CN111666719A - Gamma radiation multilayer shielding accumulation factor calculation method, device, equipment and medium - Google Patents
Gamma radiation multilayer shielding accumulation factor calculation method, device, equipment and medium Download PDFInfo
- Publication number
- CN111666719A CN111666719A CN202010512787.5A CN202010512787A CN111666719A CN 111666719 A CN111666719 A CN 111666719A CN 202010512787 A CN202010512787 A CN 202010512787A CN 111666719 A CN111666719 A CN 111666719A
- Authority
- CN
- China
- Prior art keywords
- accumulation
- shielding
- neural network
- deep neural
- gamma radiation
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computer Hardware Design (AREA)
- Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Biomedical Technology (AREA)
- Geometry (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Measurement Of Radiation (AREA)
Abstract
The application discloses a method, a device, equipment and a medium for calculating a gamma radiation multilayer shielding accumulation factor, which comprise the following steps: determining various parameters influencing the accumulation factors, generating a plurality of groups of different shielding samples, and calculating corresponding accumulation factor values by combining an MCNP program; taking various determined parameters influencing the accumulation factors as input, taking the calculated corresponding accumulation factor values as output, and constructing a deep neural network; training the deep neural network, and finishing training until the set requirement is met by continuously debugging the learning parameters; inputting various actual parameters influencing the accumulation factors into the trained deep neural network, and directly predicting the corresponding gamma radiation multilayer accumulation factors. According to the method, the deep neural network is constructed, the pre-calculated data samples are adopted for deep neural network learning, the gamma radiation multilayer accumulation factors can be quickly and accurately calculated, the calculation time is short, a large number of accumulation factors can be calculated at one time, and the calculation precision is relatively high.
Description
Technical Field
The invention relates to the field of radiation safety and protection, in particular to a method, a device, equipment and a medium for calculating a gamma radiation multilayer shielding accumulation factor.
Background
Currently, in radiation safety and protection, the gamma radiation accumulation Factor (build-up Factor) is a physical quantity that describes the influence of scattered photons. Generally, it refers to the ratio of the true value of a certain radiation quantity to the radiation quantity caused by the rays emitted by the radioactive source that do not interact with the shield at the point of investigation. The accumulation factor is usually different for different amounts of radiation. The physical quantities commonly used in the radiation protection include fluence, irradiation dose and absorption dose, and the corresponding cumulative factors are fluence cumulative factor, irradiation dose cumulative factor and absorption dose cumulative factor. In radiation protection, in order to protect the safety of workers, the radiation condition of the working environment is often required to be known, and the three-dimensional radiation field of the working environment is required to be calculated. The three-dimensional radiation field calculation generally adopts point-kernel integration, while the calculation of the accumulation factor is the key of the point-kernel integration, and the accuracy of the value directly determines the error of the point-kernel integration calculation, thereby determining the accuracy of the three-dimensional radiation field calculation. The main task of the accumulation factor calculation is to optimize the correction of the point kernel integration adopted in the three-dimensional radiation field calculation.
In the current practical engineering application, the correction and optimization of the accumulation factors adopted by the three-dimensional radiation field calculation method are realized by adopting an empirical formula or a database interpolation method, but the empirical formula or the database interpolation method is mainly suitable for calculating the accumulation factors during single-layer shielding. In a specific radiation field, the shielding body is often multilayer, each layer is composed of different materials, an empirical formula or a database interpolation method cannot accurately calculate the multilayer accumulated factor value, the error is usually very large, and the accuracy of the three-dimensional radiation field cannot be ensured.
Therefore, how to accurately and quickly calculate the multilayer radiation shielding accumulation factor for the three-radiation-field calculation is a technical problem to be solved urgently by those skilled in the art.
Disclosure of Invention
In view of the above, the present invention provides a method, an apparatus, a device and a medium for calculating a gamma radiation multi-layer shielding accumulation factor, which not only consumes less time for calculation, but also can calculate a large number of accumulation factors at one time, and has relatively high calculation accuracy. The specific scheme is as follows:
a gamma radiation multilayer shielding accumulation factor calculation method, comprising:
determining various parameters influencing the accumulation factors, generating a plurality of groups of different shielding samples, and calculating corresponding accumulation factor values by combining an MCNP program;
taking various determined parameters of the influence accumulation factors as input, and taking the corresponding calculated accumulation factor value as output to construct a deep neural network;
training the deep neural network, and finishing training until a set requirement is met by continuously debugging learning parameters;
inputting various actual parameters influencing the accumulation factors into the trained deep neural network, and directly predicting the corresponding gamma radiation multilayer accumulation factors.
