WO2021155506A1 - 智能光电分选机及产品分离方法 - Google Patents

智能光电分选机及产品分离方法 Download PDF

Info

Publication number
WO2021155506A1
WO2021155506A1 PCT/CN2020/074327 CN2020074327W WO2021155506A1 WO 2021155506 A1 WO2021155506 A1 WO 2021155506A1 CN 2020074327 W CN2020074327 W CN 2020074327W WO 2021155506 A1 WO2021155506 A1 WO 2021155506A1
Authority
WO
WIPO (PCT)
Prior art keywords
sorted
product
products
ray
label
Prior art date
Application number
PCT/CN2020/074327
Other languages
English (en)
French (fr)
Inventor
李太友
梁兴国
葛小东
Original Assignee
天津美腾科技股份有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 天津美腾科技股份有限公司 filed Critical 天津美腾科技股份有限公司
Priority to AU2020427333A priority Critical patent/AU2020427333A1/en
Priority to CN202080097700.0A priority patent/CN115190825A/zh
Priority to PCT/CN2020/074327 priority patent/WO2021155506A1/zh
Publication of WO2021155506A1 publication Critical patent/WO2021155506A1/zh

Links

Images

Classifications

    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
    • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
    • B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
    • B07C5/34—Sorting according to other particular properties

