Method, system and equipment for measuring radon radiation concentration by CR-39

文档序号：1323504 发布日期：2020-07-14 浏览：13次中文

阅读说明：本技术 一种cr-39测量氡气辐射浓度的方法、系统及设备 (Method, system and equipment for measuring radon radiation concentration by CR-39 ) 是由陈瀚蔡述庭于 2020-02-28 设计创作，主要内容包括：本申请公开了一种CR-39测量氡气辐射浓度的方法、系统及设备,包括：获取CR-39样品的信号图像；将信号图像输入到浓度测量模型的第一层卷积神经网络中进行校准,获取包括候选质子信号窗口的信号图像；将校准后的信号图像输入至第二层卷积神经网络中进行再次校准,得到进一步校准后的信号图像；将进一步校准后的信号图像输入至浓度测量模型的第三层卷积神经网络中,得到包括质子信号定位的图像；计算包括质子信号定位的图像中的质子的数量,完成对氡气浓度的检测。本申请解决了现有方法中固有噪声和质子信号难以区分的技术问题。(The application discloses a method, a system and equipment for measuring radon radiation concentration by CR-39, comprising the following steps: acquiring a signal image of the CR-39 sample; inputting the signal image into a first layer of convolutional neural network of a concentration measurement model for calibration, and acquiring a signal image comprising a candidate proton signal window; inputting the calibrated signal image into a second layer of convolutional neural network for recalibration to obtain a further calibrated signal image; inputting the signal image after further calibration into a third layer of convolutional neural network of the concentration measurement model to obtain an image including proton signal positioning; and calculating the quantity of protons in the image including the proton signal positioning to finish the detection of the radon gas concentration. The method solves the technical problem that the intrinsic noise and the proton signals are difficult to distinguish in the existing method.)

1. A CR-39 method for measuring radon radiation concentration, comprising:

acquiring a signal image of the CR-39 sample;

inputting the signal image into a first layer of convolutional neural network of a concentration measurement model for calibration, and acquiring the signal image comprising a candidate proton signal window;

inputting the signal image comprising the candidate proton signal window into a second layer of convolutional neural network of the concentration measurement model for recalibration to obtain a further calibrated signal image comprising the candidate proton signal window;

inputting the further calibrated signal image comprising the candidate proton signal window into a third layer of convolutional neural network of the concentration measurement model to obtain an image comprising proton signal positioning;

and calculating the quantity of protons in the image including the proton signal positioning to finish the detection of the radon gas concentration.

2. The method for measuring radon radiation concentration as set forth in claim 1, wherein said inputting said signal image into a first layer of convolutional neural network of concentration measurement model for calibration, and obtaining said signal image including candidate proton signal window specifically comprises:

inputting the signal image into a first layer of convolutional neural network of the concentration measurement model, obtaining a candidate proton signal window and a boundary frame regression vector, and calibrating the candidate proton signal window by using the boundary frame regression vector to remove the overlapped candidate proton window, so as to obtain a calibrated signal image comprising the candidate proton signal window.

3. The method for CR-39 measurement of radon radiation concentration as defined in claim 2, wherein said inputting said signal image containing candidate proton signal window into said second layer convolutional neural network of said concentration measurement model for recalibration, and obtaining further calibrated signal image containing candidate proton signal window is specifically:

and inputting the signal image comprising the candidate proton signal window into a second layer of convolutional neural network of the concentration measurement model, and calibrating the candidate proton signal window by using the bounding box regression vector to obtain a further calibrated signal image comprising the candidate proton signal window.

4. The method of claim 1, wherein said first convolutional neural network comprises a convolutional layer, a pooling layer and a fully-connected layer connected in sequence, wherein the size of said convolutional layer is 3 x 3, and said convolutional layer and said fully-connected layer are followed by a RE L U function respectively as a non-linear excitation function.

5. The method of claim 1, wherein said second convolutional neural network comprises two convolutional layers and a fully-connected layer connected in series, wherein the size of said convolutional layer is 3 x 3, and said convolutional layers and said fully-connected layer are followed by RE L U functions respectively as non-linear excitation functions.

6. The method of claim 1, wherein said third convolutional neural network comprises three convolutional layers, pooling layers and fully-connected layers connected in sequence, wherein the size of said convolutional layers is 3 x 3, and said convolutional layers, pooling layers and fully-connected layers are followed by RE L U functions respectively as non-linear excitation functions.

