Research into rolling bearing fault diagnosis methods is of great significance because rolling bearings are a key part of mechanical equipment. The effect of iterative generalized demodulation (IGD) on the demodulation of the fundamental frequency component is obvious in the fault diagnosis of rolling bearings at variable speeds. However, there is a problem; the frequency curve of the demodulation octave frequency component overlaps, and multiple determinations of the bandpass filter parameters produce an artificial error that leads to the misdiagnosis of faults. Therefore, a method for rolling bearing fault diagnosis based on adaptive generalized demodulation (AGD) is proposed. First, the resonance band is intercepted by the fast kurtogram and its envelope results. Second, the adaptive chirp mode decomposition (ACMD) algorithm is used to decompose the envelope signal, the relationship between the time and frequency of the signal is clearly characterized by the form of multimedia pictures, and the instantaneous frequency of each signal component is calculated. Third, the instantaneous frequency is used as the phase function to perform generalized demodulation for each signal component. Last, all the demodulated signals are accumulated, and a fast Fourier transform (FFT) is used to extract the fault's characteristic frequency. The proposed method is compared with IGD by using simulation signals and actual bearing signals collected by sensors under the Internet of Things (IoT). An adaptive diagnosis function is realized through this proposed method at variable speeds. Moreover, the average frequency spectrum identification rate of rolling bearing faults is improved by more than 2.6 times compared with that of the IGD in the simulation signal verification and by more than 1.7 times compared with that of the IGD in the real signal verification. This method is strongly immune to noise. INDEX TERMS Fault diagnosis, rolling bearing, adaptive generalized demodulation, Internet of Things, multimedia.

Sensors are used to sense the state information of physical entities in the Internet of Things (IoT). Thus, a large amount of dynamic real-time data is generated. The entity similarity search based on the quantitative dynamic sensor data is thus worth studying. To the best of our knowledge, there is no research on the entity similarity search based on feature data selection for the quantitative dynamic sensor data in the IoT. This paper proposes a selection mechanism for the entity main features (SMEF). The SMEF is a feature data selection method based on the quantitative dynamic sensor data. It uses the feature matrix to delete the irrelevant entity features, applies an improved relief algorithm (iRelief) to calculate the feature data relevance and proposes a three-component storage relation table of the entities, models, and features (TEMF) for the dynamic feature weights calculation. The experimental results show that the similarity search algorithm based on feature data selection can improve the average search accuracy by more than 10%, as well as increase the search speed and reduce the data transmission and storage costs.