Mechanical rock breaking intelligent dust removal system and dust removal method

Abstract

This invention relates to the field of excavator dust control technology, specifically to an intelligent dust control system and method for mechanical rock breaking. A laser module emits a laser beam towards the working area of ​​the excavator's actuators. When dust is generated in the working area, a vision sensor observes the reflected laser beam. Based on the length and brightness of the laser beam, the dust range and concentration are determined, generating a spray parameter combination for the spray module. This spray parameter combination is then sent to the spray module, which sprays water mist towards the rock breaking face where dust is generated. The water mist combines with the dust particles to suppress the dust. The entire process requires no manual intervention, achieving good dust suppression while improving operator safety and reducing labor costs.

Description

Technical Field

[0001] This invention relates to the field of dust removal technology for excavators, specifically to an intelligent dust removal system and method for mechanical rock breaking. Background Technology

[0002] In the mechanical excavation processes of hydropower projects, mining projects, and transportation road projects, mechanical rock breaking methods are increasingly being used. This method has significant advantages over the traditional drill and blast method in ensuring excavation efficiency and reducing disturbance to the surrounding rock. Mechanical rock breaking mainly employs hydraulic breaking, or uses excavators equipped with boom booms or hydraulic breakers to break rocks in tunnels or surrounding areas.

[0003] However, mechanical impact or rock excavation generates a lot of dust. In order to enable the driver to see the working face clearly, the current measure is to have a worker stand near the working face and use a water pipe to remove the dust. However, this method has two significant drawbacks: on the one hand, it increases labor costs; on the other hand, during mechanical rock breaking, there will inevitably be flying debris, which can easily cause personal injury. Summary of the Invention

[0004] The main objective of this invention is to provide a mechanical rock-breaking intelligent dust removal system and method to solve the technical problems of poor safety and high labor costs of manual dust removal at the work surface in the prior art.

[0005] To achieve the above objectives, this invention provides an intelligent dust removal system for mechanical rock breaking, applied to an excavator, comprising a laser module, a sensor module, a control module, and a spraying module; wherein;

[0006] The laser module is fixed to the actuating component of the excavator, and the laser beam emitted by the laser module is directed towards the rock-breaking working face;

[0007] The sensor module is mounted on the excavator. The sensor module includes a vision sensor, and the acquisition direction of the vision sensor is set at an angle to the laser beam.

[0008] The spraying module is located on both sides of the actuating component, and the spraying direction of the spraying module is towards the rock breaking working face;

[0009] The control module is connected to the laser module, the sensor module, and the spray module, respectively.

[0010] Furthermore, the laser module includes a laser emitter and a detachable connector, the laser emitter being detachably connected to the detachable connector, and the detachable connector being mounted on the actuating component of the excavator.

[0011] More preferably, the detachable connector includes a base, an operating component, a magnet, a buffer unit, and a sliding bracket. The magnet is movably installed in the base, the operating component is installed on the base, and the operating component is connected to the magnet to control the movement of the magnet in the base to achieve attraction and locking or unlocking. The sliding bracket is slidably connected to the base, and the buffer unit is connected between the sliding bracket and the base. The laser emitter is installed on the sliding bracket.

[0012] More preferably, the buffer unit includes an elastic element, a piston, a rod, and a control valve, and the seat is provided with a slide groove, and the sliding frame is slidably connected in the slide groove;

[0013] The seat body is provided with a damping cavity, the piston is slidably connected in the damping cavity, the first end of the rod is fixedly connected to the piston, and the second end of the rod passes through the damping cavity and is fixedly connected to the sliding frame.

[0014] The piston divides the damping chamber into a rod chamber and a rodless chamber. The seat is also provided with a first channel and a second channel. The first channel connects the rodless chamber to the outside, and the second channel connects the rod chamber to the outside.

[0015] The control valve is slidably connected to the seat body, and the control valve intersects with both the first channel and the second channel to control the size of the first channel and the second channel;

[0016] The elastic element is arranged on the side of the sliding frame away from the rod, with one end of the elastic element abutting against the seat and the other end of the elastic element abutting against the sliding frame.

[0017] More preferably, the control valve includes a valve stem and a valve cap, the seat is provided with a valve hole, the valve hole intersects with both the first channel and the second channel, the valve cap is coaxially fixedly connected to one end of the valve stem, and the valve stem is threadedly connected to the valve hole; the valve stem includes a first conical surface and a second conical surface, the first conical surface is disposed at a position corresponding to the first channel to adjust the size of the flow cross-sectional area of ​​the first channel, and the second conical surface is disposed at a position corresponding to the second channel to adjust the size of the flow cross-sectional area of ​​the second channel.

[0018] This invention also provides a mechanical rock-breaking intelligent dust removal method, applied to the mechanical rock-breaking intelligent dust removal system described above, comprising the following steps:

[0019] S1. Collect dust characteristics data, environmental parameters, and work intensity data during the mechanical rock breaking operation. Preprocess the collected data to obtain a real-time data matrix. The dust characteristics data include dust concentration, dust range, and average dust particle size. The environmental parameters include ambient wind speed, ambient humidity, and work surface humidity. The work intensity data includes rock breaking output frequency and hydraulic system pressure.

[0020] S2. Obtain the calculation weight matching model, identify the current construction scenario, and obtain the calculation weight matrix corresponding to the current construction scenario based on the calculation weight matching model; wherein, the calculation weight matching model contains the mapping relationship between the construction scenario and the calculation weights of each parameter in the real-time data matrix;

[0021] S3. Obtain the spray parameter decision model, input the real-time data matrix and the calculated weight matrix into the spray parameter decision model to obtain the spray parameter combination; wherein, the spray parameters include spray flow rate, droplet size, spray angle and spray frequency;

[0022] S4. Control the operation of the spray module according to the spray parameter combination, and collect the real-time dust concentration after waiting for a preset time.

[0023] S5. Determine whether the real-time dust concentration is less than or equal to the preset dust concentration threshold; if yes, maintain the operation of the spray module and return to step S4; if no, obtain the preset correction amount of the spray parameter combination, correct the spray parameter combination according to the preset correction amount, and then return to step S4.

