One-Dimensional Convolutional Auto-Encoder for Predicting Furnace Blowback Events from Multivariate Time Series Process Data—A Case Study

Modern industrial mining and mineral processing applications are characterized by large volumes of historical process data. Hazardous events occurring in these processes compromise process safety and therefore overall viability. These events are recorded in historical data and are often preceded by characteristic patterns. Reconstruction-based data-driven models are trained to reconstruct the characteristic patterns of hazardous event-preceding process data with minimal residuals, facilitating effective event prediction based on reconstruction residuals. This investigation evaluated one-dimensional convolutional auto-encoders as reconstruction-based data-driven models for predicting positive pressure events in industrial furnaces. A simple furnace model was used to generate dynamic multivariate process data with simulated positive pressure events to use as a case study. A one-dimensional convolutional auto-encoder was trained as a reconstruction-based model to recognize the data preceding the hazardous events, and its performance was evaluated by comparing it to a fully-connected auto-encoder as well as a principal component analysis reconstruction model. This investigation found that one-dimensional convolutional auto-encoders recognized event-preceding patterns with lower detection delays, higher specificities, and lower missed alarm rates, suggesting that the one-dimensional convolutional auto-encoder layout is superior to the fully connected auto-encoder layout for use as a reconstruction-based event prediction model. This investigation also found that the nonlinear auto-encoder models outperformed the linear principal component model investigated. While the one-dimensional auto-encoder was evaluated comparatively on a simulated furnace case study, the methodology used in this evaluation can be applied to industrial furnaces and other mineral processing applications. Further investigation using industrial data will allow for a view of the convolutional auto-encoder’s absolute performance as a reconstruction-based hazardous event prediction model.

Intelligent methods for improving the accuracy of prediction of rare hazardous events in railway transportation

The paper Aims to examine various approaches to the ways of improving the quality of predictions and classification of unbalanced data that allow improving the accuracy of rare event classification. When predicting the onset of rare events using machine learning techniques, researchers face the problem of inconsistency between the quality of trained models and their actual ability to correctly predict the occurrence of a rare event. The paper examines model training under unbalanced initial data. The subject of research is the information on incidents and hazardous events at railway power supply facilities. The problem of unbalanced data is expressed in the noticeable imbalance between the types of observed events, i.e., the numbers of instances. Methods. While handling unbalanced data, depending on the nature of the problem at hand, the quality and size of the initial data, various Data Science-based techniques of improving the quality of classification models and prediction are used. Some of those methods are focused on attributes and parameters of classification models. Those include FAST, CFS, fuzzy classifiers, GridSearchCV, etc. Another group of methods is oriented towards generating representative subsets out of initial datasets, i.e., samples. Data sampling techniques allow examining the effect of class proportions on the quality of machine learning. In particular, in this paper, the NearMiss method is considered in detail. Results. The problem of class imbalance in respect to the analysis of the number of incidents at railway facilities has existed since 2015. Despite the decreasing share of hazardous events at railway power supply facilities in the three years since 2018, an increase in the number of such events cannot be ruled out. Monthly statistics of hazardous event distribution exhibit no trend for declines and peaks. In this context, the optimal period of observation of the number of incidents and hazardous events is a month. A visualization of the class ratio has shown the absence of a clear boundary between the members of the majority class (incidents) and those of the minority class (hazardous events). The class ratio was studied in two and three dimensions, in actual values and using the method of main components. Such “proximity” of classes is one of the causes of wrong predictions. In this paper, the authors analysed past research of the ways of improving the quality of machine learning based on unbalanced data. The terms that describe the degree of class imbalances have been defined and clarified. The strengths and weaknesses of 50 various methods of handling such data were studied and set forth. Out of the set of methods of handling the numbers of class members as part of the classification (prediction of the occurrence) of rare hazardous events in railway transportation, the NearMiss method was chosen. It allows experimenting with the ratios and methods of selecting class members. As the results of a series of experiments, the accuracy of rare hazardous event classification was improved from 0 to 70-90%.

