A shield door driving system driven directly by a linear motor

Abstract

The present invention provides a shielding door driving system directly driven by a linear motor, which belongs to the field of closing device application technology. The driving system includes a driving module, a monitoring module and a control module; the driving module uses a linear motor to work in coordination with multiple shielding door components to achieve smooth opening and closing of the door; the monitoring module uses a contact sensor and an image sensor to monitor the operating status of the door and its surrounding environment in real time to ensure the safety of operation. The control module integrates the functions of the above two modules and realizes precise control and coordinated operation through preset working logic. This driving system simplifies the mechanical structure and reduces moving parts; the high-precision position feedback mechanism integrated in the system ensures the movement accuracy of the door, effectively avoids safety hazards such as pinching people, and greatly improves the safety and user experience of the automated door system.

Description

Technical Field

[0001] The present invention belongs to the technical field of closing device application, and in particular, relates to a shielding door driving system directly driven by a linear motor. Background Art

[0002] With the extensive application of automation equipment, a large number of buildings and environmental spaces are equipped with automatic closing moving doors, such as the common shield door devices in subways and rail trains. The existing shield door systems mostly use wire ropes, belts, and screw drives. Their structural components are numerous and complex, and it is difficult to accurately control the driving force of opening and closing the door, which poses a major safety hazard of pinching people when closing the door; at the same time, these driving components have many moving parts, and the active matching mechanism requires more precise assembly and matching, and requires a lot of periodic maintenance, and their operating reliability is poor.

[0003] After consulting the relevant public technologies, the technical solution with the announcement number CN102747916B proposes a shielding door control system, which uses multiple logic valves to control the pneumatic components to perform precise opening and closing control of the shielding door, thereby reducing the operation intensity of the shielding door opening and closing control process; the technical solution with the publication number WO2009086756A1 proposes a shielding door safety detection device, which monitors whether there are people or foreign objects in the closed position of the shielding door through laser probes arranged on the two sides of the shielding door, thereby realizing a safe opening and closing process; the technical solution with the announcement number EP2117901B1 proposes a shielding door with an indicator panel, which uses a microprocessor to monitor the process parameters of the shielding door during the opening and closing process, and displays the parameters on the indicator panel of the shielding door, thereby realizing information display of the entire opening and closing process.

[0004] The above technical solutions all propose a variety of methods and structures for implementing shielding door control. However, for shielding door application scenarios involving complex application scenarios, more effective and precise control methods are still needed.

[0005] The foregoing discussion of the background art is intended only to facilitate an understanding of the present invention. This discussion does not acknowledge or admit that any of the material referred to is part of the common general knowledge. Summary of the invention

[0006] The purpose of the present invention is to provide a shielding door drive system directly driven by a linear motor, which belongs to the field of closing device application technology. The drive system includes a drive module, a monitoring module and a control module; the drive module uses a linear motor to work in conjunction with multiple shielding door components to achieve smooth opening and closing of the door; the monitoring module uses contact sensors and image sensors to monitor the operating status of the door and its surrounding environment in real time to ensure the safety of operation. The control module integrates the functions of the above two modules and realizes precise control and coordinated operation through preset working logic. This drive system simplifies the mechanical structure and reduces moving parts; the high-precision position feedback mechanism integrated in the system ensures the movement accuracy of the door, effectively avoids safety hazards such as pinching people, and greatly improves the safety and user experience of the automated door system.

[0007] The present invention adopts the following technical solution:

[0008] A shielding door driving system directly driven by a linear motor; the driving system comprises a driving module, a monitoring module and a control module;

[0009] The driving module includes a linear motor and a plurality of shielding door components, and is configured to drive the shielding door to open and close through the linear motor; the linear motor includes at least a magnetic track component and a linear motor coil component; the magnetic track component and the roller component, the door hanging component and the shielding door fastened to the magnetic track component are driven to move along the aluminum profile track direction through the electromagnetic force generated between the magnetic track component and the linear motor coil component;

[0010] The monitoring module at least includes a position feedback sensor and an image sensor, and is configured to monitor the working state of the shielding door and the surrounding environment of the shielding door;

[0011] The control module is communicatively connected to the driving module and the monitoring module, and is configured to make the above two working modules work together according to a preset working logic; the control module includes a computing unit; the computing unit includes a processor and a memory for storing the monitoring image of the surrounding environment of the shielding door acquired by the image sensor;

[0012] The driving system determines the crowd density on at least one side of the platform shielding door, and further calculates and sets the opening / closing speed and braking force of the left and right platform shielding doors, and finally generates a control instruction and sends it to the driving module to control the movement of the platform shielding door;

[0013] Preferably, the driving system determines the opening / closing movement speed V of the shielding door according to the following calculation formula: , formula 1;

[0014] And according to the following calculation formula, determine the braking force F of the shield door:

[0015] , formula 2;

[0016] in,

[0017] ;

[0018] ;

[0019] In the above calculation formulas, α, β, and γ are three nonlinear factors for adjustment, which are determined by relevant technicians through experiments based on the specific mechanical properties of the drive module and the specific performance of the shielding door; S i Indicates the distance value of the ith position on the front of the shielding door; U i For S i The crowd density of the location; w i For S i The weight factor corresponding to the location reflects the importance of crowd density at different distances, w i The specific settings shall be made by relevant technical personnel;

[0020] V max and V min is the preset maximum and minimum values ​​of the moving speed of the platform shield door, F base is the basic braking force that the linear motor in the drive module can provide. The above three parameters are determined by relevant technical personnel after measuring the performance of each part of the drive module;

[0021] Preferably, the drive module comprises an aluminum profile track (15), a roller assembly (16), a left linear motor coil assembly (1), a right linear motor coil assembly (2), a left magnetic track assembly (3), a right magnetic track assembly (4), a left door hanger assembly (5), a right door hanger assembly (6), a left shielding door (7), a right shielding door (8), a door lock assembly (9), a left lock tongue (10), a right lock tongue (11), a control terminal assembly (12), a coil drive assembly (13) and a position feedback sensor (14);