[0024] More preferably, step S2 specifically includes the following steps:

[0025] A scene classifier is obtained to collect the core identification features of the current construction scene. Based on the core identification features, the scene classifier identifies the category of the current construction scene. The scene classifier classifies mechanical rock breaking construction scenes into tunnel scenes, open-pit scenes, and foundation pit scenes. The scene classifier uses three parameters—wind speed stability, operation enclosure, and working face slope—as the core identification features for scene classification.

[0026] Obtain the weight matching model and obtain the weight matrix corresponding to the current construction scenario based on the category of the current construction scenario; wherein, the weight matrix is ​​a preset initial weight matrix, and the initial weights in the initial weight matrix are set according to the degree of influence of dust characteristics data, environmental parameters and work intensity data on the spraying effect under different scenarios.

[0027] More preferably, after step S5, the following steps are also included:

[0028] Obtain the real-time data matrix after spraying, determine the rate of change of each parameter in the real-time data matrix per unit time, and determine whether the rate of change of each parameter per unit time is greater than a first preset threshold.

[0029] If the rate of change per unit time is greater than the first preset threshold, the real-time data is determined to be a mutation data, and it is determined whether there is any one or more mutation data in the real-time data matrix after spraying.

[0030] If there is one or more abrupt changes in the real-time data matrix after spraying, the initial weights in the initial weight matrix corresponding to the abrupt changes are increased by a preset correction step size, and the process returns to step S3.

[0031] More preferably, after step S5, the following steps are also included:

[0032] Obtain the real-time data matrix after spraying, determine the deviation of each parameter in the real-time data matrix from the average value of each parameter under the same construction scenario, and determine whether the deviation is greater than a second preset threshold.

[0033] If the deviation is greater than the second preset threshold, the real-time data is determined to be abnormal deviation data, and it is determined whether there is any one or more abnormal deviation data in the real-time data matrix after spraying.

[0034] If any one or more deviation abnormal data exist in the real-time data matrix after spraying, the initial weight matrix of the open-air scene is obtained, the initial weight ratio of the open-air scene is obtained based on the initial weight matrix of the open-air scene, the initial weight of the initial weight matrix of the current construction scene is corrected according to the initial weight ratio with a preset correction step size, and the process returns to step S3.

[0035] More preferably, step S3 specifically includes the following steps:

[0036] A spray parameter decision model is obtained, which includes a random forest model and a feature attention layer, wherein the feature attention layer is embedded between the input layer and the decision tree training layer of the random forest model;

[0037] The real-time data matrix and the calculated weight matrix are input to the input layer. The feature attention layer matches weight coefficients according to the parameters of the calculated weight matrix and the real-time data matrix to obtain a weighted feature vector.

[0038] The feature vector is input into each decision tree of the random forest model for independent training. Each decision tree outputs its own parameter prediction results. The parameter prediction results of all decision trees are merged by weighted voting to obtain the final spray parameter combination.

[0039] Compared with the prior art, the present invention has the following beneficial effects:

[0040] This invention uses a laser module to emit a laser beam towards the working area of ​​the excavator's actuators. When dust is generated in the working area, a vision sensor observes the reflected laser beam. Based on the length and brightness of the laser beam, the dust range and concentration are determined, generating a set of spraying parameters for the spraying module. These parameters are then sent to the spraying module, which sprays water mist towards the dust-generating rock-breaking face. The water mist combines with the dust particles to suppress the dust. Longer and brighter laser beams result in more water being sprayed, promoting rapid dust settling. Shorter and dimmer laser beams result in less water being sprayed, achieving dust suppression while conserving water and energy. The entire process requires no manual intervention, improving operator safety while achieving effective dust suppression and reducing labor costs.

[0041] The dust removal method provided by this invention collects multi-dimensional data related to dust during operations, providing a comprehensive consideration of multi-dimensional parameter changes for subsequent decision-making. It utilizes a computational weight matching model that maps scene and parameter weights to adapt weight allocation to the current construction scenario, improving decision-making targeting. By integrating real-time data matrices and computational weight matrices through a spray parameter decision model, it outputs adapted parameter combinations, achieving precise parameter matching to working conditions. Furthermore, it dynamically adjusts the spray parameter combinations based on real-time dust concentration after spraying and preset correction values, ensuring dynamic adaptability of dust removal control. This invention integrates scene-based weight matching and dynamic parameter correction into a multi-dimensional data-driven spray decision-making process, achieving intelligent adaptive dust removal control for different mechanical rock breaking conditions, improving dust removal efficiency and control accuracy. Attached Figure Description

[0042] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the structures shown in these drawings without creative effort.

[0043] Figure 1 This is a first-view schematic diagram of the overall structure of an embodiment of the present invention installed on an excavator;

[0044] Figure 2 This is a second-view schematic diagram of the overall structure of an embodiment of the present invention installed on an excavator;

[0045] Figure 3This is a partially enlarged schematic diagram of a laser module installed on an excavator actuator in one embodiment of the present invention;

[0046] Figure 4 This is a schematic diagram of the internal structure of the magnetic connector in one embodiment of the present invention;

[0047] Figure 5 for Figure 4 Enlarged view of point A in the middle;

[0048] Figure 6 This is a schematic diagram of the overall structure of the magnetic connector in one embodiment of the present invention;

[0049] Figure 7 This is a schematic flowchart of a mechanical rock-breaking intelligent dust removal method according to an embodiment of the present invention.

[0050] The components include: 1. Laser module; 11. Laser emitter; 12. Magnetic connector; 121. Seat body; 1211. Slide groove; 1212. Damping cavity; 1213. First channel; 1214. Second channel; 122. Operating component; 123. Magnet; 124. Buffer unit; 1241. Elastic component; 1242. Piston; 1243. Rod; 1244. Control valve; 1245. Valve stem; 1246. Valve cap; 1247. First conical surface; 1248. Second conical surface; 125. Sliding frame; 126. Guide rod; 2. Vision sensor; 3. Spray module; 31. Pumping unit; 311. Water tank; 312. Water pump; 32. Water supply pipe; 321. Fixed rigid pipe; 322. Connecting flexible hose; 323. Flexible positioning pipe; 33. Spray head; 34. Solenoid valve.

[0051] The objectives, features, and advantages of this invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0052] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0053] 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 a part of the embodiments of the present invention, and not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0054] It should be noted that all directional indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present invention are only used to explain the relative positional relationship and movement of each component in a certain specific posture (as shown in the figure). If the specific posture changes, the directional indication will also change accordingly.

