distance->For data->And cluster center point->Is used to determine the absolute value of the data difference value of (c),for data->And cluster center point->Euclidean distance between the coordinate information of (a).
Preferably, the clustering effect evaluation coefficient of the relevant parameters of the lithium manganese battery is obtained according to the relation among the clustering clusters of the relevant parameter data of the lithium manganese battery, and the expression is as follows:
in the method, in the process of the invention,evaluating coefficients for the clustering effect of the manganese-lithium battery related parameter p,/->Respectively clustering center points of two clustered classes, S is the number of clustered classes, and +.>For data->Data->Euclidean distance between coordinate information of (2),. About.>For data->Absolute value of difference between>Cluster center for category s +.>Data within category s->Euclidean distance between coordinate information of (2),. About.>For category s and data->The same number of data>Is the total number of data within category s.
Preferably, the obtaining the optimal clustering result of the relevant parameters of each manganese lithium battery according to the clustering effect evaluation coefficient of the relevant parameters of each manganese lithium battery includes the following specific steps: and carrying out normalization processing on the clustering effect evaluation coefficients of the relevant parameter data of each manganese lithium battery, setting an evaluation coefficient threshold value, and taking the clustering result of the relevant parameter data of each manganese lithium battery corresponding to the clustering evaluation coefficient higher than the evaluation coefficient threshold value as the optimal clustering cluster dividing result.
Preferably, the abnormality degree of the relevant parameters of each lithium-manganese battery production line is obtained according to the relation among the clusters corresponding to the relevant parameters of each lithium-manganese battery production line, and the specific expression is as follows:
in the method, in the process of the invention,clustering cluster set of relevant parameters p of lithium-manganese battery production line>The maximum cluster data mean value and the minimum cluster data mean value in the related parameter p cluster set of the lithium-manganese battery production line are respectively,clustering center points of two clusters of related parameters p of lithium-manganese battery production line respectively are +.>For normalization operations, ++>The abnormal degree of the related parameter p of the lithium-manganese battery production line.
Preferably, the abnormal early warning value of the lithium-manganese battery production system is obtained according to the abnormal degree of the related parameters of each lithium-manganese battery production line, and the specific expression is as follows:
in the method, in the process of the invention,weight factor of relevant parameter p of lithium-manganese battery production line, < ->For the abnormality degree of the related parameter p of the lithium-manganese battery production line, < >>The abnormal early warning value of the lithium-manganese battery production system is obtained.
Preferably, the monitoring result of the lithium-manganese battery production system is obtained according to the abnormal early warning value of the lithium-manganese battery production system, and the specific steps are as follows:
and carrying out normalization processing on abnormal early-warning values of the lithium-manganese battery production system, setting an early-warning threshold value, setting an abnormal degree threshold value of related parameters of the lithium-manganese battery production line, sending out early warning when the abnormal early-warning values of the lithium-manganese battery production system are higher than the early-warning threshold value, prompting related operators to detect and maintain the related parameters of the lithium-manganese battery production line with the abnormal degree higher than the abnormal degree threshold value, and completing monitoring of the lithium-manganese battery production system.
The invention has at least the following beneficial effects:
the invention realizes the monitoring of the manganese lithium battery production system and improves the production efficiency of the manganese lithium battery by analyzing the data of each related parameter in the production process of the manganese lithium battery. According to the method, neighborhood distribution indexes are calculated by combining data distribution conditions of each data neighborhood range, the deviation degree of each data is obtained, noise points in relevant parameters of each lithium-manganese battery production line are extracted and filtered according to the deviation degree of the data, the influence of the noise points in relevant parameter data of each lithium-manganese battery production line is solved, the influence of the noise points on the data clustering precision is avoided, and the data purity is improved;
for the problem that the conventional clustering precision is low and the clustering effect cannot be guaranteed, the clustering effect evaluation coefficient is constructed according to the effect after each clustering, the clustering process of the related parameter data of each lithium-manganese battery production line is adaptively regulated and controlled by combining the clustering effect evaluation coefficient, the clustering precision is improved, the clustering time is shortened, and the problems of multiple times and low precision of the conventional clustering iteration are solved. The invention has higher monitoring precision of the power type manganese lithium battery production system, ensures the normal operation of the manganese lithium battery production system, and can effectively improve the production efficiency of the manganese lithium battery.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a power lithium-manganese battery production system provided by the invention.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following detailed description refers to the specific implementation, structure, characteristics and effects of a power lithium-manganese battery production system according to the invention with reference to the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
The following specifically describes a specific scheme of the power lithium-manganese battery production system provided by the invention with reference to the accompanying drawings.
