Chatter occurs frequently during the curve surface machining process, and it results in poor quality of finished surface. In order to identify chatter quickly and accurately, a method based on hidden Markov model (HMM) and support vector machine (SVM) for chatter recognition and prediction was proposed in this paper. Firstly, according to the phenomenon that the transition period of formation process of the curve surface machining chatter is short and difficult to distinguish from normal processing and chatter burst stages, a chatter identification and prediction system based on HMM–SVM hybrid model was designed, which combined the strong similarity classification ability of HMM and the strong classification ability of SVM. Then, the acceleration sensor was used to measure the tool vibration signal during the curve surface machining process, and the characteristic signals of machining states was obtained. Finally, HMM and HMM–SVM were used to carry out recognition experiments of curve surface machining state, and the results were analyzed and compared. The experimental results show that the proposed HMM–SVM method drastically improve the recognition accuracy rate, compared with HMM model alone. The recognition accuracies of the three processing states are over 95%, and the recognition time is less than 1.5s. Rapid identification and prediction of chatter are realized, which provide basis and guarantee for the subsequent chatter suppression.

    Aiming at the development of new information technology and the application requirements of intelligent manufacturing in the aerospace industry, the multi-dimensional framework of the open and smart CNC system was established by analyzing the technical trends of the CNC system. Then a reconfigurable CNC system platform, a process chain integration based on an information terminal and a product life cycle management system based on industrial big data was proposed. Finally, the Lantian CNC system was developed, and the implementation routine of the open and smart CNC system was explored through the application and practice of the processing and control of typical parts in aeronautical engineering.

    Diamond wheel grinding machining is essential for the accuracy and efficiency of the large scale optical lens. Monitoring system is the indispensable part of the new generation grinding machine for the high demand of the reliability and stability. This paper is dedicated to the intelligent monitoring system of the precision grinding machine. PXI platform of National Instruments Corporation is used to acquire processing signals during machine operating and grinding. PXI controller is connected with the numerical control system of the machine, and the internal sensor signals and the processing parameters can also be output to the monitoring system. All the dynamic and static data related to the machine are stored and managed by the monitoring system database. Thermal error of the machine is acquired by the monitoring system and compensated for high machining precision. Grinding fluid circle system is also monitored and the numerical control system can give alarm for the emergency. Grinding wheel performance is real-time predicted which can give reliable guidance for wheel dressing.

    In order to reduce the influence of thermal error on the machining accuracy of CNC machine tool, the position of temperature rise of machine tool was preliminarily found out by thermal imager, and then the collected temperature measurement point test data was optimized by using gray correlation theory to find out the measurement point with high correlation degree of thermal error. The selected temperature measurement point data and the measured Z-axis thermal error data were divided, and GM (1,n) grey prediction and BP neural network were used to establish the thermal error prediction model, which was verified on the test machine tool. The experimental results show that the difference between the predicted results of gray GM (1,n) model and the actual measurement is 10.17%, and the difference between the predicted results of BP neural network and the actual measurement results is 5.19%, which is better than the prediction of gray GM (1,n) model and can play a role in improving the accuracy of thermal error prediction.

    The Spindle system is an important functional component of CNC machine tool, and its operating status directly affect the reliability of machine tool and the machining accuracy of parts. In order to achieve real-time monitoring, fault warning and maintenance strategy optimization, a status monitoring scheme was designed for machining center spindle system, and the hardware and software systems of status monitoring platform were developed and built. The wavelet de-noising method and empirical mode decomposition (EMD)-support vector machine (SVM) algorithms were used to process and analyze the signals, so as to achieve the status real-time monitoring and diagnosis of typical fault status for the machining center spindle system. Based on the spindle status monitoring system, the spindle belt looseness fault status monitoring test was carried out, and the accuracy of recognizing the typical fault status of the spindle system was verified.

    In order to realize the compound process of rapid forming and high precision milling for complex pieces, our assignment group developed a five-axis additive-subtractive hybrid machining center. Based on the five-axis additivesubtractive hybrid machining center, the developing process and integrating control principles are expounded, and the control method of total precision is analyzed. Furthermore, the relevant experiments were carried out. The tapered bench specimens in the acceptance criteria of aerospace engineering impeller and five-axis machine tool are used for material subtraction trial manufacturing. We carried out some additive manufacturing experiments for the impeller blades and S specimens, algorithms optimization of generating additive manufacturing path were also applied. The expected machining performance is preliminarily acc omplished.

