Existing bearing fault diagnosis methods have some disadvantages, one being that most methods cannot completely consider all specific fault attributes. Another disadvantage is that the qualitative diagnosis method considers different fault types as a whole, and qualitative diagnosis of a single fault attribute is complicated. A convolutional neural network is proposed for application in the multi‐attribute quantitative bearing fault diagnosis. Multiple combinations of convolutional layers are adopted to directly extract features from one‐dimensional vibration signals. In addition, a softmax layer is designed to realise the simultaneous recognition of different fault attributes. The advantage of this approach is that it can realise diagnostic results for any combination of fault attributes and corresponding types, which overcomes the disadvantage of single attribute recognition in the traditional method. The method is simple but has strong generalisation ability with average diagnostic accuracy of more than 95%. According to bearing data from Case Western Reserve University and laboratory experiments by the authors, the results verify that the method can accurately and quantitatively diagnose bearing faults.

In order to solve the problem of uncontrollable cutting depth and the rough incision edge of the cornea with manual trephine in lamellar keratoplasty, an ultrasonic‐assisted corneal trephination method has been proposed for the first time in accordance with the advantage of ultrasonic vibration cutting, and the corresponding robotic system has been designed and researched. According to the traditional process of lamellar keratoplasty, the requirements of the surgical robotic system were first proposed. On this basis, the robotic system was designed and its schematic diagram was introduced. Second, the key components of the robotic body such as the eccentric adjusting mechanism and the end‐effector of ultrasonic scalpel were illustrated, which can realise corneal trephination of different incision diameters without scalpel replacement. Then the operation flow chart of a robot‐assisted lamellar keratoplasty was put forward. Finally, the preliminary verified experiments were performed using a grape and a porcine eyeball, respectively, in vitro with the prototype system. The results show that the robotic system can basically satisfy the operation requirements of lamellar keratoplasty. Owing to the less cutting force and smoother corneal incision edge of ultrasonic‐assisted lamellar keratoplasty compared with manual trephine, it was proved to be more feasible and superior.

Speech enhancement is an important preprocessing step in a wide diversity of practical fields related to speech signals, and many signal‐processing methods have already been proposed for speech enhancement. However, the lack of a comprehensive and quantitative evaluation of enhancement performance for multi‐speech makes it difficult to choose an appropriate enhancement method for a multi‐speech application. This work aims to study the implementation of several enhancement methods for multi‐speech enhancement in indoor environments of T60 = 0 s and T60 = 0.3 s. Two types of enhancement approaches are proposed and compared. The first type is the basic enhancement methods, including delay‐and‐sum beamforming (DSB), minimum variance distortionless response (MVDR), linearly constrained minimum variance (LCMV), and independent component analysis (ICA). The second type is the robust enhancement methods, including improved MVDR and LCMV realized by eigendecomposition and diagonal loading. In addition, online enhancement performance based on the iteration of single‐frame speech signals is researched, as is the comprehensive performance of various enhancement methods. The experimental results show that the enhancement effects of LCMV and ICA are relatively more stable in the case of basic enhancement methods; in the case of the improved enhancement algorithms, methods that employ diagonal loading iterations show better performance. In terms of online enhancement, DSB with frequency masking (FM) yields the best performance on the signal‐to‐interference ratio (SIR) and can suppress interference. The comprehensive performance test showed that LCMV and ICA yielded the best effects when there was no reverberation, while DSB with FM yielded the best SIR value when reverberation was present.

With the aim to identify new fault diagnosis and advanced robotic systems, this paper first proposes a fault diagnosis algorithm based on an artificial immune network model that can adjust the pruning threshold. Secondly, the algorithm is improved based on neighbourhood rough set theory, in which the relationships among the pruning threshold, misdiagnosis rate, and missed diagnosis rate in the shape space are discussed. In addition, an improved algorithm for adjusting the adaptively pruning threshold based solely on an observation index is described. The simulation experiments show that the algorithm can identify the new fault modes while keeping the misdiagnosis and missed diagnosis rates low.

The extreme learning machine‐based autoencoder (ELM‐AE) has attracted a lot of attention due to its fast learning speed and promising representation capability. However, the existing ELM‐AE algorithms only reconstruct the original input and generally ignore the probability distribution of the data. The minimum error entropy (MEE), as an optimal criterion considering the distribution statistics of the data, is robust in handling non‐linear systems and non‐Gaussian noises. The MEE is equivalent to the minimisation of the Kullback–Leibaler divergence. Inspired by these advantages, a novel randomised AE is proposed by adopting the MEE criterion as the loss function in the ELM‐AE (in short, the MEE‐RAE) in this study. Instead of solving the output weight by the Moore–Penrose generalised inverse, the optimal output weight is obtained by the fixed‐point iteration method. Further, a quantised MEE (QMEE) is applied to reduce the computational complexity of. Simulations have shown that the QMEE‐RAE not only achieves superior generalisation performance but is also more robust to non‐Gaussian noises than the ELM‐AE.