CN116258424B

CN116258424B - Product analysis method, battery product analysis method, device, equipment and medium

Info

Publication number: CN116258424B
Application number: CN202310547072.7A
Authority: CN
Inventors: 田达; 薛庆瑞; 张子格; 翁文辉; 邵孔木; 刘楚君; 黄瑶; 何俊晨
Original assignee: Contemporary Amperex Technology Co Ltd
Current assignee: Contemporary Amperex Technology Co Ltd
Priority date: 2023-05-16
Filing date: 2023-05-16
Publication date: 2023-09-29
Anticipated expiration: 2043-05-16
Also published as: CN116258424A

Abstract

The application discloses a product analysis method, a battery product analysis method, a device, equipment and a medium. The product analysis method comprises the following steps: carrying out statistics and quantization analysis on production attribute information of a product to be analyzed to obtain a quantization analysis result; wherein the product types of the products to be analyzed are the same, and at least one product feature with different feature values of the same product feature exists among the products to be analyzed; determining the differential production attribute of the product to be analyzed according to the quantitative analysis result; the difference production attribute is used for indicating the difference reason that the product to be analyzed has differences between the characteristic values of the same product characteristics.

Description

Product analysis method, battery product analysis method, device, equipment and medium

Technical Field

The application relates to the technical field of data analysis, in particular to a product analysis method, a battery product analysis method, a device, equipment and a medium.

Background

Industrial products generally refer to products produced by an industrial production line. Industrial production lines include pipeline equipment that is required for use in industrial production. The processing, packaging and other operations of materials can be completed through the assembly line equipment, so that industrial products are obtained.

Industrial production lines are susceptible to interference from a variety of factors during the production of industrial products, resulting in variations in the industrial products during the production process. When the difference is large, the product quality of the industrial product is affected, thereby reducing the product yield of the industrial product.

The statements made above merely serve to provide background information related to the present disclosure and may not necessarily constitute prior art.

Disclosure of Invention

In view of the above problems, the product analysis method, the battery product analysis method, the device, the equipment and the medium provided by the embodiment of the application can be used for relieving the problem that large product differences exist among industrial products due to interference factors of industrial production lines in the production process of the products.

In a first aspect, the present application provides a method of product analysis comprising:

carrying out statistics and quantization analysis on production attribute information of a product to be analyzed to obtain a quantization analysis result; wherein the product types of the products to be analyzed are the same, and at least one product feature with different feature values of the same product feature exists among the products to be analyzed;

determining the differential production attribute of the product to be analyzed according to the quantitative analysis result; the difference production attribute is used for indicating the difference reason that the product to be analyzed has differences between the characteristic values of the same product characteristics.

According to the technical scheme provided by the embodiment of the application, the production attribute information of the product to be analyzed can be subjected to statistical quantitative analysis, so that a quantitative analysis result is obtained. Therefore, the difference significance of the production attribute information of the product to be analyzed in the production process can be reflected through the quantitative analysis result, so that a judgment basis is provided for determining the difference production attribute. After determining the difference production attribute by quantifying the analysis result, a difference cause in which the product to be analyzed has a difference between the feature values of the same product feature may be determined based on the difference production attribute. By analyzing the reasons of the differences, an adjustment basis can be provided for the industrial production line, so that the production attribute information of the industrial production line is adjusted according to the adjustment basis, and the product differences among products to be analyzed are reduced, and the product yield is ensured.

In some embodiments, the performing statistical quantitative analysis on the production attribute information of the product to be analyzed to obtain a quantitative analysis result includes:

obtaining a quantitative analysis result based on the production attribute information of the normal products and the production attribute information of the abnormal products in the products to be analyzed; the quantitative analysis result is used for representing the association degree of each production attribute information and an abnormal reason, wherein the abnormal reason is the reason that the characteristic value of the product characteristic of the abnormal product is abnormal.

The production attribute information of the normal products and the production attribute information of the abnormal products are subjected to statistical quantitative analysis to obtain quantitative analysis results, so that the difference significance of the production attribute information in the production process can be determined, a judgment basis is provided for the determination of the difference production attribute, the difference production attribute can be automatically determined according to the judgment basis, the determination efficiency of the difference production attribute is improved, and the product quality of an industrial production line is ensured.

In some embodiments, obtaining the quantitative analysis result based on the production attribute information of the normal product and the production attribute information of the abnormal product in the product to be analyzed includes:

determining statistical data of at least one production attribute information of the normal product and the abnormal product;

and determining the quantitative analysis result based on the statistical data.

Under normal conditions, if there is a large difference in the feature values of the same product features, there is a certain difference between the production attribute information of the products. Therefore, the normal product and the abnormal product can be more intuitively reflected by the processing mode, and the difference between the production attribute information in the production process is generated, so that a more reasonable judgment basis is provided for the abnormal reason of the abnormal product.

In some embodiments, the determining statistical data of at least one production attribute information of the normal product and the abnormal product includes:

calculating a first statistical variable of each production attribute information of the normal product; calculating a second statistical variable of each production attribute information of the abnormal product; determining the statistical data according to the first statistical variable and the second statistical variable.

The statistical data is determined by calculating statistical variables for representing the information concentration degree and the information divergence degree of the production attribute information, so that more reasonable statistical analysis can be performed on the production attribute information, and more reasonable statistical data can be obtained.

determining a first normalization test result of each production attribute information of the normal product; wherein the first normalization test result is used for representing the probability that each production attribute information of the normal product does not accord with a normal distribution;

determining a second normalization test result for each production attribute information of the abnormal product; wherein the second normalization test result is used for representing the probability that each production attribute information of the abnormal product does not accord with a normal distribution;

And determining the statistical data according to the first normal testing result and the second normal testing result.

By means of determining the normal test results of each production attribute information of the normal products and each production attribute information of the abnormal products, whether the information distribution form of the production attribute information accords with normal distribution or not can be determined, so that the information rationality of the production attribute information can be determined, more reasonable judgment basis can be provided for a product analysis method, and the accuracy of the different production attributes is improved.

In some embodiments, the obtaining the quantitative analysis result based on the production attribute information of the normal product and the production attribute information of the abnormal product in the product to be analyzed includes:

determining product difference data between the normal product and the abnormal product based on the production attribute information of the normal product and the production attribute information of the abnormal product;

and determining the quantitative analysis result based on the product difference data.

Through the product difference data, the difference between the normal product and the abnormal product in the same production attribute information in the production process of the product can be determined, so that a difference type judgment basis can be provided for determining the abnormal reason of the abnormal product, and the accuracy of the difference production attribute can be improved.

In some embodiments, the determining product difference data between the normal product and the abnormal product based on the production attribute information of the normal product and the production attribute information of the abnormal product includes:

determining a statistical data difference between the statistical data of the production attribute information of the normal product and the statistical data of the production attribute information of the abnormal product;

the product variance data is determined based on the statistical data variance.

By determining the statistical data difference between the statistical data of the production attribute information and further determining the product difference data according to the statistical data difference, the attribute difference between the production attribute information of the normal product and the production attribute information of the abnormal product can be reflected from the data statistics angle, so that a more reasonable difference type judgment basis is provided for determining the abnormal cause.

determining the result of difference significance test of the production attribute information of the normal product and the production attribute information of the abnormal product; wherein the result of the difference saliency test is used for indicating the probability that no difference exists between the production attribute information of the normal product and the production attribute information of the abnormal product;

And determining the product difference data according to the result of the difference significance test.

The probability that each production attribute information is the difference production attribute can be determined in a probability manner by determining the result of the difference significance test of the production attribute information of the normal product and the abnormal product, so that a more reliable quantized judgment basis is provided for a product analysis method, and the accuracy of the difference production attribute is improved.

In some embodiments, the production attribute information is of a variety of types;

and determining the differential production attribute of the product to be analyzed according to the quantitative analysis result, wherein the differential production attribute comprises the following steps:

comparing the quantitative analysis result of each production attribute information of the product to be analyzed with a preset threshold value to obtain a comparison result;

and determining the different production attribute in a plurality of production attribute information according to the comparison result.

By comparing the quantitative analysis result with a preset threshold value and determining the differential production attribute according to the comparison result, the differential production attribute which possibly causes the difference of the product to be analyzed among the characteristic values of the same product characteristics can be rapidly determined in the production attribute information, so that the determination efficiency of the differential production attribute is improved.