Preferably, in the method for calculating a gamma radiation multilayer shielding accumulation factor provided in an embodiment of the present invention, the various parameters affecting the accumulation factor include incident particle energy, density of shielding materials of each layer, number of shielding free paths of each layer, shielding scattering cross section of each layer, shielding photoelectric effect cross section of each layer, and shielding electron pair effect cross section of each layer.
Preferably, in the method for calculating a gamma radiation multilayer shielding accumulation factor provided in the embodiment of the present invention, generating a plurality of groups of different shielding samples, and calculating corresponding accumulation factor values by combining with an MCNP program specifically includes:
establishing a plurality of groups of different models according to the determined characteristics of various parameters affecting the accumulation factors;
generating MCNP input files with different particle energies, different shielding materials and different shielding free path number combinations in batches;
calling an MCNP program to calculate according to the generated MCNP input file, and extracting the dose considering scattering and the dose not considering scattering after shielding in batch from a calculation result;
calculating a corresponding cumulative factor value by a ratio of the scatter-considered dose to the scatter-not-considered dose.
Preferably, in the method for calculating a gamma radiation multilayer shielding accumulation factor according to an embodiment of the present invention, while constructing the deep neural network, the method further includes:
and determining the topological structure of the deep neural network according to the number of the input parameters and the number of the output parameters.
Preferably, in the above method for calculating a gamma radiation multilayer shielding accumulation factor provided by the embodiment of the present invention, the hidden layer of the deep neural network employs double-layer neurons;
the node transfer functions of the deep neural network comprise a relu function and a linear function;
the training function of the deep neural network comprises an SDG function and a momentum function.
Preferably, in the method for calculating a gamma radiation multilayer shielding accumulation factor according to an embodiment of the present invention, the setting requirement includes that an average relative error of the validation set is smaller than a set prediction accuracy or reaches a set number of iterations.
The embodiment of the invention also provides a device for calculating the gamma radiation multilayer shielding accumulation factor, which comprises:
the accumulation factor calculation module is used for determining various parameters influencing the accumulation factors, generating a plurality of groups of different shielding samples and calculating corresponding accumulation factor values by combining an MCNP program;
the deep neural network construction module is used for taking various determined parameters of the influence accumulation factors as input and taking the corresponding calculated accumulation factor value as output to construct a deep neural network;
the deep neural network training module is used for training the deep neural network, and finishing training until a set requirement is met by continuously debugging learning parameters;
and the accumulation factor prediction module is used for inputting various actual parameters influencing the accumulation factors into the trained deep neural network and directly predicting the corresponding gamma radiation multilayer accumulation factors.
Preferably, in the above γ -radiation multilayer shielding accumulation factor calculation apparatus provided in an embodiment of the present invention, the accumulation factor calculation module specifically includes:
the model establishing unit is used for establishing a plurality of groups of different models according to the determined characteristics of various parameters of the influence accumulation factors;
the MCNP file generating unit is used for generating MCNP input files with different particle energies, different shielding materials and different shielding free path number combinations in batches;
the MCNP program calculating unit is used for calling an MCNP program to calculate according to the generated MCNP input file, and extracting the dose considering scattering and the dose not considering scattering after shielding in batch from a calculation result;
and the accumulation factor calculation unit is used for calculating a corresponding accumulation factor value through the ratio of the scattering considered dose to the non-scattering considered dose.
The embodiment of the present invention further provides a gamma radiation multilayer shielding accumulation factor calculation device, which includes a processor and a memory, wherein the processor implements the above gamma radiation multilayer shielding accumulation factor calculation method provided in the embodiment of the present invention when executing the computer program stored in the memory.
Embodiments of the present invention further provide a computer-readable storage medium for storing a computer program, where the computer program is executed by a processor to implement the above-mentioned gamma radiation multilayer shielding accumulation factor calculation method provided by the embodiments of the present invention.
It can be seen from the above technical solutions that, the method, apparatus, device and medium for calculating a gamma radiation multilayer shielding accumulation factor provided by the present invention includes: determining various parameters influencing the accumulation factors, generating a plurality of groups of different shielding samples, and calculating corresponding accumulation factor values by combining an MCNP program; taking various determined parameters influencing the accumulation factors as input, taking the calculated corresponding accumulation factor values as output, and constructing a deep neural network; training the deep neural network, and finishing training until the set requirement is met by continuously debugging the learning parameters; inputting various actual parameters influencing the accumulation factors into the trained deep neural network, and directly predicting the corresponding gamma radiation multilayer accumulation factors.
