CN109884033A - Random forest algorithm combined with laser-induced breakdown spectroscopy to detect metal elements - Google Patents
Random forest algorithm combined with laser-induced breakdown spectroscopy to detect metal elements Download PDFInfo
- Publication number
- CN109884033A CN109884033A CN201910274617.5A CN201910274617A CN109884033A CN 109884033 A CN109884033 A CN 109884033A CN 201910274617 A CN201910274617 A CN 201910274617A CN 109884033 A CN109884033 A CN 109884033A
- Authority
- CN
- China
- Prior art keywords
- random forests
- forests algorithm
- induced breakdown
- oily sludge
- laser induced
- 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
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 41
- 238000007637 random forest analysis Methods 0.000 title claims abstract description 41
- 229910052751 metal Inorganic materials 0.000 title claims abstract description 32
- 238000002536 laser-induced breakdown spectroscopy Methods 0.000 title claims abstract description 25
- 238000000034 method Methods 0.000 claims abstract description 65
- 239000010802 sludge Substances 0.000 claims abstract description 37
- 238000012360 testing method Methods 0.000 claims abstract description 28
- 238000004611 spectroscopical analysis Methods 0.000 claims abstract description 21
- PXHVJJICTQNCMI-UHFFFAOYSA-N Nickel Chemical compound [Ni] PXHVJJICTQNCMI-UHFFFAOYSA-N 0.000 claims abstract description 18
- 239000002184 metal Substances 0.000 claims abstract description 16
- 238000001514 detection method Methods 0.000 claims abstract description 15
- 230000015556 catabolic process Effects 0.000 claims abstract description 11
- 150000002739 metals Chemical class 0.000 claims abstract description 11
- 231100000331 toxic Toxicity 0.000 claims abstract description 11
- 230000002588 toxic effect Effects 0.000 claims abstract description 11
- VYZAMTAEIAYCRO-UHFFFAOYSA-N Chromium Chemical compound [Cr] VYZAMTAEIAYCRO-UHFFFAOYSA-N 0.000 claims abstract description 9
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 claims abstract description 9
- HCHKCACWOHOZIP-UHFFFAOYSA-N Zinc Chemical compound [Zn] HCHKCACWOHOZIP-UHFFFAOYSA-N 0.000 claims abstract description 9
- 229910052804 chromium Inorganic materials 0.000 claims abstract description 9
- 239000011651 chromium Substances 0.000 claims abstract description 9
- 229910052802 copper Inorganic materials 0.000 claims abstract description 9
- 239000010949 copper Substances 0.000 claims abstract description 9
- 229910052759 nickel Inorganic materials 0.000 claims abstract description 9
- 238000012545 processing Methods 0.000 claims abstract description 9
- 229910052725 zinc Inorganic materials 0.000 claims abstract description 9
- 239000011701 zinc Substances 0.000 claims abstract description 9
- 238000001228 spectrum Methods 0.000 claims abstract description 7
- WURBVZBTWMNKQT-UHFFFAOYSA-N 1-(4-chlorophenoxy)-3,3-dimethyl-1-(1,2,4-triazol-1-yl)butan-2-one Chemical compound C1=NC=NN1C(C(=O)C(C)(C)C)OC1=CC=C(Cl)C=C1 WURBVZBTWMNKQT-UHFFFAOYSA-N 0.000 claims abstract description 5
- 238000000605 extraction Methods 0.000 claims abstract description 3
- 238000005259 measurement Methods 0.000 claims description 9
- 230000003595 spectral effect Effects 0.000 claims description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 6
- 239000011159 matrix material Substances 0.000 abstract description 6
- 239000000284 extract Substances 0.000 abstract description 5
- 238000004458 analytical method Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 4
- 230000000052 comparative effect Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000003208 petroleum Substances 0.000 description 3
- 238000004445 quantitative analysis Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 238000011088 calibration curve Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- PCHJSUWPFVWCPO-UHFFFAOYSA-N gold Chemical compound [Au] PCHJSUWPFVWCPO-UHFFFAOYSA-N 0.000 description 2
- 229910052737 gold Inorganic materials 0.000 description 2
- 239000010931 gold Substances 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 239000002910 solid waste Substances 0.000 description 2
- 238000010183 spectrum analysis Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000003915 air pollution Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000010779 crude oil Substances 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 230000001627 detrimental effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000007599 discharging Methods 0.000 description 1
- 238000000921 elemental analysis Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000003921 oil Substances 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 239000013618 particulate matter Substances 0.000 description 1
- 231100000572 poisoning Toxicity 0.000 description 1
- 230000000607 poisoning effect Effects 0.000 description 1
- 125000005575 polycyclic aromatic hydrocarbon group Chemical group 0.000 description 1
- 238000007670 refining Methods 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000012958 reprocessing Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000004904 shortening Methods 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 238000003900 soil pollution Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Landscapes
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The present invention provides a kind of methods of random forests algorithm combination laser induced breakdown spectroscopy detection metallic element, this method is to measure site spectrum data gathering in oily sludge sample difference with laser induced breakdown spectrograph device, it is divided into calibration set and test set, optimal Wavelet Denoising Method method is chosen to calibration set and test set spectroscopic data Wavelet Denoising Method, variable importance extracts again, find the optimal threshold value of prediction result, establish random forests algorithm calibration set model, with OOB error validity accuracy, tenor in the oily sludge sample of the test set of prediction after processing.The method that random forests algorithm combination laser induced breakdown spectroscopy is quantitative determined especially toxic metals copper, zinc, chromium and nickel in oily sludge sample by the present invention, random forests algorithm can overcome the interference of matrix effect, the spectroscopic data of Wavelet Denoising Method processing calibration set and test set overcomes noise in signal and improves prediction accuracy, variable importance extraction can improve predictablity rate, shorten the modeling time.