Impact of Perceived Stress Safety Attitude and Flight Experience on Hazardous Event Involvement of Aviators

The pilots’ attitude and its influence on flying performance have an imperative bearing on flight safety. Recent studies suggest that attitude and stress correlate with flying performance and could be one of the many factors, which contribute to accidents or incidents. The objective of the current research was to study the relationship between aviation safety attitude, flight experience, perceived stress, and hazardous event involvement among aviators. The study also investigated whether aviation safety attitude, perceived stress, and flying experience predict the hazardous event involvement of aviators or not. It was hypothesised that less flying experience, perceived stress, and aviation safety attitude will predict the hazardous event involvement of aviators. The data was collected from 360 aviators by using the aviation safety attitude scale, hazardous event scale, and perceived stress scale. Correlation and regression analysis were used for analysing the obtained data. The findings of the study indicated that flight experience and safety attitude are significantly negatively correlated with hazardous event involvement and perceived stress is significantly positively associated with hazardous event involvement. In addition to this, aviation safety attitude, perceived stress, and flying experience were found to be strong predictors of hazardous event involvement. The findings of the study will help in building effective training programs as accidents can be prevented by improved pilot training involving perceived stress and attitude identification and management.

Inadvertent internal carotid artery (ICA) injury during transsphenoidal surgery: review of literature

Background Internal carotid artery (ICA) injury is a hazardous catastrophe for the skull base surgery team. We aimed to illustrate the vital joints in this hazardous event during endoscopic surgery. Main text The condition is rare (1.1%) but fatal per se. Working in the field of endoscopic surgery is not free of charges. It demands a thorough knowledge of anatomy, variations, and pathoanatomy to expect what can be seen thereafter. Once the injury occurs, one must have a quite clear plan to proceed. Marvelous bleeding is confusing not only in the field but also in the mind process. Conclusion Endoscope teams when expose to this event should think in a stepwise manner. In our review, we explained the pathoanatomy of the field after an injury, pre-conditions of injury, and how to avoid certain drawbacks during management.

Purchasing policy, quarantine and acclimation practices of breeding gilts in Belgian pig farms

Background The breeding population is very important in pig herds, for productivity, health and profitability. Replacement of breeding animals can be accomplished by own rearing of breeding gilts or by purchasing them. Purchasing breeding gilts is a hazardous event in terms of biosecurity and introduction of pathogens into a farm. However, in literature, little is known about gilt introduction in a herd. The present study investigated the introduction procedures of purchased breeding gilts in Belgian pig herds, and the compliance of these herds to the optimal introduction procedures. A questionnaire consisting of twenty questions related to farm characteristics (n = 2), purchasing policy (n = 6), quarantine period (n = 5), and acclimation practices (n = 7) was designed, and 68 farms completed the questionnaire during an on-farm interview. Results The median (min. – max.) number of sows on the farms was 300 (85–2500). Fifty-seven per cent of the farms purchased breeding gilts, and there was a lot of variation in the frequency of purchase and the age at which gilts are purchased. On 95 % of those farms, a quarantine unit was used, and on most of these farms the quarantine was located on the farm itself (internal quarantine). The median (min. – max.) duration of the quarantine period was 42 (14–140) days. The most common acclimation practice was vaccination against Porcine parvovirus (96 %) and Erysipelothrix rhusiopathiae (94 %), although in some farms exposure of gilts to farm-specific micro-organisms was done by providing faeces from suckling piglets (18 %) and bringing gilts in contact with sows that will be culled (16 %). Only 10 % of the farms complied with the optimal introduction procedures, i.e. purchasing policy, quarantine building and quarantine management. Conclusions This study showed that in many farms, practices related to purchasing, quarantine and acclimation could be improved to maintain optimal biosecurity.

