CN111898903A - Method and system for evaluating uniformity and comprehensive quality of steel product - Google Patents
Method and system for evaluating uniformity and comprehensive quality of steel product Download PDFInfo
- Publication number
- CN111898903A CN111898903A CN202010739592.4A CN202010739592A CN111898903A CN 111898903 A CN111898903 A CN 111898903A CN 202010739592 A CN202010739592 A CN 202010739592A CN 111898903 A CN111898903 A CN 111898903A
- Authority
- CN
- China
- Prior art keywords
- data
- batch
- quality
- temperature
- data set
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Factory Administration (AREA)
Abstract
The invention discloses a method and a system for evaluating the uniformity and comprehensive quality of steel products, wherein the method comprises the following steps: acquiring a data set to be evaluated; wherein each batch comprises a plurality of temperature curves and a plurality of quality indexes; calculating the relative volume of the temperature curve of each batch and the specification area and the relative distance between the temperature curve of each batch and the target temperature value; combining the relative volume and the relative distance with the quality indexes in the corresponding batch of data to form a quality index data set and carrying out standardization processing to eliminate dimension influence; and calculating the relative closeness degree of each batch and the optimal scheme to be used as a basis for evaluating the quality of the current batch. The method solves the problem of uniformity evaluation of the abnormal process data by using a nuclear density estimation method; the method is divided into two processes of training and evaluating, so that an objective similarity is given to a new batch as a comprehensive evaluation index of multiple quality indexes.
Description
Technical Field
The invention relates to the technical field of process industrial quality control and optimization, in particular to a method and a system for evaluating the uniformity and comprehensive quality of steel products.
Background
In the process of industrial production, a good mathematical model is required to be established to perform uniformity analysis on process curves such as temperature curves of a plurality of rolling processes of high-quality wire rods, so as to obtain a uniformity evaluation index. However, almost all steel production processes are rolled many times, so the data obtained contain numerous process curves such as process temperature.
On the other hand, in the enterprise production and operation activities, a plurality of quality indexes of the product need to be comprehensively evaluated, so that the comprehensive classified pricing of the product is realized. Therefore, it is necessary to analyze the several detection indexes determining the fluctuation of the product quality by using a comprehensive evaluation method.
However, the existing method is not suitable for multivariate abnormal data, and can not comprehensively evaluate a plurality of quality indexes.
Disclosure of Invention
The invention provides a method and a system for evaluating the uniformity and comprehensive quality of a steel product, which aim to solve the technical problems that the existing method is not suitable for multivariate abnormal data and can not comprehensively evaluate a plurality of quality indexes.
In order to solve the technical problems, the invention provides the following technical scheme:
in one aspect, the invention provides a method for evaluating the uniformity and comprehensive quality of a steel product, which comprises the following steps:
acquiring a data set to be evaluated; the data set to be evaluated comprises a plurality of batches of data, and each batch of data respectively comprises a plurality of temperature curves and a plurality of quality indexes in the rolling process of the current product to be evaluated;
calculating the relative volume of the temperature data of each batch of data and the specification area and the relative distance between the temperature data of each batch of data and the target temperature value on the basis of the temperature curve in each batch of data;
combining the relative volume and the relative distance with the quality indexes in the corresponding batch data to form a quality index data set, and carrying out standardization processing on the quality index data set to eliminate dimension influence;
and calculating the relative closeness degree of each batch of data and the optimal scheme based on the quality index data set after the standardization processing to obtain the uniformity and comprehensive quality evaluation result of the steel product corresponding to the current batch of data.
Further, the temperature profile includes: a start rolling temperature curve, a finish rolling temperature curve and a spinning temperature curve; the plurality of quality indicators include: the tensile strength, the reduction of area, the diameter qualification rate of various standards and the out-of-roundness qualification rate of various standards of the product to be evaluated at present.
Further, the calculating the relative volume of the temperature data of each batch of data and the specification area and the relative distance between the temperature data of each batch of data and the target temperature value based on the temperature curve in each batch of data comprises:
based on a dynamic curve regulation method, aligning a plurality of temperature curves with different lengths in each batch of data to ensure that the lengths of the temperature curves are equal;
calculating the relative volume of the temperature data and the specification area of each batch based on a nuclear density estimation method;
and calculating the relative distance between the temperature data of each batch and the target temperature value based on a Euclidean distance method.
Further, the aligning a plurality of temperature curves with different lengths in each batch of data based on a dynamic curve adjustment method to make the lengths of the temperature curves equal includes:
and aligning a plurality of temperature curves with different lengths in each batch of data by using a dynamic time warping method so as to enable the lengths of the temperature curves to be equal.
Further, calculating the relative volume of the temperature data and the specification area of each batch based on a nuclear density estimation method comprises:
fitting the multivariate data distribution by a kernel density estimation method, dividing the specification area into a plurality of grids, and calculating the probability density value of each grid point in the divided grids; and taking the ratio of the number of the grid points with the corresponding probability density value larger than the preset threshold value to the total number of the grid points as the volume ratio of the corresponding temperature data to the specification area so as to obtain the relative volume of the temperature data and the specification area.
Further, calculating the relative distance between the temperature data of each batch and the target temperature value based on the Euclidean distance method, including:
and comparing the deviation of the temperature data and the target temperature value with the process target interval to eliminate dimensional influence.
Further, the normalizing the quality index data set to eliminate the dimension influence includes:
carrying out forward processing on the quality index data set to obtain a forward matrix;
the resulting forward matrix is normalized to eliminate dimensional effects.
Further, performing forward processing on the quality index data set to obtain a forward matrix, including:
multiplying the column of the forward index and the column of the reverse index by-1 in the matrix corresponding to the quality index data set to obtain a forward matrix; wherein the forward index is an index positively correlated with the product quality, and the reverse index is an index negatively correlated with the product quality.