Description
Technical field
The invention belongs to field of spectral analysis technology, and in particular to a kind of random forests algorithm combination laser-induced breakdown light
The method of spectrum detection metallic element.
Background technique
Oil leak often occurs in the exploitation, reprocessing and transportational process of petroleum, recycles the problems such as incomplete, meeting
Cause soil, water resource and air pollution, especially soil pollution.Production, fortune with the development of petroleum industry, in crude oil
A large amount of oily sludge can be all generated in defeated, storage and refining process.It is one of the solid waste that petroleum industry generates, and is each
The mixture of the substances such as kind polycyclic aromatic hydrocarbon (PHCs), water, toxic metals and solid particulate matter.According to Chinese environmental standard
(GB5085.7-2007) it provides, oily sludge belongs to hazardous solid waste.If oily sludge does not reach country before discharging
Defined discharge standard, the toxic metals in oily sludge can be progressively enriched with by food chain, then passed through food and stored
In human organ, slow poisoning is caused, is detrimental to health.So quickly analyzing the concentration of toxic metals in oily sludge
It is all of great significance to the processing of oily sludge, migration, improvement, monitoring and reparation.
Laser induced breakdown spectroscopy (laser-induced breakdown spectroscopy, LIBS) is 20th century hair
The emerging atomic emission analysis spectral technique of one kind that exhibition is got up has quick analysis, Simultaneous multi element analysis and is not necessarily to sample
The advantages such as product pretreatment, therefore, LIBS technology is considered as one of most promising analysis means.In recent years, LIBS technology is wide
It is general to be applied to the fields such as environmental pollution, process analysis procedure analysis, science tour, space exploration, especially there is very big answer in field of metallurgy
Use potentiality.Therefore " following superstar " is described as by famous spectrum analysis scholar J.Winfordner.
The quantitative analysis method of laser induced breakdown spectroscopy refers mainly to calibration method and without calibration (CF) method.Calibration curve
Method is one of most simple, most widely used calibration method, it constructs integrated intensity or the (analysis of intensity ratio of elemental analysis line
Line and reference line) and one group of calibration sample known concentration between relationship.But calibration curve be always it is univariate, time
Returning model is established using the intensity of single feature line and the respective concentration of tested element, analyzes result vulnerable to laser energy
Fluctuation, the influence of sample inhomogeneities and complicated substrate effect.Since oily sludge is a complicated matrix, in the mistake of measurement
The chemical component measurement result of sample is easy to be influenced by a variety of matrix effects in journey, and conventional single argument calibrating patterns without
Method eliminates the influence of these disturbing factors.Multivariate Correction analysis method is to eliminate the effective tool of complex samples matrix effect.Mesh
Before, the Multivariate Correction algorithm of quantitative analysis includes: principal component analysis (PCA), artificial neural network (ANN), support vector machines
(SVM) and extreme learning machine etc..Random forests algorithm (Random Forest, abbreviation RF) be it is a kind of it is important based on
The integrated learning approach of Bagging can be used to do the problems such as classifying, returning, obtain success in the quantitative analysis of LIBS
Application.In machine learning, RF is a kind of Statistical Learning Theory, extracts repeated sampling method and carries out regression analysis.In spectrum
RF algorithm has obtained certain application in qualitative and quantitative.
