CN110133703A - A kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm - Google Patents
A kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm Download PDFInfo
- Publication number
- CN110133703A CN110133703A CN201910402753.8A CN201910402753A CN110133703A CN 110133703 A CN110133703 A CN 110133703A CN 201910402753 A CN201910402753 A CN 201910402753A CN 110133703 A CN110133703 A CN 110133703A
- Authority
- CN
- China
- Prior art keywords
- neural network
- spectrum
- gamma
- rays
- power spectrum
- 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
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 54
- 238000004422 calculation algorithm Methods 0.000 title claims abstract description 19
- 238000004980 dosimetry Methods 0.000 title claims abstract description 17
- 238000001228 spectrum Methods 0.000 claims abstract description 80
- 238000000034 method Methods 0.000 claims abstract description 35
- 238000005259 measurement Methods 0.000 claims abstract description 18
- 230000005251 gamma ray Effects 0.000 claims abstract description 15
- 238000004088 simulation Methods 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims abstract description 12
- 230000004044 response Effects 0.000 claims abstract description 11
- 238000001514 detection method Methods 0.000 claims abstract description 4
- 230000006870 function Effects 0.000 claims description 18
- 230000008021 deposition Effects 0.000 claims description 17
- 238000005070 sampling Methods 0.000 claims description 13
- 210000002569 neuron Anatomy 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 2
- 239000004973 liquid crystal related substance Substances 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 238000005086 pumping Methods 0.000 claims description 2
- 238000012360 testing method Methods 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 abstract description 2
- 238000010801 machine learning Methods 0.000 abstract 1
- 238000010183 spectrum analysis Methods 0.000 abstract 1
- 239000000523 sample Substances 0.000 description 21
- 238000013459 approach Methods 0.000 description 3
- 230000001447 compensatory effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 239000013078 crystal Substances 0.000 description 2
- 230000005855 radiation Effects 0.000 description 2
- 238000004611 spectroscopical analysis Methods 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000002939 conjugate gradient method Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 239000007788 liquid Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 230000007723 transport mechanism Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01T—MEASUREMENT OF NUCLEAR OR X-RADIATION
- G01T1/00—Measuring X-radiation, gamma radiation, corpuscular radiation, or cosmic radiation
- G01T1/02—Dosimeters
- G01T1/023—Scintillation dose-rate meters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- High Energy & Nuclear Physics (AREA)
- Measurement Of Radiation (AREA)
Abstract
The present invention relates to a kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm.The detection system that method of the present invention is calculated using conventional use of portable NaI (Tl) gamma ray spectrometer as simulation and actual measurement uses, portable NaI (Tl) gamma ray spectrometer structure is modeled using MCNP software, simulation calculates the gamma spectrum for obtaining Single photon, establish the gamma spectrum and dosage map relationship of Single photon, multipotency amount mixed spectrum independent same distribution sample is constructed using the gamma spectrum of Single photon based on principle of stacking, and the dosage of multipotency amount mixed spectrum is calculated, then the computation model of power spectrum and matched doses is established using BP neural network algorithm training sample.Using method of the present invention, the connection of dose value and energy response is established by machine learning, avoids the manual operations bring complexity such as energy spectrum analysis processing and mathematical analysis, and dose prediction is simple, quick, accurate.
Description
Technical field
The present invention relates to nuclear engineering technologies and radiation protection technique field, and in particular to one kind is based on BP neural network and illiteracy
The gamma-rays Dosimetry of special Carlow algorithm.
Background technique
The gamma-ray monitoring in the scene such as nuclear power and dose assessment are the important contents of radiation protection work, accurately determine spoke
Penetrating dosage can help staff correctly to take counter-measure, the health and safety of support personnel.Due to live source item feelings
Condition is complicated, and energy of γ ray exists from low energy to the wider range of about 7-8MeV high energy, for conventional non-tissue equivalent or non-empty
The equivalent detector of gas, energy response compensatory approach when for dosage measurement one of have been a hot spot of research and challenge.
