Current Issue : October - December Volume : 2019 Issue Number : 4 Articles : 5 Articles
The probability-based filtering method has been extensively used for solving the simultaneous localization and mapping (SLAM)\nproblem.Generally, the standard filter utilizes the system model and prior stochastic information to approximate the posterior state.\nHowever, in the real-time situation, the noise statistics properties are relatively unknown, and the system is inaccurately modeled.\nThus the filter divergence might occur in the integration system. Moreover, the expected accuracy might be challenging to be\nreached due to the absence of the responsive time-varying of both the process and measurement noise statistic which naturally can\nenlarge the uncertainty in the continuous system. Consequently, the traditional strategy needs to be improved aiming to provide\nan ability to estimate those properties. In order to accomplish this issue, the new adaptive filter is proposed in this paper, termed\nas an adaptive smooth variable structure filter (ASVSF). Sequentially, the improved SVSF is derived and implemented; the process\nand measurement noise statistics are estimated by utilizing the maximum a posteriori (MAP) creation and the weighted exponent\nconcept, and the covariance correction step is added based on the divergence suppression concept. In this paper the ASVSF is applied\nto overcome the SLAM problem of an autonomous mobile robot; henceforth it is abbreviated as an ASVSF-SLAM algorithm. It is\nsimulated and compared to the classical algorithm. The simulation results demonstrated that the proposed algorithm has better\nperformance, stability, and effectiveness....
Quality inspection is the necessary procedure before bearings leaving manufacturing factories. A testing machine with low\nshaft speed and light radial load condition is generally used to test the dynamic quality of bearings, which avoids creating any\npotential damages to testing bearings. However, the signal of defective bearings is easily polluted by very weak noise using the\ntraditional vibration-based measurement method due to the low shaft speed and light radial load condition specified for\nnondestructive inspection, which needs complicated and time-consuming calculation and is not suitable for online inspection.\nThus, there are problems about special operating conditions and weak fault severity in quality inspection of bearings, which is\nquite different from the fault diagnosis of bearings. In this paper, a novel dynamic quality evaluation technique is proposed\nbased on the measurement of Hertz deformations. The measurement system is mainly composed of an eddy current sensor,\nsensor fixture, and data acquisition platform with less transfer path than the vibration-based measurement system. The sensor\nfixture is optimized through numerical simulations to obtain signals with a high signal-to-noise ratio. Accurate evaluation of\ndynamic quality can be implemented reliably with simple signal processing. )e proposed method can be used with a rotating\nspeed of 100 rev/min and test load of 100 N, which is remarkably lower than the traditional quality inspection machineries with\na rotating speed of around 1000 rev/min and the test load of 400 N. Both simulation and experiment studies have verified the\nproposed method....
In this paper, we propose a novel prediction algorithm based on an improved Elman neural network (NN) ensemble for quality\nprediction, thus achieving the quality control of designed products at the product design stage. First, the Elman NNparameters are\noptimized using the grasshopper optimization (GRO) method, and then the weighted averagemethod is improved to combine the\noutputs of the individual NNs, where the weights are determined by the training errors. Simulationswere conducted to compare the\nproposed method with other NNmethods and evaluate its performance.The results demonstrated that the proposed algorithm for\nquality prediction obtained better accuracy than other NN methods. In this paper, we propose a novel Elman NN ensemble model\nfor quality prediction during product design. Elman NN is combined with GRO to yield an optimized Elman network ensemble\nmodel with high generalization ability and prediction accuracy....
For statistical evaluations that involve within-group and between-group variance\ncomponents................................
In this paper, a novel three-dimensional environmental quality dynamic system is introduced. Bayesian estimation was used to\ncalibrate environmental quality variables, and Genetic algorithm (GA) optimized Levenberg-Marquardt Back Propagation (LMBP)\nneural network method was used to effectively identify the system parameters for calibration of various variables and official\ndata.The studies found that the effect of increasing investment in environmental protection on energy intensity and environmental\nquality is not obvious, and it also aggravates the economic instability. Adjustment of peak parameters of pollution emissions can\naccelerate the evolution of energy intensity and environmental quality to a stable speed and eventually stabilize with a certain value.\nBut if the peak value of pollution emissions reaches too early, it will pose a certain threat to the environment. Although the speed\nof ecological environment self-repair is increased, it cannot effectively reduce energy intensity, improve environmental quality, and\nmaintain economic growth; it can control the stability of the control system or effectively control pollution.Therefore, in order to\nimprove the environmental quality, we need to take more measures in parallel, use more means and resources for environmental\ngovernance, and ultimately achieve â??win-winâ? between environmental quality and economy....
Loading....