Physicochemical properties of particulate matter (PM2.5) from the steel industry in Indonesia

Particulate matter (PM) as one of the pollutants in the atmosphere needs to be studied. PM has physical and chemical characteristics and is called physicochemical properties. These properties vary depending on the source of the PM. PM samplers are used for air sampling to characterize some fine particles (PM2.5). The PM2.5 samples have collected from four sampling sites in the steel industry in Cilegon, Indonesia. The sampling sites are the main gate, the hot strip mill, the billet post, and the hot blast plant. The sampling period was four months. The physicochemical properties analysed are morphology, elements content, heavy metals, and particle size. The instruments used to analyse were Scanning Electron Microscopy (SEM) and Energy Dispersive Spectrometry (EDS), Inductively Coupled Plasma Atomic Emission Spectroscopy (ICP-AES), and Particle Size Analyzer (PSA). The morphology of PM2.5 detected varied, but the elements and the most elements found were F and C particles. The metals concentration was below the Indonesia Regulation. While the average particle size analysed was below 2,500 nm. The physicochemical properties of PM2.5 are affected by the type of production process in the industry.

Anomaly Detection in Asset Degradation Process Using Variational Autoencoder and Explanations

Development of predictive maintenance (PdM) solutions is one of the key aspects of Industry 4.0. In recent years, more attention has been paid to data-driven techniques, which use machine learning to monitor the health of an industrial asset. The major issue in the implementation of PdM models is a lack of good quality labelled data. In the paper we present how unsupervised learning using a variational autoencoder may be used to monitor the wear of rolls in a hot strip mill, a part of a steel-making site. As an additional benchmark we use a simulated turbofan engine data set provided by NASA. We also use explainability methods in order to understand the model’s predictions. The results show that the variational autoencoder slightly outperforms the base autoencoder architecture in anomaly detection tasks. However, its performance on the real use-case does not make it a production-ready solution for industry and should be a matter of further research. Furthermore, the information obtained from the explainability model can increase the reliability of the proposed artificial intelligence-based solution.

Human Resource Planning Study in Hot Strip Mill 2 (HSM#2) factory at PT. Krakatau Steel, Tbk

The purpose of this study was to analyze the human resource planning process at the Hot Strip Mill 2 (HSM#2) factory at PT. Krakatau Steel, Tbk from before it was established until the first commercial operation (first coil). The existence of human resource planning is very important forfactory new, so that human resources will be obtained in quantity and quality in accordance with the needs to support effectiveness and efficiency in order to achieve the vision and mission set by the company. HSM#2 factory isproduction work unitPT. Krakatau Steel, Tbk which started operating for the first time (first coil) on May 17, 2021. The research method is qualitative descriptive using a phenomenological approach that will reveal the experiences of leaders and the human resource planning department related to the HSM#2 factory. The number of informants is7 people consisting of2 persons the manager who makes the mapping of human resource needs, and5 staff person directly involved in human resource planning at the HSM#2 plant. Data were collected beforehand by using interview techniques, document studies, and field observations. Data were analyzed using SWOT matrix analysis by considering strengths, weaknesses, opportunities, and threats. The results of the study indicate that at the time of planning human resources, the procurement of employees is divided into two, namely those from internal for supervisory, superintendent, and manager positions and those frommix of internal and external for officer, foreman, and supervisor positions.