Further, based on the quality index data set after the standardization processing, the relative approach degree of each batch of data and the optimal scheme is calculated, and the uniformity and comprehensive quality evaluation result of the steel product corresponding to the current batch of data is obtained, and the method comprises the following steps:
dividing the quality index data set after the standardization treatment into a training set and a data set to be evaluated;
finding the optimal scheme and the worst scheme in the training set; the optimal scheme is a vector formed by the maximum value in each column in the training set, and the worst scheme is a vector formed by the minimum value in each column in the training set;
calculating the distance between each batch of data in the data set to be evaluated and the optimal scheme and the worst scheme;
based on the distance between each batch of data and the optimal scheme and the worst scheme, the relative approach degree of each batch of data and the optimal scheme is obtained through the following formula and is used as a basis for evaluating the quality of the current batch:
wherein Rc represents the relative closeness of the current batch data to the optimal solution, D1 represents the distance between the current batch data and the worst solution, and D2 represents the distance between the current batch data and the optimal solution.
In another aspect, the present invention further provides a system for evaluating uniformity and comprehensive quality of steel products, comprising:
the data set acquisition module is used for acquiring a data set to be evaluated; the data set to be evaluated comprises a plurality of batches of data, and each batch of data respectively comprises a plurality of temperature curves and a plurality of quality indexes in the rolling process of the current product to be evaluated;
the uniformity evaluation index acquisition module is used for calculating the relative volume between the temperature curve of each batch of data and the specification area and the relative distance between the temperature curve of each batch of data and the target temperature value on the basis of the temperature curve of each batch of data acquired by the data set acquisition module;
the quality index data set construction module is used for combining the relative volume and the relative distance calculated by the uniformity evaluation index acquisition module with the quality indexes in the corresponding batch of data to form a quality index data set, and carrying out standardization processing on the quality index data set to eliminate dimensional influence;
and the good and bad solution distance calculation module is used for calculating the relative approach degree of each batch of data and the optimal scheme by adopting the quality index data set subjected to the standardized processing of the quality index data set construction module, so as to obtain the uniformity and comprehensive quality evaluation result of the steel product corresponding to the current batch of data.
In yet another aspect, the present invention also provides an electronic device comprising a processor and a memory; wherein the memory has stored therein at least one instruction that is loaded and executed by the processor to implement the above-described method.
In yet another aspect, the present invention also provides a computer-readable storage medium having at least one instruction stored therein, the instruction being loaded and executed by a processor to implement the above method.
The technical scheme provided by the invention has the beneficial effects that at least:
the method comprises the steps of calculating the relative volume of the temperature data of each batch of data and a specification area and the relative distance between the temperature data of each batch of data and a target temperature value; combining the relative volume and the relative distance with the quality indexes in the corresponding batch of data to form a quality index data set, and carrying out standardization processing on the quality index data set to eliminate dimension influence; and dividing the quality index data set after the standardization treatment into a training set and a data set to be evaluated, and then calculating the relative closeness degree of each batch of data to the optimal scheme to obtain the uniformity and comprehensive quality evaluation result of the steel product corresponding to the current batch of data. Therefore, the problem of uniformity evaluation of the abnormal process data is solved by using a nuclear density estimation method; the method is divided into two processes of training and evaluating, so that an objective similarity is given to a new batch as a comprehensive evaluation index of multiple quality indexes.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a method for evaluating the uniformity and comprehensive quality of a steel product according to a first embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method for evaluating the uniformity and comprehensive quality of a steel product according to a second embodiment of the present invention;
FIG. 3 is a flowchart illustrating a distance method for good/bad solutions according to a second embodiment of the present invention;
fig. 4 is a schematic diagram of a distribution of cluster generated data according to a second embodiment of the present invention;
FIG. 5 is a schematic diagram of the relative area of 100 batches of rolling process temperature data provided by a second embodiment of the present invention;
FIG. 6 is a graph illustrating the relative distance between the temperature data of 100 batches of rolling processes according to a second embodiment of the present invention;
FIG. 7 is a multi-index radar chart according to a second embodiment of the present invention;
fig. 8 is a schematic diagram illustrating the comparison between the area and the volume of the radar map and the combined quality index of the 27 batches by the good-bad solution distance method according to the second embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
First embodiment
The embodiment provides a method for evaluating the uniformity and comprehensive quality of a steel product, which can be realized by electronic equipment, wherein the electronic equipment can be a terminal or a server. The execution flow of the method for evaluating the uniformity and the comprehensive quality of the steel product is shown in figure 1 and comprises the following steps:
s101, acquiring a data set to be evaluated; the data set to be evaluated comprises a plurality of batches of data, and each batch of data respectively comprises a plurality of temperature curves and a plurality of quality indexes in the rolling process of the current product to be evaluated;
it should be noted that the acquired temperature profile may include: a start rolling temperature curve, a finish rolling temperature curve, a spinning temperature curve and other process curves; the obtained quality indicators may include: the tensile strength, the reduction of area, the diameter qualification rate of various standards, the out-of-roundness qualification rate of various standards and other indexes of the current product to be evaluated.
S102, calculating the relative volume of the temperature data of each batch of data and the specification area and the relative distance between the temperature data of each batch of data and a target temperature value based on the temperature curve in each batch of data;
before calculating the relative volume and the relative distance, if the temperature curves are not equal in length, the temperature curves in different lengths in each batch of data need to be aligned based on a dynamic curve adjustment method, such as a dynamic time adjustment method, so that the lengths of the temperature curves are equal; the relative volume can be obtained by a nuclear density estimation method, and the relative distance can be obtained by a Euclidean distance method. The relative volume and the relative distance are uniformity evaluation indexes for evaluating uniformity of the process parameters; the relative volume may be used to describe how dense the process data is, and the relative distance may be used to describe how far the process data is deviated.
