For multi-modular nuclear power plants under the scheme of multiple nuclear steam supply system (NSSS) modules driving a single steam turbine, the NSSS modules are coupled tightly with each other by the common turbine, giving more complex normal operation with respect to the single-modular plants. To limit the operation cost of multi-modular plants, one operator is assigned to monitor and control two or more modules, whose feasibility should be verified. Combined with the characteristics of multi-module control rooms and multi-module running tasks, this paper designs a comprehensive situation awareness measurement method that combines SART, NASA-TLX (NASA Task Load Index), and eye movement tracking methods. The SART, NASA-TLX, and gaze entropy are adopted to measure the operators’ SA, and a series of accident handling experiments are performed on a full-scale simulator to gain enough data for analysis. The operators’ eye trajectories on the human–machine interface (HMI) during the experiments are all recorded for calculating the gaze entropy. Both the SART and NASA-TLX scales are filled by the operators after finishing the experiments. The experiment results show that the difference in operators’ workload and SA amongst all the experimental scenarios is limited, even between the toughest and tenderest scenarios, indicating the feasibility of one operator driving two NSSS modules simultaneously.
Ensuring the safety of nuclear energy necessitates proactive measures to prevent the escalation of severe operational conditions. This article presents an efficient and interpretable framework for the swift identification of abnormal events in nuclear power plants (NPPs), equipping operators with timely insights for effective decision-making. A novel neural network architecture, combining Long Short-Term Memory (LSTM) and attention mechanisms, is proposed to address the challenge of signal coupling. The derivative dynamic time warping (DDTW) method enhances interpretability by comparing time series operating parameters during abnormal and normal states. Experimental validation demonstrates high real-time accuracy, underscoring the broader applicability of the approach across NPPs.
20 March 2014 in Science and Technology of Nuclear Installations
Integral type reactors may need to be grouped to produce as much energy as a utility demands due to the small electrical output of an individual reactor. Sharing of systems among modules at a nuclear plant site is economically beneficial. Operation of systems shared between modules in a multi-modular plant is an issue never met in current NPPs, which may impact human performance. A design of operation of the shared systems via a common control system is presented as a technical approach to solve the problem. Modules and shared systems are controlled in independent network domains, respectively. Different from current NPPs, a limitation of operation authorities corresponding to certain modules and shared systems is defined to minimize the operation confusion between modules by one operator and to minimize the operation confusion of shared systems by different operators. Different characteristics of the shared system are analyzed, and different operation and control strategies are presented. An example is given as an application of the operation strategies. The operation design of the multi-modular system is in the preliminary stage, and, as an concept design, more verification and validation is needed in further works.