Dynamic cost forecasting model based on extreme learning machine - A case study in steel plant

Highlights

• This research focuses on the dynamic cost forecasting.

• Steel material fluctuated and hard to earn profit without appropriate cost estimation.

• A hybrid-forecasting model with Grey Relation Analysis and extreme learning machine is proposed.

• Managers are able to reconsider the purchasing of raw material and adjust the pricing strategy to pursuit the profit target.

Abstract

Without a doubt, the current commercial circumstance exists in a strong competition and is full of uncertainty. Managers focus on continuous effort for increasing profits and reducing cost in their organization. In the past two decades, the price of raw materials has fluctuated severely and steel plants found it hard to earn profits and keep the capacity normal. Whereas some steel plants reduced the overcapacity of production by revamping the blast furnace or cutting down the throughput, others tried to limit and eliminate unnecessary cost. However, these strategies have failed to keep pace with the frequent changes in the raw material prices and could not support the profit targets greatly. This study aims at addressing such concerns by proposing an extreme learning machine (ELM) to predict the major raw material price in steel plants. Typically, this paper focuses on integration of Grey Relation Analysis (GRA) with a hybrid forecasting model to forecast the cost of iron ore and coking coal that are majorly used in steel plants. Here we attempt to establish a dynamic cost system to forecast the manufacturing cost of end products and adjust the purchasing and production strategy. This forecasting model can offer an accurate and rapidly predicting result of raw material price. Managers can use this forecasting results to reconsider the purchasing of raw materials and adjust the pricing strategy to pursuit their company’s profit targets.

Introduction

In competitive and complex markets, such as the cold rolling commodities in steel plants, having the ability to forecast major material cost and envisioning the behavior of changing prices in each of them constitute a competitive advantage for organizations. One of the most important cost-related decisions is to know how to produce good commodities at the lowest possible cost. This involves understanding the origin of costs in an integrated steel plant along with understanding and managing the process, which leads to the lowest possible costs (Troelsen, 2006). Since late 1960s, the purchasing issues related to raw materials have been tackled well by enterprises. Purchasing raw materials is not only the beginning of all production activities and linked to the connection between production operating activities, but also the major part of the production cost for an enterprise (Gao & Tang, 2003). By estimating, material cost accounts for 60–80% in total cost (Bender, Brown, Isaac, & Shapiro, 1985), especially in steel plant.

Making a time series forecasting model for raw material price assists in developing the dynamic cost system for cold rolling product in the steel plant. Actually, time series prediction techniques have been used in many real-world applications, such as financial market prediction, electric utility load forecasting, weather and environmental state prediction, and reliability forecasting. The existing traditional quantitative approaches include heuristic methods, such as time series decomposition and exponential smoothing as well as time series regression and autoregressive and integrated moving average (ARIMA) models that have formal statistical foundations (Chu & Zhang, 2003). Nevertheless, their forecasting ability is limited by their assumption of a linear behavior, and thus, is the results are not always satisfactory (Sapankevych and Sankar, 2009, Zhang, 2003). This paper considers establishing a dynamic cost forecasting model of the end products in a large-scale steel plant, studies the special cost forecasting model involved, proposes an extreme learning machine (ELM) algorithm to predict the price of raw materials, and construct a cost simulation system for cold rolling products.

The rest of this paper is organized as follows. Section 2 describes the related work. Section 3 introduces the characteristics of steel plants. Section 4 discusses the forecasting model and describes the features and behavior of the model in detail. Section 5 illustrates an example of the dynamic cost simulation model. Conclusions and further research directions are outlined in Section 6.