S103, combining the relative volume and the relative distance with the quality indexes in the corresponding batch of data to form a quality index data set, and carrying out standardization processing on the quality index data set to eliminate dimension influence;
it should be noted that the process of normalizing the quality index data set includes: carrying out forward processing on the quality index data set to obtain a forward matrix; the resulting forward matrix is normalized to eliminate dimensional effects. The method comprises the following steps of carrying out forward processing on a quality index data set to obtain a forward matrix, specifically: multiplying the column of the forward index by 1 and the column of the reverse index by-1 in the matrix corresponding to the quality index data set to obtain a forward matrix; wherein, the positive index refers to the index which is positively correlated with the product quality, and the reverse index refers to the index which is negatively correlated with the product quality.
And S104, calculating the relative closeness of each batch of data to the optimal scheme based on the standardized quality index data set, and obtaining the uniformity and comprehensive quality evaluation result of the steel products corresponding to the current batch.
It should be noted that the calculation process of the relative proximity includes: dividing the quality index data set after the standardization treatment into a training set and a data set to be evaluated; finding out the optimal scheme and the worst scheme in the training set; the optimal scheme is a vector formed by the maximum value in each column in the training set, and the worst scheme is a vector formed by the minimum value in each column in the training set; calculating the distance between each batch of data in the data set to be evaluated and the optimal scheme and the worst scheme; based on the distance between each batch of data and the optimal scheme and the worst scheme, the relative approach degree of each batch of data and the optimal scheme is obtained through the following formula and is used as a basis for evaluating the quality of the current batch:
wherein Rc represents the relative closeness of the current batch data to the optimal solution, D1 represents the distance between the current batch data and the worst solution, and D2 represents the distance between the current batch data and the optimal solution.
In summary, the present invention calculates the relative volume between the temperature data of each batch and the specification area, and the relative distance between the temperature data of each batch and the target temperature value; combining the relative volume and the relative distance with the quality indexes in the corresponding batch of data to form a quality index data set, and carrying out standardization processing on the quality index data set to eliminate dimension influence; and dividing the quality index data set after the standardization treatment into a training set and a data set to be evaluated, and then calculating the relative proximity degree of each batch of data to the optimal scheme to obtain the uniformity and comprehensive quality evaluation result of the steel product corresponding to the current batch of data. Therefore, the problem of uniformity evaluation of the abnormal process data is solved by using a nuclear density estimation method; the method is divided into two processes of training and evaluating, so that an objective similarity is given to a new batch as a comprehensive evaluation index of multiple quality indexes.
Second embodiment
The embodiment provides a method for evaluating the uniformity and comprehensive quality of a steel product, which can be realized by electronic equipment, wherein the electronic equipment can be a terminal or a server. The execution flow of the method for evaluating the uniformity and the comprehensive quality of the steel product is shown in figure 2 and comprises the following steps:
s101, acquiring a data set to be evaluated;
it should be noted that the data set to be evaluated in this embodiment may be an original data set, or may be obtained by random extraction on the original data set. The acquired data set to be evaluated comprises a plurality of batches of data, and each batch of data respectively comprises a plurality of temperature curves and a plurality of quality indexes in the rolling process of the current product to be evaluated; the temperature profile obtained may include: a start rolling temperature curve, a finish rolling temperature curve, a spinning temperature curve and other process curves; the obtained quality indicators may include: the tensile strength, the reduction of area, the diameter qualification rate of various standards, the out-of-roundness qualification rate of various standards and other indexes of the current product to be evaluated.
Further, when acquiring the data set to be evaluated, the present embodiment further includes the following processes: if the tensile strength and the reduction of area are within the acceptable range, the values outside the range should be set to 0, and the values within the acceptable range are retained. The diameter data is converted into statistical values. Namely, the ratio of the number of points satisfying the diameter standard 1 to the total number of measurement points, the ratio of the number of points satisfying the diameter standard 2 to the total number of measurement points, the ratio of the number of points satisfying the diameter standard 3 to the total number of measurement points, and so on. The out-of-roundness data is converted into statistical values. Namely, the ratio of the number of points satisfying the out-of-roundness standard 1 to the total number of measured points, the ratio of the number of points satisfying the out-of-roundness standard 2 to the total number of measured points, the ratio of the number of points satisfying the out-of-roundness standard 3 to the total number of measured points, and so on.
S102, aligning a plurality of temperature curves with different lengths in each batch of data based on a dynamic curve adjusting method so as to enable the lengths of the temperature curves to be equal;
it should be noted that the two sequences as a whole have very similar shapes, but these shapes are not aligned in the x-axis. One (or both) of the sequences needs to be warped in the time axis to achieve alignment before their similarities are compared. Dynamic time warping is an effective way to achieve this distortion. Dynamic time warping calculates the similarity between two time series properties by extending and shortening the time series. In this embodiment, a dynamic time warping method is adopted to align a plurality of temperature curves with different lengths in each batch of data, so that the lengths of the temperature curves are equal, and the subsequent operations are facilitated.
S103, calculating the relative volume of the temperature data and the specification area of each batch of data based on a nuclear density estimation method;
in addition, S103 specifically includes: fitting the multivariate data distribution by a kernel density estimation method, dividing the specification area into a plurality of grids, and calculating the probability density value of each grid point in the divided grids; and taking the ratio of the point number of the grid point with the corresponding probability density value larger than the preset threshold value to the total point number of the grid point as the volume ratio of the corresponding temperature data to the specification area.
The kernel density estimation is to estimate a probability density function, estimate the distribution of a plurality of samples and calculate the probability density function, and can obtain the probability of any interval. Therefore, kernel density estimation is a process from a sample to a universal probability density, and then a universal guide is used to solve a specific problem, and the method is suitable for non-normal data.