The invention provides a multilayer accumulation factor calculation based on a deep neural network, provides a brand-new method for gamma radiation multilayer shielding accumulation factor calculation, adopts pre-calculated data samples to carry out deep neural network learning under the condition of not decoupling complex physical relations between input and output by constructing the deep neural network, can realize quick and accurate calculation of the gamma radiation multilayer accumulation factors, has less calculation time consumption, can calculate a large number of accumulation factors at one time, has relatively higher calculation precision, and can meet the precision requirement of three-dimensional radiation field calculation on nuclear integral correction.
Drawings
In order to more clearly illustrate the embodiments of the present invention or technical solutions in related arts, the drawings used in the description of the embodiments or related arts will be briefly introduced below, it is obvious that the drawings in the following description are only embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the provided drawings without creative efforts.
Fig. 1 is a flowchart of a gamma radiation multilayer shielding accumulation factor calculation method provided by an embodiment of the present invention;
FIG. 2 is a schematic diagram of a double-layer flat geometry model provided in an embodiment of the present invention;
FIG. 3 is a diagram of deep neural network training errors provided by an embodiment of the present invention;
fig. 4 is a regression graph of the predicted values and the original data of the data including the training set, the verification set and the test set during the double-layer shielding according to the embodiment of the present invention;
FIG. 5 is a statistical diagram of the error of the prediction result of the deep neural network according to the embodiment of the present invention;
FIG. 6 is a graph comparing the predicted accumulation factor of AL + FE double-layer shielding with 0.6MeV incident photon energy and the real value;
FIG. 7 is a graph comparing the predicted accumulation factor of AL + FE double-layer shielding with 1.5MeV incident photon energy and the real value;
FIG. 8 is a graph comparing the predicted accumulation factor of AL + FE double-layer shielded deep neural network with incident photon energy of 8MeV and the real value provided by the embodiment of the present invention;
fig. 9 is a schematic structural diagram of a gamma radiation multi-layer shielding accumulation factor calculation apparatus according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, 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.
The invention provides a gamma radiation multilayer shielding accumulation factor calculation method, as shown in figure 1, comprising the following steps:
s101, determining various parameters influencing the accumulation factors, generating a plurality of groups of different shielding samples, and calculating corresponding accumulation factor values by combining an MCNP program;
in particular implementations, the various parameters that affect the accumulation factor may include the incident particle energy, the density of the shielding material in each layer, the number of free paths (thickness) in each layer, the shielding scattering cross-section in each layer, the shielding photoelectric effect cross-section in each layer, and the shielding electron pair effect cross-section in each layer. It should be noted that the mcnp (monte Carlo N Particle Transport code) program refers to a monte Carlo Particle Transport calculation program, which can be used for calculating neutrons, photons, electrons in a three-dimensional complex geometry structure or a general software package for coupling neutron/photon/electron Transport problems;
s102, taking various determined parameters influencing the accumulation factors as input, taking the calculated corresponding accumulation factor values as output, and constructing a Deep Neural Network (DNN);
it should be noted that, taking various determined parameters affecting the accumulation factors and corresponding accumulation factor values as learning samples, preprocessing the learning samples, dividing the learning samples into input items and corresponding output items, and performing deep neural network learning through the learning samples, so as to realize relatively accurate calculation of the multilayer accumulation factors;
s103, training the deep neural network, and finishing training until the set requirement is met by continuously debugging the learning parameters;
in particular implementations, the set requirement may include an average relative error of the validation set being less than a set prediction accuracy or a set number of iterations. That is, when the neural network is used to train and learn the accumulated factor calculation data, the neural network training is ended by adjusting the neural network learning parameters until the average relative error of the verification set is less than the set prediction precision (e.g. 0.5%) or the set iteration number is reached;
s104, inputting various actual parameters influencing the accumulation factors into a trained deep neural network, and directly predicting corresponding gamma radiation multilayer accumulation factors;
specifically, after the neural network learning is completed, the corresponding gamma radiation accumulation factor value can be quickly and accurately obtained by inputting incident photon energy, shielding free path number of each layer, shielding scattering cross section of each layer, photoelectric effect cross section and electron pair effect cross section in prediction.
In the method for calculating the gamma radiation multilayer shielding accumulation factor provided by the embodiment of the invention, the deep neural network is constructed, and the pre-calculated data sample is adopted to carry out deep neural network learning under the condition of not decoupling the complex physical relationship between input and output, so that the gamma radiation multilayer accumulation factor can be quickly and accurately calculated, the calculation time consumption is low, a large number of accumulation factors can be calculated at one time, the calculation precision is relatively high, and the precision requirement of three-dimensional radiation field calculation on the correction of the point-nuclear integral can be met.
