Control method and system for dust removal device of whole vehicle railway tunnel

Abstract

The invention provides a control method and system for a whole vehicle railway tunnel dust removal device, and the method comprises the steps: carrying out the acceleration detection of a transmission path of a folding conveying belt of the railway tunnel dust removal device, and determining a node transmission stability sequence based on the transmission acceleration of each path node of the transmission path; performing electrostatic adsorption detection on the current transmission belt node to obtain electrostatic adsorption quality characteristics of the current transmission belt node; the method comprises the steps of performing feature learning according to electrostatic adsorption quality features, determining the transmission diffusivity of nodes of a current folding conveying belt, determining a first transmission speed based on the transmission diffusivity, performing real-time correction on the first transmission speed according to a node transmission stability sequence, and controlling the folding conveying belt to perform transmission based on a second transmission speed after real-time correction. The conveying speed of the folding conveying belt can be controlled based on the electrostatic adsorption quality characteristics, and the risk of reentrainment of dust in the conveying process of the folding conveying belt is reduced.

Description

Technical Field

[0001] The present application relates to the technical field of conveyor belt control, and more specifically, to a control method and system for a whole-vehicle railway tunnel dust removal device. Background Art

[0002] The railway tunnel dust removal device is mainly used to treat the sand damage caused by locomotive sand spreading operations in long and steep tunnels; the device mainly includes working parts such as power unit, pipeline system, dust box (including ash hopper and discharger), horizontal conveyor belt and folding conveyor belt; when the device is in operation, the sand particles scattered by the locomotive are collected and transported to the dust box through the pipeline; the sand particles are initially separated at the upper part of the dust box and then settled in the ash hopper below, and then discharged by the discharger at the bottom of the ash hopper and fall to the horizontal conveyor belt; then, the material is transported to the folding conveyor belt via the horizontal conveyor belt, and finally transported to the material transport vehicle for storage, and then transported out of the tunnel; This can effectively control tunnel sand damage, reduce the spread of sand and dust, indirectly achieve dust removal effects inside the tunnel, and improve the tunnel environment.

[0003] As an important component for conveying sand and dust materials, the folding conveyor belt is widely used in the construction and maintenance of railway tunnels, especially for conveying residual sand and dust generated by sand spreading operations from the inside of the tunnel to the outside. However, due to the complex tunnel environment and limited space, the folding conveyor belt is often disturbed by the vibration of the equipment body and uneven road surface during operation, causing periodic or sudden bumps and shaking in the conveying path, resulting in loosening, jumping, and sliding of sand on the conveyor belt, thereby causing secondary dust. It not only affects the dust removal effect, but may also cause secondary pollution of the equipment or wear and dust accumulation in key parts, which seriously limits the stable application and promotion of the folding conveyor belt in the dust removal scene of railway tunnels. Therefore, how to suppress the dust risk caused by vibration and improve the transmission stability of the folding conveyor belt under complex working conditions has become one of the key technical issues that need to be solved urgently. Summary of the invention

[0004] The present application provides a control method and system for a whole-vehicle railway tunnel dust removal device, which can control the transmission speed of a folded conveyor belt based on the electrostatic adsorption quality characteristics, thereby reducing the risk of secondary dust emission during the transmission process of the folded conveyor belt.

[0005] In a first aspect, the present application provides a control method for a whole-vehicle railway tunnel dust removal device, which can be executed by a network device, or can also be executed by a chip configured in the network device, and the present application does not limit this.

[0006] Specifically, the method includes: Perform acceleration detection on the transmission path of the folding conveyor belt of the railway tunnel dust removal device, and determine the node transmission smoothness sequence based on the transmission acceleration of each path node on the transmission path; Perform real-time detection on the current transmission quality of the folding conveyor belt, and determine whether the current conveyor belt node meets the transmission conditions according to the current transmission quality; If the conveyor belt node meets the transmission conditions, perform electrostatic adsorption detection on the current conveyor belt node to obtain the electrostatic adsorption quality characteristics of the current conveyor belt node; Perform feature learning from the electrostatic adsorption quality characteristics to determine the transmission diffusion degree of the current folding conveyor belt node, determine the first transmission speed based on the transmission diffusion degree, and perform real-time correction on the first transmission speed according to the node transmission smoothness sequence, and control the folding conveyor belt to transmit based on the second transmission speed after real-time correction.

[0007] Combined with the first aspect, in some implementation manners of the first aspect, determining the node transmission smoothness sequence based on the transmission acceleration of each path node on the transmission path specifically includes: Obtain the acceleration detection information corresponding to each path node on the transmission path during the transmission process; Extract the vibration intensity for the acceleration detection information corresponding to any one path node to obtain a plurality of vibration intensity characteristics, and determine the node transmission smoothness corresponding to the path node based on the characteristic mean of the vibration intensity characteristics; According to the label order of the path nodes, form the node transmission smoothness corresponding to each path node into the node transmission smoothness sequence.