S104, calculating the relative distance between the temperature data of each batch of data and the target temperature value based on a Euclidean distance method;
the degree of deviation of the process curve such as temperature from the target value is calculated using the euclidean distance. Firstly, three temperatures at each point on the length of the wire rod are regarded as a vector, the Euclidean distance between the vector and a target temperature vector is calculated, and then the average distance between all the measuring points and a target temperature value is calculated. This average distance serves as a deviation indicator. In which the deviation of each temperature should be compared with the upper and lower intervals of the temperature in calculating the euclidean distance between the vectors so as to eliminate the dimensional influence.
The relative volume and the relative distance calculated by the above S103 and S104 are uniformity evaluation indexes for evaluating uniformity of the process parameter; the relative volume may be used to describe how dense the process data is, and the relative distance may be used to describe how far the process data is deviated.
S105, combining the relative volume and the relative distance with the quality indexes in the corresponding batch data to form a quality index data set containing a plurality of batches and pair indexes;
s106, carrying out standardization processing on the quality index data set to eliminate dimension influence;
it should be noted that the process of normalizing the quality index data set includes: carrying out forward processing on the quality index data set to obtain a forward matrix; the resulting forward matrix is normalized to eliminate dimensional effects. The method comprises the following steps of carrying out forward processing on a quality index data set to obtain a forward matrix, specifically: multiplying the column of the forward index by 1 and the column of the reverse index by-1 in the matrix corresponding to the quality index data set to obtain a forward matrix; wherein, the positive index refers to the index which has positive correlation with the product quality, such as tensile strength, reduction of area, qualification rate of various diameters, qualification rate of various out-of-roundness, and the like. The reverse index refers to an index negatively correlated with the product quality, such as relative volume, relative distance.
In addition, before the normalization process, an entropy weight method should be used to calculate an objective weight coefficient for each quality index.
S107, randomly dividing the quality index data set after the standardization treatment into a training set and a data set to be evaluated, and finding out the optimal scheme and the worst scheme in the training set;
wherein, the proportion of the data set to be evaluated is set as a certain percentage, and the number of samples in the training set should be large enough, so that the obtained optimal scheme and the worst scheme belong to global optimal or global worst rather than local.
The optimal scheme is a vector formed by maximum values in each column in the training set, and the worst scheme is a vector formed by minimum values in each column in the training set.
S108, calculating the distance between each batch of data in the data set to be evaluated and the optimal scheme and the worst scheme;
s109, calculating the relative closeness degree of each batch of data and the optimal scheme based on the distance between each batch of data and the optimal scheme and the worst scheme, and using the relative closeness degree as a basis for evaluating the quality of the current batch.
Based on the distance between each batch of data and the optimal scheme and the worst scheme, the relative approach degree of each batch of data and the optimal scheme is obtained through the following formula and is used as a basis for evaluating the quality of the current batch:
wherein Rc represents the relative closeness of the current batch data to the optimal solution, D1 represents the distance between the current batch data and the worst solution, and D2 represents the distance between the current batch data and the optimal solution.
The above-mentioned S107 to S109 are good-bad solution distance methods, and the flow thereof is shown in fig. 3, since the optimal solution and the worst solution are derived from the training set when the method is used, the finally obtained relative closeness degree is an objective value and will not change with the change of the data set to be evaluated.
In the embodiment, the process capability index is applied to the uniformity analysis research of steel products such as wire rods and the like, and the temperature data in the rolling process is used for verification analysis.
The rolling process temperature data set used for the verification of the present embodiment comprises 265 batches, each batch comprising three temperature profiles of different lengths: a start rolling temperature curve, a finish rolling temperature curve, and a spinning temperature curve.
The rolling process temperature data set for the above validation was subjected to the following processing:
carrying out isometric treatment on the three temperature curves by utilizing dynamic time bending; calculating the distribution of the temperature data in a three-dimensional space by utilizing nuclear density estimation to obtain a probability density function; dividing specification areas at equal intervals by grids, and calculating the probability value of each grid intersection point by using the probability density function; and calculating the deviation degree of the temperature data and the target central temperature value by using the Euclidean distance.
In order to verify the effectiveness of the uniformity evaluation method, the present embodiment uses cluster generation data for analysis.
The clustered data set included 20 x 3 samples, containing two distribution centers, each sample including 400 x 2 data points. The data distribution is shown in fig. 4. In the simulation data set, the mean value gradually deviates from the target center along with the change of the mean value, and the relative distance shows an ascending trend. The variation in the standard deviation has substantially no effect on the relative distance. With the increase of standard deviation in the simulation data set, the discrete degree of the process data is larger and larger, and the relative area shows an ascending trend. The change in the mean value has substantially no effect on the relative area.
Further, the following will explain the method of this embodiment by taking actual data as an example, where the data set includes 265 batches, each of which has three temperature lines with different lengths, including a start rolling temperature line, a finish rolling temperature line, and a laying temperature line; the quality data set comprises tensile strength, reduction of area, diameter qualification rate of three standards and out-of-roundness qualification rate of three standards of 265 batches of wire rods, and the method comprises the following steps:
1) and (4) carrying out equal length treatment on the three temperature curves by utilizing dynamic time bending.
2) And fitting the multivariate distribution of the temperature data by using the kernel density estimation to obtain a probability density function.
3) The specification area is divided into 100 × 100 grids, and the probability density value of each grid point is calculated. The threshold value is set to 0.001, and the ratio of the number of mesh points having a probability density value greater than the threshold value to the total number of mesh points is set as the volume ratio of the process area to the specification area, with the result shown in fig. 5.
4) The deviation degree of the temperature data from the target central temperature value was calculated using the euclidean distance, and the result is shown in fig. 6.
5) Assuming that n indexes of m batches are evaluated, an initial matrix is established.
6) And carrying out normalization processing on the index matrix. And carrying out normalization processing on each index.
7) And calculating the entropy weight of each index. First, the entropy of the j index is defined as:
9) And constructing a normalized matrix.
