[tcb_logo href=’https://inquizity.com’ data-id-d=’13’ data-css=’tve-u-16ffb2a32b7′ data-img-style=” class=” data-alt=”]
Alumina / Chemicals Manufacturing Company – MTO
Module: Master Production PlanningIndustry: Chemicals
Schedule a FREE Demo
Client Overview: Alumina Division of a Global Major in Aluminium FRP / Extrusion.The client is a global major part of large conglomerate in India. The plant manufactures special alumina and alumina hydrates for refractory, ceramics, polishing, fire retardant filler in polymer composites, alum, zeolite with ability to produce 120 different grades, serving more than 600 customers, across 32 countries and Group consumption.
Key Features
- <li “=”” style=”text-align: justify;” tve-u-17a55e998c4″=””>Medium / Short Term Planning tool <li “=”” style=”text-align: justify;” tve-u-17a55e998c4″=””>Multiple Objectives of Capacity Utilization, OTIF, Contribution, Demand Fulfilment <li “=”” style=”text-align: justify;” tve-u-17a55e998c4″=””>Sequence Dependency <li “=”” style=”text-align: justify;” tve-u-17a55e998c4″=””>Scenario Analysis
Problem Method and Result
The Puzzle
- The Client has a about 100-120 grades of Alumina with 4 main Kiln resources producing the various grades.
- Some of the SFG can be considered as FG and sold off while the rest is taken to further processing.
- Further processing results in Coarse, Mill and Micro variants. <li “=”” =””=”” style=”text-align: justify;” tve-u-17a55ce2d50″=””>There is a sequence dependency that is considered for the process of planning. <li “=”” =””=”” style=”text-align: justify;” tve-u-17a55ce2d50″=””>The client was using Excel to Plan its operations and looking to optimise its Production Plan. <li “=”” =””=”” style=”text-align: justify;” tve-u-17a55ce2d50″=””>Client required Production Planning both at the Monthly Level as well as on a Daily level.
The Solution
- Demand Aggregation Portal was configured to first collect demand at the customer / SKU level.
- The solution was designed such that demand satisfaction gets priority. Whilst trying to maximize capacity utilization by grouping of similar orders to reduce set up times.
- The model suggested the Product Mix considering priority of the certain products over the other so that contribution is maximized.
- The model looked at demand constraints, capacity constraints, set up matrix, Inventory balance constraint etc. to arrive at optimal mix of product as well as their schedule for the production.
- The model also suggested SKUs to manufacturing in case of capacity gaps based on future demand.
The Result
- Automated Production Start and End date of the orders.
- Prioritisation products based on contribution.
- Monthly and Daily Planning
- Visibility of capacity utilization / inventory.
- Suggestions on future products to be produced in case of Capacity availability.
- Changeover time minimization through proper sequence of products
More Case Studies
Crompton
Simultaneous planning for finite capacity and material for APIs and Formulations.
ATG
Optimize planning of product mix to minimize changeovers considering various planning and production constraints.
Related Products
S Suite
A Suite
V Suite
I Suite
Related Products
Replenishment Planning
Demand Forecasting
Dashboards
Production Planning and Scheduling
Address
3rd Floor Stellar tower, Sion Panvel Road,Opposite K Star Mall, Chembur, Mumbai,Maharashtra 400071
Contact
info@inquizity.com+91-9833257112
Copyright
Copyright (c) 2020 Inquizity Metanoia OPC Pvt. Ltd.GST: 27AAECI6558A1ZN
Schedule a FREE Demo
Fabric & Domestic Cleaning Products Company
SOLUTIONS DESIGNED TO SYSTEMATICALLY ESTIMATE MARKET DEMAND
Be it New Product Development, Planning, or Promotions, implementing collaborative Demand Forecasting provides you with statistical / ML / AI data to support the course of action in the medium term.
the puzzle
Demand Planning comprises key step of arriving at a baseline number. This is done by using Statistical and ML/AI methods. The Module applies various methods of forecasting on the historical Sales data to arrive at the forecast in the coming months. The forecasting can be done at various levels such as SKU-Depot / Brand-Region / SKU Region
the solution
the result
Multiple Heirarchy
Forecasting at multiple Hierarchies e.g. SKU-Location, SKU-Sales Office, Brand-Channel etc.
Supersession
Supersession that allows linking of old to new items to provide meaningful continuity in history for effective forecasting new product
Statistical Methods
Variety of Forecasting Techniques using efficient Python to take care of different distributions such as seasonality, promotions etc. Also allows for Outlier Detection
Classification of Products
Dynamic Classification of Products across Runner / Repeater / Stranger using different parameters of frequency, variability etc.
ML / AI Methods
Selection of different AI / ML Methods for cases where ML can be implemented
Choice of Error Methods
Selection of Techniques based on different Error Measures with ability to add custom Statistical Techniques