The research on driver fatigue detection is of great significance to improve driving safety. This paper proposes a real-time comprehensive driver fatigue detection algorithm based on facial landmarks to improve the detection accuracy, which detects the driver’s fatigue status by using facial video sequences without equipping their bodies with other intelligent devices. A tasks-constrained deep convolutional network is constructed to detect the face region based on 68 key points, which can solve the optimization problem caused by the different convergence speeds of each task. According to the real-time facial video images, the eye feature of the eye aspect ratio (EAR), mouth aspect ratio (MAR) and percentage of eye closure time (PERCLOS) are calculated based on facial landmarks. A comprehensive driver fatigue assessment model is established to assess the fatigue status of drivers through eye/mouth feature selection. After a series of comparative experiments, the results show that this proposed algorithm achieves good performance in both accuracy and speed for driver fatigue detection.

The scattering layer in the TiO₂photoanode (PAs) of dye-sensitized solar cells (DSSCs) is doped with single-layer graphene (G), and DSSC is prepared by doctor blade coating method. A small amount of graphene (0.0016 wt.%) in a graphene aqueous solution (G-AS) and a G-TiO₂paste was prepared to make 2–20 wt.% of G-AS in the deionized water (DIW). The UV-Vis measurement results show that the TiO₂scattering layers doped with graphene effectively improve the visible light absorption intensity of DSSC PAs and increase the current density (Jsc) from 13.84 mA/cm²to 16.20 mA/cm². The Electrochemical Impedance Spectroscopy (EIS) measurement showed that the internal structural impedance Rk [ ] decreased from 12.086 [ ] (without graphene doping) to 9.875 [ ] at 5 wt.% of the graphene doping. The photoelectric conversion efficiency (PCE) increased from 6.56% of the original un-doped graphene to the maximum PCE value of 7.57% at 5 wt.%. The results show that the best PCE is obtained when the concentration of G-AS is 5 wt.%.

The doctor blade coating method is used to prepare dye-sensitized solar cells (DSSCs) and dope the original titanium dioxide (TiO₂, P25) photoanode (PA) with single-layer graphene (G), graphene quantum dots (GQDs), and gold (Au) nanoparticles in this research. The results show that doping PAs with G, GQDS, and Au effectively increases the short-circuit current density ([ ], conversion efficiency ([ ]), and decreases the internal structure impedance ([ ]) of DSSCs. [ ] increases from 13.62 to 17.02, 15.22, 16.05 mA/cm², while [ ] (%) increases from 6.36 to 7.50, 7.08, 7.04% when doping G, GQDs, and Au, respectively. The analysis of Electrochemical Impedance Spectroscopy (EIS) reveals that the doping decreases [ ] from 11.28 to 8.36, 8.78, 8.54 [ ], respectively. Then, the titanium dioxide (TiO[ ]-doped G-GQDs, G-Au, and QDs-Au on DSSCs influence [ ] that increases to 5.45, 15.37, and 15.31 mA/cm², respectively. In this case, the values of [ ] are found to be 7.21%, 7.35%, and 7.00%, while those of [ ] are 8.44, 8.63, and 9.18 [ ]. The values of [ ] and [ ] are highest but that of [ ] are lowest when doping with G, which proves that the photoanode of the DSSC effectively activates the photogenerated electrons in the film by doping single-layer graphene and TiO₂captures its electrons through graphene. The decreasing electron–hole recombination rate allows the photogenerated electrons to be quickly transferred to the external circuit. As a result, the efficiency of DSSCs is improved.

In this study, a loader drive axle digital model was built using 3D commercial software. On the basis of this model, the transmission efficiency of the main reducing gear, the differential planetary mechanism, and the wheel planetary reducing gear of the loader drive axle were studied. The functional relationship of the transmission efficiency of the loader drive axle was obtained, including multiple factors: the mesh friction coefficient, the mesh power loss coefficient, the normal pressure angle, the helix angle, the offset amount, the speed ratio, the gear ratio, and the characteristic parameters. This revealed the influence law of the loader drive axle by the mesh friction coefficient, mesh power loss coefficient, and speed ratio. The research results showed that the transmission efficiency of the loader drive axle increased with the speed ratio, decreased when the mesh friction coefficient and the mesh power loss coefficient increased, and that there was a greater influence difference on the transmission efficiency of the loader drive axle.