Collecting multi-channel sensory signals is a feasible way to enhance performance in the diagnosis of mechanical equipment. In this article, a deep learning method combined with feature fusion on multi-channel sensory signals is proposed. First, a deep neural network (DNN) made up of auto-encoders is adopted to adaptively learn representative features from sensory signal and approximate non-linear relation between symptoms and fault modes. Then, Locality Preserving Projection (LPP) is utilized in the fusion of features extracted from multi-channel sensory signals. Finally, a novel diagnostic model based on multiple DNNs (MDNNs) and softmax is constructed with the input of fused deep features. The proposed method is verified in intelligent failure recognition for automobile final drive to evaluate its performance. A set of contrastive analyses of several intelligent models based on the Back-Propagation Neural Network (BPNN), Support Vector Machine (SVM) and the proposed deep architecture with single sensory signal and multi-channel sensory signals is implemented. The proposed deep architecture of feature extraction and feature fusion on multi-channel sensory signals can effectively recognize the fault patterns of final drive with the best diagnostic accuracy of 95.84%. The results confirm that the proposed method is more robust and effective than other comparative methods in the contrastive experiments.

Erosion wear at the key point of a drill string is very severe in gas drilling. The investigation shows that failure of drill string is very serious in gas drilling. The probability of failure of the drill pipe and the drill collar is the highest in all the drill string, and the near placement of pin and box is often damaged. According to the investigation of drill string failure and erosion theory, the erosion model of drill string is established. The erosion rate at the key point of a drill string is solved using the Grant and Tabakoff formula. Different factors, such as gas injection volume, rate of penetration (ROP), cuttings' diameter, cuttings' shape factor, cuttings' number, and temperature of the annulus, are considered. The result shows that the erosion rate at the key point is more severe than that of other locations on the drill pipe. Because of higher peak stress for a drill string with eroded wear, there is a more serious effect on the residual strength of a drill string with eroded wear. Crack forms easily, due to severe erosive wear and deeper pits. Also, fracture failure of a drill string is caused by larger axial load and torque. In this paper, analysis of such influencing parameters as gas injection volume, ROP, cuttings' particle size, cuttings' shape factor, cuttings number and temperature of the annulus is conducted, among which gas injection volume, ROP and cuttings number are proven as the main controlling factors that affect the erosion wear at the key point of a drill pipe.

Coiled tubing (CT) has been widely used for oil and gas exploitation, however corrosion of CT under high pressure and high temperature (HPHT) environment was often reported, also corrosion induced failures of CT welds were often observed to occur during service. Corrosion related behaviors of CT welds are not clear. Therefore, a study of the corrosion resistance of CT welds under HPHT environment is carried out. In order to efficiently evaluate the corrosion resistance of welds, some test samples were obtained by linear cutting out of a CT110 in service on the site. The water samples from gas field were used as the test reagent to simulate the actual corrosive medium. Based on the results of weight loss test under HPHT corrosive environment and tensile test under room conditions, the corrosion sensitivities of the welding seam and base material under various temperatures and partial pressures of CO₂ as well as the mechanical properties of the corroded CT were compared and evaluated quantitatively, the corrosion morphologies and material products of the test samples were analyzed by scanning electron microscope (SEM). The test results showed that the corrosion rates of the welding seam in a HPHT caldron were 1.7, 2.0 and 1.2 times of the base metal’s when the total pressure is 4MPa, and the temperature is 30°C, 60°C and 90°C, respectively. The corrosion rates of the welding seam is 2.0, 2.1 and 2.0 times of the base metal’s when the partial pressure of CO₂ is 0.1MPa, 0.2MPa and 0.3MPa, respectively. The yield strength of the weld seam after corrosion test was found to be reduced by 4.8% (the yield strength of the base metal was reduced by 4.0%) and its tensile strength was reduced by 8.2% (the base metal was reduced by 7.1%). This indicates that CT weld seam is more susceptible to corrosion than CT base material under service condition.