The invention provides a power lithium-manganese battery production system, which comprises a data acquisition module, a data processing module and an early warning module.
Specifically, the system for producing a power lithium-manganese battery of the present embodiment provides a method for producing a power lithium-manganese battery, referring to fig. 1, comprising the following steps:
step S001, a multi-sensor device of a manganese lithium battery production system.
The multi-sensor device of the manganese lithium battery production system is used for collecting data of relevant parameters of a lithium-manganese battery production line and obtaining data monitored by the lithium-manganese battery production line. In the embodiment, the production line of the manganese lithium battery is monitored mainly through detection and analysis of the parameter data in the production process of the manganese lithium battery. The embodiment aims at monitoring the data of the related parameters of the manganese lithium battery production line in real time, extracting abnormal data and realizing the monitoring of the manganese lithium battery production line. It should be noted that there are many parameters related to the lithium-manganese battery production line, including but not limited to the concentration of each formulation of the electrolyte solution, the concentration of nitrogen produced by the lithium-manganese battery, the drying temperature, the drying humidity, etc., and the number of parameters related to the lithium-manganese battery production line is denoted as M, and the parameter data of the lithium-manganese battery production line is collected by the corresponding sensor to obtain the data of each parameter. It should be noted that the sensor type and the location deployment implementation can select the setting by themselves. The installation position of each sensor in the multi-sensor device on the manganese lithium battery production line can be automatically deployed according to actual conditions. In order to avoid the power consumption in the data acquisition process of the sensor, and meanwhile, to consider that the change of the data of each parameter in the lithium-manganese battery production process has certain continuity, the implementation sets a data acquisition time interval t, namely, data of each parameter is acquired once every time interval t, N times of data are acquired for each parameter, the embodiment is set to t=1, N=500, and other embodiments can be set by an implementer according to the actual self.
After acquiring data of each parameter related to a lithium-manganese battery production line, the embodiment constructs a lithium-manganese battery production line monitoring matrix according to the data of each parameter, uses the data of each parameter as each row of the lithium-manganese battery production line monitoring matrix, and the data of M parameters can form a lithium-manganese battery production line monitoring matrix with M x N, wherein the lithium-manganese battery production line monitoring matrix specifically comprises:
in the method, in the process of the invention,is the data of the relevant parameter M of the lithium-manganese battery production line at the data acquisition time N, wherein (/ -for the relevant parameter M)>) Also data->And K is the monitoring matrix of the lithium-manganese battery production line.
So far, the data of each parameter related to the lithium-manganese battery production line can be acquired by each data acquisition sensor, and a lithium-manganese battery production line matrix can be obtained.
Step S002, an abnormal data extraction device of the manganese lithium battery production system.
And the abnormal data extraction device of the manganese lithium battery production system processes related parameter data of the lithium-manganese battery production line and detects the abnormality to extract abnormal data of the manganese lithium battery production process. And analyzing the obtained lithium-manganese battery production line monitoring matrix to detect and extract abnormal data, so as to monitor the lithium-manganese battery production line and ensure the high-efficiency operation of a lithium-manganese battery production system. The specific process of the data processing module is as follows:
in order to avoid the problem of low abnormal data extraction precision caused by the mutual influence of different parameters in the lithium-manganese battery production process, the embodiment sequentially analyzes the relevant parameters of each lithium-manganese battery production line in the lithium-manganese battery production line monitoring matrix, namely independently analyzes the data of the relevant parameters of each lithium-manganese battery production line so as to detect the abnormal conditions of the relevant parameters of the lithium-manganese battery production line;
for relevant parameters of each lithium-manganese battery production line of the lithium-manganese battery production line monitoring matrix, in the embodiment, data in relevant parameters of each lithium-manganese battery production line are clustered and divided through a clustering algorithm, in order to improve data class division precision and avoid influences of noise points on data class division, the embodiment firstly extracts the noise points in relevant parameters of each lithium-manganese battery production line so as to prevent the noise points from influencing each clustering class. Taking a parameter p related to a lithium-manganese battery production line of a lithium-manganese battery production line monitoring matrix as an example, the embodiment extracts the data of the noise points in the lithium-manganese battery production line:
for each data in the relevant parameters p of the lithium-manganese battery production line, the embodiment calculates the neighborhood distribution index of each data according to the data distribution condition in the neighborhood range of each data, and obtains the neighborhood distribution index of each data according to the data distribution condition in the neighborhood range of each data, wherein the neighborhood distribution index expression is as follows:
in the method, in the process of the invention,for data->Domain distribution index of>Representing a functional relationship->For all data sets of the relevant parameters p of the lithium-manganese battery production line,/for the lithium-manganese battery production line>Respectively corresponding data of relevant parameters p of the lithium-manganese battery production line at data acquisition time a and data acquisition time b, < + >>For data->Absolute value of difference between>Data difference cut-off distance, +.>The value of (a) can be set by the practitioner himself, and the embodiment is set as +.>. Repeating the method to obtain the neighborhood distribution index of each data in the relevant parameters p of the lithium-manganese battery production line;
