Are you a master student planning to write your Master Thesis during spring 2020? Join us on our journey into the future #Siemens
Be part of an open and dynamic workplace where professional and personal development is high on the agenda. By making sustainable energy solutions more cost effective, developing new technologies for the future's smart industry and electrifying passenger and freight transport, we make reality of our vision of a sustainable world.
We are now looking for a student to take on the assignment “Predictive Maintenance via Anomaly Detection using Machine Learning.”
Who we are?
Data Analytics in SIT AB, the digitalization transformation performed by Siemens during the
recent years has had many consequences. One of the most important ones has been
the establishment of processes to collect and maintain useful data in a
database format. On the one hand, the extensive maintenance reports database
provides the company with useful information about unexpected events, component
repair and operation history. On the other hand, multiple sensors placed along
the turbine deliver information about thermodynamic parameters and operating
parameters as the amount of produced MWh. The data analytics department has
been working extensively using this data to automate decision making process
for the power plants operators, as well as to provide useful information to
other departments within SIT AB. Some examples of these projects have been:
creating visualization tools to investigate the operation profile of the
turbines, optimizing the compressor washing time, calculating the available
capacity using thermodynamics models of the engine or optimizing the power
production of the plants according to market and demand forecasts using machine
learning.
The assignment:
This master thesis is part of Siemens efforts to develop advanced maintenance strategies that can help the power plant operators to increase availability and reliability of their assets as well as minimize their CAPEX and OPEX. The final goal of this project is to develop a machine learning pipeline that can detect anomalies in some components of the power plant based on historical sensor data as well of field service data.
- Which are the signals that are relevant in order to evaluate the status of each component of the gas turbine?
Are these signals available? Do they have enough data quality? Is the resolution (sampling time) enough for the analysis?
How are the signals of different components linked with each other? Abnormal behavior of system X will be reflected in the sensor values of system Y?
Is there any kind of additional data that can provide information about the status of the machine? Do the fleet historical service reports provide additional information?
The second step consist of selecting one of the subsystems analyzed in step one and develop the machine learning pipeline that can detect the potential anomalies. The following steps should be performed:
- Which are the frameworks available for anomaly detection in industrial equipment? (literature review of unsupervised learning, semi-supervised learning, supervised learning, condition monitoring based with physic-based models etc…)
Which are the machine learning based algorithms for anomaly detection in time series (HDBSCAN, EMM, DTW, Deep Neural Networks etc…).
Implement the reviewed algorithms in a pipeline and compare them in qualitative terms.
Implement clustering algorithms to detect similar anomalous patterns during the whole history of the subsystem operation and check if it is possible to match these patterns with the operational data of the same subsystem in a different gas turbine.
Develop future working lines and improvements to the work developed.
Students will be provided with access to all the needed data. They will be working closely with domain experts with strong backgrounds in thermodynamics, reliability analysis, data mining, machine learning and mathematical optimization.
Your Profile:
- The project is suitable students with academic background in energy systems, engineering, computer science, mathematics or another relevant field.
As a student you have strong analytical skills and solid mathematical background.
Besides, you are interested in data analytics (especially in prescriptive analytics and hold good programming skills (preferable: Python, R or Julia).
We consider meritorious skills the knowledge of machine learning oriented libraries (scikit-learn or caret), data handling libraries (Pandas or tidyverse).
We also consider meritorious SQL knowledge.
Application:
Do not hesitate - apply today via
siemens.se/jobb ref nr 179986 and no later than 2019-11-30.