Molybdenum ore recognition algorithm, sorting method and sorting system

Abstract

The invention discloses a molybdenum ore recognition algorithm. The molybdenum ore recognition algorithm comprises the steps that a signal value of molybdenum ore to be sorted is obtained; the signal values are subjected to complex quadrature calculation processing, and data of the molybdenum ore to be sorted are obtained; and inputting the data of the to-be-sorted molybdenum ore into an ore sorting area model to obtain the category of the to-be-sorted molybdenum ore. According to the molybdenum ore recognition algorithm, sorting method and sorting system provided by the invention, the problems of low production efficiency, high cost and high labor intensity of workers when the molybdenum ore is sorted by adopting a manual sorting mode are solved, the automation of molybdenum ore sorting is realized, the production efficiency is greatly improved, and the production cost is reduced. The invention further discloses a sorting method and a sorting system based on the molybdenum ore recognition algorithm.

Description

Technical Field

[0001] The present invention relates to the technical field of ore sorting, and more specifically, to an identification algorithm, a sorting method, and a sorting system for molybdenum ore. Background Art

[0002] Molybdenum plays an important role in multiple fields and is widely used in many fields such as the shipbuilding, automotive, and electrical industries.

[0003] However, with the continuous mining of mines in recent years, the associated ores have increased, the subsequent refining cost has increased, and the economic benefits of the ores have decreased accordingly. Therefore, ore sorting before refining molybdenum ore and throwing out waste rocks is an important way to solve the above problems. In the prior art, manual selection is often used to sort molybdenum ore, which has defects such as low production efficiency, high cost, and high labor intensity of workers. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to provide an identification algorithm, a sorting method, and a sorting system for molybdenum ore to solve the problems existing in the prior art.

[0005] According to the first aspect of the present invention, an identification algorithm for molybdenum ore is provided, including:

[0006] Obtaining the signal value of the molybdenum ore to be sorted;

[0007] Performing complex multiplication calculation processing on the signal value to obtain the data of the molybdenum ore to be sorted;

[0008] Inputting the data of the molybdenum ore to be sorted into the ore sorting area model to obtain the category of the molybdenum ore to be sorted.

[0009] Preferably, the signal value of the molybdenum ore to be sorted includes:

[0010] High-energy x-ray signal value I H0 , low-energy x-ray signal value I L0 ;

[0011] X-ray high-energy transmission signal value I Hi of n pixel points, and x-ray low-energy transmission signal value I Li of n pixel points;

[0012] Wherein, the X-ray is used to irradiate and penetrate the molybdenum ore to be sorted.

[0013] Preferably, performing complex multiplication calculation processing on the signal value to obtain the data of the molybdenum ore to be sorted includes:

[0014] Calculating the average value I H, and the average value I of the low-energy X-ray signal value L , and calculate the R value of each piece of molybdenum ore to be sorted according to the composite quadrature algorithm.

[0015] Preferably, calculating the R value of each piece of molybdenum ore to be sorted according to the composite quadrature algorithm includes:

[0016] The transmission signal formula of the substance under the continuous spectrum is In the formula, E is the energy of the X-ray, N(E) is the relative number of photons of the X-ray at this energy, and P d (E) is the detection efficiency of the detector when the X-ray energy is E. The above parameters are all calculated from the fixed parameters of the light source and the detector. Therefore, after determining the light source and the detector, the above parameters are all determined. E in is the incident energy of the X-ray, -μ t (E) is the linear attenuation coefficient of a certain substance transmitted by the X-ray at this X-ray energy, t is the effective thickness of the X-ray penetrating the substance, and let Q(E)=N(E)P d (E)E, and the high-energy transmission signal value can be obtained as follows:

[0017]

[0018] The low-energy transmission signal value is:

[0019] Among them, E H is the high-energy value of the incident energy in the dual-energy X-ray system, and E L is the low-energy value of the incident energy;

[0020] Solve the composite quadrature formula for the X-ray high-energy transmission signal value and the X-ray low-energy transmission signal value: Let Divide the continuous-spectrum X-ray energy into n equal parts to obtain Formula 1: Among them, M is the n equal parts mentioned above, and M-1=n;

