CN113063861B - Oxygen nitrogen hydrogen analyzer measurement system based on classification algorithm - Google Patents
Oxygen nitrogen hydrogen analyzer measurement system based on classification algorithm Download PDFInfo
- Publication number
- CN113063861B CN113063861B CN202110276485.7A CN202110276485A CN113063861B CN 113063861 B CN113063861 B CN 113063861B CN 202110276485 A CN202110276485 A CN 202110276485A CN 113063861 B CN113063861 B CN 113063861B
- Authority
- CN
- China
- Prior art keywords
- standard
- data
- oxygen
- nitrogen
- module
- 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.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
- G01N30/86—Signal analysis
- G01N30/8665—Signal analysis for calibrating the measuring apparatus
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
- G01N30/02—Column chromatography
- G01N30/86—Signal analysis
- G01N30/8696—Details of Software
-
- 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
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Probability & Statistics with Applications (AREA)
- Pathology (AREA)
- Evolutionary Biology (AREA)
- Mathematical Physics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Computational Mathematics (AREA)
- Databases & Information Systems (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Pure & Applied Mathematics (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Operations Research (AREA)
- Algebra (AREA)
- Fuzzy Systems (AREA)
- Computational Linguistics (AREA)
- Investigating And Analyzing Materials By Characteristic Methods (AREA)
- Sampling And Sample Adjustment (AREA)
Abstract
The invention discloses an oxygen-nitrogen-hydrogen analyzer measuring system based on a classification algorithm, and relates to the technical field of metal characteristic analysis; the invention is provided with a standard analysis module, and the standard analysis module is used for analyzing standard measurement data; the standard analysis module performs instrument correction on the oxygen nitrogen hydrogen analyzer through a standard position, obtains standard measurement data corresponding to a standard substance, and obtains a standing point sequence and an extreme point sequence according to the standard measurement data, so that a data basis is provided for establishing a classification model, and the analysis precision of the oxygen nitrogen hydrogen analyzer is ensured; the invention is provided with a sample analysis module, which acquires the oxygen, nitrogen and hydrogen content in the metal to be detected according to a classification model; the sample analysis module acquires the oxygen, nitrogen and hydrogen content in the sample to be detected by combining the classification model according to sample measurement data of the sample to be detected, generates an analysis report, and is favorable for improving the measurement precision of the oxygen, nitrogen and hydrogen content and enabling an analysis result to be more visual by combining the artificial intelligence model.
Description
Technical Field
The invention belongs to the field of metal characteristic analysis, relates to a classification technology, and particularly relates to an oxygen-nitrogen-hydrogen analyzer measurement system based on a classification algorithm.
Background
The contents of oxygen, nitrogen and hydrogen directly affect the characteristics of metals (such as steel, titanium and copper), so the contents of oxygen, nitrogen and hydrogen are accurately measured in the quality control process; usually carry out the detection and analysis through the oxygen nitrogen hydrogen analyzer to the oxygen nitrogen hydrogen content in the metal, the oxygen nitrogen hydrogen analyzer among the prior art includes the furnace end, and the furnace end includes the furnace body, and there is the protective chamber furnace body inside, is provided with the graphite crucible that is used for holding the sample in the furnace intracavity, and fixed carrier gas that is used for to the inside export gas of furnace chamber that is provided with on the furnace body purifies filter tube and upper electrode, lower motor, and the furnace end still includes the pneumatic elevating system who is used for detecting the inside temperature detector of furnace chamber and control electrode removal.
The invention patent with publication number CN105223135A provides a carrier gas purifying filter tube for an oxygen-nitrogen-hydrogen analyzer, a furnace head and the oxygen-nitrogen-hydrogen analyzer; the device comprises a filter pipe, a filter material and a linear displacement detection device, wherein the filter material is arranged in the filter pipe and used for filtering gas, and the linear displacement detection device is used for detecting the displacement of the filter material.
In the scheme, the linear displacement detection device is used for accurately displaying the amount of the graphite powder adsorbed by the filtering material in the filtering pipe, and the filtering material is replaced in time, so that the accuracy of an analysis result is improved, and the analysis cost is also reduced; however, the above solution improves the accuracy of the analysis result by improving the internal structure of the oxyhydrogen-nitrogen analyzer, which results in a more complex structure of the oxyhydrogen-nitrogen analyzer and a limited improvement of the accuracy of the analysis result; therefore, the above solution still needs further improvement.
