Intelligent Systems Report December 1995 Volume 12 No. 12
AUTOFACT '95
Manufacturers Want More
Power and Smarts
By David Blanchard/Editor
The state of the art in manufacturing technology has changed dramatically just within the past five years, thanks in large part to the increasing influence of virtual reality (VR) and 3-D simulation, as well as intelligent software. As both hardware and software continue to become more user-friendly, manufacturers in ever-growing numbers are beginning to rely on the competitive edge possible by implementing intelligent systems. Evidence of this technological evolution was on display at the AUTOFACT conference and exhibition, held last month in Chicago, Ill.
Consider, for a moment, the applications on display at Superscape's exhibition hall booth. Motorola University (Schaumburg, Ill.), a training campus for the chip manufacturer, demonstrated VR software that allows the user to assemble pagers on a virtual manufacturing assembly line. This application was tested by using a control group, a desktop VR group and a group wearing head-mounted displays (HMDs) to train workers to assemble pagers. The two groups using VR products from Superscape (Palo Alto, Calif.), a vendor of VR software development tools, won out over the control group in terms of learning capability and performing fewer errors.
Smart Machines (San Jose, Calif.) used a robot to demonstrate issues concerning burning-in semiconductor chips. This demonstration illustrates how the robot works with a customer's equipment as well as to test equipment while in the design phase. Sony (Japan), meanwhile, used VR software to model its Watchman video player because VR can show how products in the design phase can be viewed in all dimensions. Changes can be made to the design in real time.
Making wipers more intelligently
Trico Products Corp. (Southfield, Mich.), a supplier of automotive windshield wipers, is using knowledge-based systems as their preferred tool to capture, retain, apply and evolve their best product development processes. According to Trico's Jeffrey Blake, "Knowledge-based systems have given Trico the opportunity to evaluate and redefine its entire approach to product development, not just product design."
Blake pointed out that these intelligent systems have made it possible for Trico to perform detailed analysis across a broad spectrum of product development activities, from conceptual design through cost accounting. The benefits have been impressive: In one instance, Trico was able to respond to a request in two hours, when previously it would have taken two days to run the cases, provide graphical data and reports, and make design recommendations. In another instance, a $60,000 tooling charge was saved when the intelligent system detected a design in violation of manufacturing rules.
Advantages of knowledge-based systems
Knowledge-based engineering systems provide a number of significant advantages for a computer-aided design (CAD) organization, reported Gavin Finn, senior vice president of Stone & Webster Advanced Systems Development Services (Boston, Mass.), a developer of intelligent systems for manufacturing applications. Among the most advantageous benefits are the following:
- "Knowledge-based systems can multiply the know-how of skilled specialists by making it available to all engineers and designers through the CAD system network.
- "Knowledge-based systems can drive parametric CAD functionality, providing the ability to generate new designs automatically from changed input parameters with little or no manual intervention.
- "Knowledge-based systems can generate preliminary designs from customer specifications, create drawings, calculate material and labor costs, and produce bid estimates and proposals, often in a matter of hours.
- "Knowledge-based design systems can contribute significantly to reduction of lead times through efficient automated design, elimination of the need for physical mockups, and reduction of design iterations due to improved first-pass design quality," according to Finn.
GM simulates truck designs
General Motors Truck Group (Detroit, Mich.) has decided to use 3-D simulation software from Deneb Robotics Inc. (Auburn Hills, Mich.) to improve time-to-market and quality. GMTG believes that virtual prototyping and virtual manufacturing technologies will help reduce tooling development costs, optimize manufacturing operations and time-to-market "through the ability to eliminate equipment design problems with simulation prior to actual creation of manufacturing tools," according to John Schweikert, GMTG's group director-manufacturing engineering.
"Our envisioned process will validate up-front product/process interfaces, tooling, operational ergonomics, workplace layout, and total process flow prior to production tool build," Schweikert continued. "This will optimize total cycle time from concept initiation to start of pilot build by allowing earlier identification and correction of tooling, operator and layout problems. GMTG will also be able to better link up-front design alternatives with the Truck Bill of Process to optimize Design for Manufacturability/Design for Assembly and capture the lessons learned."
Sandia develops intelligent CAD tool
Sandia National Laboratories (Albuquerque, N.M.) has developed an intelligent CAD tool, called HoldFast, that automatically designs fixtures and pallets. According to its developers, Randy Brost and Ralph Peters, "the HoldFast algorithm enumerates all possible fixtures considering the workpiece shape, the task constraints and the fixture kit." Thus, it can find a fixture design if one exists, and it can also find the optimal fixture, in far less time than previous methods.
Brost and Peters demonstrated how HoldFast was used to design and build fixtures for finish-machining and drilling of a cast part for prototype fabrication and mass production fabrication. Pallet fixtures using HoldFast were designed for the vertical assembly of a personal cassette player as well as a glue gun.
When in doubt, consider hybrid systems
Santosh Ananthraman, manager of the Advanced Technology Group at Neural Applications Corp. (Coralville, Iowa), summarized the influence of intelligent systems in manufacturing with his presentation, which looked at neural networks, fuzzy logic, genetic algorithms and expert systems. "These intelligent techniques are extremely powerful tools," he said, "and depending on the process at hand, the right combination of these tools should be employed together with classical methods to achieve the desired system response."
Ananthraman explained that "process optimization solutions to real-world prediction, classification and control problems can be provided using hybrid systems developed using a combination of classical and novel methods." Besides the above-named technologies, he also included agile manufacturing, system modeling, sensor technology and virtual reality simulations. Not coincidentally, Neural Applications has introduced an intelligent process control software tool called Aegis that allows a user to utilize many of these technologies (see "Intelligent Applications").
Despite the subtle sales pitch, though, Ananthraman's main point was right on target: With manufacturers being bombarded on all sides by the latest technological marvels, oftentimes the best and most sensible route to success involves hybrid systems. There is almost never a case when one and only one intelligent technology or product will solve the problem, but by implementing a well-considered combination of systems, the real-world return on investment can be considerable.
For more information
For more extensive coverage of the AUTOFACT '95 Conference & Exhibition, including an in-depth look at company announcements and new product introductions, refer to the December 1995 issue of our sister publication, Intelligent Manufacturing. To receive a free copy, call Lionheart Publishing at (800) 392-7294, ext. 204. You will also be given an opportunity to take advantage of a charter subscription to IM.
Click here to return to Table of Contents for the ISR December issue
ISR: Intelligent Systems Report Copyright © 2020 - AIWeek Inc. All rights reserved.