Breaking station ore inlet lump ore analysis method and alarm system

Abstract

The invention provides a crushing station ore inlet lump ore analysis method and an alarm system. According to the method, a radar sensor is arranged near an ore unloading position of a truck to detect entering and exiting of an ore unloading car; a light supplementing lamp installed on a pan-tilt of the pan-tilt camera is used for automatically supplementing light for the car hopper of the mine unloading car; real-time detection is conducted on the conditions of a mine unloading vehicle and a discharging opening through a pan-tilt camera, and real-time mine pouring images of the crushing station are obtained and transmitted to a server; the server analyzes and obtains ore granularity data by analyzing truck unloading real-time image information collected by the pan-tilt camera, and further calculates the equivalent elliptical diameter of the ore; if the selected particle size result is greater than an alarm threshold value, the server sends an alarm signal to an edge controller; the edge controller controls the audible and visual alarm to give an alarm; the audible and visual alarm is arranged in front of the side of the ore unloading car and used for giving an alarm for large ore conditions; and the server stores the alarm message into a database, and provides alarm data for an upper monitoring system at the same time.

Description

Technical Field

[0001] The present invention relates to the technical field of mine crushing. Specifically, it particularly relates to a method for analyzing large-sized ore at the ore inlet of a crushing station and an alarm system. Background Art

[0002] During the ore unloading process of the ore unloading truck in the rough crushing process section of the mine, the situation of blockage of large-sized ore at the feeding opening of the crusher often occurs. This situation will cause production to stagnate and seriously affect the operating efficiency of the equipment. At present, most of the large-sized ore in the rough crushing and ore unloading is manually monitored and processed afterwards, with low efficiency. At the same time, the data cannot be traced back, and the superior process cannot be guided. Summary of the Invention

[0003] In view of the technical problems mentioned in the above background art, a method for analyzing large-sized ore at the ore inlet of a crushing station and an alarm system are provided.

[0004] The technical means adopted by the present invention are as follows:

[0005] A method for analyzing large-sized ore at the ore inlet of a crushing station, comprising the following steps:

[0006] Step 1: Collect real-time image information and position information of the truck unloading ore, and real-time identify the motion data of the truck hopper. Transmit the collected motion data to the control pan-tilt through the Ethernet interface; adjust the collection angle according to the feedback data.

[0007] Step 2: Supplement the light; supplement the collected light through the supplementary light lamp set on the pan-tilt.

[0008] Step 3: When the truck arrives and starts to unload ore, obtain the contour surface area of the ore based on the acquired real-time image information, and based on the area of this irregular figure, obtain the ore particle size data for calculating the equivalent particle diameter of the ore.

[0009] Step 4: After obtaining the ore particle size data, track the movement trajectory of the ore by the StrongSORT algorithm for multi-object tracking; first, use the Mask R-CNN neural network model to detect the ore and extract relevant features. For known tracking objects, perform Kalman filter prediction in the next frame to estimate the new position and speed; then use the Hungarian algorithm to match the predicted trajectory with the detection result of the current frame. If the Mahalanobis distance is less than the preset threshold, it is matched as the same target; then update the Kalman filter prediction in the next frame until the ore leaves the detection area.

[0010] Step 5: Set the alarm threshold to 1 meter by default, which can be set through the analysis software interface, with a setting range of 0.5 - 2m; when the ore particle size calculated by the equivalent ellipse diameter method is greater than the alarm threshold, an alarm signal is sent to the edge controller, and the edge controller controls the audible and visual alarm to alarm for large ore pieces.

[0011] Further, the real-time image of the truck discharging is collected by a pan-tilt camera.

[0012] Further, the position information is obtained through a radar sensor; the radar sensor is set at the edge of the truck discharging position to detect the position of the ore unloading truck.

[0013] Further, in step 3, the obtained real-time image information needs to be binarized before obtaining the contour surface area of the ore.

[0014] Further, in step 3, the Mask R-CNN neural network model is used to infer and analyze the original ore image; the ore contour is obtained according to the mask and bounding box results output by the model, and two different particle size output results are set;

[0015] When preventing the crushing port from being blocked, the length and width of the minimum circumscribed rectangle of the ore are calculated according to the contour, and then the long side value is output as the particle size data;

[0016] When counting the particle size distribution, the equivalent diameter of the ore is calculated by the equivalent ellipse diameter method, and the formula is:

[0017] d = ([S(a + b)]) / π,

[0018] where d represents the equivalent ellipse diameter; S represents the contour surface area of the ore; a represents the long axis of the ellipse, that is, the long side of the minimum circumscribed rectangle of the ore; b represents the short axis of the ellipse, that is, the short side of the minimum circumscribed rectangle; π is taken as 3.14.