In a specific implementation, in the method for calculating a gamma radiation multilayer shielding accumulation factor according to the embodiment of the present invention, the step S101 generates a plurality of different shielding samples, and calculates a corresponding accumulation factor value by combining with an MCNP program, which may specifically include: firstly, establishing a plurality of groups of different models according to the characteristics of various parameters influencing the accumulation factors; then, generating MCNP input files with different particle energies, different shielding materials and different shielding free path number combinations in batches; then, calling an MCNP program to calculate according to the generated MCNP input file, and extracting the dose considering scattering after shielding and the dose not considering scattering in batch from the calculation result; finally, the corresponding cumulative factor value is calculated by taking into account the ratio of the scattered dose to the dose not taken into account.
Specifically, the formula for calculating the corresponding cumulative factor value is as follows:
wherein the content of the first and second substances,
to take account of the scattered dose, D1For doses not accounting for scatter, B is the corresponding cumulative factor value.
In specific implementation, in the method for calculating a gamma radiation multilayer shielding accumulation factor according to the embodiment of the present invention, when the step S102 is executed to construct the deep neural network, the method may further include: according to the number n of input parameters1And the number n of output parameters2To determine the topology of the deep neural network.
Further, considering the complexity of the practical shielding problem, the deep neural network structure has the following guiding principles:
firstly, for complex engineering problems, a hidden layer of a deep neural network adopts double-layer neurons;
secondly, in the single-layer hidden layer neural network, the number structure of the whole neural network neurons is recommended as follows:
n1→2n1±1→n2；
thirdly, in the double-layer hidden layer neural network, the number structure of the whole neural network neurons is recommended as follows:
n1→1.5n1→2n1±1→n2；
for the deep neural network training parameters, the following recommendations are made:
the node transfer functions of the first deep neural network comprise a relu function and a linear function; preferably, the node transfer function is: relu + relu + relu + linear;
secondly, the training function of the deep neural network comprises an SDG function and a momentum function; the training function is: SDG + momentum.
The following describes the method for calculating the gamma radiation multilayer shielding accumulation factor provided by the embodiment of the present invention in detail by taking a double-layer flat model as an example of a calculation model of the accumulation factor:
as shown in fig. 2, the double-layered flat plate model is formed by combining two flat plates made of different materials. Firstly, converting an accumulative factor solving problem into solving the ratio of the dose after considering scattering and the dose value without considering scattering after double-layer shielding through modeling; then, calculating a series of doses of different particle source energies, different free path numbers and different double-layer material combinations after shielding by using an MCNP program; further sorting the neural network learning sample data (including incident photon energy, material density of each layer, average free path number of each layer, scattering cross section of each layer, photoelectric effect cross section of each layer and electron pair effect cross section of each layer); then training the sample by using a neural network, and achieving that the predicted relative average error is below 0.5%; and finally, directly predicting the value of the accumulative factor to be solved by utilizing the well-learned neural network. The method comprises the following specific steps:
determining various parameters influencing the accumulation factor, such as incident particle energy, shielding materials of all layers, the thickness (free path number) of shielding layers of all layers, cross section data (photoelectric effect cross section, scattering cross section and electron pair effect cross section) of shielding materials of all layers and the like;
and step two, establishing N groups of different flat plate models according to the parameter characteristics needing to be learned determined in the step one. Then, generating MCNP input files of different shielding materials with different shielding thicknesses and different energies in batches by using a sample batch generation program;
and step three, calculating a sample by using an MCNP program, extracting the dose which is obtained by MCNP calculation and takes scattering into consideration and the dose which is not taken into consideration after shielding in batch, calculating corresponding cumulative factor values, and finally taking each parameter and the corresponding cumulative factor value as a learning sample of the neural network. The partial MCNP calculated data and the corresponding accumulation factor data are shown in table one below:
| Scattering dose not taken into account (Gy) | Considering the scattering dose (Gy) | Cumulative factor value |
| 1.47234E-13 | 3.90952E-13 | 2.655310594 |
| 1.95883E-14 | 8.06854E-14 | 4.119060868 |
| 6.77E-15 | 3.41936E-14 | 5.052380235 |
| 3.09427E-14 | 1.16454E-13 | 3.763537119 |
| 3.25E-16 | 2.62E-15 | 8.047588175 |
| 2.89E-15 | 1.67444E-14 | 5.787881826 |
| 7.61E-15 | 3.73717E-14 | 4.911648238 |
And step four, preprocessing the learning sample data, and dividing the learning sample into an input item and a corresponding output item. It can be seen that there are 11 parameters of the two-layer entry, including: incident photon energy, first layer shielding material density, first layer photoelectric effect cross section, first layer scattering cross section, first layer electron pair effect cross section, first layer shielding free path number, second layer shielding material density, second layer photoelectric effect cross section, second layer scattering cross section, second layer electron pair effect cross section and second layer shielding free path number. The output term is the cumulative factor value.