Summary of the invention
Technical problem to be solved by the present invention lies in view of the above shortcomings of the prior art, provide a kind of random forest calculation
The method that method combination laser induced breakdown spectroscopy detects metallic element, this method is by random forests algorithm combination laser-induced breakdown
Spectrochemical Determination oily sludge Gold Samples category, the especially method of toxic metals copper, zinc, chromium and nickel, random forests algorithm
The interference that the factors such as matrix effect can be overcome handles the spectroscopic data of calibration set and test set by Wavelet Denoising Method, can be very
The good noise overcome in signal, effectively improves prediction accuracy, and further progress variable importance can not only mention after extracting
High predictablity rate, has stronger generalization ability at the time needed for also greatly shortening modeling.
In order to solve the above technical problems, the technical solution adopted by the present invention is that: a kind of random forests algorithm combination laser lures
The method for leading breakdown spectral detection metallic element, comprising the following steps:
Step 1: being surveyed respectively in the difference of oily sludge sample several different using laser induced breakdown spectrograph device
It measures site and carries out spectrum data gathering；
Step 2: being divided into calibration set and test set from the oily sludge sample several different in step 1；Calibration set
Spectroscopic data quantity ratio with the oily sludge sample of test set is 2.5:1；
Step 3: with the spectroscopic data of calibration set and test set in 28 kinds of different Wavelet Denoising Method method processing steps two,
It chooses after optimal Wavelet Denoising Method method carries out Wavelet Denoising Method to the spectroscopic data of calibration set and test set, then to carry out variable important
Property extract, find the optimal threshold value of prediction result, establish random forests algorithm calibration set model；
Step 4: with the accuracy for the random forests algorithm calibration set model established in OOB error validity step 3；
Step 5: the oily sludge of the test set using the random forests algorithm calibration set model prediction established after processing
Tenor in sample.
Preferably, the laser energy of laser induced breakdown spectrograph device described in step 1 is 150mJ, and fundamental light wave is a length of
1064nm, pulsewidth 10ns, delay time are 8 μ s, and repetition rate 5Hz, spectral region is 220nm~500nm.
Preferably, the quantity of oily sludge sample described in step 1 is not less than 16.
Preferably, each oily sludge sample of oily sludge sample several different described in step 2 is chosen at random
50 measurement points are selected, each measurement point obtains 1 spectroscopic data after 5 continuous laser pulses strike.
Preferably, wavelet basis function is db1, db2, db3 and db4, decomposition layer in Wavelet Denoising Method method described in step 3
Number is 1~7.
Preferably, the model of random forests algorithm calibration set described in step 3 is using related coefficient and root-mean-square error as commenting
Valence parameter.
Preferably, metal described in step 5 be one of toxic metals copper, zinc, chromium and nickel or more than one.
Preferably, the spectroscopic data of the oily sludge sample of treated in step 5 test set is in step 3 through too small
Wave filter is made an uproar and the test set spectroscopic data after variable importance extraction.
Compared with the prior art, the present invention has the following advantages:
Random forests algorithm combination laser induced breakdown spectroscopy is quantitative determined oily sludge Gold Samples category by the present invention, especially
It is the method for toxic metals copper, zinc, chromium and nickel, and random forests algorithm can overcome the interference of the factors such as matrix effect, pass through
Wavelet Denoising Method handles the spectroscopic data of calibration set and test set, can be good at overcoming the noise in signal, effectively improves prediction
Predictablity rate not only can be improved after extracting in accuracy, further progress variable importance, also greatly shortens modeling institute
The time needed has stronger generalization ability.
Below with reference to embodiment, invention is further described in detail.
