Ore mining transportation device with discharge port dust suppression mechanism and method of ore mining transportation device

Abstract

The invention discloses an ore mining transportation device with a discharge port dust suppression mechanism and a method of the ore mining transportation device, and belongs to the technical field of mineral mining, material transportation and dust pollution control. Comprising the following steps: soft measurement of material flow characteristics: fusing a current signal of a power monitor, a vibration signal of an acoustic probe and an image signal of an industrial camera through a controller, and estimating the instantaneous flow rate and apparent moisture content of a material in real time; optimal atomization strategy prediction control: the controller performs rolling optimization through a dynamic mechanism model on the basis of the estimated instantaneous flow rate and apparent moisture content in combination with wind speed disturbance data of an anemometer, and outputs a control instruction to an atomization spray gun; and feedback constraint and closed loop: when the controller is optimized, the dust concentration measured by the turbidity sensor is taken as a minimization target, and the exhaust humidity measured by the humidity sensor does not exceed a preset threshold value is taken as a constraint condition, so that the accuracy and robustness of an estimation result are improved, and a foundation is laid for subsequent accurate control.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of mineral exploitation, material transportation and dust pollution control, in particular to a mineral exploitation and transportation device with a dust suppression mechanism for an outlet and a method thereof. BACKGROUND

[0002] With the rapid development and construction of mineral exploitation projects, in the typical scene of transporting materials, especially at the outlet position, serious dust pollution problems will be formed. The traditional mineral transportation method mainly relies on fixed spraying strategies for dust suppression; however, in actual working conditions, the material flow characteristics such as instantaneous flow and apparent moisture content of the material frequently and sharply change; in such changing working conditions, the traditional fixed spraying strategy is difficult to adapt; the traditional dust suppression method uses a single spraying action to cope with complex material flow changes, and its defects include: Unstable suppression effect: when the material flow suddenly increases or the dryness rises, the fixed spraying amount cannot provide enough suppression force, resulting in a sharp increase in dust concentration, causing serious dust pollution; risk of over-wetting material: when the material flow decreases or the apparent moisture content is high, the fixed spraying amount may cause waste of water resources and result in over-wetting of the material, affecting the subsequent conveying and processing process; in addition, traditional sensors used to feedback the dust suppression effect, such as turbidity sensors and humidity sensors, are lagging in response; they can only monitor the state after dust dispersion and exhaust humidity rise have occurred, and cannot provide early warning when the material flow state changes sharply, so that the control system can only take a lagging response, making it difficult to achieve advanced suppression.

[0003] Therefore, how to actively and in advance adjust the dust suppression strategy under the premise that the apparent moisture content of the material does not exceed the preset threshold to effectively cope with the instantaneous changes of the material flow is a key problem to be solved in the current mineral transportation field.

[0004] The above information disclosed in the above background section is only used to strengthen the understanding of the background of the present disclosure, and therefore it can include information that does not constitute prior art known to those of ordinary skill in the art. SUMMARY

[0005] The purpose of the present application is to provide a mineral exploitation and transportation device with a dust suppression mechanism for an outlet and a method thereof to solve the problems raised in the above background; specifically, the technical solution of the present application is as follows: A mineral exploitation and transportation method with a dust suppression mechanism for an outlet, comprising the following steps: Material flow characteristic soft measurement: the controller fuses the current signal of the power monitor, the vibration signal of the acoustic probe and the image signal of the industrial camera to estimate the instantaneous flow and apparent moisture content of the material in real time; Optimal atomization strategy predictive control: the controller, based on the estimated instantaneous flow rate and apparent moisture content, combined with the wind speed disturbance data of the anemometer, performs rolling optimization through a dynamic mechanism model, and outputs control instructions to the atomization spray gun; Feedback constraint and closed loop: the controller, in the optimization, takes the dust concentration measured by the turbidity sensor as the minimization target, and takes the exhaust humidity measured by the humidity sensor as the constraint condition, which is not more than the preset threshold.

[0006] Preferably, the material flow feature soft measurement step specifically includes: Acquisition: the power monitor obtains the motor load current as the reference mass flow, the acoustic probe picks up the structural vibration soundprint of the material impact, and the industrial camera acquires the instantaneous cross-sectional profile of the material through the high-brightness LED stroboscopic light source exposure; Fusion estimation: the deep neural network model in the controller receives the current signal, the vibration soundprint and the cross-sectional profile, and outputs the estimated value of the instantaneous flow rate and the apparent moisture content through multi-modal fusion calculation.

