A method and system for monitoring production operation of an electrophoresis production line

By dividing the monitoring data intervals and calculating the fluctuation sensitivity and abnormality degree, establishing an optimization error function model for spline interpolation, the problem of noise interference in the monitoring data of the electrophoretic production line is solved, and the accuracy of the monitoring data is improved.

CN118467908BActive Publication Date: 2024-11-12JIANGSU XICHENG ENVIRONMENTAL SCI RES INST CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410911808.9
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-09
Publication Date
2024-11-12
Estimated Expiration
2044-07-09

AI Technical Summary

Technical Problem

There is noise interference in the monitoring data of the electrophoresis production line and the sampling frequency is different between different data, resulting in poor interpolation processing results and affecting the monitoring accuracy.

Method used

By dividing the electrophoretic production operation monitoring data sequence into multiple monitoring data intervals, the fluctuation sensitivity, abnormality degree and isolated values ​​of each dimension data are calculated, the reference factor is obtained, the optimization error function model is established, and the spline interpolation is performed.

Benefits of technology

It improves the accuracy of interpolation results, enhances the accuracy of real-time monitoring data of the electrophoretic production line, and effectively distinguishes and removes noise data.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118467908B_ABST
    Figure CN118467908B_ABST
Patent Text Reader

Abstract

The present invention relates to the field of data processing technology, and in particular to a method and system for monitoring the production and operation of an electrophoresis production line, including: obtaining an electrophoresis production and operation monitoring data sequence; dividing the electrophoresis production and operation monitoring data sequence into a plurality of monitoring data intervals; obtaining the fluctuation sensitivity of the monitoring data of each dimension; obtaining the degree of fluctuation anomaly of the monitoring data of each dimension in each monitoring data interval; obtaining the fluctuation anomaly isolated value of the monitoring data of each dimension in each monitoring data interval; obtaining the reference factor of each monitoring data of each dimension in each monitoring data interval; obtaining an optimized error function model according to the reference factor; performing spline interpolation on the electrophoresis production and operation monitoring data sequence through the optimized error function model to obtain the interpolated electrophoresis production line operation monitoring data. The present invention improves the accuracy of the production and operation monitoring of the electrophoresis production line.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for monitoring the production operation of an electrophoresis production line. Background Art

[0002] The electrophoretic production line refers to a production line that uses electrophoretic technology for coating. During the electrophoretic process, since the various operating parameters collected are based on those collected by sensors, there is noise interference in the obtained operation monitoring data, and the sampling frequencies of different data are different. Therefore, in order to achieve more accurate combined analysis in the same sequence and improve the monitoring effect of the operating status of the electrophoretic production line, it is usually necessary to improve the analysis accuracy between parameters through interpolation processing.

[0003] When implementing conventional spline interpolation, an indifferent error function is usually used to optimize the interpolation parameters. Since the monitoring data obtained by the sensors in the electrophoresis production equipment itself has certain noise interference, its own fitting error should not be used as the basis for interpolation parameter optimization when participating in fitting. Conventionally, after directly removing these data through abnormal data cleaning, the missing data will lead to poor interpolation results, making the production and operation monitoring data of the electrophoresis production line inaccurate. Summary of the invention

[0004] In order to solve the above problems, the present invention provides a method and system for monitoring the production operation of an electrophoresis production line.

[0005] An embodiment of the present invention provides a method for monitoring the production operation of an electrophoresis production line, the method comprising the following steps:

[0006] Obtaining an electrophoresis production operation monitoring data sequence; dividing the electrophoresis production operation monitoring data sequence into a plurality of monitoring data intervals; each monitoring data interval includes monitoring data of a plurality of dimensions; each dimension of monitoring data includes a plurality of monitoring data;

[0007] According to the fluctuation of the monitoring data of each dimension in different monitoring data intervals and the number of extreme points, the fluctuation sensitivity of the monitoring data of each dimension is obtained;

[0008] According to the difference of monitoring data of each dimension in different monitoring data intervals, the degree of abnormal fluctuation of monitoring data of each dimension in each monitoring data interval is obtained; according to the difference of abnormal fluctuation degree of monitoring data of different dimensions in the monitoring data interval, the abnormal fluctuation isolated value of monitoring data of each dimension in each monitoring data interval is obtained; according to the abnormal fluctuation isolated value, abnormal fluctuation degree and fluctuation sensitivity, the reference factor of each monitoring data of each dimension in each monitoring data interval is obtained;

[0009] An optimized error function model is obtained according to reference factors; spline interpolation is performed on the electrophoresis production operation monitoring data sequence through the optimized error function model to obtain interpolated electrophoresis production line operation monitoring data.

