Utilizing cumulative correlation information already existing in an evolutionary process, this paper proposes a predictive approach to the reproduction mechanism of new individuals for differential evolution (DE) algorithms. DE uses a distributed model (DM) to generate new individuals, which is relatively explorative, whilst evolution strategy (ES) uses a centralized model (CM) to generate offspring, which through adaptation retains a convergence momentum. This paper adopts a key feature in the CM of a covariance matrix adaptation ES, the cumulatively learned evolution path (EP), to formulate a new evolutionary algorithm (EA) framework, termed DEEP, standing for DE with an EP. Without mechanistically combining two CM and DM based algorithms together, the DEEP framework offers advantages of both a DM and a CM and hence substantially enhances performance. Under this architecture, a self-adaptation mechanism can be built inherently in a DEEP algorithm, easing the task of predetermining algorithm control parameters. Two DEEP variants are developed and illustrated in the paper. Experiments on the CEC'13 test suites and two practical problems demonstrate that the DEEP algorithms offer promising results, compared with the original DEs and other relevant state-of-the-art EAs.
Pure ZnO hexagonal microwires and Fe(Ⅲ)-doped ZnO microwires (MWs) with a novel rectangular cross section were synthesized in a confined chamber by a convenient one-step thermal evaporation method. An oriented attachment mechanism is consistent with a vapor-solid growth process. Photoluminescence (PL) and Raman spectroscopy of the Fe(Ⅲ)-doped ZnO MWs and in situ spectral mappings indicate a quasi-periodic distribution of Fe(Ⅲ) along a one-dimensional (1-D) superlattice ZnO:ZnFe 2 O 4 wire, while PL mapping shows the presence of optical multicavities and related multimodes. The PL spectra at room temperature show weak near-edge doublets (376 nm and 383 nm) and a broad band (450-650 nm) composed of strong discrete lines, due to a 1-D photonic crystal structure. Such a 1-D coupled optical cavity material may find many applications in future photonic and spintronic devices.
In order to effectively solve the problem of installation cost of automobile electric windows and the safety of passengers, the window regulator of the car must have an intelligent control function. For example, most automobile windows now have an anti-pinch function. In this paper, the model of DC brushed motor is analyzed, an intelligent control scheme for automotive power windows is proposed, and the relationship between current ripple and window travel, motor current and external resistance are verified. In the hardware design, S9S12G128 is the main control chip, and the motor current acquisition method is designed. In the software design, intelligent control methods such as current integration method, adaptive and self-learning algorithm and intelligent speed regulation method are proposed to realize functions such as automatic window opening and closing, intelligent anti-pinch and intelligent speed regulation. After many experiments, the results prove the feasibility of the above methods and the stability of the system.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.