[0007] Preferably, the deep neural network model is established by the following steps: In the debugging phase, collect historical working condition data sets, and record the current signal of the power monitor, the vibration signal of the acoustic probe and the image signal of the industrial camera as the input features of the model synchronously; Periodic offline calibration is performed using a high-precision weighing hopper to obtain a reference mass flow, and the reference apparent moisture content is obtained by drying the intercepted material sample, and the reference flow rate and apparent moisture content data are used as the supervision label of the model; Adjust the internal weights of the model to establish a non-linear mapping relationship from the three-way sensor input features to the supervision label.

[0008] Preferably, the optimal atomization strategy predictive control step specifically includes: Prediction: the controller, based on the change rate of the instantaneous flow rate and the apparent moisture content, establishes a short-time prediction model to calculate the material flow state in the future control period; Optimization solution: the controller, based on the material flow state, the wind speed disturbance data, and the dynamic mechanism model describing the relationship between the spray gun action and the dust concentration and the exhaust humidity, solves the objective function through a rolling optimization algorithm to determine the start-stop timing of the atomization spray gun.

[0009] Preferably, it further includes a sensor state self-diagnosis and degradation step: Verification: the controller continuously runs the consistency verification logic, and cross-compares the data streams of the power monitor, the acoustic probe and the industrial camera; Diagnosis: when data difference is detected continuously, it is determined that a specific sensor is malfunctioning; Degradation: the controller triggers a dynamic control strategy degradation procedure immediately, activates a pre-trained degradation version soft-sensing model which is independent of the malfunctioning sensor according to the fault and pre-fault material characteristic parameters.

[0010] A mineral exploitation and transportation device with a dust suppression mechanism at the discharge port, the device comprising: a conveyor end for conveying material; a dust suppression hood fixed at the discharge port position of the conveyor end; a power monitor for monitoring the load current of the motor driving the conveyor; a sensing array comprising an industrial camera fixed to the frame of the dust suppression hood and an acoustic probe fixed to the conveyor end; an atomizing spray gun arrayed on the inner wall of the dust suppression hood; a state monitor comprising a turbidity sensor and a humidity sensor installed in the exhaust duct of the dust suppression hood; an anemometer installed inside the exhaust duct; a controller connected to the power monitor, the sensing array, the atomizing spray gun, the state monitor and the anemometer respectively.

[0011] Preferably, a discharge chute is installed on the conveyor end, and the acoustic probe is a piezoelectric contact microphone fixed to the outer wall of the bottom plate of the discharge chute through a rigid connecting seat.

[0012] Preferably, the industrial camera is a high-speed industrial camera, and a high-brightness LED stroboscopic light source is fixed to the lens of the industrial camera through the same mounting bracket.

[0013] Preferably, the power monitor is a high-precision wide-frequency current transformer, and a non-contact clamp is applied to the main power supply cable of the motor driving the conveyor.

[0014] Preferably, the atomizing spray gun is controlled by an independent electrically controlled high-frequency pulse width modulation valve.

[0015] The present application provides a mineral exploitation and transportation device with a dust suppression mechanism at the discharge port and a method thereof by improvement, compared with the prior art, having the following improvements and advantages: 1. The present application introduces a material flow feature soft measurement step, through a deep neural network model, multi-modal fusion of three heterogeneous data streams from the motor current signal of the power monitor, the vibration acoustic fingerprint of the acoustic probe and the cross-sectional profile image signal of the industrial camera, real-time and accurate estimates of instantaneous flow and apparent moisture content of the material are obtained, compared with the measurement method relying on a single sensor, this fusion method combines the stability of the current signal and the instantaneous nature of the acoustic / visual signal, improves the accuracy and robustness of the estimation result, and lays the foundation for subsequent accurate control; 2. Optimal atomization strategy predictive control is adopted, through a short-term prediction model and a rolling optimization algorithm based on a dynamic mechanism model, the start-stop timing of the atomization lance is determined according to the predicted future material flow state and wind speed disturbance data, which gets rid of the lag response of the traditional method, and can calculate and layout the matching enhanced fog field in advance before the high flow or dry material really reaches the discharge port, significantly improving the initiative and effectiveness of dust suppression, in the optimization solution, the dust concentration measured by the turbidity sensor is taken as the minimum target, and the exhaust humidity measured by the humidity sensor is not more than the preset threshold as the constraint condition, which ensures that the best dust suppression effect is achieved while avoiding over-wetting of the material, and realizes the accurate dynamic balance between dust suppression effect and apparent moisture content; 3. A sensor state self-diagnosis and degradation step is added, the sensor data is cross-compared through consistent verification logic running continuously, and when a specific sensor failure is determined, a degraded version of the soft measurement model that does not depend on the failed sensor is activated, ensuring that the dust suppression system can continue to run the adaptive dust suppression function even if a single sensing component fails in harsh mine environments; avoids the complete paralysis of traditional systems caused by sensor failure, sacrifices part of the control accuracy, but greatly improves the running reliability and fault tolerance of the entire system. BRIEF DESCRIPTION OF DRAWINGS