There are mainly two types of currently used energy response compensatory approaches: one is optimized by panel detector structure from hardware angle
Degree compensates, and another kind is that the pulse amplitude spectrum numerical value processing obtained to detector carries out soft compensation from angle is calculated.Soft benefit
Compensation method is usually the functional relation that power spectrum and dosage are constructed on the basis of detector measurement spectral information, and common method is such as
G (E) function weighted and integral method, solution spectrometry etc..
Soft compensation method used at present can generally be related to math equation and physics in many spectroscopies and dosimeter
Intension, parameter selection lead to the dependence of artificial experience and disposal skill to calculate the disadvantages of complicated and result is uncertain high.
The gamma-rays Dosimetry established the present invention is based on BP neural network and Monte carlo algorithm can effectively solve the problems, such as this.
Summary of the invention
In view of the deficiencies in the prior art, the object of the present invention is to provide one kind to be based on BP neural network and Meng Teka
The gamma-rays dosage rapid survey calculation method of Lip river algorithm.
To achieve the above objectives, the technical solution adopted by the present invention is that: one kind is calculated based on BP neural network and Monte Carlo
The gamma-rays Dosimetry of method, comprising the following steps:
S1. the detection system used is calculated and surveyed as simulation using conventional use of portable NaI (Tl) gamma ray spectrometer,
Portable NaI (Tl) gamma ray spectrometer structure is modeled using MCNP software；
S2. the deposition power spectrum f for obtaining 1~9MeV difference projectile energy Single photon Ei is calculated by the simulation of MCNP software
(E, Ei) establishes the mapping relations of deposition power spectrum f (E, the Ei) and Neutron Ambient Dose Equivalent value of Single photon Ei, and to Single photon
The deposition power spectrum of Ei does reliability demonstration；
S3. independently same using deposition power spectrum f (E, Ei) the construction multipotency amount mixed spectrum of Single photon Ei based on principle of stacking
It is distributed sample, building method is random sampling formula, establishes what codomain was evenly distributed using the dynamic self-adapting of sampling number
Sample；
S4. the dosage that corresponding treatment process calculates multipotency amount mixed spectrum is superimposed using power spectrum, i.e., by forming mixed spectrum
The dose equivalent value of the deposition power spectrum of Single photon Ei is multiplied by the dosage that corresponding coefficient acquires multipotency amount mixed spectrum；
S5. the power spectrum that obtains simulation and superimposed structure, dose value are as training sample, according to the input of training sample ginseng
Number, output parameter determine the BP neural network number of plies, design BP neural network structure；
S6. training sample is learnt using the ability of BP neural network Approximation of Arbitrary Nonlinear Function, establishes power spectrum
And the computation model of matched doses, the output valve for making predicted dose and target value relative deviation are within ± 3%；
S7. the measurement of live power spectrum is carried out using the detector, and directly will using trained BP neural network structure
Measurement spectrum is scaled Neutron Ambient Dose Equivalent, without carrying out energy compensation.
Further, the deposition power spectrum f (E, Ei) of Single photon Ei and the specific side of dosage map relationship are established in step S2
Method is as follows: doing normalized to the deposition power spectrum f (E, Ei) of simulation, provides measuring system to unit fluence photon in per pass
Counting response；The corresponding Neutron Ambient Dose Equivalent value of conversion coefficient interpolation calculation list energy response spectra that the report recommends according to ICRP
Hi, to establish the spectrum and dosage map relationship of single energy ray.
Further, the specific method is as follows for reliability demonstration in step S2: utilizing detector pair under identical measuring condition60Co
The actual measurement spectrum of γ point source is compared with MCNP analog response broadening spectrum, carries out the reliability demonstration of sample, it is ensured that full energy peak actual measurement effect
Rate and computational efficiency relative deviation are within ± 10%.
Further, BP neural network is the three-layer neural network structure containing a hidden layer, the neural network node
Number is R1/2It is a, wherein R is the neuron number of input sample.
Further, the random sampling in step S3 method particularly includes: randomly select in all monoenergetic spectrum sample N m
Power spectrum, and multiply a random coefficient β i respectively, superposition summation obtains a new multi-power spectrum；Wherein m is the random number less than a, a
Indicate mixed spectrum greatest combined quantity；β i is the random number less than b, and b represents the coefficient upper limit, determined by actual conditions；Pass through pumping
The method optimization sample codomain range for taking number m logarithm dynamic adjustment, makes the variance of sampling distribution become larger.