[0055] Furthermore, the use of terms such as "first" and "second" in this invention is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined with "first" or "second" may explicitly or implicitly include at least one of that feature. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. When the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed by this invention.

[0056] When an excavator uses a hydraulic breaker to work on a tunnel face, dust is generated at the breaker location. This dust obstructs the operator's view, making it difficult to see the work area and affecting the operation. Research has shown that if a laser is used to irradiate the dust, the laser beam will undergo diffuse reflection at the dust location, making the diffusely reflected segments of the laser beam clearly observable. It should be noted that when there is no dust in the air, laser irradiation will not produce diffuse reflection, and the laser beam will not be observable. The length of the laser beam can be used to determine the extent of dust generation; a longer laser beam indicates a larger dust area, and vice versa. The brightness of the laser beam can be used to determine the concentration of dust; a brighter laser beam indicates more diffusely reflected light and a higher concentration of dust particles in the air. Based on this discovery, the inventors designed the following intelligent dust removal system for mechanical rock breaking.

[0057] Please see Figures 1 to 6 This embodiment provides a mechanical rock-breaking intelligent dust removal system applied to an excavator, including a laser module 1, a sensor module, a control module, and a spraying module 3; wherein;

[0058] The laser module 1 is fixed to the actuating component of the excavator, and the laser beam emitted by the laser module 1 is directed towards the rock-breaking working face;

[0059] The sensor module is mounted on the excavator. The sensor module includes a vision sensor 2, and the acquisition direction of the vision sensor 2 is set at an angle to the laser beam.

[0060] The spraying module 3 is disposed on both sides of the actuating component, and the spraying direction of the spraying module 3 is towards the rock breaking working face;

[0061] The control module is connected to the laser module 1, the sensor module and the spray module 3 respectively.

[0062] In this embodiment, laser module 1 emits a laser beam towards the work area operated by the excavator's actuators. When dust occurs in the work area, vision sensor 2 observes the reflected laser beam. Based on the length and brightness of the laser beam, the dust range and concentration are determined, thereby generating a combination of spraying parameters for spray module 3. This combination of parameters is then sent to spray module 3, which sprays water mist towards the rock-breaking face where dust is generated. The water mist combines with dust particles to suppress dust. When the laser beam is longer and brighter, spray module 3 sprays more water to help the dust settle quickly; conversely, when the laser beam is shorter and dimmer, spray module 3 sprays less water, achieving dust suppression while conserving water and energy. The entire process requires no manual intervention, improving operator safety while achieving good dust suppression and reducing labor costs.

[0063] It is worth noting that the direction of the laser beam forms an angle with the direction captured by the vision sensor 2, and this angle is controlled between 45 degrees and 90 degrees (when the angle is 90 degrees, the length of the laser beam captured by the vision sensor 2 is equal to the actual length of the laser beam; the smaller the angle, the smaller the length of the laser beam captured by the vision sensor 2 is relative to the actual length of the laser beam). The spray module 3 adopts an intermittent spraying method. It can be seen that by using intermittent spraying, on the one hand, it can minimize the impact on the operator's line of sight during the spraying process, and on the other hand, it can prevent continuous spraying from causing water diffusion in the laser beam, thus preventing the spray module 3 from spraying incorrectly.

[0064] During use, it was found that the laser module 1 is a relatively precision part, while the excavator's actuators generate strong vibrations during operation, which can easily damage the laser module 1. Furthermore, when the excavator is working on hard rock, the actuators typically use a hydraulic breaker, while for softer soil and rock layers, a bucket or hook arm is used. Therefore, the spray module 3 and laser module 1, which are connected to the actuators, require frequent disassembly and reassembly. Based on this, the following further improvements were made to this embodiment.

[0065] In this embodiment, the laser module 1 further includes a laser emitter 11 and a detachable connector. The laser emitter 11 is detachably connected to the detachable connector, which is mounted on the excavator's actuator. Specifically, in this embodiment, the detachable connector is a magnetic connector 12, and the laser emitter 11 is an infrared laser emitter. Red light has higher visibility, which is beneficial for the vision sensor 2 to collect images.

[0066] It is understood that the laser emitter 11 is used to emit a laser beam. In this embodiment, the laser beam is a fixed infrared laser beam. The laser beam irradiates the rock-breaking working face, and when dust is generated at the construction site, a bright laser beam will appear at the dust location. The magnetic connector 12 is magnetic. The excavator's actuator is made of steel. The laser emitter 11 can be quickly and detachably connected to the excavator's actuator via the magnetic connector 12. In this application, the excavator's actuator is a hydraulic breaker, and the laser emitter 11 can be quickly and detachably connected to the side wall of the hydraulic breaker via the magnetic connector; thus, the laser emitter 11 can be quickly installed and removed. When it is necessary to replace the hydraulic breaker with a hook boom, it is convenient to install and remove the laser emitter 11.

[0067] More preferably, the detachable connector includes a base 121, an operating element 122, a magnet 123, a buffer unit 124, and a sliding frame 125. The magnet 123 is movably installed inside the base 121. The operating element 122 is installed on the base 121 and connected to the magnet 123 to control the movement of the magnet 123 within the base 121 to achieve attraction and locking or unlocking. The sliding frame 125 is slidably connected to the base 121. The buffer unit 124 is connected between the sliding frame 125 and the base 121. The laser emitter 11 is installed on the sliding frame 125. Specifically, the operating element 122 is a knob or throttle. By rotating the knob or throttle, the magnet 123 moves within the base 121. This is a conventional technology and is not shown in detail in the attached drawings. The magnet 123 in the base 121 moves toward the actuator of the excavator that is being attracted, thereby locking the magnet 123 onto the actuator of the excavator. When unlocking is required, the knob or throttle is rotated in the opposite direction to move the magnet 123 away from the actuator, thus unlocking the device.

[0068] It is known that during use, the excavator's actuator vibrates. The seat 121 is fixedly connected to the actuator, so the seat 121 vibrates along with the actuator. The buffer assembly plays a role in shock absorption and buffering, so that less vibration is transmitted to the sliding frame 125 and the laser emitter 11 mounted on the sliding frame 125, preventing the laser emitter 11 from being damaged by strong vibration, thereby improving the service life of the laser emitter 11.