In some embodiments, the product to be analyzed comprises a normal product and an abnormal product;

said determining said differential production attribute from a plurality of said production attribute information based on said comparison result comprises:

determining production attribute information of the product difference data meeting a first threshold requirement based on a comparison result of the product difference data; wherein the product difference data is used for indicating attribute differences between each production attribute information of the normal product and the abnormal product;

and determining the differential production attribute according to the production attribute information meeting the first threshold requirement.

Because the difference between the production attribute information of the products with the same product model is smaller, the difference production attribute is determined according to the product difference data of the production attribute information, and the difference production attribute can be determined from the production attribute information more quickly and accurately. The above described determination process of the differential production attribute does not require analysis of the abnormal failure mechanism of the abnormal product in advance, and therefore, the determination process can also simplify the determination flow of the differential production attribute and save the determination cost of the differential production attribute.

In some embodiments, the determining production attribute information for the product differential data to meet a first threshold requirement based on a comparison of the product differential data includes:

Determining production attribute information meeting a second threshold requirement based on a comparison result of the statistical data;

determining the production attribute information meeting the first threshold requirement according to the production attribute information meeting the second threshold requirement; wherein the statistical data includes statistical data of each of the production attribute information of the normal product or statistical data of each of the production attribute information of the abnormal product.

By determining the production attribute information of which the statistical data meets the second threshold requirement and determining the production attribute information meeting the first threshold requirement according to the production attribute information, the abnormal failure mechanism of the abnormal product does not need to be analyzed in advance for analysis, so that the determination process can simplify the determination flow of the differential production attribute and save the determination cost of the differential production attribute.

In a second aspect, the present application provides a battery product analysis method comprising:

acquiring production attribute information of a normal battery and production attribute information of an abnormal battery;

carrying out statistics and quantization analysis on the production attribute information of the normal battery and the production attribute information of the abnormal battery to obtain a quantization analysis result;

Determining a difference production attribute according to the quantitative analysis result; wherein the difference production attribute is used for indicating an abnormality cause of the abnormality of the abnormal battery.

In the embodiment of the application, the production attribute information of the normal battery and the production attribute information of the abnormal battery can be respectively subjected to statistics and quantization analysis to obtain a quantization analysis result of the production attribute information; thereafter, the differential production attribute may be determined in the production attribute information by quantifying the analysis result. The difference significance of the production attribute information of the battery in the production process is reflected through the quantization index in the whole process, so that a judgment basis is provided for determining the difference production attribute; the whole process does not need to analyze the abnormal failure mechanism of the abnormal product in advance, so that the determination process can simplify the determination flow of the differential production attribute and save the determination cost of the differential production attribute.

In a third aspect, the present application provides a product analysis device comprising:

the first quantization unit is used for carrying out statistics and quantization analysis on the production attribute information of the product to be analyzed to obtain a quantization analysis result; wherein the product types of the products to be analyzed are the same, and at least one product feature with different feature values of the same product feature exists among the products to be analyzed;

The first determining unit is used for determining the difference production attribute of the product to be analyzed according to the quantitative analysis result; wherein the difference production attribute is used for indicating a difference reason for a difference between characteristic values of product characteristics of the product to be analyzed.

In a fourth aspect, the present application provides a battery product analysis apparatus comprising:

an acquisition unit configured to acquire production attribute information of a normal battery and production attribute information of an abnormal battery;

the second quantization unit is used for carrying out statistical quantization analysis on the production attribute information of the normal battery and the production attribute information of the abnormal battery to obtain a quantization analysis result;

a second determining unit, configured to determine a difference production attribute according to the quantitative analysis result; wherein the difference production attribute is used for indicating an abnormality cause of the abnormality of the abnormal battery.

In a fifth aspect, the present application provides an electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the method according to any one of the first and second aspects.

In a sixth aspect, the present application provides a computer readable storage medium having stored thereon a computer program, characterized in that the program is executed by a processor to implement the method according to any one of the first and second aspects.

In a seventh aspect, the present application provides a computer program product comprising a computer program, characterized in that the computer program is executed by a processor to implement the method according to any one of the first and second aspects.

The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.

Drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the accompanying drawings.

FIG. 1 is a flow diagram of a method of product analysis according to one or more embodiments.

FIG. 2 is another flow diagram of a method of product analysis in accordance with one or more embodiments.

FIG. 3 is a flow diagram of a process for determining a differential production attribute provided in accordance with one or more embodiments.

Fig. 4 is a flow diagram of a method of battery product analysis according to one or more embodiments.

Fig. 5 is a schematic structural diagram of a product analysis device provided in accordance with one or more embodiments.

Fig. 6 is a schematic structural diagram of a battery product analysis device provided in accordance with one or more embodiments.

FIG. 7 is a block diagram of an electronic device in accordance with one or more embodiments.

FIG. 8 is a schematic diagram of a computer-readable storage medium in accordance with one or more embodiments.

Detailed Description

Embodiments of the technical scheme of the present application will be described in detail below with reference to the accompanying drawings. The following examples are only for more clearly illustrating the technical aspects of the present application, and thus are merely examples, and are not intended to limit the scope of the present application.

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 application belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application; the terms "comprising" and "having" and any variations thereof in the description of the application and the claims and the description of the drawings above are intended to cover a non-exclusive inclusion.

In the description of embodiments of the present application, the technical terms "first," "second," and the like are used merely to distinguish between different objects and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated, a particular order or a primary or secondary relationship. In the description of the embodiments of the present application, the meaning of "plurality" is two or more unless explicitly defined otherwise.

Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.

In the description of the embodiments of the present application, the term "and/or" is merely an association relationship describing an association object, and indicates that three relationships may exist, for example, a and/or B may indicate: a exists alone, A and B exist together, and B exists alone. In addition, the character "/" herein generally indicates that the front and rear associated objects are an "or" relationship.

In the description of the embodiments of the present application, the term "plurality" means two or more (including two), and similarly, "plural sets" means two or more (including two), and "plural sheets" means two or more (including two).

Industrial production lines, also known as assembly lines, belong to a production mode in industry. The industrial production line comprises a plurality of production links, each production link comprises one or more production line devices, wherein each production link focuses on the work of processing a certain processing segment of a material, the material is processed through the industrial production line, and the mode of obtaining industrial products can improve the working efficiency and the yield.

Each production link of the industrial production line is used for continuously processing materials or conveying products. Each production link of the industrial production line can be completed by specific workers, and the processing of materials is realized through the cooperation of machines and staff, so that the production of industrial products is finally completed.

The production process of an industrial production line is susceptible to interference from many factors, including the following dimensions: material dimension, production environment dimension, worker dimension, and line equipment dimension.

Here, the material dimension refers to the property of the material itself. Since the materials of the same model are not likely to be identical, the industrial products obtained after the materials of the same model are processed by the same industrial production line are not necessarily identical. The production environment dimension refers to the environment in which the industrial production line is located. Because the environment is not fixed, the industrial products processed by the materials with the same model in different environments are not necessarily identical after passing through the same industrial production line. The worker dimension refers to the operator of each production link. Pipeline device dimensions refer to device attributes of the pipeline device itself. Because of certain loss of the equipment, the state of the pipeline equipment at different moments is different. The state of the equipment also affects the processing of the industrial product, thereby producing a differentiated industrial product.

When the product difference between industrial products is large, abnormal products are liable to occur. When the number of abnormal products is large, the product yield of the industrial products will be affected.

To avoid large differences between industrial products or to avoid a large number of abnormal products in the industrial products. In the related art, the industrial products are generally subjected to sampling inspection in a manual sampling inspection mode, and then the product quality is ensured according to sampling inspection results. However, this method consumes a lot of manpower, and cannot fundamentally solve the problem of large difference between industrial products.

Based on the above, the embodiment of the application designs a product analysis method, which performs statistical quantitative analysis on the production attribute information of the product to be analyzed to obtain a quantitative analysis result; further, according to the quantitative analysis result, determining the differential production attribute of the product to be analyzed; wherein, the product model of the products to be analyzed is the same, and at least one product feature with different feature values of the same product feature exists among the products to be analyzed; the variance production attribute is used to indicate the variance cause of the variance of the product to be analyzed between the characteristic values of the same product characteristics.