[0010] Preferably, the fluctuation sensitivity of the monitoring data of each dimension is obtained according to the fluctuation of the monitoring data of each dimension in different monitoring data intervals and the number of extreme value points, including the specific method of:

[0011] For Monitoring data of the first dimension and monitoring data intervals, except for the The monitoring data of other dimensions other than the monitoring data of this dimension are in the The fluctuations in the monitoring data interval are obtained. The monitoring data of the dimensions are The fluctuation characteristic factors within the monitoring data interval;

[0012] The first Within the monitoring data interval The number of extreme points of the monitoring data in the dimension All the monitoring data in the interval The ratio of the total number of monitoring data in the dimension is recorded as The monitoring data of the dimensions are The proportion of extreme values ​​in the monitoring data interval; All the monitoring data in the interval The standard deviation of the monitoring data in the dimension The monitoring data of the dimensions are The proportion of extreme values ​​in the monitoring data interval and the The monitoring data of the dimensions are The product of the three fluctuation characteristic factors within the monitoring data interval is taken as the The monitoring data of the dimensions are The fluctuation sensitivity factor within the monitoring data interval; The mean of the fluctuation sensitivity factor of the monitoring data of the dimension in all monitoring data intervals is taken as the The fluctuation sensitivity of monitoring data in different dimensions.

[0013] Preferably, the The monitoring data of the dimensions are The fluctuation characteristic factors within the monitoring data interval include the following specific methods:

[0014] Will remove The monitoring data of other dimensions other than the monitoring data of the first dimension are recorded as the monitoring data of the target dimension; all the monitoring data of the target dimension are recorded in the first dimension. The cumulative sum of the standard deviations within the monitoring data interval is recorded as the first cumulative sum; the difference between 1 and the normalized value of the first cumulative sum is recorded as the second cumulative sum. The monitoring data of the dimensions are The fluctuation characteristic factors within a monitoring data interval.

[0015] Preferably, the method of obtaining the degree of abnormal fluctuation of the monitoring data of each dimension in each monitoring data interval according to the difference of the monitoring data of each dimension in different monitoring data intervals includes the following specific methods:

[0016] Get the The monitoring data of the dimensions are The fitting curve within the monitoring data interval;

[0017] The first The monitoring data of the dimensions are The monitoring data of the monitoring data point in the fitting curve within the monitoring data interval is recorded as The monitoring data of the dimensions are The fitting data within the monitoring data interval; The monitoring data of the dimensions are monitoring data interval and The difference of fitting data between monitoring data intervals is obtained. The monitoring data of the dimensions are monitoring data interval and The data differences between the monitoring data intervals;

[0018] The first The monitoring data of the dimensions are The mean of the data differences between the first monitoring data interval and all other monitoring data intervals is taken as the The monitoring data of the dimensions are The degree of abnormal fluctuation within a monitoring data interval.

[0019] Preferably, the obtaining The monitoring data of the dimensions are The fitting curve within the monitoring data interval includes the following specific methods:

[0020] For Monitoring data of the first dimension and monitoring data interval, with time as the horizontal axis and the The monitoring data of the first dimension is the vertical axis, All the monitoring data in the interval The monitoring data of the first dimension is input into the two-dimensional coordinate system, and several monitoring data points are obtained. All monitoring data points are fitted by the least squares method to form the first The monitoring data of the dimensions are The fitting curve within the monitoring data interval.

[0021] Preferably, the obtaining The monitoring data of the dimensions are monitoring data interval and The data differences between the monitoring data intervals include the following specific methods:

[0022] No. The monitoring data of the dimensions are monitoring data interval and The monitoring data interval The absolute value of the difference between the fitted data is recorded as The first absolute value of the difference of the fitted data; The monitoring data of the dimensions are In the monitoring data interval, The fitted data and The absolute value of the difference between the first and second monitoring data is recorded as the second absolute value of the difference; The monitoring data of the dimensions are In the monitoring data interval, The fitted data and The absolute value of the difference between the first and second monitoring data is recorded as the third absolute value of the difference; the normalized value of the sum of the second absolute value of the difference and the third absolute value of the difference is recorded as the first The first difference of the fitted data; The product of the absolute value of the first difference of the fitted data and the first difference is recorded as The first product of the fitted data; The monitoring data of the dimensions are monitoring data interval and The reciprocal of the cumulative sum of the first products of all the fitting data between the monitoring data intervals is taken as the first The monitoring data of the dimensions are monitoring data interval and The data differences between the monitoring data intervals.

[0023] Preferably, the method of obtaining the abnormal fluctuation isolated value of the monitoring data of each dimension in each monitoring data interval according to the difference in the abnormal fluctuation degree of the monitoring data of different dimensions in the monitoring data interval includes the following specific methods:

[0024] Will remove The monitoring data of other dimensions other than the monitoring data of the first dimension are recorded as the monitoring data of the target dimension; for the monitoring data of any target dimension, according to the The difference between the monitoring data of the first dimension and the monitoring data of the target dimension in the monitoring data interval is used to obtain the abnormal fluctuation degree of the first dimension. The monitoring data of the first dimension and the monitoring data of the target dimension are in the Abnormal fluctuation difference value within the monitoring data interval;

[0025] The first The monitoring data of this dimension is combined with the monitoring data of all other target dimensions in the The average of the fluctuation anomaly difference values ​​within the monitoring data interval is taken as the The monitoring data of the dimensions are Abnormal isolated values ​​of fluctuations within a monitoring data interval.

