546 results about "Nuclear radiation" patented technology

The invention discloses a nuclear radiation index early warning system based on multi-algorithm fusion, and the system comprises an environment data collection module which is used for collecting gamma-ray dose rate data, wind speed data, wind direction data and geographic position information, and constructing a nuclear radiation environment data set; the dose rate prediction module is used for predicting a future change trend of gamma ray dose rate data based on a sparse recurrent neural network model; the anomaly detection module is used for identifying an abnormal mutation point and positioning the position of a high-risk sensor; the diffusion region modeling module is used for calculating a nuclear radiation diffusion influence region; the grid risk evolution module is used for simulating time sequence evolution of a regular grid risk state based on the multi-state cellular automaton; and the fusion judgment module is used for fusing output results and generating a final early warning grade and a spatial risk distribution result. According to the invention, accurate prediction of the nuclear radiation risk and dynamic space early warning are realized, and the early warning accuracy and response efficiency are significantly improved.

The invention relates to the technical field of unmanned aerial vehicle-mounted nuclear radiation detection, and provides an unmanned aerial vehicle-mounted nuclear radiation detection method and system based on deep learning, and the method comprises the steps: collecting a gamma energy spectrum signal, and carrying out the digitization of the gamma energy spectrum signal, and obtaining original energy spectrum data; preprocessing the original energy spectrum data to obtain preprocessed energy spectrum data; constructing a nuclide identification model based on a deep learning network, and performing nuclide identification on the preprocessed energy spectrum data to obtain an original nuclide identification result; performing post-processing analysis and refinement on the original nuclide identification result to obtain a nuclide identification result; and fusing the nuclide identification result with the geographic position information to obtain a nuclear radiation pollution distribution diagram, and setting a multi-level early warning mechanism based on nuclide types and intensity. According to the invention, the precision of nuclide identification in a complex environment is improved, and high-sensitivity detection of various nuclides under the condition of low signal-to-noise ratio is realized.

The invention discloses an intelligent nuclear radiation dose real-time monitoring system based on deep learning, and the system comprises the steps: S1, a multi-mode sensing module which is used for outputting radiation intensity data with timestamps, environment image data and geographic space position information; s2, a preprocessing module used for outputting a structured feature sequence; s3, a fusion modeling module which is used for generating a unified fusion feature vector; s4, an end-edge reasoning module which is used for processing the fusion feature vector in stages and generating a nuclear radiation dose prediction result; s5, the task scheduling module is used for dynamically determining whether the reasoning task is executed on the end side or the edge node; s6, an anomaly detection module which is used for determining whether there is an abnormal change of the nuclear radiation dose; and S7, the system control module is used for coordinating the modules. The method has the advantages of being high in environmental adaptability, fast in reasoning response and high in anomaly recognition precision.

The invention belongs to the technical field of nuclear radiation measurement, and relates to a liquid flash TDCR multi-nuclide beta spectrum analysis method and system based on artificial intelligence. The method comprises the following steps: constructing a numerical model of a liquid flash detector spectrometer by using a Monte Carlo technology to simulate the energy spectrum response of a single nuclide under different quenching conditions; constructing a training database by adopting a parameterized data synthesis algorithm; constructing a multi-task mixed spectrum analysis neural network model; carrying out model training by utilizing the constructed database; and inputting an actual measurement spectrogram, and outputting the multi-nuclide absolute activity, the detector efficiency and the decomposition energy spectrum contribution curve in real time by using the trained neural network model. According to the method, differential distribution characteristics and quenching response curve characteristics of the beta continuous energy spectrum are creatively fused, a neural network architecture with physical mechanism constraints is constructed, and liquid flash TDCR multi-nuclide energy spectrum characteristic decoupling and accurate activity solving are achieved under the unknown quenching condition.