[0022] Aluminum profile rails (15) are arranged on both the left and right sides of the shielding door; the cross section of the aluminum profile rail (15) is a closed top and open bottom shape; and a left linear motor coil assembly (1) and a right linear motor coil assembly (2) are fixedly mounted on the tops of the aluminum profile rails (15) on the left and right sides, respectively; the roller assembly (16) includes a plurality of ball bearings, which are arranged on the left and right sides of the aluminum profile rail (15) and are distributed and arranged along the sliding direction of the aluminum profile rail (15);

[0023] The left magnetic track assembly (3) and the right magnetic track assembly (4) are installed in the aluminum profile track (15) and are arranged above the two rows of balls of the roller assembly (16), and smooth movement on the aluminum profile track (15) is achieved through the roller assembly (16); the left door hanging assembly (5) and the right door hanging assembly (6) are installed below the roller assembly (16) and are respectively connected to the left magnetic track assembly (3) and the right magnetic track assembly (4) through a connecting mechanism; the connecting mechanism is located between the left and right balls. and in contact with the surface of the ball bearing; a left shielding door (7) and a right shielding door (8) are respectively installed below the left door hanging assembly (5) and the right door hanging assembly (6); a door lock assembly (9) is installed in the area above the middle position of the two shielding doors; the left lock tongue (10) and the right lock tongue (11) are respectively installed on the left door hanging assembly (5) and the right door hanging assembly (6); when the left and right shielding doors are closed, the left lock tongue (10) and the right lock tongue (11) are locked by the door lock assembly (9);

[0024] The left magnetic track assembly (3) cooperates with the left linear motor coil assembly (1), and the right magnetic track assembly (4) cooperates with the right linear motor coil assembly (2), so that the electromagnetic force generated between the magnetic track assembly and the linear motor coil assembly drives the magnetic track assembly and the roller assembly, door hanging assembly, and shielding door fastened to the magnetic track assembly to move along the direction of the aluminum profile track;

[0025] Preferably, the linear motor is one or more of the following types of motors: an induction linear motor, a permanent magnet synchronous linear motor, an iron coreless linear motor, an iron core linear motor, a flat linear motor, a flat linear motor, a double-sided coil linear motor, a U-shaped linear motor, a tubular linear motor, and a rod-shaped linear motor;

[0026] Preferably, the position feedback sensor (14) is one or more of the following sensor types: a Hall encoder, a magnetic grating encoder, a grating encoder, a time grating encoder, a Hall reading head, a magnetic grating reading head, a grating reading head, a time grating reading head;

[0027] Preferably, the drive system comprises at least two groups of image sensors, respectively configured to monitor areas located on the front and back sides of the shielding door;

[0028] The front image sensor is arranged on the front of the platform screen door, facing the waiting crowd; the front image sensor is used to monitor the crowd density in the waiting area of ​​the platform in real time and to monitor the relative speed between individuals at different distances from the platform screen door and the platform screen door;

[0029] The reverse image sensor is set on the reverse side of the platform screen door, facing the train track, and is used to monitor the train's entry and stop status as well as the crowd situation on the platform opposite the platform screen door;

[0030] Preferably, the calculation module includes running a deep neural network model to calculate the crowd density; wherein the deep neural network model includes:

[0031] A preprocessing module for graying the captured image and extracting low-level feature maps;

[0032] The first-level sub-network consists of multiple convolutional layers and pooling layers, which are used to extract high-level semantic feature maps from low-level feature maps;

[0033] The fully connected layer is used to determine the crowd density level based on the high-level semantic feature map and select the corresponding second sub-network configuration;

[0034] The secondary sub-network contains multiple sub-columns with different convolution kernel sizes. Each sub-column corresponds to a specific crowd density level, which is used to adapt to the image scale of different scenes and extract the main feature map for crowd density estimation;

[0035] The crowd location mask module is used to generate crowd location information masks based on high-level semantic feature maps;

[0036] The feature map weighted linking module is used to weight the crowd location information mask and the main feature map and link them on the channel to generate a feature map with added crowd location information;

[0037] The dimension transformation layer is used to convert the feature map with added crowd location information into a crowd density measurement map and number calculation result at a specific distance from the shielding door.

[0038] The beneficial effects achieved by the present invention are:

[0039] The drive system of this technical solution uses precise motor control technology to achieve high-precision control of the opening and closing actions of the shielding door; compared with traditional wire rope, belt or screw drive methods, linear motor direct drive technology can more accurately control the movement of the door, reducing safety hazards such as door pinching caused by inaccurate control; the position feedback sensor integrated in the system ensures that the movement of the door can be monitored in real time and adjusted as needed, thereby greatly improving the safety of the shielding door.

[0040] The driving system of this technical solution directly uses linear motors to drive the movement of the shielding door, which greatly simplifies the mechanical structure of the system and omits complex transmission mechanisms such as reducers, transmission shafts or chains, thereby reducing the failure points of the system and improving the operating reliability and maintenance convenience of the entire system; at the same time, the simplified structure also means fewer wearing parts and lower noise levels, thereby improving the user experience.

[0041] The driving system of this technical solution supports independent control of the left and right shielding doors, which means that each door can be operated separately according to specific usage requirements and environmental conditions, increasing the flexibility and adaptability of the system; independent control also allows the system to handle abnormal situations more effectively, ensuring the efficiency and reliability of the system.

[0042] The software and hardware parts of the driving system of the present technical solution adopt a modular design. The various working modules and components of the hardware part of the system, as well as the instructions, parameters, and algorithms of the software part can be conveniently replaced and / or upgraded later, thereby reducing the construction cost and maintenance cost of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] The present invention can be further understood from the following description in conjunction with the accompanying drawings. The components in the figures are not necessarily drawn to scale, but the emphasis is placed on illustrating the principles of the embodiments. In different views, the same reference numerals designate corresponding parts.

