Ore visual image preselection testing machine

Abstract

The invention provides an ore visual image preselection testing machine, which is arranged on a workbench, comprises an image acquisition unit, an illumination unit, a variable-speed movement limiter, a material bearing bracket, an image acquisition bracket, a lifting mechanism and a driving motor, and belongs to the technical field of mineral processing. According to the invention, the image acquisition process during ore batch sorting in industrial production can be simulated in a laboratory, clear and accurate images of ore and gangue can be obtained, and equipment and technical support are provided for the laboratory to research an ore image color sorting technology and collect ore image samples.

Description

Technical Field

[0001] The invention relates to the technical field of image processing, and in particular to an ore visual image pre-selection testing machine. Background Art

[0002] Mineral resources are an important foundation for maintaining national economic and social development. With the large-scale development and utilization of mineral resources, the reserves of high-grade and easy-to-select mineral resources are decreasing. At present, my country's mineral resources have problems such as low ore grade, fine particle size of useful minerals, and complex ore composition. Therefore, the efficient development and utilization of low-grade and difficult-to-mine ores are becoming more and more urgent. Based on the principle of "more crushing and less grinding, and early throwing when possible", pre-selection can improve the grade of the selected ore, reduce the load of grinding and selection operations, save energy and reduce consumption, and improve resource utilization. It plays an important role in the development and utilization of low-grade, complex and difficult-to-select mineral resources. Common pre-selection methods in traditional mineral processing technology include: manual selection, heavy medium pre-selection, dry magnetic separation pre-selection, etc.

[0003] Since the beginning of the 21st century, cutting-edge technologies such as computers and artificial intelligence have developed rapidly. Intelligent photoelectric pre-selection technology has become a popular means of pre-selection and disposal of waste due to its high sorting efficiency and high accuracy. One of them is to use various optical signals to perform line scanning on bulk materials, and use sensors or a combination of different sensors to detect bulk materials particle by particle. According to the sensor detection results and data processing results, some particles that do not meet the requirements in composition are mechanically removed. The sorting technology mainly includes: image color sorting technology, XRT sorting technology, XRF sorting technology, etc. Among them, compared with other intelligent photoelectric pre-selection technologies, image color sorting technology is to perform line scanning on ore under natural light, artificial light source, polarized light source, infrared light source or ultraviolet light source, etc., to detect the differences in surface color, texture, gloss, shape, etc. between ore and waste rock, and realize the sorting of mine waste. It can distinguish mine waste without X-ray irradiation, and has the advantages of low cost and small equipment footprint. When there is a significant color difference between ore and waste rock, the use of image pre-selection technology is an economical and effective pre-selection method.

[0004] The image color sorter used in industry mainly consists of four parts: feeding system, image acquisition system, data processing system and sorting execution system. Among them, collecting clear ore sample images, conducting a comprehensive investigation of the color and texture characteristics of ore samples, and building a complete image acquisition system are the keys to achieving accurate and efficient sorting.

[0005] At present, there are many cases of research and application of image color sorting technology in the food industry, solid waste industry, non-metallic minerals and coal at home and abroad, but few suitable laboratory image acquisition platforms for metal ores have been established. Domestic and foreign laboratories often use ordinary high-definition cameras to acquire images under high-power electric lights or ordinary lighting. The images obtained often have problems such as ore color deviation, uneven illumination, and shadows in the image. A Canadian university once built a laboratory ore image acquisition system in the laboratory, including an industrial RGB camera with a 25mm lens. The lighting system uses three Panasonic EFT28E50 bulbs arranged in a triangle, and a polarized light filter is used to reduce light reflection on the ore surface, eventually forming a 32cm×24cm shooting area on the conveyor belt. A domestic laboratory used a belt ore image system to collect ore images, using a pair of 200W industrial LEDs as auxiliary light sources to form a surface illumination of more than 8000lux to ensure the clarity of the image, but there are still problems such as uneven illumination. In addition, factors such as the size of the color difference on the local surface of the ore, the camera's shooting method, the difference in light source, the resolution, and occlusion between ores will all affect the effect of image recognition.