[0019] Further, in step 2, the fill light is automatically turned on when the low illuminance is lower than 1 lux; the fill light rotates synchronously with the pan-tilt.

[0020] The present invention also includes a large ore piece analysis and alarm system at the ore inlet of the crushing station, including: a pan-tilt camera, a server, a radar sensor, an edge controller, an audible and visual alarm, and a fill light;

[0021] The pan-tilt camera conducts real-time detection on the ore unloading vehicle and the feeding port situation;

[0022] The server analyzes the real-time image information of the truck unloading collected by the pan-tilt camera to obtain ore particle size data, and then calculates the equivalent elliptical diameter of the ore. If the selected particle size result is greater than the alarm threshold, the server sends an alarm signal to the edge controller; the server stores the alarm message in the database and provides the alarm data to the upper monitoring system at the same time.

[0023] The radar sensor is set near the truck ore unloading position to detect the entry and exit of the ore unloading vehicle.

[0024] The edge controller controls the sound and light alarm to give an alarm.

[0025] The sound and light alarm is set in front of the side of the ore unloading vehicle to give an alarm prompt for the situation of large pieces of ore.

[0026] The supplementary light is set on the pan of the pan-tilt camera and is turned on when the low illuminance is lower than lux.

[0027] Further, the edge controller is set in the edge control box; the edge control box is set near the truck ore unloading port.

[0028] Further, the edge controller is connected to the radar switch and the sound and light alarm through digital input / output signals.

[0029] Further, the pan-tilt camera, the server, and the edge controller are connected through an Ethernet switch to realize data communication.

[0030] Compared with the prior art, the present invention has the following advantages:

[0031] The detection effect of this system is stable and reliable, and it can replace manual work to work continuously for 24 hours. Among them, the pan-tilt camera can flexibly adjust the viewing angle according to the vehicle position; the image recognition model adopts a deep learning neural network model to realize end-to-end inference, and has stronger robustness compared with the traditional system algorithm. The sound and light alarm can timely remind the driver to stop feeding in advance and minimize the loss. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0033] Figure 1 It is a schematic diagram of the overall system of the present invention.

[0034] Among them, 1 is a pan-tilt camera; 2 is a server; 3 is a radar sensor; 4 is an edge controller; 5 is an audible and visual alarm; 6 is a fill light. Specific embodiments

[0035] In order to enable those skilled in the art of this technology to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0036] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data used in appropriate cases can be interchanged so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0037] As Figure 1 shown, a method for analyzing large pieces of ore at the ore inlet of a crushing station according to the present invention includes the following steps:

[0038] Step 1: Collect real-time image information and position information of the truck unloading, and identify the motion data of the truck hopper in real time. Transmit the collected motion data to the control pan-tilt through an Ethernet interface; adjust the collection angle according to the feedback data. The real-time image of the truck unloading is collected by the pan-tilt camera. The position information is obtained through the radar sensor; the radar sensor is set at the edge of the truck unloading position to detect the position of the ore unloading truck.

[0039] Step 2: Supplement the light; supplement the collected light through the fill light set on the pan-tilt; the fill light automatically turns on when the low illuminance is lower than 1 lux; the fill light rotates synchronously with the pan-tilt.

[0040] Step 3: When the truck arrives and starts unloading ore, before obtaining the contour surface area of the ore, it is necessary to perform binary processing on the acquired real-time image information. Obtain the contour surface area of the ore based on the acquired real-time image information, and based on the area of this irregular figure, obtain the ore particle size data for calculating the equivalent particle diameter of the ore; use the Mask R-CNN neural network model to perform inference and analysis on the original ore image; obtain the ore contour according to the mask and bounding box results output by the model, and set two different particle size output results;

[0041] When preventing blockage of the crushing opening, calculate the length and width of the minimum circumscribed rectangle of the ore according to the contour, and then output the long side value as the particle size data;

[0042] When counting the particle size distribution, use the equivalent ellipse diameter method to calculate the equivalent diameter of the ore. The formula is:

[0043] d = ([S(a + b)]) / π,

[0044] where d represents the equivalent ellipse diameter; S represents the contour surface area of the ore; a represents the major axis of the ellipse, that is, the long side of the minimum circumscribed rectangle of the ore; b represents the minor axis of the ellipse, that is, the short side of the minimum circumscribed rectangle; π is taken as 3.14.