    Different combination of grinding process parameters are designed to research the surface integrity of IC10 directionally solidified superalloy in creep feed grinding. The effects of process parameters on the surface roughness, surface topography, microhardness and microstructure alteration of the subsurface are investigated in detail. The results show that a better surface quality can be obtained during creep feed grinding of IC10 superalloy under the conditions: the wheel speed ranges from 15 to 20m/s, the workpiece speed is not more than 200mm/min, and the grinding depth is not more than 0.5mm. In addition, surface hardening phenomenon appears on the ground surface, the maximum hardening degree can reach 26.9% and the maximum depth of the hardened layer is 230μm. At the same time, the white layer and plastic deformation layer are produced in the subsurface, the depth of the white layer and deformation layer ranges from 0.24μm to 3.2μm and 0.48μm to 3.8μm respectively.

     In order to reduce the internal porosity and improve the quality of aluminum alloy weld seam, the wobbling fiber laser is performed on the 8mm 5083 aluminum alloy locked bottom butt joint in laser-MIG hybrid welding. The influence of the weaving frequency and amplitude of the laser beam on the porosity and the penetration was studied. Orthogonal experiments were carried out to investigate the primary and secondary relations between the influence of laser power, welding speed, welding current and weaving frequency on the formation of weld porosity. The optimal parameters were obtained and the microstructure and mechanical properties of the weld joint under the optimal parameters were analyzed. The result shows that the laser beam swing frequency and amplitude are helpful to eliminate stomatal imperfections. The effect of the factors on the porosity is following by the laser weaving frequency, welding current, welding speed, laser power. To weld 6mm 5083 aluminum alloy by using the parameters, power 6800W, welding current 136A, welding speed 28mm/s, weaving frequency 240Hz, wobble amplitude 1.5mm, we can get joint with no obvious pores, which average hardness is 70.4HV, and the tensile strength of welded joints can reach 278MPa, reaching 91.9% of the base metal.

    The superelastic TiNi alloy can be used in the manufacture of aerospace functional devices, and the method of selective laser melting can obviously improve the freedom and complexity of the design of functional devices. The superelasticity of TiNi is studied through analyzing microstructure of TiNi alloy and condcuting the superelasticity cycling tests. The results show that in 20 times cycling tests, superelasticity behaves well and has a phase transition platform of more than 6% strain, martensitic transformation start and end stress have a small attenuation about 4MPa, phase transformation stress is stable, and the cumulative residual strain is only 1.8%; Under different strain amplitude, the energy consumption in the alloy deformation increases from 23N · mm to 156N · mm, and the energy consumption linearly increases with strain amplitude; The superelastic property of the alloy does not significantly change at different strain rates. Under different loading conditions, the TiNi alloy manufactured by selective laser melting has a more stable superelastic behavior compared with the TiNi alloy manufactured by traditional way, and is more conducive to manufacture the stable functional devices.

    Aircraft skin parts are characterized with complex shape, large size, weak rigidity, difficult to machine and so on. Recently, the skin mirror milling technology appeared as a high precision green machining technology. Due to the weak rigidity of the skin blank, the gravity of the blank and the clamping force will cause deformation, which will result in the deviation between the actual surface and the design surface of the blank. To solve the above problem, an adaptive machining technology of aircraft large skin based on rapid scanning was proposed. The actual surface of the skin blank could be obtained quickly by laser scanning on machine, and then the machining program was transplanted based on a feature mapping method. The transplanted machining program has been successfully applied to practical production. The proposed adaptive machining technology solves the key problem of the skin mirror milling technology, can generate the machining program efficiently and satisfy the requirements of the form accuracy and thickness accuracy of the skin parts, and improve the production efficiency of the skin effectively, which will bring significant advancement to the mass production of domestic large aircraft.

    Research on high performance machining plans on aircraft part is one of most significant methods based on the rapid growth of aviation industry. This paper proposes new fixture designs, which are based on the viewpoint of embedded and unit modes, to solve machining efficiency of typical part. A complete solution is given in this paper, and typical parts have been manufactured to validate the feasibility. It can be proved from the experimental results that this new method has a certain advantage in the aspects of fixture management and clamping efficiency, and also has high value of applications.

    The 3D laser scanning system mounted on an industrial robot is capable of detecting the surface information of parts quickly, and can enhance the system capability by improving the accuracy of measurement. In this paper, the measurement error of scanning system is analyzed and evaluated. The scanning system used in this experiment consists of an industrial robot and a commercial 3D laser scanner T-Scan. The basic principle of this commercial 3D laser scanner is laser triangulation, as a result, its measuring error is affected by scanning posture. In this experiment scanning posture is decomposed into scan depth, pitching angle and yawing angle. And the influence of scanning posture on random error and systematic error is studied by a series of experiments which control the variation of three parameters in sequence. Experiment result shows that the random error of the measurement is small compared with systematic error. And the systematic error shows a bilinear relationship with the scan depth and the pitching angle. A prediction model is developed and the maximum deviation between the model and the experimental results is only 26mm. The prediction model is a precondition to optimize the scanning trajectory and improve the measurement accuracy.