Nearly 1,500 oil and gas (O&G) rigs are located offshore across the globe, the largest share of which are in the North Sea and Gulf of Mexico. The recent trend in O&G industry is to install the subsea processing loads on the seabed for reducing the required space on the platform or even removing the platform altogether. The subsea processes (or subsea factory) include gas compression, boosting, water injection, and separation. Typical power consumption of the Subsea loads is in the range of 5-300 MW, traditionally supplied by local gas turbines or diesel generators. Such power generation strategies have led to significant increase in greenhouse gas emissions. Also, the electric distribution system of O&G platforms is characterized as a weak electric grid, resulting in poor power quality, lower power factor, voltage and current harmonics, voltage notches, and common mode voltages. All these result in increased losses and also affect the long-term reliability.

This research work is mainly focused on identifying the individual components in a hand-drawn schematic diagram, and thus performing simulative analysis of a power converter. YOLOR (You Only Learn One Representation) – the state-of-the-art deep learning-based object detection model is used to detect the electronic components i.e. resistor, capacitor, diode, etc. in a circuit diagram. A Hough transform algorithm is used to trace the horizontal and vertical wire connection, whereas KMeans clustering is used to segregate the points-of-intersection between those horizontal and vertical lines to identify the nodes in the circuit. By using all of this circuit information, a netlist of the circuit is generated – that can be fed into any spice-based circuit simulators. In this work, PySpice – an open-source python module, is used to auto-simulate the identified hand-drawn schematic diagram. In future, this work will be extended to automate the PCB design of the detected hand-drawn circuit diagram. The overall workflow algorithm of this research work is as depicted in the flowchart.

Wireless communication uses radio frequency power amplifiers (RFPAs) to amplify the signal before transmitting. Traditional RFPAs in communication base stations use fixed voltage DC power supplies. For the communication signal with high peak to average power ratio (PAPR), linear RFPAs will be inefficient and excess power will dissipate as heat. Therefore, a larger cooling system will be required and make communication base station system bulky. To improve the efficiency and miniaturize the system, envelope tracking power supplies are being used. Envelope tracking (ET) power supply utilize envelope extractor to obtain the envelope of the transmitted signal waveform. The output voltage is modulated to track the envelope of communication signal and supply the RFPAs. Communication signal will be distorted if the converter switching frequency is less than signal bandwidth. Thus, ET power supplies are required to switch at several tens of MHz for 4G/5G signals.

This project involves technology that will improve the converter system’s power density, efficiency, and operational life across pulsed power applications such as healthcare tech (e.g., MRI) and water purification; where the miniaturized size of the system will also disruptively reduce the cost of downhole well logging tools used in fossil and geothermal energy production. The project is funded by the U.S. Department of Energy’s Advanced Research Projects Agency with a $1 million grant for three years starting in April 2022. Part of the project will include designing a DC-DC converter with a few Kilowatts and the capability to work with high-temperature operations up to 175 degrees Celsius for downhole tools to perform sub-surface characterization and the other part involved power converter development for MRI application.