[0021] Use the composite Simpson's formula for each divided interval to obtain Formula 2:

[0022] Among them, h is the step size, m = M-1, and ε(f) is a value depending on the function f based on the mean value theorem;

[0023] Among them, the step size is h = E m+1 -E m , substitute Formula 2 into Formula 1 to obtain the composite Simpson's formula for the X-ray transmission signal: In the formula, Ψ m =μ t (E m )t,

[0024]

[0025] Since the models of the detector and the X-ray light source are both determined, the value of a is calculated through known parameters, and then Ψ is deduced by the detected high- and low-energy transmission signal values. m The value of Ψ is deduced by the detected high- and low-energy transmission signal values. m Through the average values I H and I L of the obtained high- and low-energy X-ray signal values, the attenuation coefficients Ψ H and Ψ L under high- and low-energy conditions are calculated, and then R of the ore can be obtained by using . Replace the traditional R value with R Ψ . Ψ Replace the traditional R value with R

[0026] Preferably, the data of the molybdenum ore to be sorted is input into the ore sorting area model, and the categories of the molybdenum ore to be sorted obtained include:

[0027] The average value I L of the low-energy X-ray signal value of each ore and the R value are obtained, and the data of each ore is input into the ore sorting area model, and the category of each ore is judged according to the specific area of the ore sorting area model where each ore falls.

[0028] Preferably, the construction method of the ore sorting area model includes:

[0029] The first sample ore model is trained through the molybdenum-containing ore data, and the second sample ore model is trained through the non-molybdenum-containing ore data;

[0030] Determine the threshold according to the first sample ore model and the second sample ore model;

[0031] Divide the coordinate system grid area according to the threshold, so as to obtain the ore sorting area model.

[0032] Preferably, the construction method of the ore sorting area model further includes:

[0033] Before training the first sample ore model and the second sample ore model, first collect the stepped sample signal values of the molybdenum-containing ore and the stepped sample signal values of the non-molybdenum-containing ore;

[0034] Perform complex integration on the stepped sample signal values of the molybdenum-containing ore and the stepped sample signal values of the non-molybdenum-containing ore to obtain the stepped sample data of the molybdenum-containing ore and the stepped sample data of the non-molybdenum-containing ore.

[0035] Preferably, after dividing the coordinate system grid area, the molybdenum-containing ore area and the non-molybdenum-containing ore area are determined.

[0036] According to a second aspect of the present invention, there is provided a molybdenum ore sorting method based on an identification algorithm of molybdenum ore, including:

[0037] Using the identification algorithm of the molybdenum ore to identify the molybdenum ore to be sorted;

[0038] Separating the molybdenum-rich ore from the molybdenum-poor ore according to the identification result.

[0039] According to a third aspect of the present invention, there is provided a molybdenum ore sorting system. The sorting method uses the molybdenum ore sorting system to sort molybdenum ore, and is characterized by including:

[0040] An identification unit for identifying the molybdenum ore to be sorted during transportation;

[0041] A separation unit, electrically connected to the identification unit, for receiving the separation instruction of the identification unit and separating the molybdenum-rich ore from the molybdenum-poor ore according to the separation instruction.

[0042] The identification algorithm, sorting method and sorting system of molybdenum ore provided by the present invention solve the problems of low production efficiency, high cost and high labor intensity of workers in sorting molybdenum ore by manual selection, realize the automation of molybdenum ore sorting, greatly improve the production efficiency and reduce the production cost. Brief Description of the Drawings

[0043] Through the following description of the embodiments of the present invention with reference to the drawings, the above and other objects, features and advantages of the present invention will become clearer.

[0044] Figure 1 is a flowchart of the steps of an identification algorithm of molybdenum ore provided by an exemplary embodiment of the present invention.

[0045] Figure 2 is a flowchart of the steps of a method for constructing an ore sorting area model provided by an exemplary embodiment of the present invention.

[0046] Figure 3 is a flowchart of the steps of a molybdenum ore sorting method based on an identification algorithm of molybdenum ore provided by an exemplary embodiment of the present invention.

[0047] Figure 4 is a schematic structural diagram of a molybdenum ore sorting system provided by an exemplary embodiment of the present invention.

