Data-driven rolling-bearing fault diagnosis methods are mostly based on deep-learning models, and their multilayer nonlinear mapping capability can improve the accuracy of intelligent fault diagnosis. However, problems such as gradient disappearance occur as the number of network layers increases. Moreover, directly taking the raw vibration signals of rolling bearings as the network input results in incomplete feature extraction. In order to efficiently represent the state characteristics of vibration signals in image form and improve the feature learning capability of the network, this paper proposes fault diagnosis model MTF-ResNet based on a Markov transition field and deep residual network. First, the data of raw vibration signals are augmented by using a sliding window. Then, vibration signal samples are converted into two-dimensional images by MTF, which retains the time dependence and frequency structure of time-series signals, and a deep residual neural network is established to perform feature extraction, and identify the severity and location of the bearing faults through image classification. Lastly, experiments were conducted on a bearing dataset to verify the effectiveness and superiority of the MTF-ResNet model. Features learned by the model are visualized by t-SNE, and experimental results indicate that MTF-ResNet showed better average accuracy compared with several widely used diagnostic methods.

To solve the troubles existing in laryngeal surgical operation and extend surgeon's ability, a master-slave robot system with the name ¿Microhand-III¿ was designed. The novel slave robot employs hybrid mechanism and enables the 7 DOF end effector complex surgical manipulation ability. Mechanical details of the slave robot were described and an experiment prototype was established. The kinematics of master device and slave robot were studied followed by the master-slave mapping arithmetic. Redundancy control solution for the slave manipulator trajectory planning was also investigated. The experiment results approved both the design of the system and the master-slave mapping arithmetic. Suturing experiment further validated the potential of the system to enhance the laryngeal surgical operation.

The advent of internet of things (IoT) technology has ushered in a new dawn for the digital realm, offering innovative avenues for real-time surveillance and assessment of the operational conditions of intricate mechanical systems. Nowadays, mechanical system monitoring technologies are extensively utilized in various sectors, such as rotating and reciprocating machinery, expansive bridges, and intricate aircraft. Nevertheless, in comparison to standard mechanical frameworks, large amusement facilities, which constitute the primary manned electromechanical installations in amusement parks and scenic locales, showcase a myriad of structural designs and multiple failure patterns. The predominant method for fault diagnosis still relies on offline manual evaluations and intermittent testing of vital elements. This practice heavily depends on the inspectors’ expertise and proficiency for effective detection. Moreover, periodic inspections cannot provide immediate feedback on the safety status of crucial components, they lack preemptive warnings for potential malfunctions, and fail to elevate safety measures during equipment operation. Hence, developing an equipment monitoring system grounded in IoT technology and sensor networks is paramount, especially considering the structural nuances and risk profiles of large amusement facilities. This study aims to develop customized operational status monitoring sensors and an IoT platform for large roller coasters, encompassing the design and fabrication of sensors and IoT platforms and data acquisition and processing. The ultimate objective is to enable timely warnings when monitoring signals deviate from normal ranges or violate relevant standards, thereby facilitating the prompt identification of potential safety hazards and equipment faults.

To realize the reduction in cutting force and guarantee pruning section quality in the pruning and stubble work of Caragana korshinskii (C.K.), a concentric curvilineal edge sliding cutter was proposed and the related cutting characteristics were studied. The impacts of branch diameter (D), cutting speed (${\mathrm{V}}_{\mathrm{c}}$), blade wedge angle ($\mathsf{\beta }$), cutting clearance ($\mathrm{c}$) and moisture content (W) on peak torque (T) and cutting energy (E) with this cutter were explored in single-factor tests. On the basis of the Box—Behnken principle, a multi-factor test was further conducted based on the single-factor tests with ${\mathrm{V}}_{\mathrm{c}}$, $\mathsf{\beta }$ and c as influencing factors and with T and E as targets, and a regression model was established. Test results indicate that the peak torque (T) increases with the increase in D and $\mathsf{\beta }$ and reduces with the growth of ${\mathrm{V}}_{\mathrm{c}}$ and W; with the increase in $\mathrm{c}$, it reduces first and then rises; the cutting energy (E) increases with the growth of D and $\mathsf{\beta }$, declines with the increase in W and diminishes first and then rises with the increase in ${\mathrm{V}}_{\mathrm{c}}$ and $\mathrm{c}$. The optimal parameter combination of the regression model was obtained with ${\mathrm{V}}_{\mathrm{c}}$ of 2.16 rad/s, $\mathsf{\beta }$ of 20$°$ and $\mathrm{c}$ of 1.0 mm, which resulted in a T of 17.25 N·m and P of 7.03 J. The discrepancies between the observed and forecasted values for T and E are 0.87% and 5.004%. New cutting tool and data support for the development of subsequent C.K. branch stubble equipment can be obtained with this new sliding cutter.

Compressed Sensing (CS) has emerged as an efficient framework for sensor-based data acquisition and reconstruction, and is now widely employed in image processing. Deep unfolding networks integrate deep neural networks with optimization algorithms, emerging as a prevalent approach for image CS by enhancing interpretability and reconstruction performance. However, most existing deep unfolding networks suffer from insufficient integration and utilization of feature information during the iterative process. To address this limitation and achieve the goal of fusing complementary information to form a richer and finer feature representation, we propose an Iterative Shrinking-Threshold Algorithm (ISTA)-based deep unfolding network with optimized feature aggregation architecture for high-quality image CS, dubbed ISTOF-Net. By introducing a feature aggregation architecture, ISTOF-Net enhances both the integration and utilization of local detail features and global structural features. Specifically, in the reconstruction module, we design a novel Optimized Feature Aggregation Module (OFAM), which combines global structural features with local detail features, enhancing their integration and utilization through feature modulation and attention mechanisms. Moreover, we introduce auxiliary Convolutional Module (CM) to further refine and enhance fine image details. In addition, we adopt a lightweight network design, effectively reducing both computational complexity and reconstruction time. Experimental results on datasets acquired by image sensors and on remote sensing image demonstrate that ISTOF-Net outperforms state-of-the-art methods in both reconstruction quality and efficiency. Its high performance and lightweight design make ISTOF-Net ideal for sensor-based imaging systems that demand data compression and rapid imaging.

PDC (polycrystalline diamond compact) bit is the key equipment for drilling holes inside the rock in oil and mining industry. Inspired by the shape and structure of Capra sibirica horn, a bionic lateral PDC reamer bit with variable lateral reaming radius was developed. Side view of Capra sibirica horn was employed for fitting the horn shape curve based on picture processing method. PDC teeth were arranged on the horn shape blade imitating the transverse ridges on the horn to cut the rock material, found with only 30 utilization rate of the total teeth and load concentration of the last tooth. A bionic blade curve evolved from the Capra sibirica horn was defined with geometric method for the lateral reamer bit; the utilization rate of the teeth on the bionic blade curve was improved to 90 with uniformly distributed reaming load. Multigroup simulations were conducted with the finite element method; the effects of bit revolution speed and rotation feed speed of the bionic blade to reaming load were emphatically studied. Concrete sample was reamed indoors from 240mm to 407mm in diameter, and the bionic lateral PDC reamer bit was approved by the test result.