The control system of CNC machine tools can logically process, decode and represent the programs with control codes or other symbolic instructions, and input them into CNC devices through information carriers. Today, I will introduce the intelligent technology of CNC machine tools to you. Welcome to reading.
Intelligent machine tools first appeared in Wright (P? k？ Wright) and Bowen (D? Answer? Bourne) 1998, the first monograph in the field of intelligent manufacturing research, manufacturing intelligence [1]. Intelligent technology has attracted the attention of all countries because of its important role in advanced manufacturing. The United States launched the Intelligent Machining Platform Program (SMPI); European implementation? Next generation production system? Research; Germany has started? Industry 4.0? Plan; China's medium and long-term scientific and technological development, right? Digital intelligent manufacturing technology? Put forward urgent needs and formulate corresponding ones? Twelfth Five-Year Plan? Development planning; At IMTS2006 held in Chicago, USA, Japanese Mazak Company launched the first model named? Smart machine? This intelligent machine tool has the same name as Okuma Company in Japan? thinc？ Intelligent CNC system opens the era of intelligent CNC machine tools [2].
Based on sensors, the intelligent technology of CNC machine tools is divided into intelligent sensors, intelligent functions, intelligent components, intelligent systems and other parts. The intelligent technology is summarized, the shortcomings are pointed out, the development direction is revealed and the future is prospected.
Intelligent sensor
The CNC machine tool manufacturing system, which consists of machine tools, cutters and workpieces, is accompanied by various complex physical phenomena in the processing process, which contains rich information [3]. In this dynamic, nonlinear, time-varying and uncertain environment, the sensing technology of CNC machine tools is the basic condition to realize intelligence.
To realize the intelligentization of CNC machine tools, various sensors are needed to collect the information of external environment and internal state, which is similar to the function of human five senses to perceive environmental changes, as shown in Table 1. For people, the eyes are the most important sensory organs among the five senses, which can obtain more than 90% environmental information, but the application of visual sensors in CNC machine tools is still relatively small. With the improvement of automation and intelligence, visual function will play an increasingly important role in CNC machine tools.
With the development of MEMS technology, embedded technology, intelligent materials and structures, sensors tend to be miniaturized. The mature application of MEMS micro-sensor, thin film sensor and optical fiber sensor has laid the foundation for the sensor to be embedded in CNC machine tools.
Due to the unpredictable or unpredictable complex phenomena and strange problems in the manufacturing process, as well as the timeliness, accuracy and integrity of monitoring information, the sensor is required to have the intelligence of analysis, reasoning and learning, which requires the sensor to have a high-performance intelligent processor to act as a? Brain? . Qualcomm is developing an artificial intelligence system microprocessor, which can simulate the work of the human brain. In the future, the microprocessor, sensor, signal processing circuit and I/O interface of high-performance artificial intelligence system can be integrated on the same chip through semiconductor integration technology to form a large-scale integrated circuit intelligent sensor, which not only has the functions of detection, identification, storage and analysis, but also has the ability of self-learning and even thinking [4]. It is believed that with the continuous progress of computer technology, signal processing technology, MEMS technology, high-tech materials technology and wireless communication technology. Intelligent sensors will bring new changes to the intelligent perception of CNC machine tools.
Intelligent function
The development of CNC machine tools to high speed, high efficiency and high precision requires that CNC machine tools have intelligent functions such as thermal compensation, vibration monitoring, wear monitoring, condition monitoring and fault diagnosis. Through the combination of several intelligent sensors and the method of artificial intelligence, the intelligent function of CNC machine tools is realized through identification, analysis, judgment and reasoning, which lays the foundation for the realization of intelligent components.
Errors of CNC machine tools include geometric errors, thermal (deformation) errors, force (deformation) errors, assembly errors and so on. The research shows that geometric error and thermal error account for more than 50% of the total error of machine tools, which are the key factors affecting the machining accuracy of machine tools, as shown in figure 1 [5]. Among them, the geometric error is related to the machine tool structure itself, which does not change much with time and belongs to static error. The error prediction model is relatively simple and can be effectively controlled by the compensation function of the system, while the thermal error changes greatly with time, which belongs to dynamic error, and the error prediction model is complex, which is a difficult and hot spot in international research.