The method provided by the embodiment of the application can reflect the difference significance of the production attribute information of the product to be analyzed in the production process through quantifying the analysis result, thereby providing a judgment basis for determining the difference production attribute. After determining the difference production attribute by quantifying the analysis result, a difference cause in which the product to be analyzed has a difference between the feature values of the same product feature may be determined based on the difference production attribute. By analyzing the reasons of the differences, an adjustment basis can be provided for the industrial production line, so that the production attribute information of the industrial production line is adjusted according to the adjustment basis, and the product differences among products to be analyzed are reduced, and the product yield is ensured.

The product analysis method provided by the embodiment of the application can be applied to analysis processing of any product to be analyzed, including but not limited to products which can be produced by an industrial production line. For example, the product to be analyzed may be any product that can be produced by an industrial production line, such as an electronic product (e.g., a battery), a food product, a living article, a study product, a vehicle product, or the like.

The battery in the embodiment of the application can be a lithium ion battery, a lithium metal battery and the like, such as a lithium cobaltate battery, a lithium manganate battery, a nickel cobalt lithium aluminate battery, a lithium iron phosphate battery, a lithium titanate battery, a lithium sulfur battery and the like. Alternatively, the battery in embodiments of the present application includes, but is not limited to, batteries of other material systems, such as lead acid batteries, nickel-metal hydride batteries, or sodium ion batteries, among others.

In some embodiments of the present application, the devices involved in the product analysis method may include, but are not limited to, a storage device and an upper computer. The storage device may include, but is not limited to, a device that stores production attribute information for a product to be analyzed. The host computer may include, but is not limited to, a server or terminal connected to a storage device. The connection relationship between the upper computer and the storage device can be wired connection or wireless connection, etc.

In these embodiments, the upper computer may acquire production attribute information of the product to be analyzed from the storage device, and perform statistical quantization analysis on the production attribute information, so as to obtain a quantization analysis result. And then, the upper computer can also determine the difference production attribute of the product to be analyzed according to the quantitative analysis result so as to determine the difference reason of the difference of the product to be analyzed among the characteristic values of the same product characteristics according to the difference production attribute. By the processing process, the reason of the difference can be analyzed, and an adjustment basis is provided for the industrial production line, so that the production attribute information of the industrial production line is adjusted according to the adjustment basis, and the product difference among products to be analyzed is reduced, so that the product yield is ensured.

For convenience of description, the specific processing procedure of the embodiment of the present application will be described in detail below by taking an example that the related devices include an upper computer and a storage device.

Referring to fig. 1, an embodiment of the present application provides a method for analyzing a product, which specifically includes the following steps:

step 101: carrying out statistics and quantization analysis on production attribute information of a product to be analyzed to obtain a quantization analysis result; the product types of the products to be analyzed are the same, and at least one product feature with different feature values of the same product feature exists among the products to be analyzed.

Here, the product to be analyzed may be a product of the same type as a product produced by an industrial line. For example, the product to be analyzed may be a battery of XXX model, or may be a food of YYY model, or the like.

During normal production of an industrial production line, each product may be assigned a corresponding product number. Here, the product number may be a text having a certain length; wherein the product number includes, but is not limited to, numbers, letters, and other characters. For example, the product number may be a pure number, may be a pure letter, or may be a mixture of numbers and letters. The product numbers have uniqueness, namely each product corresponds to one product number, and the product numbers of different products are different. The uniqueness of the product number may be uniqueness of the product number within a specified range. For example, it may refer to the uniqueness of the product number within the same industrial line; and for example, the uniqueness of the product numbers within the same base, within the same company, within the same group.

In the normal product process of the industrial production line, the production attribute information of the product can be collected through production equipment. The production attribute information may be determined based on an attribute value of at least one production attribute of the industrial production line during the production of the product. The production attributes include product material attributes, production environment attributes, worker operation attributes, and pipeline equipment attributes. If the number of production links of the product is multiple, the attribute value of the production attribute of each production link can be recorded, so that the production attribute information can be obtained.

In some embodiments, product material properties include, but are not limited to, basic properties of the material including material size, material weight, material density, material type (e.g., chemical, mechanical parts), and the like. Production environment attributes include, but are not limited to, environmental temperature, environmental humidity, industrial line number, production base number where the industrial line is located, etc. attributes associated with the production environment. Worker operation attributes include, but are not limited to, the length of time a worker operates each product, the total number of products operated during a specified period of time, the length of time on duty, the degree of skill in the operation, and the like. The pipeline equipment attributes include, but are not limited to, production equipment attributes and production process attributes, wherein the production equipment attributes comprise equipment basic attributes such as equipment numbers, equipment categories, equipment capabilities, equipment states and the like, and the production process attributes comprise the current production process name, time intervals between the current production process and the previous production process, input and output parameters of the current process and the like related to the production process.

The production attribute information collected in the production process of the product is related to a specific product, for example, for a battery, attribute values of production attributes such as impedance, capacity and the like of the battery can be collected; for snack type products, the package air tightness and weight, etc. production attribute values may be collected.

After the attribute value of the production attribute is acquired, the attribute value may be determined as production attribute information; the attribute value of the production attribute can be derived, and then the production attribute information can be obtained. Here, deriving the attribute value of the production attribute means mapping the attribute value of the production attribute to a new attribute value by the specified calculation logic, and then determining the new attribute value as production attribute information. For example, multiplying the attribute value in minutes by 60 yields a new attribute value in seconds.

After obtaining the product number and the production attribute information of each product, the product number and the production attribute information of the product can be associated; and storing the associated product number and production attribute information in a storage device, such as a database. In the database, the production attribute information is associated with the product number, and the corresponding production attribute information can be obtained through product number inquiry.

Here, other product attributes, such as the planned production quantity of a product, design information of a product, and the like, associated with the product may be recorded in the database in addition to the production attribute information described above.

In the sampling inspection stage of the products, quality inspection can be carried out on the products produced by the industrial production line, the difference among the products can be sampled and inspected through sampling inspection on the products, and the sampled and inspected products are grouped according to the difference, so that the products to be analyzed are obtained. For example, 100 products are inspected, and the value interval of the feature value of the 100 products for the same product feature a is interval 1 and interval 2, at this time, the product with the feature value in interval 1 and the product with the feature value in interval 2 may be determined as the product to be analyzed.

After the products to be analyzed are determined, the production attribute information of each product to be analyzed can be obtained from the database based on the product numbers of the products to be analyzed, and the production attribute information is quantitatively analyzed to obtain a quantitative analysis result.

Step 102: determining the differential production attribute of the product to be analyzed according to the quantitative analysis result; the difference production attribute is used for indicating the difference reason that the product to be analyzed has differences between the characteristic values of the same product characteristics.

After the quantitative analysis result is determined, a difference cause indicating that the product to be analyzed has a difference between the feature values of the same product features, that is, a difference production attribute, may be determined from the production attributes of the product to be analyzed. And then, the production attribute of the industrial production line can be adjusted according to the difference production attribute so as to reduce the difference between normal products of the industrial production line and further ensure the product yield of the industrial production line.

In the above embodiment, the difference significance of the production attribute information of the product to be analyzed in the production process is reflected by quantifying the analysis result, so as to provide a judgment basis for determining the difference production attribute. After determining the difference production attribute by quantifying the analysis result, a difference cause in which the product to be analyzed has a difference between the feature values of the same product feature may be determined based on the difference production attribute. By analyzing the reasons of the differences, an adjustment basis can be provided for the industrial production line, so that the production attribute information of the industrial production line is adjusted according to the adjustment basis, and the product differences among products to be analyzed are reduced, and the product yield is ensured.

In some embodiments of the present application, statistical quantization analysis is performed on production attribute information of a product to be analyzed to obtain a quantization analysis result, including the following steps:

In this embodiment, the products to be analyzed may be classified into normal products and abnormal products. For example, 100 products are inspected, and the value interval of the feature value of the 100 products for the same product feature a is a normal interval 1 and an abnormal interval 2, where the product with the feature value in the normal interval 1 may be determined as a normal product, and the product with the feature value in the abnormal interval 2 may be determined as an abnormal product.

On the basis, the reasons for abnormality between the characteristic values of the product characteristics of the normal product and the abnormal product are required to be analyzed, so that the production attribute of the industrial production line is adjusted according to the reasons for abnormality, and the product yield is ensured.

After the spot check products are divided into the normal products and the abnormal products, the production attribute information of the normal products can be obtained in the database based on the product numbers of the normal products, and the production attribute information of the abnormal products can be obtained in the database based on the product numbers of the abnormal products.

