CN114968990A - Design method of diagnosis model for influencing factors of experimental data - Google Patents
Design method of diagnosis model for influencing factors of experimental data Download PDFInfo
- Publication number
- CN114968990A CN114968990A CN202210381572.3A CN202210381572A CN114968990A CN 114968990 A CN114968990 A CN 114968990A CN 202210381572 A CN202210381572 A CN 202210381572A CN 114968990 A CN114968990 A CN 114968990A
- Authority
- CN
- China
- Prior art keywords
- experimental data
- data
- experimental
- initial
- target
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000013461 design Methods 0.000 title claims abstract description 11
- 238000003745 diagnosis Methods 0.000 title abstract description 10
- 238000001514 detection method Methods 0.000 claims description 35
- 238000002474 experimental method Methods 0.000 claims description 32
- 238000004140 cleaning Methods 0.000 claims description 22
- 238000012216 screening Methods 0.000 claims description 12
- 230000000007 visual effect Effects 0.000 claims description 10
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 230000011218 segmentation Effects 0.000 claims description 8
- 239000013598 vector Substances 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000005856 abnormality Effects 0.000 claims description 4
- 238000000429 assembly Methods 0.000 claims description 4
- 230000000712 assembly Effects 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000009286 beneficial effect Effects 0.000 description 6
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 229910052760 oxygen Inorganic materials 0.000 description 5
- 239000001301 oxygen Substances 0.000 description 5
- PFUVRDFDKPNGAV-UHFFFAOYSA-N sodium peroxide Chemical compound [Na+].[Na+].[O-][O-] PFUVRDFDKPNGAV-UHFFFAOYSA-N 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 239000000843 powder Substances 0.000 description 3
- 239000007787 solid Substances 0.000 description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 1
- 238000013101 initial test Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
- G06F16/285—Clustering or classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/33—Querying
- G06F16/3331—Query processing
- G06F16/334—Query execution
- G06F16/3344—Query execution using natural language analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/279—Recognition of textual entities
- G06F40/289—Phrasal analysis, e.g. finite state techniques or chunking
Abstract
The invention discloses a design method of a diagnosis model of experimental data influence factors, which comprises the following steps: acquiring influence factors of experimental data; setting a plurality of corresponding experimental variables according to the influence factors to obtain initial experimental data; adjusting the experimental variable corresponding to one influence factor each time, and keeping the experimental variables corresponding to other influence factors unchanged to obtain a plurality of adjustment experimental data; calculating through a polynomial fitting function of matlab according to the initial experimental data and the plurality of adjusted experimental data to obtain a fitting function; and designing a diagnostic model according to the fitting function. The influence of each influencing factor on the experimental data is found out, the experimental process data is provided, a diagnosis model is established, the experimental result is pre-judged, the experimental efficiency and the effectiveness of the data are improved, meanwhile, the influence of each factor on the experimental data is solved, the influence of each factor is reduced by modifying the process quantity, the time can be saved, and the universality is high.
Description
Technical Field
The invention relates to the technical field of diagnosis, in particular to a design method of a diagnosis model for influencing factors of experimental data.
Background
In the experimental process, experimental result data is often influenced by the environmental temperature and humidity, airflow and the running state of experimental instruments or equipment, but the influence of the factors on the experimental result is often ignored, or correct data is found through repeated experiments, and the experimental method is time-consuming and labor-consuming. The present application is therefore directed to a method for designing a diagnostic model for influencing factors in experimental data.
Disclosure of Invention
The present invention is directed to solving, at least to some extent, one of the technical problems in the art described above. Therefore, the invention aims to provide a method for designing a diagnosis model of the influence factors of the experimental data, find out the influence of each influence factor on the experimental data, provide experimental process data, establish a diagnosis model, and pre-judge an experimental result so as to improve the experimental efficiency and the data validity, solve the influence of each factor on the experimental data, and reduce the influence of each factor by modifying the process quantity, thereby saving time and having strong universality.
