Fuel starvation during PEMFC (proton exchange membrane fuel cell) operations can produce serious irreversible damages. A large over-pressure, i.e., the differential pressure between anode and cathode, would damage proton like causing pinholes reducing performance of PEMFC. In order to ensure safe stable operation PEM cell, this paper proposes a flow modeling control approach for system under overpressure case. At first, Considering chemical reaction reactants volume relationship, model is...

Aiming at the control problem of dual-motor driving servo system with dead-zone nonlinearity,we proposed model linear part.We used describing function methods to analyze nonlinearity characteristic.The simulation experiments nonlinear were carried out.The results show that represents phenomenon zero deflection step response,error curve exists peak commutation time sine response.In end,we compensation strategy weaken impact on system.Finally illustrates effectiveness strategy.

Background: The binding of transcription factors (TFs) to TF-binding sites plays a vital role in the process regulating gene expression and evolution. With development machine learning deep learning, some successes have been achieved predicting sites. Then natural question arises: for given factor site, do they bind? This is main motivation this work. Results: In paper, we develop model BTFBS, which predicts whether bacterial combine or not. takes both amino acid sequences nucleotide as...

Large Language Models (LLMs) are proficient at retrieving single facts from extended contexts, yet they struggle with tasks requiring the simultaneous retrieval of multiple facts, especially during generation. This paper identifies a novel "lost-in-the-middle" phenomenon, where LLMs progressively lose track critical information throughout generation process, resulting in incomplete or inaccurate retrieval. To address this challenge, we introduce Find All Crucial Texts (FACT), an iterative...

The interior of a fuel cell is complex chemical reaction process. How to design an algorithm achieve energy optimization challenging problem. Due the nonlinearity system, it usually difficult obtain real-time global optimal control strategy directly. In this paper, near-optimal controller proposed for polymer electrolyte membrane (PEMFC) air supply system. goal maximize net output power PEMFC system by tracking desired oxygen excessive ratio. problem formulated as receding-horizon and...

A reader should identify tags quickly and accurately, so an anti-collision algorithm is important part in a RFID system. Q-Algorithm hot topic algorithms. In EPC Global Class-1 Gen-2, parameter Q adopted to adjust the frame sizes dynamically, ISO/IEC 18000-6 Type C, with C makes reduction of equipment loss by lessening adjustments Q, but it compromises system efficiency. this paper, Multidimensional Q-Selection Random Tree (MQRT) proposed. It hybrid method deterministic can lessen...

Reliable degradation prediction of the proton exchange membrane fuel cell (PEMFC) can provide sufficient decision support for its predictive maintenance. However, most methods only focus on point and do not consider uncertainty in prediction. In this paper, an optimized deep learning method with quantification is initially proposed PEMFC Specifically, based belief network (DBN) extreme machine (ELM) combined lower upper bound estimation to construct a novel model. It quantify through...

Aiming at the control of a class bounded disturbance uncertain nonlinear systems,we applied robust and backstepping control,introduced concept virtual quantity,chose Lyapunov function through stepwise recursion,offered adaptive law parameters estimate,designed an controller with state feedback in premise unknown systems, analyzed its stability. Compared conventional PID simulation results, designed has better robustness system parameter uncertainty disturbances, can ensure entire closed-loop...

Aiming at the control problem of dual-motor driving servo system with backlash nonlinearity, we proposed model linear part. We used describing function methods to analyze nonlinearity characteristic. The simulation experiments nonlinear were carried out. results show that represents residual self-oscillation step response, nonstationarity low speed tracking and error abrupt change produced by sinusoidal reversing. In end, compensation strategy weaken impact on system. Finally illustrates...

Entity-based semantic search has been widely adopted in modern engines to improve accuracy by understanding users' intent. In e-commerce, an accurate and complete product type (PT) ontology is essential for recognizing entities queries retrieving relevant products from catalog. However, finding types (PTs) construct such usually expensive due the considerable amount of human efforts it may involve. this work, we propose active learning framework that efficiently utilizes domain experts'...

Proton exchange membrane fuel cell (PEMFC) degradation prediction is essential, especially in the industrial power generation system, since it can provide decision supports for equipment maintenance. As phenomena inside PEMFC are strongly nonlinear and inter-coupled, accurate extremely challenging. Thus, a novel data-driven method based on adaptive variational mode decomposition (AVMD) deep belief network (DBN) proposed. Firstly, an improved AVMD employed to decomposes original voltage...