The heat sources in the machining process of CNC machine tools include bearings, ball screws, motors, gearboxes, guide rails, cutters, etc. The temperature rise of these parts will cause the changes of spindle elongation, coordinate change and tool elongation, which will lead to the increase of machine tool errors. Because of the large number and wide distribution of temperature sensitive points, the optimal design of temperature measuring points is very important. The main methods are genetic algorithm, neural network, fuzzy clustering, rough set, information theory and grey system [6]. On the basis of determining the temperature measuring point, neural network, genetic algorithm, fuzzy logic, grey system and support vector machine are commonly used to predict and compensate the error [7].
In the aerospace field, with the wide application of difficult-to-machine materials such as titanium alloy, nickel alloy and high-strength steel, and the increasing cutting amount under the condition of high-speed cutting, vibration is easy to occur between the tool and the workpiece, which seriously affects the machining accuracy and surface quality of the workpiece. Because cutting force is the original characteristic signal of cutting process and can best reflect the dynamic characteristics of machining process, vibration monitoring can be carried out with the help of cutting force monitoring and prediction. With the help of dynamometer, force sensor and feed motor current, the cutting force is modeled and predicted by using particle swarm optimization, fuzzy theory, genetic algorithm and grey theory [8]. Considering that the vibration of machine tools is mainly caused by spindle, lead screw, bearing and other components, we can also collect the vibration, cutting force, acoustic emission and other signals of these components, and directly monitor the vibration by using intelligent methods such as neural network, fuzzy logic and support vector machine.
The cutter is installed at the front end of the spindle, which is in contact with the workpiece and directly cuts the surface of the workpiece, which has the most direct and critical influence on the machining quality. Abnormal phenomena such as tool wear and breakage affect machining accuracy and work safety. In view of the defect that the direct measurement method needs off-line detection, one or more indirect signals such as current, cutting force, vibration, power and temperature are often collected, and intelligent algorithms such as RBF neural network, fuzzy neural network, wavelet neural network and support vector machine are used to intelligently monitor the tool wear state.
With the improvement of automation, the functions of CNC machine tool integration are more and more, and the complexity is getting higher and higher. In order to run efficiently, it is necessary to monitor and evaluate the internal state of CNC machine tools, and make early warning and diagnosis of faults. Because the failure mode can't be copied and it is difficult to collect samples, intelligent methods such as BP neural network, which need more samples, are not suitable for this occasion. Intelligent methods such as SOM neural network, fuzzy logic, support vector machine, expert system and multi-agent are often used for condition monitoring and fault diagnosis.
Researchers continue to explore and study new methods of intelligent function or a mixture of various methods, but most of them are concentrated in the laboratory environment, lacking methods with high real-time and online functions, and need to further develop concise, fast and adaptable intelligent methods.
Intelligent component
The mechanical part of CNC machine tool mainly includes supporting structure, main drive, feed drive, cutter and other parts, involving lathe bed, column, spindle, cutter, lead screw, guide rail and rotating shaft. These components can integrate one or more intelligent functions of intelligent sensors to form intelligent components of CNC machine tools, as shown in Figure 2.
Spindle is the main transmission component, and as the core component, it is directly related to the machining accuracy of the workpiece. Because of the high rotating speed of spindle, especially motorized spindle, heating, wear and vibration have great influence on machining quality. Therefore, more and more intelligent sensors are integrated into the spindle to realize the monitoring, early warning and compensation functions of the working state. Developed by Madzak Yamazaki? Intelligent spindle? , equipped with temperature, vibration, displacement, distance and other sensors, not only has the functions of monitoring and protecting temperature, vibration and fixture life, but also can intelligently coordinate machining parameters according to temperature and vibration state [13]. The motorized spindle manufactured by Step-Tec and IBAG in Switzerland is equipped with various sensors such as temperature, acceleration and axial displacement [14], as shown in Figure 3, which can be used for thermal compensation and vibration monitoring.
Lead screw and guide rail are the key components of coordinate movement and positioning of CNC machine tools, and their performance directly affects the precision and dynamic characteristics of coordinate movement and greatly affects the machining quality of workpieces. Therefore, it is of great significance to monitor the performance change and life prediction of the lead screw guide pair in the machining process for the intelligence of CNC machine tools. Through sensor signals such as motor driving current signal, power, cutting force and sound, combined with process parameters such as feed speed, cutting depth and screw speed, the wear of screw and guide rail can be monitored, the remaining life can be predicted, and an alarm can be given in time to prevent major production accidents.