[0048] In the figure: feeder 1, conveyor belt 2, X-ray source 3, linear array X-ray detector 4, linear array of high-speed pneumatic switching valves 5, control and identification device 6. Detailed Embodiments

[0049] Hereinafter, exemplary embodiments of the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all embodiments of the present invention. It should be understood that the present invention is not limited by the exemplary embodiments described herein.

[0050] It should be noted that: Unless otherwise specifically stated, the relative arrangements, numerical expressions, and numerical values of the components and steps set forth in these embodiments do not limit the scope of the present invention.

[0051] Those skilled in the art can understand that terms such as "first", "second", etc. in the embodiments of the present invention are only used to distinguish different steps, devices, or modules, etc., and neither represent any specific technical meaning nor indicate an inevitable logical order between them.

[0052] It should also be understood that in the embodiments of the present invention, "a plurality of" may refer to two or more, and "at least one" may refer to one, two, or more.

[0053] It should also be understood that for any component, data, or structure mentioned in the embodiments of the present invention, without clear definition or contrary indication in the context, it can generally be understood as one or more.

[0054] In addition, the term "and / or" in the present invention is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in the present invention generally represents an "or" relationship between the associated objects before and after.

[0055] It should also be understood that the present invention emphasizes the differences between the various embodiments, and their similarities or similarities can be referred to each other. For the sake of brevity, they will not be elaborated one by one.

[0056] At the same time, it should be understood that for the convenience of description, the dimensions of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0057] The following description of at least one exemplary embodiment is actually only illustrative and in no way restricts the present invention and its application or use.

[0058] Technologies, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and devices should be regarded as part of the specification.

[0059] It should be noted that: Similar reference numerals and letters denote similar items in the following drawings. Therefore, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0060] Embodiments of the present invention can be applied to electronic devices such as terminal devices, computer systems, servers, etc., which can operate together with many other general-purpose or special-purpose computing system environments or configurations. Examples of well-known terminal devices, computing systems, environments, and / or configurations suitable for use with electronic devices such as terminal devices, computer systems, servers, etc. include, but are not limited to: personal computer systems, server computer systems, thin clients, thick clients, handheld or laptop devices, microprocessor-based systems, set-top boxes, programmable consumer electronics, network personal computers, minicomputer systems, mainframe computer systems, and distributed cloud computing technology environments including any of the above systems, and so on.

[0061] Electronic devices such as terminal devices, computer systems, servers, etc. can be described in the general context of computer system-executable instructions (such as program modules) executed by a computer system. Generally, program modules can include routines, programs, target programs, components, logics, data structures, etc., which perform specific tasks or implement specific abstract data types. The computer system / server can be implemented in a distributed cloud computing environment, where tasks are executed by remote processing devices linked through a communication network. In a distributed cloud computing environment, program modules can be located on local or remote computing system storage media including storage devices.

[0062] As Figure 1 shown, the present invention discloses an identification algorithm for molybdenum ore, and the identification algorithm for molybdenum ore includes the following steps S01)-S03):

[0063] S01), obtaining the signal values of the molybdenum ore to be sorted;

[0064] Referring to Figure 4 , in this step, after the molybdenum ore to be sorted is spread on the conveyor belt by the feeder, the conveyor belt 2 conveys the ore to the X-ray detection device. The X-ray source 3 emits X-rays to penetrate the ore, and the penetrated X-rays are received by the linear array X-ray detector 4, converting the optical signal into an electrical signal and transmitting the signal to the control and identification device 6. The transmitted information includes the high-energy x-ray signal value I H0 , the low-energy x-ray signal value I L0 , the high-energy x-ray transmission signal values I of n pixel points Hi , and the low-energy x-ray transmission signal values I of n pixel points Li .

[0065] S02), performing complex multiplication calculation processing on the signal values to obtain the data of the molybdenum ore to be sorted;

[0066] In this step, calculate the average value I of the high-energy X-ray signal of each ore in the molybdenum ore to be sorted H , and the average value I of the low-energy X-ray signal L , and calculate the R value of each ore in the molybdenum ore to be sorted according to the composite quadrature algorithm.