Determining a topological structure of the deep neural network according to the number of input parameters and the number of output parameters of the sample; the ratio among the input layer, the hidden layer and the output layer of the neural network parameters can be set as 11: [ 508050 ] 1; a node transmission function adopts relu + relu + relu + linear; the training function adopts SDG + momentum;
step six, training and learning the accumulated factor calculation data by utilizing a neural network; the neural network learning is finished by continuously debugging the neural network learning parameters until the prediction precision that the average relative error is less than 0.5 percent is reached or the set iteration times are reached; the training error change is shown in fig. 3, the regression curves of the predicted values and the true values of the training set, the verification set and the test set are shown in fig. 4, and it can be known from fig. 4 that the neural network well fits the cumulative factor calculation data, and over-fitting and under-fitting conditions do not exist;
after learning of the neural network is completed, corresponding cumulative factor values can be predicted quickly and accurately by inputting incident particle energy, shielding thickness (free path number), photoelectric effect cross section, scattering cross section and electron pair effect cross section; the prediction error is shown in fig. 5.
The following table two shows partial data of neural network predicted accumulation factors:
watch two
Three groups of incident photon energies of 0.6MeV, 1.5MeV and 8MeV are selected for verification as follows:
incident photon energy 0.6 MeV: shielding the model: al + Fe (aluminum for the first shield layer and iron for the second shield layer), shielding free path number: within 10 free paths, the predicted value is compared with the true value based on the accumulated factor of the deep neural network, as shown in fig. 6. The average absolute error is 1.06%, and the maximum absolute error is 11.71%.
Incident photon energy 1.5 MeV: shielding the model: al + Fe (aluminum for the first shield layer and iron for the second shield layer), shielding free path number: within 10 free paths, the predicted value is compared with the real value based on the accumulated factor of the deep neural network, as shown in fig. 7. The average absolute error is 2.70%, and the maximum absolute error is 6.46%.
In this example, as is clear from table ii, fig. 6, fig. 7, and fig. 8, the absolute average error of the prediction is within 5%, and the maximum error is within an acceptable range. The method shows that the neural network is used for calculating the cumulative factor, so that a large amount of cumulative factor data can be calculated quickly, and the accuracy of the cumulative factor value can be ensured to a great extent. It is feasible to calculate the cumulative factor value using a neural network.
Based on the same inventive concept, embodiments of the present invention further provide a gamma radiation multilayer shielding accumulation factor calculation apparatus, and as the principle of solving the problem of the gamma radiation multilayer shielding accumulation factor calculation apparatus is similar to the aforementioned gamma radiation multilayer shielding accumulation factor calculation method, the implementation of the gamma radiation multilayer shielding accumulation factor calculation apparatus can refer to the implementation of the gamma radiation multilayer shielding accumulation factor calculation method, and repeated details are omitted.
In specific implementation, the apparatus for calculating a gamma radiation multilayer shielding accumulation factor according to the embodiment of the present invention, as shown in fig. 9, specifically includes:
the cumulative factor calculation module 11 is configured to determine various parameters affecting the cumulative factor, generate a plurality of groups of different mask samples, and calculate corresponding cumulative factor values by combining an MCNP program;
a deep neural network construction module 12, configured to take the determined various parameters affecting the accumulation factor as inputs and take the calculated corresponding accumulation factor value as an output to construct a deep neural network;
the deep neural network training module 13 is used for training a deep neural network, and finishing the training until the set requirement is met by continuously debugging the learning parameters;
and the accumulation factor prediction module 14 is used for inputting various actual parameters influencing the accumulation factors into the trained deep neural network, and directly predicting the corresponding gamma radiation multilayer accumulation factors.
In the gamma radiation multilayer shielding accumulation factor calculation device provided by the embodiment of the invention, under the condition that the decoupling of the complex physical relationship between the input and the output is not performed through the interaction of the four modules, the deep neural network learning is performed by adopting the pre-calculated data sample, the fast and accurate calculation of the gamma radiation multilayer accumulation factors is realized, the calculation time is short, a large number of accumulation factors can be calculated at one time, the calculation precision is relatively high, and the precision requirement of the three-dimensional radiation field calculation on the point-nuclear integral correction is met.
Further, in a specific implementation, in the gamma radiation multilayer shielding accumulation factor calculation apparatus provided in the embodiment of the present invention, the accumulation factor calculation module 11 may specifically include:
the model establishing unit is used for establishing a plurality of groups of different models according to the characteristics of the determined various parameters influencing the accumulation factors;
the MCNP file generating unit is used for generating MCNP input files with different particle energies, different shielding materials and different shielding free path number combinations in batches;
the MCNP program calculating unit is used for calling the MCNP program to calculate according to the generated MCNP input file, and extracting the dose considering scattering after shielding and the dose not considering scattering in batches from the calculation result;
and the accumulation factor calculation unit is used for calculating a corresponding accumulation factor value by taking the ratio of the scattered dose to the dose without taking the scattering into account.
For more specific working processes of the modules, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
Correspondingly, the embodiment of the invention also discloses a gamma radiation multilayer shielding accumulation factor calculation device, which comprises a processor and a memory; wherein the processor implements the gamma radiation multi-layer shielding accumulation factor calculation method disclosed in the foregoing embodiments when executing the computer program stored in the memory.
For more specific processes of the above method, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
Further, the present invention also discloses a computer readable storage medium for storing a computer program; the computer program when executed by a processor implements the gamma radiation multi-layer shielding accumulation factor calculation method disclosed previously.
For more specific processes of the above method, reference may be made to corresponding contents disclosed in the foregoing embodiments, and details are not repeated here.
The embodiments are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same or similar parts among the embodiments are referred to each other. The device, the equipment and the storage medium disclosed by the embodiment correspond to the method disclosed by the embodiment, so that the description is relatively simple, and the relevant points can be referred to the method part for description.
Those of skill would further appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The steps of a method or algorithm described in connection with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. A software module may reside in Random Access Memory (RAM), memory, Read Only Memory (ROM), electrically programmable ROM, electrically erasable programmable ROM, registers, hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.
To sum up, a method, an apparatus, a device and a medium for calculating a gamma radiation multilayer shielding accumulation factor according to embodiments of the present invention include: determining various parameters influencing the accumulation factors, generating a plurality of groups of different shielding samples, and calculating corresponding accumulation factor values by combining an MCNP program; taking various determined parameters influencing the accumulation factors as input, taking the calculated corresponding accumulation factor values as output, and constructing a deep neural network; training the deep neural network, and finishing training until the set requirement is met by continuously debugging the learning parameters; inputting various actual parameters influencing the accumulation factors into the trained deep neural network, and directly predicting the corresponding gamma radiation multilayer accumulation factors. Therefore, by constructing the deep neural network, under the condition of not decoupling the complex physical relationship between input and output, the deep neural network learning is carried out by adopting the pre-calculated data samples, the rapid and accurate calculation of the gamma radiation multilayer accumulation factors can be realized, the calculation time is less, a large number of accumulation factors can be calculated at one time, the calculation precision is relatively high, and the precision requirement of the three-dimensional radiation field calculation on the correction of the nuclear integral can be met.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The method, the device, the equipment and the medium for calculating the gamma radiation multilayer shielding accumulation factor provided by the invention are described in detail, a specific example is applied in the text to explain the principle and the implementation mode of the invention, and the description of the embodiment is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A gamma radiation multilayer shielding accumulation factor calculation method is characterized by comprising the following steps:
determining various parameters influencing the accumulation factors, generating a plurality of groups of different shielding samples, and calculating corresponding accumulation factor values by combining an MCNP program;
taking various determined parameters of the influence accumulation factors as input, and taking the corresponding calculated accumulation factor value as output to construct a deep neural network;
training the deep neural network, and finishing training until a set requirement is met by continuously debugging learning parameters;
inputting various actual parameters influencing the accumulation factors into the trained deep neural network, and directly predicting the corresponding gamma radiation multilayer accumulation factors.
2. The method of claim 1, wherein the parameters affecting the accumulation factor include incident particle energy, density of shielding material in each layer, number of free path of shielding in each layer, scattering cross section of shielding in each layer, photoelectric effect cross section of shielding in each layer, and electron pair effect cross section of shielding in each layer.
3. The method of claim 2, wherein generating a plurality of different mask samples and calculating corresponding cumulative factor values in conjunction with the MCNP program comprises:
establishing a plurality of groups of different models according to the determined characteristics of various parameters affecting the accumulation factors;
generating MCNP input files with different particle energies, different shielding materials and different shielding free path number combinations in batches;
calling an MCNP program to calculate according to the generated MCNP input file, and extracting the dose considering scattering and the dose not considering scattering after shielding in batch from a calculation result;
calculating a corresponding cumulative factor value by a ratio of the scatter-considered dose to the scatter-not-considered dose.
4. The method for calculating the gamma radiation multilayer shielding accumulation factor according to claim 1, further comprising the following steps of, while constructing the deep neural network:
and determining the topological structure of the deep neural network according to the number of the input parameters and the number of the output parameters.
5. The gamma-emitting multilayer shielded accumulation factor calculation method as set forth in claim 4, wherein the hidden layer of the deep neural network employs double-layer neurons;
the node transfer functions of the deep neural network comprise a relu function and a linear function;
the training function of the deep neural network comprises an SDG function and a momentum function.