10) Determining an ideal point P+And a negative ideal point P-。
11) The distance of each batch in the test data set to the ideal point and the negative ideal point is calculated.
12) The relative closeness of each batch in the test dataset to the ideal solution, i.e. the evaluation index, is calculated:
in the formula: ci∈[0,1]And C in the schemeiThe larger the better the scheme.
In order to verify the effectiveness of the comprehensive evaluation method of the good and bad solution distance method, the similarity index calculated by the good and bad solution distance method is compared with the area of the radar map. The multi-index radar chart is shown in fig. 7.
The area calculation formula of the radar map is as follows:
the calculation formula of the perimeter of the radar map is as follows:
the comparison result is shown in fig. 8, which shows that the comprehensive quality evaluation based on the good-bad solution distance method of the embodiment can well reflect the multi-aspect quality of one batch of wire rods by comparing with the area of the radar map.
Third embodiment
The embodiment provides a system for evaluating the uniformity and the comprehensive quality of a steel product, which comprises the following modules:
the data set acquisition module is used for acquiring a data set to be evaluated; the data set to be evaluated comprises a plurality of batches of data, and each batch of data respectively comprises a plurality of temperature curves and a plurality of quality indexes in the rolling process of the current product to be evaluated;
the uniformity evaluation index acquisition module is used for calculating the relative volume between the temperature curve of each batch of data and the specification area and the relative distance between the temperature curve of each batch of data and the target temperature value based on the temperature curve of each batch of data acquired by the data set acquisition module;
the quality index data set construction module is used for combining the relative volume and the relative distance calculated by the uniformity evaluation index acquisition module with the quality indexes in the corresponding batch of data to form a quality index data set, and carrying out standardization processing on the quality index data set to eliminate dimensional influence;
and the good and bad solution distance calculation module is used for calculating the relative closeness degree of each batch of data to the optimal scheme by adopting the quality index data set subjected to the standardized processing of the quality index data set construction module, so as to obtain the uniformity and comprehensive quality evaluation result of the steel product corresponding to the current batch of data.
The system for evaluating the uniformity and the comprehensive quality of the steel product of the embodiment corresponds to the method for evaluating the uniformity and the comprehensive quality of the steel product of the first embodiment; the functions realized by the functional modules in the system for evaluating the uniformity and the comprehensive quality of the steel product of the embodiment correspond to the flow steps in the method for evaluating the uniformity and the comprehensive quality of the steel product of the first embodiment one by one; therefore, it is not described herein.
Fourth embodiment
The present embodiment provides an electronic device, which includes a processor and a memory; wherein the memory has stored therein at least one instruction that is loaded and executed by the processor to implement the method of the first embodiment.
The electronic device may generate a large difference due to different configurations or performances, and may include one or more processors (CPUs) and one or more memories, where at least one instruction is stored in the memory, and the instruction is loaded by the processor and performs the following steps:
s101, acquiring a data set to be evaluated; the data set to be evaluated comprises a plurality of batches of data, and each batch of data respectively comprises a plurality of temperature curves and a plurality of quality indexes in the rolling process of the current product to be evaluated;
s102, calculating the relative volume of the temperature data of each batch of data and the specification area and the relative distance between the temperature data of each batch of data and a target temperature value based on the temperature curve in each batch of data;
s103, combining the relative volume and the relative distance with the quality indexes in the corresponding batch of data to form a quality index data set, and carrying out standardization processing on the quality index data set to eliminate dimension influence;
and S104, calculating the relative closeness of each batch of data to the optimal scheme based on the standardized quality index data set, and obtaining the uniformity and comprehensive quality evaluation result of the steel products corresponding to the current batch.
The electronic device of the embodiment calculates the relative volume of the temperature data of each batch and the specification area and the relative distance between the temperature data of each batch and the target temperature value; combining the relative volume and the relative distance with the quality indexes in the corresponding batch of data to form a quality index data set, and carrying out standardization processing on the quality index data set to eliminate dimension influence; and dividing the quality index data set after the standardization treatment into a training set and a data set to be evaluated, and then calculating the relative proximity degree of each batch to the optimal scheme to obtain the uniformity and comprehensive quality evaluation results of the steel products corresponding to the current batch. Therefore, the problem of uniformity evaluation of the abnormal process data is solved by using a nuclear density estimation method; the method is divided into two processes of training and evaluating, so that an objective similarity is given to a new batch as a comprehensive evaluation index of multiple quality indexes.
Fifth embodiment
The present embodiments provide a computer-readable storage medium having at least one instruction stored therein, the instruction being loaded and executed by a processor to implement the above-mentioned method. The computer readable storage medium may be, among others, ROM, Random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like. The instructions stored therein may be loaded by a processor in the terminal and perform the steps of:
s101, acquiring a data set to be evaluated; the data set to be evaluated comprises a plurality of batches of data, and each batch of data respectively comprises a plurality of temperature curves and a plurality of quality indexes in the rolling process of the current product to be evaluated;
s102, calculating the relative volume of the temperature data of each batch of data and the specification area and the relative distance between the temperature data of each batch of data and a target temperature value based on the temperature curve in each batch of data;
s103, combining the relative volume and the relative distance with the quality indexes in the corresponding batch of data to form a quality index data set, and carrying out standardization processing on the quality index data set to eliminate dimension influence;
and S104, calculating the relative closeness of each batch of data to the optimal scheme based on the standardized quality index data set, and obtaining the uniformity and comprehensive quality evaluation result of the steel products corresponding to the current batch.
The program stored in the storage medium of this embodiment calculates the relative volume between the temperature data of each batch and the specification area, and the relative distance between the temperature data of each batch and the target temperature value; combining the relative volume and the relative distance with the quality indexes in the corresponding batch of data to form a quality index data set, and carrying out standardization processing on the data set to eliminate dimension influence; and dividing the quality index data set after the standardization treatment into a training set and a data set to be evaluated, and then calculating the relative proximity degree of each batch to the optimal scheme to obtain the uniformity and comprehensive quality evaluation results of the steel products corresponding to the current batch. Therefore, the problem of uniformity evaluation of the abnormal process data is solved by using a nuclear density estimation method; the method is divided into two processes of training and evaluating, so that an objective similarity is given to a new batch as a comprehensive evaluation index of multiple quality indexes.
Furthermore, it should be noted that the present invention may be provided as a method, apparatus or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media having computer-usable program code embodied in the medium.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks. These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It is further noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. The terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
Finally, it should be noted that the above describes only a preferred embodiment of the invention and that, although a preferred embodiment of the invention has been described, numerous modifications and adaptations can be made by those skilled in the art without departing from the principles of the present invention and are intended to be within the scope of the invention. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Claims (10)
1. A method for evaluating the uniformity and comprehensive quality of a steel product, the method comprising:
acquiring a data set to be evaluated; the data set to be evaluated comprises a plurality of batches of data, and each batch of data respectively comprises a plurality of temperature curves and a plurality of quality indexes in the rolling process of the current product to be evaluated;
calculating the relative volume of the temperature data of each batch of data and the specification area and the relative distance between the temperature data of each batch of data and the target temperature value on the basis of the temperature curve in each batch of data;
combining the relative volume and the relative distance with the quality indexes in the corresponding batch data to form a quality index data set, and carrying out standardization processing on the quality index data set to eliminate dimension influence;
and calculating the relative closeness degree of each batch of data and the optimal scheme based on the quality index data set after the standardization processing to obtain the uniformity and comprehensive quality evaluation result of the steel product corresponding to the current batch of data.
2. The method for the homogeneity and comprehensive quality assessment of steel products according to claim 1, characterized in that said temperature profile comprises: a start rolling temperature curve, a finish rolling temperature curve and a spinning temperature curve;
the plurality of quality indicators include: the tensile strength, the reduction of area, the diameter qualification rate of various standards and the out-of-roundness qualification rate of various standards of the product to be evaluated at present.
3. The method of claim 1, wherein the calculating the relative volume of the temperature data and the specification area of each batch of data and the relative distance between the temperature data and the target temperature value of each batch of data based on the temperature profile of each batch of data comprises:
based on a dynamic curve regulation method, aligning a plurality of temperature curves with different lengths in each batch of data to ensure that the lengths of the temperature curves are equal;
calculating the relative volume of the temperature data and the specification area of each batch based on a nuclear density estimation method;
and calculating the relative distance between the temperature data of each batch and the target temperature value based on a Euclidean distance method.
4. The method of claim 3, wherein the aligning the plurality of temperature curves of different lengths in each batch of data based on a dynamic curve normalization method to equalize the lengths of the temperature curves comprises:
and aligning a plurality of temperature curves with different lengths in each batch of data by using a dynamic time warping method so as to enable the lengths of the temperature curves to be equal.
5. The method of claim 3, wherein calculating the relative volume of temperature data and gauge area for each batch based on a nuclear density estimation method, comprises:
fitting the multivariate data distribution by a kernel density estimation method, dividing the specification area into a plurality of grids, and calculating the probability density value of each grid point in the divided grids; and taking the ratio of the number of the grid points with the corresponding probability density value larger than the preset threshold value to the total number of the grid points as the volume ratio of the corresponding temperature data to the specification area so as to obtain the relative volume of the temperature data and the specification area.
6. The method of claim 3, wherein the calculating the relative distance between the temperature data of each batch and the target temperature value based on the Euclidean distance method comprises:
and comparing the deviation of the temperature data and the target temperature value with the process target interval to eliminate dimensional influence.
7. The method of claim 1, wherein normalizing the quality index dataset to eliminate dimensional effects comprises:
carrying out forward processing on the quality index data set to obtain a forward matrix;
the resulting forward matrix is normalized to eliminate dimensional effects.
8. The method of claim 7, wherein the step of performing a forward processing on the quality index dataset to obtain a forward matrix comprises:
multiplying the column of the forward index and the column of the reverse index by-1 in the matrix corresponding to the quality index data set to obtain a forward matrix; wherein the forward index is an index positively correlated with the product quality, and the reverse index is an index negatively correlated with the product quality.
9. The method for evaluating the uniformity and the comprehensive quality of steel products according to claim 1, wherein the step of calculating the relative closeness degree of each batch of data to the optimal scheme based on the quality index dataset after the standardization process to obtain the result of evaluating the uniformity and the comprehensive quality of the steel products corresponding to the current batch of data comprises the steps of:
dividing the quality index data set after the standardization treatment into a training set and a data set to be evaluated;
finding the optimal scheme and the worst scheme in the training set; the optimal scheme is a vector formed by the maximum value in each column in the training set, and the worst scheme is a vector formed by the minimum value in each column in the training set;
calculating the distance between each batch of data in the data set to be evaluated and the optimal scheme and the worst scheme;
based on the distance between each batch of data and the optimal scheme and the worst scheme, the relative approach degree of each batch of data and the optimal scheme is obtained through the following formula and is used as a basis for evaluating the quality of the current batch:
wherein Rc represents the relative closeness of the current batch data to the optimal solution, D1 represents the distance between the current batch data and the worst solution, and D2 represents the distance between the current batch data and the optimal solution.