7. A system for measuring radon radiation concentration in a CR-39, comprising:

the signal acquisition module is used for acquiring a signal image of the CR-39 sample;

the first image calibration module is used for inputting the signal image into a first layer of convolutional neural network of the concentration measurement model for calibration to obtain the signal image comprising a candidate proton signal window;

the second image calibration module is used for inputting the signal image comprising the candidate proton signal window into a second layer of convolutional neural network of the concentration measurement model for recalibration to obtain a further calibrated signal image comprising the candidate proton signal window;

the proton signal positioning module is used for inputting the signal image which is subjected to further calibration and comprises a candidate proton signal window into a third layer of convolutional neural network of the concentration measurement model to obtain an image comprising proton signal positioning;

and the concentration calculation module is used for calculating the number of protons in the image including the proton signal positioning to finish the detection of the radon gas concentration.

8. The CR-39 system for measuring radon radiation concentration as in claim 7, wherein said first image calibration module is further configured to:

9. The CR-39 system for measuring radon radiation concentration as in claim 7, wherein said second image calibration module is further configured to:

and inputting the signal image comprising the candidate proton signal window into a second layer of convolutional neural network of the concentration measurement model, and calibrating the candidate proton signal window by using a bounding box regression vector to obtain a further calibrated signal image comprising the candidate proton signal window.

10. A CR-39 radon radiation concentration measuring device, said device comprising a processor and a memory:

the memory is used for storing program codes and transmitting the program codes to the processor;

the processor is configured to execute the method of CR-39 of any one of claims 1-6 for measuring radon radiation concentration in accordance with instructions in the program code.

Technical Field

The application relates to the technical field of radon gas concentration measurement, in particular to a method, a system and equipment for measuring radon gas radiation concentration by CR-39.

Background

The harm of radon and its decay daughter to human health is mainly related to the concentration of radon in indoor environment and the length of time that people stay in the room, that is, the exposure concentration and the exposure time. The radon exists in the indoor air (the outdoor condition is also the same), the upper limit value of the indoor radon concentration means the radon concentration range of the indoor air where people live and are not harmed by radon for a lifetime, and the value is generally 70-150 Bq m < -3 >. If the radon concentration in the room exceeds the upper limit value, measures are taken when the radon concentration reaches the action value. The mobility value of radon concentration in the chamber is generally 150-400 Bq m-3. Therefore, it is one of the requirements to measure the radon gas concentration and judge whether the environment can live.

Disclosure of Invention

The application provides a method, a system and equipment for measuring radon radiation concentration by CR-39, which solve the technical problem that inherent noise and proton signals are difficult to distinguish.

In view of the above, the present application provides, in a first aspect, a method for measuring radon radiation concentration by CR-39, the method comprising:

acquiring a signal image of the CR-39 sample;

and calculating the quantity of protons in the image including the proton signal positioning to finish the detection of the radon gas concentration.

Optionally, the inputting the signal image into the first layer of convolutional neural network of the concentration measurement model for calibration, and the obtaining the signal image including the candidate proton signal window specifically includes:

Optionally, the inputting the signal image including the candidate proton signal window into the second layer of convolutional neural network of the concentration measurement model for recalibration, and obtaining the further calibrated signal image including the candidate proton signal window specifically includes:

Optionally, the first convolutional neural network comprises a convolutional layer, a pooling layer and a fully-connected layer which are connected in sequence, the size of the convolutional layer is 3 × 3, and an RE L U function is used as a nonlinear excitation function after the convolutional layer and the fully-connected layer respectively.

Optionally, the second convolutional neural network comprises two convolutional layers and a fully-connected layer which are sequentially connected, the size of each convolutional layer is 3 × 3, and an RE L U function is used as a nonlinear excitation function after each convolutional layer and each fully-connected layer.

Optionally, the third convolutional neural network comprises three convolutional layers, a pooling layer and a fully-connected layer which are connected in sequence, the size of each convolutional layer is 3 × 3, and an RE L U function is used as a nonlinear excitation function after each convolutional layer, each pooling layer and each fully-connected layer are connected in sequence.

In a second aspect, the present application provides a system for CR-39 measurement of radon radiation concentration, said system comprising:

the signal acquisition module is used for acquiring a signal image of the CR-39 sample;

and the concentration calculation module is used for calculating the number of protons in the image including the proton signal positioning to finish the detection of the radon gas concentration.

