Data-Driven Predictive Maintenance And Optimal Plan* (40 Hours)

*This is a non-WSQ module.

This programme is in collaboration with the Sectoral AI Centre of Excellence for Manufacturing (AIMfg).

Introduction

This course is targeted towards manufacturing companies which need artificial intelligence (AI) help to solve their daily operation issues. Unlike generic AI applications designed for text or image processing, this course focuses on applying AI to manufacturing and industrial process data. Participants will learn how to transform machine sensor readings, equipment logs, vibration signals, temperature data, and production time-series data into actionable insights. By integrating data science with manufacturing domain knowledge, learners will be equipped to develop AI-driven solutions to solve real-world challenges on the production floor, including:

Failure of root cause identification
Data correlation analysis
Quality prediction at an earlier stage
Predictive maintenance
Shopfloor performance prediction
Process parameter optimisation
Smart DOE by predictive models

About the Programme

Before investing in full-scale AI development and deployment, organisations need to determine whether AI is technically feasible and capable of delivering measurable business value. This programme provides the essential foundation by equipping participants with the knowledge and practical skills to apply data mining, machine learning, and AI techniques to solve real-world manufacturing and operational challenges.

Unlike generic AI courses that focus on text or image applications, this programme is designed specifically for industrial and manufacturing environments. Participants will work on feasibility study projects using their own company’s operational data—or trainer-provided datasets where necessary—to develop Proof-of-Concept (PoC) solutions. Through this hands-on approach, participants gain the confidence and capability to apply AI and data-driven techniques to improve day-to-day manufacturing operations.

Programme Highlights

Participants will learn to:

Apply a structured methodology for solving manufacturing and operational problems using data mining and AI.
Gain practical knowledge of the latest AI and machine learning techniques for industrial applications
Experience a unique “Train-and-Mentor” approach, combining classroom learning with guided Proof-of-Concept (PoC) feasibility projects.
Analyse your organisation’s own operational datasets to identify opportunities for process improvement and AI adoption.
Evaluate the business impact of AI solutions by assessing improvements in performance, quality, yield, productivity, and operational efficiency.
Understand the principles of data-driven predictive maintenance and its role in improving equipment reliability.
Develop predictive maintenance models using AI and advanced data analytics techniques.
Leverage predictive models to optimise maintenance planning, reduce unplanned downtime, and improve asset utilisation.

Who Should Attend

This course is designed for engineers, managers, researchers, and support professionals working in Production, Operations, R&D, QC/QA, IT, Inventory, Marketing and Sales, and HR and Finance across industries such as semiconductors, electronics, precision engineering, aerospace, automation, medtech, pharmaceuticals, oil and gas, manufacturing, and logistics.

Course Outline

The programme is divided into ten sessions of four hours each, covering the topics below:

S/No	Session Topic	Topics Covered
1	PoC Project Identification	To describe the issues facing (problem statements) in their manufacturing production lines and what needs AI help. To define a case study with the problem statements for the Proof-of-Concept (PoC) project by using AI methods to solve the problem statements. To clearly define the project objectives and impacts with details.
2	Building up Predictive Modelling Structure	To identify predictive model output variables as improvement targets. To identify predictive model input variables which influence output targets. To determine the data sources of input and output variables.
3	Data Collection	To collect correct product quality/equipment failure data as output targets and process parameters as input variables
4	Data Pre-Processing	To transform production and operational datasets into AI training-ready data formats
5	Data Clustering for Noise Filtering	To use advanced data clustering methods for noise filtering in datasets
6	Correlation Analysis	To use feature selection methods for correlation analysis to define the major input parameters that highly influence output performance.
7	Predictive Modelling by Regression Methods	To build up regression models to predict the output target
8	Predictive Modelling by Machine Learning/AI Methods	To build up machine learning/AI models to predict the output target
9	Predictive Modelling by Deep Learning Method	To build up deep learning models to predict the output target and identify a golden model for implementation.
10	Benefit Analysis and Implementation Proposal for Next Phase	To provide the final PoC conclusion with the benefits analysis results and submit a new proposal for the next phase of implementation if the PoC is accepted.

Upon Completion of This Course

Upon Completion Of This Course

Participants will be awarded with a Certificate of Attendance (COA) by SIMTech and/or ARTC if they meet the following criteria:

Achieve at least 75% course attendance;
Take all assessments; and
Pass the course.

Note: Trainees will have to bear the full course fee upon failure to meet either one of the criteria.

Pre-Requisites, Full and Nett Course Fees

Pre-Requisites

Applicants should possess a degree in any discipline or a diploma with a minimum of 3 years of related working experience.
Applicants who do not have the required academic qualifications are still welcome to apply, but shortlisted candidates may be required to attend an interview for special approval.
Proficiency in written and spoken English.

Full Course Fee

The full course fee for this course is $4,000 before funding and prevailing GST.

