An Innovative Deep Architecture for Flight Safety Risk Assessment Based on Time Series Data

With the development of the integration of aviation safety and artificial intelligence,research on the combination of risk assessment and artificial intelligence is particularly important in the field of risk management,but searching for an efficient and accurate risk assessment algorithm has become a challenge for the civil aviation industry.Therefore,an improved risk assessment algorithm(PS-AE-LSTM)based on long short-term memory network(LSTM)with autoencoder(AE)is proposed for the various supervised deep learning algorithms in flight safety that cannot adequately address the problem of the quality on risk level labels.Firstly,based on the normal distribution characteristics of flight data,a probability severity(PS)model is established to enhance the quality of risk assessment labels.Secondly,autoencoder is introduced to reconstruct the flight parameter data to improve the data quality.Finally,utilizing the time-series nature of flight data,a long and short-termmemory network is used to classify the risk level and improve the accuracy of risk assessment.Thus,a risk assessment experimentwas conducted to analyze a fleet landing phase dataset using the PS-AE-LSTMalgorithm to assess the risk level associated with aircraft hard landing events.The results show that the proposed algorithm achieves an accuracy of 86.45%compared with seven baseline models and has excellent risk assessment capability.

Construction and Application of Knowledge Graph for Quality and Safety Supervision of Transportation Engineering

Knowledge graph technology play a more and more important role in various fields of industry and academia.This paper firstly introduces the general framework of the knowledge graph construction,which includes three stages:information extraction,knowledge fusion and knowledge processing.In order to improve the efficiency of quality and safety supervision of transportation engineering construction,this paper constructs a knowledge graph by acquiring multi-sources heterogeneous data from supervision of transportation engineering quality and safety.It employs a bottom-up construction strategy and some natural language processing methods to solve the problems of the knowledge extraction for transportation engineering construction.We use the entity relation extraction method to extract the entity triples from the multi-sources heterogeneous data,and then employ knowledge inference to complete the edges in the constructed knowledge graph,finally perform quality evaluation to add the valid triples to the knowledge graph for updating.Subgraph matching technology is also exploited to retrieve the constructed knowledge graph for efficiently acquiring the useful knowledge about the quality and safety of transportation engineering projects.The results show that the constructed knowledge graph provides a practical and valuable tool for the quality and safety supervision of transportation engineering construction.

The Analysis of Human Behaviour and Evacuation in a Fire Situation in a Building for Higher Education

The paper presents the analysis of a human evacuation from a higher education building located in Iassy,Romania,by means of engineering techniques to approach fire safety.Because in Romania(as in other European countries)fire safety design of buildings is prescriptive and not performance-based,a fire safety engineering approach arouse great interest in many countries such as the U.S.A.,Australia,New Zealand,England,Sweden,Finland,etc.This paper is based on the assumption of starting a fire in the space of a hall for festivities,located on the ground floor of the building,near two human evacuation routes;We consider two building evacuation scenarios:two exits and,respectively,just one exit(assuming that the second would be accidentally blocked).

Analysis on evaluation ability of nonlinear safety assessment model of coal mines based on artificial neural network

Based on the integration analysis of goods and shortcomings of various methods used in safety assessment of coal mines, combining nonlinear feature of mine safety sub-system, this paper establishes the neural network assessment model of mine safety, analyzes the ability of artificial neural network to evaluate mine safety state, and lays the theoretical foundation of artificial neural network using in the systematic optimi- zation of mine safety assessment and getting reasonable accurate safety assessment result.

A New Safety Electric Initiating System

Based on the analysis of weakness on the safety of traditional electric detonators, a BJ-l safety electric detonator initiatingsystem and its corresponding safe examination technique were successfully developed. By leading false foot wires and taking advantageof the transmitting frequency band of Mo-Zn ferrite, detonators in this new system can completely impede the direct induction of outsidecrosstalk that may cause casual firing in the ordinary as well as eleclromagnetic ones. Possible causality by lightning was discussed. Results are presented, of its safety tests on resistance to direct and alternating current, electrostatic, and crosstalk induced by damp leakagein saturated salty water.

Research on Distribution Regularities of Dust Concentration and Granularity in Large Mining Height Working Face

The key for dust control of coal mine is to clarify the dust concentration distribution and sedimentation in different areas. Both similarity experiment and numerical simulation method have certain restrictions and are quite different from the actual situation on site. In order to study the dust sedimentation regularity of coal mine in large mining height, “filter membrane method” is adopted in this paper, i.e., to dry and weigh the filter membrane before and after sampling, collect the dust of respirable zone on mining face and calculate the dust concentration based on a main airway of 100 m. The result shows that: A large amount of dust will be produced during coal mining, wherein the maximum dust concentration from 6 m upstream to 100 m downstream of coal cutter is 121 mg/m3, while the minimum dust concentration is 61 mg/m3;The dust concentration in return airway is reduced with the distance increases, while the dust concentration at the entrance is 91 mg/m3;A large amount of dust may fall from roof during section advancing and improves the dust concentration of hydraulic support in walking area obviously;The dust granularity of mining face and return airway is 0 - 100 μm, but the amount of respirable dust is higher than 80%, the larger the dust particle size, the higher the dust concentration. Besides, dust in small particle size can be suspended in air flow for longer, but that in large particle size may subside under the action of gravity;To reduce dust exposure, the mining position shall be located in the windward direction of advancing or coal cutter. This research can provide guidance for taking dust prevention measures of working face in large mining height.