Further, the activation primitive of the hidden layer and output layer of BP neural network is purelin function.
Further, the training function of BP neural network is that trainscg quantifies conjugate gradient function.
Further, the learning function of BP neural network is that learngdm gradient declines momentum function.
Further, the initial power threshold value of BP neural network is the random number of normal distribution, and the mean value of the normal distribution is
0, standard deviation R-1/2, wherein R is the neuron number of input sample.
Further, in step S7, the specific method is as follows for the measurement of live dosage: by an one chip microcomputer system and liquid
Portable NaI (Tl) gamma ray spectrometer that crystal display access field measurement uses, is implanted into trained BP neural network structure and meter
Instruction is calculated, the dose value for obtaining tested point rapidly can be composed according to field measurement.
Effect of the invention is that: 1. this method can measure rapidly around the live gamma field unit time such as nuclear power
Dose equivalent value realizes On-line sampling system dosage rate to obtain dosage rate values；
2. efficiently learning and establishing mapping ability processing power spectrum using neural network algorithm, conventional power spectrum pressure is avoided
Contracting, filtering, except the preprocessing process such as make an uproar；
3. directly mapping dose value avoids common gamma-spectrometric data treatment process, without to full energy peak, Compton level ground etc.
Information extracts；
4. constructed by power spectrum, can mixing power spectrum to multiple kinds of energy realize dosage measurement, it is not necessary to be confined to Dan Nengguang
Sub- power spectrum；
5. being calculated using the solution nonlinear equation that the extremely strong capability of fitting of neural network simplifies conventional soft compensatory approach
Journey reduces people because of the influence of processing.
6. trained network structure is implanted into spectrometer, dose prediction is simple and quick, accurate and visual.
Detailed description of the invention
Fig. 1 is the flow chart of the method for the invention.
Specific embodiment
Present invention will be further described below with reference to the accompanying drawings and specific embodiments.
As shown in Figure 1, a kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm, including with
Lower step:
Step 1 is calculated and is surveyed the detection system used as simulation using NaI (Tl) gamma ray spectrometer,
NaI (Tl) gamma ray spectrometer is that have the advantages that maintenance is simple, portable, is gamma spectrometer practical extensively, main to wrap
Probe portion and collection part are included, probe portion is made of NaI (Tl) scintillation crystal, photomultiplier tube, emitter follower；It collects
Part is by Linear Amplifer, multichannel pulse size analyzer, the composition such as recorder, printer.Gamma-rays can produce after passing through detector
A raw electric impulse signal completes the analysis to incident gamma ray by the way that the signal is measured and analyzed.
Step 2 models portable NaI (Tl) gamma ray spectrometer structure using MCNP software, and simulation calculates the single energy of series
The transport process of photon counts the probability of sedimentary energy.MCNP(Monte Carlo Neutron and Photo
Transport Code) be by Los Alamo National Laboratory, the U.S. based on Monte Carlo EGS4 method, developed for retouching
State and solve photon, neutron, the transport mechanism of electronics and the program of physical computing.
By MCNP software simulate calculate obtain 1~9MeV difference projectile energy Single photon Ei deposition power spectrum f (E,
Ei), normalized is done to simulated spectrum, provides counting response of the measuring system to unit fluence photon in per pass；According to
The corresponding Neutron Ambient Dose Equivalent value Hi of conversion coefficient interpolation calculation list energy response spectra that ICRP the report recommends, so that establishing list can penetrate
The spectrum and dosage map relationship of line；Utilize detector pair under identical measuring condition60The actual measurement spectrum of Co γ point source is rung with MCNP simulation
Spectrum should be broadened and compare the reliability demonstration for carrying out sample, it is ensured that full energy peak efficiency by inputoutput test and computational efficiency relative deviation are ± 10%
Within.