[0016] The present application will be further explained below in conjunction with the drawings and examples: Figure 1 is a schematic diagram of the overall structure of the device outside; Figure 2 is a schematic diagram of the cross-sectional structure of the dust suppression cover; Figure 3 is a schematic diagram of the exhaust pipe and its connection structure; Figure 4 is a schematic diagram of the method flow structure of the present application.

[0017] In the figure: 100, end of conveyor; 110, discharge chute; 120, power monitor; 200, dust suppression hood; 210, exhaust duct; 220, anemometer; 230, atomizing spray gun; 300, sensory array; 310, industrial camera; 320, acoustic probe; 400, state monitor; 410, turbidity sensor; 420, humidity sensor; 500, controller. DETAILED DESCRIPTION

[0018] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application is further described in detail below with specific examples.

[0019] Example 1 Please refer to Figures 1-4 The present application provides a kind of ore mining with discharge port dust suppression mechanism transport method, comprising the following steps: Material flow characteristic soft measurement: through the current signal of power monitor 120, vibration signal of acoustic probe 320 and image signal of industrial camera 310, instantaneous flow and apparent moisture content of material are estimated in real time by controller 500 fusion; Optimal atomization strategy predictive control: based on the estimated instantaneous flow and apparent moisture content, wind speed disturbance data of anemometer 220 is combined, and control instructions are output to atomizing spray gun 230 by dynamic mechanism model rolling optimization by controller 500; Feedback constraint and closed loop: when optimizing, the dust concentration measured by turbidity sensor 410 is minimized as the target, and the exhaust humidity measured by humidity sensor 420 does not exceed the preset threshold as the constraint condition.

[0020] The exhaust humidity does not exceed the preset threshold Hmax is a safety index, which is used to define the maximum exhaust humidity allowed in the dust suppression process, and its physical meaning is that when the exhaust humidity exceeds this value, it indicates that the atomization amount may be too large, which has the risk of causing the material to be too wet;The threshold value needs to be determined offline in the debugging stage by dynamic atomization test on typical ore samples in the laboratory, and combining the requirements of subsequent processing process on the apparent moisture content of material. The threshold value is a hard constraint condition of the rolling optimization algorithm in the optimal atomization strategy predictive control step, which ensures that the dust concentration is minimized while avoiding the material from being too wet; The ore mining and transportation method with a dust suppression mechanism at the discharge port of the present embodiment takes the soft measurement of the material flow characteristics as the starting point of the entire control logic; this step obtains a real-time estimate of the material state by fusing sensor data from multiple sources, which is the basis for subsequent precise control; the optimal atomization strategy prediction control step uses this real-time estimate and combines external environmental interference factors to calculate prospective spraying actions through a model; the feedback constraint and closed-loop step sets clear goals and boundaries for the entire control process, i.e., while suppressing dust, the material must not be over-wetted; the three steps work together to enable the dust suppression system to actively adapt to changing working conditions, overcoming the limitations of traditional fixed spraying strategies, and achieving a balance between dust suppression effectiveness and material moisture content.

[0021] The soft measurement of the material flow characteristics specifically includes: Collection: the power monitor 120 obtains motor load current to represent the reference mass flow, the acoustic probe 320 picks up the structural vibration soundprint of the material impact, and the industrial camera 310 exposes and collects the instantaneous cross-sectional profile of the material through the high-brightness LED stroboscopic light source; Fusion estimation: the deep neural network model in the controller 500 receives the current signal, vibration soundprint, and cross-sectional profile, and outputs the estimated value of the instantaneous flow and apparent moisture content through multi-modal fusion calculation.

