ArduCode: Predictive Framework for Automation Engineering

TL;DR

ArduCode introduces a machine learning framework that assists automation engineers in classifying automation code, finding similar code snippets, and recommending hardware components, thereby reducing development iterations.

Contribution

The paper presents a novel ML-based architecture for automation engineering tasks, including code classification, similarity search, and hardware recommendation, validated on large real-world datasets.

Findings

Code classification F1-score of 72% close to human annotation

High accuracy in finding similar code snippets

Autoencoder-based hardware recommendation with p@3 of 0.79 and p@5 of 0.95

Abstract

Automation engineering is the task of integrating, via software, various sensors, actuators, and controls for automating a real-world process. Today, automation engineering is supported by a suite of software tools including integrated development environments (IDE), hardware configurators, compilers, and runtimes. These tools focus on the automation code itself, but leave the automation engineer unassisted in their decision making. This can lead to increased time for software development because of imperfections in decision making leading to multiple iterations between software and hardware. To address this, this paper defines multiple challenges often faced in automation engineering and propose solutions using machine learning to assist engineers tackle such challenges. We show that machine learning can be leveraged to assist the automation engineer in classifying automation, finding similar code snippets, and reasoning about the hardware selection of sensors and actuators. We validate our architecture on two real datasets consisting of 2,927 Arduino projects, and 683 Programmable Logic Controller (PLC) projects. Our results show that paragraph embedding techniques can be utilized to classify automation using code snippets with precision close to human annotation, giving an F1-score of 72%. Further, we show that such embedding techniques can help us find similar code snippets with high accuracy. Finally, we use autoencoder models for hardware recommendation and achieve a p@3 of 0.79 and p@5 of 0.95.