6. The gamma radiation multi-layer shielding accumulation factor calculation method as claimed in claim 1, wherein the set requirement includes that the average relative error of the validation set is less than a set prediction accuracy or reaches a set number of iterations.
7. A gamma radiation multilayer shield accumulation factor calculation apparatus, comprising:
the accumulation factor calculation module is used for determining various parameters influencing the accumulation factors, generating a plurality of groups of different shielding samples and calculating corresponding accumulation factor values by combining an MCNP program;
the deep neural network construction module is used for taking various determined parameters of the influence accumulation factors as input and taking the corresponding calculated accumulation factor value as output to construct a deep neural network;
the deep neural network training module is used for training the deep neural network, and finishing training until a set requirement is met by continuously debugging learning parameters;
and the accumulation factor prediction module is used for inputting various actual parameters influencing the accumulation factors into the trained deep neural network and directly predicting the corresponding gamma radiation multilayer accumulation factors.
8. The gamma radiation multi-layer shielding accumulation factor calculation device of claim 7, wherein the accumulation factor calculation module specifically comprises:
the model establishing unit is used for establishing a plurality of groups of different models according to the determined characteristics of various parameters of the influence accumulation factors;
the MCNP file generating unit is used for generating MCNP input files with different particle energies, different shielding materials and different shielding free path number combinations in batches;
the MCNP program calculating unit is used for calling an MCNP program to calculate according to the generated MCNP input file, and extracting the dose considering scattering and the dose not considering scattering after shielding in batch from a calculation result;
and the accumulation factor calculation unit is used for calculating a corresponding accumulation factor value through the ratio of the scattering considered dose to the non-scattering considered dose.
9. A gamma radiation multi-layer shielding accumulation factor calculation device comprising a processor and a memory, wherein the processor implements the gamma radiation multi-layer shielding accumulation factor calculation method according to any one of claims 1 to 6 when executing a computer program stored in the memory.
10. A computer-readable storage medium for storing a computer program, wherein the computer program when executed by a processor implements the gamma radiation multi-layered shielding accumulation factor calculation method of any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010512787.5A CN111666719B (en) | 2020-06-08 | 2020-06-08 | Gamma radiation multilayer shielding accumulation factor calculation method, device, equipment and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010512787.5A CN111666719B (en) | 2020-06-08 | 2020-06-08 | Gamma radiation multilayer shielding accumulation factor calculation method, device, equipment and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111666719A true CN111666719A (en) | 2020-09-15 |
| CN111666719B CN111666719B (en) | 2022-02-08 |
Family
ID=72387116
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010512787.5A Active CN111666719B (en) | 2020-06-08 | 2020-06-08 | Gamma radiation multilayer shielding accumulation factor calculation method, device, equipment and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111666719B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112733439A (en) * | 2020-12-29 | 2021-04-30 | 哈尔滨工程大学 | Method for calculating shielding material accumulation factor based on BP neural network |
| CN113268863A (en) * | 2021-05-08 | 2021-08-17 | 中国辐射防护研究院 | Gamma radioactive source and electron linear accelerator machine room radiation shielding calculation method and device |
| CN113392499A (en) * | 2021-05-08 | 2021-09-14 | 中国辐射防护研究院 | Electron linear accelerator machine room radiation shielding and ozone concentration calculating method and device |
| CN117648875A (en) * | 2024-01-30 | 2024-03-05 | 湖南军芃科技股份有限公司 | Parameter optimization method of radiation shielding device and ore separator thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5844241A (en) * | 1996-07-19 | 1998-12-01 | City Of Hope | System and method for determining internal radioactivity and absorbed dose estimates |
| CN104933245A (en) * | 2015-06-15 | 2015-09-23 | 南华大学 | Ship reactor shielding design optimization method based on neural network and genetic algorithm |
| CN107330187A (en) * | 2017-06-30 | 2017-11-07 | 哈尔滨工程大学 | A kind of elimination of nuclear facilities radiation field dosage distributed simulation method |
| CN108229657A (en) * | 2017-12-25 | 2018-06-29 | 杭州健培科技有限公司 | A kind of deep neural network training and optimization algorithm based on evolution algorithmic |
| CN108549753A (en) * | 2018-03-28 | 2018-09-18 | 中国船舶重工集团公司第七〇九研究所 | A kind of radiation shield computational methods that Point- kernel integral method is coupled with Monte Carlo method |