Bearing is the key component of the rotating shaft of NC machine tool, which plays the role of supporting load and reducing friction coefficient, and its running state directly affects the running accuracy and reliability of machine tool. Bearing is the most easily damaged part, because it has intense friction and high heat generation at high speed. Therefore, monitoring the running state of bearings can avoid equipment abnormality or damage caused by bearing problems. The external intelligent bearing produced by SKF company in Sweden is shown in Figure 4 [15]. In the application environment, the key parameters such as speed, temperature, speed, vibration and load are measured by self-power, and the state information of external intelligent bearings is sent through wireless network to realize the state monitoring of bearings.
The tool is in direct contact with the workpiece, and the surface of the workpiece is prone to generate heat and vibration, which has a great influence on the surface quality. Therefore, more and more sensors are integrated into the tool to realize the functions of tool wear monitoring, vibration monitoring, fracture alarm and so on. As shown in Figure 5, the intelligent tool holder invented by Christopher and Robert. Integrated force/torque, temperature, processor, wireless transceiver and other chips. And can estimate and predict the flutter frequency, suggest to stabilize the spindle speed, monitor the wear and suggest the feed speed, etc. [16]. The intelligent cutting tool produced by ACTICUT Company in Switzerland is composed of mechanism, sensor and driver, which is used for precision CNC turning and can monitor wear, speed and temperature [17].
Intelligent system
CNC machine tools are generally composed of CNC system, driving system, auxiliary system and machine body, as shown in Figure 6. With the continuous maturity of artificial intelligence technology, neural network, fuzzy theory and expert system are gradually applied to numerical control system, driving system and auxiliary system to realize the functions of process parameter optimization, adaptive control, machining process monitoring and intelligent diagnosis of expert system.
The parts that need to be processed in the field of aviation manufacturing include holes, grooves, grooves, cavities and other features, and the processing technology is complex, so it is inevitable to embed an expert system for optimizing process parameters in CNC machine tools. Expert system uses artificial intelligence technology to solidify the knowledge and experience of one or more experts in a certain field into a program, simulate the decision-making process of human experts, and make reasoning and judgment to solve complex problems in processing. The Swiss company Myquelau has collected the crystallization of decades of milling experience and developed the Operator Support System (OSS), which can adjust the relevant process parameters and optimize the machining program according to the machining requirements, and obtain more ideal machining results [18].
With the development of CNC system, mainstream CNC system manufacturers have embedded practical functions such as adaptive control, machining process monitoring and intelligent diagnosis in their products. Siemens CNC system has the functions of adaptive operation of motor parameters, automatic load identification, tool life monitoring and safety integration. Combined with OMAT-PRO, an Israeli OMATIVE optimization milling controller, the spindle power can be constrained, and the optimal state of spindle power can be mastered through learning and relearning, so as to monitor the change of spindle power in real time during machining and adjust the feed speed in time [19]. The Crash Guard anti-collision guardrail system in WFL, Austria, uses the high-speed processing ability of the numerical control system to monitor the movement of the machine tool in real time to ensure the normal operation of the machine tool in various motion modes such as manual and automatic, reduce the occurrence of accidents during the operation of the machine tool, and improve the safety and reliability of the machine tool [3]. Proficy software of GE Fanuc Company monitors and analyzes the complex basic data of machine tools, and remotely diagnoses the working state and health state of machine tools [20]. German ARTIS monitoring system is a system to monitor the working state. Through learning, the characteristics of monitoring signals can be obtained, and abnormal behaviors such as tool breakage, tool wear and collision can be monitored in real time [2 1].
prospect
Intelligentization is an advanced stage in the development of CNC machine tools, which can realize high automation and further liberate people's spiritual intelligence. With the development of technology and the improvement of demand, there are more and more intelligent functions, intelligent components and intelligent systems in CNC machine tools. Although its intelligence level is still in the development stage, with the miniaturization and intelligent development of artificial intelligence technology, computer technology, sensor and microprocessor technology, it has achieved real significance? Self-learning and self-evolution? CNC machine tools with human intelligence level will no longer be? Dream? .
;