Specific embodiment
Embodiment 1
The method of the random forests algorithm combination laser induced breakdown spectroscopy detection metallic element of the present embodiment, including it is following
Step:
Step 1: being surveyed respectively in the difference of oily sludge sample several different using laser induced breakdown spectrograph device
It measures site and carries out spectrum data gathering；The laser energy of the laser induced breakdown spectrograph device is 150mJ, and fundamental light wave is a length of
1064nm, pulsewidth 10ns, delay time are 8 μ s, and repetition rate 5Hz, spectral region is 220nm~500nm；
Step 2: being divided into calibration set and test set from the different oily sludge sample of 16 in step 1；Calibration set with
The spectroscopic data quantity ratio of the oily sludge sample of test set is 2.5:1；Described 16 different each of oily sludge samples
Oily sludge sample selects 50 measurement points at random, and each measurement point obtains 1 spectrum after 5 continuous laser pulses strike
Data；
Step 3: with the spectroscopic data of calibration set and test set in 28 kinds of different Wavelet Denoising Method method processing steps two,
It chooses after optimal Wavelet Denoising Method method carries out Wavelet Denoising Method to the spectroscopic data of calibration set and test set, then to carry out variable important
Property extract, find the optimal threshold value of prediction result, be respectively that input variable handles laser and lures with threshold value 0,0.01,0.02 and 0.03
Breakdown spectral is led, random forests algorithm calibration set model is established；In the Wavelet Denoising Method method wavelet basis function be db1, db2,
Db3 and db4, Decomposition order are 1~7；The random forests algorithm calibration set model is made with related coefficient and root-mean-square error
For evaluation parameter；
Step 4: with the accuracy for the random forests algorithm calibration set model established in OOB error validity step 3；
Step 5: the oily sludge of the test set using the random forests algorithm calibration set model prediction established after processing
Tenor in sample；The spectroscopic data of the oily sludge sample of treated test set is to pass through Wavelet Denoising Method in step 3
Test set spectroscopic data after being extracted with variable importance；The metal is one of toxic metals copper, zinc, chromium and nickel or one
Kind or more.
Comparative example 1
The method of the random forests algorithm combination laser induced breakdown spectroscopy detection metallic element of this comparative example, including it is following
Step:
Step 1~Step 2: with embodiment 1；
Step 3: establishing random forests algorithm calibration set model with calibration set in step 2；
Step 4: utilizing the oily sludge of the test set in the random forests algorithm calibration set model prediction step two established
Tenor in sample；The metal be one of toxic metals copper, zinc, chromium and nickel or more than one.
Prediction result is to the prediction result for comparing copper, zinc, chromium and nickel in test set sample before and after 1 spectral manipulation of table
Comparison laser induced breakdown spectroscopy does not pre-process (comparative example 1) and extracts by Wavelet Denoising Method and variable importance
In conjunction with the prediction result (embodiment 1) of random forests algorithm, the correlation of prediction result is significantly improved, root-mean-square error
Also it decreases.Therefore, random forests algorithm, Wavelet Denoising Method and variable importance combination laser induced breakdown spectroscopy can
With the detection for especially toxic metals copper, zinc, chromium and the nickel of metal in oily sludge.
The above is only presently preferred embodiments of the present invention, is not intended to limit the invention in any way.It is all according to invention skill
Art any simple modification, change and equivalence change substantially to the above embodiments, still fall within technical solution of the present invention
Protection scope in.
Claims (8)
1. a kind of method of random forests algorithm combination laser induced breakdown spectroscopy detection metallic element, which is characterized in that including
Following steps:
Step 1: using laser induced breakdown spectrograph device respectively in the different measurement positions of oily sludge sample several different
Point carries out spectrum data gathering；
Step 2: being divided into calibration set and test set from the oily sludge sample several different in step 1；Calibration set and survey
The spectroscopic data quantity ratio of the oily sludge sample integrated is tried as 2.5:1；
Step 3: being chosen with the spectroscopic data of calibration set and test set in 28 kinds of different Wavelet Denoising Method method processing steps two
After optimal Wavelet Denoising Method method carries out Wavelet Denoising Method to the spectroscopic data of calibration set and test set, then carries out variable importance and mention
It takes, finds the optimal threshold value of prediction result, establish random forests algorithm calibration set model；
Step 4: with the accuracy for the random forests algorithm calibration set model established in OOB error validity step 3；
Step 5: the oily sludge sample of the test set using the random forests algorithm calibration set model prediction established after processing
In tenor.
2. a kind of side of random forests algorithm combination laser induced breakdown spectroscopy detection metallic element according to claim 1
Method, which is characterized in that the laser energy of laser induced breakdown spectrograph device described in step 1 is 150mJ, and fundamental light wave is a length of
1064nm, pulsewidth 10ns, delay time are 8 μ s, and repetition rate 5Hz, spectral region is 220nm~500nm.
3. a kind of side of random forests algorithm combination laser induced breakdown spectroscopy detection metallic element according to claim 1
Method, which is characterized in that the quantity of oily sludge sample described in step 1 is not less than 16.