Definitions

  • This application relates to the technical field of dry sorting, for example, to an intelligent photoelectric sorting machine and a product separation method.
  • Intelligent dry separation technology has been widely used in many fields such as coal, minerals, food, garbage, building materials, etc.
  • the separation method is divided into two processes: identification and separation.
  • the execution process is that the materials are laid flat on the moving distributor, and the recognition mechanism recognizes each piece of material by means of image, color, X-ray transmission, X-ray fluorescence, etc.
  • After the material identification is completed, either through sorting, or when the material is thrown from the end of the distributor, the falling trajectory of the material is changed by the impact of the elastic component or the instantaneous high-pressure air blowing, so as to realize the separation of the material.
  • the X-ray sorting machine is based on the transmission high-low dual-energy X-ray detection principle. Due to the use of continuous spectrum X-rays, the distinction between high-energy and low-energy is not clear enough, and the overlap effect is serious; and the thickness of the detected material is uneven. Although, based on the two dimensions of high-energy and low-energy information, the algorithm eliminates the influence of the difference in the thickness of some detected substances, but the detection error caused by the uneven thickness of the substance is still large, especially the substances with similar atomic numbers cannot be effectively identified.
  • This application provides an intelligent photoelectric sorting machine and a product separation method.
  • An intelligent photoelectric sorting machine including a belt transmission mechanism, a discriminating device, and a collecting mechanism; the belt driving mechanism is configured to convey a variety of products to be sorted; the discriminating device is configured to discriminate the plurality of products to be sorted And define the various products to be sorted with different labels; the collecting mechanism includes a plurality of collecting channels, and the number of the plurality of collecting channels is related to the number of the various products to be sorted. The number of product categories is the same, and each collection channel is electrically connected to the identification device, and is configured to identify the label corresponding to the collection channel, and control the products to be sorted corresponding to the label to enter the collection channel .
  • a product separation method of an intelligent photoelectric sorting machine includes the following steps:
  • the first label to the Nth label are defined for the N products to be sorted in descending order, where: N is greater than 1;
  • N collection channels are arranged corresponding to the first label to the Nth label in sequence
  • Controlling the collecting channel to transmit a signal to the solenoid valve according to the label corresponding to the collecting channel;
  • the air nozzle is controlled by the solenoid valve to blow the product to be sorted into the collecting channel.
  • Figure 1 is a schematic structural diagram of an intelligent photoelectric sorting machine provided by the present application.
  • Figure 2 is a flow chart of a sorting method for an intelligent photoelectric sorting machine provided by the present application.
  • the terms “installed”, “connected”, and “connected” should be understood in a broad sense.
  • it can be a fixed connection or a detachable connection; it can be a mechanical connection.
  • It can also be an electrical connection; it can be directly connected, or indirectly connected through an intermediate medium, and it can be the internal communication between two components.
  • the meaning of the above terms in this application can be understood according to the situation.
  • the present application provides an intelligent photoelectric sorting machine, including a belt transmission mechanism 4, a discrimination device, and a collection mechanism 9; the belt transmission mechanism 4 is configured to convey a variety of products to be sorted; and the discrimination device is configured as Identify a variety of products to be sorted and define a variety of products to be sorted with different labels.
  • the collection mechanism 9 includes multiple collection channels, the number of multiple collection channels and a variety of products to be sorted The number of categories is the same, and each collection channel is electrically connected to the identification device, and is set to identify the label corresponding to the collection channel, and control the products to be sorted with the corresponding label to enter the collection channel.
  • the number of the multiple collection channels is greater than or equal to the preset number of product categories.
  • the sorting machine further includes a leveling device 6, which is arranged below the belt drive mechanism 4, and the leveling device 6 drives the conveyor belt of the belt drive mechanism 4 to vibrate to make the products to be sorted It is laid flat on the conveyor belt to avoid accumulation of products to be sorted, resulting in inaccurate subsequent identification and sorting.
  • the tiling device 6 is a vibrator that can vibrate the conveyor belt. In other embodiments, it can also be other forms of vibration mechanism, as long as it can vibrate the conveyor belt so that the products to be sorted can be flattened. Just put it on the conveyor belt.
  • the cleaning mechanism 1 is arranged above the end of the belt drive mechanism 4 where the product falls.
  • the cleaning mechanism 1 includes a dust hood and a vacuum cleaner connected to the dust hood.
  • the vacuum cleaner can sort products through the dust hood. The generated dust is absorbed to prevent the generated dust from polluting the air.
  • the sorting machine further includes a feeding mechanism 5, which is arranged above the belt drive mechanism 4, and the products to be sorted that are conveyed slip to the belt drive mechanism 4 through the feeding mechanism 5.
  • the feeding mechanism 5 make the products to be sorted slip to the conveyor belt smoothly to avoid the adhesion/overlap of the products to be sorted on the conveyor belt, resulting in the subsequent failure of effective identification and sorting.
  • the feeding mechanism 5 in this embodiment is a vibrating feeder. In other embodiments, it may also be a chute or a sliding plate, etc., which is not too limited here.
  • the identification device includes an X-ray system 2 and/or an image identification system 3.
  • the discrimination device in this embodiment includes an X-ray system 2 and an image discrimination system 3.
  • the X-ray system 2 can distinguish the products to be sorted according to the photoelectric properties of the products to be sorted, and the image discrimination system 3 can distinguish the products to be sorted according to the The image nature of the product is used for image recognition of the products to be sorted.
  • the X-ray system 2 uses the pixel equivalent of the product's atomic number of the image collected by the product.
  • the X-ray system 2 includes an X-ray emitting mechanism 21, an X-ray fluorescence receiver 23 and an X-ray linear array detector 22.
  • the X-ray emitting mechanism 21 emits continuous energy.
  • Spectral X-rays transmitted by the products to be sorted are received by the X-ray linear array detector 22, reflected by the products to be sorted, and received by the X-ray fluorescence receiver 23.
  • the image discrimination system 3 obtains the image information of the products to be sorted.
  • the category information of the products to be sorted is obtained according to the voting weight mechanism to determine the category of the product, and multiple products are defined one by one with different tags, and the tags are transmitted To the aggregate channel.
  • the X-ray light source emits a continuous energy spectrum. After being transmitted by the products to be sorted, due to the different product densities, the X-ray continuous energy of the products to be sorted is calculated by the X-rays received by the X-ray linear array detector 22.
  • the discrimination device only includes the X-ray system 2, and the X-ray system 2 performs ray discrimination on the products to be sorted according to the photoelectric properties of the products to be sorted. And define a variety of products one by one with different labels, and transfer the labels to the aggregate channel.
  • the belt transmission mechanism 4 includes a driving member and a driving roller and a driven roller that are spaced and arranged side by side.
  • the conveyor belt is wound on the driving roller and the driven roller, and the driving roller and the driven roller are connected by the conveyor belt.
  • the output shaft of the driving part is in transmission connection with the driving roller, and the driving part can drive the driving roller to rotate through the belt, coupling or gear assembly transmission connection, so as to drive the conveyor belt to transport the products to be sorted.
  • the driving part is a motor, such as a servo motor with adjustable speed, a stepping motor, or a decelerating motor.
  • the driving part can control the speed of the conveyor belt, thereby controlling the conveying speed of the product, and avoiding the speed of two adjacent ones that are too fast. Interference occurs when a product falls.
  • the classification component includes an air nozzle 8, an air tank 7, and an air compressor.
  • the air nozzle 8 is arranged below and/or obliquely above the belt drive mechanism 4, and the setting position and the setting number are designed according to the actual needs of the site.
  • the air tank 7 is connected to the air nozzle 8 and can provide high-pressure gas to the air nozzle 8.
  • the air nozzle 8 is located at the end where the product falls.
  • the air nozzle 8 is provided with a solenoid valve which is electrically connected to the collecting channel. When products with the same label are transferred, the collecting channel controls the solenoid valve to control the air nozzle 8 to blow air, so that the products enter the corresponding collecting channel.
  • the air compressor is connected to the gas tank 7.
  • the air compressor can replenish the gas tank 7 with high-pressure gas.
  • a pressure sensor is arranged in the gas tank 7, and the detection value of the pressure sensor is used to determine whether to add high-pressure gas to the gas tank 7 .
