Copper-containing waste rock enrichment system based on photoelectric separation optimization parameters

Abstract

The invention discloses a copper-containing waste rock enrichment system based on photoelectric separation optimization parameters, which comprises a material conveying device comprising a vibration distributor, a feeding belt, a tailing belt and a concentrate belt which are arranged along the conveying direction; according to the airflow sorting device, a nozzle guide plate is arranged at the discharging end of the feeding belt, and the nozzle guide plate obliquely and upwards sprays high-pressure airflow from the bottom of the discharging end of the feeding belt; and the photoelectric separation controller is provided with an imaging analysis source, and the imaging analysis source can obtain the physical and chemical characteristics of the copper-containing waste rocks on the feeding belt. A sorting parameter optimization model is arranged in the photoelectric sorting controller, so that after an imaging analysis source obtains optical information of conveyed copper-containing waste rocks in real time, sorting parameters can be output in real time to dynamically adjust the vibration feeding frequency of a vibration distributing device and the speed of a feeding belt, a tailing belt and a concentrate belt; and the high-pressure air injection delay time of the nozzle guide plate and the opening duration of the spray valve are controlled, and the photoelectric sorting effect is improved.

Description

Technical Field

[0001] This invention relates to the field of ore sorting technology, specifically to a copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters. Background Technology

[0002] Copper-containing waste rock, as an important byproduct of mining production, has become a research hotspot in the mining industry due to its efficient utilization. Photoelectric sorting technology, as a highly efficient sorting technology based on mineral physical properties (such as color, shape, reflectivity, etc.), has advantages such as high sorting efficiency, good environmental performance, and high degree of intelligence, and shows great potential in the recycling of copper-containing waste rock resources.

[0003] However, existing photoelectric sorting technology still faces some technical bottlenecks when processing copper-containing waste rock. On the one hand, the setting of sorting parameters is somewhat subjective and not precise enough, resulting in insufficient stability and reliability of the sorting effect, making it difficult to meet the needs of industrial production. On the other hand, the sorting parameters for copper-containing waste rock of different grade ranges lack targeted optimization and fail to fully consider the matching relationship between raw material properties, equipment performance, and sorting processes, affecting the overall sorting efficiency and economy. Furthermore, during the transportation of copper-containing waste rock, sand and dust in the crushed copper-containing waste rock can cover or partially obscure the surface of the copper-containing waste rock, making it difficult for the photoelectric components to collect accurate physicochemical characteristics, thus affecting the analysis results and the effectiveness of photoelectric sorting.

[0004] In summary, existing photoelectric sorting technologies mainly rely on manual calculation and setting of sorting parameters, making it difficult to adjust them in real time according to the characteristics of copper-containing waste rock. Furthermore, the dust in the copper-containing waste rock can affect the optical information collection of the photoelectric sorting system, thus affecting the sorting effect. Summary of the Invention

[0005] The purpose of this invention is to provide a copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters, in order to solve the technical problems in the prior art where the sorting parameters are mainly set manually, making it difficult to adjust them in real time according to the characteristics of copper-containing waste rock, and the sand and dust in the copper-containing waste rock affect the optical information acquisition of the copper-containing waste rock by photoelectric sorting, thus affecting the sorting effect.

[0006] To solve the above-mentioned technical problems, the present invention specifically provides the following technical solution: A copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters includes: A material conveying device, comprising a vibrating distributor, a feeding belt, a tailings belt and a concentrate belt arranged sequentially along the conveying direction, wherein the vibrating distributor is located above the feed end of the feeding belt, and the tailings belt and the concentrate belt are located below the discharge end of the feeding belt and arranged sequentially, and can independently weigh the weight of copper-containing waste rock falling on them. An airflow separation device is provided with a nozzle guide plate at the discharge end of the feeding belt. The nozzle guide plate sprays high-pressure airflow at an angle from the bottom of the discharge end of the feeding belt to separate the copper-containing waste rock discharged from the discharge end of the feeding belt to the tailings belt and the concentrate belt. A photoelectric sorting controller, wherein an imaging analysis source is provided above the feeding belt, and the imaging analysis source is capable of acquiring the physicochemical properties of copper-containing waste rock on the feeding belt; The photoelectric sorting controller can output sorting parameters to control the vibrating feeder, the feeding belt, the tailings belt, the concentrate belt, and the nozzle guide plate. The sorting parameters include the vibrating feeding frequency, the belt speed, the high-pressure air injection delay time, and the spray valve opening time. Furthermore, the photoelectric sorting controller has a built-in sorting parameter optimization model, which can output the optimal sorting parameters based on the input physicochemical properties, so as to dynamically adjust the vibration feeding frequency of the vibrating feeder, the speed of the feeding belt, the tailings belt and the concentrate belt, as well as the high-pressure air injection delay time of the nozzle guide plate and the opening time of the spray valve in real time.

[0007] As a preferred embodiment of the present invention, the feeding belt is provided with a plurality of material troughs, which are equally spaced along the length of the feeding belt. The material troughs are used to collect copper-containing waste rock falling from the vibrating distributor for batch transportation.

[0008] As a preferred embodiment of the present invention, the surface of the feeding belt between two adjacent material troughs is raised upward to form an arc-shaped protrusion, the arc surface of the arc-shaped protrusion is smoothly connected to the trough wall, and the trough wall and bottom wall of the material trough are in the shape of a trumpet. A retaining edge is provided on the side of the feeding belt. The portion of the retaining edge covering the material trough slopes inward from top to bottom to form an inclined wall. The inclined wall smoothly connects with the trough wall and the bottom of the material trough.

