This study proposes a composite-surfactant-assisted method for preparing Fe₃O₄ water-based nanolubricants to enhance environmental and tribological performance in rolling applications. The dispersion stability of nanoparticles in the suspension was analyzed. The optimal concentration of the nanolubricant was identified. In addition, the reaction mechanism between nanoparticles and water-based nanolubricants was discussed. The experimental results demonstrated that the lubricant containing 6 wt% Fe₃O₄ nanoparticles exhibited the best anti-friction and anti-wear performance. The aqueous lubricant with composite surfactants showed improved dispersion stability, with its Zeta potential increasing to −43.45 mV, and the intensity curve exhibited a single peak. Through contact angle measurements, wettability was also significantly improved. The molecular interactions of composite surfactants in the prepared water-based nanolubricants were investigated using numerical simulations. The water-based nanolubricant containing composite surfactants displayed enhanced adsorption capacity on Fe₃O₄ crystals. Compared to other surfactants, the Fe₃O₄ water-based nanolubricant prepared with composite surfactants exhibited stable dispersion properties. Therefore, composite surfactants can enhance the stability and wettability of water-based nanolubricants. This method enables the preparation of high-performance water-based rolling nanolubricants.

It is very important to carry out effective safety inspections on suppression rigging because of the bad service environment of suppression rigging: marine environments. In this paper, the multi-parameter simulation method in ANSYS and ANSYS Electronics Suite simulation software is used to simulate the effect of geomagnetic fields on the magnetic induction intensity of defective pressed rigging under the variable stress in marine environments. The results of the ANSYS simulation and geomagnetic flaw detection equipment are verified. The simulation results show that, according to the multi-parameter simulation results of ANSYS and ANSYS Electronics Suite simulation software, it can be found that, under the action of transverse force, the internal stress of the pressed rigging will affect the magnetic field around pressed rigging with defects. With an increase in internal stress in the range of 0~20 MPa, the magnetic induction intensity increases to 0.55 A/m, and with an increase in internal stress in the range of 20~150 MPa, the magnetic induction intensity decreases to 0.06 A/m. From the use of a force magnetic coupling analysis method, it can be obtained, under the lateral force of the defects in suppressing rigging, that magnetic flux leakage signals decrease with an increase in the rigging’s radial distance. The experiment results show that the difference between the peak and trough of the magnetic induction intensity at the pressed rigging defect calculated by the ANSYS simulation is very consistent with the results measured by the geomagnetic flaw detection equipment.

In this paper, technical code analysis and recognition of the defect signal of the suppression rigging based on a convolutional neural network are carried out given the difficulty and low recognition rate of the defect detection and recognition of the suppression rigging. Firstly, the magnetic induction signal of the suppression rigging defects is collected using CM-801 (Anshan, China), Kalman filtering is used to screen and pre-process the collected data, and the noise reduction data are presented in the form of a cloud image. The pressed rigging defect data set is constructed, and the region of broken wire defect and stress in the image is calibrated. The single-stage object detection algorithm YOLOv5 (You Only Look Once) based on convolutional neural network model calculation is used, the scale detection layer and positioning loss function of the YOLOv5 algorithm are improved and optimized, and the improved YOLOv5 algorithm is used for experiments. The experimental results show that the detection accuracy of the convolution neural network model can reach 97.1%, which can effectively identify the defect signal of the suppressed rigging.