In order to achieve the above object, an embodiment of the present invention provides a method for designing a diagnostic model for influencing factors of experimental data, including:
acquiring influence factors of experimental data;
setting a plurality of corresponding experimental variables according to the influence factors to obtain initial experimental data;
adjusting the experimental variable corresponding to one influence factor each time, and keeping the experimental variables corresponding to other influence factors unchanged to obtain a plurality of adjustment experimental data;
calculating through a polynomial fitting function of matlab according to the initial experimental data and the plurality of adjusted experimental data to obtain a fitting function;
and designing a diagnostic model according to the fitting function.
According to some embodiments of the invention, the influencing factors include temperature and humidity, airflow, personnel, and experimental procedures.
According to some embodiments of the invention, designing a diagnostic model from the fitting function comprises:
carrying out visual interface layout design;
compiling a callback function according to the fitting function, setting a parameter association relation, and performing function programming;
debugging the calculation result based on the programming result to obtain a debugging result;
and when the debugging result is that the debugging is successful, verifying the application through actual engineering.
According to some embodiments of the invention, a visual interface layout design is performed, comprising:
acquiring an experiment scene image, and analyzing the experiment scene image to obtain a target object and experiment layout information;
generating a corresponding target component according to the target object;
selecting a target layout style from preset layout styles according to the experimental layout information;
combining the target assemblies in the target layout style to obtain a first interface;
obtaining description information associated with the target component;
performing word segmentation processing on the description information, and obtaining a plurality of word vectors according to word segmentation results;
clustering the word vectors to obtain a plurality of cluster sets, and extracting central words in the cluster sets;
and filling the central word to the corresponding edge area of the target assembly to obtain a second interface.
According to some embodiments of the present invention, before the calculating by the polynomial fitting function of matlab according to the initial experimental data and the plurality of adjusted experimental data, the method further comprises: and screening the initial experimental data and the plurality of adjusted experimental data.
According to some embodiments of the invention, the data screening of the initial experimental data and the adjusted experimental data comprises:
determining a clustering center for the initial experimental data based on a kmeans clustering algorithm, and classifying the initial experimental data according to the clustering center to obtain a plurality of sub-initial experimental data;
determining a clustering center for the adjusting experimental data based on a kmeans clustering algorithm, and classifying the adjusting experimental data according to the clustering center to obtain a plurality of sub-adjusting experimental data;
the sub initial experimental data and the sub adjustment experimental data of the same type are used as a data set;
randomly selecting an element in a data set as a detection element, and respectively determining the association relationship between the detection element and other elements except the detection element in the data set;
acquiring experiment information of the detection elements, inquiring a preset data table according to the experiment information to obtain a target incidence relation, calculating the matching degree of the incidence relation and the target incidence relation, and judging whether the matching degree is smaller than the preset matching degree;
when the matching degree is determined to be smaller than a preset matching degree, representing that the detection element is abnormal; removing the data group in the detection element to obtain a new data group;
re-selecting an element in the new data set, and repeatedly detecting until the whole data set is traversed;
performing the same steps for a plurality of types of data sets;
screening out initial experimental data and/or adjusted experimental data of detection elements which do not comprise the abnormality as effective data;
and setting corresponding experimental variables to be acquired again, wherein the initial experimental data and/or the adjusted experimental data of the abnormal detection elements are used as invalid data.
According to some embodiments of the present invention, before the calculating by the polynomial fitting function of matlab according to the initial experimental data and the plurality of adjusted experimental data, the method further comprises: and carrying out data cleaning on the initial experimental data and the plurality of adjusted experimental data.
According to some embodiments of the invention, data cleaning the initial experimental data and the adjusted experimental data comprises:
acquiring the initial experimental data and adjusting the attribute information of the experimental data;
inquiring a preset attribute information-cleaning rule data table according to the attribute information to obtain a target cleaning rule;
and performing data cleaning on the initial experimental data and the plurality of adjusted experimental data according to the target cleaning rule.
According to some embodiments of the invention, the attribute information comprises at least one of a data dimension characteristic, a data clustering characteristic, and a data timing characteristic.
According to some embodiments of the invention, further comprising: during the course of the experiment, several experimental variables were monitored.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of a method of designing a diagnostic model for influencing factors in experimental data according to one embodiment of the present invention;
FIG. 2 is a flow diagram of designing a diagnostic model based on the fitting function according to one embodiment of the present invention;
FIG. 3 is a flow diagram of performing visualization interface layout design according to one embodiment of the present invention;
FIG. 4 is a diagram of an experimental layout according to one embodiment of the present invention;
FIG. 5 is a flow chart for designing a diagnostic model according to yet another embodiment of the present invention.