[0009] As a preferred embodiment of the present invention, a plurality of drainage holes are provided at the bottom of the feeding belt, the plurality of drainage holes are arranged in an array along the length direction of the feeding belt, and the drainage holes penetrate and communicate with the corresponding material trough, so as to drain the dust in the copper-containing waste rock that is fed by the vibrating distributor in the material trough.

[0010] As a preferred embodiment of the present invention, a dust collection box is provided at the bottom of the feeding belt, the dust collection box is arranged on the material receiving side of the imaging analysis source, and multiple dust collection boxes are arranged along the length direction of the feeding belt. The dust collection box is provided with a dust collection port on the side near the feeding belt. The dust collection box is disposed against the feeding belt. The dust collection port covers a plurality of corresponding leakage holes to correspond to one of the material troughs. Furthermore, multiple dust collection boxes are connected in parallel via dust collection pipes to a dust collector to remove dust from the material trough.

[0011] In a preferred embodiment of the present invention, a fluff layer is provided on the side of the dust collection box near the feeding belt, the fluff layer is arranged around the edge of the dust collection port, and the dust collection box is attached to the bottom of the feeding belt through the fluff layer.

[0012] In a preferred embodiment of the present invention, a plurality of dust collection boxes are located between the conveying section and the return section of the feeding belt, and the plurality of dust collection boxes are respectively attached to the inner side of the conveying section and the return section of the feeding belt, and the plurality of dust collection boxes located in the return section of the feeding belt are distributed from the unloading end to the feeding end.

[0013] As a preferred embodiment of the present invention, a dustproof box is provided outside the feeding belt, and the conveying section of the feeding belt is exposed above the dustproof box. The bottom of the dustproof box is connected to a dust collector through a dust suction pipe.

[0014] As a preferred embodiment of the present invention, a partition is provided inside the dustproof box, and the partition is disposed between the two belt rollers of the feeding belt.

[0015] As a preferred embodiment of the present invention, the method for constructing the sorting parameter optimization model built into the photoelectric sorting controller includes: The photoelectric sensor of the imaging analysis source is used to obtain the physicochemical properties of copper-containing waste rock samples, and the sorting parameters and sorting indexes are obtained by multi-component sorting tests of copper-containing waste rock samples using the system. A neural network model is used to establish the mapping relationship between the physical properties, sorting parameters and sorting indicators, so as to obtain a sorting effect prediction model that predicts the sorting indicators based on the physical properties and sorting parameters. The sorting effect prediction model is transformed into an optimization objective. The optimization objective is solved using an optimization algorithm to obtain the optimal sorting parameters that enable the physical and chemical properties to reach the optimal sorting index. The optimal sorting parameters are then used to perform reinforcement learning on the sorting effect prediction model. A neural network model is used to establish the mapping relationship between the physical properties, sorting indicators and optimal sorting parameters, so as to obtain a sorting parameter optimization model that predicts the optimal sorting parameters based on the physical properties and sorting indicators. The optimal sorting parameters of the system are determined in real time by using a sorting parameter optimization model based on the physicochemical properties of the copper-containing waste rock to be sorted in real time and the sorting index that matches the preset sorting requirements.

[0016] Compared with the prior art, the present invention has the following advantages: This invention improves the photoelectric sorting effect by incorporating a sorting parameter optimization model into the photoelectric sorting controller. After the optical information of the copper-containing waste rock being transported is acquired in real time by the imaging analysis source, the sorting parameters can be output in real time to dynamically adjust the vibration feeding frequency of the vibrating feeder, the speed of the feeding belt, the tailings belt and the concentrate belt, as well as the high-pressure air injection delay time of the nozzle guide plate and the opening time of the spray valve.

[0017] Furthermore, by setting up a trough on the outside of the feeding belt and a dust collection box on the inside of the feeding belt, the sand and dust are concentrated in the trough and sucked away by the dust collection box. This not only standardizes the batch transportation of copper-containing waste rock, but also reduces the impact of sand and dust on photoelectric sorting, thereby improving the effect of photoelectric sorting. Attached Figure Description

[0018] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings in the following description are merely exemplary, and those skilled in the art can derive other embodiments based on the provided drawings without creative effort.

[0019] Figure 1 A schematic diagram of the structural composition of a copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters provided in an embodiment of the present invention; Figure 2 This is a schematic diagram of the material tank structure of the copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters provided in an embodiment of the present invention. Figure 3 A schematic diagram of the dustproof box structure of the copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters provided in an embodiment of the present invention; Figure 4 This invention provides a method for constructing a sorting parameter optimization model for a copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters, as provided in an embodiment of the invention.