Disclosure of Invention
In order to solve the problems existing in the scheme, the invention provides an oxygen-nitrogen-hydrogen analyzer measuring system based on a classification algorithm.
The purpose of the invention can be realized by the following technical scheme: an oxygen nitrogen hydrogen analyzer measuring system based on a classification algorithm comprises an oxygen nitrogen hydrogen analyzer body and a control system; the control system comprises a processor, a data acquisition module, a standard analysis module, a sample analysis module, an execution control module, a background management module and a data storage module;
the data acquisition module is used for acquiring working data of the oxygen-nitrogen-hydrogen analyzer, wherein the working data comprises operation data, standard measurement data and sample measurement data; the data acquisition module respectively transmits the standard measurement data to the standard analysis module, the sample analysis module and the data storage module, and simultaneously transmits the operation data to the processor; the data acquisition module respectively transmits the sample measurement data to the sample analysis module and the data storage module;
the sample analysis module obtains the content of oxygen, nitrogen and hydrogen in the metal to be detected according to the classification model, and the method comprises the following steps:
after the sample analysis module receives the sample measurement data, the classification model is obtained through the data storage module; the sample measurement data comprises sample instrument parameters and sample detection data, the sample instrument parameters comprise a temperature value, a voltage value, degassing power, degassing time, a current value and the concentration of protective gas in the sample analysis process, and the sample detection data comprises the weight of a sample and the dosage of a fluxing agent in the sample analysis process;
obtaining a classification model;
inputting the measured data of the sample into a classification model after data normalization processing to obtain an output result, wherein the output result is the oxygen nitrogen hydrogen content corresponding to the sample;
generating and sending a sample analysis report to a data storage module; the sample analysis report includes sample measurement data and an output.
Preferably, the execution control module is used for realizing intelligent control on the oxygen-nitrogen-hydrogen analyzer according to the instrument early warning signal; the instrument early warning signals comprise temperature abnormal signals, current abnormal signals, concentration abnormal signals and operation risk signals.
Preferably, the background management module is used for monitoring the operation data of the oxygen, nitrogen and hydrogen analyzer in real time; and the background management module is also used for scheduling workers to maintain the oxygen-nitrogen-hydrogen analyzer.
Preferably, the specific obtaining step of the classification model includes:
acquiring training data through a data storage module; the training data comprises instrument setting data, a stationing point sequence, an extreme value point sequence and standard measurement data;
after data normalization, dividing training data into a training set and a test set according to a set proportion; the set ratio comprises 4:1 and 2: 1;
constructing a fusion model; the fusion model is constructed by combining three intelligent models, namely an SVM (support vector machine), a BP (back propagation) neural network and an RBF (radial basis function) neural network, with a fusion mode, wherein the fusion mode comprises a linear weighted fusion method, a cross fusion method, a waterfall fusion method, a feature fusion method and a prediction fusion method;
training and testing the fusion model through a training set and a testing set; when the training precision of the fusion model reaches the target precision, judging that the training of the fusion model is finished, and marking the trained fusion model as a classification model;
and respectively sending the classification models to the sample analysis module and the data storage module through the processor.
Preferably, the standard analysis module is configured to analyze standard measurement data, and includes:
selecting a standard substance; the standard substance is a metal substance with fixed and known oxygen, nitrogen and hydrogen contents;
performing instrument calibration on the oxygen nitrogen hydrogen analyzer through a standard substance; analyzing a standard substance according to the operation steps and acquiring standard measurement data, wherein the standard measurement data comprises instrument setting parameters and standard measurement data; the instrument setting parameters comprise a temperature value, a voltage value, degassing power, degassing time, a current value and the concentration of protective gas in the standard substance analysis process; the standard measurement data comprises the weight of a standard substance in the standard substance analysis process, the dosage of a fluxing agent and the contents of oxygen, nitrogen and hydrogen acquired by a thermal conductivity detector;
establishing a standard change curve by taking time as an independent variable and the weight of a standard substance, the dosage of a fluxing agent, the concentration of protective gas, a voltage value, a temperature value and a current value; the standard change curve comprises a substance weight change curve, a fluxing agent dosage change curve, a protective gas concentration change curve, a voltage change curve, a temperature change curve and a current change curve;
acquiring the number of stagnation points and the number of extreme points of a curve in a standard change curve, and establishing a stagnation point sequence and an extreme point sequence according to the standard change curve sequence;
and respectively sending the instrument setting data, the stagnation point sequence, the extreme point sequence and the standard measurement data to the sample analysis module and the data storage module.
