Nuclide type identification method based on surface pollution detector

Abstract

The invention discloses a nuclide type identification method based on a surface pollution detector. The nuclide type identification method comprises the steps that S1, the number of radioactive particles of a detected radioactive source in a certain period is measured through the surface pollution detector; s2, calculating a corresponding decay constant according to the number of radioactive particles of the measured radioactive source in a certain period; s3, inputting the decay constant of the measured radioactive source into the trained nuclide identification model, and outputting a corresponding nuclide type prediction result; wherein the nuclide identification model is constructed based on a deep learning model; and S4, taking the nuclide type prediction result as a nuclide type identification result of the measured radioactive source. According to the invention, a nuclide identification function (method) is designed on the basis of the surface pollution detector, and two tasks of radiation dose measurement and nuclide type identification can be completed at the same time through one surface pollution detector, so that the comprehensive performance of the surface pollution detector is improved, and the cost of radiation monitoring is reduced.

Description

Technical Field

[0001] The invention relates to the technical field of nuclide type identification, and in particular to a nuclide type identification method based on a surface contamination detector. Background Art

[0002] The surface contamination detector is a device used to detect the degree of radioactive contamination on the surface of an object. It is widely used in nuclear energy, nuclear medicine, environmental protection, scientific research and other fields. Its core principle is to use the detector to sense the α, β, γ and other radiation particles released by the radioactive source, and to evaluate the level of radioactive contamination on the surface of the object by measuring the number of these particles. The main function of the surface contamination detector is to provide quantitative readings of radiation doses to help users understand the radioactive status of the current environment and take corresponding protective measures.

[0003] Surface contamination detectors are generally composed of detectors, signal processing circuits, display devices, and power supplies. The detector is a key component of the detector, which can convert the received radiation signals into electrical signals. The signal processing circuit amplifies, filters, and digitizes these electrical signals to ultimately obtain readable radiation dose data. The display device is used to display the test results for easy viewing by staff.

[0004] Although existing surface contamination detectors play an important role in assessing radioactive contamination levels, in actual applications, users often need to know specific nuclide types. This is because different types of nuclides have different radiation characteristics and biological effects, and their effects on the environment and human body are also different. Therefore, it is not enough to know the radiation dose, but also to know which nuclide caused the contamination.

[0005] In response to the above problems, the applicant thought of designing a function for nuclide type identification based on the surface contamination detector. On the one hand, by integrating relevant nuclide identification algorithms, the surface contamination detector has the ability to identify nuclide types without adding additional hardware equipment, so that one device can simultaneously complete the two tasks of radiation dose measurement and nuclide type identification, thereby improving the overall performance of the equipment and reducing the cost of use. On the other hand, after integrating the nuclide type identification function, users can obtain complete test results more quickly, including radiation dose and nuclide type information, which helps users make decisions more quickly and take corresponding protective measures to ensure the safety of personnel and the environment. However, how to design a nuclide type identification method based on a surface contamination detector is a technical problem that needs to be solved urgently. Summary of the invention

[0006] In view of the above-mentioned deficiencies in the prior art, the technical problem to be solved by the present invention is: how to provide a radionuclide type identification method based on a surface contamination detector, and a radionuclide identification function (method) is designed on the basis of the surface contamination detector, which can simultaneously complete the two tasks of radiation dose measurement and radionuclide type identification through one surface contamination detector, thereby improving the comprehensive performance of the surface contamination detector and reducing the cost of radiation monitoring.

[0007] In order to solve the above technical problems, the present invention adopts the following technical solutions:

[0008] A method for identifying nuclide types based on a surface contamination detector, comprising:

[0009] S1: Measure the number of radioactive particles of the measured radiation source within a certain period through a surface contamination detector;

[0010] S2: Calculate the corresponding decay constant according to the number of radioactive particles of the measured radioactive source within a certain period;

[0011] S3: Input the decay constant of the radioactive source to be tested into the trained nuclide identification model, and output the corresponding nuclide type prediction result; the nuclide identification model is constructed based on the deep learning model;

[0012] S4: The nuclide type prediction result is used as the nuclide type identification result of the measured radioactive source.

[0013] Preferably, in step S1, the surface contamination detector comprises:

[0014] A scintillator detector is used to generate a light signal when receiving radiation particles from a radiation source;

[0015] Photomultiplier tube, used to convert the light signal generated by the scintillator detector into an electrical signal;

[0016] A preamplifier is used to amplify the electrical signal converted by the photomultiplier tube to obtain an amplified electrical signal;

[0017] A pulse shaping circuit, used for converting the amplified electrical signal obtained by the preamplifier into a pulse signal;

[0018] A discriminator is used to discriminate the pulse signal converted by the pulse shaping circuit to obtain a radiation particle signal;

[0019] The counter is used to count the radiation particle signals obtained by the discriminator to obtain the number of radioactive particles.