[0022] In addition, in another embodiment, the deep neural network model in the controller 500 can be replaced by a Kalman filter-based adaptive fusion algorithm. This algorithm establishes a state space model, uses the signal of the power monitor 120 as the main measurement input, and uses the instantaneous signals of the acoustic probe 320 and the industrial camera 310 as correction terms for model prediction, to achieve multi-sensor state estimation of instantaneous flow and apparent moisture content, and also obtain accurate and robust estimation results; The input source of multi-modal fusion calculation is the current signal of the power monitor 120, the vibration soundprint picked up by the acoustic probe 320, and the cross-sectional profile collected by the industrial camera 310; the logical steps include: Step 1: the controller 500 synchronizes the time stamps of the three signals and performs denoising preprocessing. Step 2: input the processed signals into the deep neural network model. Step 3: the network performs weighted and nonlinear combination of the extracted features of the three through feature-level or decision-level fusion layers. The final output of the process is the real-time estimate of the instantaneous flow and apparent moisture content of the material, which is the core input in the optimal atomization strategy prediction control step; In this embodiment, the material flow feature soft measurement step is further refined; the acquisition process utilizes three different physical principle sensing means; the power monitor 120 provides a relatively stable, low-frequency signal reflecting the overall quality of the reactants by measuring the load current of the conveyor motor, which is used to characterize the reference mass flow; the acoustic probe 320 is used to capture the high-frequency structural vibration soundprint generated by the collision and friction of the material with the equipment, which is closely related to the particle size and impact kinetic energy of the material; the industrial camera 310, with the cooperation of the high-brightness LED stroboscopic light source, can capture clear images without motion blur, which are used to calculate the instantaneous cross-sectional profile and surface texture of the flow; in the fusion estimation step, the three data streams containing different dimensional information, current signal, vibration soundprint and cross-sectional profile, are simultaneously input into the deep neural network model deployed in the controller 500; the model processes these heterogeneous data through multi-modal fusion calculation, and outputs the estimated values of instantaneous flow and apparent moisture content in real time; this fusion method uses the stability of the current signal to calibrate the mean value of the results, and at the same time uses the instantaneous nature of the acoustic and visual signals to capture the dramatic flow fluctuations, and the estimated results obtained are superior to the measurement method relying on a single sensor in terms of accuracy and robustness.

[0023] The deep neural network model is established by the following steps: In the debugging phase, collect historical working condition data sets, and record the current signal of the power monitor 120, the vibration signal of the acoustic probe 320 and the image signal of the industrial camera 310 simultaneously as the input features of the model; Use a high-precision weighing hopper for periodic offline calibration to obtain the reference mass flow, and measure the reference apparent moisture content of the intercepted material sample by drying method, and the reference flow and moisture content data are used as the supervision labels of the model; Adjust the internal weights of the model to establish a nonlinear mapping relationship from the input features of the three sensors to the supervision labels.

[0024] In this embodiment, the establishment process of the deep neural network model is completed in the debugging stage before the formal operation of the device. The purpose of this process is to teach the model how to derive accurate material state from the input signals of the sensors; specifically, first, a historical working condition data set needs to be collected, that is, under a variety of typical material transportation conditions, the system synchronously records the raw data from the power monitor 120, the acoustic probe 320 and the industrial camera 310, which constitutes the input features of the model; at the same time, the real state of the material under these working conditions must be obtained as the answer or supervision label for model learning. This is achieved through offline calibration: a high-precision weighing hopper is used at the discharge port to actually measure the reference mass flow of the material, and the intercepted material sample is measured by the drying method to obtain its reference apparent moisture content. After sufficient input features and corresponding supervision labels are obtained, the training of the model begins. During the training process, the model will continuously adjust the internal weights, essentially optimizing its internal complex calculation logic, with the purpose of continuously reducing the error between the result calculated by the model according to the three-sensor input features and the real supervision label, i.e., the reference flow and moisture content; this process continues until the model converges, forming a stable nonlinear mapping relationship, at which point the model has the ability to accurately estimate the material state from the sensor signals.

[0025] The optimal atomization strategy prediction control step specifically includes: Prediction: the controller 500 establishes a short-term prediction model based on the instantaneous flow and the change rate of the apparent moisture content, and calculates the material flow state in the future control period; Optimization solution: the controller 500 determines the start-stop timing of the atomizing gun 230 by solving the objective function through a rolling optimization algorithm based on the material flow state, the wind speed disturbance data, and the dynamic mechanism model describing the relationship between the action of the spray gun and the dust concentration and the exhaust humidity.

