JOURNAL OF COMPUTING, VOLUME 3, ISSUE 5, MAY 2011, ISSN 2151-9617 HTTPS://SITES.GOOGLE.COM/SITE/JOURNALOFCOMPUTING/ WWW.JOURNALOFCOMPUTING.ORG 38 Butter Churning Process Automating Based on Acoustic Signals Ahmad Aljaafreh Abstract— This Paper describes a system for automating butter churning process by utilizing digital signal processing techniques based on the the sound of the churning process. Butter churning is a process to extract butter from the whole milk by mechanical motion. To the best of our knowledge we are the first who thinks of automating butter churning process based on churning acoustic signature. The argument of this paper is that sound of the churning varies according to the phase of the whole process. The churning process is divided in this paper into three phases. The first, is the churning phase, the second is the butter-begin phase, where the butter start coming, and the last phase is the butter collection phase, where the butter grains is gathered and the churning process ends. This paper characterizes the sound of each churning phase. A feature vector is extracted from each phase sound based on spectrum distribution. Artificial neural network is used in this paper as a classifier. Results show that the sound of each phase can be used to characterize the phases of the churning process. The shushing sound of the butter grains motion is recognized in this paper and can be utilized to automate the churning process. This paper also describes the design and in implementation of the system using dsPIC digital signal controller. Index Terms— Butter Churning, Acoustic Signal, Classification, Neural Network, dsPIC. ——————————  —————————— 1 INTRODUCTION butter churn is a device used to make butter by shaking up the whole milk (or cream). The device agitates the cream by the mechanical motion, which dis- rupts the fat in the milk. Butter grains are formed by breaking down the membranes that surround the fat. Churning causes these grains to fuse with each other and form the butter. The liquid that is left out without fat is called buttermilk. Because of the technological develop- ment butter churns have varied over time. First, butter churns were made of animal materials like animal skins. Later other materials like wood, metal or glass were used as containers to churn butter. After that electrical centrif- ugal cream separators were used. Churning process is still a manual process, where human being makes the decision when to end the churning process, when the op- timal quantity or equality of fat or butter milk is collected. Human being depends on external devices to decide when to finish the churning process, like the device that measures the fat density on the buttermilk. This research has two major objectives, the first is to automate the but- ter churning process, and the second one is to improve the churning process efficiency. In this research we sug- gest a new method to detect the end of the churning pro- cess based on the sounds that is emitted from the churn- ing process. We assume that the sound of the churning varies according to the phase of the whole process. A shushing noise is heard when the butter comes [1] or when the cream breaks into butter particles and butter- milk. When the butter is coming, it is easily ascertained by the sound [2]. To the best of our knowledge we are the first who study automating butter churning process based on acoustic noise. This motivates us to analyze the sound of the butter churning. Thus, different churning sounds are recorded to be analyzed. These sounds are analyzed to extract and select the best feature vector that discrimi- nates between the different phases of the churning pro- cess. After that the ripening time is determined by classi- fication of the churning sounds, which affects the charac- teristics of the churning. Effect of physical ripening time of the cream on churning characteristics is explained in [5]. This paper proposes a new, cheap, and efficient method to automate the churning process since automat- ing food industry improves the production efficiency. 2 FEATURE EXTRACTION In feature extraction certain transforms or techniques are used to select and generate the features that represent the characteristics of the sound signal. This set of features is called a feature vector. Feature vectors could be generated in time, frequency, or time \ frequency domain [3]. Fre- quency based feature generation methods, like Fast Fou- rier Transform (FFT), are common approaches in acoustic signature classification. Classification in this paper is based on frequency domain analysis. The overall spec- trum distribution is used to extract features, since we as- sume most of the information of different churning phase's sounds is represented by spectrum distribution [3]. In this paper we used the modified variation of the scheme we developed in [4] for extracting a low dimen- sion feature vector to obtain good classification results. The feature extraction technique of acoustic signals in this paper is based on the low frequency band of the overall spectrum distribution. The low frequency band is uti- lized, because most of the frequency components are harmonics that are based on the angular speed of the but- ————————————————  Author is with the Department of Electrical Engineering, Tafila Technical University, Tafila 66110, Jordan. A