We determined burrow temperature variation for the Chinese pangolin in winter over a study period from 1 December 2009 to 28 February 2010, at Luofushan Nature Reserve, China. Our results show that the air temperature inside the burrow was stable with only a slight fluctuation, the diurnal variation amplitude was merely 0.0-0.5 °C (SD = 0.08 ± 0.09 °C, n = 90), and winter temperature fluctuated between 17.8-21.0 °C. On the contrary, air temperature outside the burrow fluctuated dramatically, the diurnal variation
amplitude ranging from 0.7-20.0 °C (SD = 4.99 ± 3.47 °C, n = 90); the seasonal temperature fluctuated between 4.6-38.3 °C. In winter,
the average temperature inside the burrow was 18.96 °C (SD = 0.91, n = 90), and significantly higher than the average temperature
outside the burrow (p < 0.01), which was 15.16 °C (SD = 3.85, n = 90). No significant relationship was found between the temperatures inside and outside the burrow, and the temperature changes outside the burrow had almost no significant influence on thermal conditions inside the burrow. It was therefore proposed that the most optimum ambient temperature for Chinese pangolins in winter was in the range of 18-21 °C.
In this paper, a continuous wavelet process neural network (CWPNN) model is proposed based on the wavelet theory and process neural network model. The network offers good compromise between robust implementations resulting from the redundancy characteristic of non-orthogonal wavelets, and efficient functional representations that build on the time-frequency localization property of wavelets. Moreover, the network can deal with continuous input signals directly. The corresponding learning algorithm is given and the network is used to solve the problems of aeroengine condition monitoring. The simulation test results indicate that the CWPNN has a faster convergence speed and higher accuracy than the same scale process neural network (PNN) and BP neural network. This provided an effective way for the problems of aeroengine condition monitoring.
Aero engine condition monitoring (ECM) is essential in terms of improving availability and reducing life-cycle costs of the aero engine. Aero engine exhaust gas temperature (EGT) plays the most critical role in the ECM. By monitoring the EGT, maintenance crews can realize the aero engine health condition and speculate about the latent faults of the aero engine in advance. But it is difficult for traditional methods to predict the tendency of the EGT. So, a new model of hybrid recurrent process neural network (HRPNN) is proposed. The HRPNN acquires hidden-to-hidden and output-to-hidden feedbacks by introducing respectively the context units with self-feedback connections, and its inputs are time-varied functions. Hence, it can represent more states of the complicated nonlinear dynamical system such as aero engine more directly. A learning algorithm base on resilient backpropagation (Rprop) is developed for the HRPNN. To simplify the learning algorithm, a set of appropriate orthogonal basis functions are introduced to expand the input functions and the connection weight functions of the HRPNN. The method validation is proved by a benchmark of the Mackey-Glass chaos time series prediction. A practical utilization of the aero engine EGT prediction also demonstrates this point in terms of aero engine condition monitoring, the results indicate HRPNN can be used as an efficient ECM tool.
The observations of Sunda pangolin reproductive parameters in this paper were based on the wild-caught animals and those that had spent time in captive environments, however, when analyzing the results, we did not consider differences in terms of breeding habits between the two. Still, this research has led to an increase in knowledge of the breeding habits of the Sunda pangolin. Our results suggest that there is no breeding season or season of parturition for the Sunda pangolin, which breeds all year round. We estimated the gestation period in this species to be around six months. Sexual maturity occurred at one year old or as early as six-seven months
old in some individuals, and requires further investigation. Each Sunda pangolin in this study gave birth to one offspring at a time. The sex ratio at birth was 0.875:1 (♀:♂) (n = 15); and the weaning age was estimated at four months with a weight of 1.19 ± 0.50 kg (n = 3), which concurs with recent research. Findings in this study will contribute to future analyses of population dynamics, species conservation, and both in situ and ex situ management of the Sunda pangolin. Despite this contribution, further studies are needed on the reproductive parameters of Sunda pangolin.