Here, statistical quantization analysis may be performed on production attribute information of a normal product and production attribute information of an abnormal product, thereby obtaining a quantization analysis result. From the result of the quantitative analysis, a degree of association between each production attribute information and the cause of the abnormality can be determined, wherein the degree of association can be used to indicate a probability that the production attribute information is the cause of the abnormality.

In some embodiments of the present application, a quantitative analysis result is obtained based on production attribute information of a normal product and production attribute information of an abnormal product in a product to be analyzed, including the steps of:

determining statistical data of at least one production attribute information of the normal product and the abnormal product; the quantitative analysis result is determined based on the statistical data.

In this embodiment, descriptive statistical analysis may be performed on at least one production attribute information of a normal product to obtain statistical data, and descriptive statistical analysis may be performed on at least one production attribute information of an abnormal product to obtain statistical data.

Here, descriptive statistical analysis may be performed on production attribute information of a normal product for each production attribute, thereby obtaining statistical data of each production attribute information; and carrying out descriptive statistical analysis on the production attribute information of the abnormal product aiming at each production attribute, thereby obtaining the statistical data of each production attribute information.

In this embodiment, the kind of production attribute information of the normal product is the same as the kind of production attribute information of the abnormal product. For each production attribute information, the normal products and the abnormal products can be counted to obtain corresponding statistical data.

For example, the production attribute information contains the following categories: the first type of production attribute information, the second type of production attribute information, and the third type of production attribute information.

For normal products, the first type of production attribute information of the normal products can be subjected to statistical analysis to obtain statistical data A1; carrying out statistical analysis on the second type of production attribute information of the normal product to obtain statistical data A2; and carrying out statistical analysis on the third type of production attribute information of the normal product to obtain statistical data A3. For abnormal products, the first type of production attribute information of the abnormal products can be subjected to statistical analysis to obtain statistical data B1; carrying out statistical analysis on the second type of production attribute information of the abnormal product to obtain statistical data B2; and carrying out statistical analysis on the third type of production attribute information of the abnormal product to obtain statistical data B3.

Under normal conditions, if there is a large difference in the feature values of the same product features, there is a certain difference between the production attribute information of the products. Therefore, the method for obtaining the statistical data by respectively carrying out statistical analysis on at least one production attribute information of the normal product and at least one production attribute information of the abnormal product can more intuitively reflect the difference between the production attribute information of the normal product and the abnormal product in the production process, thereby providing more reasonable judgment basis for the abnormality reason of the abnormal product.

In some embodiments of the present application, determining statistical data of at least one production attribute information of the normal product and the abnormal product includes the steps of:

calculating a first statistical variable of each production attribute information of the normal product; calculating a second statistical variable of each production attribute information of the abnormal product; the statistical data is determined from the first statistical variable and the second statistical variable.

In this embodiment, the first statistical variable and the second statistical variable may include, but are not limited to, the following quantities associated with descriptive statistics: the number of values, the number of non-duplicate values, the mean, median, maximum, minimum of the data.

Here, the number of values refers to the information amount of normal products for each production attribute information and the information amount of abnormal products for each production attribute information. The number of non-duplicate values refers to the number of different information in each production attribute information of a normal product and the number of different information in each production attribute information of an abnormal product. The average value of the data refers to the information average value of each production attribute information of the normal product and the information average value of each production attribute information of the abnormal product. The median refers to the median of each production attribute information of normal products and the median of each production attribute information of abnormal products. The maximum value refers to maximum information of each production attribute information of a normal product and maximum information of each production attribute information of an abnormal product. The minimum value refers to minimum information of each production attribute information of a normal product and minimum information of each production attribute information of an abnormal product.

Here, a first statistical variable of each production attribute information of the normal product and a second statistical variable of each production attribute information of the abnormal product may be calculated, respectively. Wherein the type of the first statistical variable is the same as the type of the second statistical variable. For example, if the type of the first statistical variable is a median, then the type of the second statistical variable is also a median.

In this embodiment, a set of production attribute information may be mapped to a numerical value by applying calculation logic, and then the numerical value may be determined as a statistical variable, where the calculation logic may be represented as y=f (x), where x is production attribute information of a normal product or production attribute information of an abnormal product, y is a first statistical variable of the normal product or a second statistical variable of the abnormal product calculated, and f is a logical relationship applied by the calculation process. Here, a corresponding calculation logic may be set for each type of descriptive statistics.

In this embodiment, the types of the first statistical variable and the second statistical variable may be determined based on the product types of the products to be analyzed, and then a preset calculation logic is determined according to the types, so that the first statistical variable of the normal product and the second statistical variable of the abnormal product are respectively determined according to the calculation logic; and determining the first statistical variable and the second statistical variable as statistical data.

The statistical data mode is determined by calculating the statistical variables used for representing the information centralized trend and the information divergence degree of the production attribute information, the production attribute information can be analyzed from each dimension, and further more reasonable statistical analysis can be performed on the production attribute information, so that more reasonable statistical data is obtained.

In other embodiments of the present application, determining statistical data of at least one production attribute information of the normal product and the abnormal product includes the steps of:

determining a first normalization test result of each production attribute information of the normal product; the first normal test result is used for representing the probability that each production attribute information of the normal product does not accord with normal distribution; determining a second normal inspection result of each production attribute information of the abnormal product; the second normal test result is used for representing the probability that each production attribute information of the abnormal product does not accord with normal distribution; and determining statistical data according to the first normal test result and the second normal test result.

The statistical data includes, in addition to the statistical variations described in the above embodiments, a normalization check result calculated by a complex mathematical algorithm on the production attribute information. The probability that the production attribute information of the normal product does not accord with the normal distribution can be determined through the normal test result, and the probability that each production attribute information of the abnormal product does not accord with the normal distribution can be determined.

In this embodiment, the production attribute information may be subjected to a normalization hypothesis test to obtain a P value, and determined as a normalization test result based on the P value.

Here, a first P value (i.e., a first normalization check result) from which the probability that the production attribute information of the normal product does not conform to the normal distribution may be determined may be obtained by performing a normalization hypothesis check on each production attribute information of the normal product; the normal hypothesis test may also be performed on each production attribute information of the abnormal product to obtain a second P value (i.e., a second normal test result), from which a probability that each production attribute information of the abnormal product does not conform to the normal distribution may be determined.

Determining product difference data between the normal product and the abnormal product based on the production attribute information of the normal product and the production attribute information of the abnormal product; and determining a quantitative analysis result based on the product difference data.

In this embodiment, the production attribute information of the normal product and the production attribute information of the abnormal product may be subjected to attribute difference analysis, so that the attribute difference is obtained by the analysis, and the product difference data between the normal product and the abnormal product is determined. That is, the product difference data is used to indicate a difference in attribute between the production attribute information of the normal product and the abnormal product.

When the production attribute information is of a plurality of types, the same production attribute information of the normal product and the abnormal product can be subjected to attribute difference analysis, so that the attribute difference of the type of production attribute information is obtained.

Aiming at the first type of production attribute information, attribute difference analysis can be carried out on the first type of production attribute information of normal products and the first type of production attribute information of abnormal products to obtain attribute difference C1; aiming at the second-class production attribute information, carrying out attribute difference analysis on the second-class production attribute information of the normal product and the second-class production attribute information of the abnormal product to obtain an attribute difference C2; aiming at the third type of production attribute information, attribute difference analysis can be carried out on the third type of production attribute information of the normal products and the third type of production attribute information of the abnormal products to obtain attribute difference C3. Then, the above product difference data may be determined based on the attribute differences C1, C2, and C3.

In some embodiments of the present application, product difference data between a normal product and an abnormal product is determined based on production attribute information of the normal product and production attribute information of the abnormal product, comprising the steps of:

determining a statistical data difference between the statistical data of the production attribute information of the normal product and the statistical data of the production attribute information of the abnormal product; product variance data is determined based on the statistical data variance.

In this embodiment, the statistical data difference refers to a difference in statistical data for describing data, for example, a difference between statistical data for describing production attribute information of a normal product and statistical data of production attribute information of an abnormal product, wherein the statistical data may be descriptive statistical indicators.

At this time, the statistical data difference may be used to describe a difference between the average value of the production attribute information of the normal product and the average value of the production attribute information of the abnormal product, or may be used to describe a difference between the median of the production attribute information of the normal product and the median of the production attribute information of the abnormal product.

In this embodiment, a set of production attribute information may be mapped to a value by applying calculation logic, which may be denoted as y=f (x 1, x 2), and then determining the value as a statistical data difference.

In one possible embodiment, x1 may be production attribute information of a normal product, x2 may be production attribute information of an abnormal product, y is a calculated statistical data difference, and f is a logical relationship applied in the calculation process. At this time, the statistical data of the production attribute information of the normal product can be calculated by the calculation logic, and the statistical data of the production attribute information of the abnormal product is determined by the calculation logic, so that the difference between the statistical data is determined by the calculation logic.

In another possible embodiment, x1 may be the statistics of the production attribute information of the normal product, x2 may be the statistics of the production attribute information of the abnormal product, y is the calculated statistics difference, and f is the logical relationship applied by the calculation process. At this point, the difference between the statistics can be determined by the calculation logic.

In the case where the kinds of production attribute information are plural, the difference between the statistical data of the same kind of production attribute information can be determined.

Aiming at the first type of production attribute information, carrying out attribute difference analysis on the statistical data of the first type of production attribute information of the normal product and the statistical data of the first type of production attribute information of the abnormal product to obtain an attribute difference C1; wherein the attribute differences C2 and C3 may be obtained for the second type of production attribute information and the third type of production attribute information, respectively, and will not be described in detail herein. Then, the attribute difference C1, the attribute difference C2, and the attribute difference C3 may be determined as the above-described statistical data differences.

In other embodiments of the present application, product difference data between a normal product and an abnormal product is determined based on production attribute information of the normal product and production attribute information of the abnormal product, comprising the steps of:

Determining the result of difference significance test of the production attribute information of the normal product and the production attribute information of the abnormal product; wherein the result of the difference saliency test is used for indicating the probability that no difference exists between the production attribute information of the normal product and the production attribute information of the abnormal product; product difference data is determined from the results of the difference significance test.

The product difference data includes, in addition to the statistical data differences described in the above embodiments, the results of the difference saliency check calculated by a complex mathematical algorithm on the production attribute information of the normal product and the abnormal product. The probability that there is no difference between each production attribute information of the normal product and the abnormal product can be determined by the result of the difference saliency check.

In this embodiment, an equal-value hypothesis test may be performed on each production attribute information of the normal product and the abnormal product to obtain a statistical difference P value, and then a probability that there is no difference between each production attribute information of the normal product and the abnormal product may be determined from the statistical difference P value, that is, the statistical difference P value is determined as a result of the difference saliency test.

Here, for each production attribute information, a statistical difference P value may be calculated to determine a probability that there is no difference between the production attribute information for a normal product and an abnormal product from the statistical difference P value.

In some embodiments of the present application, in the case that the kinds of the production attribute information are plural, determining the differential production attribute of the product to be analyzed according to the quantitative analysis result includes the steps of:

comparing the quantitative analysis result of each production attribute information of the product to be analyzed with a preset threshold value to obtain a comparison result; and determining the differential production attribute in the multiple production attribute information according to the comparison result.

After the statistical quantization analysis is performed on the production attribute information of the product to be analyzed to obtain the quantization analysis result, the differential production attribute of the product to be analyzed may be determined according to the quantization analysis result, so as to determine the cause of the difference of the product to be analyzed between the feature values of the same product features according to the differential production attribute.

In this embodiment, a corresponding preset threshold value may be set in advance for the quantization analysis result, wherein the preset threshold value set in advance for each production attribute information is not exactly the same, and the number of preset threshold values set for each production attribute information may be one or plural.

In the case where the number of preset thresholds set for each production attribute information is plural, plural threshold ranges can be determined by the plural preset thresholds. For example, the preset thresholds are M and N, and M is smaller than N, at this time, the plurality of threshold ranges may be a threshold range smaller than the preset threshold M, a threshold range between the preset threshold M and the preset threshold N, and a threshold range larger than the preset threshold N. In this case, the threshold range in which the quantized analysis result is located may be determined by comparing the quantized analysis result with each preset threshold value, thereby obtaining a comparison result between the quantized analysis result and the preset threshold value.

Here, the preset threshold is a critical value for determining production attribute information as a result of the quantitative analysis of the differential production attribute. By comparing the quantization analysis result with a preset threshold value, it is possible to determine whether the production attribute information is a differential production attribute according to the comparison result.

In some embodiments of the present application, in the case where the product to be analyzed includes a normal product and an abnormal product, determining a differential production attribute among a plurality of production attribute information according to the comparison result, includes the steps of:

determining production attribute information of the product difference data meeting a first threshold requirement based on a comparison result of the product difference data; wherein the product difference data is used for indicating attribute differences between each production attribute information of the normal product and the abnormal product; and determining the differential production attribute according to the production attribute information meeting the first threshold requirement.

As is apparent from the description of the above embodiments, the quantitative analysis result may contain product difference data between each production attribute information of the normal product and the abnormal product. From the product difference data, the degree of product difference between the normal product and the abnormal product can be determined.

In this embodiment, the product difference data may be compared with a corresponding preset threshold value to obtain a comparison result. And determining a threshold range of the product difference data according to the comparison result, and further determining whether the product difference data meets a first threshold requirement according to the threshold range, wherein if the first threshold requirement is met, determining that the production attribute information corresponding to the product difference data is a difference production attribute.

For example, product difference data P determined based on first type production attribute information of normal products and abnormal products, the preset threshold value corresponding to the product difference data P is a threshold value Q. At this time, if the product difference data P is greater than the preset threshold Q, it is determined that the product difference data P meets the first threshold requirement, and the difference production attribute may be determined according to the first type production attribute information.

Here, the first threshold requirements of the product difference data of different production attribute information are not identical in content. For example, the first threshold requirement may be that the product variance data is greater than a preset threshold, or that the product variance data is less than a preset threshold. Here, the content of the first threshold requirement corresponding to the product difference data may be determined according to the kind of the production attribute information.

In this embodiment, if the product difference data of each production attribute information is plural, for example, the product difference data contains a statistical data difference and a statistical difference P value. Here, the statistical data difference may be determined in the manner described in the above embodiments, and the statistical difference P value may be understood as the result of the difference saliency test described in the above embodiments. The preset threshold corresponding to the statistical data difference is Q1, and the preset threshold corresponding to the statistical difference P value is Q2. And if the statistical data difference and the statistical difference P value are determined to respectively meet the respective first threshold requirements, determining that the production attribute information is a difference production attribute. For example, if it is determined that the statistical difference P value is smaller than the preset threshold Q2 and that the statistical data difference is larger than the preset threshold Q1, the production attribute information is determined to be a difference production attribute.

In this embodiment, if there is product difference data of a plurality of production attribute information satisfying a first threshold requirement, it may be determined that the plurality of production attribute information is determined as a difference production attribute; it is also possible to determine an absolute value of a difference between the product difference data of each production attribute information and a preset threshold value, and determine the first X pieces of production attribute information having the largest absolute value as the difference production attributes, wherein X is smaller than the number of candidate production attributes, and X is greater than 0.

In some embodiments of the present application, determining production attribute information for which the product differential data meets a first threshold requirement based on a comparison of the product differential data includes the steps of:

determining production attribute information meeting a second threshold requirement based on the comparison result of the statistical data; determining production attribute information meeting the first threshold requirement according to the production attribute information meeting the second threshold requirement; wherein the statistical data includes statistical data of each production attribute information of the normal product or statistical data of each production attribute information of the abnormal product.

As is apparent from the description of the above embodiments, the quantization analysis result may include statistical data of each production attribute information of a normal product and statistical data of each production attribute information of an abnormal product. Wherein the statistics may be determined in the manner described in the above embodiments, and will not be described in detail here.

In this embodiment, the statistical data may be compared with a corresponding preset threshold value, so as to obtain a comparison result of the statistical data. Production attribute information meeting a second threshold requirement may then be determined based on the comparison, wherein the content of the second threshold requirement is associated with the type of statistical data. The meeting of the second threshold requirement may be that the statistical data is greater than a corresponding preset threshold, or that the statistical data is less than a corresponding preset threshold.

In this embodiment, if it is determined that the statistical data of the production attribute information of the normal product satisfies the second threshold requirement according to the comparison result, or if it is determined that the statistical data of the production attribute information of the abnormal product satisfies the second threshold requirement, the production attribute information satisfying the first threshold requirement is determined in the production attribute information, and then the differential production attribute is determined according to the production attribute information satisfying the first threshold requirement.

