Search

With the rapid development of 3D reconstruction, especially the emergence of algorithms such as NeRF and 3DGS, 3D reconstruction has become a popular research topic in recent years. 3D reconstruction technology provides crucial support for training extensive computer vision models and advancing the development of general artificial intelligence. With the development of deep learning and GPU technology, the demand for high-precision and high-efficiency 3D reconstruction information is increasing, especially in the fields of unmanned systems, human-computer interaction, virtual reality, and medicine. The rapid development of 3D reconstruction is becoming inevitable. This survey categorizes the various methods and technologies used in 3D reconstruction. It explores and classifies them based on three aspects: traditional static, dynamic, and machine learning. Furthermore, it compares and discusses these methods. At the end of the survey, which includes a detailed analysis of the trends and challenges in 3D reconstruction development, we aim to provide a comprehensive introduction for individuals who are currently engaged in or planning to conduct research on 3D reconstruction. Our goal is to help them gain a comprehensive understanding of the relevant knowledge related to 3D reconstruction.

It is necessary to test the reliability of the operation of the machine itself for meeting the high-speed, ultra-precision, flexible, and other modern manufacturing and processing needs. In practical applications, the obtained reliability detection information presents a variety of uncertainties such as randomness, imprecision, incompleteness and so on, due to the complexity of the machining environment, the limitations of the sensor itself and the imperfections of the information acquisition technology. The uncertainty reasoning method is proposed to test reliability and accuracy precision. Based on the multi-sensor information characteristic, the rule of the credibility sets is established to achieve the operational reliability analysis. It can realise the uncertainty reasoning for the modal and reliability rules. Examples of analysis show that during the high-end CNC machine tools operational reliability analysis, it has a practical effect to study the uncertainty reasoning method of the modal and reliability propositional rule and the analysis basis can be provided for the precision degradation and fault diagnosis.

By connecting the symmetrical spiral inductive sensor to the oil return pipeline of the lubricating oil, a full flow online detection of the size, quantity and other parameters of the tiny metal debris particles in the lubricating oil solution is realised. Inductive sensors are used to excite symmetrical double helix coils, and alternating electromagnetic fields are generated. Changes in induced electromotive force are detected by the centre induction coil. In order to improve the detection accuracy of tiny metal debris particles, the degree of anti-jamming of the excitation signal, and the transmission distance, a method of stimulating using sinusoidal AC steady current signals was designed. The sinusoidal signal generator is designed based on FPGA, and the sinusoidal AC steady current excitation signal is realised through differential amplification, low-pass filtering, and AC steady current amplification, and experimental verification is performed to achieve better excitation and detection results.

According to the analysis characteristic of the on-line sensor of the mechanical device, the on-line magnetic field of the double excitation sensor is analysed by using the most advanced F-30 multi-dimensional digital magnetic measurement system. Using F-30 mode scanning analysis of the dual incentive sensor of two-dimensional (2D) and 3D characteristics, a system of a 3D mesh of the sensor is obtained, the 3D graph, the 3D graphic model, at last, through export data for magnetic field distribution of more detailed information. The accuracy of the F-30 magnetic field analysis system is very high, and the field distribution information of the sensor is more practical. This analysis is of a great reference value for the experimental analysis of the sensor.

Lubrication is one of the critical factors for the normal operation of wind turbine's gearbox, which carries abundant and various wear debris. Accordingly, these debris reflects the running state of the equipment and forecasts the early fault of wind turbine gearbox effectively. Thus, the authors can achieve predictive maintenance, even avoid the occurrence of safety accidents. In order to realise real-time online monitoring of lubrication, this article studied the principle of wear debris detection sensor, constructed approximate mathematical model of inductive wearing debris sensor, produced a prototype device, and carried out the monitoring test of metal wearing debris without oil. Experiment shown that the designed sensor can detect the signal of metal wear debris with the smallest diameter to 80μm, which can diagnose the early fault of the wind turbine.

When a single image segmentation method is used for image segmentation of wind turbine blade images under a complex background, the results obtained are not accurate and complete. This article proposes an image segmentation algorithm that applies morphology to Canny edge detection. It uses morphological opening to erode and dilate the binary image after Canny algorithm processing, and removes redundant edge information to obtain a complete fan blade image. Experimental results show that the results obtained by the image segmentation method proposed here have good integrity and accuracy, and can improve the segmentation effect of the image.

Zinc-coated steel sheets, a kind of high-quality sheet, is widely used in all sorts of manufacturing industry. The fault on its surface is one of the factors which exert bad effects on its quality. Due to its complex texture, the experts first put forward to the defect segmentation methods of Discrete Fourier Spectrum Residuals and Gabor Filtering Image Fusion. Then, they analysed the grey form of the faults and the deficiencies of the two methods and made some improvements on them using Morphological black hat operation and eventually achieved the goal of effective defect segmentation. According to some results of experiments, the improved method is of high accuracy in the defect segmentation and to some extent can serve as the reference method to examine the faults of the zinc-coated sheets.

The sine eccentric shaft is one of the most important parts for industrial robot RV reducer, and its machining quality has immediate effect on the overall device performance. The eccentric shaft X-C linkage grinding model is built based on the tangential point tracing machining principle, and the method of calculating the roundness error for eccentric circle grinding is proposed here. The research is performed on non-uniform rational B-spline (NURBS) interpolation for the coordinates’ densification of eccentric shaft X-C linkage grinding, and the algorithm process is put forward. The process of eccentric grinding is simulated and analysed by wheel inversion envelope method. The results show that the eccentric tangent point tracking model proposed is correct. Compared with the linear interpolation, NURBS interpolation can remarkably improve the accuracy of eccentric shaft tangent point tracking grinding.

