{"id":93800,"date":"2025-03-03T21:05:29","date_gmt":"2025-03-03T14:05:29","guid":{"rendered":"https:\/\/bahtera.jp\/solver\/"},"modified":"2026-09-16T21:47:37","modified_gmt":"2026-09-16T14:47:37","slug":"solver","status":"publish","type":"post","link":"https:\/\/bahtera.jp\/en\/solver\/","title":{"rendered":"Asprova Solver and AI Scheduling\uff5cOptimization of Conflicting Conditions with Weighting"},"content":{"rendered":"<p>In Indonesian manufacturing sites, conflicting conditions such as &#8220;meeting delivery deadlines while reducing setups, controlling inventory, and increasing furnace fill rates&#8221; often arise simultaneously. Traditionally, dispatching rules and manual adjustments were relied upon, but using search methods like genetic algorithms allows for rapid exploration of candidate schedules based on weighted objectives.<\/p>\n\t\t\t\t<a href=\"https:\/\/bahtera.jp\/en\/indonesia-scheduler\/\" class=\"st-cardlink\" aria-label=\"Production Scheduler in Indonesia\">\r\n\t\t\t\t<div class=\"kanren st-cardbox\" >\r\n\t\t\t\t\t\t\t\t\t\t<dl class=\"clearfix\">\r\n\t\t\t\t\t\t<dt class=\"st-card-img\">\r\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<img decoding=\"async\" width=\"150\" height=\"150\" src=\"https:\/\/bahtera.jp\/wp-content\/uploads\/2025\/03\/indonesia-5-150x150.png\" class=\"attachment-st_thumb150 size-st_thumb150 wp-post-image\" alt=\"Structured diagram of production schedulers, PSI tables, and load planning in Indonesia\" srcset=\"https:\/\/bahtera.jp\/wp-content\/uploads\/2025\/03\/indonesia-5-150x150.png 150w, https:\/\/bahtera.jp\/wp-content\/uploads\/2025\/03\/indonesia-5-100x100.png 100w\" sizes=\"(max-width: 150px) 100vw, 150px\" \/>\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<\/dt>\r\n\t\t\t\t\t\t<dd>\r\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<p class=\"st-cardbox-t\">Production Scheduler in Indonesia<\/p>\r\n\t\t\t\t\t\t\t\r\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<div class=\"st-card-excerpt smanone\">\r\n\t\t\t\t\t\t\t\t\t<p>Production planning and load planning are closely related and require verification based on quantities. It is important to compare production quantities,\u2026<\/p>\n\t\t\t\t\t\t\t\t<\/div>\r\n\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t\t<p class=\"cardbox-more\">\u7d9a\u304d\u3092\u898b\u308b<\/p>\r\n\t\t\t\t\t\t\t\t\t\t\t\t\t<\/dd>\r\n\t\t\t\t\t<\/dl>\r\n\t\t\t\t<\/div>\r\n\t\t\t\t<\/a>\r\n\t\t\t\t\n<p><strong>Positioning of this article:<\/strong> This is a definitive guide on &#8220;optimization search (Solver)&#8221; under the production scheduler hub. It is not a general discussion on generative AI but focuses on how to optimize the objective functions and constraints of production schedules. Refer to <a href=\"https:\/\/bahtera.jp\/en\/solver8\/\">Solver8<\/a> for planning AI demos, <a href=\"https:\/\/bahtera.jp\/en\/asprova-operator-schedule\/\">mold\/operator constraints<\/a> for constraint placement, and <a href=\"https:\/\/bahtera.jp\/en\/asprova\/\">Asprova<\/a> for the product.<\/p>\n<div class=\"article-point\" id=\"key-takeaways\">\n<h2 class=\"article-point-title\">What this article covers<\/h2>\n<ul>\n<li>This article is a definitive guide on optimization search (Solver\/Genetic Algorithm) in production scheduling.<\/li>\n<li>Leveling, fill rate, setup reduction, stockout avoidance, and inventory minimization are trade-offs, often requiring more than a single rule.<\/li>\n<li>Asprova&#8217;s Solver applies coefficients (weights) to conflicting conditions to rapidly explore high-precision schedules.<\/li>\n<li>Without clear objectives and constraints, &#8216;optimal&#8217; cannot be defined; thus, KPI articulation is a prerequisite.<\/li>\n<li>The Solver8 article focuses on planning AI demos, while this article covers optimization concepts and implementation changes.<\/li>\n<li>Reading this alongside constraint modeling (mold\/operator) clarifies the meaning of the search space.