In this embodiment, the reliability of the product difference data determined based on the production attribute information can be determined by the statistical data. If the statistical data of the production attribute information of the normal product or the statistical data of the production attribute information of the abnormal product meets the second threshold requirement, determining that the reliability of the product difference data determined based on the production attribute information is high; otherwise, the reliability is determined to be low.

By determining the production attribute information of which the statistical data meets the second threshold requirement and determining the production attribute information meeting the first threshold requirement according to the production attribute information, the abnormal failure mechanism of the abnormal product does not need to be analyzed in advance for analysis, so that the determination process can simplify the determination flow of the differential production attribute, save the determination cost of the differential production attribute and improve the reliability of the differential production attribute.

The analysis process of the product analysis method will be described below with reference to a specific example, which is exemplified by an industrial production line for performing batteries, in which the storage device is a database. Referring to the flow chart shown in fig. 2, this specific example specifically includes the following steps.

S21: the product number of the battery is obtained.

Here, each cell in production may be numbered to obtain a product number of each cell, wherein each cell may be numbered "date of production-line number-number" in the form of: 20230101-001-000001. Wherein, since the production line number of the industrial production line has uniqueness, the product number of the battery also has uniqueness.

S22: and collecting production attribute information of the battery.

The battery production process may undergo various processes, such as liquid injection, formation, and the like. In each process of the battery, production attribute information is collected. For example, production attribute information that may be collected during the priming process includes, but is not limited to: the weight of the battery before liquid injection, the vacuumizing time before liquid injection, the vacuum degree before liquid injection, the weight of the battery after liquid injection, the liquid injection amount and the like. The liquid injection amount is production attribute information obtained by carrying out derivative treatment based on the weight of the battery before liquid injection and the weight of the battery after liquid injection, and is equal to the weight of the battery after liquid injection minus the weight of the battery before liquid injection.

S23: the product number and the production attribute information of the battery are associated and stored in a database.

The production attribute information of the battery and the product number of the battery may be stored in association in the database using the storage structure of table 1 as follows.

TABLE 1

The first data in table 1 is the battery weight (No. zyqddczl) of the battery with product No. 20230101-001-000001 before the injection step (No. ZHUYE). The attribute value of the battery weight before the liquid injection (namely, the production attribute information) is 2000, and the acquisition time is 2023/01/01:15:30.

S24: and acquiring production attribute information of the normal battery based on the product number of the normal battery, and acquiring production attribute information of the abnormal battery based on the product number of the abnormal battery.

S25: statistical data of production attribute information of the normal battery and production attribute information of the abnormal battery are respectively determined.

Assume that an industrial production line of batteries performs a spot check of 100 batteries, wherein 10 batteries have a problem of abnormal capacity and 90 batteries have normal capacities. Assuming that production attribute information of 1000 batteries is stored in the database in total, at this time, the following operations may be performed:

since the production attribute information of the battery in the database is associated with the product number of the battery, the production attribute information may be classified into production attribute information of a normal battery (i.e., normal group data) and production attribute information of an abnormal battery (i.e., abnormal group data) according to whether the capacity of the battery is normal.

Next, descriptive statistical indexes of each of the normal group data and the abnormal group data, for example, the number of values C1 of the normal group data and the number of values C2 of the abnormal group data are calculated.

S26: product difference data of production attribute information of a normal battery and production attribute information of an abnormal battery are calculated.

Here, the result of the difference saliency check between the normal group data and the abnormal group data and the statistical data difference may be calculated by an algorithm of the equal-mean hypothesis test. The difference significance check result may be a Wilcoxon rank sum test P value calculated from the normal group data and the abnormal group data, and the statistical data difference may be a median difference value calculated from the normal group data and the abnormal group data. Wherein the median difference value is used to describe the difference between the median of the normal group data and the abnormal group data; the Wilcoxon rank sum test is a test method for an equal-mean hypothesis test.

Then, each production attribute information of the battery is respectively associated with the calculated descriptive statistical index and the product difference data, and the result is as shown in table 2 below.

TABLE 2

Producing attribute information	C1	C2	P	Q
					Attribute 1	90	10	0.000001	0.8
Attribute 2	90	10	0.3	0.05
					…	…	…	…	…

S27: and determining the difference production attribute according to the statistical data and the product difference data.

Here, the analysis may be performed based on the meaning of the statistical data and the product difference data, for example, the smaller P is, the greater the probability of correlation of the production attribute information with the battery capacity abnormality is; the larger Q is, the larger the difference between the production attribute information is. The larger C1 is, the more the number of values of the production attribute information of the normal battery is, and the larger C2 is, the more the number of values of the production attribute information of the abnormal battery is; wherein the more abundant the number of values, the more the number of production attribute information is indicated, and the more reliable the product difference data determined based on the production attribute information is.

Here, if the preset threshold 1 of C1 and C2 is set to be smaller than 90, the preset threshold 2 of P is set to be smaller than 0.3 and larger than 0.000001 (for example, may be 0.01), and the preset threshold 3 of Q is set to be smaller than 0.8 and larger than 0.05 (for example, may be 0.7); wherein, C1 and C2 are greater than a preset threshold 1, then it is determined that the second threshold requirement is satisfied, P is less than a preset threshold 2, and Q is greater than a preset threshold 3, then it is determined that the first threshold requirement is satisfied. Then by analyzing the production attribute information of the normal battery and the abnormal battery, which meet the second threshold requirement for the attribute 1 and the attribute 2, and the P value and the Q value of the normal battery and the abnormal battery, which meet the first threshold requirement for the attribute 1, it can be determined that the attribute 1 has a very significant association with the battery capacity abnormality, while the attribute 2 has a less significant association with the capacity abnormality.

The process of determining the differential production attribute will be described with reference to fig. 3, where the attribute N in the production attribute information is described as an example, and other kinds of attributes in the production attribute information are the same as the process of determining the attribute N, and will not be described one by one.

S31: it is determined whether the number of values C1 of the attribute N of the normal battery or the number of values C2 of the attribute N of the abnormal battery is smaller than a preset threshold value 1. If yes, step S35 is performed, otherwise step S32 is performed.

S32: it is determined whether the P value is greater than a preset threshold 2 (e.g., 0.01). If yes, step S35 is performed, otherwise step S33 is performed.

S33: it is determined whether the Q value is less than a preset threshold 3. If yes, step S35 is performed, otherwise step S34 is performed.

S34: the determined attribute N is a variance production attribute.

S35: it is determined that attribute N is not a variance production attribute.

In the embodiment of the application, the production attribute information of the normal battery and the production attribute information of the abnormal battery can be respectively subjected to statistical analysis to obtain the value quantity of each production attribute information; meanwhile, the production attribute information of the normal battery and the production attribute information of the abnormal battery can be subjected to difference analysis, so that product difference data are obtained; thereafter, it can be determined whether each attribute is a differential production attribute by the product differential data and the number of values of the production attribute information. The difference significance of the production attribute information of the battery in the production process is reflected through the quantization index in the whole process, so that a judgment basis is provided for determining the difference production attribute; the whole process does not need to analyze the abnormal failure mechanism of the abnormal product in advance, so that the determination process can simplify the determination flow of the differential production attribute and save the determination cost of the differential production attribute.

The foregoing description of various embodiments is intended to highlight differences between the various embodiments, which may be the same or similar to each other by reference, and is not repeated herein for the sake of brevity.

As shown in fig. 4, another embodiment of the present application provides a flowchart of a battery product analysis method, which specifically includes the following steps:

s401: production attribute information of a normal battery and production attribute information of an abnormal battery are acquired.

In the production process of the battery, the production attribute information of the battery can be acquired through production equipment. The production attribute information may be determined based on an attribute value of at least one production attribute of the industrial production line during the production of the product. The production attributes include production material attributes, production environment attributes, worker operation attributes, and line equipment attributes of the battery. If the number of the production links of the battery is multiple, the attribute value of the production attribute of each production link can be recorded, so that the production attribute information can be obtained.

The production attribute information of the battery and the product number of the battery may be stored in association in the database using the storage structure of table 1 as described above.

Suppose that an industrial production line of batteries has run through 100 batteries, of which 10 batteries are abnormal and 90 batteries are normal. It is assumed that production attribute information of 1000 batteries is stored in the database in total, at this time, the production attribute information of the 100 batteries may be acquired in the database according to the product numbers of the batteries, and the production attribute information may be classified into production attribute information of a normal battery and production attribute information of an abnormal battery according to whether the batteries are normal or not.

