In large-scale power plants such as nuclear and thermal power plants, thousands of sensors are installed to monitor the performance and health of the plant. However, it is difficult for operators to monitor all sensor values at all times. Therefore, Toshiba has developed a unique AI technology that comprehensively monitors thousands of sensor values and detects possible abnormalities earlier than humans. In a power plant, there are major fluctuations in sensor values during operation and minute fluctuations...
英字タイトル:
Development of anomaly detection system using AI Anomaly detection AI technology, two-stage autoencoder

In power plants, a large number of sensors are installed and the measured values are used to control and operate the plants. Although operators monitor the measured values for daily operation and maintenance, the number that can be visually confirmed is limited. So far, we have proposed two-stage autoencoder for anomaly detection. To evaluate its effectiveness, it and simple autoencoder as a comparison method were applied to the operational data of a power plant. As a result, deterioration of a thermometer ...
英字タイトル:
Development of Anomaly Detection System using AI (2) Evaluation of two-stage autoencoder using power plant data

New inspection system is supposed to be introduced in nuclear power plants in Japan. In the corrective action program (CAP) based on quality management system, sharing of nonconformity information, management of corrective and preventative action are required. For management of the corrective action, relevant data have to be correctly and efficiently recorded and managed. In order to address the new system, we developed a maintenance support tool using augmented reality (AR) technology. This tool helps user...
英字タイトル:
Development of a Maintenance Supporting Tool Using Augmented Reality Technology

New inspection system is supposed to be introduced in nuclear power plants in Japan. In the corrective action program (CAP) based on quality management system、 sharing of nonconformity information、management of corrective and preventative action are required. For management of the corrective action、relevant data have to be correctly and efficiently recorded and managed. In order to address the new system、we developed a maintenance support tool using augmented reality (AR) technology. This tool helps users i...
英字タイトル:
Development of a Maintenance Supporting Tool Using Augmented Reality Technology(2)

The current edition of “Guideline of Inspection and Evaluation for Reactor Internals issued by Japan Nuclear Safety Institute (JANSI) consists of inspection target, inspection method, and evaluation. Recently, the guideline is revised based on the safety function of the Reactor Internals, domestic operation experience, and the new knowledge. In this report, summary of “Guidelines of Inspection and Evaluation for Reactor Internals [Core Shroud] and [Shroud Support]....
英字タイトル:
Guideline for BWR Inspection Program Revision Policy of Guidelines for Core Shroud and Shroud Support

JSME シビアアクシデント時の構造健全性評価ガイドラインのうち BWR 鉄筋コンクリート製格納容器（RCCV）編について、RCCV のコンクリート部、ライナ部、鋼製耐圧部についての耐圧・耐漏えい性評価概要を記述する。 ...
英字タイトル:
Summary of Structural Integrity Evaluation Guideline under Severe Accident Condition (BWR Reinforced Concrete Containment)

When quasi-laminar defects are detected in the RPV shell, these defects are modeled to single circular crack with a diameter of 2a and an angle of ? from RPV wall enveloping these micro-defects like as the model used in the structural integrity assessment for Doel-3. An acceptable crack size is investigated for fracture assessment and initial crack size considering the fatigue crack growth by 60 years operation due to the JSME Fitness-for-Service (FFS) code. It was found that the initial crack with 2a of 4%...
英字タイトル:
Structural Integrity Assessment for Internal Crack in RPV Shell

Condition-based maintenance(CBM) is maintenance performed on the basis of the condition of the equipment. The transition to CBM being considered, it is necessary to make appropriate decision, such as judgment of normality or abnormality. The threshold approach has generally been used for the judgment, but it provides ambiguous decisions due to individual variability of the equipment. Diagnosis using Data Analysis is a promising method to detect variations of the condition of rotating machinery. In this meth...
英字タイトル:
Development of Diagnosis Method for Rotating Machinery by Data Analysis

Although a large amount of data (especially in abnormal conditions) is necessary to predict deterioration of nuclear power plant equipment, it is quite difficult to obtain it. For this reason, simulation is expected to be an effective approach to estimate conditions of equipment instead of data acquisition. In this study, we focused on and built a model for a motor operated valve, since the inspection cost is generally expensive due to the number of the valves used in a nuclear power plant. We analyzed the ...
英字タイトル:
Development of a Method for Predicting Deterioration of Plant Equipment -Simulating Deterioration Behavior of a Motor Operated Valve-

We verified that the eddy current testing (ECT) has the enough detectability for defects on the heat affected zone (HAZ) in welding of in-core monitor (ICM) housing inner surfaces for a special inspection involved in long-term operation. It is presumed that a detectability of ECT is decreased because a HAZ of ICM housing inner surfaces is deformed by welding. We conducted full-scale defect detection tests using the simulated ICM housing specimen with the welded part, the rotational ECT probe and the probe m...
英字タイトル:
Verification of Eddy Current Testing for In-Core Monitor Housing