[0069] In a more preferred embodiment, the buffer unit 124 includes an elastic element 1241, a piston 1242, a rod 1243, and a control valve 1244. The seat 121 is provided with a sliding groove 1211, and the sliding frame 125 is slidably connected in the sliding groove 1211.

[0070] The seat 121 is provided with a damping cavity 1212, the piston 1242 is slidably connected in the damping cavity 1212, the first end of the rod 1243 is fixedly connected to the piston 1242, and the second end of the rod 1243 passes through the damping cavity 1212 and is fixedly connected to the sliding frame 125.

[0071] The piston 1242 divides the damping chamber 1212 into a rod chamber and a rodless chamber. The seat 121 is also provided with a first channel 1213 and a second channel 1214. The first channel 1213 connects the rodless chamber to the outside, and the second channel 1214 connects the rod chamber to the outside.

[0072] The control valve 1244 is slidably connected to the seat 121. The control valve 1244 intersects with both the first channel 1213 and the second channel 1214 to control the size of the first channel 1213 and the second channel 1214.

[0073] The elastic element 1241 is arranged on the side of the sliding frame 125 away from the rod 1243. One end of the elastic element 1241 abuts against the seat 121, and the other end of the elastic element 1241 abuts against the sliding frame 125. Specifically, the elastic element 1241 is a compression helical spring. In some other embodiments of this application, the elastic element 1241 can also be a gas spring, leaf spring, or other component or structure capable of storing elastic potential energy.

[0074] It is known that during the execution of the component, the seat 121 vibrates along with the component, causing the seat 121 to reciprocate in one direction. During this reciprocating movement, the sliding frame 125 and the laser emitter 11 remain stationary or move slightly relative to the ground due to inertia. That is, during the vibration, the seat 121 reciprocates relative to the sliding frame 125. During the movement of the seat 121 relative to the sliding frame 125, because the piston 1242 and the rod 1243 are both fixedly connected to the sliding frame 125, the piston 1242 moves within the damping chamber 1 when the seat 121 moves relative to the sliding frame 125. The piston 1242 moves back and forth within the damping chamber 1212, compressing or drawing in external gas. When the external gas enters the rodless chamber from the first channel 1213, or when the gas in the rodless chamber is discharged to the outside from the first channel 1213, energy is consumed due to the damping effect of the air, thus preventing the vibration energy of the seat 121 from being transmitted to the sliding frame 125. At the same time, when the external gas enters the rod chamber from the second channel 1214, or when the gas in the rod chamber is discharged to the outside from the second channel 1214, energy is also consumed, further preventing the vibration energy of the seat 121 from being transmitted to the sliding frame 125, thus playing a role in vibration isolation.

[0075] As a further preferred embodiment, the control valve 1244 includes a valve stem 1245 and a valve cap 1246. The seat 121 is provided with a valve hole, which intersects with both the first channel 1213 and the second channel 1214. The valve cap 1246 is coaxially fixedly connected to one end of the valve stem 1245, and the valve stem 1245 is threadedly connected to the valve hole. The valve stem 1245 includes a first conical surface 1247 and a second conical surface 1248. The first conical surface 1247 is disposed at a position corresponding to the first channel 1213 to adjust the flow cross-sectional area of ​​the first channel 1213. The second conical surface 1248 is disposed at a position corresponding to the second channel 1214 to adjust the flow cross-sectional area of ​​the second channel 1214.

[0076] It is understood that by rotating the valve cap 1246, the valve stem 1245 is moved along its own axis, so that the first conical surface 1247 moves closer to or further away from the first channel 1213. When the first conical surface 1247 moves closer to the first channel 1213, the first conical surface 1247 reduces the flow cross-sectional area of ​​the first channel 1213, making it difficult for gas to pass through the first channel 1213, and vibration is easily transmitted to the sliding frame 125. When the first conical surface 1247 moves away from the first channel 1213, the flow cross-sectional area of ​​the first channel 1213 increases, making it easier for gas to pass through the first channel 1213, and vibration is not easily transmitted to the sliding frame 125. However, this can easily cause the sliding frame 125 to move to the end of the slide groove 1211 and collide with the inner wall of the seat 121. Therefore, it is necessary to adjust the valve and the valve stem 1245 to keep the valve stem 1245 in a suitable position so that the buffer unit 124 has good buffering performance while the sliding frame 125 does not collide with the inside of the seat 121. Both the first conical surface 1247 and the second conical surface 1248 are arranged on the valve stem 1245, and the first channel 1213 and the second channel 1214 can be adjusted simultaneously by adjusting the valve stem 1245.

[0077] Furthermore, the magnetic connector 12 also includes a guide rod 126, both ends of which are fixedly connected to the base 121. The guide rod 126 passes through the sliding frame 125, and the sliding frame 125 is slidably engaged with the guide rod 126. The guide rod 126 guides the sliding frame 125, causing it to move along the axis of the guide rod 126 relative to the base 121, thereby improving the stability of the sliding frame 125 and enabling the buffer unit 124 to provide better cushioning.

[0078] In one embodiment, the spray module 3 includes a pumping unit 31, a water supply pipe 32, a nozzle 33, and a solenoid valve 34. One end of the water supply pipe 32 extends from the pumping unit 31, and the second end of the water supply pipe 32 extends to the excavator's actuator. The nozzle 33 is installed at the second end of the water supply pipe 32. The solenoid valve 34 is installed on the end of the water supply pipe 32 near the nozzle 33. The water supply pipe 32 is installed on the excavator's actuator via a magnetic connector 12. The solenoid valve 34 is electrically connected to the vision sensor 2 and is used to receive electrical signals from the vision sensor 2 and respond accordingly.

[0079] It is understood that the pumping unit 31 pumps water outward, and the water pumped out by the pumping unit 31 is delivered to the nozzle 33 through the water supply pipe 32. The solenoid valve 34 controls the water supply through the water supply pipe 32, thereby controlling the timing and duration of water spraying from the nozzle 33. Specifically, when the vision sensor 2 detects the laser beam, it sends an opening command to the solenoid valve 34, and the solenoid valve 34 opens, allowing water to spray out from the nozzle 33 to form a water mist, thus reducing dust in the work area. At the same time, the arrangement of the magnetic connector 12 reduces the vibration of the water supply pipe 32 and the solenoid valve 34, thereby improving their service life.