[0044] Description of the accompanying drawings: 1-left linear motor coil assembly; 2-right linear motor coil assembly; 3-left magnetic rail assembly; 4-right magnetic rail assembly; 5-left door hanging assembly; 6-right door hanging assembly; 7-left shielding door; 8-right shielding door; 9-door lock assembly; 10-left lock tongue; 11-right lock tongue; 12-control terminal assembly; 13-coil drive assembly; 14-position feedback sensor; 15-aluminum profile track; 16-roller assembly; 700-computer system; 702-bus; 704-processor; 706-main memory; 708-read-only memory; 710-storage device; 712-display; 714-input device; 716-cursor control device; 718-network device;

[0045] Figure 1 A schematic diagram of the architecture framework of a drive system in an embodiment of the present invention;

[0046] Figure 2 This is a schematic diagram of the structure of a driving module in an embodiment of the present invention;

[0047] Figure 3 It is a schematic diagram of the positions of the shielding door and the monitoring module in the driving system in the embodiment of the present invention;

[0048] Figure 4 Schematic diagram of the process of distinguishing electrical signals in the door opening process in an embodiment of the present invention;

[0049] Figure 5 Schematic diagram of the process of distinguishing electrical signals in the door closing process in an embodiment of the present invention;

[0050] Figure 6 A schematic diagram of the steps of analyzing crowd density and distribution using a deep neural network in an embodiment of the present invention;

[0051] Figure 7 It is a schematic diagram of the framework of the computer system used by the control module in the embodiment of the present invention. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention is further described in detail below in conjunction with its embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention. For those skilled in the art, after reviewing the following detailed description, other systems, methods and / or features of the present embodiment will become apparent. It is intended that all such additional systems, methods, features and advantages are included in this specification. Included within the scope of the present invention and protected by the appended claims. Additional features of the disclosed embodiments are described in the following detailed description, and these features will be apparent from the following detailed description.

[0053] The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there are terms such as "upper", "lower", "left", "right" and the like indicating the orientation or positional relationship based on the orientation or positional relationship shown in the drawings, it is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or component referred to must have a specific orientation. The invention is constructed and operated in a specific orientation, so the terms describing the positional relationship in the drawings are only used for exemplary description and cannot be understood as a limitation of this patent. For ordinary technicians in this field, the specific meanings of the above terms can be understood according to the specific circumstances.

[0054] Embodiment 1, exemplarily proposes a screen door driving system driven directly by a linear motor; Figure 1 As shown, the driving system includes a driving module, a monitoring module and a control module;

[0055] The driving module includes a linear motor and a plurality of shielding door components, and is configured to drive the shielding door to open and close through the linear motor; the linear motor includes at least a magnetic track component and a linear motor coil component; the magnetic track component and the roller component, the door hanging component and the shielding door fastened to the magnetic track component are driven to move along the aluminum profile track direction through the electromagnetic force generated between the magnetic track component and the linear motor coil component;

[0056] The monitoring module at least includes a position feedback sensor and an image sensor, and is configured to monitor the working state of the shielding door and the surrounding environment of the shielding door;

[0057] The control module is communicatively connected to the driving module and the monitoring module, and is configured to make the above two working modules work together according to a preset working logic; the control module includes a computing unit; the computing unit includes a processor and a memory for storing the monitoring image of the surrounding environment of the shielding door acquired by the image sensor;

[0058] The driving system determines the crowd density on at least one side of the platform shielding door, and further calculates and sets the opening / closing speed and braking force of the left and right platform shielding doors, and finally generates a control instruction and sends it to the driving module to control the movement of the platform shielding door;

[0059] Preferably, the driving system determines the opening / closing movement speed V of the shielding door according to the following calculation formula:

[0060] , formula 1;

[0061] And according to the following calculation formula, determine the braking force F of the shield door:

[0062] , formula 2;

[0063] in,

[0064] ;

[0065] ;

[0066] In the above calculation formulas, α, β, and γ are three nonlinear factors for adjustment, which are determined by relevant technicians through experiments based on the specific mechanical properties of the drive module and the specific performance of the shielding door; S i Indicates the distance value of the ith position on the front of the shielding door; U i For S i The crowd density of the location; w i For S i The weight factor corresponding to the location reflects the importance of crowd density at different distances, w i The specific settings shall be made by relevant technical personnel;

[0067] V max and V min is the preset maximum and minimum values ​​of the moving speed of the platform shield door, F base is the basic braking force that the linear motor in the drive module can provide. The above three parameters are determined by relevant technical personnel after measuring the performance of each part of the drive module;

[0068] Preferably, as attached Figure 2As shown, the drive module includes an aluminum profile track 15, a roller assembly 16, a left linear motor coil assembly 1, a right linear motor coil assembly 2, a left magnetic track assembly 3, a right magnetic track assembly 4, a left door hanging assembly 5, a right door hanging assembly 6, a left shielding door 7, a right shielding door 7, a door lock assembly 7, a left lock tongue 10, a right lock tongue 11, a control terminal assembly 12, a coil drive assembly 13 and a position feedback sensor 14;

[0069] Aluminum profile rails 15 are provided on both the left and right sides of the shielding door; the cross section of the aluminum profile rails 15 is a closed top and open bottom shape; and the left linear motor coil assembly 1 and the right linear motor coil assembly 2 are fixedly installed on the top of the aluminum profile rails 15 on the left and right sides, respectively; the roller assembly 16 includes a plurality of balls, which are respectively provided on the left and right sides of the aluminum profile rails 15 and are distributed and arranged along the sliding direction of the aluminum profile rails 15;