Car drivers coping with hazardous events in real versus simulated situations: Declarative, behavioral and physiological data used to assess drivers’ feeling of presence

More than 1.3 million people lose their lives every year in traffic accidents. Improving road safety requires designing better vehicles and investigating drivers’ abilities more closely. Driving simulators are constantly being used for this purpose, but the question which often arises as to their validity tends to be a barrier to developments in this field. Here we studied the validity of a simulator, defined as how closely users’ behavior under simulated conditions resembles their behavior on the road, based on the concept of drivers’ feeling of presence. For this purpose, the driving behavior, physiological state and declarative data of 41 drivers were tested in the Sherpa2 simulator and in a real vehicle on a track while driving at a constant speed. During each trial, drivers had to cope with an unexpected hazardous event (a one-meter diameter gym ball crossing the road right in front of the vehicle), which occurred twice. During the speed-maintenance task, the simulator showed absolute validity, in terms of the driving and physiological parameters recorded. During the first hazardous event, the physiological parameters showed that the level of arousal (Low Heart Rate/High Heart Rate ratio x10) increased up to the end of the drive. On the other hand, the drivers’ behavioral (braking) responses were 20% more frequent in the simulator than in the real vehicle, and the physiological state parameters showed that stress reactions occurred only in the real vehicle (+5 beats per minute, +2 breaths per minute and the phasic skin conductance increased by 2). In the subjects’ declarative data, several feeling of presence sub-scales were lower under simulated conditions. These results suggest that the validity of motion based simulators for testing drivers coping with hazards needs to be questioned.

HAZOP and ALOHA Analysis of Acetone

A potential hazard can happen because of a technical and personal failures, natural disasters, terrorist attacks, and fires. The potential hazards can be dangerous for human health and environment, also cause economic losses. In an industrial plant, prevention and control of these consequences have an importancy. Hazard and Operability Analysis (HAZOP) is a technique for a system evaluation and determination of risk management of hazards. In particular, HAZOP is used in order to determine potential hazards in a system and operability problems. Moreover, Areal Location of Hazardous Atmosphere (ALOHA) is the potential hazard modelling programme, which is used to plan chemical emergencies. Acetone, a colorless liquid also known as propanone, is a solvent used in manufacture of plastics and other industrial products. The most hazardous property of acetone is its flammability. Acetone is a solvent widely used in the chemical industries and stored in large volumes, therefore, acetone is an important source of danger for chemical processes.  In this study, acetone was investigated to be a hazardous chemical using HAZOP and ALOHA software in order to prevent and control a big hazardous event in an industrial plant. 

Impact of Cognitive Distractions on Drivers’ Hazardous Event Anticipation and Mitigation Behavior in Vehicle–Bicycle Conflict Situations

Vehicle–bicycle collisions are increasing alarmingly. A recent study shows that cognitively distracted drivers who are glancing on the forward roadway are also less likely to glance toward areas for potential vehicle–bicyclist conflicts. But this study did not determine whether cognitively distracted drivers who did glance toward the appropriate area were as likely to process the information as drivers who were not cognitively distracted. Evidence that drivers who were cognitively distracted and glanced toward the bicyclist were not as likely to process the information could be inferred either from shorter fixations in the area where a bicyclist could appear or from smaller reductions in the speed of their vehicle to mitigate a potential conflict. This study intends to add to previous results by examining only glance and vehicle behaviors of participants who glance toward the latent hazardous events involving bicyclists. Specifically, the durations of the glances toward the latent hazardous events of participants who are and are not cognitively distracted are compared as well as their velocity while approaching the potential strike zones. Two groups of 20 participants (one distracted, one not distracted) each drove through seven scenarios on a fixed-based driving simulator while their eye movements were continuously tracked using an eye tracker. Analysis of the participants’ longest glance duration toward the latent hazardous events indicated that distracted drivers made shorter glances toward the latent hazardous events when compared with their non-distracted counterparts. However, there was no difference in vehicle velocity between distracted and non-distracted drivers near the potential strike zones.