Reference numerals:
A. an air supply outlet;
B. an air outlet;
C. an air supply outlet;
D. an air outlet;
E. temperature and humidity sensor.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
As shown in fig. 1, an embodiment of the present invention provides a method for designing a diagnostic model of influence factors of experimental data, including steps S1-S5:
s1, acquiring influence factors of experimental data;
s2, setting a plurality of corresponding experimental variables according to the influence factors to obtain initial experimental data;
s3, adjusting the experimental variables corresponding to one influence factor each time, and keeping the experimental variables corresponding to other influence factors unchanged to obtain a plurality of adjustment experimental data;
s4, calculating through a polynomial fitting function of matlab according to the initial experimental data and the plurality of adjusted experimental data to obtain a fitting function;
and S5, designing a diagnostic model according to the fitting function.
The working principle of the technical scheme is as follows: acquiring influence factors of experimental data; setting a plurality of corresponding experimental variables according to the influence factors to obtain initial experimental data; adjusting the experimental variable corresponding to one influence factor each time, and keeping the experimental variables corresponding to other influence factors unchanged to obtain a plurality of adjustment experimental data; calculating through a polynomial fitting function of matlab according to the initial experimental data and the plurality of adjusted experimental data to obtain a fitting function; and designing a diagnostic model according to the fitting function.
The beneficial effects of the above technical scheme are as follows: the influence of each influencing factor on the experimental data is found out, the experimental process data is provided, a diagnosis model is established, the experimental result is pre-judged, the experimental efficiency and the effectiveness of the data are improved, meanwhile, the influence of each factor on the experimental data is solved, the influence of each factor is reduced by modifying the process quantity, the time can be saved, and the universality is high.
Specifically, as shown in fig. 4, in one embodiment, the following experimental variables are controlled: temperature and humidity, air flow, personnel and flow, and the experiment sodium peroxide reacts with water to extract the oxygen production.
Scene one: in the experimental layout structure chart, air is supplied from an opening A, and the air volume is 1000m 3 H, air exhaust at the port B and 1200m air volume 3 And H, the temperature and humidity E is 23 ℃, 60%, the experimenter F and the experimental process is H, and the experimental data are recorded.
Scene two: in the experimental layout structure chart, air is supplied from an opening A, and the air volume is 1000m 3 H, air exhaust at the port B and 1200m air volume 3 And H, the temperature and humidity E is 23 ℃, 60%, the experimenter G is H, and the experimental data are recorded.
Scene three: in the experimental layout structure chart, air is supplied from an opening A, and the air volume is 1000m 3 H, air exhaust at the port B and 1200m air volume 3 And/h, the temperature and humidity E is 23 ℃, 60%, the experimenter F and the experimental process I, and the experimental data are recorded.
Scene four: experimental clothIn the structure diagram, the air is supplied from the port A, and the air quantity is 1000m 3 H, air exhaust at the port B, and the air quantity is 1200m 3 The temperature and humidity E is 10 ℃, the temperature and the humidity E are 80%, the laboratory technician F, the experimental process is H, and the experimental data are recorded.
Scene five: in the experimental layout structure chart, air is supplied from an opening C, and the air volume is 1000m 3 Exhaust air at the D port in the per hour mode, and the air volume is 1200m 3 And H, the temperature and humidity E is 23 ℃, 60%, the experimenter F and the experimental process is H, and the experimental data are recorded.
Wherein, H, the operation flow: taking 3g of sodium peroxide solid powder, placing the sodium peroxide solid powder in water, and collecting oxygen by a drainage method; I. the operation process comprises the following steps: 3gg sodium peroxide solid powder is taken and placed in a beaker, 50ml of water is added dropwise, and oxygen is collected by using a drainage method.
Fitting a function by means of a polynomial of matlab;
y-a 0+ a1r1(x) + … + amrm (x), r1(x) r2(x) is m functions, a0, a1 bits of fitting parameters, the above experimental variation factors are substituted into formula x, and the experimental results are substituted into Y, to derive the fitting function.
