Search

ObjectiveIn order to improve the safe and stable operation level of compressor equipment, this paper puts forward a rapid diagnosis method of surge states based on hybrid deep learning parameter identification, and proposes an active disturbance rejection control (ADRC) strategy to realize compressor anti-surge. MethodFirst, a long-short-term memory neural network (LSTM) is used to process the time series relationship of the input and output data for compressor parameter identification; the interval probability estimation ability of Gaussian process regression (GPR) is integrated; a combination of LSTM and GPR (LSTM-GPR) is proposed; and a hybrid deep learning parameter identification algorithm is used to realize the rapid diagnosis of the compressor surge state. Then, based on the ADRC method, the parameters of the compressor's throttle valve are controlled, and the accurate control of the surge state of the compressor is realized through the compensation of the throttle valve parameters by the control amount. ResultsThe results show that the hybrid deep learning parameter identification algorithm can accurately identify the critical Greitzer parameters of the compressor and quickly and accurately judge whether it is in a surge state, and the ADRC-based control strategy can effectively allow the compressor to exit the surge state, which is faster and more effective than traditional PID control and nonlinear feedback control without losing the working range of the compressor. ConclusionThe proposed parameter identification and ADRC method can be applied to the surge diagnosis and active control of compressors to improve their safety and stability.

ObjectiveIn order to overcome the influence of the nonlinear time-varying characteristics of gas turbines on dynamic control and performance monitoring，this paper combines the time series memory and nonlinear relation expression ability of a long short-term memory neural network (LSTM) with the interval probability estimation ability of Gaussian process regression (GPR) to propose an online parameter identification algorithm for the key dynamic parameters of gas turbines based on an LSTM and GPR-based hybrid deep learning model (LSTM-GPR). MethodsFirst, the dynamic mechanism model of a gas turbine is established, and a large amount of training data is generated by taking fuel calorific value, compressor efficiency and load power moment as the parameters to be identified. Next, the parameter identification network model of LSTM-GPR is constructed, and the training data is input for network training and weight coefficient learning. Finally, the trained LSTM-GPR hybrid deep learning model is used to identify the dynamic operating parameters of the gas turbine model online, and the identification results are analyzed to verify the effectiveness of the proposed algorithm.ResultsThe simulation results show that the online identification results of the proposed LSTM-GPR hybrid model algorithm are accurate, with a recognition error of less than 1% and good real-time performance. Compared with the LSTM single model, the proposed algorithm can obtain a better mean estimation effect and provide a reliable confidence interval range. ConclusionsThe LSTM-GPR hybrid algorithm can be effectively applied to the online parameter identification of a gas turbine model, laying a foundation for its further application to the dynamic operation parameter identification of practical units.

Abstract Platinum‐based ordered alloy catalysts possess higher intrinsic activity in oxygen reduction reactions (ORR). High‐temperature annealing during ordered alloy formation frequently results in larger nanoparticles, and the strategy for obtaining ordered alloys at 600 °C is still undefined. Herein, an ordered Fe‐doped PtCo catalyst (O‐PtCoFe/C) with a size of sub‐4 nm was prepared at 600 °C derived from PtFe@CoO. CoO can generate oxygen vacancies by H2 reduction, lowering the atomic migration barrier and serving as a protective layer to inhibit nanoparticle migration. Experimental analyses showed the formation of O‐PtCoFe/C and electron‐rich Pt atoms due to Pt, Co, and Fe, which was advantageous for ORR performance. The mass activity of the prepared catalyst for ORR was 382.8 mA mgPt−1, which is 5.4 times greater than Pt/C. After 10000 potential cycles, the half‐wave potential was only negatively shifted by 10 mV. In PEMFC (proton exchange membrane fuel cells) tests, the O‐PtCoFe/C showed only 3 % decay after 3000 cycles, whereas the Pt/C showed a significant loss (18.4 %). This work provides an effective method for preparing ordered PtCo alloys for fuel cell cathode catalysts at 600 °C.