[0026] The dynamic mechanism model aims to establish the dynamic causal relationship between the action of the atomizing gun 230, the input and the final dust concentration and exhaust humidity, thereby supporting the advanced prediction control. The model logically contains a multi-input-multi-output time series prediction structure. It receives the future material flow state from the prediction sub-step, the wind speed disturbance of the anemometer 220 and the spray gun start-stop timing u(t+k) to be optimized as input; the model represents the physical laws of collision, condensation, sedimentation of water mist particles and dust particles and dynamic change of gas humidity in the dust suppression hood 200 under the consideration of the coupling effect of material characteristics and environmental wind disturbance; In this embodiment, the core of the optimal atomization strategy predictive control step is to achieve a proactive suppression rather than a reactive response; the prediction sub-step is the prerequisite to achieve this goal; the short-time prediction model within the controller 500 continuously analyzes the instantaneous flow rate and apparent moisture content provided by the soft measurement step, especially their rate of change; if it detects a rapid upward trend in flow rate and dryness, it will make a prediction based on this that the material flow state in the future control period, for example, after 0.5 seconds, will be high flow and dry; the subsequent optimization solving sub-step then makes decisions based on this predicted material flow state rather than the current state; the controller 500 calls the dynamic mechanism model, which integrates the predicted material state, the wind speed disturbance data obtained from the anemometer 220, and the mathematical relationship between the flow rate of different spray gun combinations and the final dust concentration, exhaust humidity of the spray gun action; this dynamic mechanism model is established by system identification method during the equipment debugging stage. The logical steps of its establishment are as follows: Data acquisition: during debugging, the controller 500 applies a series of pre-set, dynamically changing test control signals to the atomizing spray gun 230, for example, fast start-stop or pseudo-random sequence signals under different duty cycles to simulate different spray actions.

[0027] Response recording: in this process, the wind speed disturbance data from the anemometer 220, the dust concentration data from the turbidity sensor 410, and the exhaust humidity data from the humidity sensor 420 are recorded synchronously at high speed.

[0028] Model identification: the test spray gun control signal and the measured wind speed disturbance are used as input data of the model, and the measured dust concentration and exhaust humidity are used as output data of the model; a data-driven identification algorithm, such as an ARX model identification based on least squares or a recurrent neural network RNN, is used to fit these input-output time series data.

[0029] Model solidification: a mathematical model is obtained that can accurately describe how spray gun action and wind speed disturbance dynamically affect dust concentration and exhaust humidity together, i.e., a dynamic mechanism model, which is solidified in the controller 500 for real-time calling by the optimization solving step.

[0030] The calculation logic of the optimization solving sub-step is essentially to solve a constrained optimization problem. The objective function is to minimize the cumulative dust concentration predicted by the dynamic mechanism model in the future short time domain, for example, in the next control period, under the premise of meeting the constraints.

[0031] The calculation logic can be expressed as: Minimization objective: ; Constraints: For all ; For all ; The meanings of the letters involved are not clearly stated in the original text: The dynamic mechanism model predicts the future... Dust concentration for each control cycle.

[0032] The dynamic mechanism model predicts the future... The exhaust humidity is controlled for each cycle.

[0033] : The preset maximum allowable threshold for exhaust humidity, i.e., the constraint condition.

[0034] The controller 500 will output in the future... The spray gun control action for each control cycle, such as PWM duty cycle.

[0035] and The physical limitations of spray gun control actions, such as , .

[0036] The number of control cycles contained in the prediction time domain of rolling optimization.

[0037] Controller 500 in the current At any given moment, based on this mathematical framework, the future is calculated iteratively. Optimal control sequence of steps However, only the calculated first step of the control action is considered. Send to atomizing spray gun 230 for execution; in the next control cycle When the time comes, the system repeats the entire calculation process described above.

[0038] The controller 500 iteratively calculates using a rolling optimization algorithm to solve the objective function: under the premise of satisfying the exhaust humidity constraint, what start-stop sequence of the atomizing spray gun 230 should be used to minimize the predicted dust concentration; the calculated optimal start-stop sequence is immediately sent to the atomizing spray gun 230 for execution. In this way, when the high-flow-rate dried material actually arrives at the discharge port, the matched and enhanced mist field has already been pre-positioned, thereby effectively suppressing dust generation.

[0039] It also includes sensor status self-diagnosis and degradation steps: Verification: The controller 500 continuously runs a consistency verification logic, cross-comparing the data streams of the power monitor 120, the acoustic probe 320 and the industrial camera 310; Diagnosis: When a persistent data discrepancy is detected, a specific sensor is determined to be malfunctioning; Degradation: The controller 500 immediately triggers a dynamic control strategy degradation procedure, activating a pre-trained, fault-sensor-independent degraded soft-sensor model, based on the fault and pre-failure material characteristic parameters.

