Challenges of “Setup Time” and “On-Time Delivery” Faced by Japanese Automotive Parts Factories in Indonesia
Many Japanese automotive parts manufacturers have established operations in Indonesia, and in their production facilities, parts are routinely manufactured using molding machines such as injection molding machines. In these factories, in order to efficiently produce a wide variety of components, mold changes (setups) are required whenever the product type changes. However, since setup operations take time, frequent product changeovers can reduce production efficiency.
At the same time, the automotive industry requires strict adherence to delivery deadlines. Therefore, creating a production plan that minimizes the number of setups while still ensuring on-time delivery has become a major challenge.
Optimizing these complex conditions manually is not easy.
An effective solution to this challenge is the production scheduler Asprova. With its advanced scheduling capabilities powered by AI, it becomes possible to automatically generate an optimal production plan that simultaneously considers setup time and delivery constraints.
Why It Is Difficult to Create an Optimal Production Plan Manually
In production planning for molding factories, simply arranging production orders in the order they are received does not result in an optimal schedule.
Each product has a delivery deadline, and planners must consider various constraints such as available molding machines, the number of molds, and the setup time required when switching between products. While grouping production by the same mold can reduce setup time, there are cases where orders with earlier delivery dates must be prioritized. Furthermore, when equipment failures or sudden order changes occur, the production plan must be revised.
Because many conditions interact with each other in production planning, it is extremely difficult to determine the optimal production sequence while considering the entire situation manually. As a result, planning often relies on experience and intuition, which can lead to problems such as increased setup frequency and delivery delays.
Production Planning that Simultaneously Achieves Reduced Setup Time and On-Time Delivery Through AI Optimization
The production scheduler Asprova creates production plans that balance reduced setup time and on-time delivery by using AI optimization through iterative improvement.
For example, orders with flexible delivery dates can be grouped and produced together to reduce setup frequency, while orders with imminent deadlines are prioritized for production. In this way, the system automatically adjusts the schedule while considering the overall balance.
A key feature of this mechanism is that various constraints are quantified as “penalty values” and calculated as a single evaluation metric.
By integrating factors such as delivery delays, setup frequency, and equipment constraints into a unified evaluation, the AI repeatedly improves the schedule while searching for a better plan. As a result, even when the number of constraints increases, it is possible to generate realistic and executable production schedules in a short time without significantly increasing the time required for planning.
Production Schedule Optimization Using Genetic Algorithms
There are various types of optimization algorithms used in Advanced Planning and Scheduling (APS). For example, deep learning requires a large amount of training data, and preparing data to train whether a schedule is feasible in advance can be difficult. In addition, it may be challenging to handle demand patterns that have never occurred before.
In contrast, a Genetic Algorithm (GA) is an evolutionary algorithm that searches for optimal solutions by generating a vast number of candidate solutions on its own, making it well suited for complex optimization problems such as production scheduling.
First, multiple randomly generated schedule candidates (individuals) are evaluated, and those with higher evaluation scores are selected as parents. Next, new schedules are created through crossover, and some parts are randomly altered through mutation. By repeating this process across generations while maintaining diversity among solutions, the algorithm gradually improves the production plan while considering setup times and delivery constraints.
Efficient Production Planning Achieved with the AI Production Scheduler Asprova
In automotive parts molding factories, production plans that both reduce setup time and ensure on-time delivery are constantly required. However, due to the complexity of conditions such as multi-product manufacturing, equipment constraints, and sudden order changes, manual planning has its limitations.
The production scheduler Asprova is an APS (Advanced Planning and Scheduling) system that automatically generates optimal production schedules while simultaneously considering these complex conditions. It evaluates constraints such as setup time, equipment capacity, and delivery deadlines in an integrated manner, and uses AI-based optimization calculations to quickly create realistic and executable plans.
As a result, improvements can be expected in areas such as reducing setup frequency, shortening production lead times, and increasing on-time delivery rates. For Japanese manufacturing companies in Indonesia, it is being utilized as a powerful solution for achieving efficient and stable production operations.