[0067] According to the theoretical formula The R value of each molybdenum-containing ore can be calculated. However, this formula is applicable to monochromatic X-ray spectra. In the actual process, since the X-ray is a continuous spectrum, directly applying the theoretical formula to solve the R value is not accurate. Therefore, when calculating the R value, the composite quadrature algorithm is used to approximately solve the R value. The solution process is as follows:

[0068] Calculating the R value of each ore in the molybdenum ore to be sorted according to the composite quadrature algorithm includes:

[0069] The transmission signal formula of the substance under the continuous spectrum is where E is the energy of the X-ray, N(E) is the relative number of photons of the X-ray at this energy, and P d (E) is the detection efficiency of the detector when the X-ray energy is E. The above parameters can all be calculated from the fixed parameters of the light source and the detector. Therefore, after determining the light source and the detector, the above parameters are all determined. The above parameters are all calculated from the fixed parameters of the light source and the detector. Therefore, after determining the light source and the detector, the above parameters are all determined. E in is the incident energy of the X-ray, and -μ t (E) is the linear attenuation coefficient of the X-ray transmitted through a certain substance at this X-ray energy, which is related to the inherent properties of the substance and the energy of the X-ray. t is the effective thickness of the X-ray penetrating the substance. Let Q(E) = N(E)P d (E)E. Thus, the high-energy transmission signal value can be obtained as:

[0070]

[0071] The low-energy transmission signal value is:

[0072] where E H is the high-energy value of the incident energy in the dual-energy X-ray system, and E L is the low-energy value of the incident energy;

[0073] Solve the composite quadrature formula for the X-ray high-energy transmission signal value and the X-ray low-energy transmission signal value: Let Divide the continuous-spectrum X-ray energy into n equal parts to obtain Formula 1: where M is the n equal parts mentioned above, and M - 1 = n;

[0074] Use the composite Simpson's formula for each divided interval to obtain Formula 2:

[0075] Among them, h is the step size, m = M - 1, and ε(f) is a value dependent on the function f based on the mean value theorem;

[0076] Among them, the step size is h = E m+1 -E m , substituting Equation 2 into Equation 1, the composite Simpson's formula for the X-ray transmission signal is obtained: In the formula, Ψ m = μ t (E m )t,

[0077]

[0078] Since the models of the detector and the X-ray light source are both determined, the value of a m is calculated through known parameters, and then Ψ m is deduced inversely through the detected high-energy and low-energy transmission signal values. Through the average values I H and I L of the obtained high-energy and low-energy X-ray signal values, the attenuation coefficients Ψ H and Ψ L under high-energy and low-energy conditions are calculated, and then is used to calculate the R Ψ of the ore. Using R Ψ to replace the traditional R value.

[0079] S03) Input the data of the molybdenum ore to be sorted into the ore sorting area model to obtain the category of the molybdenum ore to be sorted.

[0080] In this step, the average value I L of the low-energy X-ray signal value of each ore and the R value are obtained, and the data of each ore are input into the ore sorting area model. The category of each ore is judged according to the specific area of the ore sorting area model where each ore falls.

[0081] In this embodiment, the ore sorting area model includes six areas, among which three areas are areas with high molybdenum content and three areas are areas with low molybdenum content. If the ore falls into the area with high molybdenum content, it is determined as concentrate; otherwise, it is determined as tailings.

[0082] As Figure 2 shown, the construction method of the ore sorting area model includes:

[0083] Step 1: Collect the stepped sample signal values of molybdenum-containing ores and the stepped sample signal values of molybdenum-free ores;

[0084] In this step, record the high-energy X-ray signal value I emitted by the X-ray H0 and the low-energy X-ray signal value I L0 . Select a large number of molybdenum-containing ores. The selected ores should contain full-size graded step samples. The linear array detector real-time collects the X-ray high-energy transmission signal values I of n pixel points of each molybdenum-containing ore Hi , as well as the X-ray low-energy transmission signal values I of n pixel points Li ; select a large number of molybdenum-free ores. The selected ores should contain full-size graded step samples. The array detector real-time collects the X-ray high-energy transmission signal values I' of n pixel points of each molybdenum-free ore Hi , the X-ray low-energy transmission signal values I' of n pixel points Li ;