Preferably, the processor analyzes the malfunction of the oxygen nitrogen hydrogen analyzer according to the operation data, and includes:
after the processor receives the operation data, establishing an operation curve; the operation data comprises a temperature value, a current value and the concentration of protective gas, the protective gas comprises helium and argon, the temperature value comprises a melting temperature and a chromatographic column temperature, and the current value is obtained through a direct current digital milliammeter;
respectively establishing operation curves by a polynomial fitting method by taking time as an independent variable and operation data as a dependent variable; the operation curves comprise a temperature curve, a current curve and a protective gas concentration curve;
when the temperature value is not within the temperature threshold range, generating and sending a temperature abnormal signal to the background management module and the execution control module; when the current value is not in the current threshold range, generating and sending a current abnormal signal to the background management module and the execution control module; when the concentration of the protective gas is not in the concentration threshold range, generating and sending a concentration abnormal signal to the background management module and the execution control module;
acquiring a derivative function of the operation curve, and bringing time into the derivative function to acquire a derivative value;
marking the absolute value of any derivative value as a first derivative value; obtaining a derivative value of the first derivative value corresponding to a moment before time, and marking the derivative value as a second derivative value after taking an absolute value; obtaining a derivative value at a time after the first derivative value corresponds to time, and marking the derivative value as a third derivative value after taking an absolute value;
obtaining an average of the first, second, and third derivative values and labeling as derivative average DPZ;
when the derivative average value DPZ meets YDPZ-mu is not less than DPZ and not more than YDPZ + mu, judging that the operation data is normal, and generating and sending a normal operation signal to the background management module; otherwise, judging that hidden danger exists in the operation data, and generating and sending an operation risk signal to the background management module and the execution control module; YDPZ is a derivative average threshold value, YDPZ is obtained through simulation of a large amount of data, mu is a proportionality coefficient, and mu is a real number larger than 0;
sending the average value of the derivative and the sending record of the fault signal to a data storage module for storage through a processor; the fault signals comprise temperature abnormal signals, current abnormal signals, concentration abnormal signals, normal operation signals and abnormal operation signals.
Preferably, the processor is respectively in communication connection with the data acquisition module, the standard analysis module, the sample analysis module, the execution control module, the background management module and the data storage module; the background management module is respectively in communication connection with the data storage module and the execution control module, the standard analysis module is respectively in communication connection with the data acquisition module and the sample analysis module, and the sample analysis module is in communication connection with the execution control module; the data acquisition module is connected with the oxygen, nitrogen and hydrogen analyzer in a communication and/or electrical mode; the oxygen nitrogen hydrogen analyzer comprises a pulse unit and a chromatographic unit, wherein the pulse unit comprises an upper electrode, a lower electrode, a pulse transformer, cooling water, a water pressure switch, a pulse heating cable, a time controller, furnace end starting, heating starting, an alternating current voltmeter, an alternating current ammeter, a manual/automatic change-over switch and a pressure regulating knob, the chromatographic unit comprises a chromatographic column furnace, a chromatographic column, a thermal conductivity detector, a pool balance, a sample injector, a direct current milliammeter, stopping, pressure regulating, analyzing, flushing, bridge current, carrier gas regulating, flushing regulating, a carrier gas pressure gauge, a system pressure gauge, column temperature control, a carrier gas flowmeter, a flushing gas flowmeter, carrier gas voltage stabilizing, carrier gas regulating, flushing gas regulating, a carrier gas purifier and a flushing purifier.
Compared with the prior art, the invention has the beneficial effects that:
1. the invention is provided with a standard analysis module, and the standard analysis module is used for analyzing standard measurement data; the standard analysis module performs instrument correction on the oxygen nitrogen hydrogen analyzer through a standard position, obtains standard measurement data corresponding to a standard substance, and obtains a standing point sequence and an extreme point sequence according to the standard measurement data, so that a data basis is provided for establishing a classification model, and the analysis precision of the oxygen nitrogen hydrogen analyzer is ensured;
2. the invention is provided with a sample analysis module, which acquires the oxygen, nitrogen and hydrogen content in the metal to be detected according to a classification model; the sample analysis module acquires the oxygen nitrogen hydrogen content in the sample to be detected by combining the classification model according to the sample measurement data of the sample to be detected, generates an analysis report, and is beneficial to improving the measurement precision of the oxygen nitrogen hydrogen content and enabling the analysis result to be more visual by combining the artificial intelligence model.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a schematic diagram of the control system of the present invention.