Step 3 utilizes deposition power spectrum f (E, Ei) the construction multipotency amount mixed spectrum independence of Single photon Ei based on principle of stacking
With distribution sample, building method is random sampling formula, establishes codomain using the dynamic self-adapting of sampling number and is evenly distributed
Sample.The specific methods of sampling are as follows: randomly select m power spectrum in all monoenergetic spectrum sample N, and multiply a random system respectively
Number β i, superposition summation obtain a new multi-power spectrum；Wherein m is the random number less than a, and a indicates mixed spectrum greatest combined quantity；
β i is the random number less than b, and b represents the coefficient upper limit, determined by actual conditions；By extracting doing for number m logarithm dynamic adjustment
Method optimizes sample codomain range, and the variance of sampling distribution is made to become larger.
Step 4, multipotency amount mixed spectrum dosage corresponding treatment process be superimposed using power spectrum calculated, mixed by form
The monoenergetic spectrum dose equivalent value Hi of spectrum is multiplied by the dosage that corresponding coefficient superposition acquires mixed spectrum.
Step 5 determines that the BP neural network number of plies, BP neural network structure are set according to the input parameter of sample, output parameter
It counts as follows:
(a) using the three-layer neural network structure for containing a hidden layer；
(b) neural network node number is set as 1/2 power of input sample neuron number purpose；
Determine that Neural Network Training Parameter is as follows according to debugging effect:
(a) hidden layer and output layer activation primitive: purelin function；
(b) BP neural network training function: trainscg Scaled Conjugate Gradient Method；
(c) BP neural network learning function: learngdm gradient declines momentum function；
(d) initial weight threshold value distribution use mean value for 0, standard deviation be -1/2 power of input sample neuron number just
State distribution random numbers；
Step 6 learns training sample using the ability of BP neural network Approximation of Arbitrary Nonlinear Function, reaches it
To convergence, dose prediction output valve and target value relative deviation may finally be reached within ± 3%.
Step 7 accesses an one chip microcomputer system and liquid crystal to portable NaI (Tl) gamma ray spectrometer for field measurement
Display is implanted into trained BP neural network structure and computations, measurement spectrum can be scaled Neutron Ambient Dose Equivalent, nothing
It need to carry out energy compensation.
It will be understood by those skilled in the art that method and system of the present invention is not limited to institute in specific embodiment
The embodiment stated, specific descriptions above are intended merely to explain the purpose of the present invention, are not intended to limit the present invention.This field skill
Art personnel can derive other implementation manners according to the technical scheme of the present invention, and also belong to the scope of the technical innovation of the present invention, this
The protection scope of invention is defined by the claims and their equivalents.
Claims (10)
1. a kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm, which is characterized in that the side
Method the following steps are included:
S1. the detection system used is calculated and surveyed as simulation using conventional use of portable NaI (Tl) gamma ray spectrometer, is utilized
MCNP software models portable NaI (Tl) gamma ray spectrometer structure；
S2. by MCNP software simulation calculate obtain 1~9MeV difference projectile energy Single photon Ei deposition power spectrum f (E,
Ei), the mapping relations of deposition power spectrum f (E, the Ei) and Neutron Ambient Dose Equivalent value of Single photon Ei are established, and to Single photon Ei
Deposition power spectrum f (E, Ei) do reliability demonstration；
S3. multipotency amount mixed spectrum independent same distribution is constructed using the deposition power spectrum f (E, Ei) of Single photon Ei based on principle of stacking
Sample, building method are random sampling formula, establish the sample that codomain is evenly distributed using the dynamic self-adapting of sampling number；
S4. the dosage that corresponding treatment process calculates multipotency amount mixed spectrum, i.e. single energy by forming mixed spectrum are superimposed using power spectrum
The dose equivalent value of the deposition power spectrum of photon Ei is multiplied by the dosage that corresponding coefficient acquires multipotency amount mixed spectrum；
S5. the power spectrum that obtains simulation and superimposed structure, dose value as training sample, according to the input parameter of training sample,
Output parameter determines the BP neural network number of plies, designs BP neural network structure；
S6. training sample is learnt using the ability of BP neural network Approximation of Arbitrary Nonlinear Function, establishes power spectrum and right
The computation model for answering dosage, the output valve for making predicted dose and target value relative deviation are within ± 3%；
S7. the measurement of live power spectrum is carried out using the detector, and directly will measurement using trained BP neural network structure
Spectrum is scaled Neutron Ambient Dose Equivalent, without carrying out energy compensation.