S402: and carrying out statistics and quantization analysis on the production attribute information of the normal battery and the production attribute information of the abnormal battery to obtain a quantization analysis result.

S403: determining a difference production attribute according to the quantitative analysis result; wherein the differential production attribute is used to indicate an abnormality cause of an abnormality of the abnormal battery.

After the quantitative analysis result is determined, an abnormality cause indicating that an abnormality exists in the abnormal battery, that is, a difference production attribute, may be determined from the respective production attributes of the battery. And then, the production attribute of the industrial production line can be adjusted according to the different production attribute so as to realize the product yield of the industrial production line.

In some embodiments of the present application, statistical quantization analysis is performed on production attribute information of a normal battery and production attribute information of an abnormal battery to obtain a quantization analysis result, including: determining statistical data of at least one production attribute information of the normal battery and the abnormal battery; and determining a quantitative analysis result based on the statistical data.

Here, the determination process of the statistical data is the same as that of the statistical data of at least one production attribute information of the normal product and the abnormal product in the above embodiment, and will not be described in detail here.

In some embodiments of the present application, determining statistical data of at least one production attribute information of a normal battery and an abnormal battery includes:

calculating a third statistical variable of each production attribute information of the normal battery; calculating a fourth statistical variable of each production attribute information of the abnormal battery; and determining statistical data according to the third statistical variable and the fourth statistical variable.

Here, the determination process of the third statistical variable is the same as that of the first statistical variable in the above-described embodiment, and will not be described in detail here; the determination of the fourth statistical variable is the same as the determination of the second statistical variable in the above-described embodiment, and will not be described in detail here.

determining a third normal inspection result of each production attribute information of the normal battery, and determining a fourth normal inspection result of each production attribute information of the abnormal battery; and determining statistical data according to the third normal test result and the fourth normal test result.

Here, the determination process of the third normal inspection result is the same as that of the first normal inspection result in the above-described embodiment, and will not be described in detail here; the determination process of the fourth normal check result is the same as that of the second normal check result in the above-described embodiment, and will not be described in detail here.

In some embodiments of the present application, statistical quantization analysis is performed on production attribute information of a normal battery and production attribute information of an abnormal battery to obtain a quantization analysis result, including:

determining product difference data between the normal battery and the abnormal battery based on the production attribute information of the normal battery and the production attribute information of the abnormal battery; and determining a quantitative analysis result based on the product difference data.

Here, the determination process of the product difference data is the same as that of the product difference data between the normal product and the abnormal product in the above embodiment, and will not be described in detail here.

In some embodiments of the present application, determining product difference data between a normal battery and an abnormal battery based on production attribute information of the normal battery and production attribute information of the abnormal battery includes: determining a statistical data difference between the statistical data of the production attribute information of the normal battery and the statistical data of the production attribute information of the abnormal battery; product variance data is determined based on the statistical data variance.

Here, the process of determining the statistical data difference is the same as the process of determining the statistical data difference between the statistical data of the production attribute information of the normal product and the statistical data of the production attribute information of the abnormal product in the above-described embodiment, and will not be described in detail here.

In some embodiments of the present application, determining product difference data between a normal battery and an abnormal battery based on production attribute information of the normal battery and production attribute information of the abnormal battery includes: determining a difference significance test result based on the production attribute information of the normal product and the production attribute information of the abnormal product; product difference data is determined from the results of the difference significance test.

Here, the determination process of the result of the difference saliency check is the same as that of the above embodiment, and will not be described in detail here.

As shown in fig. 5, further embodiments of the present application provide a product analysis apparatus for performing the product analysis method provided in any of the above embodiments, the apparatus comprising:

a first quantization unit 501, configured to perform statistical quantization analysis on production attribute information of a product to be analyzed, so as to obtain a quantization analysis result; wherein, the product model of the products to be analyzed is the same, and at least one product feature with different feature values of the same product feature exists among the products to be analyzed;

a first determining unit 502, configured to determine a differential production attribute of a product to be analyzed according to a quantized analysis result; wherein the variance production attribute is used for indicating a variance reason for a variance between feature values of product features of the product to be analyzed.

A first quantization unit 501, configured to obtain a quantization analysis result based on production attribute information of a normal product and production attribute information of an abnormal product in a product to be analyzed; the quantitative analysis result is used for representing the association degree of each production attribute information and an abnormal reason, wherein the abnormal reason is the reason that the characteristic value of the product characteristic of the abnormal product is abnormal.

A first quantization unit 501 for determining statistical data of at least one production attribute information of a normal product and an abnormal product; and determining a quantitative analysis result based on the statistical data.

A first quantization unit 501 for calculating a first statistical variable of each production attribute information of the normal product; wherein the first statistical variable is used for representing the information concentration degree and the information divergence degree of each production attribute information of the normal product; calculating a second statistical variable of each production attribute information of the abnormal product; wherein the second statistical variable is used for representing the information concentration degree and the information divergence degree of each production attribute information of the abnormal product; determining the statistical data according to the first statistical variable and the second statistical variable.

A first quantization unit 501 for determining a first normalization check result of each production attribute information of the normal product; wherein the first normalization test result is used for representing the probability that each production attribute information of the normal product does not accord with a normal distribution; determining a second normalization test result for each production attribute information of the abnormal product; wherein the second normalization test result is used for representing the probability that each production attribute information of the abnormal product does not accord with a normal distribution; and determining the statistical data according to the first normal testing result and the second normal testing result.

A first quantization unit 501 for determining product difference data between a normal product and an abnormal product based on production attribute information of the normal product and production attribute information of the abnormal product; and determining a quantitative analysis result based on the product difference data.

A first quantization unit 501 for determining a statistical data difference between the statistical data of the production attribute information of the normal product and the statistical data of the production attribute information of the abnormal product; product variance data is determined based on the statistical data variance.

A first quantization unit 501 for determining a result of a difference saliency check of production attribute information of the normal product and production attribute information of the abnormal product; wherein the result of the difference saliency test is used for indicating the probability that no difference exists between the production attribute information of the normal product and the production attribute information of the abnormal product; and determining the product difference data according to the result of the difference significance test.

A first determining unit 502, configured to compare a quantized analysis result of each production attribute information of a product to be analyzed with a preset threshold value to obtain a comparison result when the types of the production attribute information are multiple; and determining the differential production attribute in the plurality of production attribute information according to the comparison result.

A first determining unit 502, configured to determine, based on a comparison result of the product difference data, production attribute information that the product difference data meets a first threshold requirement, in a case where the product to be analyzed includes a normal product and an abnormal product; wherein the product difference data is used for indicating attribute differences between each production attribute information of the normal product and the abnormal product; and determining the differential production attribute according to the production attribute information meeting the first threshold requirement.

A first determining unit 502, configured to determine production attribute information meeting a second threshold requirement based on a comparison result of the statistical data, and determine the production attribute information meeting the first threshold requirement according to the production attribute information meeting the second threshold requirement; wherein the statistical data includes statistical data of each of the production attribute information of the normal product or statistical data of each of the production attribute information of the abnormal product.

As shown in fig. 6, further embodiments of the present application provide a battery product analysis apparatus for performing the battery product analysis method provided in any of the above embodiments, the apparatus comprising:

An obtaining unit 601, configured to obtain production attribute information of a normal battery and production attribute information of an abnormal battery;

a second quantization unit 602, configured to perform statistical quantization analysis on production attribute information of the normal battery and production attribute information of the abnormal battery, so as to obtain a quantization analysis result;

the second determining unit 603 is configured to determine a difference production attribute according to the quantized analysis result; wherein the differential production attribute is used to indicate an abnormality cause of an abnormality of the abnormal battery.

Another embodiment of the present application provides an electronic device, which may be a device for performing product analysis on an industrial production line such as a host computer, and the electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor, where the processor executes the program to implement the product analysis method of any one of the above embodiments.

As shown in fig. 7, the electronic device 70 may include: processor 700, memory 701, bus 702, and communication interface 703, processor 700, communication interface 703, and memory 701 being connected by bus 702; the memory 701 stores a computer program executable on the processor 700, which when executed by the processor 700 performs the method provided by any of the previous embodiments of the application.

The memory 701 may include a high-speed random access memory (RAM: random Access Memory), and may further include a non-volatile memory (non-volatile memory), such as at least one magnetic disk memory. The communication connection between the system network element and at least one other network element is implemented via at least one communication interface 703 (which may be wired or wireless), the internet, a wide area network, a local network, a metropolitan area network, etc. may be used.