The invention relates to the technical field of nuclear radiation imaging, in particular to a radiation array detector, a back scattering imaging system and a back scattering imaging method. The radiation array detector comprises an X-ray photon absorption structure which comprises high-strip-shaped scintillators and low-strip-shaped scintillators which are alternately arranged, the high-strip-shaped scintillators are used for detecting back scattering X-ray photons incident at all angles, the low-strip-shaped scintillators are used for accurately determining the incident direction of the X-ray photons through the collimation effect, and the high-strip-shaped scintillators and the low-strip-shaped scintillators are used for detecting the incident direction of the back scattering X-ray photons; after X-rays enter the photon absorption structure, the high-strip-shaped scintillators and / or the low-strip-shaped scintillators receiving X-ray photons generate scintillation photons. The silicon photomultiplier array is connected with the high strip-shaped scintillator and the low strip-shaped scintillator through a light guide and is used for converting scintillation photons into photoelectric signals; and the position and energy information coding circuit is used for carrying out position and energy information coding on the photoelectric signals generated by the silicon photomultiplier array. According to the invention, the detection efficiency and the direction identification capability of the back scattering X-ray can be effectively improved.

The invention provides a nuclear radiation diffusion analysis method based on a Gaussian mixture atmospheric diffusion model. The method comprises the steps that nuclear facility source item parameters are acquired; integrating meteorological, geography, remote sensing and radiation monitoring data by using a heterogeneous data fusion engine, extracting atmospheric turbulence, terrain and building interference characteristics and source item parameters, and forming a dynamic input parameter set; constructing an unsteady state diffusion model containing a multi-modal distribution function, processing features, obtaining a mixed distribution model, and correcting the mixed distribution model; predicting spatial and temporal distribution of radiation pollutants, and generating multi-scale diffusion field simulation; and optimizing a diffusion path, and generating a three-dimensional risk field. According to the method, multi-source data are integrated, an unsteady state diffusion model is constructed, Gaussian component weights are dynamically adjusted, the model is corrected by using real-time data, and a geographic information system is coupled to carry out spatial constraint optimization. And through multi-scale feature coupling, dynamic parameter adjustment and geographic space constraint correction, the depicting capability of the atmospheric diffusion model is remarkably improved, and the nuclear radiation diffusion prediction precision is greatly improved.

The embodiment of the invention relates to the field of exploration or detection by applying nuclear radiation, in particular to a method for determining a uranium metallogenic area of a to-be-surveyed area, which comprises the following steps of: determining natural gamma logging data and energy spectrum logging uranium content data of the to-be-surveyed area; determining the positions of a plurality of drill holes of the to-be-surveyed area; obtaining a rock core sample of one of the determined drill holes; determining uranium contents at different depths according to the rock core sample; determining the relationship between the uranium content and the energy spectrum logging uranium content data of the drill hole and the relationship between the energy spectrum logging uranium content data and the natural gamma logging data so as to determine the relationship between the uranium content and the natural gamma logging data; and determining a natural gamma logging threshold value of the uranium metallogenic area so as to determine the uranium metallogenic area of the area to be surveyed. According to the method provided by the embodiment of the invention, the natural gamma logging threshold value of the uranium metallogenic area can be accurately determined, so that the uranium metallogenic area of the area to be surveyed can be accurately determined, and the exploration cost is greatly reduced.

The invention discloses a method for selecting and triggering gamma instant radiation pulse events, and belongs to the technical field of nuclear radiation detection. The method comprises the following steps: carrying out normalization preprocessing on an original gamma pulse radiation time spectrum; s time-frequency transformation is carried out on the preprocessed data, and time-frequency features are extracted; optimizing parameters of the frequency threshold and the amplitude threshold after S time-frequency transformation by adopting a deep reinforcement learning model to obtain an optimal frequency threshold and an optimal amplitude threshold; performing filtering processing on the signal of the S time-frequency conversion result, and separating noise from an effective signal; and searching a pulse radiation event for the filtered signal by applying a morphology-based peak searching method, and positioning the position and the characteristic of a real gamma instant radiation pulse event. According to the method, time-frequency analysis is carried out through S time-frequency transformation, the problem that the frequency of an analysis window cannot be adjusted through short-time window Fourier transformation is solved, the method has better frequency resolution and phase retention characteristics, and gamma pulse signal characteristics can be represented more accurately.