Detailed Description
The technical solutions of the present invention will be described below clearly and completely in conjunction with the embodiments, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, an oxygen nitrogen hydrogen analyzer measuring system based on a classification algorithm includes an oxygen nitrogen hydrogen analyzer body and a control system; the control system comprises a processor, a data acquisition module, a standard analysis module, a sample analysis module, an execution control module, a background management module and a data storage module;
the data acquisition module is used for acquiring working data of the oxygen-nitrogen-hydrogen analyzer, wherein the working data comprises operation data, standard measurement data and sample measurement data; the data acquisition module respectively transmits the standard measurement data to the standard analysis module, the sample analysis module and the data storage module, and simultaneously transmits the operation data to the processor; the data acquisition module respectively transmits the sample measurement data to the sample analysis module and the data storage module;
the sample analysis module obtains the oxygen nitrogen hydrogen content in the metal to be detected according to the classification model, and the method comprises the following steps:
after the sample analysis module receives the sample measurement data, the classification model is obtained through the data storage module; the sample measurement data comprises sample instrument parameters and sample detection data, the sample instrument parameters comprise a temperature value, a voltage value, degassing power, degassing time, a current value and the concentration of protective gas in the sample analysis process, and the sample detection data comprises the weight of a sample and the dosage of a fluxing agent in the sample analysis process;
obtaining a classification model;
inputting the measured data of the sample into a classification model after data normalization processing to obtain an output result, wherein the output result is the oxygen nitrogen hydrogen content corresponding to the sample;
generating and sending a sample analysis report to a data storage module; the sample analysis report includes the sample measurement data and the output results.
Further, the execution control module is used for realizing intelligent control on the oxygen-nitrogen-hydrogen analyzer according to the instrument early warning signal; the instrument early warning signals comprise temperature abnormal signals, current abnormal signals, concentration abnormal signals and operation risk signals.
Further, the background management module is used for monitoring the operation data of the oxygen, nitrogen and hydrogen analyzer in real time; the background management module is also used for scheduling workers to maintain the oxygen-nitrogen-hydrogen analyzer.
Further, the specific obtaining step of the classification model comprises:
acquiring training data through a data storage module; the training data comprises instrument setting data, a stationing point sequence, an extreme value point sequence and standard measurement data;
after data normalization, dividing training data into a training set and a test set according to a set proportion;
constructing a fusion model; the fusion model is constructed by combining three intelligent models, namely an SVM (support vector machine), a BP (back propagation) neural network and an RBF (radial basis function) neural network, with a fusion mode, wherein the fusion mode comprises a linear weighted fusion method, a cross fusion method, a waterfall fusion method, a feature fusion method and a prediction fusion method;
training and testing the fusion model through a training set and a testing set; when the training precision of the fusion model reaches the target precision, judging that the training of the fusion model is finished, and marking the trained fusion model as a classification model;
and respectively sending the classification models to the sample analysis module and the data storage module through the processor.
Further, the standard analysis module is used for analyzing standard measurement data, and comprises:
selecting a standard substance; the standard substance is a metal substance with fixed and known oxygen, nitrogen and hydrogen contents;
performing instrument calibration on an oxygen-nitrogen-hydrogen analyzer through a standard substance; analyzing the standard substance according to the operation steps and acquiring standard measurement data, wherein the standard measurement data comprises instrument setting parameters and standard measurement data; the instrument setting parameters comprise a temperature value, a voltage value, degassing power, degassing time, a current value and the concentration of protective gas in the standard substance analysis process; the standard measurement data comprises the weight of the standard substance in the standard substance analysis process, the dosage of the fluxing agent and the contents of oxygen, nitrogen and hydrogen obtained by the thermal conductivity detector;
establishing a standard change curve by taking time as an independent variable and the weight of a standard substance, the dosage of a fluxing agent, the concentration of protective gas, a voltage value, a temperature value and a current value; the standard change curve comprises a substance weight change curve, a flux dosage change curve, a protective gas concentration change curve, a voltage change curve, a temperature change curve and a current change curve;
acquiring the number of stagnation points and the number of extreme points of a curve in a standard change curve, and establishing a stagnation point sequence and an extreme point sequence according to the standard change curve sequence;
and respectively sending the instrument setting data, the stagnation point sequence, the extreme point sequence and the standard measurement data to the sample analysis module and the data storage module.