Bus 702 may be an ISA bus, a PCI bus, an EISA bus, or the like. The buses may be divided into address buses, data buses, control buses, etc. The memory 701 is configured to store a program, and the processor 700 executes the program after receiving an execution instruction, and the method disclosed in any of the foregoing embodiments of the present application may be applied to the processor 700 or implemented by the processor 700.

The processor 700 may be an integrated circuit chip having signal processing capabilities. In implementation, the steps of the methods described above may be performed by integrated logic circuitry in hardware or instructions in software in processor 700. The processor 700 may be a general-purpose processor, and may include a central processing unit (Central Processing Unit, CPU for short), a network processor (Network Processor, NP for short), and the like; but may also be a Digital Signal Processor (DSP), application Specific Integrated Circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present application may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The steps of the method disclosed in connection with the embodiments of the present application may be embodied directly in the execution of a hardware decoding processor, or in the execution of a combination of hardware and software modules in a decoding processor. The software modules may be located in a random access memory, flash memory, read only memory, programmable read only memory, or electrically erasable programmable memory, registers, etc. as well known in the art. The storage medium is located in the memory 701, and the processor 700 reads information in the memory 701, and in combination with its hardware, performs the steps of the above method.

The electronic device provided by the embodiment of the application and the method provided by the embodiment of the application have the same beneficial effects as the method adopted, operated or realized by the electronic device and the method provided by the embodiment of the application due to the same inventive concept.

Another embodiment of the present application provides a computer-readable storage medium having stored thereon a computer program that is executed by a processor to implement the control method of any of the above embodiments.

Referring to fig. 8, a computer readable storage medium is shown as an optical disc 20 having a computer program (i.e., a program product) stored thereon, which, when executed by a processor, performs the method provided by any of the embodiments described above.

It should be noted that examples of the computer readable storage medium may also include, but are not limited to, a phase change memory (PRAM), a Static Random Access Memory (SRAM), a Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a flash memory, or other optical or magnetic storage medium, which will not be described in detail herein.

Another embodiment of the present application provides a computer program product including a computer program that is executed by a processor to implement the control method of any of the above embodiments.

The computer readable storage medium and the computer program product provided by the above embodiments of the present application are both the same as the methods provided by the embodiments of the present application, and have the same advantages as the methods adopted, operated or implemented by the application program stored therein.

It should be noted that:

the term "module" is not intended to be limited to a particular physical form. Depending on the particular application, modules may be implemented as hardware, firmware, software, and/or combinations thereof. Furthermore, different modules may share common components or even be implemented by the same components. There may or may not be clear boundaries between different modules.

The algorithms and displays presented herein are not inherently related to any particular computer, virtual machine, or other apparatus. Various general purpose devices may also be used with the examples herein. The required structure for the construction of such devices is apparent from the description above. In addition, the present application is not directed to any particular programming language. It will be appreciated that the teachings of the present application described herein may be implemented in a variety of programming languages, and the above description of specific languages is provided for disclosure of enablement and best mode of the present application.

It should be understood that, although the steps in the flowcharts of the figures are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the flowcharts of the figures may include a plurality of sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily being sequential, but may be performed in turn or alternately with other steps or at least a portion of the other steps or stages.

The foregoing examples merely illustrate embodiments of the application and are described in more detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of the application should be assessed as that of the appended claims.

Claims

1. A method of product analysis, comprising:

determining the differential production attribute of the product to be analyzed according to the quantitative analysis result; the difference production attribute is used for indicating a difference reason that the product to be analyzed has a difference between characteristic values of the same product characteristics;

the statistical quantitative analysis is performed on the production attribute information of the product to be analyzed to obtain a quantitative analysis result, and the statistical quantitative analysis comprises the following steps:

obtaining a quantitative analysis result based on the production attribute information of the normal products and the production attribute information of the abnormal products in the products to be analyzed; the quantitative analysis result is used for representing the association degree of each production attribute information and an abnormal reason, wherein the abnormal reason is the reason that the characteristic value of the product characteristic of the abnormal product is abnormal;

Comparing the quantitative analysis result of each production attribute information of the product to be analyzed with a preset threshold value to obtain a comparison result; and determining the different production attribute in a plurality of production attribute information according to the comparison result.

2. The method according to claim 1, wherein the obtaining of the quantitative analysis result based on the production attribute information of the normal product and the production attribute information of the abnormal product in the products to be analyzed includes:

and determining the quantitative analysis result based on the statistical data.

3. The method of claim 2, wherein said determining statistical data of at least one production attribute information of said normal products and said abnormal products comprises:

calculating a first statistical variable of each production attribute information of the normal product;

calculating a second statistical variable of each production attribute information of the abnormal product;

determining the statistical data according to the first statistical variable and the second statistical variable.

4. The method of claim 2, wherein said determining statistical data of at least one production attribute information of said normal products and said abnormal products comprises:

5. The method according to claim 1, wherein the obtaining of the quantitative analysis result based on the production attribute information of the normal product and the production attribute information of the abnormal product in the products to be analyzed includes:

6. The method of claim 5, wherein the determining product difference data between the normal product and the abnormal product based on the production attribute information of the normal product and the production attribute information of the abnormal product comprises:

the product variance data is determined based on the statistical data variance.

7. The method of claim 5, wherein the determining product difference data between the normal product and the abnormal product based on the production attribute information of the normal product and the production attribute information of the abnormal product comprises:

8. The method of claim 1, wherein the product to be analyzed comprises a normal product and an abnormal product;

9. The method of claim 8, wherein determining production attribute information for the product differential data to meet a first threshold requirement based on the comparison of the product differential data comprises:

determining production attribute information meeting the second threshold requirement based on a comparison result of the statistical data, and determining the production attribute information meeting the first threshold requirement according to the production attribute information meeting the second threshold requirement; wherein the statistical data includes statistical data of each of the production attribute information of the normal product or statistical data of each of the production attribute information of the abnormal product.

10. A method of analyzing a battery product, comprising:

Carrying out statistics and quantization analysis on the production attribute information of the normal battery and the production attribute information of the abnormal battery to obtain a quantization analysis result; the quantitative analysis result is used for representing the association degree of each production attribute information and an abnormal reason, wherein the abnormal reason is the reason for the occurrence of abnormality of the characteristic value of the product characteristic of the abnormal battery;

determining a difference production attribute according to the quantitative analysis result; wherein the differential production attribute is used for indicating an abnormality cause of abnormality of the abnormal battery;

the determining the production attribute of the difference according to the quantitative analysis result comprises the following steps:

comparing the quantitative analysis result of each production attribute information with a preset threshold value to obtain a comparison result; and determining the different production attribute in a plurality of production attribute information according to the comparison result.

11. A product analysis device, comprising:

The first determining unit is used for determining the difference production attribute of the product to be analyzed according to the quantitative analysis result; wherein the difference production attribute is used for indicating a difference reason for the difference between the characteristic values of the product characteristics of the product to be analyzed;

wherein, the first quantization unit is further configured to: obtaining a quantitative analysis result based on the production attribute information of the normal products and the production attribute information of the abnormal products in the products to be analyzed; the quantitative analysis result is used for representing the association degree of each production attribute information and an abnormal reason, wherein the abnormal reason is the reason that the characteristic value of the product characteristic of the abnormal product is abnormal;

the first determining unit is further configured to: comparing the quantitative analysis result of each production attribute information of the product to be analyzed with a preset threshold value to obtain a comparison result; and determining the different production attribute in a plurality of production attribute information according to the comparison result.

12. A battery product analysis device, comprising:

The second quantization unit is used for carrying out statistical quantization analysis on the production attribute information of the normal battery and the production attribute information of the abnormal battery to obtain a quantization analysis result; the quantitative analysis result is used for representing the association degree of each production attribute information and an abnormal reason, wherein the abnormal reason is the reason for the occurrence of abnormality of the characteristic value of the product characteristic of the abnormal battery;

a second determining unit, configured to determine a difference production attribute according to the quantitative analysis result; wherein the differential production attribute is used for indicating an abnormality cause of abnormality of the abnormal battery;

the second determining unit is further configured to:

13. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the method of any one of claims 1 to 10.

14. A computer readable storage medium having stored thereon a computer program, characterized in that the program is executed by a processor to implement the method of any of claims 1 to 10.