[0085] Step 2: Perform composite quadrature on the step sample signal values of molybdenum-containing ores and the step sample signal values of molybdenum-free ores to obtain the step sample data of molybdenum-containing ores and the step sample data of molybdenum-free ores;

[0086] Calculate the average value I of the high-energy X-ray signal values of each molybdenum-containing ore H , as well as the average value I of the low-energy X-ray signal values L , and calculate the R value of each molybdenum-containing ore according to the composite quadrature algorithm; calculate the high- and low-energy signal average values I' J and I' L of each molybdenum-free ore, and calculate the R value of each molybdenum-free ore according to the composite quadrature algorithm;

[0087] Step 3: Train the first sample ore model through the molybdenum-containing ore data, and train the second sample ore model through the molybdenum-free ore data;

[0088] In this step, select the R value as the abscissa and the low-energy signal value as the ordinate, and perform normalization fitting on all the data points of the calculated molybdenum-containing ores to obtain the first sample ore model; perform normalization fitting on all the data points of the calculated molybdenum-free ores to obtain the second sample ore model; the normalization should select an appropriate function, and here y = ae bx is selected; combine the trained first sample ore model y1 = ae bx and the second sample ore model y2 = me nx in the coordinate system grid to obtain the fuzzy ore sorting region model.

[0089] Step 4: Determine the threshold based on the first sample ore model and the second sample ore model;

[0090] In this step, according to the characteristics of the first sample ore model and the second sample ore model in the coordinate system grid, a threshold value can be determined as the regional critical value for dividing the region.

[0091] Step Five: Divide the coordinate system grid into regions according to the threshold value, so as to obtain the ore sorting region model.

[0092] In this step, the regional critical value divides the coordinate system grid into regions to obtain the ore sorting region model. Specifically, for example, it is observed that only the curves of molybdenum-containing ores exist above the low energy value A, and only the curves without molybdenum exist below the low energy value B; in the region between A and B, only the curves of molybdenum-containing ores exist in the part less than the R value D, and only the curves without molybdenum exist in the part greater than the R value D; it is obtained that the determined threshold value includes two low energy values A, B and an R value D, where A > B, and the sorting region is divided into six regions: x > D, y > A; x < D, y > A; x > D, A > y > B; x < D, A > y > B; x > D, y < B; x < D, y < B.

[0093] The above division method is only for this embodiment. Due to different numbers and values of the threshold values, different numbers of regions may be divided. The number, value of the threshold value and the number of divided regions are not limited here.

[0094] Step Six: After dividing the coordinate system grid into regions, the regions containing molybdenum ore and the regions without molybdenum ore are determined.

[0095] The regional critical value divides the coordinate system grid into regions to obtain the ore sorting region model. Specifically, for example, it is observed that only the curves of molybdenum-containing ores exist above the low energy value A, and only the curves without molybdenum exist below the low energy value B; in the region between A and B, only the curves of molybdenum-containing ores exist in the part less than the R value D, and only the curves without molybdenum exist in the part greater than the R value D; it is obtained that the determined threshold value includes two low energy values A, B and an R value D, where A > B, and the sorting region is divided into six regions: x > D, y > A; x < D, y > A; x > D, A > y > B; x < D, A > y > B; x > D, y < B; x < D, y < B.

[0096] The above division method is only for this embodiment. Due to different numbers and values of the threshold values, different numbers of regions may be divided. The number, value of the threshold value and the number of divided regions are not limited here.

[0097] As Figure 3 shown, the present invention also discloses a molybdenum ore sorting method based on the recognition algorithm of molybdenum ore, and this method includes the following steps S1)-S2):

[0098] S1), Use the above recognition algorithm of molybdenum ore to identify the molybdenum ore to be sorted.

[0099] S2), separating molybdenum-rich ore from molybdenum-poor ore according to the recognition result.