[0008] Combined with the first aspect, in some implementation manners of the first aspect, during the process of determining whether the current conveyor belt node meets the transmission conditions according to the current transmission quality, taking the current transmission quality being higher than the preset transmission quality threshold as the transmission condition.

[0009] Combined with the first aspect, in some implementation manners of the first aspect, performing feature learning from the electrostatic adsorption quality characteristics to determine the transmission diffusion degree of the current folding conveyor belt node specifically includes: Obtain the preset feature learning depth, and extract a plurality of corresponding electrostatic adsorption qualities and their corresponding vibration intensity characteristics in the electrostatic adsorption quality characteristics based on the feature learning depth; Perform associated feature learning based on a plurality of electrostatic adsorption qualities and their corresponding vibration intensity characteristics to obtain a vibration influence factor; Correct the electrostatic adsorption quality characteristics based on the vibration influence factor, perform feature clustering on the corrected electrostatic adsorption quality characteristics, and determine the transmission diffusion degree of the current folding conveyor belt node based on the clustering result.

[0010] In combination with the first aspect, in some implementations of the first aspect, a single-hidden-layer neural network model is used to perform feature clustering on the corrected electrostatic adsorption quality features.

[0011] In combination with the first aspect, in some implementations of the first aspect, the real-time correction of the first transmission speed based on the node transmission smoothness sequence specifically includes: obtaining the current path node, determining the node transmission smoothness corresponding to the current path node based on the node transmission smoothness sequence, and performing proportional correction on the first transmission speed according to the node transmission smoothness to obtain a second transmission speed.

[0012] In combination with the first aspect, in some implementations of the first aspect, during the process of controlling the folding conveyor belt to transmit based on the real-time corrected second transmission speed, a closed-loop speed controller is used to adjust the motor output of the folding conveyor belt in real time.

[0013] In a second aspect, the present application provides a control system for a vehicle railway tunnel dust removal device, which includes a conveyor belt control unit, and the conveyor belt control unit includes: A conveyor belt detection module, configured to detect the acceleration of the transmission path of the folding conveyor belt of the railway tunnel dust removal device, and determine a node transmission smoothness sequence based on the transmission accelerations of each path node of the transmission path; A transmission judgment module, configured to perform real-time detection on the current transmission quality of the folding conveyor belt, and judge whether the current conveyor belt node meets the transmission conditions according to the current transmission quality; A conveyor belt control module, configured to perform electrostatic adsorption detection on the current conveyor belt node when the conveyor belt node meets the transmission conditions, to obtain the electrostatic adsorption quality feature of the current conveyor belt node; The conveyor belt control module is further configured to perform feature learning on the electrostatic adsorption quality feature, determine the transmission diffusion degree of the current folding conveyor belt node, determine a first transmission speed based on the transmission diffusion degree, perform real-time correction on the first transmission speed according to the node transmission smoothness sequence, and control the folding conveyor belt to transmit based on the real-time corrected second transmission speed.

[0014] In a third aspect, the present application provides a computer terminal device, which includes a memory and a processor, the memory stores code, and the processor is configured to obtain the code and execute the above-mentioned control method for a vehicle railway tunnel dust removal device.

[0015] Fourthly, the present application provides a computer-readable storage medium storing at least one computer program, which is loaded and executed by a processor to implement the operations performed by the above-mentioned control method for a vehicle-mounted railway tunnel dust removal device.

[0016] The technical solutions provided by the disclosed embodiments of the present application have the following beneficial effects: In the control method and system for a vehicle-mounted railway tunnel dust removal device provided by the present application, first, the acceleration of the transmission path of the folding conveyor belt of the railway tunnel dust removal device is detected, and the node transmission smoothness sequence is determined based on the transmission acceleration of each path node of the transmission path; the current transmission quality of the folding conveyor belt is detected in real time, and it is judged whether the current conveyor belt node meets the transmission conditions according to the current transmission quality; if the conveyor belt node meets the transmission conditions, the electrostatic adsorption detection is performed on the current conveyor belt node to obtain the electrostatic adsorption quality characteristics of the current conveyor belt node; feature learning is performed from the electrostatic adsorption quality characteristics to determine the transmission diffusion degree of the current folding conveyor belt node, the first transmission speed is determined based on the transmission diffusion degree, and the first transmission speed is corrected in real time according to the node transmission smoothness sequence, and the folding conveyor belt is controlled to transmit based on the second transmission speed after real-time correction.

