The Performance Analysis of PSO-ResNet for the Fault Diagnosis of Vibration Signals Based on the Pipeline Robot.

In the context of pipeline robots, the timely detection of faults is crucial in preventing safety incidents. In order to ensure the reliability and safety of the entire application process, robots' fault diagnosis techniques play a vital role. However, traditional diagnostic methods for motor drive end-bearing faults in pipeline robots are often ineffective when the operating conditions are variable. An efficient solution for fault diagnosis is the application of deep learning algorithms. This paper proposes a rolling bearing fault diagnosis method (PSO-ResNet) that combines a Particle Swarm Optimization algorithm (PSO) with a residual network. A number of vibration signal sensors are placed at different locations in the pipeline robot to obtain vibration signals from different parts. The input to the PSO-ResNet algorithm is a two-bit image obtained by continuous wavelet transform of the vibration signal. The accuracy of this fault diagnosis method is compared with different types of fault diagnosis algorithms, and the experimental analysis shows that PSO-ResNet has higher accuracy. The algorithm was also deployed on an Nvidia Jetson Nano and a Raspberry Pi 4B. Through comparative experimental analysis, the proposed fault diagnosis algorithm was chosen to be deployed on the Nvidia Jetson Nano and used as the core fault diagnosis control unit of the pipeline robot for practical scenarios. However, the PSO-ResNet model needs further improvement in terms of accuracy, which is the focus of future research work.

Effects of compound probiotics on growth performance, rumen fermentation, blood parameters, and health status of neonatal Holstein calves.

This study aimed to investigate the effects of compound probiotics (consisting of 108 cfu/g of Lactobacillus plantarum, 108 cfu/g of Pediococcus acidilactici, 108 cfu/g of Pediococcus pentosaceus, 107 cfu/g of and Bacillus subtilis) on growth performance, rumen fermentation, bacteria community, blood parameters, and health status of Holstein calves at the first 3 mo of age. Forty-eight newborn calves were randomly divided into the following 3 groups: control group (milk replacer with no compound probiotics), low compound probiotics group (milk replacer + 0.12 g of compound probiotics per head per day), and high compound probiotics group (HP; milk replacer + 1.2 g of compound probiotics per head per day). Starter pellets of the low compound probiotics and HP groups were coated with 0.05% compound probiotics. Milk replacer was provided from 2 to 63 d of age (6 L at 2-10 d, 8 L at 11-42 d, 6 L at 43-49 d, 4 L at 50-56 d, and 2 L at 57-63 d), and starter pellets were provided ad libitum from 7 to 90 d of age. Body weight and body size (d 1, 30, 60, and 90), blood (d 40 and 80), and rumen fluid (d 90) were analyzed using the one-way ANOVA procedure; fecal score was recorded daily and analyzed as repeated measures using the mixed model procedure. Results showed that diet supplemented with compound probiotics had no effects on the body weight, average daily gain, dry matter intake, and feed efficiency. At 90 d of age, diet supplemented with compound probiotics decreased the withers height. Immunity activities increased in the HP group, supported by the increased concentrations of serum total protein and immunoglobulins at 40 d of age, and by the increased activity of superoxide dismutase at 80 d of age. Diet supplemented with compound probiotics altered rumen fermentation, indicated by the decreased rumen acetic acid and propionic acid, and the increased butyric acid concentrations. Diet supplemented with compound probiotics improved the health status of calves, indicated by the decreased fecal score at 3 wk of age and the decreased medicine treatments. In summary, although diet supplemented with HP decreased the withers height, this level of probiotics is recommended to improve rumen development and health status of newborn Holstein calves.

Enhancing the sensitivity of aptameric detection of lysozyme with a "feed-forward" network of DNA-related reaction cycles.

In this study, a network of DNA-related reaction cycles was established to enhance the sensitivity of lysozyme detection with dual signal amplification, and aptamer-based reactions were integrated into this system to provide high specificity. The network was organized in a feed-forward manner: the "upstream cycles" recognized the lysozyme (the target) and released the "messenger strands" from probe A (a DNA construct); the "downstream cycles" received them and then released the "signal strands" from another DNA construct, probe B, in multiplied quantities to that of the original inputted lysozyme. The upstream cycles centered on "target-displacement polymerization", which circulates the lysozyme to provide primary amplification; the downstream cycles centered on "strand-displacement polymerization", which circulates the messenger strand to provide further amplification. There were also several "nicking-polymerization" cycles in both reaction groups that provide extra signal amplification. In total, the network enclosed eight interconnected and autonomic reaction cycles, with only two probes, two primers, and two enzymes needed as raw feeds, and the network can be operated simply in one-pot mode. With this network, lysozyme could be quantified at lysozyme concentrations as low as 2.0×10(-14) M, with a detection limit of 3.6×10(-15) M (3σ rule), which was seven orders of magnitude lower than that obtained without any amplification(1.8×10(-8) M). Detection of lysozyme in real serum samples confirmed the reliability and practicality of the assay based on this reported reaction network.