No abstract

No abstract

Large lifting equipment is used regularly in the maintenance operations of chemical plant installations, where safety controls must be carried out to ensure the safety of lifting operations. This paper presents a convolutional neural network (CNN) methodology, based on the PyTorch framework, to identify unsafe behavior among lifting operation drivers, specifically, by collecting 22,352 images of equipment lifting operations over a certain time period in a chemical plant. The lifting drivers’ behavior was divided into eight categories, and a ResNet50 network model was selected to identify the drivers’ behavior in the pictures. The results show that the proposed ResNet50 network model based on transfer learning achieves a 99.6% accuracy rate, a 99% recall rate and a 99% F1 value for the expected behaviors of eight lifting operation drivers. This knowledge regarding unsafe behavior in the chemical industry provides a new perspective for preventing safety accidents caused by the dangerous behaviors of lifting operation drivers.

In order to identify the content of various heavy metals, soils of the farmland surrounding the Huashan's gold tailing mine are studied. Surrounding soil samples are collected in new and old tailing mines. Flame atomic absorption spectrometry is taken to measure the content of Pb, Zn, Cd, Cr, and Cu. In addition, the method of combining the Geo-accumulation index and the potential ecological risk index is applied to evaluation the pollution in soils. It is able to provide the technical basis to the environmental management and recovery in this mine region.The results show that: (1) the pollution of Cu in soil samples is most important, others are arrayed in decreasing order: Cu>Pb>Zn>Cd>Cr. It should be noted that the coefficient of variation of Cu, Cd and Zn are larger, indicating that the strong impact of activities by the human; (2) the relationship between various heavy metals in old mine and the distance of sampling is not clear. However, a negative relationship is given between new mine and the distance of sampling; (3) some correlations are existed in the content of heavy metals. More closely relationships are shown in Cd and Cu, Cd and Cr, Pb and Zn. It demonstrates that these heavy metals have some homologous characteristic; (4) the results of Geo-accumulate index show that: Cu pollution levels are high, but Pb, Zn, Cd and Cr are slightly polluted. Otherwise, the two tailing mines are 2 levels pollution, a big accumulate index are presented surrounding old tailing mine; (5) From the method of potential ecological risk, we can get that: Cu is the first one for ecological harm, Cd is second, and Zn, Pb and Cr have slight harm. All results show that the two tailing mines are medium harm. According to the results, the protective system should be established, and the crops should be planted far from the tailing mines.

Taking the western Qinling Mountain, in the southern Shaanxi Province of china, as an example, based upon comprehensive analysis of geological data for 20 debris flow gullies, the author has put forward a series of indices system and has developed the immune genetic neural network system, which can quantitatively evaluate the dangerous degree of mine debris flow. This software system manage initial data through Access's data-base technology, and determine and optimize the hidden layer network by immune genetic algorithm, as well as achieve the dangerous degree evaluation of mine debris flow by virtue of artificial neural network which has been successfully trained. The calculating results of mine debris flow examples testify that this method is reliable and can accurately evaluate the dangerous degree of mine debris flow. These evaluation results have some important instructive significance for the disaster prevention and reduction of mine debris flow.