[0017] It can be seen that in the present application, by simulating the electrostatic dust removal mechanism, after the dust particles are adsorbed by the electrode plate at the current conveyor belt node, the adhesion quality of the particles on the electrode surface is detected. The higher the adsorption quality, the easier it is for the dust to be stripped and adsorbed by the electric field, indicating that the particles are looser and have poorer adhesion, which also means that these particles are more likely to be lifted during vibration or accelerated transmission. Therefore, the electrostatic adsorption quality characteristics are used as the characterization basis for the transmission diffusion degree of the ash and sand during the transmission process. The transmission speed of the folding conveyor belt is corrected once based on the transmission diffusion degree, and the transmission smoothness of different path nodes is determined according to the vibration intensity during the transmission process. The transmission speed of the folding conveyor belt is corrected twice based on the transmission smoothness, realizing the adaptive control of the conveyor belt speed based on the adhesion characteristics of the ash and sand and the vibration condition of the transmission path, reducing the suspension and diffusion of dust particles caused by the transmission process, and improving the dust suppression ability and working stability of the folding conveyor belt in the railway tunnel environment.

[0018] In summary, the present application can control the transmission speed of the folding conveyor belt based on the electrostatic adsorption quality characteristics, reducing the risk of secondary dust generation during the transmission of the folding conveyor belt. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is an exemplary flowchart of a control method for a vehicle-mounted railway tunnel dust removal device according to some embodiments of the present application; Figure 2is the overall structure diagram of the railway tunnel dust removal device provided by this application; Figure 3 is the schematic structural diagram of the conveyor belt control unit shown in some embodiments of this application; Figure 4 is the schematic structural diagram of a computer terminal device for implementing a control method for a complete vehicle railway tunnel dust removal device shown in some embodiments of this application. Detailed implementation manners

[0020] This application detects the acceleration of the transmission path of the folding conveyor belt of the railway tunnel dust removal device, determines the node transmission smoothness sequence based on the transmission accelerations of each path node of the transmission path; detects the current transmission quality of the folding conveyor belt in real time, and determines whether the current conveyor belt node meets the transmission conditions according to the current transmission quality; if the conveyor belt node meets the transmission conditions, performs electrostatic adsorption detection on the current conveyor belt node to obtain the electrostatic adsorption quality characteristics of the current conveyor belt node; performs feature learning from the electrostatic adsorption quality characteristics to determine the transmission diffusion degree of the current folding conveyor belt node, determines the first transmission speed based on the transmission diffusion degree, and performs real-time correction on the first transmission speed according to the node transmission smoothness sequence, and controls the folding conveyor belt to transmit based on the second transmission speed after real-time correction, which can control the transmission speed of the folding conveyor belt based on the electrostatic adsorption quality characteristics and reduce the risk of secondary dust generation during the transmission of the folding conveyor belt.

[0021] To better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the specification drawings and specific implementation manners. Refer to Figure 1 , this figure is an exemplary flowchart of a control method for a complete vehicle railway tunnel dust removal device shown in some embodiments of this application. The control method 100 for the complete vehicle railway tunnel dust removal device mainly includes the following steps: In step S101, detect the acceleration of the transmission path of the folding conveyor belt of the railway tunnel dust removal device, and determine the node transmission smoothness sequence based on the transmission accelerations of each path node of the transmission path.

[0022] It should be noted that in this application, the main components of the overall machine of the railway tunnel dust removal device are as Figure 2 shown, where 1 is the control system, 2 is the folding conveyor belt, 3 is the horizontal conveyor belt, 4 is the dust collection box, 4-1 is the ash hopper, 4-2 is the discharger, 5 is the pipeline, and 6 is the power unit.

[0023] It should be noted that the transmission path of the folding conveyor belt described in this application is the placement path of the folding conveyor belt, and the path nodes are multiple position intervals separated based on the transmission path of the folding conveyor belt. Optionally, in some embodiments, the acceleration of the transmission path of the folding conveyor belt of the railway tunnel dust removal device can be detected by a three-axis acceleration sensor. Among them, the three-axis acceleration sensor includes three acceleration detection directions of X, Y, and Z. The three-axis acceleration sensor can be installed on any transmission belt node, and when the horizontal transmission belt conveys materials on the transmission path, the path node where the transmission belt node is located and the acceleration detection information are output until the acceleration detection information corresponding to each path node is output.

[0024] Optionally, in some embodiments, the node transmission smoothness sequence described in this application includes multiple node transmission smoothness and the corresponding path nodes respectively. The node transmission smoothness is used to quantify the transmission smoothness degree on this path node. Specifically, when implemented, determining the node transmission smoothness sequence based on the transmission accelerations of each path node of the transmission path specifically includes: Obtain the acceleration detection information corresponding to each path node of the transmission path during the transmission process; Extract the vibration intensity from the acceleration detection information corresponding to any one path node to obtain multiple vibration intensity features, and determine the node transmission smoothness corresponding to this path node based on the feature mean of the vibration intensity features; According to the label order of the path nodes, form the node transmission smoothness sequence with the node transmission smoothness corresponding to each path node respectively.