obtaining the deviation degree of each data according to the neighborhood distribution index of each data, wherein the deviation degree is used for detecting the outlier of the data, and the data deviation degree expression is as follows:
in the method, in the process of the invention,for data->Degree of deviation of->For data->Domain distribution index of>To avoid the minimum value of zero denominator, the practitioner sets itself to 0.01, ++>For the neighborhood distribution threshold, the practitioner can set itself, and the present embodiment sets the neighborhood distribution threshold to 10. The larger the deviation degree is, the lower the similarity degree between the data and the neighborhood data is, the smaller the neighborhood density distribution is, and the higher the probability that the data is an isolated noise point is;
repeating the above method to obtain the deviation degree of each data in the related parameters p of the lithium-manganese battery production line, and taking the data with the deviation degree higher than the deviation threshold value as noise points, wherein the deviation threshold value is set by a deviation threshold value implementer, and the deviation threshold value is set to be 3 in the embodiment. Extracting each noise point in the relevant parameter p of the lithium-manganese battery production line, filtering out noise point data, and avoiding the influence on classification of relevant parameter data of the lithium-manganese battery production line;
and repeating the method, extracting and filtering noise points in relevant parameters of each lithium-manganese battery production line of the lithium-manganese battery production line monitoring matrix, and improving the precision of the subsequent data classification.
Further, classifying the data of the relevant parameters of each lithium-manganese battery production line, wherein the clustering algorithm uses a K-means clustering algorithm for classification, wherein the number of clustering categories can be set by an operator, and the number of clustering categories is set to be 2 in the embodiment. Obtaining a clustering distance according to the relation between the data of the related parameters of each lithium manganese battery production line and the clustering center point, wherein the clustering distance expression of the data and the clustering center point in the related parameters p of the lithium manganese battery production line is as follows:
in the method, in the process of the invention,for clustering distance->For data->And cluster center point->Is used to determine the absolute value of the data difference value of (c),for data->And cluster center point->In the embodiment, rows and columns of data in a monitoring matrix of a lithium-manganese battery production line are used as coordinate information of the data, and the data is ∈ ->And cluster center pointThe euclidean distance between the coordinate information of (c) is taken as the spatial distance. It should be noted that, the calculation of the euclidean distance is a known technique, and is not in the protection scope of the embodiment, and is not described in detail;
in order to ensure the accuracy of a clustering algorithm for presetting the number of clustering categories, therefore, when data clustering is carried out, one sample corresponding to each category is added into the relevant parameters p of the lithium-manganese battery production line. Considering that the traditional clustering iterative process is long, the precision is low and the clustering speed is slow when the K-means algorithm is used for data clustering, the embodiment carries out self-adaptive regulation and control on the clustering process according to the clustering effect evaluation so as to improve the precision of data clustering;
firstly, randomly selecting 2 initial center points to cluster data according to a clustering distance and a K-means algorithm, wherein the clustering process is the prior known technology and is not in the protection scope of the embodiment, and detailed description is not made;
then, in order to improve the clustering precision and shorten the clustering time, the embodiment realizes the self-adaptive regulation and control of the clustering process according to the clustering effect evaluation coefficient, and obtains the clustering effect evaluation coefficient of the relevant parameters of the manganese lithium battery according to the relation among the clustering clusters of the relevant parameter data of the manganese lithium battery, wherein the clustering effect evaluation coefficient expression is specifically as follows:
in the method, in the process of the invention,evaluating coefficients for clustering effect of relevant parameters p of lithium-manganese battery,/-for>Respectively clustering center points of two clustered classes, wherein S is the number of clustered classes, and S=2 and ++in the embodiment>For data->Data->Euclidean distance between coordinate information of (2),. About.>For data->Absolute value of difference between>Cluster center for category s +.>Data within category s->Euclidean distance between coordinate information of (2),. About.>For category s and data->The same number of data>Is the total number of data within category s. The larger the clustering effect evaluation coefficient is, the better the corresponding clustering effect is;
in the expression of the clustering effect evaluation coefficient, the moleculesThe method is mainly used for guaranteeing that the minimum difference between data in different categories reaches the maximum, namely guaranteeing that the larger the difference between the categories is, the smaller the data similarity between the two categories is, and the better the data category dividing effect is; denominator->Entropy-based ideas are used to detect the degree of data distribution clutter within each category, +.>The larger the data distribution in each category is, the more messy the data consistency is, so that the negative correlation relationship with the clustering effect evaluation coefficient is formed; />Characterizing data within each categoryThe smaller the difference between the data in the category is, the smaller the fluctuation degree of the data in the category is, and the better the clustering effect is, so that the negative correlation relationship between the clustering effect evaluation coefficients is formed;
