This paper suggests a new method to predict the Remaining Useful Life (RUL) of rolling bearings based on Long Short Term Memory (LSTM), in order to obtain the degradation condition of the rolling bearings and realize the predictive maintenance. The approach is divided into three parts: the first part is the clustering to detect the damage state by the density-based spatial clustering of applications with noise. The second one is the health indicator construction which could give a better reflection of the bearing degradation tendency and is selected as the input for the prediction model. In the third part of the RUL prediction, the LSTM approach is employed to improve the accuracy of the prediction. The rationale of this work is to combine the two methods—the density-based spatial clustering of applications with noise and LSTM—to identify the abnormal state in rolling bearings, then estimate the RUL. The suggested method is confirmed by experimental data of bearing life cycle, and the RUL prediction results of the model LSTM are compared with the nonlinear au-regressive model with exogenous input model. In addition, the constructed health indicator is compared with the spectral kurtosis feature. The results demonstrated that the suggested method is more appropriate than the nonlinear au-regressive model with exogenous input model for the prediction of bearing RUL.
Bearings are essential components in rotating machines. They ensure the rotation and power transmission. So, these components are essential elements for industrial machines. Thus, real-time monitoring is required to detect a possible anomaly, diagnose the failure of rolling bearing and follow its evolution. This paper presents a methodology for automatic online implementation of fault diagnosis of rolling bearings, by AOC-OPTICS (automatic online classification monitoring based on ordering points to identify clustering structure, OPTICS). The algorithm consists of three phases namely: initialization, detection and follow-up. These phases use the combination of features extraction methods, smart ranking, features weighting and classification by the OPTICS method. Two methods have been integrated in the dimension reduction step to improve the efficiency of detection and the followed of the defect (relief method and t-distributed stochastic neighbor embedding method). Thus, the determination of the internal parameters of the OPTICS method is improved. A regression model and exponential model are used to track the fault. The analytical simulations discuss the influence of parameters automation. Experimental validation shows detection with 100% accuracy and regression models of monitoring reaching .
In the case of an unavoidable frontal collision between a vehicle and a pedestrian, the activation of a protection system can reduce the severity of injuries caused by the collision. However, to fulfill this objective, it is necessary to determine when the shock will occur. To overcome this problem, we place inside the front bumper a metallic sheet that emits an electric field. This field is oriented toward the front of the vehicle by means of various guard screens. The intrusion into the emitted electric field induces a capacitive coupling with the sensor. Which will enable the electronic device to detect the presence of the pedestrian at a distance of 1 m. To avoid slow drifts in time, the change in capacity is measured every millisecond. The last hundred acquisitions are considered as a history. This history is compared with the signature of a pedestrian who was established in the laboratory. When the pedestrian is about a thirty centimeters of the vehicle and the shock is inevitable, the protection systems are activated. When the vehicle is at very low speed, this device can be used as parking assistance.
Every year, lives of millions of people are cut short or considerably affected by road accidents. Most of them happen in urban areas where the speed limit is supposed to be below 50 km/h. Active protection devices (such as airbags) attached at the front of the vehicle can help reduce the severity of injuries inflicted in such circumstances. However, the effectiveness of such strategies depends greatly on how well we can anticipate the impact moment of the accident. The physical principle of capacitive coupling can be used to anticipate the impact by detecting the intrusion of the pedestrian in the detection volume of the probe. However, any intrusion into the sensing volume of probe can increase its capacitance like dust deposits on the surface of the capacitive probe, the variation of the air humidity, the air friction on the car's body, which makes the common voltage float among others that influence the capacitance of the probe and make the voltage carried by the probe vary over time. To overcome this problem, we define the concept of “pedestrian signature.” This concept can help us distinguish the presence of a pedestrian in the sensing volume of the probe from any other perturbations. Thus, we can anticipate the moment of impact early enough to trigger protection systems. The analog electronic device, we present in this paper, along with the pedestrian signature can help trigger protection devices to react at the right moment. The same device can also be used as parking aid when the vehicle speed is less than 10 km/h.
10 December 2025 in Journal of Vibration Engineering & Technologies