The invention discloses a fast thermal neutron and gamma ray multi-mode detector, and relates to the technical field of nuclear radiation detection, and the detector comprises a detector housing, and the interior of the detector housing is connected with a fast neutron detection unit, a thermal neutron detection unit and a gamma ray detection unit. The gamma ray detection unit is located between the fast neutron detection unit and the thermal neutron detection unit; and an insulating separation unit is connected between two adjacent detection units. The detector can detect fast neutrons, thermal neutrons and gamma rays in the same equipment at the same time, structures such as a cadmium thermal neutron shielding layer and a fast neutron moderation layer do not need to be added, the size of the detector can be greatly reduced, and the detector has the advantages of being compact in structure, stable in performance, wide in energy measurement range, wide in fluence rate measurement range and the like. The ultrahigh-energy high-flux neutron measurement with the neutron energy at least covering # imgabs0 # and the neutron fluence rate at least covering # imgabs1 # can be realized.

The invention discloses a nuclear radiation resistant heat-insulating protective coating for steam pipelines and a preparation method thereof. The coating comprises a surface layer and a bottom layer; the surface layer comprises 30 to 50 parts of a surface layer base, 10 to 30 parts of pigments and fillers, 5-10 parts of metal powder, 18 to 20 parts of a curing agent and 18 to 20 parts of a diluent; the bottom layer comprises 10 to 30 parts of a bottom layer base, 30 to 50 parts of pigments and fillers, 5-10 parts of metal powder, 18 to 20 parts of a curing agent and 18 to 20 parts of a diluent; wherein the surface layer base comprises acrylic modified organic silicon resin; the bottom layer base comprises water glass; the pigments and fillers comprise enamel powder, ceramics and auxiliary fillers; the auxiliary fillers comprise one or more of mica, iron oxide, zinc titanate, fluoropolymer and borosilicate; the coating of the invention can effectively insulate and protect the steam pipeline in a high temperature and nuclear radiation environment, thereby extending the service life of the steam pipeline and improving the safety and reliability of the nuclear power plant.

The invention provides a radiation shielding multi-objective optimization design method based on a Bayesian neural network, and the method is characterized in that the method comprises the following steps: S1, obtaining sample data; s2, network construction and evaluation; s3, robust design optimization is carried out; according to the method, cognitive uncertainty in the modeling process of an agent model is quantified by using a loss function based on variational inference and KL divergence derivation, a nuclear radiation shielding calculation agent model considering uncertainty factors is obtained, and radiation shielding calculation is performed on an objective function in multi-objective optimization design through the constructed agent model. And a Pareto optimal solution set with certain robustness is obtained in combination with robust optimization design. According to the method, prior distribution is added to the weights of a neural network model, then the change conditions of the weights when data are given are obtained to measure the cognitive uncertainty in radiation shielding simulation, and the robustness of an optimization result is improved.

The invention belongs to the technical field of semiconductor detectors, and particularly relates to a whole process simulation method and system for response of a semiconductor nuclear radiation detector. According to the method, through cooperative operation of a detector working parameter setting module, a carrier transport simulation module and a detection system electronics response module, whole-process response prediction of the semiconductor detector from radiation interaction to electronics output can be realized under different carrier transport characteristics and device structure conditions; according to the method, the carrier drift process is simulated in a small-step iteration mode, accurate reconstruction of a carrier drift track can be synchronously achieved, CSA signals and main amplifier forming signals can be continuously generated in real time, simulation output of an energy spectrum is finally completed, and therefore core performance indexes of a detector are comprehensively reflected. The method is wide in applicable semiconductor material range and device structure, the main amplifier module type can be flexibly configured, the overall simulation process is simple, convenient and efficient, and the method has good universality and engineering application value.

The invention relates to the technical field of nuclear radiation detection management, and discloses a nuclear radiation detection management system based on artificial intelligence, comprising: a dynamic sensing module which detects nuclear radiation through quantum sensing to obtain radiation data, captures NV color center fluorescence intensity, analyzes to obtain gamma ray dose rate, constructs a nanoscale olfactory receptor simulation structure, and sends the radiation data to a control module; radioactive gas is detected and cooperatively monitored; the reasoning calculation module is used for analyzing space-time correlation based on radiation data, optimizing algorithm to accelerate result output, adjusting calculation complexity by calculating dynamic weight distillation, and correcting data transmission in real time; the decision management module is used for constructing a four-dimensional causal graph based on the radiation data, performing intervention simulation, evaluating a decision long-term effect, screening an optimal decision, and performing adversarial training based on historical repair case data; and the fusion cooperation module is used for establishing a cross-mechanism federated learning framework, carrying out hash operation on the radiation data, and establishing an NFT (Network Fourier Transform) on a block chain through an intelligent contract for query, verification and transaction.