  • the air nozzles 8 are provided in two rows, one row is a large nozzle, and the other row is a small nozzle.
  • the gas sprayed by the large nozzle is strong, and the product is sprayed at a longer distance.
  • the small nozzle sprays The intensity of the discharged gas is small, and the distance of the product spraying is second.
  • the product that is not sprayed has the smallest forward movement distance under the action of the inertia force of the belt drive mechanism 4.
  • the storage point is fixed, a specific type of product must be stored.
  • the proportions of multiple types of products in the products to be sorted are different in different batches of products, in order to save Energy and to reduce the error of sorting, generally the products with a larger proportion fall into the collecting channel close to the belt drive mechanism 4, and the products with the smallest proportion are sprayed into the aggregate channel farthest from the belt drive mechanism 4 , The product with the middle proportion is sprayed into the middle aggregate channel.
  • the products in each collecting channel are conveyed to the corresponding storage point by the conveying mechanism.
  • the product of the first label enters the collection channel close to the belt drive mechanism 4; the product of the second label enters the middle collection channel under the drive of the small nozzle, and the product of the third label enters the large collection channel. Driven by the No. nozzle, it enters into the collection channel farthest from the belt drive mechanism 4. In order to ensure that the first label has the largest proportion of products, the label with the largest proportion needs to be defined as the first label before sorting.
  • the identification device identifies the products to be sorted, and defines multiple labels one by one with different labels.
  • the collection channel is electrically connected to the identification device, which can identify the label corresponding to the collection channel, and control the air nozzle 8 on the classification component to blow the product of the corresponding label to the corresponding collection channel, by using different labels.
  • the definition of the product facilitates the identification of multiple products and allows the product to enter the corresponding aggregate channel and separate.
  • this embodiment also provides a product separation method for an intelligent photoelectric sorting machine, which is suitable for the above-mentioned intelligent photoelectric sorting machine, and includes the following steps:
  • the products to be sorted are sequentially defined as the first label, the second label to the Nth label.
  • the products to be sorted enter the identification device after passing through the tiling device 6.
  • the X-ray linear array detector 22 obtains the X-ray continuous energy spectrum equivalent energy attenuation rate of the product to be sorted, and judges the probability that the product to be sorted is the label defined above.
  • the image recognition system 3 obtains the image information of the product to be sorted, and judges the probability that the product to be sorted is the label defined above.
  • the X-ray fluorescence receiver 23 obtains the fluorescence spectrum information of the product to be sorted, and determines the probability that the product to be sorted is the label defined above.
  • S80 Determine which label the product is according to a preset threshold of probability corresponding to the product to be sorted.
  • the collecting channel transmits the signal to the sorting mechanism according to the label corresponding to this channel.
  • the sorting mechanism controls the solenoid valve so as to control the air nozzle 8 to spray the products to be sorted into the corresponding channels.
  • the product separation method of the intelligent photoelectric sorting machine includes: defining the first label to the Nth label for the N types of products in order of the preset N types of products in descending order of their respective proportions. , Where N is greater than 1; starting from the closest end to the belt transmission mechanism 4, N collection channels are set to correspond to the first label to the Nth label in sequence; control the products to be sorted to enter after passing through the tiling device 6 Identification device; control the X-ray linear array detector 22 to obtain the X-ray continuous energy spectrum equivalent energy attenuation rate of the products to be sorted, and obtain the to-be-sorted product according to the X-ray continuous energy spectrum equivalent energy attenuation rate The first probability that the product corresponding to the different label number is controlled; the X-ray fluorescence receiver 23 is controlled to obtain the fluorescence spectrum information of the product to be sorted, and the product to be sorted corresponds to the different product according to the fluorescence spectrum information.
  • the second probability of the label number of the control the image recognition system 3 to obtain the image information of the product to be sorted, and obtain the third probability of the product to be sorted corresponding to the different label number according to the image information;
  • the obtained probability of the same label number of the product to be sorted is weighted and summed to obtain the probability of the product to be sorted corresponding to each label number; according to the set probability preset threshold, it is determined that the product to be sorted
  • the label number corresponding to the sorted product; the determined label number is transmitted to the N collection channels, and compared with the label number corresponding to the N collection channels, it is determined that it corresponds to the product to be sorted
  • the collection channel; the collection channel is controlled to transmit the signal to the solenoid valve according to the label corresponding to the collection channel; the air nozzle 8 is controlled through the solenoid valve to blow the product to be sorted into the collection ⁇ Channel.
  • the parameter ⁇ is the equivalent energy attenuation rate of the X-ray continuous energy spectrum of the products to be sorted, and the calculation method of ⁇ is as follows:
  • ⁇ ( ⁇ 1/ ⁇ n) ⁇ [n/(1+2+...+n)]+ ⁇ 2/ ⁇ (n-1) ⁇ [(n-1)/(1+2+...+n )]+...+( ⁇ n/2)/( ⁇ n/2+1) ⁇ [(n/2+1)/(1+2+...+n)];
  • ⁇ 1 is the energy attenuation rate at 1Kev energy level after the radiation passes through the substance
  • ⁇ 2 is the energy attenuation rate after the radiation passes through the substance at the 2Kev energy level
  • ⁇ n is the energy attenuation rate after the radiation passes through the substance at the nKev energy level
  • n is the maximum energy level of the X-ray system, and n is an even number.
  • the high and low energy spectrum is used for transmission.
  • This method uses the transmission total energy spectrum detection algorithm to calculate the transmission X-rays of multiple energy levels.
  • the boundaries of multiple energy levels are clear, and the data dimensions are rich, which solves the continuous spectrum X-ray
  • the identified high and low energy boundary is not clear; through multi-dimensional data, the impact of the thickness difference of the tested product on the test result is effectively eliminated.
  • the products that account for more of the products to be sorted are not exactly the same each time, for example, in coal mine sorting, coal is selected and gangue is selected when the proportion of coal is more, and gangue is selected and discharged when gangue is more.
  • the types of products to be sorted have changed, and the products that account for more in each batch of products have changed. Therefore, it is necessary to define the product with the largest quantity as the first label to save The number of sprays during sorting.
  • X-ray equivalent energy attenuation rate of gangue-bearing coal and coal-bearing gangue is different from that of coal or gangue due to the different content of coal or gangue.
  • the gangue is relatively close, or even the same. In this case, the sorting will be misjudged.
  • this application uses an image recognition system and X-ray fluorescence to assist in the identification, and a voting mechanism is set up.
  • X-ray continuous photoelectron spectroscopy is the recognition of the atomic sequence of the product. Compared with the other two recognition methods, the accuracy is higher, so its voting proportion is relatively high.
  • the weight ratio is set to 0.7, and the weight ratio of the image recognition system is set to 0.2, set the weight ratio of X-ray fluorescence to 0.1.
  • the weight setting is not limited to the above values, and is adjusted according to the characteristics of different products to be selected in different fields.
  • the X-ray continuous energy spectrum, the image recognition system, and the X-ray fluorescence are individually compared and defined label probabilities according to the preset thresholds, and then the label probabilities obtained by each method are voted by weights, such as The probability of X-ray continuous energy spectrum judging that the product is the first label is 80%, and the probability of being the second label is 20%. The image recognition system judges that the product is the first label and the probability of the second label is 70%.
  • the probability of X-ray fluorescence judging that the product is the first label is 40%
  • the probability of the second label is 60%
  • the weight of the X-ray continuous energy spectrum is set to 0.7
  • the weight ratio of the image recognition system is set Set the weight ratio of X-ray fluorescence to 0.1.
  • the preset threshold is defined when the first label has more than 0.75 votes If it is judged to be the first label, the above-mentioned vote judges that the article is the second label, the preset threshold is defined according to the product characteristics, and the setting of the above threshold is set according to the product characteristics, and is not limited to the above setting; this application uses three types of identification The methods are identified separately, and the method of voting according to the weight is finally calculated and compared to obtain the product category.
  • This application uses X-ray recognition, image recognition system, X-ray fluorescence spectroscopy to assist discrimination, and adopts a voting weight mechanism. After the weights are added, the label with the largest proportion is identified as the product, which greatly improves the precision of sorting. Reduced the misclassification rate.