[0006] With the continuous exploitation of mineral resources and the rapid development of society, the efficient development and utilization of low-grade and difficult-to-mine ores has become increasingly urgent. The selection of mature and efficient pre-selection and waste disposal technology is a prerequisite for the efficient, low-cost and green development of mineral resources. Compared with other pre-selection and waste disposal methods, image color sorting technology has the advantages of low working cost, high picking efficiency and small equipment footprint. It has a good pre-selection effect for ores with obvious differences in surface characteristics between ore and waste under visible light, polarized light, infrared light and ultraviolet light. However, under conditions similar to industrial production, collecting clear and qualified ore sample images, conducting a comprehensive investigation of the color and texture characteristics of the ore samples, and building a complete image processing and recognition method are the key to achieving accurate and efficient sorting. Summary of the invention

[0007] According to the technical problems mentioned in the above background technology, a laboratory ore visual image pre-selection test machine is provided, which innovatively adopts the high-speed line scanning stereo imaging system in the field of industrial automation detection as an image visual collector, and embeds image processing algorithms including flat field correction, flipping, white balance adjustment, etc., which can ensure the authenticity of the ore image while adjusting the image characteristics to highlight the difference between ore and waste; a high-power linear light source is used to provide sufficient and stable illumination for the acquisition environment, and the optional illumination types include visible light, infrared light, ultraviolet light and polarized light, etc., and a motion guide rail is set and a limit structure is used as the movement and positioning device of the ore, which can realize the simulation of the image acquisition process during the batch sorting operation of the industrial site, and solves the problems of color deviation, uneven illumination and shadow in the image pre-selection test machine in other laboratories. The whole system is installed on a metal workbench, and the camera configuration host is controlled by TKtool software, and the camera is controlled by IKapCViewer software to complete the work of taking pictures, collecting pictures and image processing. The obtained image can be used as the basic data for investigating the color characteristics of ore, building a mine waste classification model, and developing an image color sorter.

[0008] The technical means adopted by the present invention are as follows:

[0009] An ore visual image pre-selection test machine is arranged on a workbench, comprising: an image acquisition unit, a lighting unit, a variable speed movement limiter, a material carrying bracket, an image acquisition bracket, a lifting mechanism and a driving motor;

[0010] The ore sample to be tested is loaded into a sample box, and the sample box is set on the material carrying bracket; the material carrying bracket is set on the variable speed movable stopper, and the horizontal movement of the material carrying bracket is realized by the driving motor; the image acquisition unit is fixed above the variable speed movable stopper through the image acquisition bracket, and the ore sample to be tested under the image acquisition unit is scanned by lines, and the photographed photos are transmitted to the computer;

[0011] The lighting units are arranged in parallel on both sides below the image acquisition unit to realize the lighting of the ore to be tested; the lifting mechanism is used to install the lighting unit and adjust the angle and position of the lighting.

[0012] Furthermore, the size of the sample box matches the size of the material carrying bracket, so that when the material carrying bracket moves horizontally, the sample box will not deviate.

[0013] Furthermore, the speed-changing movement limiter is vertically arranged in the scanning direction of the image acquisition unit.

[0014] Furthermore, the image acquisition unit adopts a high-speed line scanning stereo imaging system.

[0015] Furthermore, the image acquisition unit is also provided with a dustproof sealing unit to prevent dust from entering.

[0016] Furthermore, the lighting unit is a high-power linear light source or a polarized light source or an infrared light source or an ultraviolet light source.

[0017] Furthermore, a water cooling machine pipeline is arranged inside the lighting unit; the water cooling machine pipeline is connected to the water cooling machine to realize cooling of the lighting unit.

[0018] Furthermore, the lifting mechanism includes two sets of screw lifts; the height to which the lighting unit is lifted or pushed is controlled by rotating a hand wheel on one side of the screw lift.

[0019] Compared with the prior art, the present invention has the following advantages:

[0020] (1) The system of the present invention is placed on a work platform and is suitable for small-scale image acquisition and analysis experiments in the laboratory. The overall size is controlled within 3m×1m×1.8m, leaving enough operating space for test personnel. Each unit is connected by a metal bracket and can be disassembled and assembled as needed. A pulley is installed at the bottom of the test machine to facilitate movement in the laboratory.