The invention relates to an optical fiber coupling type focusable laser cutting device. According to the device, a laser transmitter transmits laser through an input optical fiber; the laser receiving module comprises a mounting seat, an optical fiber base, a transmission mechanism and a focusing mechanism, the focusing mechanism drives the optical fiber base to move in the axial direction through the transmission mechanism, and motor-free focusing in the nuclear radiation environment is achieved; the laser conduction module comprises a parabolic reflector for collimating and focusing the laser; according to the laser cutting device, the focusing technology depending on a motor in the prior art is converted into full-mechanical transmission focusing design, the failure risk of electronic elements such as the motor in the radiation environment is avoided, and through cooperation of the focusing mechanism, the transmission mechanism and the limiting pin, the laser cutting efficiency is improved. The high-precision and high-reliability focusing function is achieved, and the laser cutting device which is good in radiation resistance, high in long-term operation stability and long in service life is achieved in the nuclear radiation environment.

The invention provides a dynamic PSD threshold value correction method, device and equipment suitable for digital pulse waveform discrimination, and relates to the technical field of nuclear radiation detection.The method comprises the steps that a current PSD-energy two-dimensional spectrum is obtained through a nuclear radiation detecting instrument, counts in a target energy range in the current PSD-energy two-dimensional spectrum are removed, and the current PSD-energy two-dimensional spectrum is obtained; converting into a one-dimensional PSD spectrum by using a preset formula; determining the position of the maximum peak and the full width at half maximum in the one-dimensional PSD spectrum, determining a PSD threshold value, and resetting the target PSD value range according to the PSD threshold value; and obtaining the target PSD-energy two-dimensional spectrum again, carrying out statistics on the discrimination target ray counting value and the total counting value, and determining a main target ray counting value according to a difference value between the total counting value and the discrimination target ray counting value so as to determine a main target ray counting rate and a discrimination target ray counting rate. By regularly and automatically analyzing the PSD-energy two-dimensional spectrum and dynamically adjusting the PSD threshold value, different particles can be more accurately discriminated, and the particle detection accuracy and efficiency are improved.

The invention relates to the technical field of nuclear reactors, and provides a nuclear reactor piezoelectric sensor sensitive material optimization method and device and a medium, and the method comprises the steps: 1, determining an initial sensitive material sample based on a sensitive material template and an initial element doping scheme; 2, performing an irradiation experiment on the initial sensitive material sample, and determining irradiation parameters corresponding to the initial sensitive material sample based on an experiment result; 3, determining the average parameter change rate of the sample based on the irradiation parameters corresponding to the plurality of initial sensitive material samples and the high-temperature performance parameters corresponding to the plurality of initial sensitive material samples subjected to the irradiation experiment, and judging whether the average parameter change rate of the sample is smaller than a preset threshold value or not; if yes, determining the initial sensitive material sample as a target optimization sensitive material; and if not, adjusting the initial element doping scheme, and returning to the step 1. According to the embodiment, the piezoelectric coefficient of the piezoelectric sensitive material in a high-temperature nuclear radiation environment is improved, and the fault monitoring precision of key equipment of a nuclear reactor is improved.

The invention discloses a paper feeding device and method for a radioactive aerosol activity monitor, and belongs to the technical field of nuclear radiation measuring instruments. The device comprises a paper feeding case and perforated filter paper; a paper feeding power assembly and a filter paper supporting assembly are arranged in the paper feeding case, and the paper feeding power assembly comprises a main motor and an auxiliary motor; the filter paper supporting assembly comprises a first filter paper shaft and a second filter paper shaft; a photoelectric switch is arranged on the second filter paper shaft; the method comprises the following steps: 1, mounting filter paper; 2, feeding filter paper; and 3, paper feeding detection. Through a dual-motor mode, the perforated filter paper is synchronously controlled to move, and the fault that the filter paper slips or is stacked under the condition that a driven shaft is loosened under the condition of a single motor, or the filter paper is broken due to the fact that the motor pulls the filter paper under the fastening condition is solved; the unstable factors that under the condition of a traditional single motor, the tightness degree of the driven shaft cannot guarantee the standard performance of adjustment every time due to manual non-standard adjustment and the driven shaft can be gradually loosened and needs to be adjusted again can be directly removed, and the operation stability of the whole device is guaranteed.

