30results about How to "Improve grading accuracy" patented technology

The invention discloses a method and a device for computer visual inspection classification of the quality of fresh corn ears, which aim to solve the problem that an artificial classification method makes the accuracy and the reproducibility of classification generated adverse effects. The method comprises the following steps of: 1, under a certain illumination condition, acquiring images of the fresh corn ears passing through a place right below a camera by an image acquisition device, and transmitting the images to a main control computer; 2, according to the acquired images of the fresh corn ears, performing image analysis by the main control computer through intelligent analysis software through the steps of: partitioning backgrounds of the images of the fresh corn ears by adopting aniteration-replacement method, and then extracting characteristics as quality indexes of the fresh corn ears on the basis of the images obtained after the background partitioning of the images of the fresh corn ears; and 3, on the basis of the quality indexes, which are acquired through the image analysis, of the fresh corn ears, and according to a grading standard that the fresh corn ears are classified into three grades, performing grade estimation on the fresh corn ears by using a fuzzy neural network. The invention also provides a detection device for implementing the method.

The invention relates to graded screening equipment for stone used in highway construction, in particular to a single-grade stone fine screening mechanism. According to a technical proposal provided by the invention, the upper part of a machine frame is provided with an inclined upper screen grader, an inclined lower screen grader is arranged on the machine frame under the upper screen grader, andthe discharging port of the upper screen grader is communicated with the feed port of the lower screen grader. The single-grade stone fine screening mechanism is characterized in that: both the inside of the upper screen grader and the inside of the lower screen grader comprise two layers of screen mesh; the position of the mesh upper outlet of each layer of the screen mesh is provided with a stone outlet; and the mesh lower outlets of the upper-layer screen meshes in the upper screen grader and the lower screen grader are the inlets of the lower-layer screen meshes. The graded screening equipment can finely grade the stone and improve the quality of constructed pavement.

The invention provides a coarse aggregate equivalent granularity grading method based on a three-dimensional image. The method comprises the following steps of obtaining coarse aggregate pictures through a CCD (Charge Coupled Device) camera, and carrying out a series of image processing operations (such as image filtering, image binarization, image filling, contour extraction and the like) on the coarse aggregate pictures to obtain coordinate points and thickness information of an outer contour of a particle; calculating equivalent granularity and various grain shape parameters (such as needle piece degree, flatness, three angles and sphericity degree) of the coarse aggregate according to the obtained thickness information and the outer contour coordinate points, and comparing by a characterization method of the thickness of the coarse aggregate; a new equivalent particle size characterization method being provided for coarse aggregates of different shapes, the difference error between an image method and a screening method being further corrected, and accurate grading being achieved. According to the coarse aggregate equivalent particle size grading method based on the three-dimensional image, accurate measurement of the coarse aggregate equivalent particle size is achieved, and grading precision of coarse aggregate particles is improved.

The invention discloses a method for synthesizing a standard-grade tobacco leaf image database based on digital image processing technology. The standard-grade tobacco leaf sample is photographed to obtain the tobacco leaf sample image, and then the image processing software is used to select a relatively representative area. The image preprocessing operation is to obtain a clear image of the tobacco leaf sample area, and the clear image of the tobacco leaf sample area is binarized to obtain a binary image, and the binary image is reversed to obtain a binary image template. The channel is used to extract color features, and the extracted tobacco leaf color feature values ​​are used to synthesize standard-grade tobacco leaf images to construct a tobacco leaf image database. The present invention utilizes digital image processing and image feature recognition technologies to construct a standard-grade tobacco leaf image database, which can realize the scientific classification of flue-cured tobacco leaves. Quantification greatly reduces the workload in the purchase of tobacco leaves, and the product classification accuracy is high.