And (3) deducing a model through simulation, designing a required oxygen amount, calculating each factor parameter, and verifying whether the optimally designed oxygen amount is obtained through experiments.
According to some embodiments of the invention, the influencing factors comprise temperature and humidity, airflow, personnel, and experimental procedures.
As shown in FIG. 2, according to some embodiments of the present invention, designing a diagnostic model based on the fitting function includes steps S51-S54:
s51, carrying out visual interface layout design;
s52, compiling a callback function according to the fitting function, setting a parameter association relation, and programming a function;
s53, debugging the calculation result based on the programming result to obtain a debugging result;
and S54, verifying the application through actual engineering when the debugging result is that the debugging is successful.
The working principle of the technical scheme is as follows: carrying out visual interface layout design; compiling a callback function according to the fitting function, setting a parameter association relation, and performing function programming; debugging the calculation result based on the programming result to obtain a debugging result; and when the debugging result is that the debugging is successful, verifying the application through actual engineering.
The beneficial effects of the above technical scheme are that: and an accurate diagnosis model is convenient to obtain.
FIG. 5 is a schematic diagram of a diagnostic model designed for another embodiment.
As shown in fig. 3, according to some embodiments of the present invention, a visual interface layout design is performed, including S511-S518:
s511, acquiring an experiment scene image, and analyzing the experiment scene image to obtain a target object and experiment layout information;
s512, generating a corresponding target component according to the target object;
s513, selecting a target layout style from preset layout styles according to the experimental layout information;
s514, combining the target assemblies in the target layout style to obtain a first interface;
s515, acquiring description information associated with the target component;
s516, performing word segmentation processing on the description information, and obtaining a plurality of word vectors according to word segmentation results;
s517, clustering the word vectors to obtain a plurality of cluster sets, and extracting central words in the cluster sets;
s518, filling the central word into the corresponding edge area of the target component to obtain a second interface.
The working principle of the technical scheme is as follows: acquiring an experiment scene image, and analyzing the experiment scene image to obtain a target object and experiment layout information; the target object includes an air supply outlet, an air exhaust outlet, and the like. The experimental layout information includes a positional relationship between the respective target objects. Generating a corresponding target component according to the target object; selecting a target layout style from preset layout styles according to the experimental layout information; combining the target assemblies in the target layout style to obtain a first interface; obtaining description information associated with the target component; performing word segmentation processing on the description information, and obtaining a plurality of word vectors according to word segmentation results; clustering the word vectors to obtain a plurality of cluster sets, and extracting central words in the cluster sets; and filling the central word to the corresponding edge area of the target assembly to obtain a second interface. The first interface includes image information; the second interface comprises image information and character information.
The beneficial effects of the above technical scheme are that: based on the combination of the target components in the target layout style, the development cost and threshold of the visual interface are reduced conveniently, and the development efficiency of the visual interface is improved. And filling the central word into the corresponding edge area of the target component to obtain a second interface, ensuring the integrity of the data of the second interface, facilitating the user to clearly know the information corresponding to each component, ensuring the user to clearly and accurately know the information at a glance and ensuring the accuracy of the established visual interface.
According to some embodiments of the present invention, before the calculating by the polynomial fitting function of matlab according to the initial experimental data and the plurality of adjusted experimental data, the method further comprises: and screening the initial experimental data and the plurality of adjusted experimental data.
According to some embodiments of the invention, the data screening of the initial experimental data and the adjusted experimental data comprises:
determining a clustering center for the initial experimental data based on a kmeans clustering algorithm, and classifying the initial experimental data according to the clustering center to obtain a plurality of sub-initial experimental data;
determining a clustering center for the adjusting experimental data based on a kmeans clustering algorithm, and classifying the adjusting experimental data according to the clustering center to obtain a plurality of sub-adjusting experimental data;
the sub initial experimental data and the sub adjustment experimental data of the same type are used as a data set;
randomly selecting an element in a data set as a detection element, and respectively determining the association relationship between the detection element and other elements except the detection element in the data set;
acquiring experiment information of the detection elements, inquiring a preset data table according to the experiment information to obtain a target incidence relation, calculating the matching degree of the incidence relation and the target incidence relation, and judging whether the matching degree is smaller than the preset matching degree;
when the matching degree is determined to be smaller than a preset matching degree, representing that the detection element is abnormal; removing the data group in the detection element to obtain a new data group;
re-selecting an element in the new data set, and repeatedly detecting until the whole data set is traversed;
performing the same steps for a plurality of types of data sets;
screening out initial experimental data and/or adjusted experimental data of detection elements which do not comprise the abnormality as effective data;
and setting corresponding experimental variables to be acquired again, wherein the initial experimental data and/or the adjusted experimental data of the abnormal detection elements are used as invalid data.