The invention relates to the technical field of materials for anti-nuclear radiation clothes, in particular to ethylene propylene rubber for anti-nuclear radiation clothes and a preparation method of the ethylene propylene rubber. A composite multi-walled carbon nanotube subjected to pretreatment; an accelerant; a fiber; a plasticizer; an anti-aging agent; stearic acid; through an innovative raw material formula and a corresponding preparation process, the novel ethylene propylene rubber material for the nuclear radiation prevention clothing is mainly researched and developed. In the aspect of raw materials, the radiation shielding performance of the ethylene propylene rubber is remarkably improved by introducing the specially pretreated composite multi-walled carbon nanotubes and reasonably matching the nano zinc oxide. Meanwhile, the specific dosage ratio of the ethylene propylene rubber, the accelerant, the fiber, the plasticizer and other raw materials ensures that the product has excellent shielding performance and also has good weather resistance, flexibility and comfort.

The invention discloses a helium-bubble-induced numerical simulation method and system for performance degradation of a critical component material of an inspection and maintenance robot, and relates to the technical field of numerical simulation. Firstly, experimental data of the critical component material in a nuclear radiation environment are collected and analyzed, and an SRIM / TRIM simulation model is utilized to quantify initial conditions of irradiation damage; the method comprises the following steps of: firstly, acquiring key data, then simulating an atomic scale related process by means of LAMMPS molecular dynamics to obtain key data, then performing data conversion in Python to obtain equivalent porosity, and finally researching a material performance degradation rule through ABAQUS. Influences of various factors of helium bubbles on the material performance are comprehensively considered, and accurate prediction is achieved; through numerical simulation, the performance degradation condition of the material under different helium bubble sizes, numbers and dosage rates can be rapidly evaluated, and the evaluation efficiency is greatly improved. Meanwhile, the accuracy of a numerical simulation result is ensured through experimental verification, so that an evaluation result is more reliable.

The invention discloses a dose rate measurement method, device and equipment based on Poisson maximum likelihood estimation, and a storage medium, and the method comprises the steps: obtaining and preprocessing environment nuclear radiation monitoring data, and obtaining a fusion data sequence; dividing the fused data sequence into a plurality of time windows and determining an envelope spectrum sequence; performing radiation dose rate estimation on the envelope spectrum sequence through a Poisson maximum likelihood estimation method to obtain a preliminary dose rate estimation value; determining an environment correction factor according to the temperature data sequence, the humidity data sequence and the air pressure data sequence; correcting the initial dose rate estimation value to obtain a corrected dose rate estimation value; and inputting the corrected dose rate estimated value and the average dose rate and the maximum dose rate in each time window into a support vector machine model for prediction to obtain a future nuclear radiation dose rate prediction result, and updating the optimal estimated value of the dose rate in real time by introducing a Poisson maximum likelihood estimation algorithm. The accuracy and response speed of dose rate estimation are improved.

The invention discloses a convolutional neural network and multi-source data fusion-based nuclear radiation on-line monitoring method, which comprises the following steps of: acquiring laser radar point cloud data, a radiation dose rate and a radiation image of a monitoring area by adopting an unmanned aerial vehicle, and de-noising the radiation image by adopting a double-branch convolutional neural network; determining the track position of the unmanned aerial vehicle according to the laser radar point cloud and the de-noised image; performing space-time registration on the radiation dose rate and the track position of the unmanned aerial vehicle to form a data set, and obtaining a continuous radiation field of the monitoring area by adopting Kriging interpolation; according to the continuous radiation field, an L-BFGS-B algorithm is adopted to carry out minimization solution on a loss function with the radiation source position as an optimization variable, and position coordinates of the radiation source are obtained; performing data cleaning on the radiation dose in the continuous radiation field, and then performing multi-dimensional feature extraction to obtain a feature vector; and inputting the feature vectors into a plurality of prediction models to obtain a plurality of predicted radiation doses, and carrying out weighted fusion to obtain a predicted dose rate of the radiation source.

