At present, intelligent manufacturing has become the main direction of China's manufacturing power strategy, and a number of Intelligent Manufacturing "demonstration enterprises" have emerged in China.
What is the essence of intelligent manufacturing? The Fourth Industrial Revolution seemed to emphasize the integration of digital and physical worlds. Intelligent manufacturing is the main embodiment of the fourth industrial revolution in the field of manufacturing. Is the integration of digital and physical world the essence of intelligent manufacturing? No, integration is just a phenomenon.
After the second and third industrial revolution, people's understanding and control of certainty in engineering has become mature. There are a lot of uncertainties in manufacturing, whether it involves efficiency, quality, cost, or green, service, etc. In addition, there are many non model problems in manufacturing, such as the energy-saving problem of a factory or workshop, which not only can not be described by mathematical model, but also has no fixed model. For human beings who try to clearly understand and even control the manufacturing process, the problem of non pattern and uncertainty is the biggest problem. How many factors in the system are related to each other and how much influence each other?
Fortunately, big data, artificial intelligence and other technologies have opened the door for human beings to further understand and control the non pattern and uncertainty of the objective world. Therefore, the essence and essence of intelligent manufacturing is to use advanced technologies (such as digitization, networking, big data, artificial intelligence, etc.) to understand and control the uncertainty problems in manufacturing system in order to achieve higher goals. The reason why Japan's early intelligent manufacturing plan did not achieve obvious results may be related to the lack of Technology (such as big data and artificial intelligence) to deal with such problems at that time.
There are two kinds of uncertainty problems. One is the objective uncertainty, such as the uncertainty of quality in the process of processing, the uncertainty of product performance and so on. The second is subjective uncertainty, or cognitive uncertainty, which mainly refers to the uncertainty of people's understanding of the original certainty problems in manufacturing system due to the failure of digitization. For example, the arrangement of various activities and processes in an enterprise is inherently deterministic, but because there are too many people involved and the occurrence time is different, without special means, it will be chaotic for people's understanding. This is the subjective uncertainty or cognitive uncertainty. Why is subjective uncertainty also regarded as uncertainty of manufacturing system? Because the manufacturing system should also include relevant people.
What is the key to the implementation of intelligent manufacturing? Naturally, there are many key issues. Here, we only draw people's attention to the most basic issue, data and Internet.
Whether it is objective uncertainty or subjective uncertainty, with the corresponding data, there is a basis for understanding uncertainty. It is possible to find out the factors that affect the processing quality that people didn't realize before by analyzing the data of the aspects in the processing; Only by mastering the relevant data of various activities can we reduce the uncertainty of cognition, make the new activities more orderly and make the corresponding decisions more reasonable. As for non pattern scenarios, data analysis is needed.
Access to data requires interconnection. Interconnection first refers to the acquisition of physical quantities in the manufacturing process (such as installing sensors on the equipment). By analyzing these data, we may have a deeper understanding of its uncertainty, and may find some correlation between some seemingly unrelated physical quantities. Interconnection naturally should also include the data connection between various activities determined by people, and its premise is that the related activities must be digitized.
The concept of interconnection cannot be limited to the enterprise. We should have the awareness of "enterprise ecosystem", that is to say, the concept of "system" can not be limited within the enterprise. Suppliers, customers and so on constitute the enterprise ecosystem, and the members of the enterprise ecosystem should have some data interconnection and sharing. Now there is the concept of "digital supply chain", that is, not only the supply and demand of materials, but also the supply and demand of data between enterprises. A good enterprise ecosystem should include "digital ecosystem", or enterprise ecosystem should emphasize data interconnection.
The awareness of interconnection even urges entrepreneurs and engineers to redefine the boundaries of industries and products. For example, enterprises that make smart lights need to consider the data connection between lights and entertainment devices, and the automotive industry needs to consider the data interconnection between cars and smart cities.
The era of man-machine intelligence is coming. What is the future development of intelligent manufacturing? At present, it is relatively easy to speculate that "knowledge engineering" will play an increasingly important role, and most of the mental work of engineers may be replaced by intelligent systems; The boundary between virtual space and real space will be more and more blurred. Augmented reality (AR) and hybrid reality (MR) technology will be applied in more scenes. It is difficult to speculate how to position and play the role of human when manufacturing system becomes more and more "intelligent". In this regard, we can only explore the answer in practice as time goes on.
What is the best path of intelligent manufacturing? This is a problem that the government, entrepreneurs and R & D personnel should pay special attention to and think about. At present, the hot "machine replacement", "millions of industrial enterprises on the cloud, the implementation of millions of industrial app" are all exploring and practicing in this aspect. What is the final answer? It is still unknown, but one thing is certain. Intelligent manufacturing must rely on many basic intelligent technologies and tools, such as sensors, Internet of things, intelligent numerical control system, big data analysis tools, intelligent software, etc. to achieve major breakthroughs and occupy the commanding heights in these fields is the premise of building an intelligent manufacturing power. We should always be aware of this.