Abstract

公开了一种智能光电分选机及智能光电分选机的产品分离方法。智能光电分选机包括皮带传动机构（4）、辨别装置和集料机构（9）；皮带传动机构（4）设置为输送多种待分拣的产品；辨别装置设置为辨别多种待分拣的产品并以不同的标签编号一一定义多种待分拣的产品；集料机构（9）包括多个集料通道，每一集料通道与辨别装置电连接，设置为识别与集料通道对应的标签编号，并控制对应标签编号的待分拣的产品进入集料通道。

Description

智能光电分选机及产品分离方法 技术领域
本申请涉及干法分拣技术领域，例如涉及一种智能光电分选机及产品分离方法。
背景技术
智能干选技术已经广泛地应用于煤炭、矿物、食品、垃圾、建材等众多领域，分选方式分为识别和分选两种过程。执行过程为物料平铺在运动的布料器上，识别机构通过图像、颜色、X射线透射、X射线荧光等方式对每一块物料进行识别。在物料识别完成后，或通过分拣，或在物料从布料器尾端抛落的过程中通过弹力部件击打或者瞬时高压风喷吹改变物料的抛落轨迹，以此实现物料的分离。
相关技术中，智能干选往往只能对两种产品进行分选，对于多种产品由于识别机构无法在识别后有效定义，从而影响后续多种产品的分离。
另外，X射线分选机中基于透射高低双能X射线检测原理进行检测，由于采用了连续谱X射线，高能与低能的区分不够清晰、叠交影响严重；而且检测物质的厚度不均一。虽然，依据高能与低能两个维度信息，通过算法消除了部分检测物质厚度差异产生的影响，但物质厚度不均一导致的检测误差依然很大，尤其是原子序数相近物质无法有效识别。
发明内容
本申请提供一种智能光电分选机及产品分离方法。
一种智能光电分选机，包括皮带传动机构、辨别装置和集料机构；所述皮带传动机构设置为输送多种待分拣的产品；所述辨别装置设置为辨别所述多种待分拣的产品并以不同的标签一一定义所述多种待分拣的产品；所述集料机构包括多个集料通道，所述多个集料通道的数目与所述多种待分拣的产品的类别数目相同，每一集料通道与所述辨别装置电连接，设置为识别与所述集料通道对应的标签，并控制对应所述标签的待分拣的产品进入所述集料通道。
一种智能光电分选机的产品分离方法，包括如下步骤：
根据N种待分拣的产品分别在所述N种待分拣的产品中所占比例由多至少的顺序依次为所述N种待分拣的产品定义第一标签至第N标签，其中，N大于 1；
从距离皮带传动机构最近端开始，设置N个集料通道依次对应所述第一标签至所述第N标签；
控制待分拣的产品经过平铺装置后进入辨别装置；
控制X射线线阵探测器获得所述待分拣的产品的X射线连续能谱等效能量衰减率，根据所述X射线连续能谱等效能量衰减率获得所述待分拣的产品对应不同的标签的第一概率；
控制X射线荧光接收器获得所述待分拣的产品的荧光光谱信息，根据所述荧光光谱信息获得所述待分拣的产品对应所述不同的标签的第二概率；
控制图像辨别系统获得所述待分拣的产品的图像信息，根据所述图像信息获得所述待分拣的产品对应所述不同的标签的第三概率；
对获得的所述待分拣的产品的相同标签的概率进行权重加和，获得所述待分拣的产品对应每个标签的概率；
根据设定的概率预设阈值，判断所述待分拣的产品对应的标签；
将确定出的标签传送至所述N个集料通道，并与所述N个集料通道对应的标签比较，确定与所述待分拣的产品对应的集料通道；
控制所述集料通道根据与所述集料通道对应的标签将信号传送至电磁阀；
通过所述电磁阀控制空气喷嘴将所述待分拣的产品喷吹进入所述集料通道。
附图说明
图1是本申请提供的一种智能光电分选机的结构示意图；
图2是本申请提供的一种智能光电分选机分选方法的流程图。
图中：
1、清洁机构；2、X射线系统；21、X射线发出机构；22、X射线线阵探测器；23、X射线荧光接收器；3、图像辨别系统；4、皮带传动机构；5、送料机构；6、平铺装置；7、储气罐；8、空气喷嘴；9、集料机构。
具体实施方式
下面结合附图和实施方式说明本申请的技术方案。此处所描述的具体实施例仅仅用于解释本申请，而非对本申请的限定。为了便于描述，附图中仅示出 了与本申请相关的部分而非全部。
在本申请的描述中，除非另有规定和限定，术语“安装”、“相连”、“连接”应做广义理解，例如，可以是固定连接，也可以是可拆卸连接；可以是机械连接，也可以是电连接；可以是直接相连，也可以通过中间媒介间接相连，可以是两个元件内部的连通。可以根据情况理解上述术语在本申请中的含义。
如图1所示，本申请提供一种智能光电分选机，包括皮带传动机构4、辨别装置和集料机构9；皮带传动机构4设置为输送多种待分拣的产品；辨别装置设置为辨别多种待分拣的产品并以不同的标签一一定义多种待分拣的产品，集料机构9包括多个集料通道，多个集料通道的数目与多种待分拣的产品的类别数目相同，每一集料通道与辨别装置电连接，设置为识别与本集料通道对应的标签，并控制对应标签的待分拣的产品进入本集料通道。
一实施例中，多个集料通道的数目大于或等于预设的产品类别数目。
一实施例中，本分选机还包括平铺装置6，平铺装置6设置于皮带传动机构4的下方，平铺装置6驱使皮带传动机构4的输送带振动，以使待分拣的产品平铺于输送带上，避免待分拣的产品在堆积，导致后续辨别和分拣不精确。本实施例中，平铺装置6为振动器，能够使输送带振动，在其它实施例中也可以为其他形式的振动机构，只要是能够使输送带振动，以使待分拣的产品平铺于输送带上即可。