[0026] Preferably, the obtaining The monitoring data of the first dimension and the monitoring data of the target dimension are in the The abnormal fluctuation difference value within the monitoring data interval includes the following specific methods:

[0027] The first The monitoring data of the dimensions are The degree of abnormal fluctuation in the monitoring data interval is related to the monitoring data of the target dimension in the The absolute value of the difference in the degree of abnormal fluctuation within the monitoring data interval is recorded as The monitoring data of the first dimension and the monitoring data of the target dimension are in the The abnormal fluctuation difference value within the monitoring data interval.

[0028] Preferably, the reference factor of each monitoring data in each monitoring data interval of each dimension is obtained according to the fluctuation anomaly isolated value, fluctuation anomaly degree and fluctuation sensitivity, and the specific method includes:

[0029] In the The monitoring data of the dimensions are In the monitoring data interval, The fitted data and The absolute value of the difference between the monitoring data is recorded as The fitting difference of the monitoring data; The absolute value of the difference in the fluctuation sensitivity of the monitoring data of the first dimension is recorded as the first target difference; the first target difference, the The monitoring data of the dimensions are The fluctuation anomaly isolated value within the monitoring data interval, The product of the three fitting differences of the monitoring data is recorded as the target product; the inverse proportional normalized value of the target product is taken as the The monitoring data of the dimensions are Within the monitoring data interval A reference factor for monitoring data.

[0030] The present invention also proposes an electrophoresis production line production operation monitoring system, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any one of the steps of the electrophoresis production line production operation monitoring method when executing the computer program.

[0031] The beneficial effects of the technical solution of the present invention are as follows: the present invention divides the electrophoresis production operation monitoring data sequence into several monitoring data intervals, and obtains the fluctuation sensitivity of the monitoring data of each dimension, and obtains the reference factor of each monitoring data in each monitoring data interval of each dimension according to the fluctuation anomaly isolated value, fluctuation anomaly degree and fluctuation sensitivity; by combining the abnormal interference between the monitoring data of different dimensions in the actual scene, further distinguishing the noise data existing in each monitoring data interval, and finally obtaining the optimized error function model according to the reference factor; performing spline interpolation on the electrophoresis production operation monitoring data sequence through the optimized error function model, and obtaining the electrophoresis production line operation monitoring data after interpolation, thereby improving the accuracy of the interpolation result, and then improving the accuracy of the real-time monitoring data of the electrophoresis production line. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0033] Figure 1 A flow chart of the steps of a method for monitoring the production operation of an electrophoresis production line according to the present invention;

[0034] Figure 2 This is a characteristic relationship flow chart of production operation monitoring of an electrophoresis production line of the present invention. DETAILED DESCRIPTION

[0035] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the electrophoresis production line production operation monitoring method and system proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0036] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0037] The specific scheme of the electrophoresis production line production operation monitoring method and system provided by the present invention is described in detail below with reference to the accompanying drawings.

[0038] See also Figure 1 , which shows a flow chart of a method for monitoring the production operation of an electrophoresis production line provided by an embodiment of the present invention, the method comprising the following steps:

[0039] Step S001: Acquire an electrophoresis production operation monitoring data sequence; divide the electrophoresis production operation monitoring data sequence into a plurality of monitoring data intervals.

[0040] It should be noted that during the electrophoresis process, since the various operating parameters collected are based on those collected by sensors, there is noise interference in the obtained operation monitoring data, and the sampling frequencies of different data are different. Therefore, in order to achieve more accurate combined analysis in the same sequence and improve the monitoring effect of the operating status of the electrophoresis production line, it is usually necessary to improve the analysis accuracy between parameters through interpolation processing.

[0041] Specifically, it is necessary to first collect the electrophoresis production operation monitoring data sequence. The specific process is as follows:

[0042] In the electrophoresis production line, current sensors, voltage sensors, temperature sensors and liquid level sensors are used to collect monitoring data in four dimensions, namely, temperature data, current data, voltage data and liquid level data at each moment in turn; the temperature data, current data, voltage data and liquid level data at all moments are used as the electrophoresis production operation monitoring data sequence.

[0043] Among them, the electrophoresis production operation monitoring data series includes monitoring data in several dimensions.

[0044] It should be noted that dividing the electrophoresis production operation monitoring data sequence of each dimension into several monitoring data intervals can ensure that within each monitoring data interval, there is no need to consider external influences. Under ideal conditions, the changes in various parameters in the electrophoresis production operation monitoring data are periodic.

[0045] The electrophoresis production operation monitoring data sequence is divided into several monitoring data intervals; each monitoring data interval starts at the first moment when the electrophoresis product is ready for electrophoresis, and the first moment when the next electrophoresis product is ready for electrophoresis is the end point of the monitoring data interval and the starting point of the next monitoring data interval.

[0046] So far, several monitoring data intervals of the electrophoresis production operation monitoring data sequence are obtained through the above method.