The invention belongs to the technical field of asphalt pavement cold regeneration, and in particular relates to a method for grading cold recycled mixtures, the cold recycled mixtures comprising new aggregates, road milling materials, cement, mineral powder, emulsified asphalt and water; wherein In terms of parts by mass, the total parts of the new aggregate, road milling material, cement and mineral powder are 100 parts, the new aggregate is 0-50 parts, and the road milling material is 50-100 parts 1.5-2.5 parts of the cement, 2 parts of the mineral powder, 2.5-4.5 parts of the emulsified asphalt, and 3-5 parts of the water. The production method can not only improve the strength of the pavement, but also effectively improve the utilization rate of the old asphalt pavement and realize the green development of the road.

The present invention provides a method for grading coarse aggregates based on three-dimensional images. image filling and contour extraction, etc.) to obtain the coordinate points and thickness information of the outer contour of the particles; according to the obtained thickness information and outer contour coordinate points, the equivalent particle size and various particle shape parameters of the coarse aggregate (for example, the pin size) are calculated. , flatness, triangularity and sphericity), by comparing the characterization methods of coarse aggregate thickness; by proposing a new equivalent particle size characterization method for coarse aggregates of different shapes, and further modifying the image method and sieving method The difference between them generates errors to achieve accurate grading. The invention discloses a method for grading the equivalent particle size of coarse aggregate based on a three-dimensional image, which realizes the accurate measurement of the equivalent particle size of the coarse aggregate and improves the grading accuracy of the coarse aggregate particle.

The invention relates to a method for stirring a renewable asphalt mixture. The method comprises the following steps that a renewable recycled material is subjected to primary smashing in a cold state; the renewable recycled material enters a drying cylinder through a recycling ring for heating and softening with new aggregate; a renewable recycled asphalt mixture obtained by mixing the renewable recycled material with the new aggregate enters a continuous double-shaft stirring pan for stirring and rubbing; the renewable recycled material is subjected to secondary smashing; and the renewable recycled asphalt mixture flows out from the discharging hole of the continuous double-shaft stirring pan, enters the charging hole of an aggregate hoisting machine, and is fed into a vibration screen by the aggregate hoisting machine for screening. By the method, various types of aggregate are separated thoroughly after the renewable recycled material is treated; the heated mixture cannot be adhered to the screen mesh of the vibration screen when passing through the vibration screen; the graduation precision of the mixture is improved to a great extent; the method is low in cost and convenient to operate; and the addition ratio of the renewable recycled material is improved.

The invention discloses a method and system for grading defects in an X-ray weld image. The grading method includes: acquiring an image of an X-ray weld; determining the type and position of a defect in the X-ray weld image according to the X-ray weld image and size; determining the defect level of the X-ray weld image according to the type, position and size of the defect. The grading method in the present invention realizes the full automation of X-ray weld image defect detection and grading, avoids missed judgments and misjudgments caused by manual evaluation, and improves the grading accuracy.

The invention relates to the technical field of rock mass engineering, and provides a stage division method for large deformations of tunnel surrounding rock in a survey and design stage. Firstlylargedeformation grades of the surrounding rock are divided into n grades; then the maximum principal stress, lithology and rock mass integrity data, and active fault data of a tunnel site area are obtained; then the maximum principal stress and the lithology and rock mass integrity data of the tunnel site area are combined for performing an initial assessment, and the maximum principal stress and theactive fault data of the tunnel site area are combined for performing a second preliminary assessment to calculate the preliminary assessment grade of the surrounding rock large deformation in the tunnel site area; then groundwater situation data, the angle between the rock layer direction and the tunnel axis, and the inclination of the rock layer in the tunnel site area are obtained and combinedto calculate grade correction parameters to correct the preliminary assessment grade of the surrounding rock large deformations in the tunnel site area to obtain the surrounding rock large deformation correction level in the tunnel site area. According to the stage division method for the large deformations of the tunnel surrounding rock in the survey and design stage, the risk level of the large-scale deformation disaster of the surrounding rock in the survey and design stage can be evaluated, index selection is relatively comprehensive and easy to obtain, and thus the grade division accuracy is improved.