一实施例中，清洁机构1设置于皮带传动机构4的产品下落的一端的上方，清洁机构1包括吸尘罩和与吸尘罩相连的吸尘器，吸尘器通过吸尘罩可以将产品分拣过程中产生的粉尘吸附，避免产生的粉尘污染空气。
一实施例中，本分选机还包括送料机构5，送料机构5设置于皮带传动机构4的上方，被输送过来的待分拣的产品经送料机构5溜至皮带传动机构4上，送料机构5使待分拣的产品顺滑地溜至输送带上，避免待分拣的产品在输送带上黏连/重叠，导致后续不能进行有效辨别和分选。本实施例中的送料机构5为振动给料机，在其他实施例中还可以为溜槽或滑板等，在此不做过多限制。
一实施例中，辨别装置包括X射线系统2和/或图像辨别系统3。本实施例中辨别装置包括X射线系统2和图像辨别系统3，X射线系统2能够根据待分拣的产品的光电性质对待分拣的产品进行射线辨别，图像辨别系统3能够根据待分拣的产品的图像性质对待分拣的产品进行图像辨别。一实施例中，X射线系统2通过采集的产品的图片的像素等效产品的原子序数，当X射线穿透组织密度较低的物体时，X射线被吸收的量较少，剩余的较多，因此形成的图片较明亮，而当X射线穿透高密度物体时，X射线被吸收的量较多，剩余的较少， 故形成的图像较暗，最终会在荧屏上形成黑白对比和明暗差的图像单位体积内不同的原子序数代表不同的产品。
两个系统相配合能够更加精确地确认产品的类别，其中，X射线系统2包括X射线发出机构21、X射线荧光接收器23和X射线线阵探测器22，X射线发出机构21发出连续能谱的X射线经待分拣产品透射后由X射线线阵探测器22接收，经待分拣产品反射后由X射线荧光接收器23接收，图像辨别系统3获得待分拣产品的图像信息，并与上述的X射线光电子能谱和X射线荧光光谱按照投票权重机制获得待分拣的产品的类别信息，以判定产品的类别，并以不同的标签一一定义多种产品，并将标签传递至集料通道。一实施例中，X射线光源发出连续能谱，被待分拣产品透射后，由于产品密度不同，通过X射线线阵探测器22接收到的X射线计算获得待分拣产品的X射线连续能谱等效能量衰减率，并判断该产品是哪个标签的概率；X射线光源发出连续能谱，被待分拣产品反射后，激发出荧光光谱，被X射线荧光接收器23接收，并根据接收到的荧光光谱判断该产品是哪个标签的概率。
在其它实施例中，对辨别精度要求不高的场所，还可以是，辨别装置仅包括X射线系统2，X射线系统2根据待分拣的产品的光电性质对待分拣的产品进行射线辨别，并以不同的标签一一定义多种产品，并将标签传递至集料通道。
一实施例中，皮带传动机构4包括驱动件及间隔且并排设置的主动辊和从动辊，输送带绕于主动辊和从动辊上，主动辊和从动辊通过输送带连接。驱动件的输出轴与主动辊传动连接，可以通过皮带、联轴器或齿轮组件传动连接驱动件能够驱动主动辊转动，以带动输送带输送待分拣的产品。本实施例中驱动件为电机，例如为速度可调节的伺服电机、步进电机或减速电机等，驱动件可以控制输送带的转速，从而控制产品的输送速度，避免速度过快相邻的两个产品下落时产生干涉。
一实施例中，分类组件包括空气喷嘴8、储气罐7及空气压缩机，空气喷嘴8设置于皮带传动机构4下方和/或斜上方，设置位置及设置数量根据现场实际需要来进行设计。储气罐7连接于空气喷嘴8，能够为空气喷嘴8提供高压气体，空气喷嘴8位于产品下落的一端，空气喷嘴8上设置有电磁阀，电磁阀与集料通道电连接。当有相同标签的产品传输过来，集料通道控制电磁阀从而控制空气喷嘴8进行吹气，使得产品进入对应的集料通道内。空气压缩机连接于储气罐7，空气压缩机能够为储气罐7补充高压气体，在储气罐7内设置有压力传感器，根据压力传感器的检测值决定是否向储气罐7补充高压气体。本实施例中空气喷嘴8设置有两排，一排为大号喷嘴，一排为小号喷嘴，大号喷嘴喷出的气体的强度大，将产品喷吹的距离较远，小号喷嘴喷出的气体的强度小，将产 品喷出的距离次之，未被喷吹的产品在皮带传动机构4的惯性力的作用下，向前运动的距离最小。
一实施例中，由于存料点是固定的，必须存放特定类型的产品，然而待分拣的产品中的多个类型的产品所占的比例在不同的批次产品中是不同的，为了节省能源和减小分选的误差，一般占比例较大的产品落至靠近皮带传动机构4的集料通道内，占比最小的产品被喷吹至距离皮带传动机构4最远的集料通道内，占比中间的产品被喷吹至中间的集料通道内。每个集料通道内的产品由输送机构输送至对应的存料点。在本实施例中，第一标签的产品进入靠近皮带传动机构4的集料通道内；第二标签的产品在小号喷嘴的带动下进入中间的集料通道内，第三标签的产品在大号喷嘴的带动下进入距离皮带传动机构4最远的集料通道内。为了保证第一标签是产品占比最多的，需要在分拣之前将占比最多的定义为第一标签。
本申请所提供的智能光电分选机，其上的皮带传动机构4将待分拣的产品输送至辨别装置的下方时，辨别装置辨别待分拣的产品，并以不同的标签一一定义多种产品，集料通道与辨别装置电连接，能够识别与本集料通道对应的标签，并控制分类组件上的空气喷嘴8将对应标签的产品吹至对应的集料通道，通过采用不同的标签对产品进行定义，方便了多种产品的识别，并使得产品进入对应的集料通道分离。
如图2所示，本实施例还提供了一种智能光电分选机的产品分离方法，适用于如上所述的智能光电分选机，包括如下步骤：
S10、待分拣产品依次定义为第一标签、第二标签至第N标签。
S20、将集料通道由距离皮带传动机构4最近端按标签数量由多到少依次标记。