Abstract Southeast Asia comprises 11 countries that span mainland Asia across to numerous islands that stretch from the Andaman Sea to the South China Sea and Indian Ocean. This region harbors an impressive diversity of history, culture, religion and biology. Indigenous people of Malaysia display substantial phenotypic, linguistic, and anthropological diversity. Despite this remarkable diversity which has been documented for centuries, the genetic history and structure of indigenous Malaysians remain under-studied. To have a better understanding about the genetic history of these people, especially Malaysian Negritos, we sequenced whole genomes of 15 individuals belonging to five indigenous groups from Peninsular Malaysia and one from North Borneo to high coverage (30X). Our results demonstrate that indigenous populations of Malaysia are genetically close to East Asian populations. We show that present-day Malaysian Negritos can be modeled as an admixture of ancient Hoabinhian hunter-gatherers and Neolithic farmers. We observe gene flow from South Asian populations into the Malaysian indigenous groups, but not into Dusun of North Borneo. Our study proposes that Malaysian indigenous people originated from at least three distinct ancestral populations related to the Hoabinhian hunter-gatherers, Neolithic farmers and Austronesian speakers.

With the rapid development of deep learning-based detection algorithms, deep learning is widely used in the field of infrared small target detection. However, well-designed adversarial samples can fool human visual perception, directly causing a serious decline in the detection quality of the recognition model. In this paper, an adversarial defense technology for small infrared targets is proposed to improve model robustness. The adversarial samples with strong migration can not only improve the generalization of defense technology, but also save the training cost. Therefore, this study adopts the concept of maximizing multidimensional feature distortion, applying noise to clean samples to serve as subsequent training samples. On this basis, this study proposes an inverse perturbation elimination method based on Generative Adversarial Networks (GAN) to realize the adversarial defense, and design the generator and discriminator for infrared small targets, aiming to make both of them compete with each other to continuously improve the performance of the model, find out the commonalities and differences between the adversarial samples and the original samples. Through experimental verification, our defense algorithm is not only able to cope with multiple attacks but also performs well on different recognition models compared to commonly used defense algorithms, making it a plug-and-play efficient adversarial defense technique. [ABSTRACT FROM AUTHOR]

The past and present status of Grapholita pallifrontana in Cambridgeshire has been investigated. The species was discovered in Cambridgeshire by William Warren, most likely in 1887; the next published record was in 2021. Its sole larval foodplant, Wild Liquorice Astragalus glycyphyllos has been well-documented by botanists since 1660. We visited the 15 monads with post-1985 records and relocated plants in 11 of them, plus one new adjacent monad. We subsequently revisited these 12 monads during the season when larvae are detectable within the seedpods, and found G. pallifrontana in six of the monads, concentrated in the southeast and southwest of VC29. The botanical history of these sites suggests that Wild Liquorice has probably only been present in these locations for the last half-century, and that both foodplant and moth must therefore be quite mobile. Records from adjacent vicecounties demonstrate an overall L-shaped G. pallifrontana distribution, with the Cambridgeshire colonies at its eastern extremity, and raise the question of whether most may belong to a single meta-population. [ABSTRACT FROM AUTHOR]

The article focuses on the distribution and conservation of the Liquorice Piercer moth, Grapholita pallifrontana, in Huntingdonshire, VC31. Topics include the moth's status as a category 3 Red Data Book species, its reliance on Wild Liquorice (Astragalus glycophillus) as a foodplant, and the increasing interest in tracking its current distribution for conservation efforts.

We report the results of a second six-year study of the macromoths in a village-edge garden in southern England. 121 additional species were recorded, mainly by light trapping, but also by daytime recording (including pheromones) or early stages. One-third were likely to be residents nearby and a few were migrants from overseas, but the majority were considered likely wanderers from more distant locations in England. Species previously identified as expanding or declining nationally generally showed similar patterns in our garden, but with a few striking exceptions. The rate of species addition with time showed no sign of levelling off and trapping when the night-time maximum temperature exceeded 20°C was identified as the most effective way to record low-frequency wanderers and thus add further species. [ABSTRACT FROM AUTHOR]

A personal narrative is presented which explores the author's experience of recording Scarlet Tiger moths in their garden in the southeast of Cambridgeshire in England since March 31, 2021.

A standard Robinson-pattern light trap with a mercury vapour bulb was run alternately with or without amyl acetate for a year, recording a total of 6920 macromoths. Amyl acetate increased the number of individuals by 29% (total) or 18% (geometric mean/night). The same experiment was repeated using a Skinner trap with an actinic tube. We found that this effect was seasonal; no significant increase was found during the winter. We conclude that amyl acetate provides a simple and cost-effective way of increasing macromoth catches during much of the year. [ABSTRACT FROM AUTHOR]

The article presents the discussion on light traps providing the most popular way of surveying and recording moths. Topics include having the disadvantage of requiring a mains electricity supply or a heavy and expensive generator or batteries being so difficult for using in remote locations; and traps need to be exchanged frequently between the locations and data accumulated over multiple nights to smooth out night-to-night variation due to factors such as the weather. .