[0025] Among them, during the process of extracting the vibration intensity from the acceleration detection information corresponding to any one path node to obtain multiple vibration intensity features, the acceleration detection information corresponding to the path node is multiple discrete three-dimensional acceleration detection information, and each three-dimensional acceleration detection information is obtained by equally spaced acceleration detection through a three-dimensional acceleration sensor, and one vibration intensity feature is respectively extracted for each three-dimensional acceleration detection information.

[0026] Specifically, when implemented, the vibration intensity feature can be determined according to the following formula:

[0027] Wherein, is the extracted vibration intensity feature, 、 and are the xyz three-axis acceleration values of the three-dimensional acceleration detection information corresponding respectively, 、 、 They are the vibration intensity weights corresponding to the x, y, and z axes respectively, and are calibrated as constants based on experience.

[0028] Preferably, in some embodiments, the node transmission smoothness corresponding to this path node = the preset standard vibration intensity feature / the feature mean of the multiple vibration intensity features corresponding to this path node.

[0029] In step S102, the current transmission quality of the folding conveyor belt is detected in real time, and it is judged whether the current conveyor belt node meets the transmission conditions according to the current transmission quality.

[0030] It should be noted that the current conveyor belt node is a local area or monitoring point with independent detection and control functions in the transmission path of the horizontal conveyor belt or the folding conveyor belt. The current transmission quality is used to indicate the instant material state of the conveyor belt node under the discharger. A pressure sensor or a weighing module is arranged at this node to collect the mass data of the material when it falls onto the conveyor belt after being discharged through the discharger. By comprehensively analyzing information such as the load value, stacking thickness, and distribution uniformity of the material at this position, a material detection quality index corresponding to the node is formed. This material detection quality is the current transmission quality, which is used to judge whether this node meets the transmission stability requirements. If it meets, it enters the next electrostatic adsorption detection and speed correction control process. Optionally, in some embodiments, a weighing sensor is used to detect the current transmission quality of the folding conveyor belt in real time.

[0031] Optionally, in some embodiments, in the process of judging whether the current conveyor belt node meets the transmission conditions according to the current transmission quality, taking the current transmission quality being higher than the preset transmission quality threshold as the transmission condition. Specifically, when implementing, to ensure the safe operation of the conveyor belt, an effective interval range of the current transmission quality can also be preset. When the detected current transmission quality is within the effective interval range, it is judged that the transmission conditions are met.

[0032] In step S103, if the conveyor belt node meets the transmission conditions, an electrostatic adsorption detection is performed on the current conveyor belt node to obtain the electrostatic adsorption quality feature of the current conveyor belt node.

[0033] It should be noted that in this application, through electrostatic adsorption detection, the adsorption process of the electrostatic precipitator is simulated, so as to evaluate the adhesion and dust emission risk of the material on the conveyor belt (mainly dust or sand dust particles). Specifically, it is quantified by the difference in the electrostatic adsorption efficiency of particles under the same transmission quality. For example, a local electrostatic adsorption unit is set, so that the particles are under the action of a high-voltage electric field when passing through this detection area. The dust particles are adsorbed onto the electrode plate in the electric field, and the adhesion of the dust and the dust emission trend are indirectly determined by the proportion of the adsorbed particles or the mass difference of the residual particles after adsorption.

[0034] It should be noted that the electrostatic adsorption quality described in this application refers to the ratio of the mass of adsorbed particles to the total mass of transported dust after the adsorption treatment of unit mass dust under the action of an electric field through the simulation of the electrostatic adsorption method in a specific transport node area. The larger the electrostatic adsorption quality, the weaker the adhesion force between dust particles, the easier it is to be stripped by the electric field, and the higher the risk of dust emission; on the contrary, the stronger the particle adhesion and the more stable the dust deposition. Optionally, in some embodiments, the electrostatic adsorption detection is performed on the current conveyor belt node through a high-voltage electrode group. Specifically, when implemented, an electrostatic adsorption detection unit is established above or beside the current conveyor belt node. The electrostatic adsorption detection unit consists of a high-voltage electrode group and a corresponding capacitance sensor. Among them, the high-voltage electrode group includes a corona wire and a micro dust collection electrode plate. By applying a negative high voltage, an electrostatic adsorption field is simulated, and the electrostatic adsorption field is a non-persistent electric field, and the detection process is locally triggered for a short time. The dust adhesion mass on the micro electrode plate is detected by the capacitance sensor as the electrostatic adsorption quality.