Optionally, the first image calibration module is specifically configured to:

Optionally, the second image calibration module is specifically configured to:

A third aspect of the present application provides a CR-39 device for measuring radon radiation concentration, the device comprising a processor and a memory:

the memory is used for storing program codes and transmitting the program codes to the processor;

the processor is configured to perform the steps of the method for measuring radon radiation concentration as described above in relation to the CR-39 according to the first aspect, in accordance with instructions in the program code.

According to the technical scheme, the method has the following advantages:

the application provides a method for measuring radon radiation concentration by CR-39, which comprises the steps of acquiring a signal image of a CR-39 sample; inputting the signal image into a first layer of convolutional neural network of a concentration measurement model for calibration, and acquiring a signal image comprising a candidate proton signal window; inputting the signal image comprising the candidate proton signal window into a second layer of convolutional neural network of the concentration measurement model for recalibration to obtain a further calibrated signal image comprising the candidate proton signal window; inputting the signal image which is further calibrated and comprises the candidate proton signal window into a third layer of convolutional neural network of the concentration measurement model to obtain an image comprising proton signal positioning; and calculating the quantity of protons in the image including the proton signal positioning to finish the detection of the radon gas concentration.

The intrinsic noise and the proton signals in the CR-39 sample are distinguished by adopting the trained convolutional neural network model, and the accurate signal image comprising the proton signals is obtained through multiple times of calibration, so that the screening of protons is completed, a calculator does not need to distinguish and calculate the intrinsic noise and the proton signals through naked eyes, and the accuracy and the efficiency of radon gas concentration measurement are improved.

Drawings

FIG. 1 is a flowchart of a method of one embodiment of the present invention for CR-39 to measure radon radiation concentration;

FIG. 2 is a block diagram of a system for measuring radon radiation concentration in accordance with one embodiment of the present invention, which is a CR-39 system;

FIG. 3 is a schematic diagram of a concentration measurement model in an embodiment of the method for measuring radon radiation concentration by CR-39 according to the present invention.

Detailed Description

In order to make the technical solutions of the present application better understood, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, 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 application.

For a better understanding of the present application, please refer to fig. 1, in which fig. 1 is a flowchart of a method of an embodiment of the present application for measuring radon radiation concentration by CR-39, comprising:

101. signal images of the CR-39 sample were acquired.

It should be noted that many micro bubbles and defects are formed inside the CR-39 sample, and the noise generated by these bubbles and defects after etching is called intrinsic noise. Therefore, the signal image of the CR-39 sample was taken to include the proton signal as well as the intrinsic noise signal.

102. And inputting the signal image into a first layer of convolutional neural network of a concentration measurement model for calibration, and acquiring the signal image comprising a candidate proton signal window.

It should be noted that, in the present application, the concentration measurement model is a trained model, and the training process is to train using a large number of signal images of CR-39 samples and extract the features of proton signals, so as to obtain a concentration measurement model capable of accurately distinguishing the proton signals from the intrinsic noise signals.

The concentration measurement model may be a multi-layered convolutional neural network structure. In one specific embodiment, a three-layer convolutional neural network structure is adopted, which can be used for calibrating a proton signal window in a first layer convolutional neural network structure, and obtaining a calibrated signal image comprising the proton signal window.

In a specific embodiment, the first convolutional neural network structure comprises a convolutional layer, a pooling layer and a fully-connected layer which are connected in sequence, the size of the convolutional layer is 3 × 3, and the RE L U function is used as the nonlinear excitation function after the convolutional layer and the fully-connected layer respectively, as shown in fig. 3 in particular.

The process of inputting the signal image into the first layer of convolutional neural network of the concentration measurement model specifically includes obtaining a candidate proton signal window and a boundary box regression vector, and calibrating the candidate proton signal window by using the boundary box regression vector to remove the overlapped candidate proton window, so as to obtain a calibrated signal image including the candidate proton signal window.

103. And inputting the signal image comprising the candidate proton signal window into a second layer of convolutional neural network of the concentration measurement model for recalibration to obtain a further calibrated signal image comprising the candidate proton signal window.

It should be noted that the second layer of convolutional neural network may be used to recalibrate the signal image obtained after calibration of the first layer of convolutional neural network, so as to obtain a more accurate signal image including the proton signal.

In a specific embodiment, the second convolutional neural network comprises two convolutional layers and a fully-connected layer which are connected in sequence, the size of each convolutional layer is 3 × 3, and the RE L U function is used as the nonlinear excitation function after each convolutional layer and the fully-connected layer, and a specific schematic diagram is shown in fig. 3.