2. a kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm as described in claim 1,
It is characterized in that, established in step S2 Single photon Ei deposition power spectrum f (E, Ei) and dosage map relationship specific method such as
Under: normalized is done to the deposition power spectrum f (E, Ei) of simulation, provides meter of the measuring system to unit fluence photon in per pass
Number response；The corresponding Neutron Ambient Dose Equivalent value Hi of conversion coefficient interpolation calculation list energy response spectra that the report recommends according to ICRP, from
And establish the deposition power spectrum of Single photon and the mapping relations of dosage.
3. a kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm as described in claim 1,
It is characterized in that, the specific method is as follows for reliability demonstration in step S2: utilizing detector pair under identical measuring condition60Coγ
The actual measurement spectrum of point source is compared with MCNP analog response broadening spectrum, carries out the reliability demonstration of sample, it is ensured that full energy peak efficiency by inputoutput test
With computational efficiency relative deviation within ± 10%.
4. a kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm as described in claim 1,
It is characterized in that, random sampling in step S3 method particularly includes: m power spectrum is randomly selected in all monoenergetic spectrum sample N,
And multiplying a random coefficient β i respectively, superposition summation obtains a new multipotency amount mixed spectrum；Wherein m is the random number less than a,
A indicates mixed spectrum greatest combined quantity；β i is the random number less than b, and b represents the coefficient upper limit, determined by actual conditions；Pass through pumping
The method optimization sample codomain range for taking number m logarithm dynamic adjustment, makes the variance of sampling distribution become larger.
5. a kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm as described in claim 1,
It is characterized in that, the BP neural network is the three-layer neural network structure containing a hidden layer, the neural network node
Number is R1/2It is a, wherein R is the neuron number of input sample.
6. a kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm as claimed in claim 5,
It is characterized in that, the hidden layer of the BP neural network and the activation primitive of output layer are purelin function.
7. a kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm as claimed in claim 5,
It is characterized in that, the training function of the BP neural network is that trainscg quantifies conjugate gradient function.
8. a kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm as claimed in claim 5,
It is characterized in that, the learning function of the BP neural network is that learngdm gradient declines momentum function.
9. a kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm as claimed in claim 5,
It is characterized in that, the initial power threshold value of the BP neural network is the random number of normal distribution, the mean value of the normal distribution is
0, standard deviation R-1/2, wherein R is the neuron number of input sample.
10. a kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm as described in claim 1,
It is characterized in that, the specific method is as follows by step S7: an one chip microcomputer system and liquid crystal display are accessed field measurement
Portable NaI (Tl) gamma ray spectrometer used, is implanted into trained BP neural network structure and computations, can be according to live real
Survey the Neutron Ambient Dose Equivalent that spectrum obtains rapidly tested point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910402753.8A CN110133703A (en) | 2019-05-15 | 2019-05-15 | A kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910402753.8A CN110133703A (en) | 2019-05-15 | 2019-05-15 | A kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110133703A true CN110133703A (en) | 2019-08-16 |
Family
ID=67574214