[0100] As Figure 4 shown, the present invention also discloses a molybdenum ore sorting system, which includes:

[0101] A recognition unit for recognizing the molybdenum ore to be sorted during transportation;

[0102] A separation unit, electrically connected to the recognition unit, for receiving the separation instruction of the recognition unit and separating molybdenum-rich ore from molybdenum-poor ore according to the separation instruction.

[0103] Specifically, the recognition unit includes an X-ray detection device and a control and recognition device. The X-ray detection device is arranged on a conveyor for transporting the molybdenum ore to be sorted. The X-ray detection device includes a radiation source and a linear array X-ray detector. The control and recognition device is used to receive the data of the linear array X-ray detector, process the data, and send an action instruction to the separation unit.

[0104] The separation unit includes a conveyor and a linear array of high-speed pneumatic switching valves. The conveyor can specifically be a belt conveyor. A feeder is arranged at the front end of the conveying path of the conveyor, and a linear array of high-speed pneumatic switching valves is arranged at a preset distance from the conveying belt at the rear end of the conveying path of the conveyor. Both the feeder and the linear array of high-speed pneumatic switching valves are arranged on the support of the conveyor.

[0105] The feeder 1 is used to evenly disperse the molybdenum ore and vibrate the ore onto the belt. The molybdenum ore supplied by the feeder 1 can be the raw ore directly mined in the mine, or the roughly processed ore obtained by crushing and screening the raw ore mined in the mine. The roughly processed ore is obtained by screening the particle size on the basis of the raw ore, excluding the ore with too large or too small particle size, and obtaining the required optimal particle size ore. It can be understood that the specific form of the feeder 1 here obviously does not constitute a limitation on the specific protection scope of the present application.

[0106] The conveyor belt 2 is used to transport the molybdenum ore arranged by the feeder to a designated position. The position for loading the ore can be set as the initial position of the conveyor belt. The determination of the position for loading the ore is related to the specific design of the conveyor belt and the feeder. The conveyor belt must pass through the preset X-ray detection device and the linear array of high-speed pneumatic switching valves. In the overall device design concept, the X-ray detection device is used to collect data of the ore containing molybdenum elements and the ore without molybdenum elements in the raw ore, so as to realize the subsequent molybdenum ore treatment. The distance between the position for loading the ore and the X-ray detection device is the main factor affecting the size of the overall equipment. The more regular the shape of the ore, the simpler and more stable the movement state on the belt, the smaller the required distance between positions, and the more conducive to ore sorting.

[0107] An X-ray detection device is used to collect X-ray transmission signal data of molybdenum ore at a predetermined position and transmit the data to a control and recognition device 6. The X-ray detection device may include an X-ray source 3 and a linear array X-ray detector 4. The X-ray detection device transmits the collected data to the control and recognition device 6 for sorting molybdenum ore.

[0108] The high-speed pneumatic switch valve linear array 5 is used to execute the detection result of the control and recognition device 6 and blow the target molybdenum ore. The function of the high-speed pneumatic switch valve linear array 5 is to separate the identified molybdenum-rich ore from the molybdenum-poor ore.

[0109] The control and recognition device 6 specifically includes an industrial computer, an operating system, a sorting program for molybdenum ore, and various communication protocol serial ports. When the X-ray detection device collects and transmits the data of molybdenum ore to the industrial computer, the industrial computer runs the corresponding recognition program. After determining whether to execute, it sends an execution command to the material separation device to complete the sorting of a piece of molybdenum ore.

[0110] The control and recognition device obtains the position information of the raw ore on the conveyor belt 2 and determines the type of the ore. After judging whether separation is required, if separation is required, it transmits a signal to the high-speed pneumatic switch valve linear array 5 to control the high-speed pneumatic switch valve linear array 5 to perform a blowing operation. If not, it does not transmit a signal and deletes the ore data to achieve the separation of the required molybdenum-containing ore and waste rock.

[0111] The recognition algorithm, sorting method, and sorting system for molybdenum ore provided by the present invention solve the problems of low production efficiency, high cost, and high labor intensity of workers in sorting molybdenum ore by hand selection, realize the automation of molybdenum ore sorting, greatly improve the production efficiency, and reduce the production cost.