[0020] Preferably, the surface contamination detector further comprises:

[0021] A display device is used to display the number of radioactive particles.

[0022] Preferably, the scintillator detector of the surface contamination detector is covered with an aluminum film as a light-shielding film.

[0023] Preferably, the scintillator detector and the photomultiplier tube are coupled via a cavity.

[0024] Preferably, in step S2, the decay constant is calculated by the following steps:

[0025] S201: Calculate the change value of the number of radioactive particles of the measured radiation source within the period;

[0026] S202: The decay constant is obtained by dividing the change in the number of radioactive particles of the measured radiation source by the measurement interval.

[0027] Preferably, in step S3, the processing steps of training the nuclide identification model are as follows:

[0028] S301: Obtain decay constant samples, and label the decay constant samples according to the real nuclide types to form training data;

[0029] S302: constructing a nuclide identification model based on the convolutional neural network model;

[0030] S303: input the training data into the nuclide identification model and output the nuclide type prediction result;

[0031] S304: Calculating a loss function based on the nuclide type prediction result and the corresponding real nuclide type, and reversely optimizing the model parameters of the nuclide identification model;

[0032] S305: Repeat steps S303 to S304 until the nuclide identification model converges.

[0033] Compared with the prior art, the nuclide type identification method based on the surface contamination detector in the present invention has the following beneficial effects:

[0034] The present invention designs a nuclide type identification function (method) based on the surface contamination detector. First, the existing surface contamination detector mainly focuses on the number of radioactive particles and cannot determine the specific type of nuclide. By integrating the nuclide type identification function, the detector can provide more comprehensive detection information (including the number of radioactive particles and the type of nuclide), that is, it can simultaneously complete the two tasks of radiation dose measurement and nuclide type identification through a surface contamination detector, thereby improving the comprehensive performance of the surface contamination detector and reducing the cost of radiation monitoring. Secondly, after the nuclide type identification function is integrated on the surface contamination detector, complete detection information (including the number of radioactive particles and the type of nuclide) can be obtained more quickly, which helps to make decisions more quickly, thereby improving the efficiency of radiation monitoring.

[0035] When designing the nuclide type recognition function, the present invention constructs a nuclide recognition model based on a deep learning model, and predicts the nuclide type of the radioactive source through the decay constant. First, the deep learning model has powerful feature extraction and pattern recognition capabilities, and can extract nuclide features by learning a large number of decay constants, accurately identify nuclide types, thereby improving the accuracy of nuclide type recognition. Secondly, the deep learning model learns the general laws of nuclide characteristics by training a large amount of sample data, so that it has a stronger generalization ability, so that the model can not only identify known nuclide types, but also predict and identify unknown nuclide types, so that the model can cope with more complex detection environments, thereby improving the reliability of nuclide type recognition. Finally, the existing nuclide type recognition method requires manual participation in the feature extraction and pattern recognition process, which is not only time-consuming and labor-intensive, but also may introduce human errors. The nuclide type recognition method based on the deep learning model of the present invention can automatically complete the nuclide type recognition, thereby reducing the degree of manual intervention and improving the efficiency of nuclide type recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to make the purpose, technical solution and advantages of the invention clearer, the present invention will be further described in detail below with reference to the accompanying drawings, in which:

[0037] Figure 1 The figure is a logical block diagram of the radionuclide type identification method based on the surface contamination detector.

[0038] Figure 2 This is a schematic diagram of the structure of the surface contamination detector. DETAILED DESCRIPTION

[0039] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but only represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work belong to the scope of protection of the present invention.

[0040] It should be noted that similar numbers and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. In the description of the present invention, it should be noted that the orientation or position relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inside", "outside", etc. is based on the orientation or position relationship shown in the drawings, or the orientation or position relationship in which the invention product is usually placed when used, which is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation of the present invention. In addition, the terms "first", "second", "third", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance. In addition, the terms "horizontal", "vertical", etc. do not mean that the components are required to be absolutely horizontal or suspended, but can be slightly tilted. For example, "horizontal" only means that its direction is more horizontal than "vertical", and does not mean that the structure must be completely horizontal, but can be slightly tilted. In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0041] The following is a further detailed description through specific implementation methods:

[0042] Example:

[0043] This embodiment discloses a method for identifying nuclide types based on a surface contamination detector.