[0080] In this embodiment, the pumping unit 31 includes a water tank 311 and a water pump 312. The input end of the water pump 312 extends into the water tank 311, and the output end of the water pump 312 is connected to the water delivery pipe 32. The water delivery pipe 32 includes a fixed rigid pipe 321, a connecting hose 322, and a flexible positioning pipe 323. The flexible positioning pipe 323 is arranged at the downstream end, and the end of the flexible positioning pipe 323 is connected to the nozzle 33. The fixed rigid pipe 321 is used to fix it to the excavator. The upstream end of the fixed rigid pipe 321 is connected to the water pump 312 through the connecting hose 322, and the downstream end of the fixed rigid pipe 321 is connected to the flexible positioning pipe 323 through the connecting hose 322. Specifically, the fixed rigid pipe 321 is fixedly connected to the excavator's boom by pipe clamps. Two fixed rigid pipes 321 are arranged. One fixed rigid pipe 321 is fixedly connected to the excavator's boom by pipe clamps, and the other fixed rigid pipe 321 is fixedly connected to the excavator's forearm by pipe clamps. The two fixed rigid pipes 321 are connected to each other by a connecting hose 322.

[0081] It is understood that the water tank 311 is used for water storage. Water pump 312 pumps water from the water tank 311, which is then transported via a connecting hose 322 to the fixed rigid pipe 321, and then to the flexible positioning pipe 323. Finally, the water is sprayed from the nozzle 33 at the downstream end of the flexible positioning pipe 323 to achieve dust suppression. It should be noted that the flexible positioning pipe 323 is a gooseneck tube capable of plastic deformation or a bamboo-joint tube capable of changing direction and positioning. In this application, a gooseneck tube is used. By adjusting the position of the downstream end of the gooseneck tube, the nozzle 33 is directed towards the working area of ​​the actuator to spray dust suppression.

[0082] In one embodiment, the nozzle 33 is preferably a piezoelectric ceramic driven nozzle with a droplet size of 5-50 μm; a micro servo motor is also connected to the nozzle 33 to control the pitch and deflection of the nozzle 33; the water pump 312 is a 12V DC variable frequency water pump with a variable frequency pressure of 1.0 MPa.

[0083] In this embodiment, two sets of spray modules 3 are arranged, one on each side of the excavator's actuator. By arranging two sets of spray modules 3 on each side of the actuator, the working area is sprayed simultaneously from both sides, increasing the spraying area and allowing dust to settle more quickly.

[0084] In one embodiment, the sensor module further includes a wind speed sensor, a humidity sensor, and a laser particle size analyzer. The wind speed sensor, humidity sensor, and laser particle size analyzer are respectively connected to the control module. The wind speed sensor is used to measure the ambient wind speed, the humidity sensor is used to detect the humidity of the working surface and the ambient humidity, and the laser particle size analyzer is used to detect the dust particle size.

[0085] Please see Figure 7 This embodiment also provides a mechanical rock-breaking intelligent dust removal method, applied to the mechanical rock-breaking intelligent dust removal system described above, including the following steps:

[0086] S1. Collect dust characteristics data, environmental parameters, and work intensity data during the mechanical rock breaking operation. Preprocess the collected data to obtain a real-time data matrix. The dust characteristics data include dust concentration, dust range, and average dust particle size. The environmental parameters include ambient wind speed, ambient humidity, and work surface humidity. The work intensity data includes rock breaking output frequency and hydraulic system pressure.

[0087] S2. Obtain the calculation weight matching model, identify the current construction scenario, and obtain the calculation weight matrix corresponding to the current construction scenario based on the calculation weight matching model; wherein, the calculation weight matching model contains the mapping relationship between the construction scenario and the calculation weights of each parameter in the real-time data matrix;

[0088] S3. Obtain the spray parameter decision model, input the real-time data matrix and the calculated weight matrix into the spray parameter decision model to obtain the spray parameter combination; wherein, the spray parameters include spray flow rate, droplet size, spray angle and spray frequency;

[0089] S4. Control the operation of the spray module 3 according to the spray parameter combination, and collect the real-time dust concentration after waiting for a preset time.

[0090] S5. Determine whether the real-time dust concentration is less than or equal to the preset dust concentration threshold; if yes, maintain the operation of the spray module 3 and return to step S4; if no, obtain the preset correction amount of the spray parameter combination, correct the spray parameter combination according to the preset correction amount, and then return to step S4.

[0091] The dust removal method provided in this embodiment collects multi-dimensional data related to dust during operations, providing a comprehensive consideration of multi-dimensional parameter changes for subsequent decision-making. It utilizes a computational weight matching model that maps scene and parameter weights to adapt weight allocation to the current construction scenario, improving decision-making targeting. By integrating real-time data matrices and computational weight matrices through a spray parameter decision model, it outputs adapted parameter combinations, achieving precise parameter matching to working conditions. Furthermore, it dynamically adjusts the spray parameter combinations based on real-time dust concentration after spraying and preset correction amounts, ensuring the dynamic adaptability of dust removal control. This invention integrates scene-based weight matching and dynamic parameter correction into a multi-dimensional data-driven spray decision-making process, achieving intelligent adaptive dust removal control for different mechanical rock breaking conditions, improving dust removal efficiency and control accuracy.

[0092] Specifically, in step S1, the dust concentration and dust range in the dust characteristic data are collected by a laser emitting component and a vision sensor 2. The laser emitting component emits a laser beam that passes through the dust area and produces diffuse reflection. The vision sensor 2 determines the dust concentration and dust range by identifying the brightness and length of the laser beam in the diffuse reflection. The preferred acquisition frequency is 10Hz. The dust particle size is collected by a laser particle size analyzer. The laser particle size analyzer deduces the particle size distribution of the dust particles based on the Mie scattering principle, thereby classifying the dust particles into three categories: "fine particles (<10μm), medium particles (10-50μm), and coarse particles (>50μm)". The acquisition frequency is 5Hz, and the particle size detection accuracy is ±0.1μm.