[0112] The basic principles of the present disclosure have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, advantages, effects, etc. mentioned in the present disclosure are only examples and not limitations, and it cannot be considered that these advantages, advantages, effects, etc. are essential for each embodiment of the present disclosure. In addition, the above-mentioned specific details are only for the purpose of illustration and easy understanding, and not for limitation. The above details do not limit the present disclosure to necessarily adopt the above specific details to implement.

[0113] Each embodiment in this specification is described in a progressive manner. The key point of each embodiment is to illustrate the differences from other embodiments. The same or similar parts among the embodiments can be referred to each other. For the system embodiment, since it basically corresponds to the method embodiment, the description is relatively simple, and the relevant parts can refer to the partial description of the method embodiment.

[0114] The block diagrams of the devices, apparatuses, equipment, and systems involved in the present disclosure are merely illustrative examples and are not intended to require or imply that they must be connected, arranged, and configured in the manner shown in the block diagrams. As those skilled in the art will recognize, these devices, apparatuses, equipment, and systems can be connected, arranged, and configured in any manner. Words such as "including", "comprising", "having", etc. are open-ended terms, meaning "including but not limited to", and can be used interchangeably with each other. The word "or" and "and" used herein refer to the phrase "and / or", and can be used interchangeably with it, unless the context clearly indicates otherwise. The word "such as" used herein refers to the phrase "such as but not limited to", and can be used interchangeably with it.

[0115] The methods and apparatuses of the present disclosure can be implemented in many ways. For example, the methods and apparatuses of the present disclosure can be implemented by software, hardware, firmware, or any combination of software, hardware, and firmware. The above order of the steps for the methods is for illustrative purposes only, and the steps of the methods of the present disclosure are not limited to the specific order described above, unless otherwise specifically stated. In addition, in some embodiments, the present disclosure can also be implemented as a program recorded on a recording medium, and these programs include machine-readable instructions for implementing the methods according to the present disclosure. Therefore, the present disclosure also covers the recording medium storing the programs for executing the methods according to the present disclosure.

[0116] It should also be noted that in the apparatuses, equipment, and methods of the present disclosure, each component or each step can be decomposed and / or recombined. These decompositions and / or recombinations should be regarded as equivalent solutions of the present disclosure. The above description of the disclosed aspects is provided to enable any person skilled in the art to make or use the present disclosure. Various modifications to these aspects are very obvious to those skilled in the art, and the general principles defined herein can be applied to other aspects without departing from the scope of the present disclosure. Therefore, the present disclosure is not intended to be limited to the aspects shown herein, but rather to the broadest scope consistent with the principles and novel features disclosed herein.

[0117] The above description has been given for purposes of illustration and description. In addition, this description is not intended to limit the embodiments of the present disclosure to the forms disclosed herein. Although multiple example aspects and embodiments have been discussed above, those skilled in the art will recognize certain variations, modifications, changes, additions, and sub-combinations thereof.

Claims

1. An identification algorithm for molybdenum ore, characterized in that, Including: Obtaining the signal value of the molybdenum ore to be sorted; Performing complex product calculation processing on the signal value to obtain the data of the molybdenum ore to be sorted; Inputting the data of the molybdenum ore to be sorted into the ore sorting area model to obtain the category of the molybdenum ore to be sorted.

2. The recognition algorithm of molybdenum ore according to claim 1, wherein The signal value of the molybdenum ore to be sorted includes: High-energy X-ray signal value I H0 , low-energy X-ray signal value I L0 ; The X-ray high-energy transmission signal value I of n pixel points Hi , and the X-ray low-energy transmission signal value I of n pixel points Li ; Wherein, the X-ray is used to irradiate and penetrate the molybdenum ore to be sorted.

3. The recognition algorithm of molybdenum ore according to claim 2, characterized in that, Performing complex product calculation processing on the signal value to obtain the data of the molybdenum ore to be sorted includes: Calculate the average value I of the high-energy X-ray signal of each piece of molybdenum ore to be sorted H , and the average value I of the low-energy X-ray signal L , and calculate the R value of each piece of molybdenum ore to be sorted according to the composite quadrature algorithm.