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910402753.8A Pending CN110133703A (en) | 2019-05-15 | 2019-05-15 | A kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110133703A (en) |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111666718A (en) * | 2020-06-08 | 2020-09-15 | 南华大学 | Intelligent inversion method, device and equipment for nuclear facility source activity and storage medium |
| CN111667571A (en) * | 2020-06-08 | 2020-09-15 | 南华大学 | Method, Apparatus, Equipment and Medium for Rapid Reconstruction of Three-dimensional Distribution of Source Items in Nuclear Facilities |
| CN112925006A (en) * | 2019-12-05 | 2021-06-08 | 核工业西南物理研究院 | Fusion neutron real-time energy spectrum resolution method for magnetic confinement device |
| CN113536679A (en) * | 2021-07-20 | 2021-10-22 | 南京航空航天大学 | Point source dosage rate correction method based on artificial neural network |
| CN114488266A (en) * | 2021-12-16 | 2022-05-13 | 中国原子能科学研究院 | A method for determining the absorbed dose of eye lens in beta radiation field |
| CN115166811A (en) * | 2022-05-16 | 2022-10-11 | 中国辐射防护研究院 | A Rapid Construction Method of Neutron Spectrum in Simulated Work Site |
| CN115270588A (en) * | 2022-08-03 | 2022-11-01 | 中山大学肿瘤防治中心（中山大学附属肿瘤医院、中山大学肿瘤研究所） | A fluence spectrum distribution calculation modeling, fluence spectrum distribution calculation method and device |
| CN116010785A (en) * | 2022-12-08 | 2023-04-25 | 中国辐射防护研究院 | ResNet-based gamma energy spectrum data analysis method, storage medium and system |
| CN118571384A (en) * | 2024-07-31 | 2024-08-30 | 西安聚能医工科技有限公司 | Method for establishing high-energy X-ray reference radiometric based on Monte Carlo simulation |
| CN119312014A (en) * | 2024-12-13 | 2025-01-14 | 南京信息工程大学 | A parameter-constrained Monte Carlo method for determining the energy spectrum of solar proton events |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102608649A (en) * | 2012-03-02 | 2012-07-25 | 成都理工大学 | Statistics distributed gamma or X ray energy spectrum unscrambling method |
| CN103853929A (en) * | 2014-03-17 | 2014-06-11 | 东华理工大学 | Low-resolution gamma energy spectrum inversion analysis process and method based on Monte Carlo response matrix |
| CN104536032A (en) * | 2014-12-23 | 2015-04-22 | 四川大学 | Liquid scintillator detector n/gamma ray screening method based on support vector machine |
| CN105607111A (en) * | 2014-11-05 | 2016-05-25 | 中国科学院高能物理研究所 | Gamma nuclide identification method |
-
2019
- 2019-05-15 CN CN201910402753.8A patent/CN110133703A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102608649A (en) * | 2012-03-02 | 2012-07-25 | 成都理工大学 | Statistics distributed gamma or X ray energy spectrum unscrambling method |
| CN103853929A (en) * | 2014-03-17 | 2014-06-11 | 东华理工大学 | Low-resolution gamma energy spectrum inversion analysis process and method based on Monte Carlo response matrix |
| CN105607111A (en) * | 2014-11-05 | 2016-05-25 | 中国科学院高能物理研究所 | Gamma nuclide identification method |
| CN104536032A (en) * | 2014-12-23 | 2015-04-22 | 四川大学 | Liquid scintillator detector n/gamma ray screening method based on support vector machine |
Non-Patent Citations (2)
| Title |
|---|
| 李国栋 等: "BP神经网络γ射线剂量测量方法研究", 《核电子学与探测技术》 * |
| 陈法国 等: "G(E)函数在高能γ射线剂量测量中的应用", 《核电子学与探测技术》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112925006A (en) * | 2019-12-05 | 2021-06-08 | 核工业西南物理研究院 | Fusion neutron real-time energy spectrum resolution method for magnetic confinement device |
| CN111667571A (en) * | 2020-06-08 | 2020-09-15 | 南华大学 | Method, Apparatus, Equipment and Medium for Rapid Reconstruction of Three-dimensional Distribution of Source Items in Nuclear Facilities |
| CN111667571B (en) * | 2020-06-08 | 2021-09-17 | 南华大学 | Nuclear facility source item three-dimensional distribution rapid reconstruction method, device, equipment and medium |
| CN111666718B (en) * | 2020-06-08 | 2021-10-22 | 南华大学 | Method, device, equipment and storage medium for intelligent inversion of source term activity in nuclear facilities |
| CN111666718A (en) * | 2020-06-08 | 2020-09-15 | 南华大学 | Intelligent inversion method, device and equipment for nuclear facility source activity and storage medium |
| CN113536679B (en) * | 2021-07-20 | 2024-09-24 | 南京航空航天大学 | Point source dose rate correction method based on artificial neural network |
| CN113536679A (en) * | 2021-07-20 | 2021-10-22 | 南京航空航天大学 | Point source dosage rate correction method based on artificial neural network |