Modelling and Hazard Analysis for Contaminated Sediments Using STAMP Model and STPA Tool

The goal of this article is dual： first, introducing a new model of accident named STAMP （systems-theoretic accident modeling and processes）; then applying the model to an innovative process for the treatment of contaminated substances and the re-use of treated substances. This article is a demonstration for a need of a new tool to take into account hazards and safety within socio-technical systems.

The Seasickness as Marine Problem-Case Study

Motion sickness is one of the main reasons why travelling by sea becomes a bad memory for a number of people, mainly due to a nauseating symptom. The aim of this paper is to characterize a condition called seasickness that has affected many people from a mathematical and psychological point of view. Based on the mathematical characterization, an existing model will be reviewed and described. In the psychological aspects, a statistical study of two hundred and thirteen people was performed in order to provide a comprehensive view of the different psychological factors affecting the passengers. Motion sickness also impacts onboard safety, as it reduces the effectiveness and the operating capability of the crew when responding to hazardous situations.

Numerical Analysis of Surcharge Effect on Stability and Interaction Mechanism of Slope-Pile-Footing System

To investigate the stability and interaction mechanism of the slope-pile-footing system under surcharge effects,the finite difference method(FDM)was adopted to analyze the response laws of the stability of the reinforced slope,evolution of the critical slip surface,stress characteristic of retaining structures,deformation and failure modes of the slope foundation and building footing under surcharge parameters,including the surcharge intensity,the surcharge position,and the surcharge width.The results show that surcharge parameters significantly affect the stability and the deformation characteristics of the slope-pile-footing system.Specifically speaking,with the increasing surcharge intensity and the decreasing surcharge position and width,the deformation and failure mode of the system will gradually evolve in a direction that is harmful to its stability.The interaction mechanism of the slope-pile-footing system is further clarified as the load transfer of the building footing,the generation of the additional stress in the slope foundation,and the adjustment of pile bending moment due to the stress redistribution.Correspondingly,the safety of anti-slide piles will determine the stability of the slope foundation and building footing.These findings are expected to provide guidance for the comprehensive development and utilization of filled slopes after reinforcement.

A hazard analysis via an improved timed colored petri net with time–space coupling safety constraint

Petri nets are graphical and mathematical tools that are applicable to many systems for modeling, simulation, and analysis. With the emergence of the concept of partitioning in time and space domains proposed in avionics application standard software interface (ARINC 653), it has become difficult to analyze time–space coupling hazards resulting from resource partitioning using classical or advanced Petri nets. In this paper, we propose a time–space coupling safety constraint and an improved timed colored Petri net with imposed time–space coupling safety constraints (TCCP-NET) to fill this requirement gap. Time–space coupling hazard analysis is conducted in three steps: specification modeling, simulation execution, and results analysis. A TCCP-NET is employed to model and analyze integrated modular avionics (IMA), a real-time, safety-critical system. The analysis results are used to verify whether there exist time–space coupling hazards at runtime. The method we propose demonstrates superior modeling of safety-critical real-time systems as it can specify resource allocations in both time and space domains. TCCP-NETs can effectively detect underlying time–space coupling hazards. © 2016 Chinese Society of Aeronautics and Astronautics

Safety Analysis of Flow Parameters in a Rotor-stator Cavity

In order to ensure the safety of engine life limited parts （ELLP） according to airworthiness regulations, a numerical approach integrating one-way fluid structure interaction （FSI） and probabilistic risk assessment （PRA） is developed, by which the variation of flow parameters in a rotor-stator cavity on the safety of gas turbine disks is investigated. The results indicate that the flow parameters affect the probability of fracture of a gas turbine disk since they can change the distribution of stress and temperature of the disk. The failure probability of the disk rises with increasing rotation Reynolds number and Chebyshev number, but descends with increasing inlet Reynolds number. In addition, a sampling based sensitivity analysis with finite difference method is conducted to determine the sensitivities of the safety with respect to the flow parameters. The sensitivity estimates show that the rotation Reynolds number is the dominant variable in safety analysis of a rotor-stator cavity among the flow parameters.

Correction of Wave Surge Forces to Improve Surf-Riding/Broaching Vulnerability Criterion Check Accuracy

Surf-riding/broaching is one of the five stability failure modes to be included into the International Maritime Organization (IMO) second generation intact stability criteria (which are risk-based stability criteria) that can ensure the safety of ships in actual seaways more effectively. This study focuses on the influence of wave surge force prediction accuracy on surf-riding/broaching vulnerability criterion check result. Firstly, it is demonstrated that the wave surge force prediction method adopted in the current vulnerability criterion check procedure is not accurate and may lead to wrong conclusions. The experimental data from captive model test and the numerical result based on 3D panel method both indicate that the diffraction effect must be considered to correctly predict the wave surge forces. Besides, sophisticated methods are not suitable for Level 2 vulnerability criterion check due to their complexity. Therefore, an empirical formula for wave surge force correction based on sample ship calculation results is proposed. The proposed empirical correction formula can effectively improve the vulnerability criterion check accuracy and thus contribute to the design and safety of the ships which are vulnerable to this stability failure mode. © 2017, Shanghai Jiaotong University and Springer-Verlag GmbH Germany.