An official website of the United States government
Recent advancements in physics-informed machine learning have contributed to solving partial differential equations through means of a neural network. Following this, several physics-informed neural network works have followed to solve inverse problems arising in structural health monitoring. Other works involving physics-informed neural networks solve the wave equation with partial data and modeling wavefield data generator for efficient sound data generation. While a lot of work has been done to show that partial differential equations can be solved and identified using a neural network, little work has been done the same with more basic machine learning (ML) models. The advantage with basic ML models is that the parameters learned in a simpler model are both more interpretable and extensible. For applications such as ultrasonic nondestructive evaluation, this interpretability is essential for trustworthiness of the methods and characterization of the material system under test. In this work, we show an interpretable, physics-informed representation learning framework that can analyze data across multiple dimensions (e.g., two dimensions of space and one dimension of time). The algorithm comes with convergence guarantees. In addition, our algorithm provides interpretability of the learned model as the parameters correspond to the individual solutions extracted from data. We demonstrate how this algorithm functions with wavefield videos.
more »
« less
Synergizing Machine Learning with ACOPF: A Comprehensive Overview
Alternative current optimal power flow (ACOPF) problems have been studied for over fifty years, and yet the development of an optimal algorithm to solve them remains a hot and challenging topic for researchers because of their nonlinear and nonconvex nature. A number of methods based on linearization and convexification have been proposed to solve ACOPF problems, which result in near-optimal or local solutions, not optimal solutions. Nowadays, with the prevalence of machine learning, some researchers have begun to utilize this technology to solve ACOPF problems using the historical data generated by the grid operators. The present paper reviews the research on solving ACOPF problems using machine learning and neural networks and proposes future studies. This body of research is at the beginning of this area, and further exploration can be undertaken into the possibilities of solving ACOPF problems using machine learning.
more »
« less
- Award ID(s):
- 1851602
- PAR ID:
- 10515350
- Publisher / Repository:
- Electric Power Systems Research Journal
- Date Published:
- Journal Name:
- Electric Power Systems Research Journal
- ISSN:
- 2406-10428
- Subject(s) / Keyword(s):
- AC optimal power flow, machine learning, neural network, physics-informed
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Soner, Mete (Ed.)We develop a backward-in-time machine learning algorithm that uses a sequence of neural networks to solve optimal switching problems in energy production, where electricity and fossil fuel prices are subject to stochastic jumps. We then apply this algorithm to a variety of energy scheduling problems, including novel high-dimensional energy production problems. Our experimental results demonstrate that the algorithm performs with accuracy and experiences linear to sub-linear slowdowns as dimension increases, demonstrating the value of the algorithm for solving high-dimensional switching problem. Keywords. Deep neural networks, forward-backward systems of stochastic differential equations, optimal switching, Monte Carlo algorithm, optimal investment in power generation, planning problemsmore » « less
-
Problem solving is a vital skill required to be successful in many engineering industries. One way for students to practice problem solving is through solving homework problems. However, solutions manuals for textbook problems are usually available online, and students can easily default to copying from solution manual. To address the solution manual dilemma and promote better problem-solving ability, this study utilizes novel homework problems that integrate a video component as an alternative to text-only, textbook problems. Building upon research showing visuals promote better learning, YouTube videos are reversed engineered by students to create new homework problems. Previous studies have catalogued student-written problems in a material and energy balance course, which are called YouTube problems. In this study, textbook homework problems were replaced with student-written YouTube problems. We additionally focused on examining learning attitudes after students solve YouTube problems. Data collection include attitudinal survey responses using a validated instrument called CLASS (Colorado Learning Attitudes about Science Survey). Students completed the survey at the beginning and end of the course. Analysis compared gains in attitudes for participants in the treatment groups. Mean overall attitude of participants undergoing YouTube intervention was improved by a normalized gain factor of 0.15 with a small effect size (Hedge’s g = 0.35). Improvement was most prominent in attitudes towards personal application and relation to real world connection with normalized gain of 0.49 and small effect size (Hedge’s g = 0.38).more » « less
-
Homework problems from many textbooks have solutions manuals on the Internet. Students find solutions manuals and focus on getting the right answer put little or no effort on learning. Problem solving is a signature skill of engineers that is in high demand across industries. Here, problem solving is employed when students apply course concepts to reverse engineer YouTube videos and create new homework-quality problem statements and solutions. This research seeks to examine the rigor of YouTube problems and the effect of YouTube problems on the problem-solving skills of students. A quasi-experimental, treatment/control group design is employed and data is collected and evaluated using a variety of tools. The rigor of YouTube problems is examined using the NASA Task Load Index (TLX). Problem solving skill are examined using Problem definition, representing the problem, organizing information, calculations, evaluating the solution, solution communication, and self-assessment (PROCESS) and other tools.more » « less
-
Workplace engineering problems are different from the problems that undergraduate engineering students typically encounter in most classroom settings. Students are most commonly given well-structured problems which have clear solution paths along with well-defined constraints and goals. This paper reports on research that examines how undergraduate engineering students perceived solving an ill-structured problem. Eighteen undergraduate civil engineering students were asked to solve an ill-structured engineering problem, and were interviewed after they completed solving the problem. This qualitative study is guided by the following research question: What factors do students perceive to influence their solving of an ill-structured civil engineering problem? Students’ responses to seven follow-up interview questions were transcribed and reviewed by research team members, which were used to develop codes and themes associated with these responses. Students’ transcripts were then coded following the developed codes. The analysis of data revealed that students were generally aware of the main positives and negatives of their proposed solutions to the ill-structured problem and reported that their creativity influenced their solutions and problem solving processes. Student responses also indicated that specific life events such as classes that they had taken, personal experiences, and exposure to other ill-structured problems during an internship helped them develop their proposed solution. Given students’ responses and overall findings, this supports creating learning environments for engineering students where they can support increasing their creativity and be more exposed to complex engineering problems.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- The DOI is not currently available.