The invention discloses a portable thermoluminescence dosage device based on photon counting, and relates to the technical field of nuclear radiation detection equipment, the portable thermoluminescence dosage device comprises a shell, a rack, a heating module, a photon counting module and a movement module, and accurate measurement is realized through cooperation of multiple modules. In the motion module, a cam shaft, a rotating handle and a rolling bearing are matched to drive a heating cavity to drive a heating plate to move flexibly, and a guide hole of a heating supporting table guarantees moving stability. The dosage piece positioning plate accurately positions the dosage piece, the heating plate stably heats, and the reset spring buffers and assists the heating cavity in resetting, so that the device is ensured to run circularly. The filter group is accurately mounted and is matched with the sealing ring to isolate external interference, so that the detection accuracy of the photon sensor is improved, and the measurement precision is guaranteed. The device shell is provided with the display screen and the charging interface, data can be displayed in real time, charging is convenient, portability and practicability are enhanced, and the device is suitable for portable thermoluminescence dosage measurement in multiple scenes.

The invention discloses a radioactive waste liquid surface pollution multipoint array detection system and method, and relates to the technical field of nuclear radiation detection. The radioactive waste liquid surface pollution multipoint array detection system comprises a main body fixing frame, a mobile control device, a detector and an upper computer, a plurality of mounting holes arranged in a planar array are formed in the main body fixing frame; the movement control device controls the main body fixing frame to move; the plurality of detectors are mounted in the mounting holes of the main body fixing frame; the upper computer is used for regulating and controlling parameters of the CMOS sensor and storing, displaying, analyzing and processing frame images. The radioactive waste liquid storage tank liquid level pollution monitoring method is applied to a radioactive waste liquid surface pollution multipoint array detection system and is used for monitoring alpha and beta pollution areas of a radioactive waste liquid storage tank liquid level. The whole liquid level area of the radioactive waste liquid storage tank is covered at a time through the detachable detector group arranged in the plane array, and a pollution distribution panorama can be obtained through single-time measurement.

The invention relates to the technical field of nuclear radiation monitoring, in particular to an intelligent analysis system for nuclear radiation data, which comprises an acquisition planning module, a radiation intensity monitoring module, a sensor adjusting module, a radiation source positioning module and a radiation data processing module. According to the invention, the sensitivity and sampling frequency of the nuclear radiation sensor are intelligently adjusted by combining factors such as water flow velocity and temperature so as to cope with different environmental conditions and ensure the stability and accuracy of radiation data, and high-quality radiation monitoring data can be provided in a complex marine environment. Strong support is provided for accurate evaluation of a nuclear radiation source and analysis of the radiation quantity of marine products, the limitation of a traditional static monitoring technology is effectively overcome through real-time cooperation of the sensor and the unmanned ship, the response speed and precision of data acquisition are improved through continuous tracking and optimization of sensor configuration, nuclear pollution events can be rapidly coped with, and the real-time performance of the system is improved. And the radiation source position is updated in real time.

The invention relates to the technical field of data processing, and discloses a nuclear radiation sensor data processing method based on Kalman filtering and an alarm apparatus, and the method comprises the steps: continuously obtaining nuclear radiation observation data according to a preset sampling period; acquiring Kalman filtering observation data at a previous sampling moment, and predicting Kalman filtering observation data at a current sampling moment by using a preset Kalman filtering model according to the Kalman filtering observation data at the previous sampling moment to obtain a current prediction result; and correcting the current prediction result by using the observation data at the current sampling moment to obtain Kalman filtering observation data at the current sampling moment, and displaying the Kalman filtering observation data. According to the method, the dynamic system model is established based on the Kalman filter, the state at the current sampling moment is predicted based on the Kalman filtering observation data at the previous sampling moment, the evolution of the system state is accurately estimated in combination with the measurement data of the sensor, the dynamic change of the system is better coped with, and the accuracy and reliability of nuclear radiation detection are improved.

The invention discloses an energy spectrum analysis method based on sample migration, and relates to the technical field of nuclear radiation detection, and the method comprises the following steps: taking a large amount of simulated radionuclide gamma energy spectrum data obtained through a Monte Carlo numerical simulation method as a source domain; taking marked actually measured radionuclide gamma energy spectrum data obtained by measuring a radioactive source through a detector as a target domain; source domain and target domain samples with heterogeneous data distribution are mapped to a shared subspace with discriminative feature representation through feature alignment; aligning samples of a source domain and a target domain with tag space isomerism through tag alignment; and constructing a classification model of the low-count energy spectrum through tree decision. According to the method, effective expansion of the energy spectrum number is realized through data distribution and label space heterogeneous simulated energy spectrum data, and the strong dependence of a classification model on a large amount of actually measured annotated data can be reduced.

