A Modular Ice Cream Factory Dataset on Anomalies in Sensors to Support Machine Learning Research in Manufacturing Systems

Aim:

           The aim of creating a modular ice cream factory dataset on anomalies in sensors to support machine learning research in manufacturing systems is to provide a valuable resource for the development and evaluation of machine learning models and anomaly detection algorithms in the context of manufacturing.

Abstract:

              A small deviation in manufacturing systems can cause huge economic losses, and all components and sensors in the system must be continuously monitored to provide an immediate response. The usual industrial practice is rather simplistic based on brute force checking of limited set of parameters often with pessimistic pre-defined bounds. The usage of appropriate machine learning techniques can be very valuable in this context to narrow down the set of parameters to monitor, define more refined bounds, and forecast impending issues. One of the factors hampering progress in this field is the lack of datasets that can realistically mimic the behaviors of manufacturing systems. In this paper, we propose a new dataset called MIDAS (Modular Ice cream factory Dataset on Anomalies in Sensors) to support machine learning research in analog sensor data. MIDAS is created using a modular manufacturing simulation environment that simulates the ice cream-making process. Using MIDAS, we evaluated three different supervised machine learning algorithms (Logistic Regression, Decision Tree and Random Forest) for two different problems: anomaly detection and anomaly classification. The results showed that Decision Tree is the most suitable algorithm with respect to model accuracy and execution time. We collect the Modular Ice Cream Factory Dataset from the publicly available, to enable interested researchers to enhance the state of the art by conducting further studies

Existing System:

           This research aims to create an effective prediction model using different types of ML methods to detect anomalies in Ice cream factory. First of all the datasets are collected, and then the preprocessing is accomplished via the missing values imputation. The Mean Value Imputation (MVI) method is used to impute the missing values of the dataset. Then, the categorical feature values are converted to their equivalent numerical values using the One Hot Encoding (OHE) technique. Shows that all  datasets used in this work have a object and numerical features as converted into numerical features is used to alleviate this issue. After completing the initial preprocessing, the datasets feature values are scaled using different Feature Scaling techniques. The result showed that Multilayer Perceptron is the most suitable with respect to accuracy. But the accuracy is less. Then now we create a new system for better anomaly prediction. So now we move on to the proposed system.

Proposed System:

            This research aims to create an effective prediction model using different types of ML methods to detect anomalies in Ice cream factory. First of all, the datasets are collected, and then the preprocessing is accomplished via the missing values imputation and Create an instance of RFE with the classifier and the desired number of features to select Logistic Regression classification of modeling and performance evaluation. Then we are using Decision Tree, Logistic regression and Random Forest Algorithm for prediction accuracy. Decision Tree gives a best results with respect to high accuracy. Compare to existing system our new system gives results are more Accuracy.