-
2020
- 2020-06-08 CN CN202010512787.5A patent/CN111666719B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5844241A (en) * | 1996-07-19 | 1998-12-01 | City Of Hope | System and method for determining internal radioactivity and absorbed dose estimates |
| CN104933245A (en) * | 2015-06-15 | 2015-09-23 | 南华大学 | Ship reactor shielding design optimization method based on neural network and genetic algorithm |
| CN107330187A (en) * | 2017-06-30 | 2017-11-07 | 哈尔滨工程大学 | A kind of elimination of nuclear facilities radiation field dosage distributed simulation method |
| CN108229657A (en) * | 2017-12-25 | 2018-06-29 | 杭州健培科技有限公司 | A kind of deep neural network training and optimization algorithm based on evolution algorithmic |
| CN108549753A (en) * | 2018-03-28 | 2018-09-18 | 中国船舶重工集团公司第七〇九研究所 | A kind of radiation shield computational methods that Point- kernel integral method is coupled with Monte Carlo method |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112733439A (en) * | 2020-12-29 | 2021-04-30 | 哈尔滨工程大学 | Method for calculating shielding material accumulation factor based on BP neural network |
| CN113268863A (en) * | 2021-05-08 | 2021-08-17 | 中国辐射防护研究院 | Gamma radioactive source and electron linear accelerator machine room radiation shielding calculation method and device |
| CN113392499A (en) * | 2021-05-08 | 2021-09-14 | 中国辐射防护研究院 | Electron linear accelerator machine room radiation shielding and ozone concentration calculating method and device |
| CN113268863B (en) * | 2021-05-08 | 2022-11-18 | 中国辐射防护研究院 | Gamma radioactive source and electron linear accelerator machine room radiation shielding calculation method and device |
| CN113392499B (en) * | 2021-05-08 | 2023-01-17 | 中国辐射防护研究院 | Electron linear accelerator machine room radiation shielding and ozone concentration calculating method and device |
| CN117648875A (en) * | 2024-01-30 | 2024-03-05 | 湖南军芃科技股份有限公司 | Parameter optimization method of radiation shielding device and ore separator thereof |
| CN117648875B (en) * | 2024-01-30 | 2024-04-30 | 湖南军芃科技股份有限公司 | Parameter optimization method of radiation shielding device and ore separator thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111666719B (en) | 2022-02-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111666719B (en) | Gamma radiation multilayer shielding accumulation factor calculation method, device, equipment and medium | |
| Wagner et al. | FW-CADIS method for global and regional variance reduction of Monte Carlo radiation transport calculations | |
| CN108549753B (en) | Radiation shielding calculation method for coupling point kernel integration method and Monte Carlo method | |
| Perfetti et al. | Development of a generalized perturbation theory method for sensitivity analysis using continuous-energy Monte Carlo methods | |
| Kumar et al. | Influence of nuclear data parameters on integral experiment assimilation using cook’s distance | |
| Zeitlin et al. | Fragmentation cross sections of medium-energy Cl 35, Ar 40, and Ti 48 beams on elemental targets | |
| Kardan et al. | Fast neutron spectra determination by threshold activation detectors using neural networks | |
| Martinie et al. | Analytical modeling of alpha-particle emission rate at wafer-level | |
| Shaban et al. | Applying Monte Carlo and artificial intelligence techniques for 235U mass prediction in samples with different enrichments | |
| Sahiner | Gamma spectroscopy by artificial neural network coupled with MCNP | |
| Borella et al. | Signatures from the spent fuel: simulations and interpretation of the data with neural network analysis | |
| de Camargo et al. | A stochastic model for neutrons simulation considering the spectrum and nuclear properties with continuous dependence of energy | |
| Panikkath et al. | Estimation of neutron energy distributions from prompt gamma emissions | |
| Markov et al. | Modelling the radiative electromagnetic field | |
| Kulesza et al. | Evaluation of pulsed sphere time-of-flight and neutron attenuation experimental benchmarks using MCNP6’s unstructured mesh capabilities | |
| Angelo | Representing nuclear criticality excursion experiment data by an artificial neural network | |
| Craven et al. | Software for food irradiation simulation and equipment validation | |
| Ghita et al. | A Methodology for experimental and 3-D computational radiation transport assessments of Pu-Be neutron sources | |
| Chuong et al. | A comparative study on full-energy peak efficiency calibration methods for HPGe detector: Virtual point detector, curve fitting, and machine learning models | |
| CN114113188B (en) | Efficient tritium analysis method, device, equipment and storage medium | |
| CN113901702A (en) | LET value simulation method and device | |
| Seifried | Adjoint-based uncertainty quantification with mcnp | |
| Udupi et al. | Comparison of different methods of estimating the effective dose and the ambient dose equivalent for neutrons from measured prompt gamma intensities | |
| Weiss et al. | A Data-driven approach to predicting neutron penetration through media | |
| CN117648875B (en) | Parameter optimization method of radiation shielding device and ore separator thereof |
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 |