An Interview with Professor Li Hanxiong of City University of Hong Kong: Taking You Deeper into Intelligent Manufacturing

Lei Feng Network (search "Lei Feng Network (search "Lei Feng Network" public number concerned) "public concern" by: 2016 artificial intelligence Hunan Forum and the self-innovation artificial intelligence Institute unveiling ceremony, many top experts from home and abroad at the meeting to give We made a report and accepted an exclusive interview with Lei Feng. Li Hanxiong, Ph.D., Department of Systems Engineering and Engineering Management, City University of Hong Kong, and Distinguished Professor at Central South University. He has been selected as the National Outstanding Youth Fund (Overseas) winner (2004), the Ministry of Education Yangtze River Scholar (2006), the National “Thousand Person Plan” expert (2010) and IEEE Fellow (2010). For more than two decades, he has been engaged in research on smart manufacturing, focusing on intelligent modeling, design and control of industrial processes, and intelligent decision-making based on data learning. This article has been modified by Professor Li.

What do you think is the most important thing in establishing an intelligent production line?

I think it is standardization and we must eliminate the uncertainty. The main problem in terms of production is uncertainty. Uncertainty affects product quality. Uncertainty includes a variety of uncertainties, such as uncertainty caused by man-made causes. Why do you want to have so many operators in production, because the factory cannot be fully automated. If you want to fully automate, you must remove people. The judgments that people need need to be done by machines, but machines cannot be made like humans. Standardized decision making.

With regard to smart manufacturing, what can you do recently to apply to production?

First of all, the research is divided into several categories. I focus on the academic research done at the university, while the emphasis on the product research is on the industry. Academic research done at the university is equivalent to developing tools. Take a car repair as an example. Car repair is a comprehensive application of a set of tools. University research is equivalent to providing a tool for repairing a vehicle. Repairing a vehicle and tools does not necessarily have a direct link, but a good set of repair tools will definitely improve the speed and quality of repairs. As far as smart manufacturing is concerned, it is a large area. I think no college professor can master all the smart manufacturing. The scope of my research is the electronic packaging, mainly the research of dispensing and curing process, and there are many needs to be studied in this respect. So I think smart manufacturing requires an industry chain alliance and companies work together. The product research of an enterprise must be targeted, and the research of the university should focus on a certain common problem in the production of the product.

Recently, many experts in the manufacturing field are talking about flexible manufacturing. Is this the same thing you mentioned in your speech: smart manufacturing and flexible manufacturing? If not, where is the difference?

Both of these concepts are similar, but the expression method is not the same and the essence is the same. Such as 3D printing, rapid prototyping 20 years ago, early CAD and rapid prototyping is the current 3D printing. Flexibility is actually smart, flexible, and able to make different judgments based on different situations. These are different terms, but the implementation is the same.  

Adding machine learning to smart manufacturing is, according to industry insiders, only a gimmick more than a reality. How do you see this problem?

I think machine learning is the easiest to implement in the manufacturing industry. Because manufacturing is more standardized. Uncertainty in life is too great, and it is difficult to standardize things encountered, so the highest intelligence requirements in life. In contrast, it is easier to apply machine learning in smart manufacturing.

After you just talk about modeling in PPT, it is machine learning, reinforcement learning, and evolutionary calculation. The latter three are often used in partial software, such as AlphGo. How can it be effective in the smart manufacturing hardware system?

I don't know exactly how AlphGo works, but judging by my logic, it is based on rules. Because current artificial intelligence cannot make judgments without rules. The rule judgment is relatively simple, that is, you need to decompose and modularize the problem of rule judgment, and then gradually solve it, and take out all possible problems. Then establish rules that let the machine know how to deal with each problem and the machine follows this step. Of course, the issue of playing chess is very complicated. The more complex problems require more calculations, the faster the calculation speed of the computer will be. So artificial intelligence is basically a rule judgment at present, it can't do some operations that are not arranged for it. This means that if it hasn't seen it, it can't do it. For example, people are living every day and there are many experiences every day. But if one day, put you on the alien planet, you may not know what to do, because there is no relevant experience in your memory, then you can not make a good decision. This is especially true of machines.

High Power DC Power Supplies

The MTP series DC Power Supplies are High Power DC power supplies developed by iDealTek-Electronics based on IGBT semiconductor components, adopting AC/DC power processing topology with full-bridge phase-shift soft-switching technology. This series of High-power DC power supplies have the most output models and the widest output range in the company's DC power supply series, from 3KW ~ 30KW integrated in 19-inch standard rack-mounted high-precision DC power supplies to 45KW ~ 2000KW with casters or floor-standing Cabinet type High Power DC power supplies, output voltage up to 2000VDC, output current up to 6000A.

600v 10kw Dc Power Supply Front Panel

500 2000kw High Power Dc Power Supplies


This series of High-power AC - DC power supplies are equipped with a reliable two-stage conversion mechanism drive logic circuit and a fast control loop optimized by iDealTek-Electronics. Which balances the requirements of low output ripple and fast DC output response speed, making this series of High-power switching power supplies can provide high-precision, low ripple, high-stability and High-power DC output with fast response speed feature of the switching power supply. All MTP series DC power supplies are equipped with a short-term 2 times rated current overload capacity (Except for some high-current output models) to cope with the inductive and mixed load's demand for high-current output at the moment of starting.

The full range of MTP series high-power DC power supply adopts digital control circuit. You can set and control the power output through the buttons on the front panel of the power supply (3KW ~ 30KW) or LCD touch screen (45KW ~ 2000KW). The high-precision 4 1/2-digit LED (3KW ~ 30KW) or LCD (45KW ~ 2000KW) provides intuitive, high-precision output display and measurement functions. At the same time, the full range of MTP high-power DC power supplies are equipped with RS485 interfaces as standard, following the MODBUS-RTU international communication protocol, which can realize remote control and operating status monitoring of the power supplies.

At present, this series of High Power DC power supplies are mainly used in Battery charging testing, DC motor testing, Photovoltaic inverter testing, and various cutting-edge applications that require High-power DC output.

High-power DC Power Supplies, High Power AC - DC Supplies, High-power Switching Power Supplies, High-power AC DC Supplies, High-power Power Supplies

Yangzhou IdealTek Electronics Co., Ltd. , https://www.idealtekpower.com

This entry was posted in on