Further, the processor analyzes the fault of the oxygen nitrogen hydrogen analyzer according to the operation data, and comprises the following steps:
after the processor receives the operation data, establishing an operation curve; the operation data comprises a temperature value, a current value and the concentration of protective gas, the protective gas comprises helium and argon, the temperature value comprises a melting temperature and a chromatographic column temperature, and the current value is obtained through a direct current digital milliammeter;
respectively establishing operation curves by a polynomial fitting method by taking time as an independent variable and operation data as a dependent variable; the operation curves comprise a temperature curve, a current curve and a protective gas concentration curve;
when the temperature value is not within the temperature threshold range, generating and sending a temperature abnormal signal to the background management module and the execution control module; when the current value is not in the current threshold range, generating and sending a current abnormal signal to the background management module and the execution control module; when the concentration of the protective gas is not in the concentration threshold range, generating and sending a concentration abnormal signal to the background management module and the execution control module;
acquiring a derivative function of the operation curve, and bringing time into the derivative function to acquire a derivative value;
marking the absolute value of any derivative value as a first derivative value; obtaining a derivative value of the first derivative value corresponding to a moment before time, and marking the derivative value as a second derivative value after taking an absolute value; obtaining a derivative value at a time after the first derivative value corresponds to time, and marking the derivative value as a third derivative value after taking an absolute value;
obtaining an average of the first, second, and third derivative values and labeling as derivative average DPZ;
when the derivative average value DPZ meets YDPZ-mu is not less than DPZ and not more than YDPZ + mu, judging that the operation data is normal, and generating and sending a normal operation signal to the background management module; otherwise, judging that the running data has hidden danger, generating and sending a running risk signal to the background management module and the execution control module; YDPZ is a derivative average threshold value, YDPZ is obtained through simulation of a large amount of data, mu is a proportionality coefficient, and mu is a real number larger than 0;
sending the average value of the derivative and the sending record of the fault signal to a data storage module for storage through a processor; the fault signals comprise temperature abnormal signals, current abnormal signals, concentration abnormal signals, normal operation signals and abnormal operation signals.
Furthermore, the processor is respectively in communication connection with the data acquisition module, the standard analysis module, the sample analysis module, the execution control module, the background management module and the data storage module; the background management module is respectively in communication connection with the data storage module and the execution control module, the standard analysis module is respectively in communication connection with the data acquisition module and the sample analysis module, and the sample analysis module is in communication connection with the execution control module; the data acquisition module is connected with the oxygen, nitrogen and hydrogen analyzer in a communication and/or electrical mode; the oxygen nitrogen hydrogen analyzer comprises a pulse unit and a chromatographic unit, wherein the pulse unit comprises an upper electrode, a lower electrode, a pulse transformer, cooling water, a water pressure switch, a pulse heating cable, a time controller, a furnace end start, a heating start, an alternating current voltmeter, an alternating current ammeter, a manual/automatic change-over switch and a pressure regulating knob, and the chromatographic unit comprises a chromatographic column furnace, a chromatographic column, a thermal conductivity detector, a pool balance, a sample injector, a direct current milliammeter, a stop, a pressure regulating, analysis, flushing, bridge current, carrier gas regulation, flushing regulation, a carrier gas pressure gauge, a system pressure gauge, column temperature control, a carrier gas flowmeter, a flushing gas flowmeter, carrier gas pressure stabilization, carrier gas regulation, flushing gas regulation, a carrier gas purifier and a flushing purifier.
The above formulas are all calculated by removing dimensions and taking values thereof, the formula is one closest to the real situation obtained by collecting a large amount of data and performing software simulation, and the preset parameters in the formula are set by the technical personnel in the field according to the actual situation.