[0044] like Figure 1 As shown, a method for identifying the type of nuclide based on a surface contamination detector includes:

[0045] S1: Measure the number of radioactive particles of the measured radiation source within a certain period through a surface contamination detector;

[0046] S2: Calculate the corresponding decay constant according to the number of radioactive particles of the measured radioactive source within a certain period;

[0047] S3: Input the decay constant of the radioactive source to be tested into the trained nuclide identification model, and output the corresponding nuclide type prediction result; the nuclide identification model is constructed based on the deep learning model;

[0048] S4: The nuclide type prediction result is used as the nuclide type identification result of the measured radioactive source.

[0049] In this embodiment, the decay constant λ, also known as the nuclide decay coefficient, is an important parameter describing the decay rate of a radioactive nuclide. There is an inverse relationship between the decay constant and the half-life (T1 / 2), and the specific formula is:

[0050] λ=0.693 / T1 / 2, or T1 / 2=0.693 / λ12.

[0051] The decay constant represents the ratio of the number of atomic nuclei that decay per unit time to the total number of atomic nuclei. It is an inherent constant that has nothing to do with the number of radioactive nuclides and external factors, and is only determined by the radioactivity of the nuclides. The larger the decay constant, the faster the decay rate of the radioactive nuclide; conversely, the smaller the decay constant, the slower the decay rate.

[0052] Change value / measurement interval time, i.e. half-life = decay coefficient.

[0053] The present invention designs a nuclide type identification function (method) based on the surface contamination detector. First, the existing surface contamination detector mainly focuses on the number of radioactive particles and cannot determine the specific type of nuclide. By integrating the nuclide type identification function, the detector can provide more comprehensive detection information (including the number of radioactive particles and the type of nuclide), that is, it can simultaneously complete the two tasks of radiation dose measurement and nuclide type identification through a surface contamination detector, thereby improving the comprehensive performance of the surface contamination detector and reducing the cost of radiation monitoring. Secondly, after the nuclide type identification function is integrated on the surface contamination detector, complete detection information (including the number of radioactive particles and the type of nuclide) can be obtained more quickly, which helps to make decisions more quickly, thereby improving the efficiency of radiation monitoring.

[0054] When designing the nuclide type recognition function, the present invention constructs a nuclide recognition model based on a deep learning model, and predicts the nuclide type of the radioactive source through the decay constant. First, the deep learning model has powerful feature extraction and pattern recognition capabilities, and can extract nuclide features by learning a large number of decay constants, accurately identify the nuclide type, thereby improving the accuracy of nuclide type recognition. Secondly, the deep learning model learns the general laws of nuclide characteristics by training a large amount of sample data, so that it has a stronger generalization ability, so that the model can not only identify known nuclide types, but also predict and identify unknown nuclide types, so that the model can cope with more complex detection environments, thereby improving the reliability of nuclide type recognition. Finally, the existing nuclide type recognition method requires manual participation in the feature extraction and pattern recognition process, which is not only time-consuming and labor-intensive, but also may introduce human errors. The nuclide type recognition method based on the deep learning model of the present invention can automatically complete the nuclide type recognition, thereby reducing the degree of manual intervention and improving the efficiency of nuclide type recognition.

[0055] Combination Figure 2 As shown, the surface contamination detector includes:

[0056] A scintillator detector for generating a light signal when receiving radiation particles from a radiation source;

[0057] Photomultiplier tube, used to convert the light signal generated by the scintillator detector into an electrical signal;

[0058] A preamplifier is used to amplify the electrical signal converted by the photomultiplier tube to obtain an amplified electrical signal;

[0059] A pulse shaping circuit, used for converting the amplified electrical signal obtained by the preamplifier into a pulse signal;

[0060] A discriminator is used to discriminate the pulse signal converted by the pulse shaping circuit, remove noise and interference signals, and obtain a radiation particle signal;

[0061] The counter is used to count the radiation particle signals obtained by the discriminator to obtain the number of radioactive particles.

[0062] A display device is used to display the number of radioactive particles.

[0063] Specifically, the scintillator detector of the surface contamination detector is covered with an aluminum film with a thickness of 4 to 9 μm as a light-shielding film.

[0064] In this embodiment, in order to protect the light-shielding film, a grid is arranged in front of the light-shielding film.

[0065] Specifically, the scintillator detector and the photomultiplier tube are coupled through a cavity.

