Artificial Neural Network Approach to Temperature Control Presented by Jeff Boettcher.

Slides:



Advertisements
Similar presentations
Perceptron Lecture 4.
Advertisements

G53MLE | Machine Learning | Dr Guoping Qiu
NEURAL NETWORKS Perceptron
Heat Conduction of Zinc Specimen Femlab Simulation Measurement Calibration Technique: Effects of Heat Loss Through Specimen Surface Area.
Electric Drives FEEDBACK LINEARIZED CONTROL Vector control was invented to produce separate flux and torque control as it is implicitely possible.
Binary Decision Diagrams1 BINARY DECISION DIAGRAMS.
Laboratory 5: Introduction to LabVIEW. Overview Objectives Background Materials Procedure Report / Presentation Closing.
1 MACHINE LEARNING TECHNIQUES IN IMAGE PROCESSING By Kaan Tariman M.S. in Computer Science CSCI 8810 Course Project.
Introduction to Artificial Neural Network and Fuzzy Systems
A Neural Network Approach to Predicting Stock Performance John Piefer ECE/CS 539 Project Presentation.
Presentation on 6-weeks Training Course Topic: Lab VIEW ( Laboratory virtual Instrumentation Engineering workbench ) Internal guide: Mr. Amit Kumar Application.
Performance of SPIROC chips in SKIROC mode
1 Mehran University of Engineering and Technology, Jamshoro Department of Electronic, Telecommunication and Bio-Medical Engineering Neural Networks Mukhtiar.
An Example of Course Project Face Identification.
LabVIEW Data Acquisition and Analysis Electrocardiogram and Muscle Sympathetic Nervous Activity Jennifer Britton Advisor: Richard Shiavi Biomedical Engineering.
Module 1: Introduction to PLC
LabVIEW Basics Review LabVIEW Robotics Fundamentals.
LabVIEW and MatLab E80 Teaching Team February 5, 2008.
MECH 322 Instrumentation Feedback Temperature Control Performed: 04/20/06 Pablo Araya : I believe I performed 100% of this lab Participation (__/50 points)
The Perceptron. Perceptron Pattern Classification One of the purposes that neural networks are used for is pattern classification. Once the neural network.
Perceptron Networks and Vector Notation n CS/PY 231 Lab Presentation # 3 n January 31, 2005 n Mount Union College.
ME 322: Instrumentation Lecture 37 April 22, 2015 Professor Miles Greiner Proportional control characteristics, Shift register and integral control program.
Instrumentation Overview Spring 2012 The laboratory is a controlled environment where we can measure isolated physical phenomena with a view to eventual.
Handwritten Recognition with Neural Network Chatklaw Jareanpon, Olarik Surinta Mahasarakham University.
Design and Implementation of a Dynamic Data MLP to Predict Motion Picture Revenue David A. Gerasimow.
Linear Discrimination Reading: Chapter 2 of textbook.
CSSE463: Image Recognition Day 11 Lab 4 (shape) tomorrow: feel free to start in advance Lab 4 (shape) tomorrow: feel free to start in advance Test Monday.
Support Vector Machines. Notation Assume a binary classification problem. –Instances are represented by vector x   n. –Training examples: x = (x 1,
Locally Linear Support Vector Machines Ľubor Ladický Philip H.S. Torr.
Machine Learning in CSC 196K
SVMs, Part 2 Summary of SVM algorithm Examples of “custom” kernels Standardizing data for SVMs Soft-margin SVMs.
Introduction to LabVIEW
1 An introduction to support vector machine (SVM) Advisor : Dr.Hsu Graduate : Ching –Wen Hong.
Proportional-Integral-Derivative (PID) Temperature Control & Data Acquisition System for Faraday Filter based Sodium Spectrometer Vardan Semerjyan, Undergraduate.
Introduction to LabVIEW. Overview Objectives Background Materials Procedure Report/Presentation Closing.
Plot Diagram.
Introduction to LabVIEW
Module 1: Introduction to PLC
My Tiny Ping-Pong Helper
SCADA for Remote Industrial Plant
How SCADA Systems Work?.
Ranga Rodrigo February 8, 2014
CSSE463: Image Recognition Day 11
A Support Vector Machine Approach to Sonar Classification
AV Autonomous Vehicles.
Control Systems An Overview Computer Integrated Manufacturing
Lesson 2: Introduction to Control programming using Labview
R-CNN region By Ilia Iofedov 11/11/2018 BGU, DNN course 2016.
Neural Networks: Improving Performance in X-ray Lithography Applications ECE 539 Ryan T. Hogg May 10, 2000.
Students: Meiling He Advisor: Prof. Brain Armstrong
Control Systems An Overview Computer Integrated Manufacturing
Bird-species Recognition Using Convolutional Neural Network
CSSE463: Image Recognition Day 11
Introduction to LabVIEW
Introduction to LabVIEW
Aleysha Becker Ece 539, Fall 2018
MACHINE LEARNING TECHNIQUES IN IMAGE PROCESSING
Binary Logic.
MACHINE LEARNING TECHNIQUES IN IMAGE PROCESSING
Vectors and Matrices In MATLAB a vector can be defined as row vector or as a column vector. A vector of length n can be visualized as matrix of size 1xn.
ECE/CS/ME 539 Artificial Neural Networks Final Project
FEEDBACK AMPLIFIERS.
Introduction to LabVIEW
CSSE463: Image Recognition Day 11
CSSE463: Image Recognition Day 11
Introduction to LabVIEW
Measuring the Temperature and Voltage of a Lithium Ion Battery
Introduction to LabVIEW
Labview Based Demo metro-line system
Presentation transcript:

Artificial Neural Network Approach to Temperature Control Presented by Jeff Boettcher

Project Outline u Describe the project purpose u Discuss method used to complete the project u Present results of experiments u Conclusion / Discussion

Project Purpose A reservoir of water is desired to be held at a constant temperature. There are many common approaches to control problems, but here an artificial neural network approach is explored.

Solution Method (General) A temperature sensor was selected, and its output conditioned so that the voltage produced could be easily read into the computer through a data acquisition card and LabVIEW. The water temperature was monitored and, if less than the desired temperature of 75°C, the heater was turned on. If greater than 75°C, the heater was turned off.

Solution Method (SVM) It was known that temperatures under 75°C desired an ON output to the heater, and over 75°C desired an OFF to the heater. With this two state output, a set of SVM training data was easily determined. This data can be seen in the diagram slides. Once “alpha” and “bias” terms were found by SVC training, they were fed into the classification along with the current temperature at each second to produce the binary decision of whether to turn the heater ON or OFF. All SVM calculations performed through the LabVIEW “Run Matlab script” function, with calls to Steve Gunn’s SVM toolbox.

LabVIEW Front Panel

LabVIEW Diagram (Main)

LabVIEW Diagram (Training)

LabVIEW Diagram (Classify)

Results It was found that SVM classification works well for this type of control. The temperature vs. time plot of the control scheme is shown to the right. (Jaggedness of line comes from integer temperature values.)

Conclusion / Discussion While SVM decision making is not claimed to be the best control method available, it is clear by the results that this is a feasible and very functional control method.

References Steve Gunn’s support vector machine toolbox Yu Hen Hu’s support vector machine course notes