[0047] Step S002: Obtain the fluctuation sensitivity of the monitoring data of each dimension according to the fluctuation of the monitoring data of each dimension in different monitoring data intervals and the number of extreme value points.

[0048] It should be noted that in order to obtain the credibility of the monitoring data of each dimension in the electrophoresis production operation monitoring data sequence during the electrophoresis production process, that is, whether the monitoring data of each dimension has actual anomalies or noise interference; and for the monitoring data of each dimension, except for normal data, the abnormal data needs to be retained, and the noise data should constrain its interference with the fitting parameters; but the two are relatively similar in data performance, so only based on conventional data fluctuations or amplitudes that are too large or too small, it is not possible to fully determine the abnormal data and noise data in the monitoring data of each dimension, and the degree of fluctuation of the monitoring data of each dimension is not the same; for example, the sensitivity of liquid level changes or temperature and current parameters to fluctuations is different, so the standard deviation of the monitoring data of each dimension in the monitoring data interval can be calculated to characterize the degree of fluctuation of the monitoring data of each dimension in the monitoring data interval; further, the number of missing abnormal data in the monitoring data interval and the size of the monitoring data interval are obtained.

[0049] Preferably, in some implementations of the embodiments of the present invention, according to the fluctuation of the monitoring data of each dimension in different monitoring data intervals and the number of extreme value points, the calculation method for obtaining the fluctuation sensitivity of the monitoring data of each dimension is:

[0050] For Monitoring data of the first dimension and monitoring data intervals, except for the The monitoring data of other dimensions other than the monitoring data of this dimension are in the The fluctuations in the monitoring data interval are obtained. The monitoring data of the dimensions are The fluctuation characteristic factors within the monitoring data interval;

[0051] The first Within the monitoring data interval The number of extreme points of the monitoring data in the dimension All the monitoring data in the interval The ratio of the total number of monitoring data in the dimension is recorded as The monitoring data of the dimensions are The proportion of extreme values ​​in the monitoring data interval; All the monitoring data in the interval The standard deviation of the monitoring data in the dimension The monitoring data of the dimensions are The proportion of extreme values ​​in the monitoring data interval and the The monitoring data of the dimensions are The product of the three fluctuation characteristic factors within the monitoring data interval is taken as the The monitoring data of the dimensions are The fluctuation sensitivity factor within the monitoring data interval; The mean of the fluctuation sensitivity factor of the monitoring data of the dimension in all monitoring data intervals is taken as the The fluctuation sensitivity of monitoring data in different dimensions.

[0052] The specific formula is:

[0053]

[0054] In the formula, Indicates The fluctuation sensitivity of monitoring data in different dimensions; Indicates the total number of all monitoring data intervals; Indicates All the monitoring data in the interval The standard deviation of the monitoring data in the dimensions; Indicates The monitoring data of the dimensions are The proportion of extreme values ​​in a monitoring data interval; Indicates The monitoring data of the dimensions are The fluctuation characteristic factors within a monitoring data interval.

[0055] Preferably, in some implementations of the embodiments of the present invention, The monitoring data of the dimensions are The method for obtaining the fluctuation characteristic factor within a monitoring data interval includes:

[0056] Will remove The monitoring data of other dimensions other than the monitoring data of the first dimension are recorded as the monitoring data of the target dimension; all the monitoring data of the target dimension are recorded in the first dimension. The cumulative sum of the standard deviations within the monitoring data interval is recorded as the first cumulative sum; the difference between 1 and the normalized value of the first cumulative sum is recorded as the second cumulative sum. The monitoring data of the dimensions are The fluctuation characteristic factors within a monitoring data interval.

[0057] The specific formula is:

[0058]

[0059] In the formula, Indicates The monitoring data of the dimensions are The fluctuation characteristic factors within the monitoring data interval; Indicates the number of types of monitoring data in all dimensions; Indicates All the monitoring data in the interval The standard deviation of the monitoring data of the target dimension; Represents the normalization function.

[0060] It should be noted that by calculating the The monitoring data of other dimensions other than the monitoring data of this dimension are in the The cumulative sum of the standard deviations within the monitoring data interval. The higher the cumulative sum, the Compared with the monitoring data of other dimensions, the monitoring data of this dimension is more prone to fluctuations. The fluctuation sensitivity of the monitoring data in this dimension is relatively lower; however, the corresponding anomalies of the increase in the overall trend and the fluctuation of continuous changes up and down are different. The attention paid to such data anomalies as continuous changes up and down is relatively higher. Therefore, different weights are given to each monitoring data interval based on the proportion of extreme points.

[0061] So far, the fluctuation sensitivity of the monitoring data in each dimension is obtained through the above method.

[0062] Step S003: According to the differences in the monitoring data of each dimension in different monitoring data intervals, obtain the degree of fluctuation anomaly of the monitoring data of each dimension in each monitoring data interval; according to the differences in the degree of fluctuation anomaly of the monitoring data of different dimensions in the monitoring data interval, obtain the isolated value of fluctuation anomaly of the monitoring data of each dimension in each monitoring data interval; according to the isolated value of fluctuation anomaly, the degree of fluctuation anomaly and the fluctuation sensitivity, obtain the reference factor of each monitoring data of each dimension in each monitoring data interval.