[0070] The left magnetic rail assembly 3 and the right magnetic rail assembly 4 are installed in the aluminum profile track 15 and are arranged above the two rows of balls of the roller assembly 16, and the roller assembly 16 is used to realize smooth movement on the aluminum profile track 15; the left door hanging assembly 5 and the right door hanging assembly 6 are installed below the roller assembly 16, and are respectively connected to the left magnetic rail assembly 3 and the right magnetic rail assembly 4 through a connecting mechanism; the connecting mechanism is located between the left and right balls and contacts the surface of the balls; the left shielding door 7 and the right shielding door 8 are respectively installed below the left door hanging assembly 5 and the right door hanging assembly 6; the door lock assembly 9 is installed in the upper area of ​​the middle position between the two shielding doors; the left lock tongue 10 and the right lock tongue 11 are respectively installed on the left door hanging assembly 5 and the right door hanging assembly 6, and the left lock tongue 10 and the right lock tongue 11 are locked by the door lock assembly 9 when the left and right shielding doors are closed;

[0071] The left magnetic track assembly 3 cooperates with the left linear motor coil assembly 1, and the right magnetic track assembly 4 cooperates with the right linear motor coil assembly 2. The electromagnetic force generated between the magnetic track assembly and the linear motor coil assembly drives the magnetic track assembly and the roller assembly, door hanging assembly, and shielding door fastened to the magnetic track assembly to move along the aluminum profile track direction;

[0072] Preferably, the linear motor is one or more of the following types of motors: an induction linear motor, a permanent magnet synchronous linear motor, an iron coreless linear motor, an iron core linear motor, a flat linear motor, a flat linear motor, a double-sided coil linear motor, a U-shaped linear motor, a tubular linear motor, and a rod-shaped linear motor;

[0073] Preferably, the position feedback sensor 14 is one or more of the following sensor types: Hall encoder, magnetic grating encoder, grating encoder, time grating encoder, Hall reading head, magnetic grating reading head, grating reading head, time grating reading head;

[0074] Preferably, the drive system comprises at least two groups of image sensors, respectively configured to monitor areas located on the front and back sides of the shielding door;

[0075] The front image sensor is arranged on the front of the platform screen door, facing the waiting crowd; the front image sensor is used to monitor the crowd density in the waiting area of ​​the platform in real time and to monitor the relative speed between individuals at different distances from the platform screen door and the platform screen door; as shown in the attached figure, Figure 3 As shown, the front of the screen door is divided into a plurality of distance segments, namely S1, S2 and S3, at equal intervals; in some embodiments, the distance segments may be unequally spaced; in some embodiments, the front of the screen door may be divided into a plurality of observation area blocks, rather than spacing segments;

[0076] The reverse image sensor is installed on the reverse side of the platform screen door, facing the train track, and is used to monitor the train's entry and stop status as well as the crowd situation on the platform opposite the platform screen door.

[0077] Preferably, the calculation module includes running a deep neural network model to calculate the crowd density; wherein the deep neural network model includes:

[0078] A preprocessing module for graying the captured image and extracting low-level feature maps;

[0079] The first-level sub-network consists of multiple convolutional layers and pooling layers, which are used to extract high-level semantic feature maps from low-level feature maps;

[0080] The fully connected layer is used to determine the crowd density level based on the high-level semantic feature graph and select the corresponding second sub-network configuration;

[0081] The secondary sub-network contains multiple sub-columns with different convolution kernel sizes. Each sub-column corresponds to a specific crowd density level, which is used to adapt to the image scale of different scenes and extract the main feature map for crowd density estimation;

[0082] The crowd location mask module is used to generate crowd location information masks based on high-level semantic feature maps;

[0083] The feature map weighted linking module is used to weight the crowd location information mask and the main feature map and link them on the channel to generate a feature map with added crowd location information;

[0084] Dimension transformation layer, used to convert the feature map with crowd location information into a crowd density measurement map and a number calculation result at a specific distance from the shielding door;

[0085] The implementation of the drive system is described in more detail;

[0086] In the driving system of the present technical solution, the moving speed V and the braking force F of the shielding door can be adjusted by the driving module assembly and the control strategy; the core parts of the adjustment are the linear motor coil assembly, the magnetic track assembly, and the roller assembly and the door hanging assembly matched therewith. These components work together to firstly ensure the smooth opening and closing of the shielding door, and secondly, adjust the appropriate moving speed V and the braking force F by self-adapting to the current crowd density in front of the shielding door, so as to balance the considerations of operation efficiency and operation safety;

[0087] Exemplarily, the moving speed V of the shielding door is mainly controlled by left and right linear motor coil assemblies, namely, left linear motor coil assembly 1 and right linear motor coil assembly 2; these coil assemblies are installed on the top of the aluminum profile track and correspond to the left magnetic track assembly (3) and the right magnetic track assembly (4); when current passes through these coils, electromagnetic force is generated on the magnetic track assembly, and the electromagnetic force pushes the roller assembly and the door hanging assembly fastened to the magnetic track assembly, thereby driving the shielding door to move along the aluminum profile track;

[0088] By adjusting the intensity and direction of the current flowing through the coil, the magnitude and polarity of the electromagnetic force generated can be accurately controlled, thereby adjusting the opening and closing speed of the shielding door; the control terminal component 12 generates corresponding control instructions based on the data collected from the monitoring module and the preset working logic, and adjusts the current output by the coil driving component 13 to achieve accurate control of the shielding door speed;

[0089] Exemplarily, the braking force F is mainly used to maintain the current moving state of the shielding door, including the speed state or the static state, for example, when the shielding door is close to the closed state, to ensure that it will not be accidentally opened due to external force; the application of such braking force is to enhance the safety and stability of the shielding door, especially in the face of accidents or emergencies;

[0090] In an exemplary embodiment, the drive system performs the following steps to control the opening process of the platform shielding door:

[0091] The control module sends a control instruction to the control terminal component 12; the control terminal component 12 gives a door opening signal, the electromagnet of the door lock component 9 is energized to open the lock, and the left lock tongue 10 and / or the right lock tongue 11 are released; the coil drive component 13 energizes the left linear motor coil component 1 and / or the right linear motor coil component 2 through the position loop mode to generate a magnetic field, the magnetic field generated by the left linear motor coil component 1 drives the left magnetic rail component 3 to move left, and the magnetic field generated by the right linear motor coil component 2 drives the right magnetic rail component 4 to move right; the moving left magnetic rail component 3 drives the platform screen door lifted by the left door hanging component 5 below to realize the left movement of the left screen door 7; the moving right magnetic rail component 4 drives the right screen door 8 lifted by the right door hanging component 6 below to realize the right movement of the right screen door 8; the position feedback sensor 14 is used to identify that the full stroke has been completed and the door opening is completed, so that the left screen door 7 and / or the right screen door 8 are opened;

[0092] The schematic diagram of the electrical signal judgment process in the door opening process is shown in the attached Figure 4 As shown;

[0093] In an exemplary embodiment, the drive system performs the following steps to control the closing process of the platform shielding door:

[0094] The control module sends a control instruction to the control terminal component 12; the control terminal component 12 gives a door closing signal, and the coil drive component 13 energizes the left linear motor coil component 1 and / or the right linear motor coil component 2 through the position loop mode to generate a magnetic field. The magnetic field generated by the left linear motor coil component 1 acts on the magnetic steel and drives the left magnetic rail component 3 to move to the left by a stroke L1, and the magnetic field generated by the right linear motor coil component 2 acts on the magnetic steel and drives the right magnetic rail component 4 to move to the right by a stroke L1; the moving left magnetic rail component 3 drives the platform screen door lifted by the left door hanging component 5 below to realize the rightward movement of the left screen door 7, and the moving right magnetic rail component 4 drives the right screen door 8 lifted by the right door hanging component 6 below to realize the leftward movement of the right screen door 8. The left magnetic track assembly 3 and the right magnetic track assembly 4 feed back to the coil driving assembly 13 the completed running distance L1 through the position feedback sensor 14, and the coil driving assembly 13 energizes the left linear motor coil assembly 1 and the right linear motor coil assembly 2 through the torque mode to generate a magnetic field to drive the left magnetic track assembly 3 and the right magnetic track assembly 4 to run the remaining stroke L2, and the left lock tongue 10 and the right lock tongue 11 extend into the door lock assembly 9 at the same time, triggering an internal signal to cut off the power of the electromagnet to allow the locking mechanism to lock the left and right movements of the left lock tongue 10 and the right lock tongue 11, thereby closing the left shielding door 7 and the right shielding door 8;

[0095] The schematic diagram of the electrical signal judgment process in the door closing process is shown in the attached figure. Figure 5 shown.

[0096] Embodiment 2: This embodiment should be understood to include at least all the features of any of the above embodiments, and further improve upon them;

[0097] Exemplarily, the analysis method of the monitoring module for analyzing the crowd density includes the following steps, as shown in the attached figure: Figure 6 As shown:

[0098] S100: obtaining a real-time image of the crowd in front of the shielding door by a front image sensor;

[0099] S200: Input the grayscale processed real-time crowd image into the deep neural network model for preprocessing to obtain a low-level feature map;

[0100] Preferably, when graying the real-time crowd image, the three-channel values ​​of the color image are assumed to be R, G and B, the grayed image is Gray, the right shift operation is >>, and the graying calculation formula is as follows:

[0101] Gray=(R*19595+G*38469+B*7472)>>16;

[0102] Preferably, the preprocessing process involves two convolution layers, and the real-time crowd image after grayscale processing is input into the convolution layer A in the deep neural network model to obtain a first image; the first image is input into the convolution layer B in the deep neural network model to obtain a low-level feature map; illustratively, the size of the convolution layer A and the convolution layer B are both 11*11; the real-time crowd image generates 32 feature maps after passing through the convolution layer A, and generates 64 feature maps after passing through the convolution layer B, that is, 64 low-level feature maps;

[0103] S300: Inputting the low-level feature map into a first-level sub-network in a deep neural network model to obtain a high-level semantic feature map; the first-level sub-network includes multiple convolutional layers and multiple pooling layers;

[0104] In step S300, exemplarily, the first-level subnetwork may include 6 convolutional layers and two pooling layers, and are sequentially arranged in the following manner: 3 convolutional layers, 1 pooling layer, 1 convolutional layer, 1 pooling layer and 2 convolutional layers; wherein the convolution size of the convolutional layers is 3*3, and the number of feature map channels generated is 24, 32, 16, 32, 16 and 8 respectively; the step sizes of the two pooling layers are both 2; after the low-level feature map is input into the first-level subnetwork in the deep neural network model, it passes through 3 convolutional layers, 1 pooling layer, 1 convolutional layer, 1 pooling layer and 2 convolutional layers in sequence, and a high-level semantic feature map is generated after the 6th convolutional layer;

[0105] S400: Input the high-level semantic feature map into the fully connected layer of the deep neural network model to obtain the crowd density level;

[0106] In step S400, preferably, different neurons in the last layer of the fully connected layer correspond to different crowd density levels;

[0107] Preferably, the fully connected layer includes three sublayers with different numbers of neurons, the three sublayers are sequentially combined, and the numbers of neurons in the three sublayers are: 512, 256 and 5 respectively;

[0108] Preferably, four crowd density levels can be set: "high density", "medium density", "low density", and "very low density";

[0109] Preferably, a cross entropy function is used as the loss function of the fully connected layer;

[0110] S500: Determine a corresponding sub-column of a secondary sub-network in a deep neural network model according to a crowd density level;

