Yet Another Predictive Maintenance Article -1
Industry 4.0
Industry 4.0 is the fourth revolution that has occurred in manufacturing. This means computers are connected and communicate with one another to ultimately make decisions without human involvement. Industry 4.0 is the emerging trend towards manufacturing technologies which combines Internet of Things (IoT), Cloud Computing and Artificial Intelligence. Predictive Maintenance is one of the epitome of industry 4.0. The first step to make a factory smarter is enable predictive maintenance (PdM) capabilities.
Why Predictive Maintenance?
Everyday, we depend on many systems and machines. We use a car to travel, a lift go to up and down, and a plane to fly. Electricity comes through turbines and in a hospital machine keeps us alive. These systems can fail. Some failures are an just an inconvenience, while others could mean life or death. Predictive maintenance predicts failure, and the actions could include corrective actions, the replacement of system, or even planned failure. This can lead to major cost savings, higher predictability, and the increased availability of the systems.
Predictive Maintenance
Predictive Maintenance is a method of preventing asset failure by analyzing production data to identify patterns and predict issues before they happen.
Question: Can one predict the break-point of an engine without human intervention ?
Answer: Predictive Maintenance
Predictive maintenance focuses on identifying patterns in sensor which yields data that can indicate changes in equipment condition — typically wear and tear on specific equipment. Predictive maintenance has quickly emerged as a leading Industry 4.0 use case for manufacturers and asset managers. Implementing industrial IoT technologies to monitor asset health, optimize maintenance schedules, and gaining real-time alerts to operational risks, allows manufacturers to lower service costs, maximize up-time, and improve production throughput.
HOW TO DO PREDICTIVE MAINTENANCE?
The four major components required for building up the pdM systems are:
- Data
Sensors installed in machines can be used for capturing the required data. Not any kind of data can be beneficial for prediction, we require..
The “USEFUL” Data
For pdM, data can be gathered from following sources:
- Failure history
- Maintenance history
- Machine conditions and usage
- Machine features
- Operator features
These data therefore provide the backbone for predictive maintenance system.
2. Problem definition
- Are we trying to classify whether machine is going to fail or not?
- Are we predicting the remaining useful time of the machine?
According to the our desired definition, we will choose the corresponding predictive algorithms for the system.
3. Predictive Algorithms
Here we go again…
Machine Learning algorithms such as Neural Network, Random Forest, K-means clustering, etc. can be used for predictive maintenance.
As per the problem definition, we decide the appropriate algorithm or model and train it with the gathered data and the model predicts the output. The data we captured doesn’t solely suffice for the model to work, we require cleaned and labelled dataset for our pdM system.
4. Platform to Integrate
After gathering enough data, exploring the definition and choosing the right model, we will look for the procedure to integrate all into one system. We require cloud storage to store the sensor-collected data and we can build our model over cloud by using as-a-service provided by it. The results can be generated in form of report or visualization. The model can also be used for real time prediction as well.
CONCLUSION
- We first looked at the how industry 4.0 will revolutionize the upcoming manufacturing industries by integration of several cloud technologies and AI.
- We learnt about the benefits of the predictive maintenance and why it is required in the industry.
- Lastly, we discussed the overview of how pdM systems can be deployed in the industry.
In Part-2, I will discuss about implementation of pdM system for Turbo Fan Engine dataset and give more insights about predictive Maintenance.
REFERENCES