The working principle of the technical scheme is as follows: determining a clustering center for the initial experimental data based on a kmeans clustering algorithm, and classifying the initial experimental data according to the clustering center to obtain a plurality of sub-initial experimental data; determining a clustering center for the adjusted experimental data based on a kmeans clustering algorithm, and classifying the adjusted experimental data according to the clustering center to obtain a plurality of sub-adjusted experimental data; using the same type of sub-initial experimental data and sub-adjustment experimental data as a data set; randomly selecting an element in a data set as a detection element, and respectively determining the association relationship between the detection element and other elements except the detection element in the data set; the detection elements are sub-initial experimental data or sub-adjusted experimental data. And acquiring experimental information of the detection elements, wherein the experimental information is the initial experimental data or an experimental scene corresponding to the adjusted experimental data. Inquiring a preset data table according to the experimental information to obtain a target incidence relation, calculating the matching degree of the incidence relation and the target incidence relation, and judging whether the matching degree is smaller than a preset matching degree; the preset data table is an experimental information-target relation table. When the matching degree is determined to be smaller than a preset matching degree, representing that the detection element is abnormal; removing the data group in the detection element to obtain a new data group; re-selecting an element in the new data set, and repeatedly detecting until the whole data set is traversed; performing the same steps for a plurality of types of data sets; screening out initial experimental data and/or adjusted experimental data of detection elements which do not comprise the abnormality as effective data; and setting corresponding experimental variables to be acquired again, wherein the initial experimental data and/or the adjusted experimental data of the abnormal detection elements are used as invalid data.
The beneficial effects of the above technical scheme are that: and eliminating the data group in the detection element to obtain a new data group for detection, so that the calculation amount is reduced, and the screening efficiency is improved conveniently. The same type of the test data is used as a data set, abnormal data are detected more accurately through group comparison, screening accuracy is improved, and accuracy of the obtained initial test data and the obtained adjustment test data is guaranteed.
According to some embodiments of the present invention, before the calculating by the polynomial fitting function of matlab according to the initial experimental data and the plurality of adjusted experimental data, the method further comprises: and carrying out data cleaning on the initial experimental data and the plurality of adjusted experimental data.
According to some embodiments of the invention, data cleaning the initial experimental data and the adjusted experimental data comprises:
acquiring the initial experimental data and adjusting the attribute information of the experimental data;
inquiring a preset attribute information-cleaning rule data table according to the attribute information to obtain a target cleaning rule;
and performing data cleaning on the initial experimental data and the plurality of adjusted experimental data according to the target cleaning rule.
The working principle of the technical scheme is as follows: acquiring the initial experimental data and adjusting the attribute information of the experimental data; inquiring a preset attribute information-cleaning rule data table according to the attribute information to obtain a target cleaning rule; and performing data cleaning on the initial experimental data and the plurality of adjusted experimental data according to the target cleaning rule.
The beneficial effects of the above technical scheme are that: the influence of noise data is eliminated, and the accuracy of the initial experimental data and the accuracy of a plurality of adjustment experimental data are guaranteed.
According to some embodiments of the invention, the attribute information comprises at least one of a data dimension characteristic, a data clustering characteristic, and a data timing characteristic.
According to some embodiments of the invention, further comprising: during the course of the experiment, several experimental variables were monitored.