[0093] In this embodiment, the ambient wind speed among the environmental parameters is measured using a miniature ultrasonic anemometer with a measurement range of 0-10 m / s and an accuracy of ±0.1 m / s. The miniature ultrasonic anemometer is installed on the top of the excavator cab facing the work area. The ambient humidity and the humidity of the work surface are measured using a dual-channel humidity sensor. One channel is installed on the top of the cab to collect ambient humidity data, with a measurement range of 0-100%RH and an accuracy of ±2%RH. The other channel is installed near the actuator via a magnetic base to collect humidity data from the work surface to avoid interference from ambient humidity. The sampling frequency is 5 Hz.

[0094] The work intensity data is communicated with the excavator control system via the CAN bus to collect the impact frequency of the breaker hammer (i.e., rock breaking output frequency) in real time, with a measurement range of 500-1500 times / min and the hydraulic system pressure, with a measurement range of 0-35MPa. This indirectly characterizes the work intensity. The higher the rock breaking output frequency and the greater the hydraulic pressure, the greater the amount of dust generated. The acquisition frequency is 10Hz.

[0095] In this embodiment, a sliding window filtering algorithm is used to denoise all collected data, with the window size set to 50ms to eliminate sensor data fluctuations caused by construction vibrations. Simultaneously, the data is standardized and mapped to the 0-1 range to avoid the impact of differences in data dimensions on subsequent algorithm analysis. It should be understood that the sliding window filtering algorithm in this embodiment is existing technology and will not be elaborated upon further.

[0096] In one embodiment, as a further preferred embodiment, step S2 specifically includes the following steps:

[0097] A scene classifier is obtained to collect the core identification features of the current construction scene. Based on the core identification features, the scene classifier identifies the category of the current construction scene. The scene classifier classifies mechanical rock breaking construction scenes into tunnel scenes, open-pit scenes, and foundation pit scenes. The scene classifier uses three parameters—wind speed stability, operation enclosure, and working face slope—as the core identification features for scene classification.

[0098] Obtain the weight matching model and obtain the weight matrix corresponding to the current construction scenario based on the category of the current construction scenario; wherein, the weight matrix is ​​a preset initial weight matrix, and the initial weights in the initial weight matrix are set according to the degree of influence of dust characteristics data, environmental parameters and work intensity data on the spraying effect under different scenarios.

[0099] Specifically, the wind speed stability data is as follows: Tunnel scenario: wind speed < 1 m / s with fluctuation ≤ 0.2 m / s; Open-air scenario: wind speed > 3 m / s with fluctuation ≥ 0.5 m / s; Foundation pit scenario: wind speed 1-3 m / s with fluctuation 0.2-0.5 m / s. Visual sensor 2 collects images of the working face environment and identifies the proportion of enclosed areas through image segmentation. The working face enclosure data is as follows: tunnel scenario > 80%, open-air scenario < 20%, foundation pit scenario 20-80%. The working face slope is obtained through the excavator's attitude sensor. In the foundation pit scenario, the working face slope is > 10°, while in the tunnel or open-air scenario, the working face slope is ≤ 10°.

[0100] The initial weight matrices for various construction scenarios are as follows:

[0101] Tunnel scenario: Dust concentration 30%, dust particle size 20%, work intensity 20%, work surface humidity 15%, wind speed 10%, ambient humidity 5%;

[0102] Outdoor scenario: wind speed 35%, dust concentration 20%, dust particle size 20%, work intensity 10%, ambient humidity 10%, work surface humidity 5%;

[0103] Excavation pit scenario: Dust particle size 25%, working surface humidity 20%, dust concentration 15%, work intensity 15%, wind speed 15%, ambient humidity 10%.

[0104] This embodiment extracts three core identification features—wind speed stability, operational enclosure, and working surface slope—using a scene classifier to accurately identify construction scene categories, providing a scenario-based basis for weight allocation. By employing a weight matching model, a preset initial weight matrix is ​​invoked based on the degree of influence of each parameter on the sprinkler effect under different scenarios, ensuring precise adaptation of weight allocation to scene characteristics. This application clearly defines the core feature dimensions of scene classification and presets initial weights based on the degree of parameter influence on the sprinkler effect, achieving a precise correlation between scene identification and weight allocation. This improves the targeting and rationality of feature weight allocation, laying the foundation for accurate decision-making regarding subsequent sprinkler parameter combinations.

[0105] In one embodiment, as a further preferred embodiment, the following steps are included after step S5:

[0106] A real-time data matrix after spraying is obtained, the rate of change of each parameter in the real-time data matrix is ​​determined, and it is judged whether the rate of change of each parameter is greater than a first preset threshold; in this embodiment, the first preset threshold is 30%.

[0107] If the rate of change per unit time is greater than the first preset threshold, the real-time data is determined to be a mutation data, and it is determined whether there is any one or more mutation data in the real-time data matrix after spraying.

[0108] If there is one or more abrupt changes in the real-time data matrix after spraying, the initial weights in the initial weight matrix corresponding to the abrupt changes are increased by a preset correction step size, and the process returns to step S3, where the preset correction step size is 2%.

[0109] By monitoring the dynamic changes in post-spraying data in real time to identify sudden changes in operating conditions, the corresponding parameter weights are adjusted accordingly, making the feature weight allocation more in line with real-time operating condition fluctuations. This provides more accurate weight support for subsequent spraying parameter decisions, and a dynamic weight optimization mechanism based on post-spraying data change feedback is constructed, further improving the adaptability and response accuracy of spraying parameter decisions to sudden changes in operating conditions.

[0110] As a further preferred embodiment, step S5 is followed by the following steps:

[0111] A real-time data matrix after spraying is obtained, and the deviation of each parameter in the real-time data matrix from the average value of each parameter under the same construction scenario is determined. It is then determined whether the deviation is greater than a second preset threshold; in this embodiment, the second preset threshold is 50%.

[0112] If the deviation is greater than the second preset threshold, the real-time data is determined to be abnormal deviation data, and it is determined whether there is any one or more abnormal deviation data in the real-time data matrix after spraying.

[0113] If any one or more deviation abnormal data exist in the real-time data matrix after spraying, the initial weight matrix of the open-air scene is obtained, the initial weight ratio of the open-air scene is obtained based on the initial weight matrix of the open-air scene, the initial weight of the initial weight matrix of the current construction scene is corrected according to the initial weight ratio with a preset correction step size, and the process returns to step S3.