for the clustering effect evaluation coefficient, the embodiment performs normalization processing, ensures that the clustering effect evaluation coefficient is in (0, 1), sets an evaluation coefficient threshold, and when the clustering effect evaluation coefficient is greater than the evaluation coefficient threshold, the corresponding data clustering effect is the optimal data category division. It should be noted that, the evaluation coefficient threshold value implementer may select itself, and the present embodiment is set to 0.9;
repeating the method, carrying out cluster analysis on relevant parameters of each lithium-manganese battery production line in a lithium-manganese battery production line monitoring matrix, and monitoring the production process of the lithium-manganese battery;
so far, each cluster of the related parameter data of each lithium-manganese battery production line can be obtained according to the method, and the method has higher data clustering precision;
and finally, obtaining the abnormality degree of the relevant parameters of each lithium-manganese battery production line according to the relation among the clusters contained in the relevant parameter data of each lithium-manganese battery production line, and taking the abnormality degree as the characteristic information monitored by the lithium-manganese battery production system. The abnormal degree expression of the related parameters of the lithium-manganese battery production line is as follows:
in the method, in the process of the invention,clustering cluster set of relevant parameters p of lithium-manganese battery production line>The maximum cluster data mean value and the minimum cluster data mean value in the related parameter p cluster set of the lithium-manganese battery production line are respectively,related parameters of the lithium-manganese battery production lineClustering center point of two clusters of p, < ->For normalization operations, ++>The abnormal degree of the relevant parameter p of the lithium-manganese battery production line is higher, and the possibility of abnormal data in the relevant parameter m of the lithium-manganese battery production line is higher;
and repeating the method to obtain the abnormal degree of the related parameters of each lithium-manganese battery production line, and monitoring and analyzing a lithium-manganese battery production system.
Step S003, a pre-warning device of a manganese lithium battery production system.
The early warning device of the manganese lithium battery production system mainly monitors the manganese lithium battery production line according to the extracted abnormal data. Considering that certain fault tolerance exists in the production line process, for the abnormal degree of the related parameters of each lithium-manganese battery production line, the embodiment comprehensively monitors the lithium-manganese battery production system based on the abnormal degree, and constructs an abnormal early warning value of the lithium-manganese battery production system, wherein the expression is as follows:
in the method, in the process of the invention,the weight factor of the parameters p related to the lithium-manganese battery production line can be set by the practitioner, and the embodiment is set as +.>,/>For the abnormality degree of the related parameter p of the lithium-manganese battery production line, < >>For abnormal early warning value of lithium-manganese battery production system, normalizing and protectingWith the value of (0, 1), the embodiment sets the early warning threshold value of 0.6, and an operator can select the value of the early warning threshold value by himself, when the abnormal early warning value of the lithium-manganese battery production system is higher than the early warning threshold value, the early warning is sent out timely, and related operators are prompted to further detect and maintain related parameters of the lithium-manganese battery production line with the abnormal degree higher than the abnormal degree threshold value in the lithium-manganese battery production system, so that the production efficiency of the lithium-manganese battery is ensured, and the problems of low quality and the like of the produced lithium-manganese battery caused by the abnormal production process of the lithium-manganese battery are avoided. The abnormality degree threshold value is set by the operator, and the present embodiment is set to 0.5.
In summary, the embodiment of the invention provides a power lithium-manganese battery production system, which is mainly used for realizing monitoring of the manganese-lithium battery production system and improving the production efficiency of the manganese-lithium battery by analyzing data of all relevant parameters in the production process of the manganese-lithium battery. According to the embodiment of the invention, the neighborhood distribution index is calculated by combining the data distribution condition of each data neighborhood range, the deviation degree of each data is obtained, the noise points in the relevant parameters of each lithium-manganese battery production line are extracted and filtered according to the deviation degree of the data, the influence of the noise points in the relevant parameter data of each lithium-manganese battery production line is solved, the influence of the noise points on the data clustering precision is avoided, and the data purity is improved;
for the problem that the conventional clustering precision is low and the clustering effect cannot be guaranteed, the embodiment of the invention constructs the clustering effect evaluation coefficient according to the effect after each clustering, and performs self-adaptive regulation and control on the clustering process of the related parameter data of each lithium-manganese battery production line by combining the clustering effect evaluation coefficient, so that the clustering precision is improved, the clustering time is shortened, and the problems of multiple times and low precision of the conventional clustering iteration are solved. The embodiment of the invention has higher monitoring precision of the power type manganese lithium battery production system, ensures the normal operation of the manganese lithium battery production system, and can effectively improve the production efficiency of the manganese lithium battery.