The working principle of the invention is as follows:
the data acquisition module is used for acquiring working data of the oxygen-nitrogen-hydrogen analyzer, wherein the working data comprises operation data, standard measurement data and sample measurement data; the data acquisition module respectively transmits the standard measurement data to the standard analysis module, the sample analysis module and the data storage module, and simultaneously transmits the operation data to the processor; the data acquisition module respectively transmits the sample measurement data to the sample analysis module and the data storage module;
after the processor receives the operation data, establishing an operation curve; respectively establishing operation curves by a polynomial fitting method by taking time as an independent variable and operating data as a dependent variable; when the temperature value is not within the temperature threshold range, generating and sending a temperature abnormal signal to the background management module and the execution control module; when the current value is not in the current threshold range, generating and sending a current abnormal signal to the background management module and the execution control module; when the concentration of the protective gas is not in the concentration threshold range, generating and sending a concentration abnormal signal to the background management module and the execution control module; acquiring a derivative function of the operation curve, and taking time into the derivative function to acquire a derivative value; taking any derivative value, taking an absolute value, and marking the absolute value as a first derivative value; obtaining a derivative value of the first derivative value corresponding to a moment before time, and marking the derivative value as a second derivative value after taking an absolute value; obtaining a derivative value at a time after the first derivative value corresponds to time, and marking the derivative value as a third derivative value after taking an absolute value; obtaining an average of the first, second, and third derivative values and labeling as derivative average DPZ; when the derivative average value DPZ meets the condition that YDPZ-mu is not less than DPZ and not more than YDPZ + mu, judging that the operation data is normal, and generating and sending a normal operation signal to the background management module; otherwise, judging that hidden danger exists in the operation data, and generating and sending an operation risk signal to the background management module and the execution control module; sending the average value of the derivative and the sending record of the fault signal to a data storage module for storage through a processor;
selecting a standard substance; performing instrument calibration on the oxygen nitrogen hydrogen analyzer through a standard substance; analyzing the standard substance according to the operation steps and acquiring standard measurement data; establishing a standard change curve by taking time as an independent variable and the weight of a standard substance, the dosage of a fluxing agent, the concentration of protective gas, a voltage value, a temperature value and a current value; the standard change curve comprises a substance weight change curve, a flux dosage change curve, a protective gas concentration change curve, a voltage change curve, a temperature change curve and a current change curve; acquiring the number of stagnation points and the number of extreme points of a curve in a standard change curve, and establishing a stagnation point sequence and an extreme point sequence according to the standard change curve sequence;
after the sample analysis module receives the sample measurement data, the classification model is obtained through the data storage module; obtaining a classification model; inputting the measured data of the sample into a classification model after data normalization processing to obtain an output result, wherein the output result is the oxygen nitrogen hydrogen content corresponding to the sample; generating and sending a sample analysis report to a data storage module; the sample analysis report comprises sample measurement data and an output result;
the background management module is used for monitoring the operation data of the oxygen-nitrogen-hydrogen analyzer in real time; and the background management module is also used for scheduling workers to maintain the oxygen-nitrogen-hydrogen analyzer.
In the description herein, references to the description of "one embodiment," "an example," "a specific example" or the like are intended to mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The foregoing is merely exemplary and illustrative of the present invention and various modifications, additions and substitutions may be made by those skilled in the art to the specific embodiments described without departing from the scope of the invention as defined in the following claims.