The beneficial effects of the above technical scheme are that: the method is convenient for detecting the experiment variable in the experiment scene, and avoids the experiment variable from changing to cause the inaccuracy of the obtained experiment data.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (10)
1. A method for designing a diagnostic model for influencing factors of experimental data, comprising:
acquiring influence factors of experimental data;
setting a plurality of corresponding experimental variables according to the influence factors to obtain initial experimental data;
adjusting an experimental variable corresponding to one influence factor each time, and keeping the experimental variables corresponding to other influence factors unchanged to obtain a plurality of adjustment experimental data;
calculating through a polynomial fitting function of matlab according to the initial experimental data and the plurality of adjusted experimental data to obtain a fitting function;
and designing a diagnostic model according to the fitting function.
2. The method of claim 1, wherein the influencing factors include temperature and humidity, airflow, personnel, and experimental procedures.
3. The method of claim 1, wherein designing a diagnostic model based on the fitting function comprises:
carrying out visual interface layout design;
compiling a callback function according to the fitting function, setting a parameter association relation, and performing function programming;
debugging the calculation result based on the programming result to obtain a debugging result;
and when the debugging result is that the debugging is successful, verifying the application through actual engineering.
4. The method of claim 3, wherein the designing of the visual interface layout comprises:
acquiring an experiment scene image, and analyzing the experiment scene image to obtain a target object and experiment layout information;
generating a corresponding target component according to the target object;
selecting a target layout style from preset layout styles according to the experimental layout information;
combining the target assemblies in the target layout style to obtain a first interface;
obtaining description information associated with the target component;
performing word segmentation processing on the description information, and obtaining a plurality of word vectors according to word segmentation results;
clustering the word vectors to obtain a plurality of cluster sets, and extracting central words in the cluster sets;
and filling the central word to the edge area of the corresponding target assembly to obtain a second interface.
5. The method of claim 1, wherein before calculating from the initial experimental data and the adjusted experimental data by means of a matlab polynomial fitting function, further comprising: and screening the initial experimental data and the plurality of adjusted experimental data.
6. The method of claim 5, wherein the initial experimental data and the adjusted experimental data are subjected to data screening, comprising:
determining a clustering center for the initial experimental data based on a kmeans clustering algorithm, and classifying the initial experimental data according to the clustering center to obtain a plurality of sub-initial experimental data;
determining a clustering center for the adjusting experimental data based on a kmeans clustering algorithm, and classifying the adjusting experimental data according to the clustering center to obtain a plurality of sub-adjusting experimental data;
the sub initial experimental data and the sub adjustment experimental data of the same type are used as a data set;
randomly selecting an element in a data set as a detection element, and respectively determining the association relationship between the detection element and other elements except the detection element in the data set;
acquiring experiment information of the detection elements, inquiring a preset data table according to the experiment information to obtain a target incidence relation, calculating the matching degree of the incidence relation and the target incidence relation, and judging whether the matching degree is smaller than the preset matching degree;
when the matching degree is determined to be smaller than a preset matching degree, representing that the detection element is abnormal; removing the data group in the detection element to obtain a new data group;
re-selecting an element in the new data set, and repeatedly detecting until the whole data set is traversed;
performing the same steps for a plurality of types of data sets;
screening out initial experimental data and/or adjusted experimental data of detection elements which do not comprise the abnormality as effective data;
and setting corresponding experimental variables to be acquired again, wherein the initial experimental data and/or the adjusted experimental data of the abnormal detection elements are used as invalid data.
7. The method of claim 1, wherein before calculating from the initial experimental data and the adjusted experimental data by means of a matlab polynomial fitting function, further comprising: and carrying out data cleaning on the initial experimental data and the plurality of adjusted experimental data.
8. The method of claim 1, wherein the data cleaning of the initial experimental data and the adjusted experimental data comprises:
acquiring the initial experimental data and the attribute information of the adjusted experimental data;
inquiring a preset attribute information-cleaning rule data table according to the attribute information to obtain a target cleaning rule;
and performing data cleaning on the initial experimental data and the plurality of adjusted experimental data according to the target cleaning rule.
9. The method of claim 8, wherein the attribute information comprises at least one of data dimension characteristics, data clustering characteristics, and data timing characteristics.
