Context: Neural Network (NN) algorithms have been successfully adopted in a number of Safety-Critical Cyber-Physical Systems (SCCPSs). Testing and Verification (T&V) of NN-based control software in safety-critical domains are gaining interest and attention from both software engineering and safety engineering researchers and practitioners. Objective: With the increase in studies on the T&V of NN-based control software in safety-critical domains, it is important to systematically review the state-of-the-art T&V methodologies, to classify approaches and tools that are invented, and to identify challenges and gaps for future studies. Method: By searching the six most relevant digital libraries, we retrieved 950 papers on the T&V of NN-based Safety-Critical Control Software (SCCS). Then we filtered the papers based on the predefined inclusion and exclusion criteria and applied snowballing to identify new relevant papers. Results: To reach our result, we selected 83 primary papers published between 2001 and 2018, applied the thematic analysis approach for analyzing the data extracted from the selected papers, presented the classification of approaches, and identified challenges. Conclusion: The approaches were categorized into five high-order themes: assuring robustness of NNs, assuring safety properties of NN-based control software, improving the failure resilience of NNs, measuring and ensuring test completeness, and improving the interpretability of NNs. From the industry perspective, improving the interpretability of NNs is a crucial need in safetycritical applications. We also investigated nine safety integrity properties within four major safety lifecycle phases to investigate the achievement level of T&V goals in IEC 61508-3. Results show that correctness, completeness, freedom from intrinsic faults, and fault tolerance have drawn most attention from the research community. However, little effort has been invested in achieving repeatability; no reviewed study focused on precisely defined testing configuration or on defense against common cause failure.
Purpose
Numerically analyzed the flow characteristic and explored the hydrodynamic mechanism of the pump mode hump district formation of a Francis pump-turbine.
Design/methodology/approach
Numerical simulations were conducted of the entire pump-turbine flow passage under different discharge conditions by adopting the SST-CC turbulence model. The internal flow at hump district has been explained in detail combined with the model test in this paper. The unsteady flow and pressure fluctuation characteristics are analysed under five different discharge conditions in the hump and nearby region. The reason of the hump district formation is explored combined with the flow components hydraulic loss.
Findings
The large hydraulic loss, high relative peak-to-peak amplitudes and low dominant frequencies are on account of the disorganized internal flow condition. The formation of the hump district is concerned with the large hydraulic loss inside the draft tube, runner and guide vanes as there occurs secondary flow, backflow even vortex in the hump district. In addition, the low dominant frequencies at recording points inside the flow passage are always accompanied with the change of flow patterns and the spreading of the pressure fluctuations.
Originality/value
The analysis method of each flow components hydraulic loss combined with internal flow structure is adopted to explore the mechanism of pump mode hump characteristic. The flow characteristic and pressure pulse characteristics all correspond to the flow components hydraulic loss.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.