Bo Jing

Parameter-Efficient Fine-Tuning is wildly used to transfer models between different domains. However, for some high-reliability-equipment, the degradation is at a slow rate and continually fluctuates, making it difficult to extract features effectively. Moreover, collecting an integrated source domain for high-reliability-equipment is tough due to the little sample of related dataset. Aiming at the transfer problem of time-series prediction model, this research proposed an LSTM-fine-tune model, where the parameters of the model are explicitly trained and partly frozen, such that a small number of gradient steps with a small amount of training data from a new task will produce good generalization performance on that task. The algorithm is then benchmarked on sinusoidal functions, where data were randomly generated with different phases and amplitudes. The results show that the LSTM-fine-tune model can learn knowledge from different sinusoidal data and fit a new one quickly with high accuracy. This paper also considers solving two actual problems. One is transferring oxygen concentrator data from the experimental condition to the actual service condition, the results show that the accuracy is largely improved. Moreover, this paper tried to extract more general degradation knowledge from the Wiener process and then transferred it to the degradation data of the oxygen concentrator. The results show that the model quickly achieved higher prediction accuracy with the knowledge. The code and data from the test-bed are accessible on https://github.com/panjinxin123/.

This paper investigates the problem of distributed dynamic event-triggered formation control for multiple unmanned surface vehicles (USVs) subject to external disturbances. Firstly, a novel event-based distributed formation control scheme is proposed, under an undirected communication graph. Wherein, a dynamic event-triggered data transmission mechanism is designed for communication resource reduction. The time-varying dynamic parameter ensures fewer triggering instants and a larger triggering time interval compared with the traditional static one. The adaptive laws are incorporated into the formation control scheme to address the effects of external disturbances and uncertainties. Subsequent to the theoretical analysis, it can be concluded that the relative tracking errors can converge to the origin, and all closed-loop signals are bounded. Moreover, it is proved that the triggering time sequences do not exhibit Zeno behavior. Finally, a numerical simulation is performed to verify the effectiveness of the proposed distributed formation controller.

The integrated-servo-actuator (ISA) is one of the most critical subsystems of aircraft flight-control system, which controls the speed, direction, displacement, and force of load for an aircraft. The degradation state of the ISA directly influences the safety of the aircraft. Hence, it is valuable to predict the degradation of the ISA to ensure its operating reliability. However, as a kind of complex system, the degradation mechanisms and the influences of the stress cannot be fully understood. Moreover, the nonlinear degradation process brings more difficulties to establish an accurate life prognosis model. To address these challenging issues, this paper proposed a hybrid degradation prognosis method that fused the physics-based model and data-driven model for ISA. The nonlinear Wiener process (NWP) algorithm is utilized to characterize the physical degradation process of ISA. The effect of different stresses is quantitatively modeled. Furthermore, the data-driven echo-state-network (ESN) is optimized to describe the nonlinear degradation process of ISA. More degradation data are generated based on the NWP model for ESN model training. Therefore, the degradation trajectory predicting model is fused with the physics-based degradation prognosis model so that both the degradation mechanisms and time series features within the monitoring data are combined. The experimental results based on the real ISA data illustrate that the proposed method has higher prediction accuracy which is meaningful to enhance the operating reliability of the ISA.

In this paper, the random vibration test and finite element simulation analysis of SAC305 solder joints in BGA packaged electronic chips were carried out. A failure model for BGA solder joints was established based on the life data. And Vulnerable parts in electronic chips were analyzed. Firstly, the random vibration test was conducted. Secondly a lognormal distribution model of solder joints by means of the life data was established and analyzed based on the fracture mechanics theory. Finally, the finite element simulation model of BGA packaged electronic chip was established and discussed. Failure characteristics of solder joints at different positions in electronic chips were compared and the failure mode of the solder joint was discussed using the simulation result and the observation result with scanning electron microscope(SEM). The results show that the life of each single solder joint in BGA packaged electronic chips follows a logarithmic normal distribution under the random vibration. Solder balls located at the four outermost corners of the chip are subjected to the greatest stress, which are the weakest parts in electronic chips. Cracks in solder joints are generated near the package side and emerged from the edge of the IMC layer with the largest curvature.

