Our inspiration came from our awareness of how our environment is suffering on a daily basis. We tried to come up with an idea that could help optimize companies' machine usage and lower their environmental impact at the same time.

What it does

Our model analyzes given environmental inputs, and tells the user which machine components' usage can be optimized in order to have a more positive impact on the neighboring environment where the machine is being used.

How we built it

We build our model by first analyzing the machine data we were provided. We then identified outside environmental inputs that might have been useful such as the local location, temperature, humidity, precipitation, and wind speeds. We also had to identify which machine outputs we needed to analyze as the most impactful for the environment. Some factors we decided on were fuel consumption, engine speed, and engine cooling temperature. After the factors were decided, we had to clean/modify the data from the machine we needed for our model. Our model used deep-learning and REST APIs and web-frameworks to analyze the data we were given. Finally, we created a web API to get user-data which would help our model function.

Challenges we ran into

We had a difficult time cleaning the given data and developing a model that could effectively analyze the machine data that was provided.

Accomplishments that we're proud of

We're proud of how we developed our own algorithms for data processing and how we came up with our own methods of generating a model that could operate on the given data.

What we learned

We learned about how to use various libraries in this project and how to scrape data that we needed from outside APIs to help generate a model that could analyze the machine data that was provided.

What's next for GoldenFields

We plan on using our model on factory data, and try to optimize factory equipment to lessen factories' impact on the environment.

Share this project: