Currently,direct braking-force measurement under dynamic conditions requires a considerable modification to the vehicles and has poor compatibility because there are many types of vehicles.Thus,in this paper,an indire...Currently,direct braking-force measurement under dynamic conditions requires a considerable modification to the vehicles and has poor compatibility because there are many types of vehicles.Thus,in this paper,an indirect measurement method of new-energy vehicles,braking force under dynamic braking conditions is proposed.The mechanical wheel and axle model at low/idling/high speeds is established using the piston-pressure formula,force transfer in the brake-wheel cylinder,relative movement between the wheel and the roller,among others.On this basis,the relationship between wheel braking force and roller-linear acceleration is further derived.Our method does not alter existing vehicle structures or sensor types.The standard sealing bolt is temporarily replaced with a hydraulic sensor for coefficient calibration.Afterward,the braking force can be indirectly calculated using the roller-linear velocity data.The method has characteristics of efficiency and high accuracy without refitting vehicles.展开更多
The identification of targets varies in different surge tests. A multi-color space threshold segmentation and self-learning k-nearest neighbor algorithm (k-NN) for equipment under test status identification was prop...The identification of targets varies in different surge tests. A multi-color space threshold segmentation and self-learning k-nearest neighbor algorithm (k-NN) for equipment under test status identification was proposed after using feature matching to identify equipment status had to train new patterns every time before testing. First, color space (L*a*b*, hue saturation lightness (HSL), hue saturation value (HSV)) to segment was selected according to the high luminance points ratio and white luminance points ratio of the image. Second, the unknown class sample Sr was classified by the k-NN algorithm with training set T~ according to the feature vector, which was formed from number ofpixels, eccentricity ratio, compact- ness ratio, and Euler's numbers. Last, while the classification confidence coefficient equaled k, made Sr as one sample ofpre-training set Tz'. The training set Tz increased to Tz+1 by Tz' if Tz' was saturated. In nine series of illuminant, indicator light, screen, and disturbances samples (a total of 21600 frames), the algorithm had a 98.65% identification accuracy, also selected five groups of samples to enlarge the training set from To to T5 by itself. Keywords multi-color space, k-nearest neighbor algorithm (k-NN), self-learning, surge test展开更多
文摘Currently,direct braking-force measurement under dynamic conditions requires a considerable modification to the vehicles and has poor compatibility because there are many types of vehicles.Thus,in this paper,an indirect measurement method of new-energy vehicles,braking force under dynamic braking conditions is proposed.The mechanical wheel and axle model at low/idling/high speeds is established using the piston-pressure formula,force transfer in the brake-wheel cylinder,relative movement between the wheel and the roller,among others.On this basis,the relationship between wheel braking force and roller-linear acceleration is further derived.Our method does not alter existing vehicle structures or sensor types.The standard sealing bolt is temporarily replaced with a hydraulic sensor for coefficient calibration.Afterward,the braking force can be indirectly calculated using the roller-linear velocity data.The method has characteristics of efficiency and high accuracy without refitting vehicles.
文摘The identification of targets varies in different surge tests. A multi-color space threshold segmentation and self-learning k-nearest neighbor algorithm (k-NN) for equipment under test status identification was proposed after using feature matching to identify equipment status had to train new patterns every time before testing. First, color space (L*a*b*, hue saturation lightness (HSL), hue saturation value (HSV)) to segment was selected according to the high luminance points ratio and white luminance points ratio of the image. Second, the unknown class sample Sr was classified by the k-NN algorithm with training set T~ according to the feature vector, which was formed from number ofpixels, eccentricity ratio, compact- ness ratio, and Euler's numbers. Last, while the classification confidence coefficient equaled k, made Sr as one sample ofpre-training set Tz'. The training set Tz increased to Tz+1 by Tz' if Tz' was saturated. In nine series of illuminant, indicator light, screen, and disturbances samples (a total of 21600 frames), the algorithm had a 98.65% identification accuracy, also selected five groups of samples to enlarge the training set from To to T5 by itself. Keywords multi-color space, k-nearest neighbor algorithm (k-NN), self-learning, surge test