Learning Device for Neutron Pulse Origin Inference
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Neutron measurement devices face erroneous detection of pulse signals originating from pile-up phenomena as neutrons, leading to unreliable nuclear reactor output monitoring due to the inability to distinguish between neutron and non-neutron signals in high-output regions.
Innovation Solution
A learning device is employed to generate a trained model that infers the origin of pulse signals using training data from neutron, gamma-ray, and alpha-ray detections, enabling accurate classification and exclusion of pile-up phenomenon signals as neutrons.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pulse height discrimination processing is used to remove noise signals, then the ability to distinguish neutron signals from non-neutron signals is improved, but pulse signals from pile-up phenomena are erroneously detected as neutron signals
Solution Approach 1:
The invention transitions from one-dimensional pulse height discrimination to two-dimensional analysis by incorporating both pulse height and pulse width characteristics. This dimensional expansion enables the system to distinguish between genuine neutron signals and pile-up phenomenon signals, which have different temporal profiles despite similar amplitudes, thereby resolving the contradiction between measurement precision and reliability
Solution Approach 2:
The invention changes the discrimination parameters from solely amplitude-based (pulse height) to include temporal characteristics (pulse width). By analyzing both the height and width parameters of pulse signals, the system can effectively differentiate between neutron-induced pulses and pile-up artifacts, maintaining high measurement precision while improving overall reliability
2Productivity
If the nuclear reactor output increases, then the measurement range is improved, but the generation frequency of pulse signals increases causing pile-up phenomenon
Solution Approach 1:
The invention performs preliminary analysis of pulse width characteristics before final neutron signal identification. By examining the temporal profile of each pulse signal in advance, the system can preemptively identify and exclude pile-up phenomenon signals even at high counting rates, maintaining reliable measurements across the full reactor output range
Solution Approach 2:
The invention dynamically adapts the signal discrimination criteria based on the observed pulse characteristics. By continuously analyzing both amplitude and temporal features, the system maintains effective noise rejection and pile-up identification across varying reactor power levels, ensuring reliable measurements from low to high output conditions
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The learning device effectively excludes erroneous neutron detections from pile-up phenomena, enhancing the accuracy of nuclear reactor output monitoring by correctly identifying the origin of pulse signals, thereby improving the reliability of neutron measurement.
Implementation Method 1
a nuclear fission ionization chamber, to detect a neutron
Implementation Method 2
a nuclear fission ionization chamber or a proportional counter
Data Source
AI summary
Provided is a learning device for excluding a case where a pulse signal originating from a pile-up phenomenon is erroneously detected as a neutron. This learning device is a learning device that obtains a trained model for inferring a pulse origin which is an origin of a pulse signal in a neutron measurement device using a pulse measurement method, and includes: a training data acquisition unit which acquires training data including a pulse signal outputted from a detector which is an ionization chamber or a proportional counter; and a model generation unit which generates a trained model for inferring the pulse origin from the pulse signal outputted from the detector, using the training data.Buchanan