[0020] The labels in the diagram represent the following: 1-Buffer hopper; 2-Vibrating discharge hopper; 3-Vibrating distributor; 4-Feeding belt; 5-Computer control system; 6-Imaging analysis source; 7-Dust collector; 8-Air compressor; 9-Air tank; 10-Refrigerated dryer; 11-Diverter filter; 12-Nozzle guide plate; 13-Tailings conveyor belt; 14-Concentrate conveyor belt; 15-Tailings conveyor belt scale; 16-Concentrate conveyor belt scale; 41-Trough; 42-Arc-shaped protrusion; 43-Side guard; 44-Leakage hole; 45-Dustproof box; 71-Dust collection box; 72-Dust collection port; 73-Fluff layer; 421 - Curved surface; 431 - Sloping wall; 451 - Partition. Detailed Implementation

[0021] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0022] like Figure 1 As shown, this invention provides a copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters, comprising: The material conveying device includes a vibrating distributor 3, a feeding belt 4, a tailings belt 13, and a concentrate belt 14 arranged sequentially along the conveying direction. The vibrating distributor 3 is located above the feed end of the feeding belt 4, and the tailings belt 13 and concentrate belt 14 are located below the discharge end of the feeding belt 4 and arranged sequentially. The vibrating distributor 3 is capable of independently weighing the weight of the copper-containing waste rock falling on it.

[0023] The vibrating feeder 3 is equipped with a buffer hopper 1 and a vibrating discharge hopper 2 in the material feeding direction, which are used to feed the vibrating feeder 3. The vibrating discharge hopper 2 puts the copper-containing waste rock from the silo into the vibrating feeder 3. The vibrating feeder 3 evenly distributes the copper-containing waste rock on the feeding belt 4. The feeding belt 4 transports the copper-containing waste rock to the discharge end and discharges it to the tailings belt 13 and the concentrate belt 14.

[0024] Furthermore, the tailings conveyor belt 13 and the concentrate conveyor belt 14 independently weigh the copper-containing waste rock falling on them using tailings conveyor belt scale 15 and concentrate conveyor belt scale 16, which are respectively installed on the tailings conveyor belt 13 and the concentrate conveyor belt 14. Weighing the material on the conveyor belt using belt scales is a conventional technique and will not be described in detail here.

[0025] The system also has an airflow separation device. The airflow separation device is equipped with a nozzle guide plate 12 at the discharge end of the feeding belt 4. The nozzle guide plate 12 sprays high-pressure airflow from the bottom of the discharge end of the feeding belt 4 upwards to separate the copper-containing waste rock discharged from the discharge end of the feeding belt 4 onto the tailings belt 13 and the concentrate belt 14.

[0026] The airflow sorting device also includes an air compressor 8, an air tank 9, a refrigerated dryer 10, and a diversion filter 11. The air compressor 8, air tank 9, refrigerated dryer 10, diversion filter 11, and nozzle guide plate 12 are connected in sequence through pipelines. The air compressor 8 compresses air into the air tank 9 to form high-pressure gas, and the gas is separated into water and air by the refrigerated dryer 10 and the diversion filter 11. The water in the gas is discharged and the dry high-pressure airflow is pumped into the nozzle guide plate 12. The nozzle guide plate 12 forms an inclined high-pressure air curtain at the bottom of the feed belt 4, which blows the falling copper-containing waste stone along the inclined surface of the nozzle guide plate 12 for sorting.

[0027] During this process, the waste rock products with a larger volume ratio fall freely into the tailings conveyor belt 13, while the concentrate products with a smaller volume ratio are separated from the larger waste rock products by high-pressure gas injection and fall freely into the concentrate conveyor belt 14. Both the tailings conveyor belt 13 and the concentrate conveyor belt 14 can weigh the waste rock that falls onto them.

[0028] The system also has a photoelectric sorting controller. The photoelectric sorting controller has an imaging analysis source 6 above the feeding belt 4. The imaging analysis source 6 can acquire the physicochemical properties of copper-containing waste rock on the feeding belt 4. The photoelectric sorting controller can control the vibrating feeder 3, the feeding belt 4, the tailings belt 13, the concentrate belt 14 and the nozzle guide plate 12 by outputting sorting parameters through the computer control system 5. The sorting parameters include the vibrating feeding frequency, belt speed, high-pressure air injection delay time and spray valve opening time. Furthermore, the computer control system 5 of the photoelectric sorting controller has a pre-built sorting parameter optimization model. The sorting parameter optimization model can output the optimal sorting parameters based on the input physical and chemical characteristics, so as to dynamically adjust the vibration feeding frequency of the vibrating feeder 3, the speed of the feeding belt 4, the tailings belt 13 and the concentrate belt 14, as well as the high-pressure air injection delay time of the nozzle guide plate 12 and the opening time of the spray valve in real time.

[0029] The computer control system 5 uses an imaging analysis source 6 to collect optical information about the copper-containing waste rock on the feeding belt 4 to obtain its physicochemical properties. These properties are then input into a built-in sorting parameter optimization model. The model outputs optimal sorting parameters, including the vibration feeding frequency of the vibrating feeder 3, the speeds of the feeding belt 4, tailings belt 13, and concentrate belt 14, as well as the high-pressure air injection delay time and valve opening duration of the nozzle guide plate 12. Therefore, by monitoring the physicochemical properties of the copper-containing waste rock on the feeding belt 4, the operating parameters of each device are adjusted in real time to separate the copper-containing waste rock and enrich the concentrate product.

[0030] The present invention aims to collect the copper-containing waste rock conveyed by the feed belt 4 through the imaging analysis source 6 of the photoelectric sorting controller, obtain the physicochemical properties of the copper-containing waste rock, and output the optimal sorting parameters through the built-in sorting parameter optimization model. In order to dynamically adjust the vibration feeding frequency of the vibrating feeder 3, the speed of the feed belt 4, the tailings belt 13 and the concentrate belt 14, as well as the high-pressure air injection delay time of the nozzle guide plate 12 and the opening time of the spray valve, the copper-containing waste rock conveyed is highly matched and sorted to achieve the enrichment of concentrate products.

[0031] Compared to traditional systems that manually set fixed parameters, this invention utilizes a photoelectric sorting controller to collect the physicochemical properties of the copper-containing waste rock in real time, thereby outputting optimal sorting parameters that match the physicochemical properties. These optimal sorting parameters control the vibration feeding frequency of the vibrating feeder 3, the speed of the feeding belt 4, the tailings belt 13, and the concentrate belt 14, as well as the high-pressure air injection delay time of the nozzle guide plate 12 and the opening duration of the spray valve, to achieve dynamic control of the sorting of copper-containing waste rock and improve the enrichment effect of the concentrate product.

[0032] When the feed belt 4 is conveying copper-containing waste rock, it needs to have its optical information collected by the imaging analysis source 6. If the copper-containing waste rock on the feed belt 4 is too disorderly, it will affect the collection and analysis of optical information. Based on this, the following preferred embodiment is provided.

[0033] like Figure 2 As shown, the feeding belt 4 is provided with multiple material troughs 41. The multiple material troughs 41 are arranged at equal intervals along the length of the feeding belt 4. The material troughs 41 are used to collect copper-containing waste stones falling from the vibrating distributor 3 for batch transportation.

[0034] In this embodiment, by setting material troughs 41 on the surface of the feeding belt 4, and the material troughs 41 are evenly spaced along the length direction, when the vibrating material distributor 3 feeds material onto the feeding belt 4, the feeding belt 4 can transport copper-containing waste rock in batches according to each material trough 41, reducing the difficulty of optical information acquisition and analysis.

[0035] In addition, since the copper-containing waste rock is transported in batches by the material trough 41, the optical information of the copper-containing waste rock in each material trough 41 is independent, thereby realizing intermittent time-sharing control. This makes the feeding time of the copper-containing waste rock more matched with the high-pressure air injection delay time of the nozzle guide plate 12 and the opening time of the spray valve, thus improving the sorting effect.

[0036] However, there may still be a lot of copper-containing waste rock between the two material tanks 41, which may affect batch transportation and optical information acquisition and analysis. Based on this, the following preferred embodiment is provided.

[0037] like Figure 2As shown, the surface of the feeding belt 4 between two adjacent material troughs 41 is raised upward to form an arc-shaped protrusion 42. The arc surface 421 of the arc-shaped protrusion 42 is smoothly connected with the wall of the material trough 41, and the wall of the material trough 41 and the bottom wall are in the shape of a trumpet. A retaining edge 43 is provided on the side of the feeding belt 4. The portion of the retaining edge 43 covering the material trough 41 slopes inward from top to bottom to form an inclined wall 431. The inclined wall 431 smoothly connects with the trough wall and bottom of the material trough 41.

[0038] In this embodiment, an arc-shaped protrusion 42 with an arc surface 421 is formed between two adjacent material troughs 41, and the arc surface 421 is smoothly connected to the material trough 41. A retaining edge 43 is provided on the side of the feeding belt 4, and an inclined wall 431 is formed between the retaining edge 43 and the material trough 41, and the inclined wall 431 is smoothly connected to the material trough 41. This forms an outwardly expanding funnel mouth, which can not only facilitate the collection of copper-containing waste rock, but also reduce the probability of copper-containing waste rock remaining between two adjacent material troughs 41.

[0039] In addition, copper-containing waste rock contains a large amount of dust, which may cover the surface of small-particle concentrate, affecting the acquisition of optical information and hindering high-pressure air jet separation. Based on this, the following superior embodiments are provided.

[0040] like Figure 2 As shown, multiple holes 44 are provided at the bottom of the feeding belt 4. The multiple holes 44 are arranged in an array along the length of the feeding belt 4, and the holes 44 penetrate and connect to the corresponding material trough 41 to drain the dust in the copper-containing waste rock that is fed by the vibrating material distributor 3 in the material trough 41.

[0041] In this embodiment, by setting a hole 44 on the feeding belt 4, the hole 44 penetrates the feeding belt 4 and connects to the trough 41, so that during the transportation of copper-containing waste rock, the sand and dust in the trough 41 can leak out from the hole 44, reducing its interference with the collection of optical information.

[0042] Of course, the amount of sand and dust leaking out of the leak hole 44 through vibration during the transportation process is relatively small, and it can easily affect the environment near the system and the system itself. Based on this, the following preferred embodiments are provided.

[0043] like Figure 2 As shown, a dust collection box 71 is provided at the bottom of the feeding belt 4. The dust collection box 71 is arranged on the material receiving side of the imaging analysis source 6, and multiple dust collection boxes 71 are arranged along the length of the feeding belt 4. A dust collection port 72 is provided on the side of the dust collection box 71 near the feeding belt 4. The dust collection box 71 is set against the feeding belt 4, and the dust collection port 72 covers a number of corresponding holes 44 to correspond to a material trough 41. Furthermore, multiple dust collection boxes 71 are connected to a dust collector via parallel dust collection pipes to remove dust from the material trough 41.

[0044] In this embodiment, by setting a dust collection box 71 at the bottom of the feeding belt 4, and the dust collection port 72 of the dust collection box 71 is close to the bottom of the feeding belt 4, the leakage hole 44 will pass through the dust collection port 72 during the feeding belt 4 conveying process, thereby generating negative pressure in the material trough 41 to suck out the sand and dust, so as to improve the removal rate of sand and dust.

[0045] The bottom of the feeding belt 4 refers to the surface of the feeding belt 4 that contacts the belt roller, that is, the inner surface relative to the outer surface of the material trough 41.

[0046] Of course, the direct contact and friction between the feed belt 4 and the dust collection box 71 will cause significant wear and tear on the feed belt 4. Based on this, the following preferred embodiments are provided.

[0047] like Figure 2 As shown, a fluff layer 73 is provided on the side of the dust collection box 71 near the feeding belt 4. The fluff layer 73 is arranged around the edge of the dust collection port 72, and the dust collection box 71 is attached to the bottom of the feeding belt 4 through the fluff layer 73.

[0048] In this embodiment, by providing a fluff layer 73 at the edge of the suction port 72, the suction box 71 contacts the surface of the feed belt 4 through the fluff layer 73, which can maintain negative pressure suction and reduce frictional wear on the feed belt 4.

[0049] Furthermore, although the dust collection box 71 can remove sand and dust from the material trough 41, it is usually difficult to remove it completely due to the obstruction of copper-containing waste rock. After sorting, copper-containing waste rock and a small amount of sand and dust are separated by high-pressure jet, and some sand and dust will adhere to the material trough 41 and return to the return section, which can easily lead to sand and dust being spilled by the vibrating feed belt 4. Based on this, the following preferred embodiment is provided.

[0050] like Figure 2 As shown, multiple dust collection boxes 71 are located between the conveying section and the return section of the feeding belt 4, and the multiple dust collection boxes 71 are respectively attached to the inner side of the conveying section and the return section of the feeding belt 4. The multiple dust collection boxes 71 located in the return section of the feeding belt 4 are distributed from the unloading end to the feeding end.

[0051] In this embodiment, a dust collection box 71 is also provided on the inner side wall of the return section of the feeding belt 4, and the dust collection box 71 is distributed along the material discharge end to the material feed end, so that when the material trough 41 is unloaded and returned, the sand inside is sucked out by the dust collection box 71 to reduce the probability of dust in the return section.

[0052] In addition, the lint layer 73 that comes into contact with the dust collection box 71 and the feed belt 4 of the return section can wipe it, thereby keeping the inner wall of the feed belt 4 clean and reducing the impact of sand and dust on the conveying of the feed belt 4.

[0053] Of course, in order to further reduce the impact of sandstorms, such as Figure 3 As shown, a dustproof box 45 is provided outside the feeding belt 4, and the conveying section of the feeding belt 4 is exposed above the dustproof box 45. The bottom of the dustproof box 45 is connected to a dust collector through a dust suction pipe.

[0054] In this embodiment, the dust box 45 can surround the feeding belt 4, and the dust box 45 is connected to the dust collector through the dust suction pipe, so that the inside of the dust box 45 is always a negative pressure environment, thereby effectively preventing sand and dust from spreading outward.

[0055] Furthermore, such as Figure 3 As shown, a partition 451 is provided inside the dustproof box 45, and the partition 451 is located between the two belt rollers of the feeding belt 4.

[0056] In this embodiment, the conveying section and the return section of the feed belt 4 are isolated by the partition 451, thereby reducing the impact of dust falling from the conveying section through the hole 44 on the return section.

[0057] like Figure 4 As shown, the method for constructing the sorting parameter optimization model built into the photoelectric sorting controller includes: The photoelectric sensor of the imaging analysis source is used to obtain the physicochemical properties of copper-containing waste rock samples, and the sorting parameters and sorting indexes are obtained by multi-component sorting tests of copper-containing waste rock samples using the system. A neural network model is used to establish the mapping relationship between physical properties, sorting parameters and sorting indicators, and a sorting effect prediction model is obtained to predict the sorting indicators based on physical properties and sorting parameters. The sorting effect prediction model is transformed into an optimization objective. The optimization objective is solved using an optimization algorithm to obtain the optimal sorting parameters that enable the physical and chemical properties to reach the optimal sorting index. The optimal sorting parameters are then used to perform reinforcement learning on the sorting effect prediction model. By using a neural network model, a mapping relationship is established between physical properties, sorting indices and optimal sorting parameters, resulting in a sorting parameter optimization model that predicts the optimal sorting parameters based on physical properties and sorting indices. The optimal sorting parameters of the system are determined in real time by using a sorting parameter optimization model based on the physicochemical properties of the copper-containing waste rock to be sorted in real time and the sorting index that matches the preset sorting requirements.

[0058] The physical and chemical properties include color, shape, reflectivity, texture, and volume. The sorting parameters include density threshold, vibrating feeder frequency (corresponding to vibrating distributor 3), belt speed (corresponding to feed belt 4, tailings belt 13, and concentrate belt 14), high-pressure air injection delay time (corresponding to air compressor 8), and spray valve opening time (corresponding to nozzle 12, or pneumatic plate). The sorting indicators include concentrate Cu grade, Cu recovery rate, enrichment ratio, and waste rock disposal rate. The function of the tailings conveyor belt is to allow the waste rock products, which account for a large proportion after sorting, to fall freely into the tailings conveyor belt. The function of the concentrate conveyor belt is to allow the concentrate product, which accounts for a smaller proportion after sorting, to fall freely into the sorting product conveyor belt after being separated by air jets from the nozzles.

[0059] Among them, the grade of Cu in copper-containing waste rock samples before sorting was determined. Weight of copper-containing waste rock samples before sorting The Cu grade of the concentrate is determined by measuring the Cu content of copper-containing waste rock samples that have been sorted and entered the concentrate category. The weight of copper-containing waste rock samples that entered the concentrate category after sorting was determined by belt scale. ; pass Calculate the Cu recovery rate; pass Calculate the enrichment ratio; pass Calculate the waste rock disposal rate.

[0060] By selecting copper-bearing ore samples from different grade ranges for sorting tests, and randomly setting the sorting parameters of the dry separator, the sorting results were recorded, such as the weight of the ore sample sorted onto the concentrate conveyor belt, and the Cu grade of the concentrate was determined. Based on the total ore sample weight and total ore sample Cu grade recorded before sorting, the sorting index was calculated, and the sorting effect corresponding to each sorting parameter was intuitively quantified.

[0061] Based on the data accumulated from sorting experiments, a neural network is trained to construct a neural network model that predicts the corresponding sorting indicators (sorting effect) according to the physical and chemical properties and sorting parameters, namely the sorting effect prediction model.

[0062] In traditional sample sorting, sorting parameters and physicochemical properties are simply randomly combined to obtain the corresponding sorting index (sorting effect). This approach cannot determine the optimal sorting parameters and the corresponding optimal sorting index (sorting effect) under a specific physicochemical property. Therefore, this invention utilizes a multi-objective optimization algorithm to solidify the physicochemical properties and transform the original sorting effect prediction model... The physical and chemical properties s in the middle are weakened and transformed into form.

[0063] When optimizing the sorting parameters, the target to be optimized corresponds to each index in the sorting index, namely, maximizing the Cu grade of the concentrate. Maximize Cu recovery rate Maximize enrichment ratio And to maximize the waste rock disposal rate Thus, a search and solution can be performed within the parameter allowable range of the dry separator. ,get The optimal solution is obtained, thus yielding the most suitable sorting parameters for each physical and chemical property.

[0064] After obtaining the optimal sorting parameters, a new matching relationship (enhanced dataset) is formed between the physical properties and the sorting parameters. This matching relationship represents a high-quality, high-value data point located in the globally optimal performance region. Using this data to retrain the original sorting effect prediction model enhances the model's prediction accuracy in and around the optimal region. In the next multi-objective optimization, the search based on this more accurate model will find a solution closer to the true optimum, creating a positive feedback loop. Simultaneously, the model continuously absorbs new data, expanding its knowledge boundaries to better adapt to changes in raw materials. It is no longer a static, one-off model, but a dynamic model that evolves alongside the production process, with its generalization ability and robustness continuously improving over time.

[0065] After training the sorting effect prediction model, this invention obtains a correlation formula between sorting parameters and sorting indicators (sorting effect), which is then applied to the multi-objective optimization of sorting parameters.

[0066] Methods for constructing sorting performance prediction models include: Using the physicochemical properties and sorting parameters of copper-containing waste rock samples as input terms to a neural network model, and the sorting indices of the copper-containing waste rock samples as output terms, a multilayer perceptron is trained to obtain a sorting performance prediction model. In the formula, The sorting index is the output of the sorting effect prediction model. These represent the concentrate Cu grade, Cu recovery rate, enrichment ratio, and waste rock disposal rate output by the sorting effect prediction model, respectively, where s is the physicochemical property. For sorting parameters, These are density threshold, vibrating feeder frequency, belt speed, high-pressure air injection delay time, and spray valve opening duration, respectively. MLP stands for Multilayer Perceptron. Loss function of sorting effect prediction model In the formula, For the true value of the sorting index, These are the true values ​​for concentrate Cu grade, Cu recovery rate, enrichment ratio, and waste rock disposal rate, respectively. This is the cross-entropy operation formula.

[0067] Methods for solving the optimal sorting parameters include: Sorting effect prediction model Convert to a multi-objective optimization function In the formula, max is the maximization identifier; The physicochemical properties of each copper-containing waste rock sample were fixed one by one. Using the threshold range of the dry separator's sorting parameters as the search space, a genetic algorithm or particle swarm optimization algorithm was employed. Assuming a fitness function, a multi-objective optimization function is solved to obtain the optimal sorting parameters for each copper-containing waste rock sample. In the formula , for The weight (set as needed). for The normalization result (eliminating dimensional errors).

[0068] Taking genetic algorithms as an example: Step 1, Initialization: Randomly generate a population of N individuals. Each individual represents a possible combination of parameters, for example, x_j=[ [] (Represents a set of parameter settings). Each individual is represented by a "chromosome", which is usually encoded in binary or real numbers.

[0069] The second step is to invoke the neural network. Evaluate: After decoding each individual (parameter combination) in the population, the data is input into the trained neural network model. In the middle, calculate the fitness F of each individual. Fitness is an indicator that measures whether an individual is good or bad.

[0070] Third step, select: Objective: To select superior individuals from the current population to serve as parents for the next generation. Individuals with higher fitness have a greater probability of being selected.