[0111] Specifically, the secondary subnetwork includes multiple subcolumns with different convolution kernel sizes, and the number of subcolumns is the same as the number of neurons in the last layer of the fully connected layer; the multiple subcolumns correspond one-to-one to multiple crowd density levels; when the number of neurons in the last layer of the fully connected layer is 5, the secondary subnetwork includes 4 subcolumns with different convolution kernel sizes, namely the first subcolumn, the second subcolumn, the third subcolumn and the fourth subcolumn, and each subcolumn corresponds to a crowd density level, that is, the "high density" level corresponds to the first subcolumn, the "medium density" level corresponds to the second subcolumn, the "low density" level corresponds to the third subcolumn, and the "extremely low density" level corresponds to the fourth subcolumn;

[0112] In an exemplary embodiment, each of the sub-columns is preferably specifically configured as follows:

[0113] Five sub-columns with different convolution kernel sizes are established. Each column contains five convolution layers and two pooling layers, which are 1 convolution, 1 pooling, 1 convolution, 1 pooling and 3 convolutions. The convolution sizes of the first sub-column are 9*9, 7*7, 7*7, 7*7 and 3*3, and the number of feature map channels generated are 24, 32, 16, 8 and 8 respectively; the convolution sizes of the second sub-column are 7*7, 5*5, 5*5, 5*5 and 3*3 respectively. , the number of feature map channels generated are 20, 40, 20, 10 and 8 respectively; the convolution sizes of the third sub-column are 5*5, 3*3, 3*3, 3*3 and 3*3 respectively, and the number of feature map channels generated are 24, 48, 24, 12 and 8 respectively; the convolution sizes of the fourth sub-column are 3*3, 3*3, 3*3, 3*3 and 3*3 respectively, and the number of feature map channels generated are 32, 48, 24, 18 and 8 respectively; all pooling steps are 2;

[0114] S600: Input the low-level feature map into the corresponding sub-column of the secondary sub-network to obtain the main feature map for crowd density estimation; when the low-level feature map is input into the secondary sub-network, the corresponding sub-column is used for density estimation; for example, when the output result of step S400 is "high density", the first sub-column is selected for density estimation, and the remaining three columns are not involved in the calculation; when the output result of step S400 is "medium density", the second sub-column is selected for density estimation, and the remaining three columns are not involved in the calculation; when the output result of step S400 is "low density", the third sub-column is selected for density estimation, and the remaining three columns are not involved in the calculation; when the output result of step S400 is "extremely low density", the fourth sub-column is selected for density estimation, and the remaining three columns are not involved in the calculation;

[0115] S700: Input the high-level semantic feature map into the crowd position mask module to obtain the crowd position information mask; the specific process is as follows:

[0116] The high-level semantic feature map is input into the convolution layer with a convolution kernel size of 1*1 for convolution operation. The number of channels of the generated feature map is 8, and the second feature map is obtained;

[0117] The second feature map is transformed by the Sigmoid function to obtain the crowd location information mask; the expression of the Sigmoid function is:

[0118] ,

[0119] Where z is each element of the operation result, which refers to the second feature map here, and f(z) is the result of the Sigmoid transformation of each element;

[0120] S800: Weighting the main feature map for crowd density estimation and the crowd position information mask, and linking the main feature map for crowd density estimation on the channel to obtain a feature map with added crowd position information; the specific process is as follows:

[0121] The crowd location information mask is element-wise multiplied with the main feature map for crowd density estimation to obtain a third feature map; the third feature map is then channel-linked with the main feature map for crowd density estimation to obtain a feature map with added crowd location information; the calculation formula for the whole process is:

[0122] ,

[0123] In the above formula, Sigmoid(F l ) is the result of Sigmoid transformation of the second feature map, i.e., the crowd position information mask; is an element-by-element multiplication operation, F d is the main feature map used for crowd density estimation, is the link operation on the channel, F r A feature map for adding crowd location information;

[0124] S900: Input the feature map with added crowd location information into the dimension transformation layer in the deep neural network model to obtain a crowd density estimation map and a number of people estimation result corresponding to the real-time crowd image; the dimension transformation layer includes two convolutional layers and two transposed convolutional layers, which are one convolutional layer, two transposed convolutional layers and one convolutional layer respectively; the convolution sizes of the two convolutional layers are 3*3 and 1*1 respectively, and the number of channels of the generated feature maps are 8 and 1 respectively; the convolution sizes of the two transposed convolutional layers are both 4*4, and the number of channels of the generated feature maps are respectively 16 and 8, and the step sizes are both 2; input the feature map with added crowd location information into the dimension transformation layer in the deep neural network model, and after passing through one convolutional layer, two transposed convolutional layers and one convolutional layer in sequence, the crowd density calculation result is obtained.

[0125] Embodiment 3: This embodiment should be understood to include at least all the features of any of the above embodiments, and further improve upon them;

[0126] Exemplarily, the control module uses a computer system to process, store and output data; Figure 7 As shown, the implementation of the computer system 700 used by the control module is described; the computer system 700 can be applied to the data storage, calculation and result output process of each working module in the identification and judgment system;

[0127] Illustratively, computer system 700 includes a bus 702 or other communication mechanism for communicating information, one or more processors 704 coupled to bus 702 for processing information; processor 704 may be, for example, one or more general-purpose microprocessors;

[0128] The computer system 700 also includes a main memory 706, such as a random access memory (RAM), cache, and / or other dynamic storage device, coupled to the bus 702 for storing information and instructions to be executed by the processor 704; the main memory 706 may also be used to store temporary variables or other intermediate information during the execution of instructions to be executed by the processor 704; these instructions, when stored in a storage medium accessible to the processor 704, present the computer system 700 as a special-purpose machine customized to perform the operations specified in the instructions;

[0129] The computer system 700 may also include a read-only memory (ROM) 708 or other static storage device coupled to the bus 702 for storing static information and instructions for the processor 704; a storage device 710 such as a disk, an optical disk, or a USB drive (flash drive) will be coupled to the bus 702 for storing information and instructions;