[0040] In this embodiment, to improve the system’s reliability in harsh mine environments, a sensor state self-diagnosis and degradation step is added; the verification logic continuously runs in the background in the controller 500, which cross-comparisons the data from the power monitor 120, the acoustic probe 320 and the industrial camera 310 in real time. The data of the three should have a certain correlation under normal working conditions. The diagnosis step is triggered when a persistent data discrepancy is detected, for example, when the image of the industrial camera 310 shows that the material curtain section is zero due to lens contamination, but the signals of the power monitor 120 and the acoustic probe 320 both show that there is high-flow material, the system determines that the industrial camera 310 is malfunctioning after a few seconds of persistent discrepancy. Once the diagnosis is established, the system does not stop running, but executes the degradation procedure; the controller 500 will activate the most matched degraded soft-sensor model from the pre-stored model library, based on the fault, which sensor is failed and the pre-failure material characteristic parameters, for example, whether the material before failure is dry and hard lump ore or wet and sticky fine ore. This degraded model is pre-trained during the debugging stage, and its feature is that it does not rely on the data of the malfunctioning sensor, for example, only using power and acoustic data for estimation; this dynamic degradation method, although sacrifices part of the control accuracy, ensures that the entire adaptive dust suppression function can continue to run when a single sensing component fails, avoiding the complete system failure.

[0041] Embodiment 2 Please refer to Figures 1-3 A mining transportation device with a discharge port dust suppression mechanism, the device comprising: A conveyor end 100 for conveying material; A dust suppression cover 200 fixedly connected to the discharge port position of the conveyor end 100; A power monitor 120 for monitoring the motor load current driving the conveyor; A sensing array 300 comprising an industrial camera 310 and an acoustic probe 320, the industrial camera 310 being fixed to the frame of the dust suppression cover 200, and the acoustic probe 320 being fixed to the conveyor end 100; An atomizing spray gun 230 arrayedly installed on the inner wall of the dust suppression cover 200; The state monitor 400 includes a turbidity sensor 410 and a humidity sensor 420 installed in the exhaust pipe 210 of the dust suppression cover 200. The anemometer 220 is installed inside the exhaust pipe 210. The controller 500 is connected to the power monitor 120, the sensing array 300, the atomizing spray gun 230, the state monitor 400, and the anemometer 220, respectively.

[0042] The ore mining and transporting device with a discharge port dust suppression mechanism provided in the embodiment has a structure that provides a physical carrier for implementing the above method; the conveyor end 100 is the source of the material; the dust suppression cover 200 is wrapped around the discharge port to form a basic space for suppressing the spread of dust, and the atomizing spray gun 230 is installed on the inner wall thereof for generating a mist field; the power monitor 120 is installed at the conveyor drive motor for obtaining the motor load current; the sensing array 300 is the core input unit, and the industrial camera 310 and the acoustic probe 320 thereof are used to capture the form and vibration information of the material flow; the exhaust pipe 210 is used to maintain the air pressure balance in the cover, and the anemometer 220 is installed inside the exhaust pipe 210 to monitor the environmental wind disturbance, and the state monitor 400 is also installed; the turbidity sensor 410 and the humidity sensor 420 in the state monitor 400 measure the final discharged dust concentration and humidity, respectively, as feedback signals for system control; the controller 500 is the central part of the entire device, and a programmable logic controller 500 such as a Siemens S7-1500 type or an industrial computer such as a Beckhoff C6930 type can be selected, which is connected to all the above-mentioned sensing and executing components, respectively, and is responsible for data collection, operation, and instruction issuance.

[0043] The acoustic probe 320 is a piezoelectric contact microphone, which is tightly fixed to the outer wall of the bottom plate of the discharge chute 110 through a rigid connection seat.

[0044] In the embodiment, the acoustic probe 320 has a clear functional orientation in the installation mode. The probe is a piezoelectric contact microphone; it is not suspended in the air, but is tightly fixed to the outer wall of the bottom plate of the discharge chute 110 through a rigid connection seat, such as a metal L-shaped bracket; the discharge chute 110 itself is used to converge the material flow; the purpose of this installation mode is to use the metal bottom plate of the discharge chute 110 as an acoustic waveguide; when the material rubs and collides with the chute bottom plate, the structural vibration generated will be directly transmitted to the rigidly connected acoustic probe 320; this design can effectively pick up the structural vibration soundprint with high signal-to-noise ratio, and mechanically filter out the interference noise from the air, such as the high-frequency wind noise and water spraying sound generated when the atomizing spray gun 230 is working, to ensure that the vibration signal obtained by the controller 500 mainly comes from the impact of the material itself.