<\/li>\n<\/ul>\n<\/div>\n<p><script id=\"wprestapi-ai-jsonld\" type=\"application\/ld+json\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"BlogPosting\",\"@id\":\"https:\/\/bahtera.jp\/en\/solver\/#article\",\"headline\":\"Asprova Solver and AI Scheduling\uff5cOptimization of Conflicting Conditions with Weighting\",\"description\":\"This article is a definitive guide on optimization search (Solver\/Genetic Algorithm) in production scheduling. Leveling, fill rate, setup reduction\u2026\",\"mainEntityOfPage\":{\"@type\":\"WebPage\",\"@id\":\"https:\/\/bahtera.jp\/en\/solver\/\"},\"inLanguage\":\"en\",\"datePublished\":\"2025-03-03T21:05:29\",\"author\":{\"@type\":\"Person\",\"name\":\"yamazou\"},\"about\":{\"@id\":\"https:\/\/bahtera.jp\/#organization\"},\"publisher\":{\"@id\":\"https:\/\/bahtera.jp\/#organization\"}},{\"@type\":\"ItemList\",\"@id\":\"https:\/\/bahtera.jp\/en\/solver\/#key-takeaways\",\"name\":\"What this article covers\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"This article is a definitive guide on optimization search (Solver\/Genetic Algorithm) in production scheduling.\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Leveling, fill rate, setup reduction, stockout avoidance, and inventory minimization are trade-offs, often requiring more than a single rule.\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Asprova's Solver applies coefficients (weights) to conflicting conditions to rapidly explore high-precision schedules.\"},{\"@type\":\"ListItem\",\"position\":4,\"name\":\"Without clear objectives and constraints, 'optimal' cannot be defined; thus, KPI articulation is a prerequisite.\"},{\"@type\":\"ListItem\",\"position\":5,\"name\":\"The Solver8 article focuses on planning AI demos, while this article covers optimization concepts and implementation changes.\"},{\"@type\":\"ListItem\",\"position\":6,\"name\":\"Reading this alongside constraint modeling (mold\/operator) clarifies the meaning of the search space.\"}]}]}<\/script><\/p>\n<h2>Machine Learning (Genetic Algorithm) and Production Scheduling<\/h2>\n<p>Generative AI (like ChatGPT) focuses on text generation, but in production scheduling, <strong>machine learning-oriented search<\/strong> (e.g., genetic algorithms) is often more effective. It evaluates candidate allocations and steers them in a favorable direction.<\/p>\n<p>Examples of necessary conditions frequently encountered in Japanese factories in Indonesia:<\/p>\n<div class=\"maruno\">\n<ol>\n<li>Optimize line input order within leveled production<\/li>\n<li>Approach 100% fill rate for heat treatment and furnaces<\/li>\n<li>Reduce setup frequency without delaying delivery<\/li>\n<li>Minimize raw material inventory without stockouts<\/li>\n<\/ol>\n<\/div>\n<p>These are trade-offs. Prioritizing delivery can increase setups and inventory, while increasing fill rates can reduce input order flexibility. &#8220;Scoring everything 100&#8221; is not feasible, so it is necessary to declare what score to aim for using coefficients (weights).<\/p>\n<h2>How Asprova Solver Changed Implementation<\/h2>\n<p>In past implementations in Indonesia, significant effort was required to build logic with planning commands according to requirements, leading to feedback that &#8220;implementation is difficult despite being introduced to make things easier.&#8221;<\/p>\n<p>With the Solver option, the approach of applying coefficients to conflicting conditions makes it easier to automatically generate high-precision schedules quickly. This represents a shift from &#8220;writing all sequences and branches in a program&#8221; to &#8220;declaring objectives and constraints and letting the system explore.&#8221;<\/p>\n<p>As a result, even non-IT specialists can more easily engage in scheduler implementation, and the technology itself is moving towards commoditization. Differentiation shifts to local constraint modeling (mold, skills, bonded, multi-variety) and support for adoption.<\/p>\n<h2>Decisions to Make Before Field Application<\/h2>\n<ul>\n<li><strong>KPI Articulation<\/strong> \u2014 Prioritization of delivery compliance rate, setup frequency, inventory days, fill rate, etc.<\/li>\n<li><strong>Definitive Constraints<\/strong> \u2014 Mold, operator, maintenance slots, etc. (auxiliary resource articles)<\/li>\n<li><strong>Operational Master Updates<\/strong> \u2014 Responsibility for maintaining processes, resources, setups, orders<\/li>\n<li><strong>Performance Feedback<\/strong> \u2014 Path to return the difference between plan and actual to the next weighting<\/li>\n<\/ul>\n<p>Without an operational cycle that updates before discussing accuracy, Solver will &#8220;produce a clean result once and end.