Advanced Predictive Maintenance Jobs in Chennai - dow chemical international pvt. ltd.
Job Description
Advanced Predictive Maintenance – Modelling/ Pre-processing ENGINEER(female only)
Location:- Chennai
The Advanced Predictive Maintenance team located within the Central Engineering Chennai center, is looking for a talented Engineers to support remotely various maintenance and reliability improvement initiatives of critical rotating equipments for DOW plants spread across the globe. This is an exciting opportunity that can provide the selected candidate a significant growth and exposure opportunities across various kind of rotating equipments within DOW plants globally & as well as the Reliability & Maintenance function.
This role supports the improvement of all aspects of reliability, maintenance and operations work processes and to collect & analyze data that in turn will be used to further optimize our processes.
Ideal candidate for this role should have Bachelor’s or Master’s degree in Chemical/ Mechanical/ Industrial Engineering. The candidate should have good knowledge of industrial engineering concepts, statistics and computer programming languages gained through coursework or projects.
Key Responsibilities:
· Support Sensor Mapping to Equipment
o Identify relevant sensor tags (IP.21 in-scope currently) to equipment and create a tag mapping between sensor and functional location.
o Mapping will use a pre-defined set of sensor aliases so that aggregate and transfer learning models are possible.
o Required to analyze P&IDs, working with plant/site reliability engineers, and statistical analysis of time series data.
· Provide Failure Event pre-processing
o Exporting historical work order and work notification data for in-scope equipment from SAP interface and cleanse to create cleansed failure event dataset.
o Investigate historical failure events through a combination of site focal point interviews and through analytical exploration.
· Offline Condition Identification
o Analyze to exclude periods of history from model training and testing due to unrelated plant events (turnarounds, disruptions) or equipment operating states (not operational, start-up or shut-down states).
o Analyze to identify relevant sensor and create business logic for removing both historical and online time periods where offline conditions occur.
· Anomaly Detection and Failure Signature Modeling
o Perform statistical analysis and modeling using the preprocessed dataset to develop anomaly detection and failure signature models using a combination of the Mtell interface and external applications for model development and diagnostics (SAS JMP, python/R, Aspen Tech Process Explorer).
o The model development steps will involve selecting relevant time periods, failure events, and parameter tuning for training and testing models using the available supervised and unsupervised machine learning tools available in the Mtell interface.
o This task would be overseen by a senior data scientist to confirm model quality prior to deployment.
· Support site teams and networks using LEAN fundamentals: Maintenance Group Leaders Team, Planner Networks (Daily & Turnaround), Work Coordinator Network and Scheduler Networks, Reliability Engineer Network, Production Planning
· Explore latest technologies in data mining and modeling, and their applications in context of maintenance and reliability projects
Preferred Qualifications:
- Bachelors/Masters of Science degree in Industrial, Mechanical, or Chemical Engineering from AICTE approved Universities; Diploma/ certificate courses in data science/ analysis will be an added advantage.
- Background in scripting languages (VBA), either through coursework or projects
· Solid data analysis skills, and knowledge of statistical and analytics software such as R, JMP, Python.
· Basic programming logic (Boolean conditions, business logic)
· Exposure to SAP/ Aspen Tech Mtell will be an added advantage.
Additional Experiences preferred but not required:
- 3-5 years’ of relevant Experience in areas such as manufacturing, maintenance, application of LEAN principles, advanced data analytics/modeling
- Six Sigma Experience