[0130] And further, coupled to the bus 702 may also include a display 712 for displaying various information, data, media, etc., an input device 714 for allowing a user of the computer system 700 to control, manipulate, and / or interact with the computer system 700;

[0131] A preferred way to interact with the management system may be through a cursor control device 716, such as a computer mouse or similar control / navigation mechanism;

[0132] Furthermore, the computer system 700 may also include a network device 718 coupled to the bus 702; wherein the network device 718 may include, for example, a wired network card, a wireless network card, a switching chip, a router, a switch, and other components;

[0133] In general, the terms "engine", "component", "system", "database", etc., as used herein, may refer to logic embodied in hardware or firmware, or to a collection of software instructions, possibly with entry and exit points, written in a programming language such as Java, C, or C++; software components may be compiled and linked into executable programs, installed in a dynamic link library, or may be written in an interpreted programming language (e.g., BASIC, Perl, or Python); it should be understood that software components may be callable from other components or from themselves, and / or may be called in response to detected events or interrupts;

[0134] Software components configured to execute on a computing device may be provided on a computer-readable medium, such as a compact disc, digital video disc, flash drive, diskette, or any other tangible medium, or as a digital download (and may be initially stored) in a compressed or installable format that requires installation, decompression, or decryption prior to execution); such software code may be stored in part or in whole on a memory device of the executing computing device for execution by the computing device; software instructions may be embedded in firmware, such as an EPROM; it is also understood that hardware components may be composed of connected logic units (such as gates and flip-flops), and / or may be composed of programmable units (such as programmable gate arrays or processors);

[0135] Computer system 700 includes custom hardwired logic, one or more ASICs or FPGAs, firmware, and / or program logic that, in combination with the computer system, renders computer system 700 a special-purpose computing device;

[0136] According to one or more embodiments, the techniques herein may be performed by computer system 700 in response to processor 704 executing one or more sequences of one or more instructions contained in main memory 706; such instructions may be read into main memory 706 from another storage medium, such as storage device 710; execution of the sequences of instructions contained in main memory 706 causes processor 704 to perform the process steps described herein; in alternative embodiments, hard-wired circuitry may be used in place of or in combination with software instructions;

[0137] As used herein, the term "non-transitory media" and similar terms refer to any media that store data and / or instructions that cause a machine to operate in a specific manner; such non-transitory media may include non-volatile media and / or volatile media; non-volatile media include, for example, optical or magnetic disks, such as storage device 710; volatile media include dynamic memory, such as main memory 706;

[0138] Among them, common forms of non-transitory media include, for example, floppy disks, diskettes, hard disks, solid-state drives, magnetic tapes or any other magnetic data storage medium, CD-ROMs, any other optical data storage medium, any physical medium having a pattern of holes, RAM, PROM and EPROM, FLASH-EPROM, NVRAM, any other memory chip or cartridge, and networked versions thereof;

[0139] Non-transient media are distinct from transmission media but may be used in conjunction with transmission media; transmission media participate in the transmission of information between non-transient media; for example, transmission media include coaxial cables, copper wires, and optical fibers, including the wires that make up bus 702; transmission media may also take the form of sound waves or light waves, such as radio waves and infrared data communications.

[0140] Although the present invention has been described above with reference to various embodiments, it should be understood that many changes and modifications may be made without departing from the scope of the present invention. That is, the methods, systems and devices discussed above are examples. Various configurations may appropriately omit, replace or add various processes or components. For example, in alternative configurations, the method may be performed in an order different from the order described, and / or various components may be added, omitted and / or combined. Moreover, the features described with respect to certain configurations may be combined in various other configurations, such as different aspects and elements of the configurations may be combined in a similar manner. In addition, the elements therein may be updated as the technology develops, i.e., many elements are examples and do not limit the scope of the present disclosure or claims.

[0141] Specific details are given in the specification to provide a thorough understanding of the exemplary configurations including implementations. However, the configurations may be practiced without these specific details. For example, well-known circuits, processes, algorithms, structures, and techniques have been shown without unnecessary details to avoid obscuring the configurations. This description provides only example configurations and does not limit the scope, applicability, or configurations of the claims. On the contrary, the foregoing description of the configurations will provide those skilled in the art with an enabling description for implementing the described techniques. Various changes may be made to the functions and arrangements of the elements without departing from the spirit or scope of the present disclosure.

[0142] In summary, it is intended that the above detailed description is considered to be illustrative rather than restrictive, and it should be understood that the above embodiments should be understood to be only used to illustrate the present invention and not to limit the scope of protection of the present invention. After reading the contents of the present invention, the technician can make various changes or modifications to the present invention, and these equivalent changes and modifications also fall within the scope defined by the claims of the present invention.