S30、待分拣产品经过平铺装置6后进入辨别装置。
S40、X射线线阵探测器22获得待分拣产品的X射线连续能谱等效能量衰减率，判断待分拣物品为上述定义的标签的概率。
S50、图像辨别系统3获得待分拣的产品的图像信息，判断待分拣物品为上述定义的标签的概率。
S60、X射线荧光接收器23获得待分拣产品的荧光光谱信息，判断待分拣物品为上述定义的标签的概率。
S70、将上述步骤S40-S60获得的相同标签的概率进行权重加和，获得每个标签的概率。
S80、根据设定待分拣的产品对应的概率预设阈值，判断该产品为第几标签。
S90、将确定出的标签信号传送至集料通道，并与集料通道标记的标签比较。
S100、集料通道根据与本通道对应的标签，并将信号传送至分拣机构。
S110、分拣机构控制电磁阀从而控制空气喷嘴8分别将待分拣产品喷吹进入相应通道。
一实施例中，智能光电分选机的产品分离方法包括：根据预设的N种类别产品分别对应的占比由多至少的顺序依次为所述N种类别产品定义第一标签至第N标签，其中，N大于1；从距离皮带传动机构4最近端开始，设置N个集料通道依次对应所述第一标签至所述第N标签；控制待分拣的产品经过平铺装置6后进入辨别装置；控制X射线线阵探测器22获得所述待分拣的产品的X射线连续能谱等效能量衰减率，根据所述X射线连续能谱等效能量衰减率获得所述待分拣的产品对应不同的标签编号的第一概率；控制X射线荧光接收器23获得所述待分拣的产品的荧光光谱信息，根据所述荧光光谱信息获得所述待分拣的产品对应所述不同的标签编号的第二概率；控制图像辨别系统3获得所述待分拣的产品的图像信息，根据所述图像信息获得所述待分拣的产品对应所述不同的标签编号的第三概率；对获得的所述待分拣的产品的相同标签编号的概率进行权重加和，获得所述待分拣的产品对应每个标签编号的概率；根据设定的概率预设阈值，判断所述待分拣的产品对应的标签编号；将确定出的标签编号传送至所述N个集料通道，并与所述N个集料通道对应的标签编号比较，确定与所述待分拣的产品对应的集料通道；控制所述集料通道根据与所述集料通道对应的标签将信号传送至电磁阀；通过所述电磁阀控制空气喷嘴8将所述待分拣产品喷吹进入所述集料通道。
可选地，参数μ为待分拣的产品的X射线连续能谱等效能量衰减率，μ的计算方法如下：
μ＝(μ1/μn)×[n/(1+2+...+n)]+μ2/μ(n-1)×[(n-1)/(1+2+...+n)]+...+(μn/2)/(μn/2+1)×[(n/2+1)/(1+2+...+n)]；
其中，μ1为1Kev能级处，射线透射物质后的能量衰减率；μ2为2Kev能级处，射线透射物质后的能量衰减率；μn为nKev能级处，射线透射物质后的能量衰减率；n为X射线系统的最大能级，n为偶数。
相关技术中是采用高低能谱进行透射，本方法采用透射全能谱检测算法，对多个能级的透射X射线均进行计算，多个能级分界清晰，数据维度丰富，解决了连续谱X射线识别的高低能界限不清晰问题；通过多维度数据，有效消除了检测产品厚度差异对检测结果产生的影响。
一实施例中，由于每次待分拣的产品中占比较多的产品不完全相同，比如在煤矿分选时，煤占比多就选煤排矸，当矸石占比多时就选矸排煤，对于粮食色选领域或者固体垃圾分选领域，待分拣产品的种类发生变化，每批次产品中占比较多的产品发生变化，因此需要将数量最多的产品定义为第一标签，以节约分选时喷吹的次数。
对于处于阈值附近的产品，往往会发生误判，尤其是在选煤领域，含矸的煤块和含煤的矸石的X射线等效能量衰减率因含煤或矸的含量不同会与煤或矸比较接近，甚至会相同，在这种情况下的分选就会发生误判，本申请为了避免这类情况的发生，采用图像识别系统和X射线荧光进行辅助辨别，并设置投票机制，由于X射线连续光电子能谱是对产品原子序列的识别，相对于其他两种识别方式精确度较高，因此其投票比重占比较高，设定权重比为0.7，设定图像识别系统的权重比为0.2，设定X射线荧光的权重比为0.1。权重的设定不局限于上述值，是根据不同领域不同待选产品的特性进行设定调整的。
一实施例中，X射线连续能谱、图像辨别系统、X射线荧光分别单独按照已有设定的阈值去比对并定义标签概率，然后将每种方式获得的标签概率通过权重进行投票，比如X射线连续能谱判断该产品为第一标签的概率为80％、为第二标签的概率为20％，图像辨别系统判断该产品为第一标签的概率为70％、为第二标签的概率为30％，X射线荧光判断该产品为第一标签的概率为40％、为第二标签的概率为60％，X射线连续能谱的权重设定为0.7，设定图像识别系统的权重比为0.2，设定X射线荧光的权重比为0.1，经过权重投票，第一标签得票为0.8*0.7+0.2*0.7+0.1*0.4＝0.74，第二标签得票为，0.7*0.2+0.2*0.3+0.1*0.6＝0.26，预设阈值定义当第一标签得票超过0.6时，判断为第一标签，则上述得票判断该物品为第一标签，如果预设阈值定义当第一标签得票超过0.75时，判断为第一标签，则上述得票判断该物品为第二标签，预设阈值根据产品特征定义，上述阈值的设定根据产品特性设置，并不局限于上述设定；本申请采用三种识别方式分别识别，根据权重投票的方式，最终计算并进行比对，得到产品的类别。
本申请采用X射线识别、图像辨别系统、X射线荧光光谱辅助辨别，并采用投票权重机制，经过权重加和后，占比最大的标签被认定为该产品，大大改善了分拣的精密度，降低了误分率。