[0045] Step 4: After obtaining the ore particle size data, use the StrongSORT algorithm to multi-target track the movement trajectory of the ore; first use the Mask R-CNN neural network model to detect the ore and extract relevant features. For known tracking objects, perform Kalman filter prediction in the next frame to estimate the new position and speed; then use the Hungarian algorithm to match the predicted trajectory with the detection results of the current frame. If the Mahalanobis distance is less than the preset threshold, it is matched as the same target; then update the Kalman filter prediction in the next frame until the ore leaves the detection area;

[0046] Step 5: Set the alarm threshold to 1 meter by default, and it can be set through the analysis software interface. The setting range is 0.5 - 2m; when the ore particle size calculated by the equivalent ellipse diameter method is greater than the alarm threshold, send an alarm signal to the edge controller, and the edge controller controls the sound and light alarm to alarm for large pieces of ore.

[0047] The present invention also includes a large piece of ore analysis and alarm system at the ore inlet of the crushing station, applying the above method, including: a pan-tilt camera 1, a server 2, a radar sensor 3, an edge controller 4, a sound and light alarm 5, and a fill light 6;

[0048] In this application, the pan-tilt camera 1 performs real-time detection on the ore unloading truck and the situation of the feeding port;

[0049] In this application, the server 2 analyzes the real-time image information of the truck unloading collected by the pan-tilt camera 1 to obtain the ore particle size data, and then calculates the equivalent elliptical diameter of the ore. If the selected particle size result is greater than the alarm threshold, the server 2 sends an alarm signal to the edge controller 4; the server 2 stores the alarm message in the database and provides the alarm data to the upper-level monitoring system at the same time.

[0050] In this application, the radar sensor 3 is arranged near the truck ore unloading position to detect the entry and exit of the ore unloading vehicle.

[0051] In this application, the edge controller 4 controls the sound and light alarm 5 to give an alarm; the edge controller 4 is arranged in the edge control box; the edge control box is arranged near the truck ore unloading port. The edge controller 4 is connected to the radar switch and the sound and light alarm through digital input signals.

[0052] In this application, the sound and light alarm 5 is arranged in front of the side of the ore unloading vehicle to give an alarm prompt for the situation of large pieces of ore.

[0053] In this application, the fill light 6 is arranged on the pan-tilt of the pan-tilt camera 1 and is turned on when the low illuminance is lower than 1 lux.

[0054] Preferably, the pan-tilt camera 1, the server 2 and the edge controller 4 are connected through an Ethernet switch to realize data communication. The present invention provides a method for analyzing large pieces of ore at the ore inlet of a crushing station, which includes: arranging a radar sensor near the truck ore unloading position to detect the entry and exit of the ore unloading vehicle; automatically filling light for the hopper of the ore unloading vehicle through the fill light installed on the pan-tilt of the pan-tilt camera; detecting the situation of the ore unloading vehicle and the blanking port in real time through the pan-tilt camera, obtaining the real-time image of the ore unloading at the crushing station and transmitting it to the server; the server analyzes the real-time image information of the truck unloading collected by the pan-tilt camera to obtain the ore particle size data, and then calculates the equivalent elliptical diameter of the ore; if the selected particle size result is greater than the alarm threshold, the server sends an alarm signal to the edge controller; the edge controller controls the sound and light alarm to give an alarm; the sound and light alarm is arranged in front of the side of the ore unloading vehicle to give an alarm prompt for the situation of large pieces of ore; the server stores the alarm message in the database and provides the alarm data to the upper-level monitoring system at the same time; the detection effect of this system is stable and reliable, it can work continuously for 24 hours instead of manual labor, and has the advantages of high production efficiency and low operation cost.

[0055] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages and disadvantages of the embodiments.

[0056] In the above embodiments of the present invention, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0057] In several embodiments provided in the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units can be a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling, direct coupling, or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of units or modules can be in an electrical or other form.

[0058] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0059] In addition, in each embodiment of the present invention, the functional units can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above-mentioned integrated units can be implemented in the form of hardware or in the form of software functional units.

[0060] If the above-mentioned integrated 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 such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in each embodiment of the present invention. The foregoing storage medium includes: USB flash drives, read-only memories (ROMs), random access memories (RAMs), mobile hard disks, magnetic disks, or optical disks, and other various media that can store program codes.

[0061] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions described in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of each embodiment of the present invention.