4. The recognition algorithm for molybdenum ore according to claim 3, characterized in that, Calculating the R value of each piece of ore in the molybdenum ore to be sorted according to the complex product algorithm includes: The transmission signal formula of the substance under the continuous spectrum is where E is the energy of the X-ray, N(E) is the relative number of photons of the X-ray at this energy, and P d (E) is the detection efficiency of the detector when the X-ray energy is E. The above parameters are all calculated from the fixed parameters of the light source and the detector. Therefore, after determining the light source and the detector, the above parameters are all determined. E in is the incident energy of the X-ray, and -μ t (E) is the linear attenuation coefficient of the X-ray transmitted through a certain substance at this X-ray energy, t is the effective thickness of the X-ray penetrating the substance. Let Q(E) = N(E)P d (E)E. Thus, the high-energy transmission signal value can be obtained as follows: The low-energy transmission signal value is: Among them, E H is the high energy value of the incident energy in the dual-energy X-ray system, and E L is the low energy value of the incident energy; Solve the complex integral formula for the X-ray high-energy transmission signal value and the X-ray low-energy transmission signal value: Let Divide the continuous-spectrum X-ray energy into n equal parts to obtain Formula 1: where M is the above-mentioned n equal parts, and M - 1 = n; Using the complex Simpson's formula for each divided interval to obtain Formula Two: Where h is the step size, m = M - 1, and ε(f) is a value that depends on the function f based on the mean value theorem; where the step size is h = E m+1 -E m , substituting Equation 2 into Equation 1, the composite Simpson's formula for the X-ray transmission signal is obtained: where Ψ m = μ t (E m )t, Since the models of the detector and the X-ray light source are both determined, the value of a is calculated through known parameters. Then, based on the detected high- and low-energy transmission signal values, Ψ is deduced inversely. m The average values I m and I H of the obtained high- and low-energy X-ray signal values are used to calculate the attenuation coefficients Ψ L and Ψ H under high- and low-energy conditions. Then, with L , the R of the ore can be obtained, and the traditional R value is replaced with R Ψ . Ψ ​ 5. The recognition algorithm for molybdenum ore according to claim 3, characterized in that, Inputting the data of the molybdenum ore to be sorted into the ore sorting area model to obtain the category of the molybdenum ore to be sorted includes: Obtain the average value I of the low-energy X-ray signal of each ore block L and the R value, and input the data of each ore block into the ore sorting area model described above. Determine the category of each ore block based on the specific area of the ore sorting area model into which each ore block falls.

6. The recognition algorithm for molybdenum ore according to claim 1, wherein The construction method of the ore sorting area model includes: Training a first sample ore model with molybdenum-containing ore data and training a second sample ore model with molybdenum-free ore data; Determining a threshold based on the first sample ore model and the second sample ore model; Dividing the coordinate system grid area according to the threshold to obtain the ore sorting area model.

7. The recognition algorithm for molybdenum ore according to claim 6, characterized in that, The construction method of the ore sorting area model further includes: Before training to obtain the first sample ore model and the second sample ore model, first collecting the stepped sample signal values of molybdenum-containing ore and the stepped sample signal values of molybdenum-free ore; Performing complex product integration on the stepped sample signal values of molybdenum-containing ore and the stepped sample signal values of molybdenum-free ore to obtain the stepped sample data of molybdenum-containing ore and the stepped sample data of molybdenum-free ore.

8. The recognition algorithm for molybdenum ore according to claim 6, wherein, After dividing the coordinate system grid area, the molybdenum-containing area and the molybdenum-free area are determined.

9. A molybdenum ore sorting method based on an identification algorithm of molybdenum ore, characterized in that, Including: Identifying the molybdenum ore to be sorted by using the molybdenum ore identification algorithm according to any one of claims 1-8; Separating the molybdenum-rich ore from the molybdenum-poor ore according to the identification result.

10. A molybdenum ore sorting system, the sorting method as described in claim 9 uses this molybdenum ore sorting system to sort molybdenum ore, characterized in that, Including: An identification unit for identifying the molybdenum ore to be sorted during transportation; A separation unit, electrically connected to the identification unit, for receiving the separation instruction of the identification unit and separating the molybdenum-rich ore from the molybdenum-poor ore according to the separation instruction.

Images