Claims (11)

  1. 一种智能光电分选机，包括皮带传动机构(4)、辨别装置和集料机构(9)；
    所述皮带传动机构(4)设置为输送多种待分拣的产品；
    所述辨别装置设置为辨别所述多种待分拣的产品并以不同的标签编号一一定义所述多种待分拣的产品；
    所述集料机构(9)包括多个集料通道，每一集料通道与所述辨别装置电连接，设置为识别与所述集料通道对应的标签编号，并控制对应所述标签编号的待分拣的产品进入所述集料通道。
  2. 根据权利要求1所述的智能光电分选机，其中，所述多个集料通道的数目大于或等于预设的产品类别数目。
  3. 根据权利要求1所述的智能光电分选机，还包括平铺装置(6)，所述平铺装置(6)设置于所述皮带传动机构(4)的下方，所述平铺装置(6)设置为驱使所述皮带传动机构(4)的输送带振动，以使所述多种待分拣的产品平铺于所述输送带上。
  4. 根据权利要求1所述的智能光电分选机，还包括清洁机构(1)，所述清洁机构(1)设置于所述多种待分拣的产品下落的一端的上方，所述清洁机构(1)设置为除去所述多种待分拣的产品产生的灰尘。
  5. 根据权利要求1所述的智能光电分选机，还包括送料机构(5)，所述送料机构(5)设置于所述皮带传动机构(4)的上方，所述送料机构(5)设置为将所述多种待分拣的产品输送至所述皮带传动机构(4)上。
  6. 根据权利要求1所述的智能光电分选机，其中，所述辨别装置包括以下至少之一：X射线系统(2)、图像辨别系统(3)；
    所述X射线系统(2)设置为对所述多种待分拣的产品进行射线辨别；
    所述图像辨别系统(3)设置为对所述多种待分拣的产品进行图像辨别。
  7. 根据权利要求6所述的智能光电分选机，其中，所述X射线系统(2)包括X射线发出机构(21)、X射线荧光接收器(23)和X射线线阵探测器(22)；
    所述X射线发出机构(21)设置为发出连续能谱的X射线；
    所述X射线线阵探测器(22)设置为接收所述连续能谱的X射线经每种待分拣的产品透射后产生的X射线，并根据接收的X射线确定所述待分拣的产品对应所述不同的标签编号的第一概率；
    所述X射线荧光接收器(23)设置为接收所述连续能谱的X射线经每种待分拣的产品反射后产生的X荧光射线，并根据接收的X荧光射线确定所述待分 拣的产品对应所述不同的标签编号的第二概率；
    所述图像辨别系统(3)设置为获得每种待分拣的产品的图像信息，并根据所述图像信息确定所述待分拣的产品对应所述不同的标签编号的第三概率；
    所述辨别装置是设置为根据以下至少之一按照权重机制获得每种待分拣的产品对应的标签编号，并将所述标签编号传递至所述多个集料通道：
    所述第一概率和所述第二概率；
    所述第三概率；
    所述第一概率、所述第二概率和所述第三概率。
  8. 根据权利要求3所述的智能光电分选机，其中，所述皮带传动机构(4)包括驱动件、主动辊和从动辊，所述输送带呈环状，且分别套设于所述主动辊和所述从动辊外，所述主动辊通过所述输送带与所述从动辊连接，所述驱动件与所述主动辊传动连接。
  9. 根据权利要求1所述的智能光电分选机，还包括分类组件，所述分类组件设置为将每种待分拣的产品吹至所述待分拣的产品对应的集料通道内；
    所述分类组件包括空气喷嘴(8)、储气罐(7)和空气压缩机；
    所述空气喷嘴(8)设置于所述皮带传动机构(4)中所述多种待分拣的产品下落的一端，所述空气喷嘴(8)上设置有电磁阀，所述电磁阀与所述多个集料通道电连接；
    所述储气罐(7)设置为为所述空气喷嘴(8)提供高压气体；
    所述空气压缩机设置为为所述储气罐(7)补充高压气体。
  10. 一种智能光电分选机的产品分离方法，适用于如权利要求1-9任一项所述的智能光电分选机，包括：
    根据预设的N种类别产品分别对应的占比由多至少的顺序依次为所述N种类别产品定义第一标签至第N标签，其中，N大于1；
    从距离皮带传动机构(4)最近端开始，设置N个集料通道依次对应所述第一标签至所述第N标签；
    控制待分拣的产品经过平铺装置(6)后进入辨别装置；
    控制X射线线阵探测器(22)获得所述待分拣的产品的X射线连续能谱等效能量衰减率，根据所述X射线连续能谱等效能量衰减率获得所述待分拣的产品对应不同的标签编号的第一概率；
    控制X射线荧光接收器(23)获得所述待分拣的产品的荧光光谱信息，根 据所述荧光光谱信息获得所述待分拣的产品对应所述不同的标签编号的第二概率；
    控制图像辨别系统(3)获得所述待分拣的产品的图像信息，根据所述图像信息获得所述待分拣的产品对应所述不同的标签编号的第三概率；
    对获得的所述待分拣的产品的相同标签编号的概率进行权重加和，获得所述待分拣的产品对应每个标签编号的概率；
    根据设定的概率预设阈值，判断所述待分拣的产品对应的标签编号；
    将确定出的标签编号传送至所述N个集料通道，并与所述N个集料通道对应的标签编号比较，确定与所述待分拣的产品对应的集料通道；
    控制所述集料通道根据与所述集料通道对应的标签将信号传送至电磁阀；
    通过所述电磁阀控制空气喷嘴(8)将所述待分拣产品喷吹进入所述集料通道。
  11. 根据权利要求10所述的方法，其中，μ为所述X射线连续能谱等效能量衰减率，μ的计算方法如下：
    μ＝(μ1/μn)×[n/(1+2+...+n)]+μ2/μ(n-1)×[(n-1)/(1+2+...+n)]+...+(μn/2)/(μn/2+1)×[(n/2+1)/(1+2+...+n)]；
    其中，μ1为1Kev能级处，射线透射物质后的能量衰减率；μ2为2Kev能级处，射线透射物质后的能量衰减率；μn为nKev能级处，射线透射物质后的能量衰减率；n为X射线系统的最大能级，n为偶数。
PCT/CN2020/074327 2020-02-05 2020-02-05 智能光电分选机及产品分离方法 WO2021155506A1 (zh)

Priority Applications (3)