The specific process of inputting the signal image including the candidate proton signal window into the second layer convolutional neural network of the concentration measurement model includes calibrating the candidate proton signal window by using the bounding box regression vector to obtain a further calibrated signal image including the candidate proton signal window.

104. And inputting the signal image which is further calibrated and comprises the candidate proton signal window into a third layer of convolutional neural network of the concentration measurement model to obtain an image comprising proton signal positioning.

It should be noted that the third layer of convolutional neural network can specifically locate the proton signal, so as to obtain a highly accurate signal image including the proton signal, so that an easily distinguishable proton signal can be obtained.

In a specific embodiment, the third convolutional neural network comprises three convolutional layers, pooling layers and fully-connected layers which are connected in sequence, the size of each convolutional layer is 3 x 3, and the RE L U function is used as the nonlinear excitation function after each convolutional layer, pooling layer and fully-connected layer.

And specifically, the process of inputting the signal image after further calibration into the third layer of the convolutional neural network of the concentration measurement model comprises the steps of calibrating a candidate proton signal window by using a bounding box regression vector, removing an overlapped candidate window to obtain a signal image of a precisely positioned proton signal, calculating the number of the proton signals in the signal image, and completing measurement of the radon concentration.

The above is an embodiment of the method for measuring radon radiation concentration by CR-39 in the present application, and the present application further includes an embodiment of a system for measuring radon radiation concentration by CR-39, specifically as shown in fig. 2, including:

and a signal acquisition module 201 for acquiring a signal image of the CR-39 sample.

And a first image calibration module 202, configured to input the signal image into a first layer of convolutional neural network of the concentration measurement model for calibration, and acquire a signal image including a candidate proton signal window.

And the second image calibration module 203 is configured to input the signal image including the candidate proton signal window into a second layer of convolutional neural network of the concentration measurement model for recalibration, so as to obtain a further calibrated signal image including the candidate proton signal window.

And a proton signal positioning module 204, configured to input the further calibrated signal image including the candidate proton signal window into a third layer of convolutional neural network of the concentration measurement model, so as to obtain an image including proton signal positioning.

And a concentration calculation module 205, configured to calculate the number of protons in the image including the proton signal localization, and complete detection of radon gas concentration.

Specifically, the first image calibration module 201 is specifically configured to:

inputting the signal image into a first layer of convolutional neural network of a concentration measurement model, obtaining a candidate proton signal window and a boundary frame regression vector, and calibrating the candidate proton signal window by using the boundary frame regression vector to remove the overlapped candidate proton window, thereby obtaining a calibrated signal image comprising the candidate proton signal window.

The second image calibration module 202 is specifically configured to:

The application also provides an embodiment of the device for measuring radon radiation concentration by CR-39, which comprises a processor and a memory, wherein the processor comprises: the memory is used for storing the program codes and transmitting the program codes to the processor; the processor is configured to execute, in accordance with instructions in the program code, an embodiment of a method for CR-39 of measuring radon radiation concentration in the present application.

It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.

The terms "first," "second," "third," "fourth," and the like in the description of the application and the above-described figures, if any, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the application described herein are, for example, capable of operation in sequences other than those illustrated or otherwise described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.

It should be understood that in the present application, "at least one" means one or more, "a plurality" means two or more. "and/or" for describing an association relationship of associated objects, indicating that there may be three relationships, e.g., "a and/or B" may indicate: only A, only B and both A and B are present, wherein A and B may be singular or plural. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship. "at least one of the following" or similar expressions refer to any combination of these items, including any combination of single item(s) or plural items. For example, at least one (one) of a, b, or c, may represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", wherein a, b, c may be single or plural.

In the several embodiments provided in the present application, it should be understood that the disclosed system and method may be implemented in other ways. For example, the above-described system embodiments are merely illustrative, and for example, the division of the modules is only one logical division, and other divisions may be realized in practice, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.

The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present application may be substantially implemented or contributed to by the prior art, or all or part of the technical solution may be embodied in a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

The above embodiments are only used for illustrating the technical solutions of the present application, and not for limiting the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions in the embodiments of the present application.

11页详细技术资料下载

上一篇：一种医用注射器针头装配设备

下一篇：一种利用虚拟仪器技术实现γ-γ数字符合测量的系统及方法

Method, system and equipment for measuring radon radiation concentration by CR-39

相关技术

网友询问留言