Nett Course Fee

International Participants	Singapore Citizens aged 39 years and below, Singapore Permanent Residents and LTVP+ Holders	Employer-sponsored and self-sponsored Singapore Citizens aged 40 years and above (MCES) ²	SME-sponsored local employees (i.e Singapore Citizens, Singapore Permanent Residents and LTVP+ Holders) (ETSS) ¹
$4,360	$1,308	$508	$508

All fees are inclusive of GST 9%.

Please note that fees and funding amount are subject to change.

Long Term Visit Pass Plus (LTVP+) Holders

The LTVP+ scheme applies to lawful foreign spouses of Singapore Citizens with (i) at least one Singapore Citizen child or are expecting one from the marriage, or at least three years of marriage, and (ii) where the Singapore Citizen sponsor is able to support the family.
All LTVP+ holders can be identified with their green visit pass cards, with the word ‘PLUS’ printed on the back of the card.

Enhanced Training Support For Small & Medium Enterprise (SMES) Scheme (ETSS)

The ¹Enhanced Training Support for Small & Medium Enterprises (SMEs) scheme (ETSS) is for company-sponsored participants who are subject to the eligibility criteria shown below:

SMEs that meet all of the following eligibility criteria:

Registered or incorporated in Singapore
Employment size of not more than 200 or with annual sales turnover of not more than $100 million

SME-sponsored Trainees:

Must be Singapore Citizens or Singapore Permanent Residents.
Courses have to be fully paid for by the employer.
Trainee is not a full-time national serviceman.

Further Info: This scheme is intended for all organisations, including non-business entities not registered with ACRA e.g. VWOs, societies, etc. Only ministries, statutory boards, and other government agencies are NOT eligible under Enhanced Training Support for SMEs Scheme. Sole proprietorships which meet all of the above criteria are also eligible.

SkillsFuture Mid-Career Enhanced Subsidy (MCES)

The ²SkillsFuture Mid-Career Enhanced Subsidy (MCES) is meant for employer-sponsored and self-sponsored Singapore Citizens aged 40 years old and above.

SkillsFuture Credit

All Singaporeans aged 25 years old and above are eligible for SkillsFuture Credit (Opening SkillsFuture Credit), which can be used to offset course fees (for self-sponsored registrations only).

For more information on the funding support schemes you are eligible for, please visit www.skillsfuture.gov.sg

How Course Fees are Calculated

TYPE	CATEGORY OF INDIVIDUALS
	International Participants	Singapore Citizens aged 39 years and below, Singapore Permanent Residents and LTVP+ Holders	Employer-sponsored and self-sponsored Singapore Citizens aged 40 years and above	SME-sponsored local employees (i.e Singapore Citizens, Singapore Permanent Residents and LTVP+ Holders)
	FUNDING SOURCE
	Not applicable for Funding Support	SkillsFuture Funding (Baseline)	SkillsFuture Mid-career Enhanced Subsidy (MCES) ²	SkillsFuture Enhanced Training Support for SMEs (ETSS) ¹
Full Course Fee	$4,000	$4,000	$4,000	$4,000
Funding Support	Not Applicable	($2,800)	($3,600)	($3,600)
Nett Course Fee	$4,000	$1,200	$400	$400
GST 9%	$360	$108*	$108*	$108*
Total Nett Course Fee Payable to Training Provider	$4,360	$1,308	$508	$508

* Based on 30% of Full Course Fee

About the Trainer

Registration

Please register for this course through our online form: Course Registration Form for Public Classes.
For the first question, please select "Modular Programmes (Standalone Modules".
Applicants will be placed on our waiting list if the course does not have an upcoming scheduled intake.
When the next intake is confirmed, a confirmation email with payment information will be sent to applicants to finalise their participation.

Collateral

Download brochure

Contact Us

Technical Enquiries	General Enquiries
Dr LI Xiang, Email: li_xiang_from.tp@a-star.edu.sg	Knowledge Transfer Office, Email: KTO-enquiry@a-star.edu.sg

Schedule

Module	Skills Course Reference Number	Next Intake(s)' Training Period (Click on the dates to view their schedules)	Registration Status
Data-driven Predictive Maintenance and Optimal Plan (40 hours)	TGS-2020504648	1 Oct 2026 - 3 Nov 2026	SIGN UP Now Registration for the Oct 2026 intake closes on 23 Sep 2026.

Note: A*STAR SIMTech and A*STAR ARTC reserve the right to change the class/schedule/course fee or any details about the course without prior notice to the participants.

Announcement:

From 1 Oct 2023, attendance-taking for SWDA-approved/SWDA-funded courses must be done digitally via the Singpass App. More information may be viewed here.
Participants will be provided with digital course materials when attending our courses. Please note that printed copies will not be available.

Sessions

: Full day

: Morning

: Afternoon

: Evening

Quick Links

Browse our course directory

Subscribe to our mailing list