Smart Anomaly Detection and Prediction for Assembly Process Maintenance in Compliance with Industry 4.0.

One of the big problems of today's manufacturing companies is the risks of the assembly line unexpected cessation. Although planned and well-performed maintenance will significantly reduce many of these risks, there are still anomalies that cannot be resolved within standard maintenance approaches. In our paper, we aim to solve the problem of accidental carrier bearings damage on an assembly conveyor. Sometimes the bearing of one of the carrier wheels is seized, causing the conveyor, and of course the whole assembly process, to halt. Applying standard approaches in this case does not bring any visible improvement. Therefore, it is necessary to propose and implement a unique approach that incorporates Industrial Internet of Things (IIoT) devices, neural networks, and sound analysis, for the purpose of predicting anomalies. This proposal uses the mentioned approaches in such a way that the gradual integration eliminates the disadvantages of individual approaches while highlighting and preserving the benefits of our solution. As a result, we have created and deployed a smart system that is able to detect and predict arising anomalies and achieve significant reduction in unexpected production cessation.

The spatial distribution of congener-specific human PCB concentrations in a PCB-polluted region.

Serum PCB congener concentrations were measured in 602 adults living near a PCB pollution source in eastern Slovakia. We created isoconcentration maps for 21 PCB congeners by geocoding each participant's place of residence and kriging. Concentrations of PCB congeners were inversely associated with the distance of the participants' residence from the source of pollution. Congener-specific risk factors were derived, particularly for PCBs 52 and 153. We observed that the spatial distribution of serum concentrations was influenced by micro-climatic parameters and physicochemical properties of the congeners. PCB congener profiles strongly correlated with that of the PCB commercial product Delor 106, which was manufactured in the region. The isoconcentration maps indicate that the zones with the highest predicted congener concentration have a mean area of approximately 235.75±188.56km2 and the mean enrichment of concentration of congeners in serum in these zones is about 5.12±1.36. We estimate that depending on congener approximately 23,457±18,762 individuals with PCB concentrations exceeding health-based guidance values live in these zones.

Simple reaction time in 8-9-year old children environmentally exposed to PCBs.

Simple reaction time (SRT) has been studied in children exposed to polychlorinated biphenyls (PCBs), with variable results. In the current work we examined SRT in 146 boys and 161 girls, aged 8.53 ± 0.65 years (mean ± SD), exposed to PCBs in the environment of eastern Slovakia. We divided the children into tertiles with regard to increasing PCB serum concentration. The mean ± SEM serum concentration of the sum of 15 PCB congeners was 191.15 ± 5.39, 419.23 ± 8.47, and 1315.12 ± 92.57 ng/g lipids in children of the first, second, and third tertiles, respectively. We created probability distribution plots for each child from their multiple trials of the SRT testing. We fitted response time distributions from all valid trials with the ex-Gaussian function, a convolution of a normal and an additional exponential function, providing estimates of three independent parameters µ, σ, and τ. µ is the mean of the normal component, σ is the standard deviation of the normal component, and τ is the mean of the exponential component. Group response time distributions were calculated using the Vincent averaging technique. A Q-Q plot comparing probability distribution of the first vs. third tertile indicated that deviation of the quantiles of the latter tertile from those of the former begins at the 40th percentile and does not show a positive acceleration. This was confirmed in comparison of the ex-Gaussian parameters of these two tertiles adjusted for sex, age, Raven IQ of the child, mother's and father's education, behavior at home and school, and BMI: the results showed that the parameters µ and τ significantly (p ≤ 0.05) increased with PCB exposure. Similar increases of the ex-Gaussian parameter τ in children suffering from ADHD have been previously reported and interpreted as intermittent attentional lapses, but were not seen in our cohort. Our study has confirmed that environmental exposure of children to PCBs is associated with prolongation of simple reaction time reflecting impairment of cognitive functions.

The spatial distribution of human exposure to PCBs around a former production site in Slovakia.

We evaluated concentrations of 15 PCB congeners in blood serum of 2047 adults, 431 8-9-year old children and 1134 mother-child pairs born in 2001-2003. These subjects were long-standing residents living up to 70 km (to the north) and up to 50 km (to the south) of the former Chemko Strázske PCB production facility in the Michalovce district of Slovakia. We plotted serum concentration against distance from the plant both with and without consideration of the direction of their homes from the site. The decrease in exposure with distance could be described by an exponential function which was dependent on direction and climatic parameters. By kriging we created maps depicting predicted isoconcentration contours for sex- and age-adjusted serum concentration of ∑PCBs for the same group of children, adults and mothers. The principle of our risk analysis was to relate serum concentration data, reflecting PCB body burden, using the critical concentrations established by the French Agency for Food, Environmental and Occupational Health & Safety (ANSES 2010) as thresholds below which the probability of effects on health is regarded as negligible. We conclude that 10 years ago, around 200,000 residents were at risk in this densely populated area. Exposure has since decreased but the mechanism for this has not yet been studied.

Duration of breastfeeding and serum PCB 153 concentrations in children.

Polychlorinated biphenyls (PCBs) are toxic, persistent, and bioaccumulative chemicals which, because of their lipophilic properties, are abundant in human breast milk. Breastfed infants are therefore at risk of being exposed to considerable amounts of PCBs. The commonly used exposure estimations, based solely on breast milk PCB levels and duration of breastfeeding, may lead to exposure misclassification. To improve assessments of exposure to PCBs, we determined PCB 153 serum concentration, as a model substance for PCBs, at the critical time of weaning for each child in 305 breastfed infants from 5 single time point concentration measurements spread over 7 years and data on duration of breastfeeding, using an earlier developed model of the system type. We approximated the dependence of PCB 153 serum concentration, Ctbf, adjusted to cord serum concentration, C0, on nursing period, by a polynomial function Ctbf/C0=0.596+0.278t-0.0047t(2) which reliably predicts exposure to PCB 153 of breastfed infants, important for assessment of dose-outcome relationships. Adjustment of current serum concentrations to cord serum concentration improved validity of exposure assessment.