[0114] This embodiment constructs a weight adaptation mechanism based on scene parameter deviation feedback. By monitoring the deviation between parameters and scene benchmark values, abnormal working conditions are identified. The weight is adjusted in a targeted manner by leveraging the weight ratio of open-air scenes, making the weight allocation more in line with the characteristics of abnormal working conditions, and further improving the accuracy of spray parameter decision-making in adapting to complex working condition fluctuations.

[0115] As a further preferred embodiment, step S3 specifically includes the following steps:

[0116] A spray parameter decision model is obtained, which includes a random forest model and a feature attention layer, wherein the feature attention layer is embedded between the input layer and the decision tree training layer of the random forest model;

[0117] The real-time data matrix and the calculated weight matrix are input to the input layer. The feature attention layer matches weight coefficients according to the parameters of the calculated weight matrix and the real-time data matrix to obtain a weighted feature vector.

[0118] The feature vector is input into each decision tree of the random forest model for independent training. Each decision tree outputs its own parameter prediction results. The parameter prediction results of all decision trees are merged by weighted voting to obtain the final spray parameter combination.

[0119] Specifically, in this embodiment, the spray parameter decision model adopts a multi-fusion architecture of random forest model and attention mechanism, which takes into account the strong generalization ability of random forest model and the key feature focusing ability of attention mechanism. The specific architecture is as follows:

[0120] The random forest model uses 100 CART decision trees (classification and regression trees) to form the main forest. 100 subsets are extracted from the original training dataset using Bootstrap sampling with replacement, with each subset containing 70% of the original dataset, ensuring the training data for each decision tree is differentiated. During training, a feature randomization strategy is employed, randomly selecting parameters from six categories of collected data: dust concentration, dust particle size, ambient wind speed, ambient humidity, work surface humidity, and work intensity. The splitting criterion is based on minimizing the mean squared error to suit sprinkler parameter regression prediction tasks. Growth is stopped when the decision tree depth reaches 15 layers or the number of leaf node samples is ≤5 to avoid overfitting.

[0121] A feature attention layer is embedded between the input layer and the decision tree training layer of the random forest model, forming a closed-loop architecture of feature weighting, forest training, and result fusion. The feature attention layer employs a lightweight structure of a multilayer perceptron with softmax normalization, and the sum of its output weight coefficients is 1.

[0122] The feature attention layer matches weight coefficients to the parameters of the real-time data matrix based on the calculated weight matrix, resulting in a weighted feature vector. This weighted feature vector is then input into each decision tree of the random forest model for independent training. Each decision tree outputs its own parameter prediction results. These prediction results include flow rate, droplet size, angle, and frequency. Finally, the results of all decision trees are merged through a weighted voting method, assigning higher fusion weights (20-30%) to decision trees with high attention weights and high feature sensitivity, resulting in the final spray parameter combination.

[0123] More specifically, in this embodiment, the model training and updating of the spray parameter decision model adopts a two-stage training strategy of offline pre-training and online fine-tuning to ensure that the model has both the ability to adapt to all working conditions and the ability to quickly respond to changes in new scenarios. The specific process is as follows:

[0124] Offline pre-training phase:

[0125] Training Sample Library Construction: A three-dimensional labeled sample library will be constructed, encompassing multi-dimensional data, spraying parameters, and dust removal or water-saving effects. Sample sources will cover three core construction scenarios: tunnels, open-air environments, and foundation pits. Data will be acquired through a combination of on-site construction data collection and simulation experiments. Samples must cover the full range of operating conditions: wind speed 0-10 m / s, humidity 20-100% RH, work intensity 500-1500 cycles / min, and particle size 0.1-100 μm. 100 sets of valid data will be collected for each operating condition, with a total sample size ≥ 100,000 sets.

[0126] Sample labeling and preprocessing: Each group of samples is labeled in three dimensions, namely, input feature labeling, namely, 6 types of core collected data, spray parameter labeling (including the optimal combination of flow rate, droplet size, angle and frequency, determined through orthogonal experiments), and effect index labeling (including dust removal efficiency and water saving rate). The labeled samples are processed by outlier removal and standardization using the 3σ criterion, and divided into training set, validation set and test set in a ratio of 7:2:1.

[0127] Model pre-training: The training set is input into the spray parameter decision model, and the batch gradient descent algorithm is used to optimize the model parameters. The learning rate is set to 0.01, the number of iterations is 500, and the model performance is verified with the validation set every 50 iterations. The passing standard is set as spray parameter prediction error ≤5% and dust removal efficiency prediction error ≤3%. Training is stopped when the validation set error does not decrease for 10 consecutive iterations, and the pre-trained model parameters are saved.

[0128] Model performance validation: Use the test set to evaluate the performance of the pre-trained model. The pre-trained model should have a prediction accuracy of ≥95% for spray parameter combinations, a prediction accuracy of ≥97% for dust removal efficiency, and a prediction accuracy of ≥96% for water saving rate. If the requirements are not met, return to adjust the number of decision trees in the random forest model or increase / decrease the number of MLP layers, and retrain until the requirements are met.

[0129] The parameter ranges for the spray parameter combination in this embodiment are as follows:

[0130] Flow rate: 0.3-1.0MPa (corresponding to a flow rate of 5-50L / min);

[0131] Droplet size: 5-50μm (continuously adjustable);

[0132] Angles: Pitch angle -10°~30°, Yaw angle -45°~45°;

[0133] Frequency: 1-5 times per second, using intermittent spraying. High-frequency continuous spraying is used when the dust concentration is high, and low-frequency intermittent spraying is used when the dust concentration is low.