[0066] In the specific implementation process, the decay constant is calculated through the following steps:

[0067] S201: Calculate the change value of the number of radioactive particles of the measured radiation source within the period;

[0068] S202: The decay constant is obtained by dividing the change in the number of radioactive particles of the measured radiation source by the measurement interval.

[0069] In the specific implementation process, the processing steps for training the nuclide identification model are as follows:

[0070] S301: Obtain decay constant samples, and label the decay constant samples according to the real nuclide types to form training data;

[0071] S302: constructing a nuclide identification model based on the convolutional neural network model;

[0072] In this embodiment, the number of input layer nodes of the convolutional neural network model is first determined. Then the hidden layer is designed, and the appropriate number of hidden layer nodes and activation function are selected. Then the number of output layer nodes is determined. Finally, the weights and biases of the neural network are initialized, which is completed by random initialization or other optimization methods.

[0073] S303: input the training data into the nuclide identification model and output the nuclide type prediction result;

[0074] S304: Calculating a loss function based on the nuclide type prediction result and the corresponding real nuclide type, and reversely optimizing the model parameters of the nuclide identification model;

[0075] In this embodiment, the loss function adopts the cross entropy loss function.

[0076] S305: Repeat steps S303 to S304 until the nuclide identification model converges.

[0077] The present invention predicts the nuclide type based on the decay constant through a deep learning (convolutional neural network) model. The deep learning algorithm can learn the complex nonlinear relationship between the decay constant and the nuclide type from a large amount of training data, so that the model can more accurately predict the nuclide type of the radioactive source.

[0078] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit the technical solution. Those skilled in the art should understand that those modifications or equivalent substitutions of the technical solution of the present invention that do not depart from the purpose and scope of the technical solution should be included in the scope of the claims of the present invention.

Claims

1. A method for identifying nuclide types based on a surface contamination detector, characterized in that: include: S1: Measure the number of radioactive particles of the measured radiation source within a certain period through a surface contamination detector; S2: Calculate the corresponding decay constant according to the number of radioactive particles of the measured radioactive source within a certain period; S3: Input the decay constant of the radioactive source to be tested into the trained nuclide identification model, and output the corresponding nuclide type prediction result; the nuclide identification model is constructed based on the deep learning model; S4: The nuclide type prediction result is used as the nuclide type identification result of the measured radioactive source.

2. The method for identifying nuclide types based on a surface contamination detector according to claim 1, characterized in that: In step S1, the surface contamination detector includes: A scintillator detector is used to generate a light signal when receiving radiation particles from a radiation source; Photomultiplier tube, used to convert the light signal generated by the scintillator detector into an electrical signal; A preamplifier is used to amplify the electrical signal converted by the photomultiplier tube to obtain an amplified electrical signal; A pulse shaping circuit, used for converting the amplified electrical signal obtained by the preamplifier into a pulse signal; A discriminator is used to discriminate the pulse signal converted by the pulse shaping circuit to obtain a radiation particle signal; The counter is used to count the radiation particle signals obtained by the discriminator to obtain the number of radioactive particles.

3. The method for identifying nuclide types based on a surface contamination detector according to claim 2, characterized in that: The surface contamination detector also includes: A display device is used to display the number of radioactive particles.

4. The method for identifying nuclide types based on a surface contamination detector according to claim 2, characterized in that: The scintillator detector of the surface contamination detector is covered with an aluminum film as a light-proof film.

5. The method for identifying nuclide types based on a surface contamination detector according to claim 2, characterized in that: The scintillator detector and the photomultiplier tube are coupled through a cavity.

6. The method for identifying nuclide types based on a surface contamination detector according to claim 1, characterized in that: In step S2, the decay constant is calculated by the following steps: S201: Calculate the change value of the number of radioactive particles of the measured radiation source within the period; S202: The decay constant is obtained by dividing the change in the number of radioactive particles of the measured radiation source by the measurement interval.

7. The method for identifying nuclide types based on a surface contamination detector according to claim 1, characterized in that: In step S3, the processing steps for training the nuclide identification model are as follows: S301: Obtain decay constant samples, and label the decay constant samples according to the real nuclide types to form training data; S302: constructing a nuclide identification model based on the convolutional neural network model; S303: input the training data into the nuclide identification model and output the nuclide type prediction result; S304: Calculating a loss function based on the nuclide type prediction result and the corresponding real nuclide type, and reversely optimizing the model parameters of the nuclide identification model; S305: Repeat steps S303 to S304 until the nuclide identification model converges.

Images