Application Number Priority Date Filing Date Title
AU2020427333A AU2020427333A1 (en) 2020-02-05 2020-02-05 Intelligent photoelectric sorting machine and product separation method thereof
CN202080097700.0A CN115190825A (zh) 2020-02-05 2020-02-05 智能光电分选机及产品分离方法
PCT/CN2020/074327 WO2021155506A1 (zh) 2020-02-05 2020-02-05 智能光电分选机及产品分离方法

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2020/074327 WO2021155506A1 (zh) 2020-02-05 2020-02-05 智能光电分选机及产品分离方法

Publications (1)

Publication Number Publication Date
WO2021155506A1 true WO2021155506A1 (zh) 2021-08-12

Family

ID=77199649

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/074327 WO2021155506A1 (zh) 2020-02-05 2020-02-05 智能光电分选机及产品分离方法

Country Status (3)

Country Link
CN (1) CN115190825A (zh)
AU (1) AU2020427333A1 (zh)
WO (1) WO2021155506A1 (zh)

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113926725A (zh) * 2021-10-26 2022-01-14 东北大学秦皇岛分校 基于密度估计的煤与矸石快速分选装置及方法
CN114405861A (zh) * 2021-12-31 2022-04-29 安徽中科光电色选机械有限公司 一种贝类物料分选装置
WO2022117106A1 (zh) * 2020-12-04 2022-06-09 湖州霍里思特智能科技有限公司 矿产分选机
WO2022117109A1 (zh) * 2020-12-04 2022-06-09 湖州霍里思特智能科技有限公司 矿产分选机和矿产分选方法
WO2023185417A1 (zh) * 2022-03-28 2023-10-05 同方威视技术股份有限公司 一种选矿装置

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN202411010U (zh) * 2012-01-06 2012-09-05 肇庆维胜环保资源科技有限公司 光电材质分选机
CN104923486A (zh) * 2015-07-06 2015-09-23 合肥美亚光电技术股份有限公司 一种履带式x光检测设备及物料分选装置
CN106040617A (zh) * 2016-05-29 2016-10-26 内蒙古科技大学 一种放射性矿石分选机
CN106733721A (zh) * 2017-02-16 2017-05-31 天津美腾科技有限公司 三产品智能干选机
CN207013301U (zh) * 2017-07-28 2018-02-16 合肥安杰特光电科技有限公司 一种基于输送定位机构的智能光电分选机
WO2018200866A1 (en) * 2017-04-26 2018-11-01 UHV Technologies, Inc. Material sorting using a vision system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN202411010U (zh) * 2012-01-06 2012-09-05 肇庆维胜环保资源科技有限公司 光电材质分选机
CN104923486A (zh) * 2015-07-06 2015-09-23 合肥美亚光电技术股份有限公司 一种履带式x光检测设备及物料分选装置
CN106040617A (zh) * 2016-05-29 2016-10-26 内蒙古科技大学 一种放射性矿石分选机
CN106733721A (zh) * 2017-02-16 2017-05-31 天津美腾科技有限公司 三产品智能干选机
WO2018200866A1 (en) * 2017-04-26 2018-11-01 UHV Technologies, Inc. Material sorting using a vision system
CN207013301U (zh) * 2017-07-28 2018-02-16 合肥安杰特光电科技有限公司 一种基于输送定位机构的智能光电分选机

Cited By (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2022117106A1 (zh) * 2020-12-04 2022-06-09 湖州霍里思特智能科技有限公司 矿产分选机
WO2022117109A1 (zh) * 2020-12-04 2022-06-09 湖州霍里思特智能科技有限公司 矿产分选机和矿产分选方法
CN113926725A (zh) * 2021-10-26 2022-01-14 东北大学秦皇岛分校 基于密度估计的煤与矸石快速分选装置及方法
CN114405861A (zh) * 2021-12-31 2022-04-29 安徽中科光电色选机械有限公司 一种贝类物料分选装置
WO2023185417A1 (zh) * 2022-03-28 2023-10-05 同方威视技术股份有限公司 一种选矿装置

Also Published As

Publication number Publication date
AU2020427333A1 (en) 2022-09-29
CN115190825A (zh) 2022-10-14

Similar Documents

Publication Publication Date Title
WO2021155506A1 (zh) 智能光电分选机及产品分离方法
CN104085667B (zh) 进料自动调节模块及其方法、装置、散料异物检测机构
US7351929B2 (en) Method of and apparatus for high speed, high quality, contaminant removal and color sorting of glass cullet
US10376926B2 (en) Inspection and sorting system
CN105722611B (zh) 用于分拣松散物料的设备和方法
CN114798488B (zh) 物料分选系统及分选方法
CN102781595A (zh) 用于从矿物中分拣杂质的设备及其方法
CN101632014B (zh) X射线检查装置和生产系统
CN110102501A (zh) 一种原始凭证自动分拣装置及方法
WO2016027813A1 (ja) 検査振分システム
WO2021161341A1 (en) System for modular multi-grade sorting and a method thereof
CN110125044A (zh) 一种基于双目视觉的苹果分选设备
CN114273257A (zh) 一种智能分选系统
US20230264230A1 (en) Efficient material recovery facility
EP0374792B1 (en) System for discriminating radiation-contaminated fragments and apparatus for measuring radioactivity of fragments
CN114602822A (zh) 矿物干选设备
JP2012516232A (ja) 段ばらしされた物体の経路を検出する、扁平物体の段ばらしするための装置
CN212576904U (zh) 一种用于煤炭的智能自动分选系统
CN108622642A (zh) 一种快递分拣系统及分拣方法
CN203922011U (zh) 进料自动调节装置及散料异物检测机构
WO2023185417A1 (zh) 一种选矿装置
CN212525014U (zh) 基于tdi与多能谱x射线检测技术改进的矿石分拣设备
CN115365166B (zh) 垃圾识别及分拣系统和分拣方法
CN216988689U (zh) 一种选矿装置
CN216728309U (zh) 一种处理能力倍增的分选机

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20917403

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2020427333

Country of ref document: AU

Date of ref document: 20200205

Kind code of ref document: A

122 Ep: pct application non-entry in european phase

Ref document number: 20917403

Country of ref document: EP

Kind code of ref document: A1