Claims

1. A method for analyzing bulk ore at the entrance of a crushing station, characterized in that: The following steps are involved: Step 1: Collect real-time image information and location information of the truck unloading, identify the motion data of the truck bucket in real time, and transmit the collected motion data to the control pan / tilt via the Ethernet interface; adjust the collection angle according to the feedback data; Step 2: Supplement the light; supplement the collected light by a fill light arranged on the pan / tilt; Step 3: When the truck arrives and starts to unload the ore, the contour surface area of ​​the ore is obtained according to the real-time image information obtained, and the ore particle size data is obtained based on the irregular pattern area, which is used to calculate the equivalent particle size of the ore; Step 4: After obtaining the ore particle size data, the StrongSORT algorithm is used to track the movement trajectory of the ore. First, the Mask R-CNN neural network model is used to detect the ore and extract relevant features. For known tracking objects, Kalman filter prediction is performed in the next frame to estimate the new position and speed. The Hungarian algorithm is then used to match the predicted trajectory with the detection result of the current frame. If the Mahalanobis distance is less than the preset threshold, they are matched as the same target. Then, the Kalman filter prediction is updated in the next frame until the ore leaves the detection area. Step 5: Set the alarm threshold to 1 meter by default, and it can be set through the analysis software interface, with a setting range of 0.5-2m; when the ore particle size calculated by the equivalent ellipse diameter method is larger than the alarm threshold, an alarm signal is sent to the edge controller, and the edge controller controls the sound and light alarm to alarm for large pieces of ore.

2. A method for analyzing bulk ore at the entrance of a crushing station according to claim 1, characterized in that: The real-time image of truck unloading is collected by a pan-tilt camera.

3. The method for analyzing bulk ore at the entrance of a crushing station according to claim 1, characterized in that: The position information is acquired through a radar sensor; the radar sensor is arranged at the edge of the truck unloading position to detect the position of the unloading truck.

4. The method for analyzing bulk ore at the entrance of a crushing station according to claim 1, characterized in that: In step 3, the acquired real-time image information needs to be binarized before obtaining the contour surface area of ​​the ore.

5. The method for analyzing bulk ore at the entrance of a crushing station according to claim 1, characterized in that: In step 3, the Mask R-CNN neural network model is used to reason and analyze the original ore image; the ore contour is obtained according to the mask and bounding box results output by the model, and two different particle size output results are set; To prevent the crushing port from being blocked, the length and width of the minimum circumscribed rectangle of the ore are calculated according to the contour, and then the long side value is output as the particle size data; When calculating the particle size distribution, the equivalent ellipse diameter method is used to calculate the equivalent diameter of the ore. The formula is: d=([S(a+b)]) / π, Among them, d represents the equivalent ellipse diameter; S represents the contour surface area of ​​the ore; a represents the major axis of the ellipse, that is, the long side of the minimum circumscribed rectangle of the ore; b represents the minor axis of the ellipse, that is, the short side of the minimum circumscribed rectangle; π is taken as 3.

14.

6. A method for analyzing bulk ore at the entrance of a crushing station according to claim 1, characterized in that: In the step 2, the fill light is automatically turned on when the illumination is lower than 1 lux; the fill light rotates synchronously with the gimbal.

7. A large ore analysis and alarm system for a crushing station entrance, using the method described in any one of claims 1 to 5, characterized in that: include: PTZ camera (1), server (2), radar sensor (3), edge controller (4), sound and light alarm (5) and fill light (6); The pan / tilt camera (1) performs real-time detection of the conditions of the unloading vehicle and the material discharge port; The server (2) obtains ore particle size data by analyzing the real-time image information of truck unloading collected by the pan-tilt camera (1), and then calculates the equivalent elliptical diameter of the ore. If the selected particle size result is greater than the alarm threshold, the server (2) sends an alarm signal to the edge controller (4); the server (2) stores the alarm message in a database and provides the alarm data to an upper-level monitoring system; The radar sensor (3) is arranged near the unloading position of the truck to detect the entry and exit of the unloading truck; The edge controller (4) controls the sound and light alarm (5) to sound an alarm; The sound and light alarm (5) is arranged at the front side of the unloading vehicle to give an alarm for large pieces of ore; The fill light (6) is arranged on the pan / tilt of the pan / tilt camera (1) and is turned on when the illumination is low and lower than 1 lux.

8. The large ore analysis and alarm system for the crushing station entrance according to claim 6 is characterized in that: The edge controller (4) is arranged in an edge control box; the edge control box is arranged near the ore unloading port of the truck.

9. A large ore analysis alarm system for a crushing station mine entrance according to claim 6 or 7, characterized in that: The edge controller (4) is connected to the radar switch and the sound and light alarm via a switch signal.

10. The large ore analysis and alarm system for the crushing station entrance according to claim 6 is characterized in that: The pan-tilt camera (1), the server (2) and the edge controller (4) are connected via an Ethernet switch to achieve data communication.

Images