An Improved Stacking Model for Equipment Spare Parts Demand Forecasting Based on Scenario Analysis

Abstract

The purpose of spare parts management is to maximize the system’s availability and minimize the economic costs. The problem of cost availability trade-off leads to the problem of spare parts demand prediction. Accurate and reasonable spare parts demand forecasting can realize the balance between cost and availability. So, this paper focuses on spare parts management during the equipment normal operation phase and tries to forecast the demand of spare parts in a specific inspection and replacement cycle. Firstly, the equipment operation and support scenarios are analyzed to obtain the supportability data related to spare parts requirements. Then, drawing on the idea of ensemble learning, a new feature selection method has been designed, which can overcome the limitations of a single feature selection method. In addition, an improved stacking model is proposed to predict the demand for spare parts. In the traditional stacking model, there are two levels of learning, base-learning, and meta-learning, in which the outputs of base learners are taken as the input of the meta learner. However, the proposed model brings the initial feature together with the output of the base learner layer as the input of the meta learner layer. And experiments have shown that the performance of the improved stacking model is better than the base learners and the traditional stacking model on the same data set.

AI-Based Holistic Model for Decision-Support System in Inventory Optimization using deep Learning

“…The suggested model combines the starting feature with the output of the base learner layer to serve as the input for the meta learner layer. Experiments have demonstrated that the enhanced stacking model outperforms both the base learners and the classic stacking model when applied to the same dataset [30].…”

Untitled

“…However, other aspects of criticality are linked to the ability to control the situation. The proposed possibilities are part of the criticality of so-called control, including lead time, supplier availability, and failure predictability (Yang et al, 2022). The factors that affect the criticality of spare parts are:  Specificity of a spare part (C1): A wide spectrum of spare parts are required by many users; however, a certain number of parts are specifically tailored and used by only one party.…”

Identificación de patrones de demanda de refacciones automotrices

“…El estudio utiliza el análisis envolvente de datos de intervalo (dea, por sus siglas en inglés) para analizar y priorizar todas las fallas encontradas por la técnica de análisis del modo y efecto de falla del proceso (pfmea, por sus siglas en inglés) de piezas del Peugeot 206, Peugeot 405 y Samand y combinando el análisis relacional (gra, por sus siglas en inglés) con los resultados del dea, obtienen la priorización de los procesos de fabricación en función de la criticidad de las piezas. Yang et al (2022) por su parte, propone un enfoque basado en escenarios a través de los cuales inspecciona la operación normal de un equipo y trata de predecir el período de remplazo de la pieza como mantenimiento preventivo para evitar fallas que causen un mayor costo.…”

“…La clasificación apropiada de la demanda de repuestos permitirá a los tomadores de decisiones seleccionar el modelo de pronóstico adecuado que permita la previsión precisa y razonable de la demanda, logrando el equilibrio entre el costo y la disponibilidad del producto a través de la elección de una política adecuada del control de inventario (Yang et al, 2022;Zhuang et al, 2022). Boylan y Syntetos (2007) sugieren que un método complementario de clasificación es la variabilidad del tamaño de la demanda; para ello Bacchetti y Saccani (2012) recomiendan primero realizar la clasificación de demandas de repuesto, para determinar las piezas que tienen demandas intermitentes, estacionales o de moda.…”