Claims (2)
1. An oxygen nitrogen hydrogen analyzer measuring system based on a classification algorithm is characterized by comprising an oxygen nitrogen hydrogen analyzer body and a control system; the control system comprises a processor, a data acquisition module, a standard analysis module, a sample analysis module, an execution control module, a background management module and a data storage module;
the data acquisition module is used for acquiring the working data of the oxygen, nitrogen and hydrogen analyzer; the data acquisition module respectively sends the working data to the standard analysis module, the sample analysis module, the processor and the data storage module; the standard analysis module is used for analyzing standard measurement data and instrument setting parameters to obtain a standing point sequence and an extreme point sequence;
the execution control module is used for realizing intelligent control on the oxygen, nitrogen and hydrogen analyzer according to the early warning signal of the analyzer;
the sample analysis module obtains the content of oxygen, nitrogen and hydrogen in the metal to be detected according to the classification model, and the method comprises the following steps:
after the sample analysis module receives sample measurement data, a classification model is obtained through the data storage module;
inputting the sample measurement data into a classification model after data normalization processing to obtain an output result, wherein the output result is the oxygen, nitrogen and hydrogen content corresponding to the sample;
generating and sending a sample analysis report to a data storage module; the sample analysis report comprises sample measurement data and an output result;
the specific obtaining step of the classification model comprises the following steps:
acquiring training data through a data storage module; the training data comprises instrument setting parameters, a standing point sequence, an extreme value point sequence and standard measurement data;
after data normalization, dividing training data into a training set and a test set according to a set proportion;
constructing a fusion model; the fusion model is constructed by combining three intelligent models, namely an SVM (support vector machine), a BP (back propagation) neural network and an RBF (radial basis function) neural network, with a fusion mode, wherein the fusion mode comprises a linear weighted fusion method, a cross fusion method, a waterfall fusion method, a feature fusion method and a prediction fusion method;
training and testing the fusion model through a training set and a testing set; when the training precision of the fusion model reaches the target precision, judging that the training of the fusion model is finished, and marking the trained fusion model as a classification model;
respectively sending the classification models to a sample analysis module and a data storage module through a processor;
the instrument setting parameters comprise a temperature value, a voltage value, degassing power, degassing time, a current value and the concentration of protective gas in the standard substance analysis process; the standard measurement data comprises the weight of a standard substance in the standard substance analysis process, the dosage of a fluxing agent and the contents of oxygen, nitrogen and hydrogen acquired by a thermal conductivity detector;
establishing a standard change curve by taking time as an independent variable and taking the weight of a standard substance, the using amount of a fluxing agent, the concentration of protective gas, a voltage value, a temperature value and a current value; the standard change curve comprises a substance weight change curve, a fluxing agent dosage change curve, a protective gas concentration change curve, a voltage change curve, a temperature change curve and a current change curve;
acquiring the number of stagnation points and the number of extreme points of a curve in a standard change curve, and establishing a stagnation point sequence and an extreme point sequence according to the standard change curve sequence;
and respectively sending the instrument setting parameters, the stagnation point sequence, the extreme point sequence and the standard measurement data to the sample analysis module and the data storage module.
2. The system of claim 1, wherein the processor analyzes the malfunction of the oxy-nitrogen hydrogen analyzer according to the operation data, and comprises:
respectively establishing operation curves by a polynomial fitting method by taking time as an independent variable and operation data as a dependent variable; the operation curve comprises a temperature curve, a current curve and a protective gas concentration curve;
judging the fault of the oxygen-nitrogen-hydrogen analyzer according to the operation curve, and generating and sending a fault signal to the platform management module and the execution control module when the oxygen-nitrogen-hydrogen analyzer fails; the fault signals comprise temperature abnormal signals, current abnormal signals, concentration abnormal signals, normal operation signals and abnormal operation signals.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110276485.7A CN113063861B (en) | 2021-03-15 | 2021-03-15 | Oxygen nitrogen hydrogen analyzer measurement system based on classification algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110276485.7A CN113063861B (en) | 2021-03-15 | 2021-03-15 | Oxygen nitrogen hydrogen analyzer measurement system based on classification algorithm |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113063861A CN113063861A (en) | 2021-07-02 |