The invention discloses a nuclear pulse signal discrimination method and system, and belongs to the field of nuclear radiation detection.The nuclear pulse signal discrimination method comprises the steps that firstly, a nuclear pulse data set is constructed in two modes, one mode is that a simulated nuclear pulse generator is used for generating pulse signals for determining ray types, and the pulse signals are collected through an FPGA + ADC hardware system; secondly, Python software is used for simulating and generating pulses for determining ray types according to actual nuclear pulse signal characteristics; then, a CNN model is constructed based on the LeNet network, and a triple loss function is adopted for model training; and finally, similarity matching is carried out through measurement by means of feature vectors output by the neural network, and discrimination and classification of different types of nuclear pulse signals are realized. According to the method, the nuclear pulse signal features are automatically extracted through the deep metric learning model, the limitation of dependence on artificial feature extraction in a traditional method is overcome, the accuracy of nuclear pulse signal discrimination is improved, pulse signals generated by different types of rays can be effectively distinguished, and an efficient and reliable technical scheme is provided for nuclear radiation detection.

A nuclear radiation detector composed of a PMMA light guide comprises a PMMA light guide plate, a scintillator plate, an optical coupling silica gel layer and a photomultiplier, and is characterized in that the PMMA light guide plate and the scintillator plate are connected through the optical coupling silica gel layer, and the scintillator plate is arranged on the top surface of the PMMA light guide plate; an embedded groove is formed in the PMMA light guide plate; the photomultiplier is installed in the embedded groove and located on one side of the PMMA light guide plate, and an optical coupling silicone grease layer is arranged between the photomultiplier and the embedded groove; according to the device, light attenuation can be greatly reduced, far-end light collection is increased, overall consistency is improved, and alpha and beta detection efficiency is improved; the dead zone light loss can be reduced, the light collection efficiency is improved, the detection efficiency of the tail end is improved, the overall consistency is further improved, and the alpha and beta detection efficiency is further improved; according to the invention, the overall dimension of the detector assembly can be reduced, the distance from the detector assembly to the far end is also increased, the light collection efficiency is improved, and the overall consistency and the alpha-beta detection efficiency are further improved.

The invention discloses a preparation method of nuclear radiation protective clothing, and belongs to the technical field of nuclear radiation protection. The raw materials comprise, by weight, 80-100 parts of polyester chips, 15-29 parts of modified nanometer bismuth oxide, and 12-18 parts of tungsten boride. According to the prepared protective clothing, polyester serves as a base material, the comfort level is high, wrinkles are not prone to occurring, by adding tungsten boride and modified nanometer bismuth oxide, the protective clothing is endowed with excellent shielding performance, flame retardance and aging resistance, and the protective clothing is free of lead and toxicity and environmentally friendly; the weaving technology and the coating compounding technology are combined, the coating contains polypyrrole, the shielding performance of the protective clothing can be further improved, and in conclusion, the protective clothing has important application value in the technical field of nuclear radiation protection.

The invention discloses a nuclear radiation energy spectrum double-domain collaborative optimization method and a related device, and belongs to the technical field of nuclear radiation measurement, and the method comprises the steps: obtaining an original distortion pulse sequence generated by nuclear radiation measurement; a double-domain collaborative energy spectrum optimization model is constructed, the double-domain collaborative energy spectrum optimization model comprises a pulse domain repair model and an energy spectrum domain reconstruction model which are arranged in parallel, and the pulse domain repair model is used for performing pulse-by-pulse repair on the amplitude and the arrival time of the original distorted pulse sequence and outputting a repaired pulse sequence; the energy spectrum domain reconstruction model is used for converting the repaired pulse sequence into an energy spectrum diagram; in the training process of the double-domain collaborative energy spectrum optimization model, the pulse domain repair model and the energy spectrum domain reconstruction model share the back propagation gradient of the joint loss function, so that bidirectional closed-loop collaborative optimization of the pulse repair model and the energy spectrum reconstruction model can be realized, the problem of step-by-step error amplification caused by a traditional serial processing mode is avoided, and the performance of the system is improved. And the authenticity and the accuracy of the output energy spectrum are obviously improved.