[0063] It should be noted that the distinction between abnormal data and noise data requires analysis based on the linear relationship between the monitoring data of different dimensions in the electrophoresis production line. When an actual abnormality occurs in the monitoring data of a certain dimension, it will usually interfere with the monitoring data of other dimensions. For example, a sudden change in current and voltage will often correspond to a change in the liquid temperature monitoring data in the electrophoresis pool. However, only the monitoring data affected by the noise data is inaccurate, which is completely different from the abnormal data mentioned above. Therefore, based on this logic, combined with the fluctuation sensitivity of the monitoring data of each dimension, the monitoring data of different dimensions are distinguished from fluctuation anomalies, and based on the correlation between the monitoring data of different dimensions, the isolated manifestation of fluctuation anomalies is obtained, and then the abnormal data and noise data are distinguished.

[0064] 1. Obtain the degree of fluctuation anomaly of the monitoring data of each dimension within each monitoring data interval.

[0065] It should be noted that, since the operation of the corresponding electrophoresis production line is exactly the same when each monitoring data interval is divided, under ideal circumstances, the changes in the monitoring data of different dimensions within each monitoring data interval are generally not much different. The only difference is the slight fluctuations or abnormalities and noise data interference generated therein. Therefore, it is first necessary to analyze the degree of abnormality of each monitoring data interval based on the differences between the monitoring data of each dimension itself in different monitoring data intervals. In each monitoring data interval, when the actual monitoring data of different dimensions and the fitting curves of the monitoring data of different dimensions are significantly different, it is possible that there is an abnormal fluctuation in the monitoring data of this dimension within the current monitoring data interval.

[0066] Preferably, in some implementations of the embodiments of the present invention, a method for calculating the degree of abnormal fluctuation of the monitoring data of each dimension in each monitoring data interval is obtained according to the difference of the monitoring data of each dimension in different monitoring data intervals:

[0067] Get the The monitoring data of the dimensions are The fitting curve within the monitoring data interval;

[0068] The first The monitoring data of the dimensions are The monitoring data of the monitoring data point in the fitting curve within the monitoring data interval is recorded as The monitoring data of the dimensions are The fitting data within the monitoring data interval; The monitoring data of the dimensions are monitoring data interval and The difference of fitting data between monitoring data intervals is obtained. The monitoring data of the dimensions are monitoring data interval and The data differences between the monitoring data intervals;

[0069] The first The monitoring data of the dimensions are The mean of the data differences between the first monitoring data interval and all other monitoring data intervals is taken as the The monitoring data of the dimensions are The degree of abnormal fluctuation within a monitoring data interval.

[0070] The specific formula is:

[0071]

[0072] In the formula, Indicates The monitoring data of the dimensions are The degree of abnormal fluctuation within a monitoring data interval; Indicates the total number of all monitoring data intervals; Indicates The monitoring data of the dimensions are monitoring data interval and The data differences between the monitoring data intervals.

[0073] Preferably, in some implementations of the embodiments of the present invention, The monitoring data of the dimensions are The method for obtaining the fitting curve within a monitoring data interval includes:

[0074] For Monitoring data of the first dimension and monitoring data interval, with time as the horizontal axis and the The monitoring data of the first dimension is the vertical axis, All the monitoring data in the interval The monitoring data of the first dimension is input into the two-dimensional coordinate system, and several monitoring data points are obtained. All monitoring data points are fitted by the least squares method to form the first The monitoring data of the dimensions are The fitting curve within the monitoring data interval.

[0075] Preferably, in some implementations of the embodiments of the present invention, The monitoring data of the dimensions are monitoring data interval and Methods for obtaining data differences between monitoring data intervals include:

[0076] No. The monitoring data of the dimensions are monitoring data interval and The monitoring data interval The absolute value of the difference between the fitted data is recorded as The first absolute value of the difference of the fitted data; The monitoring data of the dimensions are In the monitoring data interval, The fitted data and The absolute value of the difference between the first and second monitoring data is recorded as the second absolute value of the difference; The monitoring data of the dimensions are In the monitoring data interval, The fitted data and The absolute value of the difference between the first and second monitoring data is recorded as the third absolute value of the difference; the normalized value of the sum of the second absolute value of the difference and the third absolute value of the difference is recorded as the first The first difference of the fitted data; The product of the absolute value of the first difference of the fitted data and the first difference is recorded as The first product of the fitted data; The monitoring data of the dimensions are monitoring data interval and The reciprocal of the cumulative sum of the first products of all the fitting data between the monitoring data intervals is taken as the first The monitoring data of the dimensions are monitoring data interval and The data differences between the monitoring data intervals.

