Adapted techniques of explainable artificial intelligence for explaining genetic algorithms on the example of job scheduling

Many evolutionary artificial intelligence (AI) technologies have been applied to assist with job scheduling in manufacturing. One of the main approaches is genetic algorithms (GAs). However, due to their complexity, users may need help understanding or communicating GA applications, preventing their widespread acceptance among factory workers. The concept of explainable AI (XAI) has been proposed to address this issue. This study reviews existing XAI techniques for explaining GA applications in job scheduling and summarizes the problems existing XAI techniques face. Several novel XAI techniques are proposed to solve these problems, including decision tree-based interpretation, dynamic transformation and contribution diagrams, and improved bar charts. To illustrate the effectiveness of the proposed methodology, it is applied to a case from the literature. According to the experimental results, the proposed methodology can compensate for the deficiencies of existing XAI methods in handling high-dimensional data and visualizing the contribution of feasible solutions, thereby satisfying all the requirements for an effective XAI technique for explaining GA applications in job scheduling. Additionally, the proposed methodology can be easily extended to explain other evolutionary AI applications in job scheduling, such as ant colony optimization (ACO), particle swarm optimization (PSO), and the artificial bee colony (ABC) algorithm.