[0045] The structure vibration soundprint directly reflects the granularity distribution and impact kinetic energy of the material, and is one of the key input features for the controller 500 to estimate the instantaneous flow rate and apparent moisture content; The industrial camera 310 is a high-speed industrial camera, and a high-brightness LED stroboscopic light source is fixed beside the lens of the industrial camera 310 through the same mounting bracket and is synchronously triggered.

[0046] In the embodiment, the configuration of the industrial camera 310 is to solve the problem of clear imaging of high-speed moving objects; the camera selects a high-speed industrial camera 310, for example, the acA1920-155um model of Basler Company, which has a high frame rate characteristic; more importantly, a high-brightness LED stroboscopic light source is fixed beside the lens of the industrial camera 310 through the same mounting bracket and is synchronously triggered. The high-brightness LED stroboscopic light source is controlled by the controller 500 to make the light pulse strictly synchronized with the shutter opening of the camera; its function is to provide high-intensity illumination for a very short time, for example, tens of microseconds, during the exposure of the camera. Such a short exposure time is sufficient to freeze the high-speed falling ore material and effectively eliminates motion blur. This makes each frame of image obtained by the controller 500 from the camera clear and visible, providing a high-quality data basis for subsequent image segmentation, material curtain cross-section contour extraction and surface texture analysis.

[0047] The power monitor 120 is a high-precision wide-frequency current transformer, which is non-contact clamped on the main power cable of the motor driving the conveyor.

[0048] In the embodiment, the selection and installation mode of the power monitor 120 take into account the precision and convenience; the monitor selects a high-precision wide-frequency current transformer, for example, the IT400-S series product of LEM Company in Switzerland, which can accurately respond to the current fluctuation caused by the change of motor load; its installation mode is a non-contact clamping structure; this means that during installation, only the induction ring of the transformer needs to be opened and clamped on the main power cable of the motor driving the conveyor, without the need to cut off the cable or series in the main circuit; this design ensures the safety and convenience of installation and maintenance on the one hand, and the non-contact measurement does not produce any electrical interference to the original power system, so that it can stably measure the load current flowing through the motor, and the current value is used to convert the reference mass flow of the material carried by the conveyor.

[0049] The atomizing spray gun 230 is controlled by an independent electrically controlled high-frequency pulse width modulation valve.

[0050] In the present embodiment, the atomizing lances 230 are provided with the ability of fine adjustment. Each atomizing lance 230 constituting the array is connected with an independent electrically controlled high-frequency pulse width modulation valve on its water inlet pipeline; this valve, for example, a small high-speed electromagnetic valve, receives a pulse width modulation control signal from the controller 500. Instead of adjusting the valve opening degree by analog voltage, the controller 500 sends a high-frequency digital pulse signal, and controls the average opening time of the valve by adjusting the duty cycle of the pulse, that is, the proportion of the conduction time in a cycle. For example, a 50% duty cycle means that the valve is opened for a cumulative time of 0.5 seconds in one second; due to the high switching frequency of the valve, the response of the water flow shows a smooth flow change. This independent control method allows the controller 500 to quickly and accurately adjust the flow of any lance in the array from 0 to 100%, so that the shape, concentration and coverage area of the fog field can be dynamically reconstructed to match the complex start-stop timing calculated by the optimal atomization strategy prediction control step.

[0051] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, not limit the present application. Although the present application has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present application can be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present application.

Claims

1. A method of transporting ore for mining with a dust suppression mechanism at a discharge opening, characterized by, The method comprises the following steps: Material flow characteristic soft measurement: the controller (500) fuses the current signal of the power monitor (120), the vibration signal of the acoustic probe (320), and the image signal of the industrial camera (310) to estimate the instantaneous flow rate and apparent moisture content of the material in real time; Optimal atomization strategy predictive control: the controller (500) combines the wind speed disturbance data of the anemometer (220) to perform rolling optimization through a dynamic mechanism model based on the estimated instantaneous flow rate and apparent moisture content, and outputs control instructions to the atomization spray gun (230); Feedback constraint and closed loop: the controller (500) minimizes the dust concentration measured by the turbidity sensor (410) as an objective function during optimization, and sets the exhaust humidity measured by the humidity sensor (420) not to exceed a preset threshold as a constraint condition.