[0077] The specific formula is:

[0078]

[0079] In the formula, Indicates The monitoring data of the dimensions are monitoring data interval and The data differences between the monitoring data intervals; Indicates The monitoring data of the dimensions are The total number of all fitted data in the monitoring data interval; Indicates The monitoring data of the dimensions are monitoring data interval and The monitoring data interval The absolute value of the difference between the fitted data; Indicated in The monitoring data of the dimensions are In the monitoring data interval, The fitted data and The absolute value of the difference between the monitoring data; Indicated in The monitoring data of the dimensions are In the monitoring data interval, The fitted data and The absolute value of the difference between the monitoring data; Represents the normalization function.

[0080] It should be noted that the abnormal information displayed under the same degree of fluctuation is weaker; correspondingly, during the electrophoresis process, the electrophoresis operation status within the current monitoring data interval is extremely similar to multiple historical electrophoresis behaviors. Therefore, relative to the current electrophoresis behavior, the possibility of abnormal conditions existing within it is relatively low.

[0081] At this point, the degree of fluctuation anomaly of the monitoring data of each dimension within each monitoring data interval is obtained.

[0082] 2. Obtain the abnormal isolated values ​​of fluctuations in each monitoring data interval for each dimension of monitoring data.

[0083] It should be noted that the greater the difference in the degree of fluctuation anomaly of monitoring data of different dimensions within the monitoring data interval, the more likely it is that the abnormal performance of the monitoring data of each dimension in the same monitoring data interval is too different from the monitoring data of other dimensions. Therefore, the fluctuation anomaly of the overall monitoring data in the monitoring data interval may be closer to noise interference rather than an actual abnormal situation.

[0084] Preferably, in some implementations of the embodiments of the present invention, a calculation method for obtaining an isolated value of fluctuation anomaly of monitoring data of each dimension in each monitoring data interval is performed according to the difference in the degree of fluctuation anomaly of monitoring data of different dimensions in the monitoring data interval:

[0085] Will remove The monitoring data of other dimensions other than the monitoring data of the first dimension are recorded as the monitoring data of the target dimension; for the monitoring data of any target dimension, according to the The difference between the monitoring data of the first dimension and the monitoring data of the target dimension in the monitoring data interval is used to obtain the abnormal fluctuation degree of the first dimension. The monitoring data of the first dimension and the monitoring data of the target dimension are in the Abnormal fluctuation difference value within the monitoring data interval;

[0086] The first The monitoring data of this dimension is combined with the monitoring data of all other target dimensions in the The average of the fluctuation anomaly difference values ​​within the monitoring data interval is taken as the The monitoring data of the dimensions are Abnormal isolated values ​​of fluctuations within a monitoring data interval.

[0087] The specific formula is:

[0088]

[0089] In the formula, Indicates The monitoring data of the dimensions are Abnormal isolated values ​​of fluctuations within the monitoring data interval; Indicates the number of types of monitoring data in all dimensions; Indicates The monitoring data of the dimensions are The degree of abnormal fluctuation within a monitoring data interval; Indicates The monitoring data of the dimensions are The degree of abnormal fluctuation within a monitoring data interval; Indicates taking the absolute value.

[0090] Preferably, in some implementations of the embodiments of the present invention, The monitoring data of the first dimension and the monitoring data of the target dimension are in the The method for obtaining the fluctuation abnormal difference value within a monitoring data interval includes:

[0091] The first The monitoring data of the dimensions are The degree of abnormal fluctuation in the monitoring data interval is related to the monitoring data of the target dimension in the The absolute value of the difference in the degree of abnormal fluctuation within the monitoring data interval is recorded as The monitoring data of the first dimension and the monitoring data of the target dimension are in the The abnormal fluctuation difference value within the monitoring data interval.

[0092] At this point, the abnormal fluctuation isolated values ​​of the monitoring data of each dimension in each monitoring data interval are obtained.

[0093] 3. Obtain the reference factor of each monitoring data in each monitoring data interval for each dimension of monitoring data.

[0094] Preferably, in some implementations of the embodiments of the present invention, according to the fluctuation anomaly isolated value, the fluctuation anomaly degree and the fluctuation sensitivity, the calculation method for obtaining the reference factor of each monitoring data in each monitoring data interval of each dimension of monitoring data is:

[0095] In the The monitoring data of the dimensions are In the monitoring data interval, The fitted data and The absolute value of the difference between the monitoring data is recorded as The fitting difference of the monitoring data; The absolute value of the difference in the fluctuation sensitivity of the monitoring data of the first dimension is recorded as the first target difference; the first target difference, the The monitoring data of the dimensions are The fluctuation anomaly isolated value within the monitoring data interval, The product of the three fitting differences of the monitoring data is recorded as the target product; the inverse proportional normalized value of the target product is taken as the The monitoring data of the dimensions are Within the monitoring data interval A reference factor for monitoring data.

[0096] The specific formula is:

[0097]

[0098] In the formula, Indicates The monitoring data of the dimensions are Within the monitoring data interval Reference factors for monitoring data; Indicated in The monitoring data of the dimensions are In the monitoring data interval, The fitted data and The absolute value of the difference between the monitoring data; Indicates The monitoring data of the dimensions are Abnormal isolated values ​​of fluctuations within the monitoring data interval; Indicates The fluctuation sensitivity of monitoring data in different dimensions; represents an exponential function with a natural constant as the base, and the embodiment adopts Model to present inverse proportional relationship and normalization, As the input of the model, the implementer can choose the inverse proportional function and the normalization function according to the actual situation.