| CN114488266A (en) * | 2021-12-16 | 2022-05-13 | 中国原子能科学研究院 | A method for determining the absorbed dose of eye lens in beta radiation field |
| CN115166811A (en) * | 2022-05-16 | 2022-10-11 | 中国辐射防护研究院 | A Rapid Construction Method of Neutron Spectrum in Simulated Work Site |
| CN115270588A (en) * | 2022-08-03 | 2022-11-01 | 中山大学肿瘤防治中心（中山大学附属肿瘤医院、中山大学肿瘤研究所） | A fluence spectrum distribution calculation modeling, fluence spectrum distribution calculation method and device |
| CN116010785A (en) * | 2022-12-08 | 2023-04-25 | 中国辐射防护研究院 | ResNet-based gamma energy spectrum data analysis method, storage medium and system |
| CN118571384A (en) * | 2024-07-31 | 2024-08-30 | 西安聚能医工科技有限公司 | Method for establishing high-energy X-ray reference radiometric based on Monte Carlo simulation |
| CN119312014A (en) * | 2024-12-13 | 2025-01-14 | 南京信息工程大学 | A parameter-constrained Monte Carlo method for determining the energy spectrum of solar proton events |
| CN119312014B (en) * | 2024-12-13 | 2025-03-07 | 南京信息工程大学 | A parameter-constrained Monte Carlo method for determining the energy spectrum of solar proton events |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110133703A (en) | A kind of gamma-rays Dosimetry based on BP neural network and Monte carlo algorithm | |
| Zhang et al. | Monte Carlo simulation of a NaI (Tl) detector for in situ radioactivity measurements in the marine environment | |
| CN104678425B (en) | Fast-neutron multiple measuring-analyzing method based on liquid scintillation detector | |
| CN109655878A (en) | X/ γ dosemeter field calibration method based on x-ray source, radiation protecting systems | |
| Zhuang et al. | Time variation of the atmospheric neutrino flux at dark matter detectors | |
| Clarke et al. | Neutron and gamma-ray cross-correlation measurements of plutonium oxide powder | |
| CN113536679A (en) | Point source dosage rate correction method based on artificial neural network | |
| Ulanovsky et al. | Influence of measurement geometry on the estimate of 131I activity in the thyroid: Monte Carlo simulation of a detector and a phantom | |
| CN106814384A (en) | Nuclear power plant's point source radiation source strength backstepping method and point source radiation source strength backstepping system | |
| Priyada et al. | Use of prompt gamma emissions from polyethylene to estimate neutron ambient dose equivalent | |
| Mauring et al. | InSiCal–A tool for calculating calibration factors and activity concentrations in in situ gamma spectrometry | |
| CN111487670B (en) | Temperature-controlled fluid neutron spectrometer, measuring method thereof and analysis processing system | |
| CN106991621B (en) | The recombination radiation source strength backstepping method and system of nuclear power plant's point source face source combination | |
| Fonnesu et al. | The preparation of the Shutdown Dose Rate experiment for the next JET Deuterium-Tritium campaign | |
| Cai et al. | Rapid determination of radon progeny concentration based on artificial neural networks | |
| CN116738514A (en) | Underground kilometer grade Miao Ziliu strong prediction method | |
| Herranz et al. | Evaluation of uncertainty and detection limits in radioactivity measurements | |
| Sorimachi et al. | An intercomparison done at NIRS, Japan on continuous monitors for measuring 220Rn concentration | |
| Sahagia et al. | Education and training tradition at IFIN-HH in radon measurement and evaluation of radiological impact | |
| CN113466915A (en) | Radiation dose rate measuring system and method based on high-purity germanium detector | |
| KR20040097081A (en) | Method of a Multipurpose Environmental Radiation Monitoring and a Portable Environmental Radiation Monitor by using the Method | |
| Xu et al. | A sequential least-squares algorithm for neutron spectrum unfolding from pulse-height distributions measured with liquid scintillators | |
| Weinmann-Smith et al. | Measurement and simulation of cosmic rays effects on neutron multiplicity counting | |
| CN106991511A (en) | The recombination radiation source strength backstepping method and system of nuclear power plant's point source line source face source combination | |
| Dietze et al. | Intercomparison of dose equivalent meters based on microdosimetric techniques |
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 |