10. A system for evaluating the uniformity and comprehensive quality of a steel product, comprising:
the data set acquisition module is used for acquiring a data set to be evaluated; the data set to be evaluated comprises a plurality of batches of data, and each batch of data respectively comprises a plurality of temperature curves and a plurality of quality indexes in the rolling process of the current product to be evaluated;
the uniformity evaluation index acquisition module is used for calculating the relative volume between the temperature curve of each batch of data and the specification area and the relative distance between the temperature curve of each batch of data and the target temperature value on the basis of the temperature curve of each batch of data acquired by the data set acquisition module;
the quality index data set construction module is used for combining the relative volume and the relative distance calculated by the uniformity evaluation index acquisition module with the quality indexes in the corresponding batch of data to form a quality index data set, and carrying out standardization processing on the quality index data set to eliminate dimensional influence;
and the good and bad solution distance calculation module is used for calculating the relative approach degree of each batch of data and the optimal scheme by adopting the quality index data set subjected to the standardized processing of the quality index data set construction module, so as to obtain the uniformity and comprehensive quality evaluation result of the steel product corresponding to the current batch of data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010739592.4A CN111898903A (en) | 2020-07-28 | 2020-07-28 | Method and system for evaluating uniformity and comprehensive quality of steel product |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010739592.4A CN111898903A (en) | 2020-07-28 | 2020-07-28 | Method and system for evaluating uniformity and comprehensive quality of steel product |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111898903A true CN111898903A (en) | 2020-11-06 |
Family
ID=73182492
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010739592.4A Pending CN111898903A (en) | 2020-07-28 | 2020-07-28 | Method and system for evaluating uniformity and comprehensive quality of steel product |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111898903A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114169694A (en) * | 2021-11-16 | 2022-03-11 | 北京科技大学设计研究院有限公司 | Process capability analysis method and device based on big data platform |
| CN114580982A (en) * | 2022-05-07 | 2022-06-03 | 昆仑智汇数据科技(北京)有限公司 | Method, device and equipment for evaluating data quality of industrial equipment |
| CN114861509A (en) * | 2022-07-07 | 2022-08-05 | 苏州翔楼新材料股份有限公司 | Special steel heat treatment process data processing method and system |
Citations (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105301184A (en) * | 2015-09-14 | 2016-02-03 | 湖南中烟工业有限责任公司 | Cut tobacco production batch homogenization evaluation method |
| CN105522133A (en) * | 2015-12-21 | 2016-04-27 | 安徽工业大学 | Judgment method of bonding behavior between continuous casting slab and crystallizer copper plate |
| CN105573279A (en) * | 2015-12-31 | 2016-05-11 | 广州中国科学院先进技术研究所 | Method of monitoring industrial process based on sensor data |
| CN106153835A (en) * | 2016-08-30 | 2016-11-23 | 云南中烟工业有限责任公司 | A kind of method using Euclidean distance to judge papermaking-method reconstituted tobaccos pulp fiber distribution consistency degree |
| CN106682297A (en) * | 2016-12-21 | 2017-05-17 | 江苏大学 | Method for multi-objective quality comprehensive evaluation optimization of injection molding technology |
| US20170169380A1 (en) * | 2015-12-14 | 2017-06-15 | Wipro Limited | Method and System for Determining Quality Level of Performance Data Associated With an Enterprise |
| CN107357269A (en) * | 2017-06-17 | 2017-11-17 | 湖州师范学院 | Multistage process quality prediction method based on mixing MPLS |
| CN107657266A (en) * | 2017-08-03 | 2018-02-02 | 华北电力大学（保定） | A kind of load curve clustering method based on improvement spectrum multiple manifold cluster |
| CN108120653A (en) * | 2017-12-13 | 2018-06-05 | 安徽中烟工业有限责任公司 | A kind of method of finished cigarettes quality stability between evaluation batch |
| CN108416695A (en) * | 2018-02-24 | 2018-08-17 | 合肥工业大学 | Electric load probability density prediction technique based on deep learning and system, medium |
| CN108959249A (en) * | 2018-06-21 | 2018-12-07 | 中国农业科学院农田灌溉研究所 | A kind of evaluation method of periodical best paper |
| CN109409627A (en) * | 2018-08-17 | 2019-03-01 | 浙江华云信息科技有限公司 | A kind of acquisition terminal production firm evaluation method based on more evaluation indexes |
| CN109409628A (en) * | 2018-08-17 | 2019-03-01 | 国网浙江省电力有限公司 | Acquisition terminal production firm evaluation method based on metering big data Clustering Model |
| CN110210730A (en) * | 2019-05-20 | 2019-09-06 | 太原理工大学 | A kind of regional complex energy resource system energy efficiency state evaluation method |
| CN110348652A (en) * | 2018-04-03 | 2019-10-18 | 普华讯光（北京）科技有限公司 | The quantitative estimation method of switchgear house operation health degree |
| CN110795463A (en) * | 2019-06-27 | 2020-02-14 | 浙江大学 | Mass time series data visualization method for transient analysis of power system |
| CN111080835A (en) * | 2019-11-04 | 2020-04-28 | 北京科技大学 | Hot-rolled strip steel wedge defect diagnosis method and system based on gray comprehensive correlation degree |
| CN111191667A (en) * | 2018-11-15 | 2020-05-22 | 天津大学青岛海洋技术研究院 | Crowd counting method for generating confrontation network based on multiple scales |
| CN111310789A (en) * | 2020-01-15 | 2020-06-19 | 云南电网有限责任公司大理供电局 | Wind power interval prediction method based on kernel density estimation and implementation system thereof |
-
2020
- 2020-07-28 CN CN202010739592.4A patent/CN111898903A/en active Pending
Patent Citations (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105301184A (en) * | 2015-09-14 | 2016-02-03 | 湖南中烟工业有限责任公司 | Cut tobacco production batch homogenization evaluation method |