[0099] So far, the reference factor of each monitoring data in each monitoring data interval of each dimension of monitoring data is obtained through the above method.

[0100] Step S004: obtaining an optimized error function model according to the reference factor; performing spline interpolation on the electrophoresis production operation monitoring data sequence through the optimized error function model to obtain interpolated electrophoresis production line operation monitoring data.

[0101] It should be noted that when spline interpolation is performed, it will be iterated through continuous interpolation fitting and adjusted through the error function. The adjustment method usually uses the gradient descent method for adaptive adjustment, but this method usually gives priority to adjusting parameters based on data points with larger errors. Therefore, it is necessary to optimize the error function model at this time to reduce the performance of the data points with more serious noise interference mentioned above in the error function.

[0102] Specifically, the reference factor of each monitoring data in each monitoring data interval of each dimension is input into the gradient descent algorithm to obtain the optimized error function model; the electrophoresis production operation monitoring data sequence is spline interpolated through the optimized error function model to obtain the interpolated electrophoresis production line operation monitoring data.

[0103] It should be noted that the gradient descent algorithm and spline interpolation are existing technologies, and will not be described in detail in this embodiment.

[0104] See also Figure 2 , which shows a characteristic relationship flow chart for production operation monitoring of an electrophoresis production line.

[0105] Through the above steps, a method for monitoring the production operation of an electrophoresis production line is completed.

[0106] The present invention also proposes a production operation monitoring system for an electrophoresis production line, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, steps S001 to S004 of a method for monitoring the production operation of an electrophoresis production line are implemented.

[0107] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring the production operation of an electrophoresis production line, characterized in that: The method comprises the following steps: Obtaining an electrophoresis production operation monitoring data sequence; dividing the electrophoresis production operation monitoring data sequence into a plurality of monitoring data intervals; each monitoring data interval includes monitoring data of a plurality of dimensions; each dimension of monitoring data includes a plurality of monitoring data; According to the fluctuation of the monitoring data of each dimension in different monitoring data intervals and the number of extreme points, the fluctuation sensitivity of the monitoring data of each dimension is obtained; According to the difference of monitoring data of each dimension in different monitoring data intervals, the degree of abnormal fluctuation of monitoring data of each dimension in each monitoring data interval is obtained; according to the difference of abnormal fluctuation degree of monitoring data of different dimensions in the monitoring data interval, the abnormal fluctuation isolated value of monitoring data of each dimension in each monitoring data interval is obtained; according to the abnormal fluctuation isolated value, abnormal fluctuation degree and fluctuation sensitivity, the reference factor of each monitoring data of each dimension in each monitoring data interval is obtained; An optimized error function model is obtained according to the reference factor; spline interpolation is performed on the electrophoresis production operation monitoring data sequence through the optimized error function model to obtain the electrophoresis production line operation monitoring data after interpolation; The specific method for obtaining the fluctuation sensitivity of the monitoring data of each dimension according to the fluctuation situation and the number of extreme value points of the monitoring data of each dimension in different monitoring data intervals is as follows: For Monitoring data of the first dimension and monitoring data intervals, except for the The monitoring data of other dimensions other than the monitoring data of this dimension are in the The fluctuations in the monitoring data interval are obtained. The monitoring data of the dimensions are The fluctuation characteristic factors within the monitoring data interval; The first Within the monitoring data interval The number of extreme points of the monitoring data in the dimension All the monitoring data in the interval The ratio of the total number of monitoring data in the dimension is recorded as The monitoring data of the dimensions are The proportion of extreme values ​​in the monitoring data interval; All the monitoring data in the interval The standard deviation of the monitoring data in the dimension The monitoring data of the dimensions are The proportion of extreme values ​​in the monitoring data interval and the The monitoring data of the dimensions are The product of the three fluctuation characteristic factors within the monitoring data interval is taken as the The monitoring data of the dimensions are The fluctuation sensitivity factor within the monitoring data interval; The mean of the fluctuation sensitivity factor of the monitoring data of the dimension in all monitoring data intervals is taken as the The fluctuation sensitivity of monitoring data in different dimensions; The specific method of obtaining the abnormal fluctuation degree of the monitoring data of each dimension in each monitoring data interval according to the difference of the monitoring data of each dimension in different monitoring data intervals includes: Get the The monitoring data of the dimensions are The fitting curve within the monitoring data interval; The first The monitoring data of the dimensions are The monitoring data of the monitoring data point in the fitting curve within the monitoring data interval is recorded as The monitoring data of the dimensions are The fitting data within the monitoring data interval; The monitoring data of the dimensions are monitoring data interval and The difference of fitting data between monitoring data intervals is obtained. The monitoring data of the dimensions are monitoring data interval and The data differences between the monitoring data intervals; The first The monitoring data of the dimensions are The mean of the data differences between the first monitoring data interval and all other monitoring data intervals is taken as the The monitoring data of the dimensions are The degree of abnormal fluctuation within a monitoring data interval; The specific method of obtaining the abnormal fluctuation isolated value of the monitoring data of each dimension in each monitoring data interval according to the difference in the abnormal fluctuation degree of the monitoring data of different dimensions in the monitoring data interval is as follows: Will remove The monitoring data of other dimensions other than the monitoring data of the first dimension are recorded as the monitoring data of the target dimension; for the monitoring data of any target dimension, according to the The difference between the monitoring data of the first dimension and the monitoring data of the target dimension in the monitoring data interval is used to obtain the abnormal fluctuation degree of the first dimension. The monitoring data of the first dimension and the monitoring data of the target dimension are in the Abnormal fluctuation difference value within the monitoring data interval; The first The monitoring data of this dimension is combined with the monitoring data of all other target dimensions in the The average of the fluctuation anomaly difference values ​​within the monitoring data interval is taken as the The monitoring data of the dimensions are Abnormal isolated values ​​of fluctuations within the monitoring data interval; The specific method of obtaining the reference factor of each monitoring data in each monitoring data interval of each dimension according to the fluctuation anomaly isolated value, fluctuation anomaly degree and fluctuation sensitivity includes: In the The monitoring data of the dimensions are In the monitoring data interval, The fitted data and The absolute value of the difference between the monitoring data is recorded as The fitting difference of the monitoring data; The absolute value of the difference in the fluctuation sensitivity of the monitoring data of the first dimension is recorded as the first target difference; the first target difference, the The monitoring data of the dimensions are The fluctuation anomaly isolated value within the monitoring data interval, The product of the three fitting differences of the monitoring data is recorded as the target product; the inverse proportional normalized value of the target product is taken as the The monitoring data of the dimensions are Within the monitoring data interval A reference factor for monitoring data.