Wear is one of the common faults in the mechanical transmission system. Detection of wear particles in lubricating oil can detect and evaluate the wear degree of mechanical equipment. The electromagnetic sensor for metal wear particle detection can be connected in series with the oil circuit, which has the advantages of full liquid flow, simple structure, distinguishing metal properties, and not being influenced by bubbles and vibration. In view of the shortcomings of the existing electromagnetic sensor for wear particle detection, the detection principle and the induction electromotive force model were studied, and the magnetic field change of the metal particles through three coil differential solenoids was analysed. The optimisation design method was proposed here, which was about the related parameters, such as the wire diameter, the coil turns, the coil widths and so on. The experimental analysis of the sensor was carried out based on detection hardware system that could provide the phase-locked amplification function. The 10-mm inner diameter sensor could detect the minimum 100-μm ferromagnetic metal abrasive particles after optimisation. The developed sensor could provide data information for the abrasive particle detection, fault diagnosis and early warning of wear degree of mechanical equipment.

In order to improve the operation reliability of high-grade computer numerical control (CNC) machine tools and reduce the maintenance time of failures, the remote state monitoring and intelligent maintenance system for CNC machine tools was proposed. Through collecting the basic information of equipment, maintenance information, and the information of the vibration, temperature, main current and power of the machine tool based on soft-bus technology, the system analysed the real-time state data, got the reliability parameters, extracted the fault features and established the maintenance knowledge base. Combining the dynamic monitoring data and static data, the system evaluated the key parts of machine tools. By the fault knowledge base, the system analysed the reason for failure and recommended the maintenance method. With the function modules, the system can improve the intelligent maintenance level of CNC machine tools and improve the using efficiency of machine tools.

Online oil monitoring technique is now an important development means to monitor wear condition and diagnose wear fault real time. Inductive wear debris monitoring is the research hotspot in the current online oil monitoring for its unique characteristics. Based on the current domestic and international online inductive wear debris monitoring, the relevant comments to the online inductive wear debris monitoring technology were given. Then, the positive and inverse problems of numerical analysis of inductive wear debris monitoring are analysed. Based on the above, the difficulties and shortages of online inductive wear debris monitoring are studied and the development trend and research focus of online inductive wear debris monitoring are discussion to provide for the oil online technology research.

In view of the stability and safe service of the transmission system of the wind turbine, the trend early warning method for the stability deterioration of the electromechanical system is proposed and the level of the predictive maintenance of the complex electromechanical system is improved. It includes: establishing the dynamic model of wind power transmission system, revealing the evolution law of the system stability deterioration, putting forward the signal processing method of the weak detection information, extracting the fault features decoupling with energy and constructing the early warning methods of the system stability deterioration trend. The research results can be applied to the safety monitoring and fault warning of the wind turbine. It is beneficial to ensure the safe and reliable operation of the equipment and realise the prediction maintenance, improve the operation and management level of the equipment, reduce the economic loss caused by the failure and promote the utilisation and development of green energy.

Image segmentation is a significant step in image analysis and computer vision. Many entropy-based approaches have been presented on this topic. Among them, Tsallis entropy isone of the best-performing methods. In this paper, the surface defect images of galvanised steel sheets were studied. Atwo-dimensional asymmetric Tsallis cross-entropy image segmentation algorithm based on chaotic bee colony algorithm optimisation was used to investigate the segmentation of surface defects under complex texture backgrounds. On the basis of Tsallis entropy threshold segmentation, a more concise expression form was used to define the asymmetric Tsallis cross-entropy in order to reduce the calculation complexity of the algorithm. The chaotic algorithm was combined with the artificial bee colony (ABC) algorithm to construct the chaotic bee colony algorithm, so that the optimal threshold of Tsallis entropy could be quickly identified. The experimental results showed that compared with the maximum Shannon entropy algorithm, the calculation time of this algorithm decreased by about 58% and the threshold value increased by about (26%, 54%). Compared with the two-dimensional Tsallis cross-entropy algorithm, the calculation time of this algorithm decreased by about 35% and about 20% was improved in the g-axis direction only. Compared with the two-dimensional asymmetric Tsallis cross-entropy algorithm, the calculation time of this algorithm decreased by about 30% and the threshold values of the two algorithms were almost the same. The algorithm proposed in this paper can rapidly and effectively segment defect targets, making it a more suitable method for detecting surface defects in factories with a rapid production pace. [ABSTRACT FROM AUTHOR]

Concerning the problem of large rotating machinery like wind turbine which runs in low speed and non-stationary state, this research mainly focuses on separating fault trend feature from non-fault feature and the method of state deterioration evolution based on bi-spectrum. Firstly, the experimental signal such as low-speed startup vibration signal of rotor test rig in the normal state and a plurality of unbalanced state have been collected. Bi-spectrum method is applied to extract fault feature which submerged in complex background noise. On the basis of bi-spectrum analysis, the fault feature evolutionary matrix is defined to represent the state of equipment deterioration. The eigenvalues of fault feature evolutionary matrix are computed and fitted to a normal distribution curve, from which the mean value and variance are taken as fault feature parameters. Fault feature parameters are verified effectively by experiments. Finally, depending on fault feature parameters, graphical representation of state deterioration evolution is established. It is beneficial to provide guidelines for equipment deterioration trend. This method is applied to analyze the real vibration signal of wind turbine with the type of WD646/600 KW, and actual equipment condition verified the effectiveness of the proposed method. [ABSTRACT FROM PUBLISHER]