Due to the influence of working environment and stress, the failure degradation process of mechanical equipment is characterized by non-stationarity and uncertainty. The degradation pattern of a large number of mechanical equipment obeys the process from steady degradation to accelerated degradation. The rotating machinery wear results in gradual degradation in the early stage while rough contact surface and spall of equipment leads to accelerated degradation stage. However, the change-point of the degradation patterns are uncertain which leads to the ambiguity of the degradation pattern transition and uncertainty of the remaining life prediction model. Aiming at the problems of ambiguity of the pattern transition and uncertainty of the prediction model, the SKF-EN method is proposed in this paper. In this method the real-time data samples are processed through Switching Kalman filters, and the current degradation pattern is identified based on the posterior probability between the two filters of steady degradation and accelerated degradation. When the filters confidence indicates the entering of accelerated degradation pattern, the Elastic Net is used to model the degradation trajectory and predict its life in real time. The method was verified with an airborne fuel pump and rolling element bearings, and it realized the real-time identification of the degradation pattern and effective prediction of the remaining useful life.

Long short-term memory (LSTM) is widely applied in both academic and industrial fields. However, there is no reliable criterion on selecting hyperparameters of LSTM. Currently, although some widely used classic methods such as random search and grid search have obtained success to some extent, the problems in local optimum and convergence still exist. In this research, we propose to use grey wolf optimizer (GWO) to search for the hyperparameters of LSTM. Through the method, the superiority of metaheuristic in global optimization and the strength of LSTM in predicting are combined. In this model, number of hidden layer nodes and learning rate of LSTM are set as preys, and grey wolf pack has a simple but efficient mechanism to search for the optimal hyperparameters. The benchmark tests on several basic functions were utilized, and the results were verified by a comparative study with random search, support vector regression and several other regression methods. Specifically, we applied this algorithm in predicting the degradation trend of the airborne fuel pump. As a result, the ergodicity and convergence of the algorithm are proved mathematically based on Markov processes theory. The benchmark tests show that the GWO-LSTM model holds for predicting data with low overall slope and high partial fluctuation. The application in airborne fuel pump shows that, trained by dataset with 5700 points, the proposed model could predict sequence of 300 points with root mean square error 0.617 after 30 iterations of optimizing, which is 2.512 previously. The result further demonstrates that the proposed algorithm is applicable to make prediction with high accuracy. Overall, the effectiveness of GWO-LSTM model is verified from theoretical proof to benchmark tests and then to actual product application.

The accuracy performance of traditional direction of arrival (DOA) estimation algorithms is seriously affected by the reverberation. Considering the advantage of the sparse characteristic of speech signal in time-frequency (T-F) domain, this paper presents a new blind DOA estimation method based on integrated deep learning and convolutional non-negative matrix factorization (NMF). Firstly, mathematic models of microphone array and room impulse response are built. In addition, we extracted blindly initialization parameters of 2-D convolutional NMF using k-means clustering algorithm and singular value decomposition algorithm, which can be used to accurately estimate the main components of desired sound source in the reverberation environment of multi-path propagation. Moreover, the feedback mechanism is introduced into deep 2-D convolutional NMF and correlation coefficient between the signal decomposed by NMF and the signal to be decomposed is used to select the best separated signal for DOA estimation, which make the separation algorithm simpler and more efficient. Finally, test of orthogonality of projected subspaces (TOPS) algorithm is used to validate the DOA estimation capability of this algorithm. Compared with the unprocessed reverberation speech, the estimation error is reduced, which shows that the proposed algorithm can effectively improve the estimation accuracy of DOA estimation when the received signals are in a reverberant environment.

Nowadays, electronic equipment plays a key and important role in equipment and system, especially with the development of informatization. The failure of interconnect between the chip and PCB, is a major failure mode in electronic equipment, and vibration and temperature are the main environmental factors leading to solder joint failure, which are also the focus of this paper. This study analyzes the failure of QFP chip by random vibration test under three different temperature conditions. The test piece of QFP chip has a self-monitoring circuit, which can monitor its own state whether it is invalid or not. Firstly, the failure of interconnection structure and the effect of their location on reliability has been investigated. Then, the effect of temperature on vibration reliability for interconnection structures has been analyzed. Finally, combined with the exponential distribution of the interconnection structure, the random vibration reliability of the whole chip at different temperatures is evaluated. The results indicate that the interconnection structure of the same chip has similar failure modes, while the crack growth rate is various due to their location, resulting in the difference in their life. Failure modes of interconnect under 25°C and 75°C are similar, which different from failure modes under -25°C, and low temperature reduces vibration reliability of interconnection structure.

The airborne fuel pump as a typical high-reliability, long-life electromechanical component, its life prediction has problems such as small sample size and low prediction accuracy. Firstly, the degradation testing platform for airborne fuel pump is designed to obtain degradation data and life data. Secondly, a drift wiener process degradation model based on the combination of degradation data and life data is established. Finally, the life prediction is performed. The results show that predicted life of the airborne fuel pump, by the drift wiener process degradation model based on the combination of degradation data and life data, is closer to the true value and has higher accuracy, comparing to that by drift wiener process degradation model based on degenerate data.