| CN113063861B true CN113063861B (en) | 2022-06-24 |
Family
ID=76561499
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110276485.7A Active CN113063861B (en) | 2021-03-15 | 2021-03-15 | Oxygen nitrogen hydrogen analyzer measurement system based on classification algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113063861B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118091076A (en) * | 2024-04-28 | 2024-05-28 | 国合通用(青岛)测试评价有限公司 | Low sulfur survey monitoring system in nickel base superalloy |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5349541A (en) * | 1992-01-23 | 1994-09-20 | Electric Power Research Institute, Inc. | Method and apparatus utilizing neural networks to predict a specified signal value within a multi-element system |
| CN104764695A (en) * | 2015-03-26 | 2015-07-08 | 中国船舶重工集团公司第七二五研究所 | Method for determining oxygen/nitrogen/hydrogen content in interalloy for titanium alloys |
| CN105223135A (en) * | 2015-10-19 | 2016-01-06 | 洛阳鹏起实业有限公司 | The cleaned chimney filter of a kind of oxygen nitrogen hydrogen analyzer carrier gas, burner and oxygen nitrogen hydrogen analyzer |
| CN109828089A (en) * | 2019-02-13 | 2019-05-31 | 仲恺农业工程学院 | A kind of on-line prediction method of the water quality parameter cultured water based on DBN-BP |
| CN110023764A (en) * | 2016-12-02 | 2019-07-16 | 豪夫迈·罗氏有限公司 | For analyzing the malfunction prediction of the automatic analyzer of biological sample |
| CN110242865A (en) * | 2019-07-09 | 2019-09-17 | 北京讯腾智慧科技股份有限公司 | A kind of gas leakage detection determination method and system being easy to Continuous optimization |
-
2021
- 2021-03-15 CN CN202110276485.7A patent/CN113063861B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5349541A (en) * | 1992-01-23 | 1994-09-20 | Electric Power Research Institute, Inc. | Method and apparatus utilizing neural networks to predict a specified signal value within a multi-element system |
| CN104764695A (en) * | 2015-03-26 | 2015-07-08 | 中国船舶重工集团公司第七二五研究所 | Method for determining oxygen/nitrogen/hydrogen content in interalloy for titanium alloys |
| CN105223135A (en) * | 2015-10-19 | 2016-01-06 | 洛阳鹏起实业有限公司 | The cleaned chimney filter of a kind of oxygen nitrogen hydrogen analyzer carrier gas, burner and oxygen nitrogen hydrogen analyzer |
| CN110023764A (en) * | 2016-12-02 | 2019-07-16 | 豪夫迈·罗氏有限公司 | For analyzing the malfunction prediction of the automatic analyzer of biological sample |
| CN109828089A (en) * | 2019-02-13 | 2019-05-31 | 仲恺农业工程学院 | A kind of on-line prediction method of the water quality parameter cultured water based on DBN-BP |
| CN110242865A (en) * | 2019-07-09 | 2019-09-17 | 北京讯腾智慧科技股份有限公司 | A kind of gas leakage detection determination method and system being easy to Continuous optimization |
Non-Patent Citations (2)
| Title |
|---|
| 基于改进小波神经网络的极谱法多金属离子浓度检测信号的在线解析;王雅琳 等;《中南大学学报(自然科学版)》;20160126(第01期);全文 * |
| 提高钢中氧氮测定的准确性;孙娟 等;《中国检验检测》;20171126(第06期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113063861A (en) | 2021-07-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100480687C (en) | Real-time quality detection and alarm method for car body spot welding | |
| CN114184229A (en) | Switch cabinet operation environment monitoring system | |
| CN210487949U (en) | Oil-immersed high-voltage equipment oil-light-sound-spectrum on-line monitoring device | |
| CN105997072A (en) | Electrode contact state detecting method for electrical impedance detection based on measurement precision | |
| CN113063861B (en) | Oxygen nitrogen hydrogen analyzer measurement system based on classification algorithm | |
| US5448178A (en) | Transient technique to determine solution resistance for simple and accurate corrosion rate measurements | |
| CN110188309A (en) | Oil-immersed power transformer defect method for early warning based on Hidden Markov Model | |
| CN114369849B (en) | Method and device for monitoring health degree of electrolytic cell and electrolytic cell monitoring system | |
| CN117420452B (en) | Monitoring and early warning system for lithium battery energy storage | |
| CN106325258B (en) | Relay protection device state evaluation method based on online monitoring information | |
| CN109659587A (en) | Flow battery capacity attenuation control system and method | |
| CN117520951A (en) | Transformer health assessment method and system based on multiple characteristic quantities | |
| CN113505944A (en) | Power carbon emission prediction method based on carbon flow calculation | |
| CN208721299U (en) | A kind of tension on-line checking instrument and meter frame | |
| WO2000014523A2 (en) | Apparatus for monitoring the operability of an electrochemical sensor | |
| CN109048023A (en) | A kind of electric motor of automobile stator lead welding monitoring system and its monitoring method | |
| JP2002286623A (en) | Corrosion measuring device | |
| CN110182911A (en) | Ballast water for ship processing control apparatus, method and ship ballast water treatment system | |
| Bosch et al. | Introduction to different electrochemical corrosion monitoring techniques | |
| CN211927202U (en) | SF (sulfur hexafluoride)6Gas leakage on-line detection device in electrical equipment | |
| CN117250423B (en) | Nondestructive electric floor heating film reliability detection technology and device | |
| CN103710730B (en) | Alumina concentration determinator and method in a kind of aluminium cell | |
| CN109459786A (en) | A kind of detection system based on source range signal | |
| CN107450018A (en) | Detecting system | |
| JP2512178B2 (en) | Corrosion environment crack growth tester |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |