Belt-based online ore solid waste inspection system and method

Abstract

The present invention provides a belt-based online ore solid waste screening system and method. The system includes: a sampling module for sampling the ore on the conveyor belt to obtain an ore sample; a sample preparation module for preparing the ore sample into a standardized sample; a collection module for collecting spectral information and volatile information of the standardized sample; and an identification module for processing the spectral information and volatile information based on a neural network model to determine whether the ore corresponding to the standardized sample is solid waste. The present invention can improve the automation, accuracy and stability of ore solid waste screening.

Description

Technical Field

[0001] The present invention relates to the technical field of ore inspection, and in particular to a belt-based online ore solid waste inspection system and method. Background Art

[0002] As a major commodity, bulk ore imports and exports require solid waste screening during inspection and quarantine. These imports are typically shipped primarily by sea, with two methods of port unloading and transshipment: dump trucks and conveyor belts.

[0003] When using belt transfer, the unloading process is a continuous operation, there is uncertainty in time, the environment is dusty, and the belt runs at a fast speed. These factors are often not conducive to personnel observation, sampling and measurement, resulting in poor accuracy and stability of manual inspection results. Summary of the Invention

[0004] The embodiment of the present invention provides a belt-line type ore solid waste inspection system and method to solve the problem of automatic online inspection of belt ore.

[0005] In a first aspect, an embodiment of the present invention provides a belt-based online ore solid waste inspection system, comprising:

[0006] The sampling module is used to sample the ore on the conveyor belt to obtain ore samples;

[0007] A sample preparation module, used to prepare ore samples into standardized samples;

[0008] An acquisition module is used to collect spectral information and volatile information of standardized samples;

[0009] The identification module is used to process the spectral information and volatile matter information based on the neural network model to determine whether the ore corresponding to the standardized sample is solid waste.

[0010] In a possible implementation, the sampling module includes a sampling port and a telescopic arm; the opening direction of the sampling port is opposite to the direction of ore movement, and a weighing unit is provided inside;

[0011] The sampling module is specifically used for:

[0012] The sampling port is extended into the belt area by the telescopic arm;

[0013] Based on the weighing value of the weighing unit, it is judged whether there is sufficient sample entering the sampling port. If there is sufficient sample entering the sampling port, the telescopic arm is retracted.

[0014] In a possible implementation, the sampling module is further configured to:

[0015] Before the sampling port is extended into the belt area by the telescopic arm, samples are taken on the belt sampling device. If there is no sample on the belt sampling device, the sampling port is extended into the belt area by the telescopic arm to take samples.

[0016] In a possible implementation, the sampling module is specifically configured to:

[0017] Calculate the difference between the time when sampling starts and the time when the sample enters the sampling module as the sampling time;

[0018] Adjusting a preset sampling interval based on sampling time; wherein the preset sampling interval is determined based on a belt transport rate;

[0019] The time for starting the next sampling is determined based on the time when the current sample enters the sampling module and the adjusted sampling interval.

[0020] In one possible implementation, the sample preparation module includes a drying unit, a crushing unit, and a tablet pressing unit connected in sequence;

[0021] The sample preparation module is specifically used for:

[0022] Drying the ore sample through a drying unit to obtain a dry sample;

[0023] The dry sample is crushed and mixed by a crushing unit to obtain a crushed sample;

[0024] The crushed sample is compressed by a compression unit to obtain a standardized sample.

[0025] In a possible implementation, the drying unit further includes an air outlet pipe, the air outlet pipe is connected to the collection module, and the collection module includes a gas detection unit;

[0026] The acquisition module is specifically used for:

[0027] The gas in the outlet pipe is collected and analyzed to obtain the volatile matter information of the standardized sample.

[0028] In one possible implementation, the acquisition module includes a near-infrared unit and a LIBS unit;

[0029] The acquisition module is specifically used for:

[0030] Acquire near-infrared spectra of standardized samples using a near-infrared unit;

[0031] LIBS spectra of the standardized samples were collected by the LIBS unit.

[0032] In a possible implementation, the identification module is specifically configured to:

[0033] The near-infrared spectrum features were reduced in dimension based on principal component analysis and input into the trained KNN neural network to obtain the first classification results of the standardized samples;

[0034] The LIBS spectra were input into the trained CNN neural network to obtain the second classification results of the standardized samples;

[0035] The first classification results, the second classification results and the volatile matter information are input into the trained SVM classifier to obtain the solid waste detection results of the standardized samples.

[0036] In a second aspect, an embodiment of the present invention provides a belt-based online ore solid waste screening method, comprising:

[0037] The sampling module samples the ore on the conveyor belt to obtain ore samples;

[0038] The sample preparation module prepares the ore sample into a standardized sample;

[0039] The acquisition module collects the spectral information and volatile information of the standardized samples;

[0040] The recognition module processes the spectral information and volatile matter information based on the neural network model to determine whether the ore corresponding to the standardized sample is solid waste.

[0041] An embodiment of the present invention provides a belt-based online ore solid waste screening system and method. A sampling module is used to sample the ore on the conveyor belt, which can replace traditional manual labor and automatically sample the ore unloaded in the form of a belt 24 hours a day. Then, standardized sample preparation is performed for samples of different properties, particle sizes, and moisture content to ensure the quality of data during subsequent testing. Finally, the spectral information and volatile matter information of the sample are collected, and a neural network model is used to accurately and objectively determine whether the ore is solid waste. This can improve the degree of automation, accuracy, and stability of ore solid waste screening. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 This is a structural diagram of a belt-type online ore solid waste inspection system provided by one embodiment of the present invention;

[0044] Figure 2 It is a structural schematic diagram of a belt-type online ore solid waste inspection system provided by another embodiment of the present invention;

[0045] Figure 3 It is a structural diagram of a collection module provided by an embodiment of the present invention;

[0046] Figure 4 This is a flow chart for implementing a belt-based online ore solid waste screening method provided by one embodiment of the present invention;

[0047] Figure 5 It is a flow chart for implementing a belt-based online ore solid waste inspection method provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0048] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0049] In order to make the purpose, technical solutions and advantages of the present invention more clear, specific embodiments will be described below with reference to the accompanying drawings.

[0050] Currently, the manual inspection method for belt transfer unloading has the following shortcomings:

[0051] (1) Impact of inspection environment:

[0052] During the inspection of conveyor belt ore, customs must first conduct sensory assessments, such as touch, sight, and smell. However, terminal equipment is subject to uncertain operating hours, poor environmental conditions, and high conveyor belt speeds. These factors can impact customs inspections, including poor personnel health, environmental discomfort, and mechanical damage. During nighttime inspections, insufficient light and fatigue significantly impact inspectors' sensory assessments, making missed and misjudgment highly likely. This significantly reduces the effectiveness of traditional, personnel-based inspection methods.

[0053] (2) Impact of personnel experience:

[0054] Traditional inspection methods require a high level of personnel experience. Different personnel experiences may lead to different results, resulting in controversial results and the need for secondary judgment.

[0055] (3) The real-time nature of the inspection process is insufficient:

[0056] Current inspections require personnel to board vessels and conduct physical inspections of cargo at conveyors or storage yards. Multiple inspections are also required at intervals of 5,000 tons from the start of unloading to completion. Insufficient inspection personnel can lead to unloading delays, increasing terminal operating costs and vessel costs. Therefore, a system is urgently needed that can fully automate and continuously replace traditional manual solid waste inspections during ore unloading and transportation.

[0057] See also Figure 1 , which shows a schematic structural diagram of a belt-type online ore solid waste inspection system 1 provided by an embodiment of the present invention, and is described in detail as follows:

[0058] The sampling module 11 is used to sample the ore on the conveyor belt to obtain an ore sample;

[0059] The sample preparation module 12 is used to prepare the ore sample into a standardized sample;

[0060] The acquisition module 13 is used to acquire the spectral information and volatile information of the standardized sample;

[0061] The identification module 14 is used to process the spectral information and volatile matter information based on the neural network model to determine whether the ore corresponding to the standardized sample is solid waste.

[0062] In this embodiment, the structure, position and connection relationship of each module can be as follows: Figure 2 As shown, the sampler is a sampling module 11, which is arranged near the belt area. The bottom of the sampling module 11 is connected to the dryer in the sample preparation module 12 through a conveyor. After the sampling is completed, the ore sample is transported to the dryer by the conveyor for the drying step in the sample preparation process. The dried ore sample is then transported to the crusher by the elevator. Finally, the crusher transports the standardized sample to the analyzer, i.e., the acquisition module 13, to collect the spectral information and volatile information of the sample, and transmit it to the identification module 14 to process the spectral information and volatile information to determine whether the ore corresponding to the standardized sample is solid waste.

[0063] The embodiment of the present invention uses a sampling module to sample the ore on the conveyor belt, which can replace traditional manual labor and perform 24-hour automatic sampling of the ore unloaded in the form of a belt. Then, standardized sample preparation is performed for samples of different properties, particle sizes, and moisture to ensure the quality of data during subsequent testing. Finally, the spectral information and volatile matter information of the sample are collected, and a neural network model is used to accurately and objectively determine whether the ore is solid waste, which can improve the degree of automation, accuracy and stability of ore solid waste inspection.

[0064] In a possible implementation, the sampling module includes a sampling port and a telescopic arm; the opening direction of the sampling port is opposite to the direction of ore movement, and a weighing unit is provided inside;

[0065] The sampling module is specifically used for:

[0066] The sampling port is extended into the belt area by the telescopic arm;

[0067] Based on the weighing value of the weighing unit, it is judged whether there is sufficient sample entering the sampling port. If there is sufficient sample entering the sampling port, the telescopic arm is retracted.

[0068] In this embodiment, the sampling module utilizes bypass sampling technology. When sampling is required, a robotic arm controls a sampling port, which can be shaped like a shovel and sized to meet specific requirements. Because the sampling port is in the opposite direction of ore movement, the ore's own movement allows it to automatically enter the port for sampling. When sampling is no longer required, the port can be controlled to move away from the belt area, halting sampling.

[0069] The weighing unit can be set at the bottom of the sampling module. When the ore enters the sampling port and falls to the bottom of the sampling module, the weighing module is triggered. According to the weighing value, the weight of the ore entering the sampling module can be judged, and whether the sampling requirements are met can be determined.

[0070] Because ore sizes vary, an infrared sensor can be installed inside the sampling port. If the infrared sensor is triggered for a long time but the weighing value of the weighing module remains unchanged, it can be determined that the sampling port is blocked. If the sampling port is blocked, retract the sampling port and reinsert the belt to take a sample.

[0071] In a possible implementation, the sampling module is further configured to:

[0072] Before the sampling port is extended into the belt area by the telescopic arm, samples are taken on the belt sampling device. If there is no sample on the belt sampling device, the sampling port is extended into the belt area by the telescopic arm to take samples.

[0073] In this embodiment, the sampling module can take a single sample from the belt or take a secondary sample from the original belt sampling device. When a belt sampling device exists, the sample on the belt sampling device may have greater detection value and can be sampled on the belt sampling device first.

[0074] In a possible implementation, the sampling module is specifically configured to:

[0075] Calculate the difference between the time when sampling starts and the time when the sample enters the sampling module as the sampling time;

[0076] Adjusting a preset sampling interval based on sampling time; wherein the preset sampling interval is determined based on a belt transport rate;

[0077] The time for starting the next sampling is determined based on the time when the current sample enters the sampling module and the adjusted sampling interval.

[0078] In this embodiment, the moment when the sample enters the sampling module is the moment when the sampling is actually completed. The preset sampling interval is adjusted using the sampling time. The sampling time is subtracted from the preset sampling interval to eliminate the influence of the waiting time during the sampling process on the sampling frequency.

[0079] The preset sampling interval can be set according to the actual inspection standards, for example, an inspection is carried out every 5,000 tons of ore transferred.

[0080] In one possible implementation, the sample preparation module includes a drying unit, a crushing unit, and a tablet pressing unit connected in sequence;

[0081] The sample preparation module is specifically used for:

[0082] Drying the ore sample through a drying unit to obtain a dry sample;

[0083] The dry sample is crushed and mixed by a crushing unit to obtain a crushed sample;

[0084] The crushed sample is compressed by a compression unit to obtain a standardized sample.

[0085] In this embodiment, the sample is subjected to a standardized sample preparation process, including drying, crushing, and tableting. The processed samples can achieve consistency, ensuring the quality of the data in subsequent testing and avoiding fluctuations and interference caused by sample properties, moisture content, etc.

[0086] In a possible implementation, the drying unit further includes an air outlet pipe, the air outlet pipe is connected to the collection module, and the collection module includes a gas detection unit;

[0087] The acquisition module is specifically used for:

[0088] The gas in the outlet pipe is collected and analyzed to obtain the volatile matter information of the standardized sample.

[0089] In this example, solid waste, due to microbial activity, produces harmful gases such as methane, ammonia, and hydrogen sulfide, which carry a foul odor. Improper transportation and handling of solid waste can also produce dust and harmful gases, such as dioxins, polycyclic aromatic hydrocarbons, methane, and sulfur dioxide. Drying ore samples can accelerate the volatilization of various gas components within the ore, allowing for precise identification of the volatile characteristics of the ore.

[0090] In one possible implementation, the acquisition module includes a near-infrared unit and a LIBS unit;

[0091] The acquisition module is specifically used for:

[0092] Acquire near-infrared spectra of standardized samples using a near-infrared unit;

[0093] LIBS spectra of the standardized samples were collected by the LIBS unit.

[0094] In this embodiment, the structure of the acquisition module is as follows: Figure 3 As shown in the figure, it specifically includes the sample inlet at the top, the near-infrared unit and the LIBS unit at the lower right corner. After the sample enters the acquisition module, the near-infrared unit and the LIBS unit work in turn to collect the sample's near-infrared spectrum and LIBS spectrum respectively.

[0095] Using both near-infrared and LIBS spectroscopy techniques, we analyze the molecular composition and elemental content of solid waste, incorporating machine learning to train and validate models for both positive and negative samples. This integration of near-infrared and LIBS spectral information effectively addresses the limitations of a single technique in solid waste identification, significantly improving the overall accuracy and stability of the system.

[0096] In a possible implementation, the identification module is specifically configured to:

[0097] The near-infrared spectrum features were reduced in dimension based on principal component analysis and input into the trained KNN neural network to obtain the first classification results of the standardized samples;

[0098] The LIBS spectra were input into the trained CNN neural network to obtain the second classification results of the standardized samples;

[0099] The first classification results, the second classification results and the volatile matter information are input into the trained SVM classifier to obtain the solid waste detection results of the standardized samples.

[0100] In this example, principal component analysis (PCA) can extract the most representative and discriminative features from the raw near-infrared spectral data. This reduces the data's dimensionality and complexity, removes noise and redundant information, and retains the most important structural information, improving the model's computational efficiency and predictive performance. A KNN neural network deep learning model then captures the complex patterns and structures in the spectral data, thereby improving classification accuracy.

[0101] LIBS spectral analysis uses a convolutional neural network (CNN) to extract features from the data and map it to a new, lower-dimensional space, known as dimensionality reduction. The benefit of dimensionality reduction is that it suppresses interference from irrelevant variables. In this new space, the data for each sample is mapped so that samples of the same type (such as solid waste and solid waste, or normal and normal) are as close as possible, and samples of different types (solid waste and normal) are as close as possible. The sample data measured by the device is input into the CNN convolutional neural network and mapped to the new space. The training data sample that is closest or most similar to the sample data is calculated in this new space. The properties of this sample are then used to determine whether it is solid waste.

[0102] Finally, the classification performance of SVM, combined with the integration advantages of the Boosting method, the two classification results and volatile matter information were combined for solid waste identification, significantly improving the analysis and classification accuracy of ore solid waste data.

[0103] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0104] The following is a method embodiment of the present invention. For details not described in detail, please refer to the corresponding system embodiment described above.

[0105] Figure 4 The following is a flowchart of an implementation of a belt-type online ore solid waste inspection method provided by an embodiment of the present invention. For ease of explanation, only the parts related to the embodiment of the present invention are shown, which are detailed as follows:

[0106] like Figure 4 As shown, the belt-line ore solid waste investigation method 4 includes:

[0107] Step 401: The sampling module samples the ore on the conveyor belt to obtain an ore sample;

[0108] Step 402: The sample preparation module prepares the ore sample into a standardized sample;

[0109] Step 403: The acquisition module acquires spectral information and volatile information of the standardized sample;

[0110] In step 404 , the identification module processes the spectral information and volatile matter information based on the neural network model to determine whether the ore corresponding to the standardized sample is solid waste.

[0111] In a possible implementation, the sampling module includes a sampling port and a telescopic arm; the opening direction of the sampling port is opposite to the direction of ore movement, and a weighing unit is provided inside;

[0112] The sampling module samples the ore on the conveyor belt to obtain ore samples, including:

[0113] The sampling module drives the sampling port into the belt area through the telescopic arm;

[0114] The sampling module determines whether there is sufficient sample entering the sampling port based on the weighing value of the weighing unit, and retracts the telescopic arm if there is sufficient sample entering the sampling port.

[0115] In a possible implementation, before the sampling module drives the sampling port into the belt area through the telescopic arm, the method further includes:

[0116] The sampling module takes samples on the belt sampling device. If there is no sample on the belt sampling device, the sampling port is driven by the telescopic arm to extend into the belt area to take samples.

[0117] In a possible implementation, the sampling module samples the ore on the conveyor belt, including:

[0118] Calculate the difference between the time when sampling starts and the time when the sample enters the sampling module as the sampling time;

[0119] Adjusting a preset sampling interval based on sampling time; wherein the preset sampling interval is determined based on a belt transport rate;

[0120] The time for starting the next sampling is determined based on the time when the current sample enters the sampling module and the adjusted sampling interval.

[0121] In one possible implementation, the sample preparation module includes a drying unit, a crushing unit, and a tablet pressing unit connected in sequence;

[0122] The sample preparation module prepares ore samples into standardized samples, including:

[0123] The sample preparation module dries the ore sample through the drying unit to obtain a dry sample;

[0124] The sample preparation module crushes and mixes the dry sample through the crushing unit to obtain a crushed sample;

[0125] The sample preparation module compresses the crushed samples through the tableting unit to obtain standardized samples.

[0126] In a possible implementation, the drying unit further includes an air outlet pipe, the air outlet pipe is connected to the collection module, and the collection module includes a gas detection unit;

[0127] The acquisition module collects spectral information and volatile information of standardized samples, including:

[0128] The collection module collects the gas in the outlet pipe and analyzes it to obtain the volatile matter information of the standardized sample.

[0129] In one possible implementation, the acquisition module includes a near-infrared unit and a LIBS unit;

[0130] The acquisition module collects spectral information and volatile information of standardized samples, including:

[0131] The acquisition module acquires the near infrared spectrum of the standardized sample through the near infrared unit;

[0132] The acquisition module collects the LIBS spectrum of the standardized sample through the LIBS unit.

[0133] In one possible implementation, the recognition module processes the spectral information and volatile information based on a neural network model to determine whether the ore corresponding to the standardized sample is solid waste, including:

[0134] The recognition module reduces the dimension of the near-infrared spectrum features based on principal component analysis and inputs them into the trained KNN neural network to obtain the first classification results of the standardized samples;

[0135] The recognition module inputs the LIBS spectra into the trained CNN neural network to obtain the second classification results of the standardized samples;

[0136] The recognition module inputs the first classification result, the second classification result and the volatile matter information into the trained SVM classifier to obtain the solid waste detection results of the standardized sample.

[0137] The embodiment of the present invention uses a sampling module to sample the ore on the conveyor belt, which can replace traditional manual labor and perform 24-hour automatic sampling of the ore unloaded in the form of a belt. Then, standardized sample preparation is performed for samples of different properties, particle sizes, and moisture to ensure the quality of data during subsequent testing. Finally, the spectral information and volatile matter information of the sample are collected, and a neural network model is used to accurately and objectively determine whether the ore is solid waste, which can improve the degree of automation, accuracy and stability of ore solid waste inspection.

[0138] The belt-type online ore solid waste inspection system and method provided by the embodiment of the present invention can replace traditional manual work and implement 24-hour inspection of ore unloaded in the form of belts. When the entire system is running, the system operator sends the inspection task to the equipment from the control computer. After the equipment is started, Figure 5 The test is carried out according to the process shown in the figure. No human participation is required during the normal test process.

[0139] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0140] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant description of other embodiments.

[0141] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present invention.

[0142] In the embodiments provided by the present invention, it should be understood that the disclosed devices / terminals and methods can be implemented in other ways. For example, the device / terminal embodiments described above are merely illustrative. For example, the division of the modules or units is merely a logical functional division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interface, indirect coupling or communication connection of devices or units, and can be electrical, mechanical, or other forms.

[0143] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0144] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0145] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, it can implement the steps of the above-mentioned various belt-type online ore solid waste inspection method embodiments. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0146] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A belt-type online ore solid waste inspection system, characterized in that: include: A sampling module is used to sample the ore on the conveyor belt to obtain ore samples; A sample preparation module, used for preparing the ore sample into a standardized sample; A collection module, used for collecting spectral information and volatile information of the standardized sample; The identification module is used to process the spectral information and the volatile information based on a neural network model to determine whether the ore corresponding to the standardized sample is solid waste.

2. The belt-type online ore solid waste inspection system according to claim 1 is characterized in that: The sampling module comprises a sampling port and a telescopic arm; the opening direction of the sampling port is opposite to the moving direction of the ore, and a weighing unit is arranged inside; The sampling module is specifically used for: The sampling port is driven into the belt area by the telescopic arm; Based on the weighing value of the weighing unit, it is determined whether a sufficient amount of sample enters the sampling port, and if a sufficient amount of sample enters the sampling port, the telescopic arm is retracted.

3. The belt-type online ore solid waste inspection system according to claim 2 is characterized in that: The sampling module is also used for: Before the sampling port is extended into the belt area by the telescopic arm, sampling is performed on the belt sampling device. If no sample exists on the belt sampling device, the sampling port is extended into the belt area by the telescopic arm to perform sampling.

4. The belt-type online ore solid waste inspection system according to claim 2 is characterized in that: The sampling module is specifically used for: Calculate the difference between the time when sampling starts and the time when the sample enters the sampling module as the sampling time; Adjusting a preset sampling interval based on the sampling time; wherein the preset sampling interval is determined based on a belt transport rate; Based on the time when the current sample enters the sampling module and the adjusted sampling interval, the time to start the next sampling is determined.

5. The belt-type online ore solid waste inspection system according to claim 1 is characterized in that: The sample preparation module comprises a drying unit, a crushing unit and a tablet pressing unit connected in sequence; The sample preparation module is specifically used for: Drying the ore sample by the drying unit to obtain a dry sample; The dried sample is crushed and mixed by the crushing unit to obtain a crushed sample; The crushed sample is tableted by the tableting unit to obtain a standardized sample.

6. The belt-type online ore solid waste inspection system according to claim 5 is characterized in that: The drying unit further comprises an air outlet pipe, the air outlet pipe is connected to the collection module, and the collection module comprises a gas detection unit; The acquisition module is specifically used for: The gas in the gas outlet pipe is collected and analyzed to obtain the volatile matter information of the standardized sample.

7. The belt-type online ore solid waste inspection system according to claim 1 is characterized in that: The acquisition module includes a near infrared unit and a LIBS unit; The acquisition module is specifically used for: Collecting the near infrared spectrum of the standardized sample by the near infrared unit; The LIBS spectrum of the standardized sample is collected by the LIBS unit.

8. The belt-type online ore solid waste inspection system according to claim 7 is characterized in that: The identification module is specifically used for: Based on the principal component analysis method, the dimension of the near infrared spectrum is reduced and input into a trained KNN neural network to obtain a first classification result of the standardized sample; Inputting the LIBS spectrum into a trained CNN neural network to obtain a second classification result of the standardized sample; The first classification result, the second classification result and the volatile matter information are input into a trained SVM classifier to obtain a solid waste detection result of the standardized sample.

9. A belt-based online ore solid waste inspection method, characterized in that: include: The sampling module samples the ore on the conveyor belt to obtain ore samples; The sample preparation module prepares the ore sample into a standardized sample; The acquisition module acquires the spectrum information and volatile information of the standardized sample; The identification module processes the spectral information and the volatile matter information based on a neural network model to determine whether the ore corresponding to the standardized sample is solid waste.

10. The belt-based on-line ore solid waste screening method according to claim 9, characterized in that: The sampling module comprises a sampling port and a telescopic arm; the opening direction of the sampling port is opposite to the moving direction of the ore, and a weighing unit is arranged inside; The sampling module samples the ore on the conveyor belt to obtain an ore sample, including: The sampling module drives the sampling port to extend into the belt area through the telescopic arm; The sampling module determines whether a sufficient amount of sample enters the sampling port based on the weighing value of the weighing unit, and retracts the telescopic arm if a sufficient amount of sample enters the sampling port.

Images