[0035] It should be noted that the capacitance is determined by the insulating medium (dielectric layer) between two conductors. When dust adheres to the surface of the micro electrode plate, it is equivalent to adding a layer of medium with a certain dielectric constant between the micro electrode plate and the counter electrode, which will cause a change in the capacitance between the plates. The more dust adheres, the thicker the effective dielectric layer, resulting in a regular change in the measured capacitance value, which can be detected by a highly sensitive capacitance sensor, thereby indirectly judging the mass of the adhered dust. In some specific embodiments of this application, one side of the capacitance is a conductive electrode plate (i.e., the dust accumulation micro electrode plate), and an insulating substrate and a lower electrode are arranged coplanar with the conductive electrode plate to form a capacitor plate structure; the capacitance sensor is connected between the upper and lower electrodes to form a capacitance measurement circuit. Among them, the MEMS micro capacitance detection chip performs capacitance detection and performs linear mapping based on the capacitance detection value to obtain the corresponding electrostatic adsorption quality.

[0036] Preferably, in some embodiments, in this application, the electrostatic adsorption field is a non-persistent electric field, and the detection process is locally triggered for a short time. After the electrostatic adsorption quality detection is completed, the plate is vibrated and impacted regularly or quantitatively through a mechanical vibration device. The vibration effect loosens the particles attached to the surface of the plate and slides down along the surface of the plate into the bottom ash hopper, thereby realizing the collection and removal of particles and facilitating repeated detection of different transport states. Specifically, when implemented, the electrostatic adsorption quality corresponding to each path node can be detected separately during the transport process, and a multi-dimensional feature vector is formed according to the path node sequence as the electrostatic adsorption quality feature.

[0037] In step S104, feature learning is performed based on the electrostatic adsorption mass feature to determine the transmission diffusion degree of the current folding conveyor belt node. Based on the transmission diffusion degree, a first transmission speed is determined, and the first transmission speed is corrected in real time according to the node transmission smoothness sequence. The folding conveyor belt is controlled to transmit based on the second transmission speed after real-time correction.

[0038] It should be noted that the transmission diffusion degree in this application is used to quantify the diffusion degree of dust particles during the transmission process under the transmission state of the current conveyor belt node. Feature learning is performed based on the electrostatic adsorption mass feature to determine the transmission diffusion degree of the current folding conveyor belt node. The real-time electrostatic adsorption mass detection also avoids the interference of environmental changes on the risk of secondary dust generation. Preferably, in some embodiments, the feature learning based on the electrostatic adsorption mass feature to determine the transmission diffusion degree of the current folding conveyor belt node specifically includes: Obtain a preset feature learning depth, and extract a plurality of corresponding electrostatic adsorption masses and respectively corresponding vibration intensity features in the electrostatic adsorption mass feature based on the feature learning depth; Perform correlation feature learning based on a plurality of electrostatic adsorption masses and respectively corresponding vibration intensity features to obtain a vibration influence factor; Correct the electrostatic adsorption mass feature based on the vibration influence factor, perform feature clustering on the corrected electrostatic adsorption mass feature, and determine the transmission diffusion degree of the current folding conveyor belt node based on the clustering result.

[0039] Specifically, when implemented, the preset feature learning depth is K: which represents the number of samples extracted from the nearest K nodes. Based on the feature learning depth, a plurality of electrostatic adsorption masses closest to the current moment in the electrostatic adsorption mass feature and the vibration intensity features corresponding to the detection time of the electrostatic adsorption mass are extracted, and the Pearson correlation coefficient between the plurality of electrostatic adsorption masses and the respectively corresponding vibration intensity features is used as the vibration influence factor. The larger the vibration influence factor, the greater the interference degree of vibration on dust adhesion and diffusion. It is necessary to perform proportional correction on the electrostatic adsorption mass feature based on the vibration influence factor to improve the accuracy of feature clustering.

[0040] In some specific embodiments of the present application, a single-hidden-layer neural network model is used to perform feature clustering on the corrected electrostatic adsorption quality features, and the transmission diffusion degree of the current folding conveyor belt node is determined based on the clustering result. Specifically, when implementing, during the process of using the single-hidden-layer neural network to perform learning clustering on the corrected electrostatic adsorption quality features, the corrected electrostatic adsorption quality features can be input in the form of data vectors. The input layer receives the above data vectors, the hidden layer is provided with multiple activation function nodes, and the output layer maps the learned features to several predefined clustering categories, and each category represents a different transmission diffusion degree level. Data mapping of the transmission diffusion degree is performed according to the clustering result corresponding to the corrected electrostatic adsorption quality features, and the corresponding mapping value is obtained as the transmission diffusion degree. Among them, different dimensions of the data vector respectively include: the electrostatic adsorption quality corresponding to different path nodes.