[0021] (2) The high-speed line scanning stereo imaging system in the test machine described in the present invention belongs to the field of computer information technology. It cooperates with a high-power linear light source and a variable speed movable limiter and is used for the first time in the collection and analysis of laboratory ore images, solving the problem of inconsistency between basic test and industrial production image collection methods. Compared with the existing image collection system, it simplifies the lighting unit equipment structure, establishes a laboratory line scanning image collection method, and effectively eliminates the shadow area of ​​the ore image, highlights the edge shape of the ore particles, and provides a variety of lighting environments for ore image collection. Different light sources can be set according to needs, and the image collection of multiple pieces of moving ores can be completed in the laboratory at the same time, realizing batch collection of ore images in the laboratory, simulating the image collection process during batch sorting operations on industrial sites;

[0022] (3) The high-speed linear array image sensor integrated in the image acquisition unit of the present invention has built-in flat field correction, white balance adjustment and other image processing algorithms, which are used for the first time in a small test machine in the laboratory to cooperate with TKtool and IKapCViewer software to optimize ore images, adjust ore image features in real time, and improve the clarity and contrast of ore and gangue;

[0023] (4) The characteristics of the obtained ore images are consistent with those of ore images in industry, and can be used to prepare the original data set of the ore image recognition model, determine the sorting strategy, and establish the sorting and recognition model of image color sorting, thus providing basic data for establishing ore and waste identification methods in industry and developing new image color sorting equipment.

[0024] In summary, the present invention can simulate the image acquisition process of ore batch sorting in industrial production in the laboratory, and obtain clear and accurate images of ore and gangue, providing equipment and technical support for the laboratory to study ore image color sorting technology and collect ore image samples. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0026] Figure 1 This is a front view of the ore visual image pre-selection testing machine of the present invention.

[0027] Figure 2 This is a side view of the ore visual image pre-selection testing machine of the present invention.

[0028] Figure 3 This is a top view of the ore visual image pre-selection testing machine of the present invention.

[0029] Figure 4 Schematic diagram of the sample box of the present invention.

[0030] Figure 5 It is a schematic diagram of the ore visual image pre-selection testing machine of the present invention.

[0031] Among them, 1 is an image acquisition unit; 2 is a lighting unit; 3 is a variable speed movement limiter; 4 is a material carrying bracket; 5 is an image acquisition bracket; 6 is a water cooling system; 7 is a lifting mechanism; 8 is a workbench; and 9 is a driving motor. DETAILED DESCRIPTION

[0032] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0033] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0034] like Figure 1-2 As shown, the present invention provides an ore visual image pre-selection testing machine, including: an image acquisition unit 1, a lighting unit 2, a speed-changing movement limiter 3, a material carrying bracket 4, an image acquisition bracket 5, a water-cooling machine pipeline 6, a lifting mechanism 7, a workbench 8 and a driving motor 9.

[0035] In the present application, as a preferred embodiment, first, a representative ore sample is placed in a special sample box and placed on a material carrying bracket 4; the material carrying bracket 4 is installed on a variable speed movable limiter 4, and the material carrying bracket 4 is driven by a driving motor to move horizontally, thereby driving the ore sample to pass under the image acquisition unit 1; the image acquisition unit 1 is fixed on the top of the testing machine by an image acquisition bracket 5, and takes pictures of the ore sample in a line scanning manner, and then transfers the pictures to the computer; the lighting unit 2 needs to be used in conjunction with a water cooler, located on both sides below the image acquisition unit 1, to provide stable, high-intensity lighting for the image acquisition process, while preventing external light from interfering with the image acquisition work; the lifting mechanism 7 is used to install the lighting unit 2 and adjust the angle and position of the lighting; the workbench 2 is made of metal material and provides a working platform for the entire system.

[0036] As a preferred embodiment, in the present application, the sample box and the material carrying bracket have corresponding sizes, and the sample box can be just fixed on the material carrying bracket to ensure that the sample box will not deviate when the material carrying bracket moves horizontally.

[0037] As a preferred embodiment, in the present application, the material carrying bracket 4 is installed on the speed-changing movable limiter 3 and driven by the driving motor 9; the speed-changing movable limiter 4 is installed perpendicular to the scanning direction of the image acquisition unit 1, so that the material moves horizontally and passes under the image acquisition unit.

[0038] In this application, the image acquisition unit 1 selects a high-speed line scanning stereo imaging system in the field of industrial automation detection, which integrates a high-speed linear array image sensor with a resolution of 8320×16 and a programmable logic gate array parallel processor, and is uniformly sampled and held by a global shutter control system; the acquired image is converted into a digital signal by an analog front end, and the data is output to the outside through a high-speed industrial Camera Link bus, and it has the characteristics of high speed, high sensitivity and low noise. The high-speed line scanning stereo imaging system is embedded with image processing algorithms including flat field correction, flipping, spatial correction, white balance adjustment, time delay integration, etc., which are implemented in real time in FPGA to ensure that the collected ore images are true and reliable. The high-speed linear array image sensor is provided with dustproof sealing measures to effectively prevent dust from entering the interior and affecting the working efficiency of the sensor.

