The growing complexity of steel manufacturing, loss of veteran operators, and demand for carbon-neutral operation make tacit operational knowledge increasingly difficult to sustain. Standalone large language models (LLMs) cannot adequately address terminology mismatch, schema fragmentation, undocumented tacit knowledge, and non-traceable hallucinations in on-site data. This study proposes a domain knowledge graph-based conversational operation assistant integrating a steel-process ontology with expert–LLM dialogue. An eight-class ontology is introduced, featuring the UnfilledSlot class to explicitly represent missing knowledge. A five-phase methodology constructs an initial graph, automatically fills available slots, prioritizes remaining deficiencies, and generates targeted multiple-choice questions for experts. The completed graph supports NL2SQL, analysis, explainable AI, and response generation, while operational logs reveal new knowledge gaps. Applied to a steel continuous casting process with 8,441 slots, automatic filling achieved 62% (5,233 slots), while 600 bundled expert questions resolved 2,702 additional slots, reducing the unfilled ratio from 38% to 6%. Comparisons with a standalone LLM, retrieval-augmented generation, and an ablation without UnfilledSlot, together with expert evaluations across three graph-completeness levels, confirm that explicit deficiency handling improves response reproducibility and traceability.

This paper presents the design of an automatic circumferential chamfering device that processes the inner and outer diameter corners of centrifugal cast pipes after cutting. These large, heavy pipes (dimensions: 389 mm x 5700 mm x 36 mm; weight: 1,200 kg) are produced using the centrifugal casting method. Following manufacturing, the pipes undergo several post-processing operations, including washing, grinding, cutting, and chamfering. Traditionally, circumferential chamfering has been performed manually by workers using grinders. In this study, we conceptualized an automatic circumferential chamfering device specifically designed to chamfer the corners of large centrifugal cast pipes. A structural analysis was conducted to ensure the design's safety, yielding a safety factor greater than two. Based on these design outcomes, we manufactured the chamfering device and conducted characteristic experiments on a large centrifugal cast pipe. The results confirmed that the cylindrical chamfering device can safely and effectively chamfer the inner and outer diameters of large centrifugal cast pipes.

Recently, competition in the manufacturing industry related to the preoccupation of new markets has drastically changed due to the increase in small quantity batch production products. Besides, business models utilizing 3D printing technology suitable for flexible manufacturing are gaining interest. As 3D printing technology is becoming more common, Design for Additive Manufacturing is also in the spotlight. However, the productivity of 3D printing technology is still insufficient in terms of mass production. In this study, the possibility of innovation in mass production process that combines 3D printing technology is presented through the case of innovation in manufacturing productivity of medium-speed engine cylinder head through the integration of sand 3D printing technology. It outlines how sand 3D printing technology is applied to cylinder head mass production processes, how the quality of cylinder head products can be improved compared to conventional pattern-based molding methods, and how productivity can be maximized by reducing process time and human error through hybrid production method with sand 3D printed integrated design cores. In conclusion, this paper presents the effectiveness of sand 3D printing technology which can secure product competitiveness by increasing the production capacity of mass production process, reducing production costs, improving quality, and reducing loss.

This paper aims to develop a prediction model for the product quality of a casting process. Prediction of the product quality utilizes an artificial neural network (ANN) in order to renovate the manufacturing technology of the root industry. Various aspects of the research on the prediction algorithm for the casting process using an ANN have been investigated. First, the key process parameters have been selected by means of a statistics analysis of the process data. Then, the optimal number of the layers and neurons in the ANN structure is established. Next, feed - forward back propagation and the Levenberg - Marquardt algorithm are selected to be used for training. Simulation of the predicted product quality shows that the prediction is accurate. Finally, the proposed method shows that use of the ANN can be an effective tool for predicting the results of the casting process.