Introduction
Predictive maintenance is essential in diverse application areas, such as manufacturing industry, information, and technology, aerospace, heavy-machinery industry, etc. to estimate the future performance of a subsystem or a component to make RUL(Remaining Useful Life) estimation.
We can monitor our assets(can be any device or machine, which may lead to breakdown ) in real-time via sensors and based on the sensor data patterns we can predict when we are going to have a break-down of assets.
- Production systems deteriorate with the time and need maintenance. The regular way to keep the system good is to apply preventive maintenance practices, in the case of clearly detected malfunctions or equipment breakdowns.
- All this affect the quality, cost and in general, productivity. Other than this, the uncertainty of machine reliability at any given time also impacts on product/production delivery times.
Project WorkFlow
- Using cloud IOT core the collection of data from various assets at different geographical locations in different data forms.
- Stream real-time data and batch data with cloud pub/sub.
- Batch data will be stored at cloud storage and for data preprocessing data will be load into cloud data flow.
- Cloud data flow consume the stream data from cloud pub/sub and run the predictive model on both batch data and stream data using cloud ML engine.
Predictive Maintenance Solution Stack
- We have sensors attached with assets to monitor critical parameters in real-time such as temp, voltage, CPU usage etc.
- Process the data from sensors and analyze them in real-time to identify and report critical events without wasting any time (eg. sudden increase in temperature, irregular voltage change) and take preventive measures accordingly.
- After processing the data, store the data in data warehouse so that analysis can be on that data for predictive analysis to compute RUL(Remaining Useful Life) estimation of assets.
Critical parameters and features of real-time predictive system :
- The predictive maintenance solution provides event-based prediction by learning from historical data as well as learning from the new real-time data.
- Prediction based on the data directly from sensors and learning normal behavior of assets and identifying any abnormal behavior.
- Prediction of fail events using classification models for different failure events.
Predictive Analysis Architecture
For Iot based predictive analysis, we have sensors to monitor data at different locations, all the assets namely A1, A2, A3, A4 are connected to a common network via the Cloud IOT Core. The Cloud IOT Core transfers the real-time data to Cloud pub/sub which creates a data stream that can be consumed directly. Now we had two options available to process the stream of data:
- Batch processing
- Stream processing
In Batch processing, we store the data in a Cloud Storage and apply machine learning algorithms using Cloud ML Engine and other analysis tools later on to predict the breakdown of our assets.
In-Stream processing, the data stream is consumed by Cloud Dataflow streaming services and it analysis the data real time and based on the real-time data it does predictions and identifies any breakdown events and reports them. The data is then stored in the Big Table.
Predictive Maintenance Analytics Pipeline.
Collecting targeted data
The targeted data may reside in remote locations and getting it to the analysis pipeline includes sensors, meters, supervisory control, etc.
An efficient solution has to be flexible enough to collect data from all of these remote data sources to learn and continually make better, more informed business decisions.
Determining analytics pipeline
Establishing an advanced analytics pipeline based on the specific operation. For example, Cloud analytics should be balanced enough to reduce the burden of streaming perishable PdM data on our cloud deployment.
A distributed approach is followed to detect and respond to local events at Cloud dataflow consumer step as they happen, taking action immediately on streaming data, while simultaneously integrating additional data sources in the cloud.
Technology Stack
- Python
- Flask
- Cloud IOT Core
- Cloud pub/sub
Conclusions
- We can Reduce unplanned downtime of assets to 3.5%
- Improve the quality of equipment effectiveness
- Reduce maintenance cost of assets
- Increasing ROI on assets, hence increasing profits