Spare parts inventory management: a new hybrid approach

Maintenance Decision-Making Using Intelligent Prognostics Within a Single Spare Parts Support System

Health management is the foothold of remaining useful life (RUL) prediction, known as 'prognostics'. However, sudden failures in complex systems can lead to increased downtime and maintenance costs, ultimately diminishing system health and availability. Considering intelligent prognostics of components, maintenance decision-making for spare parts ordering and replacement is proposed within a spare parts support system. The decision-making process aims to minimize costs while maximizing availability as its primary objective. It considers spare parts ordering time and replacement time as key decision variables. By developing a maintenance decision-making model, it aims to determine the optimal time for ordering and replacing spare parts. This maintenance approach is designed to provide technical support for effective and rational equipment management decision-making.

Artificial intelligence for supply chain resilience: learning from Covid-19

Purpose

Many supply chains have faced disruption during Covid-19. Artificial intelligence (AI) is one mechanism that can be used to improve supply chain resilience by developing business continuity capabilities. This study examines how firms employ AI and consider the opportunities for AI to enhance supply chain resilience by developing visibility, risk, sourcing and distribution capabilities.

Design/methodology/approach

The authors have gathered rich data by conducting semistructured interviews with 35 experts from the e-commerce supply chain. The authors have adopted a systematic approach of coding using open, axial and selective methods to map and identify the themes that represent the critical elements of AI-enabled supply chain resilience.

Findings

The results of the study highlight the emergence of five critical areas where AI can contribute to enhanced supply chain resilience; (1) transparency, (2) ensuring last-mile delivery, (3) offering personalized solutions to both upstream and downstream supply chain stakeholders, (4) minimizing the impact of disruption and (5) facilitating an agile procurement strategy.

Research limitations/implications

The study offers interesting implications for bridging the theory–practice gap by drawing on contemporary empirical data to demonstrate how enhancing dynamic capabilities via AI technologies further strengthens supply chain resilience. The study also offers suggestions for utilizing the findings and proposes a framework to strengthen supply chain resilience through AI.

Originality/value

The study presents the dynamic capabilities for supply chain resilience through the employment of AI. AI can contribute to readying supply chains to reduce their risk of disruption through enhanced resilience.