Grey Self-memory Combined Model for Complex Equipment Cost Estimation

To improve the using rationality of complex equipment cost, this paper presents a novel grey self-memory combined model for predicting the equipment cost. The proposed model can improve the modeling accuracy by means of the self-memory prediction technique. The combined model combines the advantages of the self-memory principle and traditional grey model through coupling of the above two prediction methods. The weakness of the traditional grey prediction model, i.e., being sensitive to initial value, can be overcome by using multi-time-point initial field instead of only single-time-point initial field in the system's self-memorization equation. As shown in the two case studies of complex equipment cost estimation, the novel grey self-memory combined model can take full advantage of the system's multi-time historical monitoring data and accurately predict the system's evolutionary trend. Three popular accuracy test criteria are adopted to test and verify the reliability and robustness of the combined model, and its superior predictive performance over other traditional grey prediction models. The results show that the proposed combined model enriches equipment cost estimation methods, and can be applied to other similar complex equipment cost estimation problems.