[0071] Methods: Roulette wheel selection or tournament selection are used. In roulette wheel selection, the probability of each individual being selected is proportional to its fitness. In tournament selection, several individuals are randomly selected, and the one with the highest fitness wins.

[0072] Step 4, Cross: Objective: To simulate biological hybridization and create new offspring from two parent individuals, aiming to combine the advantages of both parents.

[0073] Method: Single-point intersection, for example, parent A:[ Parent generation B:[ Randomly select a crossover point, exchange some genes, and you may get offspring: ].

[0074] Step 5, Mutation: Objective: To introduce new genetic material by randomly altering certain genes in individuals with a small probability, thereby maintaining population diversity and avoiding local optima.

[0075] Methods: bit flipping or Gaussian perturbation, for example, child [ The second gene may mutate and become [ ].

[0076] Step 6: Formation of a new population and iteration: The new individuals produced through selection, crossover, and mutation form a new population, replacing the old population.

[0077] Repeat steps two through five (evaluation → selection → crossover → mutation) to evolve generation after generation.

[0078] Termination condition: The algorithm stops when the maximum number of iterations is reached, or when the optimal fitness no longer significantly improves after several generations. The individual with the highest fitness across all generations is output as the recommended optimal sorting parameter.

[0079] Methods for using optimal sorting parameters to perform reinforcement learning on sorting performance prediction models include: The physicochemical properties s and optimal sorting parameters of copper-containing waste rock samples were analyzed. Separation indexes from copper-containing waste rock Construct an augmented dataset; Using augmented datasets to predict sorting performance The model was retrained to obtain an enhanced prediction model for sorting performance.

[0080] Methods for constructing sorting parameter optimization models include: To enhance the centralized physical properties of the data and sorting indicators As input, with optimal sorting parameters For the output, a multilayer perceptron is trained to obtain a sorting parameter optimization model. In the formula, The sorting index is the input to the sorting parameter optimization model, where s is the physical and chemical property. The optimal sorting parameters output by the model are optimized to improve the sorting parameters. MLP stands for Multilayer Perceptron. Loss function of sorting parameter optimization model ; In the formula, To enhance the optimal sorting parameters in the dataset, For the sorting effect prediction model based on Output sorting metrics for The fitness value of the corresponding sorting index, for The fitness value, where min is the minimum identifier. This is the cross-entropy operation formula.

[0081] Furthermore, based on the enhanced dataset, this invention establishes a sorting parameter optimization model that predicts the optimal sorting parameters according to physical and chemical properties and sorting indices. This model is the opposite of the prediction logic of the sorting effect prediction model. When the model is put into practical use after training, the non-sorting indices usually refer to the sorting requirements or the desired sorting effect. This model can determine the optimal sorting parameters under certain physical and chemical properties based on sorting requirements (e.g., Cu grade of concentrate > 15%, recovery rate > 65%, etc.).

[0082] Therefore, constructing a sorting parameter optimization model can directly determine the optimal sorting parameters without the need for sorting experiments or multi-objective optimization solutions, thus improving efficiency.

[0083] This invention employs a three-part loss term when training the sorting parameter optimization model. The first part is... It is the expected model prediction result. with truth value (that is, augmenting the dataset) If the loss is consistent with the model's loss, training with this loss ensures that the prediction loss of the sorting parameter optimization model is minimized and the prediction accuracy is maximized.

[0084] The second part is ,in It is the prediction result of the sorting parameter optimization model. Substitute these into the sorting effect prediction model to obtain the sorting index (sorting effect) predicted by the sorting effect prediction model. It is the basis of expectations Obtain the sorting indicators (sorting effect). The sorting index (sorting requirements) input to the sorting parameter optimization model. Consistent, that is, able to pass get It can also be done through Restore By utilizing a two-way correspondence, this further ensures The accuracy of the prediction.

[0085] The third part is ,in It is the multi-objective optimization function in multi-objective optimization algorithms. The calculated sorting index (sorting effect) should correspond to the maximum fitness, while the sorting index (sorting requirements) should correspond to the maximum fitness. This should also correspond to the maximum fitness value. It is an expectation The obtained fitness value and The obtained fitness values ​​are consistent, and using these as the loss for training can ensure that the fitness value loss of the sorting parameter optimization model is minimized and the prediction accuracy is maximized.

[0086] The above embodiments are merely exemplary embodiments of this application and are not intended to limit this application. The scope of protection of this application is defined by the claims. Those skilled in the art can make various modifications or equivalent substitutions to this application within its substance and scope of protection, and such modifications or equivalent substitutions should also be considered to fall within the scope of protection of this application.