4. a kind of side of random forests algorithm combination laser induced breakdown spectroscopy detection metallic element according to claim 1
Method, which is characterized in that each oily sludge sample of oily sludge sample several different described in step 2 is chosen at random
50 measurement points are selected, each measurement point obtains 1 spectroscopic data after 5 continuous laser pulses strike.
5. a kind of side of random forests algorithm combination laser induced breakdown spectroscopy detection metallic element according to claim 1
Method, which is characterized in that wavelet basis function is db1, db2, db3 and db4, Decomposition order in Wavelet Denoising Method method described in step 3
It is 1~7.
6. a kind of side of random forests algorithm combination laser induced breakdown spectroscopy detection metallic element according to claim 1
Method, which is characterized in that the model of random forests algorithm calibration set described in step 3 is using related coefficient and root-mean-square error as commenting
Valence parameter.
7. a kind of side of random forests algorithm combination laser induced breakdown spectroscopy detection metallic element according to claim 1
Method, which is characterized in that metal described in step 5 be one of toxic metals copper, zinc, chromium and nickel or more than one.
8. a kind of side of random forests algorithm combination laser induced breakdown spectroscopy detection metallic element according to claim 1
Method, which is characterized in that the spectroscopic data of the oily sludge sample of treated in step 5 test set is in step 3 through too small
Wave filter is made an uproar and the test set spectroscopic data after variable importance extraction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910274617.5A CN109884033A (en) | 2019-04-08 | 2019-04-08 | Random forest algorithm combined with laser-induced breakdown spectroscopy to detect metal elements |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910274617.5A CN109884033A (en) | 2019-04-08 | 2019-04-08 | Random forest algorithm combined with laser-induced breakdown spectroscopy to detect metal elements |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109884033A true CN109884033A (en) | 2019-06-14 |
Family
ID=66936354
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910274617.5A Pending CN109884033A (en) | 2019-04-08 | 2019-04-08 | Random forest algorithm combined with laser-induced breakdown spectroscopy to detect metal elements |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109884033A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111595834A (en) * | 2020-05-27 | 2020-08-28 | 浙江大学 | A method for building a rapid quantitative detection model of heavy metal element copper in mulberry leaves |
| CN113295635A (en) * | 2021-05-27 | 2021-08-24 | 河北先河环保科技股份有限公司 | Water pollution alarm method based on dynamic update data set |
| CN116223480A (en) * | 2022-12-29 | 2023-06-06 | 南京工业大学 | Method and system for detecting heavy metal content in coal chemical industry sludge |
| CN117949436A (en) * | 2024-03-26 | 2024-04-30 | 宝鸡核力材料科技有限公司 | Metal element component detection method and system applied to titanium alloy smelting |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102519918A (en) * | 2011-12-08 | 2012-06-27 | 大连理工大学 | Method for rapid detection of waste oil based on laser-induced breakdown spectroscopy |
| CN104697964A (en) * | 2015-03-10 | 2015-06-10 | 西北大学 | Method for quantitative analysis of sulfur and phosphorus in steel and iron by combining random forest algorithm with laser induced breakdown spectroscopy |
| CN107063832A (en) * | 2017-05-23 | 2017-08-18 | 安徽中科中涣防务装备技术有限公司 | It is a kind of to be used for the on-line monitoring method of heavy metal concentration in electroplating sludge |
| CN109142251A (en) * | 2018-09-17 | 2019-01-04 | 平顶山学院 | The LIBS quantitative analysis method of random forest indirect labor's neural network |
-
2019
- 2019-04-08 CN CN201910274617.5A patent/CN109884033A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102519918A (en) * | 2011-12-08 | 2012-06-27 | 大连理工大学 | Method for rapid detection of waste oil based on laser-induced breakdown spectroscopy |
| CN104697964A (en) * | 2015-03-10 | 2015-06-10 | 西北大学 | Method for quantitative analysis of sulfur and phosphorus in steel and iron by combining random forest algorithm with laser induced breakdown spectroscopy |
| CN107063832A (en) * | 2017-05-23 | 2017-08-18 | 安徽中科中涣防务装备技术有限公司 | It is a kind of to be used for the on-line monitoring method of heavy metal concentration in electroplating sludge |
| CN109142251A (en) * | 2018-09-17 | 2019-01-04 | 平顶山学院 | The LIBS quantitative analysis method of random forest indirect labor's neural network |
Non-Patent Citations (3)
| Title |
|---|