It should be noted that: the sequence of the embodiments of the present invention is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and identical and similar parts of each embodiment are all referred to each other, and each embodiment mainly describes differences from other embodiments.
The foregoing description of the preferred embodiments of the present invention is not intended to be limiting, but rather, any modifications, equivalents, improvements, etc. that fall within the principles of the present invention are intended to be included within the scope of the present invention.
Claims (9)
1. A power lithium-manganese battery production system, the system comprising:
the system comprises a multi-sensor device of a manganese lithium battery production system, an abnormal data extraction device of the manganese lithium battery production system and an early warning device of the manganese lithium battery production system;
a multi-sensor device of a manganese lithium battery production system: the sensor collects related parameter data of the manganese lithium battery production line and constructs a manganese lithium battery production line monitoring matrix;
abnormal data extraction device of manganese lithium battery production system: obtaining neighborhood distribution indexes of each data according to the data distribution conditions in each data neighborhood range; obtaining the deviation degree of each data according to the neighborhood distribution index of each data; taking the data with the deviation degree higher than the deviation threshold value as noise points and filtering; selecting a clustering center point of each manganese lithium battery production line related parameter data cluster, and obtaining a clustering distance according to the relation between the data of each manganese lithium battery production line related parameter and the clustering center point; carrying out cluster analysis on the data of the relevant parameters of each manganese lithium battery in sequence by combining the cluster distance and a K-means clustering algorithm, and obtaining a clustering effect evaluation coefficient of the relevant parameters of the manganese lithium battery according to the relation among the clusters of the relevant parameter data of the manganese lithium battery; obtaining the optimal clustering division result of the relevant parameters of each manganese lithium battery according to the clustering effect evaluation coefficient of the relevant parameters of each manganese lithium battery; obtaining the abnormality degree of the relevant parameters of each lithium-manganese battery production line according to the relation among the clustering clusters corresponding to the relevant parameters of each lithium-manganese battery production line;
early warning device of manganese lithium battery production system: obtaining abnormal early warning values of the lithium-manganese battery production system according to the abnormal degree of the related parameters of each lithium-manganese battery production line; and monitoring results of the lithium-manganese battery production system are obtained according to the abnormal early warning value of the lithium-manganese battery production system.
2. The system for producing the power lithium-manganese battery according to claim 1, wherein the neighborhood distribution index of each data is obtained according to the data distribution condition in each data neighborhood range, and the expression is as follows:
in the method, in the process of the invention,for data->Domain distribution index of>Representing a functional relationship->For all data sets of the relevant parameters p of the lithium-manganese battery production line,/for the lithium-manganese battery production line>Respectively corresponding data of relevant parameters p of the lithium-manganese battery production line at data acquisition time a and data acquisition time b, < + >>For data->Absolute value of difference between>A data difference cutoff distance.
3. The system for producing the power lithium-manganese battery according to claim 1, wherein the deviation degree of each data is obtained according to the neighborhood distribution index of each data, and the expression is as follows:
4. The system for producing the power lithium-manganese battery according to claim 1, wherein the clustering distance is obtained according to the relation between the data of the related parameters of each manganese-lithium battery production line and the clustering center point, and the expression is as follows:
5. The power lithium-manganese battery production system according to claim 1, wherein the clustering effect evaluation coefficient of the manganese-lithium battery related parameter is obtained according to the relation among the clustering clusters of the manganese-lithium battery related parameter data, and the expression is:
in the method, in the process of the invention,evaluating coefficients for a clustering effect, +.>Respectively clustering center points of two clustered classes, S is the number of clustered classes, and +.>For data->Data->Euclidean distance between coordinate information of (2),. About.>Is data ofAbsolute value of difference between>Cluster center for category s +.>Data within category s->Euclidean distance between coordinate information of (2),. About.>For category s and data->The same number of data>For the total number of data in category s, +.>As a logarithmic function based on e, < ->To take the minimum sign.
6. The system for producing the power lithium-manganese battery according to claim 1, wherein the method for obtaining the optimal clustering result of the relevant parameters of each lithium-manganese battery according to the clustering effect evaluation coefficient of the relevant parameters of each lithium-manganese battery comprises the following specific steps: and carrying out normalization processing on the clustering effect evaluation coefficients of the relevant parameter data of each manganese lithium battery, setting an evaluation coefficient threshold value, and taking the clustering result of the relevant parameter data of each manganese lithium battery corresponding to the clustering evaluation coefficient higher than the evaluation coefficient threshold value as the optimal clustering cluster dividing result.
7. The system for producing the power lithium-manganese battery according to claim 1, wherein the degree of abnormality of the relevant parameters of each lithium-manganese battery production line is obtained according to the relation among the clusters corresponding to the relevant parameters of each lithium-manganese battery production line, and the specific expression is as follows:
in the method, in the process of the invention,clustering cluster set of relevant parameters p of lithium-manganese battery production line>The method is characterized in that the maximum cluster data average value and the minimum cluster data average value in a cluster set of related parameters p of a lithium-manganese battery production line are respectively>Clustering center points of two clusters of related parameters p of lithium-manganese battery production line respectively are +.>For normalization operations, ++>The abnormality degree of the related parameter p of the lithium-manganese battery production line is that e is a natural constant.
8. The system for producing the power lithium-manganese battery according to claim 1, wherein the abnormal early warning value of the system for producing the lithium-manganese battery is obtained according to the abnormal degree of the related parameters of each lithium-manganese battery production line, and the specific expression is as follows:
in the method, in the process of the invention,weight factor of relevant parameter p of lithium-manganese battery production line, < ->For the abnormality degree of the related parameter p of the lithium-manganese battery production line, < >>The abnormal early warning value of the lithium-manganese battery production system is obtained.
9. The system for producing the power lithium-manganese battery according to claim 1, wherein the monitoring result of the system for producing the lithium-manganese battery according to the abnormal early warning value of the system for producing the lithium-manganese battery comprises the following specific steps:
and carrying out normalization processing on abnormal early-warning values of the lithium-manganese battery production system, setting an early-warning threshold value, setting an abnormal degree threshold value of related parameters of the lithium-manganese battery production line, sending out early warning when the abnormal early-warning values of the lithium-manganese battery production system are higher than the early-warning threshold value, prompting related operators to detect and maintain the related parameters of the lithium-manganese battery production line with the abnormal degree higher than the abnormal degree threshold value, and completing monitoring of the lithium-manganese battery production system.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310670582.3A CN116404186B (en) | 2023-06-08 | 2023-06-08 | Power lithium-manganese battery production system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310670582.3A CN116404186B (en) | 2023-06-08 | 2023-06-08 | Power lithium-manganese battery production system |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116404186A true CN116404186A (en) | 2023-07-07 |
CN116404186B CN116404186B (en) | 2023-09-19 |
Family
ID=87010861
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310670582.3A Active CN116404186B (en) | 2023-06-08 | 2023-06-08 | Power lithium-manganese battery production system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116404186B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116561535A (en) * | 2023-07-11 | 2023-08-08 | 安徽建筑大学 | Individualized building interaction design processing method |
CN117706403A (en) * | 2023-12-16 | 2024-03-15 | 北京绿能环宇低碳科技有限公司 | Intelligent rapid disassembly method and system for new energy lithium battery |
Citations (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080233471A1 (en) * | 2004-05-13 | 2008-09-25 | Richard Aumayer | Battery State Detection |
CN107024663A (en) * | 2017-04-01 | 2017-08-08 | 湖南银杏数据科技有限公司 | The lithium battery screening technique clustered based on charging curve feature KPCA |
CN110687452A (en) * | 2019-09-05 | 2020-01-14 | 南京理工大学 | Lithium battery capacity online prediction method based on K-means clustering and Elman neural network |
CN111222584A (en) * | 2020-01-15 | 2020-06-02 | 北京辉腾格勒石墨烯科技有限公司 | Lithium battery real-time evaluation method based on big data and deep neural network |
CN111816936A (en) * | 2020-06-28 | 2020-10-23 | 珠海中力新能源科技有限公司 | Battery echelon utilization grouping method and system, terminal equipment and storage medium |
CN112002949A (en) * | 2020-08-21 | 2020-11-27 | 慧橙新能源发展(杭州)有限公司 | Monitoring management method and system for active equalization of power battery |
US20210055350A1 (en) * | 2018-03-15 | 2021-02-25 | Nec Corporation | Anomaly detection device, anomaly detection method, and recording medium |
CN112513883A (en) * | 2020-02-28 | 2021-03-16 | 华为技术有限公司 | Anomaly detection method and apparatus |
CN112858919A (en) * | 2021-01-18 | 2021-05-28 | 北京理工大学 | Battery system online fault diagnosis method and system based on cluster analysis |
CN113013508A (en) * | 2021-01-29 | 2021-06-22 | 中南大学 | Intelligent scheduling and tracing system and method for power battery formation process |
WO2021208309A1 (en) * | 2020-04-17 | 2021-10-21 | 许继集团有限公司 | Method and system for online evaluation of electrochemical cell of energy storage power station |
CN113887601A (en) * | 2021-09-26 | 2022-01-04 | 上海电器科学研究所(集团)有限公司 | Retired power battery recombination method based on cluster sorting |
CN114264957A (en) * | 2021-12-02 | 2022-04-01 | 东软集团股份有限公司 | Abnormal monomer detection method and related equipment thereof |
KR20220072040A (en) * | 2020-11-23 | 2022-06-02 | 현대모비스 주식회사 | Battery-independent car performance assurance method and apparatus |
CN114899457A (en) * | 2022-05-23 | 2022-08-12 | 淮阴工学院 | Fault detection method for proton exchange membrane fuel cell system |
CN114997612A (en) * | 2022-05-19 | 2022-09-02 | 宿迁聚谷智能科技有限公司 | Cluster analysis method and device for abnormal information of large grain pile |
CN115092011A (en) * | 2022-08-05 | 2022-09-23 | 安徽铎坤新能源科技有限公司 | Intelligent monitoring management system for lithium battery |
KR20220133695A (en) * | 2021-03-25 | 2022-10-05 | (주)오렌지아이 | Method for detecting anomaly in charger/discharger based on charger/discharger data for manufacturing or evaluating lithium-ion battery |
CN115201681A (en) * | 2022-06-27 | 2022-10-18 | 北京电满满科技有限公司 | Lithium battery safety performance detection method and system |
-
2023
- 2023-06-08 CN CN202310670582.3A patent/CN116404186B/en active Active
Patent Citations (20)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20080233471A1 (en) * | 2004-05-13 | 2008-09-25 | Richard Aumayer | Battery State Detection |
CN107024663A (en) * | 2017-04-01 | 2017-08-08 | 湖南银杏数据科技有限公司 | The lithium battery screening technique clustered based on charging curve feature KPCA |
US20210055350A1 (en) * | 2018-03-15 | 2021-02-25 | Nec Corporation | Anomaly detection device, anomaly detection method, and recording medium |
CN110687452A (en) * | 2019-09-05 | 2020-01-14 | 南京理工大学 | Lithium battery capacity online prediction method based on K-means clustering and Elman neural network |
CN111222584A (en) * | 2020-01-15 | 2020-06-02 | 北京辉腾格勒石墨烯科技有限公司 | Lithium battery real-time evaluation method based on big data and deep neural network |
CN112513883A (en) * | 2020-02-28 | 2021-03-16 | 华为技术有限公司 | Anomaly detection method and apparatus |
WO2021208309A1 (en) * | 2020-04-17 | 2021-10-21 | 许继集团有限公司 | Method and system for online evaluation of electrochemical cell of energy storage power station |
CN111816936A (en) * | 2020-06-28 | 2020-10-23 | 珠海中力新能源科技有限公司 | Battery echelon utilization grouping method and system, terminal equipment and storage medium |
CN112002949A (en) * | 2020-08-21 | 2020-11-27 | 慧橙新能源发展(杭州)有限公司 | Monitoring management method and system for active equalization of power battery |
KR20220072040A (en) * | 2020-11-23 | 2022-06-02 | 현대모비스 주식회사 | Battery-independent car performance assurance method and apparatus |
CN112858919A (en) * | 2021-01-18 | 2021-05-28 | 北京理工大学 | Battery system online fault diagnosis method and system based on cluster analysis |
WO2022151819A1 (en) * | 2021-01-18 | 2022-07-21 | 北京理工大学 | Clustering analysis-based battery system online fault diagnosis method and system |
CN113013508A (en) * | 2021-01-29 | 2021-06-22 | 中南大学 | Intelligent scheduling and tracing system and method for power battery formation process |