| US20170169380A1 (en) * | 2015-12-14 | 2017-06-15 | Wipro Limited | Method and System for Determining Quality Level of Performance Data Associated With an Enterprise |
| CN105522133A (en) * | 2015-12-21 | 2016-04-27 | 安徽工业大学 | Judgment method of bonding behavior between continuous casting slab and crystallizer copper plate |
| CN105573279A (en) * | 2015-12-31 | 2016-05-11 | 广州中国科学院先进技术研究所 | Method of monitoring industrial process based on sensor data |
| CN106153835A (en) * | 2016-08-30 | 2016-11-23 | 云南中烟工业有限责任公司 | A kind of method using Euclidean distance to judge papermaking-method reconstituted tobaccos pulp fiber distribution consistency degree |
| CN106682297A (en) * | 2016-12-21 | 2017-05-17 | 江苏大学 | Method for multi-objective quality comprehensive evaluation optimization of injection molding technology |
| CN107357269A (en) * | 2017-06-17 | 2017-11-17 | 湖州师范学院 | Multistage process quality prediction method based on mixing MPLS |
| CN107657266A (en) * | 2017-08-03 | 2018-02-02 | 华北电力大学（保定） | A kind of load curve clustering method based on improvement spectrum multiple manifold cluster |
| CN108120653A (en) * | 2017-12-13 | 2018-06-05 | 安徽中烟工业有限责任公司 | A kind of method of finished cigarettes quality stability between evaluation batch |
| US20190265768A1 (en) * | 2018-02-24 | 2019-08-29 | Hefei University Of Technology | Method, system and storage medium for predicting power load probability density based on deep learning |
| CN108416695A (en) * | 2018-02-24 | 2018-08-17 | 合肥工业大学 | Electric load probability density prediction technique based on deep learning and system, medium |
| CN110348652A (en) * | 2018-04-03 | 2019-10-18 | 普华讯光（北京）科技有限公司 | The quantitative estimation method of switchgear house operation health degree |
| CN108959249A (en) * | 2018-06-21 | 2018-12-07 | 中国农业科学院农田灌溉研究所 | A kind of evaluation method of periodical best paper |
| CN109409628A (en) * | 2018-08-17 | 2019-03-01 | 国网浙江省电力有限公司 | Acquisition terminal production firm evaluation method based on metering big data Clustering Model |
| CN109409627A (en) * | 2018-08-17 | 2019-03-01 | 浙江华云信息科技有限公司 | A kind of acquisition terminal production firm evaluation method based on more evaluation indexes |
| CN111191667A (en) * | 2018-11-15 | 2020-05-22 | 天津大学青岛海洋技术研究院 | Crowd counting method for generating confrontation network based on multiple scales |
| CN110210730A (en) * | 2019-05-20 | 2019-09-06 | 太原理工大学 | A kind of regional complex energy resource system energy efficiency state evaluation method |
| CN110795463A (en) * | 2019-06-27 | 2020-02-14 | 浙江大学 | Mass time series data visualization method for transient analysis of power system |
| CN111080835A (en) * | 2019-11-04 | 2020-04-28 | 北京科技大学 | Hot-rolled strip steel wedge defect diagnosis method and system based on gray comprehensive correlation degree |
| CN111310789A (en) * | 2020-01-15 | 2020-06-19 | 云南电网有限责任公司大理供电局 | Wind power interval prediction method based on kernel density estimation and implementation system thereof |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114169694A (en) * | 2021-11-16 | 2022-03-11 | 北京科技大学设计研究院有限公司 | Process capability analysis method and device based on big data platform |
| CN114580982A (en) * | 2022-05-07 | 2022-06-03 | 昆仑智汇数据科技(北京)有限公司 | Method, device and equipment for evaluating data quality of industrial equipment |
| CN114861509A (en) * | 2022-07-07 | 2022-08-05 | 苏州翔楼新材料股份有限公司 | Special steel heat treatment process data processing method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111898903A (en) | Method and system for evaluating uniformity and comprehensive quality of steel product | |
| KR101930420B1 (en) | Metrology sampling method with sampling rate decision scheme and computer program product thereof | |
| CN111199016A (en) | DTW-based improved K-means daily load curve clustering method | |
| CN109351785B (en) | Rolling force optimization method and device | |
| CN105868164A (en) | Soft measurement modeling method based on monitored linear dynamic system model | |
| CN114757660B (en) | Cold-rolled steel strip preparation method and system based on application analysis | |
| CN112241832B (en) | Product quality grading evaluation standard design method and system | |
| CN102709207B (en) | Quality estimation apparatus, quality estimation method and non-transitory computer-readable medium storing program | |
| CN116523908B (en) | Safe production method, system, equipment and medium based on coil coating production line | |
| CN111506878B (en) | Node number selection device and method based on sag system index random sample estimation | |
| CN117610195A (en) | Strip steel expansion prediction method, device, medium and electronic equipment | |
| CN113052256B (en) | Wind direction clustering method and device and electronic equipment | |
| CN116108932A (en) | Method for establishing fusion model of steel production process data and mechanism | |
| CN109212751A (en) | A kind of analysis method of free form surface tolerance | |
| CN115270861A (en) | Product composition data monitoring method and device, electronic equipment and storage medium | |
| CN111985826B (en) | Visual quality grading method and system for multi-index industrial products | |
| CN113255927A (en) | Logistic regression model training method and device, computer equipment and storage medium | |
| Arndt et al. | Analysis of Efficiency in Response Surface Designs Considering Orthogonality Deviations and Cost Models | |
| CN115858895B (en) | Multi-source heterogeneous data processing method and system for smart city | |
| CN117648657B (en) | Urban planning multi-source data optimization processing method | |
| CN113326584B (en) | Electrical equipment optimization design method taking robustness and reliability into consideration | |
| CN109344472B (en) | Method for estimating reliability parameters of mechanical and electrical components | |
| CN116596376A (en) | Online automatic grade judging method and system for deep drawing steel quality | |
| CN118274740A (en) | High-precision measuring method for blade profile of industrial cooling fan | |
| Tung | Optimizing two‐variable gamma accelerated degradation tests with a semi‐analytical approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |