I am a software developer working for past 1 year 9 months in Siemens Technology and Services pvt limited, India after completing my Bachelor's in Electronics and Communication Engineering from SRM University, Chennai.
My domain of industry experience is industrial automation and digitisation.I have been working for the first 6 months as a Software Tester for Total Integrated Automation(TIA Portal), which is indeed the largest software platform for Industrial Automation developed by Siemens. I was mainly assigned for System Testing of usability/integration of various industrial PLC like S7- 300, 400 manufactured by Siemens with TIA portal.I have also worked on developing test automation scripts.
Recently for past 1 year 3 months, I have been assigned to work on Firmware development of Industrial motor controller devices from Siemens (SIMOCODE, Soft Starter) using technologies like Embedded C and HTML 5.
In parallel with my daily job, I have successfully completed my Post Graduate Diploma in Data Science in the academic year 2019-2020.
I am also assigned to work on machine learning projects from Siemens and have been recently working on Model Development for predicting unexpected industrial motor failures and their probable lifetime . I have learned and used technologies like python(pandas,numpy,seaborn,matplot,scikitlearn,etc),SQL and tensorflow.

Few of the Interesting Pet projects i have worked on apart from my professional Experience are :
1>Development of a Text Reading Android application for the Visually Impaired people that can read primarily from pamphlets,textbooks,etc in a cutomised and user friendly manner to the users as in mentioning the specifications of the line and paragraph which is being read aloud in the text.Moreover,the users are also given an option to choose the paragraph or particular section of a page instead of reading it aloud. Developed Image process algorithms from scratch using OpenCV , Java in Android Studio. Now, I would like to extend my application with machine learning so that it can be used for real time object recognition using Deep Learning Techniques and Raspberry Pi zero W.

2> Prediction of Industrial Motor failure using Machine Learning: Given the motor faults data we obtained from an Industrial Manufacturer, we had mainly four types of data sets: datasets with motor faults caused due to Overvoltage, undervoltage,short-circuit and normal faults. On consolidating the data, we had voltage ,current torque and speed ratings of the motor at different instants of time.
The data provided to us was not perfectly clean data and had erroneous possible instances of a running motor. We analysed the maximum current imbalance , maximum voltage imbalance during the running instances which was roughly around 50 percent and 60 percent approximately, which was way higher than the recommended 2-3 % current/voltage imbalances. Derived Metrics such as temperature increase in motor windings due to voltage imbalance was also analysed and was found at a maximum value of 50 percent, which was much higher than the standard allowed limit for different classes of Industrial motor.
Although the data , provided to us gave me an insight into all possible features which can be considered for predicting motor failure , we still need to obtain more samples of data with higher sampling rate .Hence, for model creation we are working on simulating highly sampled data using Python/MATLAB. Thus , this is still an Ongoing project and we are exploring more options of generating useful data.
3> One of the interesting project I have started to work on my own , is the classification of sound patterns between a faulty and non-faulty running motor. Such models if deployed , can help to automatically trip a running faulty motor at a factory floor plant. This project uses Deep Learning and basic understanding of Frequency conversion of time variant sound signals for discretion.
4> Few of the analytical projects covered as a part of my Post Graduate Diploma Course include prediction of credit defaulters from real time data from kaggle credit card fraud detection competition, predicting customers who are likely to churn out of a telecom company, predicting customer conversion ratio for an edutech company,etc.