KR20220133695A (en) * | 2021-03-25 | 2022-10-05 | (주)오렌지아이 | Method for detecting anomaly in charger/discharger based on charger/discharger data for manufacturing or evaluating lithium-ion battery |
CN113887601A (en) * | 2021-09-26 | 2022-01-04 | 上海电器科学研究所(集团)有限公司 | Retired power battery recombination method based on cluster sorting |
CN114264957A (en) * | 2021-12-02 | 2022-04-01 | 东软集团股份有限公司 | Abnormal monomer detection method and related equipment thereof |
CN114997612A (en) * | 2022-05-19 | 2022-09-02 | 宿迁聚谷智能科技有限公司 | Cluster analysis method and device for abnormal information of large grain pile |
CN114899457A (en) * | 2022-05-23 | 2022-08-12 | 淮阴工学院 | Fault detection method for proton exchange membrane fuel cell system |
CN115201681A (en) * | 2022-06-27 | 2022-10-18 | 北京电满满科技有限公司 | Lithium battery safety performance detection method and system |
CN115092011A (en) * | 2022-08-05 | 2022-09-23 | 安徽铎坤新能源科技有限公司 | Intelligent monitoring management system for lithium battery |
Non-Patent Citations (5)
Title |
---|
MINGHU WU等: "Fault Diagnosis Method for Lithium-Ion Battery Packs in Real-World Electric Vehicles Based on K-Means and the Fréchet Algorithm", 《ACS OMEGA》, vol. 7, pages 40145 - 40162 * |
安富强;张剑波;黄俊;王浩然;李平;: "电动汽车用锂离子电池制备及其一致性演变分析", 材料热处理学报, no. 04, pages 243 - 252 * |
张增丽等: "基于模式识别的电动汽车电池故障自动诊断方法", 《河北电力技术》, vol. 41, no. 4, pages 10 - 14 * |
张骞;王雅慧;杜玉良;谢文龙;: "基于异常点检测的锂电池管理系统均衡算法", 河南科技学院学报(自然科学版), no. 05, pages 60 - 67 * |
焦东升;康栩宁;潘鸣宇;李香龙;迟忠君;: "一种动力电池容量一致性辨识方法", 电源技术, no. 07, pages 98 - 102 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116561535A (en) * | 2023-07-11 | 2023-08-08 | 安徽建筑大学 | Individualized building interaction design processing method |
CN116561535B (en) * | 2023-07-11 | 2023-09-19 | 安徽建筑大学 | Individualized building interaction design processing method |
CN117706403A (en) * | 2023-12-16 | 2024-03-15 | 北京绿能环宇低碳科技有限公司 | Intelligent rapid disassembly method and system for new energy lithium battery |
Also Published As
Publication number | Publication date |
---|---|
CN116404186B (en) | 2023-09-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116404186B (en) | Power lithium-manganese battery production system | |
CN110263846B (en) | Fault diagnosis method based on fault data deep mining and learning | |
CN112505549B (en) | New energy automobile battery abnormity detection method based on isolated forest algorithm | |
CN116304766A (en) | Multi-sensor-based quick assessment method for state of switch cabinet | |
CN105955214B (en) | Batch process fault detection method based on sample time-series and neighbour's affinity information | |
CN113112374A (en) | Empty nest user electricity utilization abnormity detection method based on machine learning algorithm | |
CN113255848A (en) | Water turbine cavitation sound signal identification method based on big data learning | |
CN110795690A (en) | Wind power plant operation abnormal data detection method | |
CN114114039B (en) | Method and device for evaluating consistency of single battery cells of battery system | |
CN116400126B (en) | Low-voltage power box with data processing system | |
CN115496644A (en) | Solid waste treatment equipment monitoring method based on data identification | |
CN111224805A (en) | Network fault root cause detection method, system and storage medium | |
CN115876258B (en) | Livestock and poultry breeding environment abnormity monitoring and alarming system based on multi-source data | |
CN115860579B (en) | Production quality monitoring system for flour processing | |
CN115372828A (en) | Battery cell consistency evaluation method based on charging segment data and unsupervised algorithm | |
CN113570200A (en) | Power grid operation state monitoring method and system based on multidimensional information | |
CN107808209B (en) | Wind power plant abnormal data identification method based on weighted kNN distance | |
CN116561535B (en) | Individualized building interaction design processing method | |
CN111797899B (en) | Low-voltage transformer area kmeans clustering method and system | |
CN111601358B (en) | Multi-stage hierarchical clustering spatial correlation temperature perception data redundancy removing method | |
CN114781551B (en) | Battery multi-fault intelligent classification and identification method based on big data | |
CN112305442B (en) | Method for quickly estimating SOH of power battery based on kmeans clustering | |
CN113113148A (en) | Method for identifying physical condition of miner based on LLE combined with SOM | |
CN112059725A (en) | Cutter wear monitoring method based on EMD-SVM | |
CN111600051A (en) | Proton exchange membrane fuel cell fault diagnosis method based on image processing |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |