Remaining useful life (RUL) prediction allows for predictive maintenance of machinery, thus reducing costly unscheduled maintenance. Therefore, RUL prediction of machinery appears to be a hot issue attracting more and more attention as well as being of great challenge. This paper proposes a model-based method for predicting RUL of machinery. The method includes two modules, i.e., indicator construction and RUL prediction. In the first module, a new health indicator named weighted minimum quantization error is constructed, which fuses mutual information from multiple features and properly correlates to the degradation processes of machinery. In the second module, model parameters are initialized using the maximum-likelihood estimation algorithm and RUL is predicted using a particle filtering-based algorithm. The proposed method is demonstrated using vibration signals from accelerated degradation tests of rolling element bearings. The prediction result identifies the effectiveness of the proposed method in predicting RUL of machinery.

Many materials which could cause a real threat of a catastrophe due to fatigue, exceeding stress limits or plastic strain have magnetic properties that could affect the local magnetic field. Though active magnetic methods of condition monitoring are quite well-known and widely applied however, passive techniques which are based only on the existence of natural magnetic field of the Earth, still require research and improvement. It is obvious that every physical object within the magnetosphere interacts with Earth's magnetic field and is subjected to special laws of physics. Such objects can attract or deflect magnetic field lines around their matter. Own magnetic field of an object: H= -grad(w), where w is the magnetic potential, is a function of the gradient of magnetization: w = w(div M). Therefore, the measure of magnetic field of an object depends on an object's magnetization and distribution of its volume in the medium (space). Considering magnetoelastic effects (Villari Effect, magnetostriction), the additional stress causes transformation of the material to magnetic state which reflects the magnetization of an object. The magnetization depends on many factors. Magneto-mechanic phenomena have been known for a long time but as the technology developed, there have emerged new possibilities of acquisition, processing and analysis of these phenomena and of their use in technical diagnosis. Following a simple model analysis, a laboratory experiment was proposed and performed. By controlling plastic and elastic range of the specimen's strain, we have investigated the existence of a relation between stress and degree of magnetization, which is strictly connected with deformation and effort. Magnetic anomalies which are generated due to magneto-mechanic effect were collected by the three axial fluxgate magnetometer, which allowed presentation of own magnetic field component, which was least sensitive to the disturbance present in a real world. Experiment included in the paper confirms the existence of a relationship between stress and magnetization degree which additionally depends on the kind of material. In addition the possibility of remote identification of magnetoelastic effects has been contemplated and examined. Finally the paper analyzes the impact of the shape of specimen on the interaction between Earth and eigen magnetic fields during a tension test. Further directions and comments on development of techniques which allow exact stress assessment of technical objects made of ferromagnetic materials have been included.