Claims

1. A copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters, characterized in that, include: The material conveying device includes a vibrating distributor (3), a feeding belt (4), a tailings belt (13), and a concentrate belt (14) arranged sequentially along the conveying direction. The vibrating distributor (3) is located above the feed end of the feeding belt (4), and the tailings belt (13) and the concentrate belt (14) are located below the discharge end of the feeding belt (4) and arranged sequentially. The device is capable of independently weighing the weight of copper-containing waste rock falling on it. An airflow separation device is provided with a nozzle guide plate (12) at the discharge end of the feeding belt (4). The nozzle guide plate (12) sprays high-pressure airflow from the bottom of the discharge end of the feeding belt (4) upwards to separate the copper-containing waste rock discharged from the discharge end of the feeding belt (4) onto the tailings belt (13) and the concentrate belt (14). The photoelectric sorting controller is equipped with an imaging analysis source (6) above the feeding belt (4). The imaging analysis source (6) can acquire the physicochemical properties of copper-containing waste rock on the feeding belt (4). The photoelectric sorting controller can output sorting parameters to control the vibrating feeder (3), the feeding belt (4), the tailings belt (13), the concentrate belt (14) and the nozzle guide plate (12). The sorting parameters include the vibrating feeding frequency, belt speed, high-pressure air injection delay time and spray valve opening time. Furthermore, the photoelectric sorting controller has a built-in sorting parameter optimization model. The sorting parameter optimization model can output the optimal sorting parameters based on the input physical and chemical properties, so as to dynamically adjust the vibration feeding frequency of the vibrating feeder (3), the speed of the feeding belt (4), the tailings belt (13) and the concentrate belt (14), as well as the high-pressure air injection delay time and the spray valve opening time of the nozzle guide plate (12) in real time.

2. The copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters according to claim 1, characterized in that, The feeding belt (4) is provided with multiple material troughs (41), which are equally spaced along the length of the feeding belt (4). The material troughs (41) are used to collect copper-containing waste stones falling from the vibrating material distributor (3) for batch transportation.

3. The copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters according to claim 2, characterized in that, The surface of the feeding belt (4) between two adjacent material troughs (41) is raised upward to form an arc-shaped protrusion (42). The arc surface (421) of the arc-shaped protrusion (42) is smoothly connected to the wall of the material trough (41), and the wall of the material trough (41) and the bottom wall are in the shape of a trumpet. A retaining edge (43) is provided on the side of the feeding belt (4). The portion of the retaining edge (43) covering the material trough (41) is inclined from top to bottom and inward to form an inclined wall (431). The inclined wall (431) is smoothly connected to the trough wall and the bottom of the material trough (41).

4. The copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters according to claim 3, characterized in that, Multiple drain holes (44) are provided at the bottom of the feeding belt (4). The multiple drain holes (44) are arranged in an array along the length direction of the feeding belt (4), and the drain holes (44) penetrate and connect to the corresponding material trough (41) to drain the dust in the copper-containing waste rock that is fed by the vibrating material distributor (3) in the material trough (41).

5. The copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters according to claim 4, characterized in that, A dust collection box (71) is provided at the bottom of the feeding belt (4). The dust collection box (71) is arranged on the material receiving side of the imaging analysis source (6) and multiple dust collection boxes are arranged along the length of the feeding belt (4). The dust collection box (71) is provided with a dust collection port (72) on the side near the feeding belt (4). The dust collection box (71) is disposed against the feeding belt (4). The dust collection port (72) covers a plurality of corresponding holes (44) to correspond to one material trough (41). Furthermore, multiple dust collection boxes (71) are connected in parallel through dust collection pipes to a dust collector to remove dust from the material trough (41).

6. The copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters according to claim 5, characterized in that, A fluff layer (73) is provided on the side of the dust collection box (71) near the feed belt (4). The fluff layer (73) is arranged around the edge of the dust collection port (72), and the dust collection box (71) is attached to the bottom of the feed belt (4) through the fluff layer (73).

7. A copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters according to claim 5 or 6, characterized in that, Multiple dust collection boxes (71) are located between the conveying section and the return section of the feeding belt (4), and multiple dust collection boxes (71) are respectively attached to the inner side of the conveying section and the return section of the feeding belt (4), and multiple dust collection boxes (71) located in the return section of the feeding belt (4) are distributed from the unloading end to the feeding end.

8. The copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters according to claim 7, characterized in that, A dustproof box (45) is provided outside the feeding belt (4), and the conveying section of the feeding belt (4) is exposed above the dustproof box (45). The bottom of the dustproof box (45) is connected to a dust collector through a dust suction pipe.

9. A copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters according to claim 8, characterized in that, A partition (451) is provided inside the dustproof box (45), and the partition (451) is located between the two belt rollers of the feeding belt (4).

10. A copper-containing waste rock enrichment system based on photoelectric sorting optimization parameters according to claim 1, characterized in that, The method for constructing the sorting parameter optimization model built into the photoelectric sorting controller includes: The photoelectric sensor of the imaging analysis source is used to obtain the physicochemical properties of copper-containing waste rock samples, and the sorting parameters and sorting indexes are obtained by multi-component sorting tests of copper-containing waste rock samples using the system. A neural network model is used to establish the mapping relationship between the physical properties, sorting parameters and sorting indicators, so as to obtain a sorting effect prediction model that predicts the sorting indicators based on the physical properties and sorting parameters. The sorting effect prediction model is transformed into an optimization objective. The optimization objective is solved using an optimization algorithm to obtain the optimal sorting parameters that enable the physical and chemical properties to reach the optimal sorting index. The optimal sorting parameters are then used to perform reinforcement learning on the sorting effect prediction model. A neural network model is used to establish the mapping relationship between the physical properties, sorting indicators and optimal sorting parameters, so as to obtain a sorting parameter optimization model that predicts the optimal sorting parameters based on the physical properties and sorting indicators. The optimal sorting parameters of the system are determined in real time by using a sorting parameter optimization model based on the physicochemical properties of the copper-containing waste rock to be sorted in real time and the sorting index that matches the preset sorting requirements.

Images