[0039] Preferably, the lighting unit 2 uses a high-power linear light source. In addition to visible light, polarized light sources, infrared light sources, and ultraviolet light sources can also be installed according to the detection needs of the detector, the surface color and shape of the ore, and other characteristics. The entire unit is installed on the lifting mechanism on both sides below the image acquisition unit to provide stable and high-intensity lighting for the image acquisition process, avoid external light from interfering with the image acquisition work, and highlight the differences in surface characteristics of the mine waste. It is designed with a water-cooling pipe inside, which can be connected to a water cooler for cooling to avoid equipment damage due to overheating.

[0040] Preferably, the lifting mechanism 7 comprises: two sets of small screw lifts. By rotating the hand wheel on one side, the height of the lighting unit can be accurately controlled to be lifted or pushed forward, so as to facilitate the adjustment of the lighting position and angle.

[0041] As a preferred embodiment, the system also needs to be equipped with corresponding auxiliary equipment. The auxiliary equipment includes: a computer, a power supply device and sunglasses. Among them, the power supply device provides power for the entire system; the sunglasses are used to block the strong light emitted by the lighting unit to protect the eyes of the test personnel. The computer is equipped with a dual-series graphics card, and TKtool and IKapCViewer software are installed to complete the image acquisition, transmission and processing. Among them, the TKtool software remotely connects to the control camera configuration host through the local area network; IKapCViewer controls the test machine to collect images, adjusts the camera white balance, image contrast and other parameters, and strengthens the color difference between ore and waste rock. After that, the obtained ore image data can be annotated, grayscale read, and a data set can be made. Different mine-waste dividing lines can be set according to mineralogical characteristics, and a sorting and recognition model for image color sorting can be established. The waste rock throwing rate is evaluated, and a suitable sorting scheme is determined, which provides basic data for establishing a mine and waste identification method in industry and developing new image color sorting equipment.

[0042] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments. In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments. In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways.

[0043] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A ore visual image pre-selection test machine, arranged on a workbench (8), characterized in that: include: An image acquisition unit (1), an illumination unit (2), a speed-changing movement limiter (3), a material carrying bracket (4), an image acquisition support (5), a lifting mechanism (7), and a driving motor (9); The ore sample to be tested is placed in a sample box, and the sample box is arranged on the material carrying bracket (4); the material carrying bracket (4) is arranged on the speed-changing movable stopper (3), and the horizontal movement of the material carrying bracket (4) is realized by the driving motor (9); the image acquisition unit (1) is fixed above the speed-changing movable stopper (3) through the image acquisition bracket (5), and the ore sample to be tested located below the image acquisition unit (1) is scanned in a line scanning manner, and the photographed ore sample is transmitted to a computer; The lighting unit (2) is arranged in parallel on both sides below the image acquisition unit (1) to realize the lighting of the ore to be tested; the lifting mechanism (7) is used to install the lighting unit and adjust the lighting angle and position.

2. The ore visual image pre-selection test machine according to claim 1 is characterized in that: The size of the sample box matches the size of the material carrying bracket (4), so that when the material carrying bracket (4) moves horizontally, the sample box will not deviate.

3. The ore visual image pre-selection test machine according to claim 1 is characterized in that: The speed-changing movement limiter (3) is arranged vertically in the scanning direction of the image acquisition unit (1).

4. A ore visual image pre-selection test machine according to claim 1 or 3, characterized in that: The image acquisition unit (1) adopts a high-speed line scanning stereoscopic imaging system.

5. The ore visual image pre-selection test machine according to claim 1, 3 or 4, characterized in that: The image acquisition unit (1) is also provided with a dustproof sealing unit to prevent dust from entering.

6. The ore visual image pre-selection test machine according to claim 1, characterized in that: The lighting unit (2) is a high-power linear light source or a polarized light source or an infrared light source or an ultraviolet light source.

7. An ore visual image pre-selection test machine according to claim 1 or 6, characterized in that: A water cooling machine pipeline (6) is arranged inside the lighting unit (2); the water cooling machine pipeline (6) is connected to a water cooling machine to achieve cooling of the lighting unit (2).

8. The ore visual image pre-selection test machine according to claim 1 is characterized in that: The lifting mechanism (7) comprises two groups of screw lifts; the height to which the lighting unit is lifted or pushed is controlled by rotating a hand wheel on one side of the screw lift.

Images