| HUSSAIN, T ET AL.: "Monitoring and assessment of toxic metals in Gulf War oil spill contaminated soil using laser-induced breakdown spectroscopy", 《ENVIRONMENTAL MONITORING AND ASSESSMENT》 * |
| 吴珊: "激光诱导击穿光谱技术结合化学计量学对钢铁定量分析方法的研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅰ辑》 * |
| 林冬秀: "基于激光诱导击穿光谱技术的泥蚶重金属污染信息的快速检测", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111595834A (en) * | 2020-05-27 | 2020-08-28 | 浙江大学 | A method for building a rapid quantitative detection model of heavy metal element copper in mulberry leaves |
| CN111595834B (en) * | 2020-05-27 | 2021-05-04 | 浙江大学 | A method for building a rapid quantitative detection model of heavy metal element copper in mulberry leaves |
| CN113295635A (en) * | 2021-05-27 | 2021-08-24 | 河北先河环保科技股份有限公司 | Water pollution alarm method based on dynamic update data set |
| CN116223480A (en) * | 2022-12-29 | 2023-06-06 | 南京工业大学 | Method and system for detecting heavy metal content in coal chemical industry sludge |
| CN116223480B (en) * | 2022-12-29 | 2023-12-19 | 南京工业大学 | Method and system for detecting heavy metal content in coal chemical industry sludge |
| CN117949436A (en) * | 2024-03-26 | 2024-04-30 | 宝鸡核力材料科技有限公司 | Metal element component detection method and system applied to titanium alloy smelting |
| CN117949436B (en) * | 2024-03-26 | 2024-06-25 | 宝鸡核力材料科技有限公司 | Metal element component detection method and system applied to titanium alloy smelting |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109884033A (en) | Random forest algorithm combined with laser-induced breakdown spectroscopy to detect metal elements | |
| US11650348B2 (en) | Model based discriminant analysis | |
| Boehme et al. | Examining CDOM fluorescence variability using principal component analysis: seasonal and regional modeling of three-dimensional fluorescence in the Gulf of Mexico | |
| CN101915744B (en) | Near infrared spectrum nondestructive testing method and device for material component content | |
| Lei et al. | Customizable machine-learning models for rapid microplastic identification using Raman microscopy | |
| Tan et al. | Feasibility of laser-induced breakdown spectroscopy (LIBS) for classification of sea salts | |
| Han et al. | On-line multi-component analysis of gases for mud logging industry using data driven Raman spectroscopy | |
| Wang et al. | Oil species identification technique developed by Gabor wavelet analysis and support vector machine based on concentration-synchronous-matrix-fluorescence spectroscopy | |
| CN105044025A (en) | Method for fast recognizing sesame oil and sesame oil doped with soybean oil through near infrared | |
| Yoshino et al. | Signal preprocessing of deep-sea laser-induced plasma spectra for identification of pelletized hydrothermal deposits using Artificial Neural Networks | |
| CN103389294B (en) | Based on fake medicine discrimination and analysis device and the method for convoluted curve screening method | |
| Parish | Reflectance spectroscopy as a chert sourcing method | |
| CN106841170A (en) | A kind of coal ash category identification method based on wavelet neural network algorithm combination LIBS technologies | |
| Wang et al. | Simultaneous quantitative analysis of four metal elements in oily sludge by laser induced breakdown spectroscopy coupled with wavelet transform-random forest (WT-RF) | |
| CN105044054A (en) | Ocean oil spill fine telemetering method based on blind source separation | |
| CN107655918B (en) | Method and device for determining energy spectrum range of heavy metals in soil | |
| CN102854151B (en) | Chemometrics method for classifying sample sets in spectrum analysis | |
| CN105069462A (en) | Qualitative determination method for organic chemical based on spectral characteristic refinement and classifier cascading | |
| CN106383103A (en) | Time-resolved oil fluorescence identification method based on main component analysis | |
| CN109696425A (en) | A kind of landwaste kind identification method and system based on laser induced breakdown spectroscopy | |
| CN208476785U (en) | A kind of laser induced breakdown spectroscopy detection device suitable for aquatic products heavy metal analysis | |
| Qin et al. | Spectral non-destructive inspection of pigments via multivariate analysis | |
| Cui et al. | Discrimination of oil contaminants using supervised Kohonen Network and unconventional steady state fluorescence spectroscopy: a comparative evaluation | |
| CN113075201B (en) | Concentration detection method and system for complex matrix samples | |
| Brunswick et al. | Rapid forensic oil identification by direct analysis in real time (DART) with time-of-flight mass spectrometry and confirmation by gas chromatography-mass spectrometry |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190614 |
|
| RJ01 | Rejection of invention patent application after publication |