10. The method of designing a diagnostic model for influencing factors on experimental data of claim 1, further comprising: during the course of the experiment, several experimental variables were monitored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210381572.3A CN114968990A (en) | 2022-04-12 | 2022-04-12 | Design method of diagnosis model for influencing factors of experimental data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210381572.3A CN114968990A (en) | 2022-04-12 | 2022-04-12 | Design method of diagnosis model for influencing factors of experimental data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114968990A true CN114968990A (en) | 2022-08-30 |
Family
ID=82977407
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210381572.3A Pending CN114968990A (en) | 2022-04-12 | 2022-04-12 | Design method of diagnosis model for influencing factors of experimental data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114968990A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649579A (en) * | 2016-11-17 | 2017-05-10 | 苏州航天系统工程有限公司 | Time-series data cleaning method for pipe net modeling |
| CN106779069A (en) * | 2016-12-08 | 2017-05-31 | 国家电网公司 | A kind of abnormal electricity consumption detection method based on neutral net |
| CN107633349A (en) * | 2017-08-28 | 2018-01-26 | 中国西电电气股份有限公司 | Fault impact factor quantitative analysis method based on high-voltage switch gear |
| CN111143777A (en) * | 2019-12-27 | 2020-05-12 | 新奥数能科技有限公司 | Data processing method and device, intelligent terminal and storage medium |
-
2022
- 2022-04-12 CN CN202210381572.3A patent/CN114968990A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106649579A (en) * | 2016-11-17 | 2017-05-10 | 苏州航天系统工程有限公司 | Time-series data cleaning method for pipe net modeling |
| CN106779069A (en) * | 2016-12-08 | 2017-05-31 | 国家电网公司 | A kind of abnormal electricity consumption detection method based on neutral net |
| CN107633349A (en) * | 2017-08-28 | 2018-01-26 | 中国西电电气股份有限公司 | Fault impact factor quantitative analysis method based on high-voltage switch gear |
| CN111143777A (en) * | 2019-12-27 | 2020-05-12 | 新奥数能科技有限公司 | Data processing method and device, intelligent terminal and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 肖溱鸽: "《基于数据分析的数控加工工艺参数能效优化方法研究》", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》, 31 March 2017 (2017-03-31), pages 4 - 5 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111352408B (en) | Multi-working-condition process industrial process fault detection method based on evidence K nearest neighbor | |
| CN110083803B (en) | Method and system for detecting water taking abnormality based on time sequence ARIMA model | |
| JP6737277B2 (en) | Manufacturing process analysis device, manufacturing process analysis method, and manufacturing process analysis program | |
| CN117056688A (en) | New material production data management system and method based on data analysis | |
| CN113255255A (en) | Integrated circuit thermal vacuum test system | |
| CN116955045B (en) | Remote JTAG multiplexing test method and system | |
| CN114968990A (en) | Design method of diagnosis model for influencing factors of experimental data | |
| CN116777861B (en) | Marking quality detection method and system for laser engraving machine | |
| CN112330063B (en) | Equipment fault prediction method, equipment fault prediction device and computer readable storage medium | |
| CN113505862A (en) | Hybrid fault detection method and device | |
| CN115905990A (en) | Transformer oil temperature abnormity monitoring method based on density aggregation algorithm | |
| TWI399660B (en) | A method of detecting variance by regression model | |
| CN113642209B (en) | Structure implantation fault response data acquisition and evaluation method based on digital twinning | |
| CN114155914A (en) | Detection and correction system based on metagenome splicing error | |
| CN113920547A (en) | Glove detection method and system based on neural network | |
| CN114037010A (en) | Method and device for identifying abnormal electric quantity data | |
| JP2020166407A (en) | Model generation device, abnormality occurrence prediction device, abnormality occurrence prediction model generation method and abnormality occurrence prediction method | |
| CN117370755A (en) | Chip detection method and chip detection system | |
| CN116638768B (en) | Intelligent powder cleaning method and system for 3D printing workpiece | |
| CN114237647B (en) | Single-chip microcomputer programming control system and single-chip microcomputer programming control method | |
| CN113782173B (en) | Intelligent parameter information acquisition system for predicting state of clinical emergency equipment | |
| CN116629707B (en) | FDC traceability analysis method based on distributed parallel computing and storage medium | |
| CN115983684B (en) | Copper pipe production defect management method and system for refrigeration | |
| EP4280007A1 (en) | Appparatus, method and program for monitoring a target device | |
| CN117315408A (en) | Fault criterion model construction method and system based on AI target detection model |
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 |