[0041] Specifically, when implementing, the system constructs a training set to supervise the single-hidden-layer neural network model to learn the clustering boundary. The training set is composed of electrostatic adsorption quality feature samples of multiple known dusts with different adhesions and their corresponding artificial scoring values of the transmission diffusion degree. During the training process, the samples are input into the single-hidden-layer neural network model for forward propagation, and the output classification label is compared with the artificial scoring value. That is, multiple corrected electrostatic adsorption quality feature samples are input into the single-hidden-layer neural network for classification training. The hidden layer of the single-hidden-layer neural network contains multiple activation function nodes for classifying and training the input samples, and the classification result is output through the output layer of the single-hidden-layer neural network. Then, the classification result is compared with the corresponding artificial scoring value of the transmission diffusion degree. When the correlation (which can use the mean square error value) between the clustering result and the artificial scoring value of the transmission diffusion degree is lower than the preset threshold, the network parameters are optimized through the backpropagation mechanism, and the activation parameters in the activation functions in the hidden layer of the single-hidden-layer neural network are adjusted until the correlation between the clustering result and the artificial scoring value of the transmission diffusion degree reaches the preset standard, and the mapping relationship between the clustering result and the artificial scoring value of the transmission diffusion degree is obtained, and it is determined that the training of this single-hidden-layer neural network model is completed.

[0042] Preferably, in some embodiments, in the process of determining the first transmission speed based on the transmission diffusion degree, interval mapping can be performed according to a preset linear mapping table and the threshold interval corresponding to the transmission diffusion degree to obtain the first transmission speed.

[0043] Optionally, in some other embodiments of the present application, it is also possible to obtain multiple electrostatic adsorption qualities corresponding to the nearest K path nodes and their corresponding vibration intensity features, use multiple linear regression to fit the influence weight of the vibration intensity features on the electrostatic adsorption quality, and form a vibration influence factor. Clustering is performed based on the vibration response factor and the electrostatic adsorption quality features, and the transmission diffusion degree is determined based on the clustering result. The present application does not make a limitation on this.

[0044] Preferably, in some embodiments, the real-time correction of the first transmission speed based on the node transmission smoothness sequence specifically includes: obtaining the current path node, determining the node transmission smoothness corresponding to the current path node based on the node transmission smoothness sequence, and performing proportional correction on the first transmission speed according to the node transmission smoothness to obtain a second transmission speed. When specifically implemented, the K-means clustering algorithm can be used to cluster the node transmission smoothness to obtain multiple cluster centers and the corresponding proportional correction coefficients respectively, and determine the proportional correction coefficient based on the cluster center corresponding to the node transmission smoothness to perform proportional correction on the first transmission speed.

[0045] Preferably, in some embodiments, in the process of controlling the folding conveyor belt to transmit based on the second transmission speed after real-time correction, a closed-loop speed controller can be used to adjust the motor output of the folding conveyor belt in real time based on the second transmission speed. When specifically implemented, the error value between the current conveying speed and the second transmission speed is collected as the controller input, and a control signal is output according to the error using the PID control algorithm to drive the motor speed regulation. Other existing speed feedback control algorithms can also be used for this part of the speed control content, and the present application does not make any limitations in this regard.

[0046] In addition, on the other hand of the present application, in some embodiments, the present application provides a control system for a vehicle railway tunnel dust removal device, and this system includes a conveyor belt control unit. Refer to Figure 3 , this figure is a schematic structural diagram of the exemplary hardware and / or software of the conveyor belt control unit shown according to some embodiments of the present application. The conveyor belt control unit 200 includes: a conveyor belt detection module 201, a transmission judgment module 202, and a conveyor belt control module 203, which are described as follows: The conveyor belt detection module 201 is used to detect the acceleration of the transmission path of the folding conveyor belt of the railway tunnel dust removal device, and determine the node transmission smoothness sequence based on the transmission accelerations of the respective path nodes of the transmission path; The transmission judgment module 202 is used to detect the current transmission quality of the folding conveyor belt in real time, and judge whether the current conveyor belt node meets the transmission conditions according to the current transmission quality; The conveyor belt control module 203 is used to perform electrostatic adsorption detection on the current conveyor belt node when the conveyor belt node meets the transmission conditions, so as to obtain the electrostatic adsorption quality characteristics of the current conveyor belt node; The conveyor belt control module 203 is further used to perform feature learning on the electrostatic adsorption quality characteristics, determine the transmission diffusion degree of the current folding conveyor belt node, determine the first transmission speed based on the transmission diffusion degree, and perform real-time correction on the first transmission speed according to the node transmission smoothness sequence, and control the folding conveyor belt to transmit based on the second transmission speed after real-time correction.

[0047] The above has introduced in detail an example of a control method and system for a vehicle railway tunnel dust removal device provided by the embodiments of the present application. It can be understood that, in order to implement the above functions, the corresponding device includes the corresponding hardware structure and / or software module for executing each function.