&#8221;<\/p>\n<h2>Reading as Knowledge<\/h2>\n<ul>\n<li><strong>This Article (Solver)<\/strong> \u2014 Concepts of weighting conflicting objectives and optimization search<\/li>\n<li><strong>Solver8<\/strong> \u2014 Planning AI, demo\/product surroundings<\/li>\n<li><strong>Mold\/Operator Constraints<\/strong> \u2014 Constraint modeling as a prerequisite for exploration<\/li>\n<li><strong>asprova-cost<\/strong> \u2014 Connecting planned labor hours from optimization results to cost\/budget<\/li>\n<\/ul>\n<h2>Frequently Asked Questions\uff5cAI and Schedule Optimization<\/h2>\n<p>As knowledge of production schedulers (APS), we organize frequently recurring questions.<\/p>\n<h3>What can AI automatically decide?<\/h3>\n<p>When objective functions and constraints are clear, it can accelerate the exploration of candidate schedules. Without clear criteria, optimal cannot be defined.<\/p>\n<h3>What is the difference from traditional dispatching rules?<\/h3>\n<p>Rules are fast and easy to explain, but have limitations with complex objectives. Combining them with search allows for selecting solutions closer to evaluation metrics.<\/p>\n<h3>What is the difference between Solver and Solver8?<\/h3>\n<p>This article covers optimization search concepts, while Solver8 focuses on planning AI demos. Also read the product LP&#8217;s Solver explanation.<\/p>\n<h3>What initial data is needed?<\/h3>\n<p>Basic master data for processes, resources, setups, orders, and a feedback path for performance. Create an operational cycle that updates before accuracy.<\/p>\n<h2>Related Links<\/h2>\n<ul>\n<li><a href=\"https:\/\/bahtera.jp\/en\/indonesia-scheduler\/\">Production Scheduler Hub<\/a> \u2014 Entry point for planning, APS, Asprova<\/li>\n<li><a href=\"https:\/\/bahtera.jp\/en\/asprova\/\">Asprova<\/a> \u2014 Product definitive (Data Bridge \/ Viewer \/ Solver)<\/li>\n<li><a href=\"https:\/\/bahtera.jp\/en\/solver8\/\">Solver8<\/a> \u2014 Planning AI, demo surroundings<\/li>\n<li><a href=\"https:\/\/bahtera.jp\/en\/scheduling-parameter\/\">Scheduling Optimization<\/a><\/li>\n<li><a href=\"https:\/\/bahtera.jp\/en\/asprova-operator-schedule\/\">Mold\/Operator Constraints<\/a><\/li>\n<li><a href=\"https:\/\/bahtera.jp\/en\/asprova-cost\/\">Standard Cost and Budget<\/a><\/li>\n<li><a href=\"https:\/\/bahtera.jp\/en\/solver\/\">Solver (Optimization Search)<\/a><\/li>\n<li><a href=\"https:\/\/bahtera.jp\/en\/production-control-indonesia\/\">Production Management Hub<\/a> \u2014 ERP, performance side<\/li>\n<\/ul>\n","protected":false},"excerpt":{"rendered":"<p>This article serves as a definitive guide on optimization search (Solver\/Genetic Algorithm) in production scheduling. It discusses how Asprova&#8217;s Solver\u2026<\/p>\n","protected":false},"author":2,"featured_media":97976,"parent":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[619],"tags":[],"class_list":["post-93800","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-production-scheduler"],"_links":{"self":[{"href":"https:\/\/bahtera.jp\/en\/wp-json\/wp\/v2\/posts\/93800","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/bahtera.jp\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/bahtera.jp\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/bahtera.jp\/en\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/bahtera.jp\/en\/wp-json\/wp\/v2\/comments?post=93800"}],"version-history":[{"count":8,"href":"https:\/\/bahtera.jp\/en\/wp-json\/wp\/v2\/posts\/93800\/revisions"}],"predecessor-version":[{"id":104852,"href":"https:\/\/bahtera.jp\/en\/wp-json\/wp\/v2\/posts\/93800\/revisions\/104852"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/bahtera.jp\/en\/wp-json\/wp\/v2\/media\/97976"}],"wp:attachment":[{"href":"https:\/\/bahtera.jp\/en\/wp-json\/wp\/v2\/media?parent=93800"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/bahtera.jp\/en\/wp-json\/wp\/v2\/categories?post=93800"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/bahtera.jp\/en\/wp-json\/wp\/v2\/tags?post=93800"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}