[0134] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A mechanical rock-breaking intelligent dust removal method, characterized in that, Includes the following steps: S1. Collect dust characteristics data, environmental parameters, and work intensity data during the mechanical rock breaking operation. Preprocess the collected data to obtain a real-time data matrix. The dust characteristics data include dust concentration, dust range, and average dust particle size. The environmental parameters include ambient wind speed, ambient humidity, and work surface humidity. The work intensity data includes rock breaking output frequency and hydraulic system pressure. S2. Obtain the calculation weight matching model, identify the current construction scenario, and obtain the calculation weight matrix corresponding to the current construction scenario based on the calculation weight matching model; wherein, the calculation weight matching model contains the mapping relationship between the calculation weights of each parameter in the construction scenario and the real-time data matrix; S3. Obtain the spray parameter decision model, and input the real-time data matrix and the calculated weight matrix into the spray parameter decision model to obtain the spray parameter combination; wherein, the spray parameters include spray flow rate, droplet size, spray angle and spray frequency; S4. Control the operation of the spray module according to the spray parameter combination, and collect the real-time dust concentration after waiting for a preset time. S5. Determine whether the real-time dust concentration is less than or equal to the preset dust concentration threshold; if yes, maintain the operation of the spray module and return to step S4; if no, obtain the preset correction amount of the spray parameter combination, correct the spray parameter combination according to the preset correction amount, and then return to step S4. Step S2 specifically includes the following steps: A scene classifier is obtained to collect the core identification features of the current construction scene. Based on the core identification features, the scene classifier identifies the category of the current construction scene. The scene classifier classifies mechanical rock breaking construction scenes into tunnel scenes, open-pit scenes, and foundation pit scenes. The scene classifier uses three parameters—wind speed stability, operation enclosure, and working face slope—as the core identification features for scene classification. Obtain the weight matching model and obtain the weight matrix corresponding to the current construction scenario based on the category of the current construction scenario; wherein, the weight matrix is ​​a preset initial weight matrix, and the initial weights in the initial weight matrix are set according to the degree of influence of dust characteristics data, environmental parameters and work intensity data on the spraying effect under different scenarios.

2. The intelligent dust removal method for mechanical rock breaking according to claim 1, characterized in that, Step S5 is followed by the following steps: Obtain the real-time data matrix after spraying, determine the rate of change of each parameter in the real-time data matrix per unit time, and determine whether the rate of change of each parameter per unit time is greater than a first preset threshold. If the rate of change per unit time is greater than the first preset threshold, the real-time data is determined to be a mutation data, and it is determined whether there is any one or more mutation data in the real-time data matrix after spraying. If there is one or more abrupt changes in the real-time data matrix after spraying, the initial weights in the initial weight matrix corresponding to the abrupt changes are increased by a preset correction step size, and the process returns to step S3.

3. The intelligent dust removal method for mechanical rock breaking according to claim 1, characterized in that, Step S5 is followed by the following steps: Obtain the real-time data matrix after spraying, determine the deviation of each parameter in the real-time data matrix from the average value of each parameter under the same construction scenario, and determine whether the deviation is greater than a second preset threshold. If the deviation is greater than the second preset threshold, the real-time data is determined to be abnormal deviation data, and it is determined whether there is any one or more abnormal deviation data in the real-time data matrix after spraying. If any one or more deviation abnormal data exist in the real-time data matrix after spraying, the initial weight matrix of the open-air scene is obtained, the initial weight ratio of the open-air scene is obtained based on the initial weight matrix of the open-air scene, the initial weight of the initial weight matrix of the current construction scene is corrected according to the initial weight ratio with a preset correction step size, and the process returns to step S3.

4. The intelligent dust removal method for mechanical rock breaking according to claim 1, characterized in that, Step S3 specifically includes the following steps: A spray parameter decision model is obtained, which includes a random forest model and a feature attention layer, wherein the feature attention layer is embedded between the input layer and the decision tree training layer of the random forest model; The real-time data matrix and the calculated weight matrix are input to the input layer. The feature attention layer matches weight coefficients according to the parameters of the calculated weight matrix and the real-time data matrix to obtain a weighted feature vector. The feature vector is input into each decision tree of the random forest model for independent training. Each decision tree outputs its own parameter prediction results. The parameter prediction results of all decision trees are merged by weighted voting to obtain the final spray parameter combination.

5. A mechanical rock-breaking intelligent dust removal system, applied to excavators, characterized in that, The mechanical rock-breaking intelligent dust removal method as described in any one of claims 1-4 includes a laser module, a sensor module, a control module, and a spraying module; in; The laser module is fixed to the actuating component of the excavator, and the laser beam emitted by the laser module is directed towards the rock-breaking working face; The sensor module is mounted on the excavator. The sensor module includes a vision sensor, and the acquisition direction of the vision sensor is set at an angle to the laser beam. The spraying module is located on both sides of the actuating component, and the spraying direction of the spraying module is towards the rock breaking working face; The control module is connected to the laser module, the sensor module, and the spray module, respectively.

6. The intelligent dust removal system for mechanical rock breaking according to claim 5, characterized in that, The laser module includes a laser emitter and a detachable connector. The laser emitter is detachably connected to the detachable connector, which is mounted on the actuating component of the excavator.

7. The intelligent dust removal system for mechanical rock breaking according to claim 6, characterized in that, The detachable connector includes a base, an operating component, a magnet, a buffer unit, and a sliding frame. The magnet is movably installed in the base. The operating component is installed on the base and connected to the magnet to control the movement of the magnet within the base to achieve attraction, locking, or unlocking. The sliding frame is slidably connected to the base. The buffer unit is connected between the sliding frame and the base. The laser emitter is installed on the sliding frame.

8. The intelligent dust removal system for mechanical rock breaking according to claim 7, characterized in that, The buffer unit includes an elastic element, a piston, a rod, and a control valve. The seat is provided with a sliding groove, and the sliding frame is slidably connected in the sliding groove. The seat body is provided with a damping cavity, the piston is slidably connected in the damping cavity, the first end of the rod is fixedly connected to the piston, and the second end of the rod passes through the damping cavity and is fixedly connected to the sliding frame. The piston divides the damping chamber into a rod chamber and a rodless chamber. The seat is also provided with a first channel and a second channel. The first channel connects the rodless chamber to the outside, and the second channel connects the rod chamber to the outside. The control valve is slidably connected to the seat body, and the control valve intersects with both the first channel and the second channel to control the size of the first channel and the second channel; The elastic element is arranged on the side of the sliding frame away from the rod, with one end of the elastic element abutting against the seat and the other end of the elastic element abutting against the sliding frame.

9. The intelligent dust removal system for mechanical rock breaking according to claim 8, characterized in that, The control valve includes a valve stem and a valve cap. The seat has a valve hole that intersects with both the first channel and the second channel. The valve cap is coaxially fixed to one end of the valve stem. The valve stem is threadedly connected to the valve hole. The valve stem includes a first conical surface and a second conical surface. The first conical surface is positioned on the valve stem corresponding to the first channel to adjust the cross-sectional area of ​​the first channel. The second conical surface is positioned on the valve stem corresponding to the second channel to adjust the cross-sectional area of ​​the second channel.

Images