[0048] Those skilled in the art should easily realize that, combining the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a certain function in the application is executed in the way of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Therefore, professionals can use different methods to implement the described function for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0049] In addition, the present application also provides a computer terminal device, the computer terminal device includes a memory and a processor, the memory stores code, and the processor is configured to obtain the code and execute the above-mentioned control method for a vehicle railway tunnel dust removal device.

[0050] In some embodiments, refer to Figure 4 , this figure is a schematic structural diagram of a computer terminal device for implementing a control method for a vehicle railway tunnel dust removal device according to some embodiments of the present application. The control method for a vehicle railway tunnel dust removal device in the above embodiments can be implemented by Figure 4 the computer terminal device shown. The computer terminal device 300 includes at least one communication bus 301, a communication interface 302, a processor 303, and a memory 304.

[0051] The processor 303 can be a general central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more for controlling the execution of the control method for a vehicle railway tunnel dust removal device in the present application.

[0052] The communication bus 301 may include a path for transmitting information between the above components.

[0053] The memory 304 can be a read-only memory (ROM) or other types of static storage devices that can store static information and instructions, a random access memory (RAM) or other types of dynamic storage devices that can store information and instructions, or can also be an electrically erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc storage, optical disc storage (including compact discs, laser discs, optical discs, digital versatile discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium that can be used to carry or store the desired program code in the form of instructions or data structures and can be accessed by a computer, but is not limited thereto. The memory 304 can exist independently and be connected to the processor 303 through the communication bus 301. The memory 304 can also be integrated with the processor 303.

[0054] Among them, the memory 304 is used to store the program code for executing the solution of this application and is controlled by the processor 303 for execution. The processor 303 is used to execute the program code stored in the memory 304. The program code can include one or more software modules. The determination of the transmission diffusion degree in the above embodiments can be implemented by one or more software modules in the processor 303 and the program code in the memory 304.

[0055] The communication interface 302 uses any device such as a transceiver to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0056] Optionally, the above computer terminal device 300 can further include a power supply 305 for supplying power to various components or circuits in the real-time computer terminal device.

[0057] In a specific implementation, as an embodiment, the computer terminal device can include multiple processors, and each of these processors can be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, the processor can refer to one or more devices, circuits, and / or processing cores for processing data (such as computer program instructions).

[0058] The above computer terminal device can be a general computer terminal device or a special computer terminal device. In specific implementation, the computer terminal device can be a desktop computer, a portable computer, a network server, a personal digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device or an embedded device. The embodiments of the present application do not limit the type of the computer terminal device.

[0059] In addition, in other aspects of the present application, there is provided a computer-readable storage medium storing at least one computer program, and the computer program is loaded and executed by a processor to implement the operations performed by the above control method for a vehicle railway tunnel dust removal device.

[0060] In summary, in the control method and system for a vehicle railway tunnel dust removal device disclosed in the embodiments of the present application, by detecting the acceleration of the transmission path of the folding conveyor belt of the railway tunnel dust removal device, determining the node transmission smoothness sequence based on the transmission accelerations of the respective path nodes of the transmission path; detecting the current transmission quality of the folding conveyor belt in real time, and judging whether the current conveyor belt node meets the transmission conditions according to the current transmission quality; if the conveyor belt node meets the transmission conditions, detecting the electrostatic adsorption of the current conveyor belt node to obtain the electrostatic adsorption quality characteristics of the current conveyor belt node; performing feature learning from the electrostatic adsorption quality characteristics to determine the transmission diffusion degree of the current folding conveyor belt node, determining the first transmission speed based on the transmission diffusion degree, and performing real-time correction on the first transmission speed according to the node transmission smoothness sequence, and controlling the folding conveyor belt to transmit based on the second transmission speed after real-time correction, it is possible to control the transmission speed of the folding conveyor belt based on the electrostatic adsorption quality characteristics, reducing the risk of secondary dust generation during the transmission of the folding conveyor belt.

[0061] The above are only the embodiments of the present application, and common specific technical solutions or characteristics and the like in the solutions are not described in detail here. It should be noted that for those skilled in the art, without departing from the technical solutions of the present application, several deformations and improvements can be made, and these should also be regarded as the protection scope of the present application, and these will not affect the implementation effect of the present application and the practicability of the patent.

[0062] The protection scope required by the present application shall be subject to the content of its claims, and the specific implementation manners and the like recorded in the specification can be used to interpret the content of the claims. Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present application fall within the scope of the claims of the present application and their equivalent technologies, the present application also intends to include these changes and modifications.