2. The method for transporting the ore for mining with the dust suppression mechanism at the discharge port according to claim 1, wherein, The material flow characteristic soft measurement step specifically comprises: Collection: the power monitor (120) acquires the motor load current as a reference mass flow, the acoustic probe (320) picks up the structural vibration soundprint of the material impact, and the industrial camera (310) acquires the instantaneous cross-sectional profile of the material through high-brightness LED stroboscopic light source exposure; Fusion estimation: a deep neural network model in the controller (500) receives the current signal, the vibration soundprint, and the cross-sectional profile, performs multi-modal fusion calculation, and outputs the estimated values of the instantaneous flow rate and apparent moisture content.

3. A method of transporting ore for mining with a dust suppression mechanism at the discharge opening as claimed in claim 2, wherein, The deep neural network model is established through the following steps: In the debugging phase, historical working condition data sets are collected, and the current signal of the power monitor (120), the vibration signal of the acoustic probe (320), and the image signal of the industrial camera (310) are synchronously recorded as input features of the model; A high-precision weighing hopper is used for periodic offline calibration to obtain a reference mass flow, and the reference apparent moisture content is obtained by drying the intercepted material sample, and the reference flow rate and apparent moisture content data are used as supervision labels of the model; The internal weights of the model are adjusted to establish a nonlinear mapping relationship from the three sensor input features to the supervision labels.

4. The method for transporting ore for mining with dust suppression mechanism at discharge port according to claim 1, characterized in that, The optimal atomization strategy predictive control step specifically comprises: Prediction: the controller (500) establishes a short-time prediction model based on the change rates of the instantaneous flow rate and apparent moisture content to calculate the material flow state in the future control period; Optimization solution: the controller (500) determines the start-stop timing of the atomization spray gun (230) by solving the objective function through a rolling optimization algorithm based on the material flow state, the wind speed disturbance data, and the dynamic mechanism model describing the relationship between spray gun action and the dust concentration and the exhaust humidity.

5. The method for transporting ore for mining with dust suppression mechanism at discharge port according to claim 1, characterized in that, It also includes a sensor state self-diagnosis and degradation step: Verification: the controller (500) continuously runs a consistency verification logic to cross-compare the data streams of the power monitor (120), the acoustic probe (320), and the industrial camera (310); Diagnosis: when a persistent data difference is detected, it is determined that a specific sensor has failed; Degradation: the controller (500) immediately triggers a dynamic control strategy degradation procedure, activates a pre-trained, degradation version soft-sensing model independent of the fault sensor according to the fault and pre-failure material characteristic parameters.

6. A mineral extraction conveyor having a dust suppression mechanism at a discharge opening for carrying out the method of mineral extraction according to any one of claims 1 to 5, characterized in that The device comprises: a conveyor end (100) for conveying material; a dust suppression hood (200) fixed to the discharge port position of the conveyor end (100); a power monitor (120) for monitoring the motor load current driving the conveyor; a perception array (300) comprising an industrial camera (310) fixed to the frame of the dust suppression hood (200) and an acoustic probe (320) fixed to the conveyor end (100); an atomizing spray gun (230) arrayed on the inner wall of the dust suppression hood (200); a state monitor (400) comprising a turbidity sensor (410) and a humidity sensor (420) installed in the exhaust duct (210) of the dust suppression hood (200); an anemometer (220) installed inside the exhaust duct (210); a controller (500) connected to the power monitor (120), the perception array (300), the atomizing spray gun (230), the state monitor (400) and the anemometer (220) respectively.

7. A mine ore conveying device with a dust suppression mechanism for the discharge opening according to claim 6, characterized in that, The conveyor end (100) is provided with a discharge chute (110), and the acoustic probe (320) is a piezoelectric contact microphone fixed to the outer wall of the bottom plate of the discharge chute (110) through a rigid connecting seat.

8. The ore mining and transporting apparatus having a dust suppression mechanism for the discharge port according to claim 6, wherein, The industrial camera (310) is a high-speed industrial camera (310) fixed with a synchronous trigger high-brightness LED stroboscopic light source through the same mounting bracket beside the lens of the industrial camera (310).

9. The ore mining and transporting apparatus having a dust suppression mechanism for the discharge opening according to claim 6, wherein, The power monitor (120) is a high-precision wide-frequency current transformer non-contact clamp on the main power supply cable of the motor driving the conveyor.

10. The ore mining and transporting apparatus having a dust suppression mechanism for the discharge opening according to claim 6, wherein, The atomizing spray gun (230) is controlled by an independent electrically controlled high-frequency pulse width modulation valve.

Images