2. The method for monitoring the production operation of an electrophoresis production line according to claim 1, characterized in that: The said The monitoring data of the dimensions are The fluctuation characteristic factors within the monitoring data interval include the following specific methods: Will remove The monitoring data of other dimensions other than the monitoring data of the first dimension are recorded as the monitoring data of the target dimension; all the monitoring data of the target dimension are recorded in the first dimension. The cumulative sum of the standard deviations within the monitoring data interval is recorded as the first cumulative sum; the difference between 1 and the normalized value of the first cumulative sum is recorded as the second cumulative sum. The monitoring data of the dimensions are The fluctuation characteristic factors within a monitoring data interval.

3. The method for monitoring the production operation of an electrophoresis production line according to claim 1, characterized in that: The acquisition The monitoring data of the dimensions are The fitting curve within the monitoring data interval includes the following specific methods: For Monitoring data of the first dimension and monitoring data interval, with time as the horizontal axis and the The monitoring data of the first dimension is the vertical axis, All the monitoring data in the interval The monitoring data of the first dimension is input into the two-dimensional coordinate system, and several monitoring data points are obtained. All monitoring data points are fitted by the least squares method to form the first The monitoring data of the dimensions are The fitting curve within the monitoring data interval.

4. The method for monitoring the production operation of an electrophoresis production line according to claim 1, characterized in that: The acquisition The monitoring data of the dimensions are monitoring data interval and The data differences between the monitoring data intervals include the following specific methods: No. The monitoring data of the dimensions are monitoring data interval and The monitoring data interval The absolute value of the difference between the fitted data is recorded as The first absolute value of the difference of the fitted data; The monitoring data of the dimensions are In the monitoring data interval, The fitted data and The absolute value of the difference between the first and second monitoring data is recorded as the second absolute value of the difference; The monitoring data of the dimensions are In the monitoring data interval, The fitted data and The absolute value of the difference between the first and second monitoring data is recorded as the third absolute value of the difference; the normalized value of the sum of the second absolute value of the difference and the third absolute value of the difference is recorded as the first The first difference of the fitted data; The product of the absolute value of the first difference of the fitted data and the first difference is recorded as The first product of the fitted data; The monitoring data of the dimensions are monitoring data interval and The reciprocal of the cumulative sum of the first products of all the fitting data between the monitoring data intervals is taken as the first The monitoring data of the dimensions are monitoring data interval and The data differences between the monitoring data intervals.

5. The method for monitoring the production operation of an electrophoresis production line according to claim 1, characterized in that: The acquisition The monitoring data of the first dimension and the monitoring data of the target dimension are in the The abnormal fluctuation difference value within the monitoring data interval includes the following specific methods: The first The monitoring data of the dimensions are The degree of abnormal fluctuation in the monitoring data interval is related to the monitoring data of the target dimension in the The absolute value of the difference in the degree of abnormal fluctuation within the monitoring data interval is recorded as The monitoring data of the first dimension and the monitoring data of the target dimension are in the The abnormal fluctuation difference value within the monitoring data interval.

6. A production operation monitoring system for an electrophoresis production line, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the electrophoresis production line production operation monitoring method as described in any one of claims 1-5 are implemented.