This is a Call for Presentations to learn, share and discuss the engineering and product aspects of Artificial Intelligence (AI), including the larger issues that surround the ecosystem:
- Tools - open source, proprietary, custom built.
- Applications of AI to solve different problems
- Engineering approaches
- Managing large volumes of data, including different types of data, labeling data, and data quality.
Anthill Inside sessions will be held once a month, to discuss these above issues. If you work on these aspects of AI, share your work. Or, suggest a topic on which you’d like to have a discussion.
For more details, call +91-7676332020 or write to email@example.com
Predictive Maintenance in HVAC Industry
Heating, Ventilation, Air Conditioning (HVAC) equipment plays a very critical role in commercial buildings by maintaining thermal comfort and indoor air quality. The performance of a HVAC equipment becomes prominent when it malfunctions. So, maintenance is a major focus area for HVAC owners and operators. Maintenance is done either by replacing parts at regular intervals even when those are working (Preventive Maintenance) or by replacing the parts only when there is failure (Reactive Maintenance). Predictive Maintenance avoids the drawbacks of Preventive Maintenance (under utilization of a part’s life) and Reactive Maintenance (unscheduled downtime). Based on the health of an equipment in the past, future point of failure can be predicted in Predictive Maintenance. Thus, replacement of parts can be scheduled just before the actual failure. Traditionally, predictive maintenance is being done using rule based techniques. With the advent of connected sensors (IoT), data from HVAC equipment is continuously collected and fed to Machine Learning based systems to predict its future health.
In this session, I am going to discuss how the HVAC industry is utilizing Machine Learning for the purpose of Predictive Maintenance.
- What is HVAC?
- Types of Maintenance in HVAC Industry
- Predictive Maintenance: Definition, Benefit & Goals
- End to End Architecture of Predictive Maintenance System
- Data Science Life Cycle for Machine Learning based Predictive Maintenance
- Conversion of Business Problem into Machine Learning Problem
- Collection of Relevant Data (HVAC Health, Maintenance, Asset Metadata)
- Aggregation of Data from different sources
- Data Preprocessing
- Feature Engineering specific to HVAC Health & Maintenance Data (Time Series)
- Selection of relevant Cross Validation technique
- Selection of Algorithms based on nature of the data & maturity of Machine Learning Pipeline
- Model Deployment: Batch Scoring
- Monitoring & Maintenance of the model
Knowledge about fundementals of Machine Learning
Arnab Biswas is a Data Scientist working in EcoEnergy, Carrier Global Corporation. He has 15 years of experience in Software Development in Telecom, Networking & HVAC industry. As a developer, he has developed highly scalable, distributed, fault tolerant softwares to manage/provision IoT devices. In Machine Learning, his current area of focus is Predictive Maintenance for HVAC Equipments using Big Data. As a Core Team member of DataKind Bangalore, he has volunteered for different Non Profit Organizations in India helping them address their Data Science related needs. He contributes to StackOverflow and different Open Source Softwares.
- Who is the speaker?: https://arnab.blog/about/
- Recording of the session presented as a part of “AI for Industrial Application at TWIMLFest”: https://youtu.be/dFpE5G6QSqI
- Kaggle Kernel explaining nature of data used for Predictive Maintenance: https://www.kaggle.com/arnabbiswas1/predictive-maintenance-exploratory-data-analysis