Claims

1. A control method for a dust removal device of a whole vehicle in a railway tunnel, characterized in that, Including: Performing acceleration detection on the transmission path of the folding conveyor belt of the railway tunnel dust removal device, and determining the node transmission smoothness sequence based on the transmission accelerations of each path node on the transmission path; Performing real-time detection on the current transmission quality of the folding conveyor belt, and judging whether the current conveyor belt node meets the transmission conditions according to the current transmission quality; If the conveyor belt node meets the transmission conditions, performing electrostatic adsorption detection on the current conveyor belt node to obtain the electrostatic adsorption quality characteristics of the current conveyor belt node; Performing feature learning from the electrostatic adsorption quality characteristics to determine the transmission diffusion degree of the current folding conveyor belt node, determining the first transmission speed based on the transmission diffusion degree, and performing real-time correction on the first transmission speed according to the node transmission smoothness sequence, and controlling the folding conveyor belt to perform transmission based on the second transmission speed after real-time correction.

2. The method according to claim 1, wherein Determining the node transmission smoothness sequence based on the transmission accelerations of each path node on the transmission path specifically includes: Obtaining the acceleration detection information corresponding to each path node on the transmission path during the transmission process; Extracting the vibration intensity from the acceleration detection information corresponding to any one path node to obtain a plurality of vibration intensity characteristics, and determining the node transmission smoothness corresponding to this path node based on the characteristic mean value of the vibration intensity characteristics; According to the label order of the path nodes, forming the node transmission smoothness corresponding to each path node into the node transmission smoothness sequence.

3. The method according to claim 1, characterized in that, During the process of judging whether the current conveyor belt node meets the transmission conditions according to the current transmission quality, taking that the current transmission quality is higher than a preset transmission quality threshold as the transmission condition.

4. The method according to claim 1, wherein Performing feature learning from the electrostatic adsorption quality characteristics to determine the transmission diffusion degree of the current folding conveyor belt node specifically includes: Obtaining a preset feature learning depth, and extracting a plurality of corresponding electrostatic adsorption qualities and the corresponding vibration intensity characteristics in the electrostatic adsorption quality characteristics based on the feature learning depth; Performing associated feature learning based on the plurality of electrostatic adsorption qualities and the corresponding vibration intensity characteristics to obtain a vibration influence factor; Correcting the electrostatic adsorption quality characteristics based on the vibration influence factor, performing feature clustering on the corrected electrostatic adsorption quality characteristics, and determining the transmission diffusion degree of the current folding conveyor belt node based on the clustering result.

5. The method according to claim 4, characterized in that, Using a single hidden layer neural network model to perform feature clustering on the corrected electrostatic adsorption quality characteristics.

6. The method according to claim 1, wherein Performing real-time correction on the first transmission speed according to the node transmission smoothness sequence specifically includes: obtaining the current path node, determining the node transmission smoothness corresponding to the current path node based on the node transmission smoothness sequence, and performing proportional correction on the first transmission speed according to the node transmission smoothness to obtain the second transmission speed.

7. The method according to claim 1, characterized in that During the process of controlling the folding conveyor belt to perform transmission based on the second transmission speed after real-time correction, using a closed-loop speed controller to adjust the motor output of the folding conveyor belt in real time.

8. A control system for a dust removal device of a whole vehicle in a railway tunnel, including a conveyor belt control unit, the conveyor belt control unit is used to execute the control method of a dust removal device of a whole vehicle in a railway tunnel according to any one of claims 1 to 7, characterized in that, The conveyor belt control unit includes: The conveyor belt detection module is used to detect the acceleration of the transmission path of the folding conveyor belt of the railway tunnel dust removal device, and determine the node transmission smoothness sequence based on the transmission accelerations of each path node of the transmission path; The transmission judgment module is used to detect the current transmission quality of the folding conveyor belt in real time, and judge whether the current conveyor belt node meets the transmission conditions according to the current transmission quality; The conveyor belt control module is used to perform electrostatic adsorption detection on the current conveyor belt node when the conveyor belt node meets the transmission conditions, and obtain the electrostatic adsorption quality characteristics of the current conveyor belt node; The conveyor belt control module is further used to perform feature learning on the electrostatic adsorption quality characteristics, determine the transmission diffusion degree of the current folding conveyor belt node, determine the first transmission speed based on the transmission diffusion degree, and perform real-time correction on the first transmission speed according to the node transmission smoothness sequence, and control the folding conveyor belt to transmit based on the second transmission speed after real-time correction.

9. A computer terminal device, characterized in that, The computer terminal device includes a memory and a processor, the memory stores code, and the processor is configured to obtain the code and execute a control method for a vehicle-mounted railway tunnel dust removal device according to any one of claims 1 to 7.

10. A computer-readable storage medium storing at least one computer program, characterized in that, The computer program is loaded and executed by the processor to implement the operations performed by a control method for a vehicle-mounted railway tunnel dust removal device according to any one of claims 1 to 7.

Images