Claims

1. A screen door driving system driven directly by a linear motor, characterized in that: The driving system includes a driving module, a monitoring module and a control module; The driving module includes a linear motor and a plurality of shielding door components, and is configured to drive the shielding door to open and close through the linear motor; the linear motor includes at least a magnetic track component and a linear motor coil component; the magnetic track component and the roller component, the door hanging component and the shielding door fastened to the magnetic track component are driven to move along the aluminum profile track direction through the electromagnetic force generated between the magnetic track component and the linear motor coil component; The monitoring module at least includes a position feedback sensor and an image sensor, and is configured to monitor the working state of the shielding door and the surrounding environment of the shielding door; By determining the crowd density on at least one side of the shielding door, and further calculating and setting the values ​​of the opening / closing speed and the braking force of the left and right shielding doors, a control instruction is finally generated and sent to the driving module to control the movement of the shielding door; The crowd location information mask is element-wise multiplied with the main feature map for crowd density estimation to obtain a third feature map; the third feature map is then channel-linked with the main feature map for crowd density estimation to obtain a feature map with added crowd location information; the calculation formula for the whole process is: ， In the above formula, Sigmoid(F l ) is the result of Sigmoid transformation of the second feature map, i.e., the crowd position information mask; is an element-by-element multiplication operation, F d is the main feature map used for crowd density estimation, is the link operation on the channel, F r A feature map for adding crowd location information; Input the feature map with added crowd location information into the dimension transformation layer in the deep neural network model to obtain the crowd density estimation map and the number of people estimation result corresponding to the real-time crowd image; the dimension transformation layer includes two convolutional layers and two transposed convolutional layers, which are one convolutional layer, two transposed convolutional layers and one convolutional layer respectively; the convolution sizes of the two convolutional layers are 3*3 and 1*1 respectively, and the number of channels of the generated feature maps are 8 and 1 respectively; the convolution sizes of the two transposed convolutional layers are both 4*4, and the number of channels of the generated feature maps are 16 and 8 respectively, and the step sizes are both 2; input the feature map with added crowd location information into the dimension transformation layer in the deep neural network model, and after passing through one convolutional layer, two transposed convolutional layers and one convolutional layer in sequence, the crowd density calculation result is obtained; The control module is communicatively connected to the driving module and the monitoring module, and is configured to make the above two working modules work together according to a preset working logic; the control module includes a computing unit; the computing unit includes a processor and a memory for storing the monitoring image of the surrounding environment of the shielding door acquired by the image sensor; The drive system determines the opening / closing movement speed V of the shielding door according to the following calculation formula: , formula 1; And according to the following calculation formula, determine the braking force F of the shield door: , formula 2; in, ； ； In the above calculation formulas, α, β, and γ are three nonlinear factors for adjustment, which are determined by relevant technicians through experiments based on the specific mechanical properties of the drive module and the specific performance of the shielding door; S i Indicates the distance value of the ith position on the front of the shielding door; U i For S i The crowd density of the location; w i For S i The weight factor corresponding to the location reflects the importance of crowd density at different distances, w i The specific settings shall be made by relevant technical personnel; V max and V min is the preset maximum and minimum values ​​of the moving speed of the platform shield door, F base is the basic braking force that the linear motor in the drive module can provide. The above three parameters are determined by relevant technical personnel after measuring the performance of each part of the drive module.

2. The drive system according to claim 1, characterized in that: The drive module comprises an aluminum profile track (15), a roller assembly (16), a left linear motor coil assembly (1), a right linear motor coil assembly (2), a left magnetic track assembly (3), a right magnetic track assembly (4), a left door hanger assembly (5), a right door hanger assembly (6), a left shielding door (7), a right shielding door (8), a door lock assembly (9), a left lock tongue (10), a right lock tongue (11), a control terminal assembly (12), a coil drive assembly (13) and a position feedback sensor (14); Aluminum profile rails (15) are arranged on both the left and right sides of the shielding door; the cross section of the aluminum profile rail (15) is a closed top and open bottom shape; and a left linear motor coil assembly (1) and a right linear motor coil assembly (2) are fixedly mounted on the tops of the aluminum profile rails (15) on the left and right sides, respectively; the roller assembly (16) includes a plurality of ball bearings, which are arranged on the left and right sides of the aluminum profile rail (15) and are distributed and arranged along the sliding direction of the aluminum profile rail (15); The left magnetic track assembly (3) and the right magnetic track assembly (4) are installed in the aluminum profile track (15) and are arranged above the two rows of balls of the roller assembly (16), and smooth movement on the aluminum profile track (15) is achieved through the roller assembly (16); the left door hanging assembly (5) and the right door hanging assembly (6) are installed below the roller assembly (16) and are respectively connected to the left magnetic track assembly (3) and the right magnetic track assembly (4) through a connecting mechanism; the connecting mechanism is located between the left and right balls. and in contact with the surface of the ball bearing; a left shielding door (7) and a right shielding door (8) are respectively installed below the left door hanging assembly (5) and the right door hanging assembly (6); a door lock assembly (9) is installed in the area above the middle position of the two shielding doors; the left lock tongue (10) and the right lock tongue (11) are respectively installed on the left door hanging assembly (5) and the right door hanging assembly (6); when the left and right shielding doors are closed, the left lock tongue (10) and the right lock tongue (11) are locked by the door lock assembly (9); By the cooperation between the left magnetic track assembly (3) and the left linear motor coil assembly (1), and the cooperation between the right magnetic track assembly (4) and the right linear motor coil assembly (2), the electromagnetic force generated between the magnetic track assembly and the linear motor coil assembly drives the magnetic track assembly and the roller assembly, door hanging assembly and shielding door fastened to the magnetic track assembly to move along the direction of the aluminum profile track.

3. The drive system according to claim 2, characterized in that: The linear motor is one or more of the following types of motors: an induction linear motor, a permanent magnet synchronous linear motor, an ironless linear motor, an iron core linear motor, a flat linear motor, a flat linear motor, a double-sided coil linear motor, a U-shaped linear motor, a tubular linear motor, and a rod-shaped linear motor.

4. The drive system according to claim 3, characterized in that: The position feedback sensor (14) is one or more of the following sensor types: a Hall encoder, a magnetic grating encoder, a grating encoder, a time grating encoder, a Hall reading head, a magnetic grating reading head, a grating reading head, and a time grating reading head.

5. The drive system according to claim 4, characterized in that: The drive system includes at least two sets of image sensors, each configured to monitor an area located on the front side and the back side of the shielding door; The front image sensor is arranged on the front of the platform screen door, facing the waiting crowd; the front image sensor is used to monitor the crowd density in the waiting area of ​​the platform in real time and to monitor the relative speed between individuals at different distances from the platform screen door and the platform screen door; The rear image sensor is installed on the rear side of the platform shielding door, facing the train track, and is used to monitor the train's entry and stopping status as well as the crowd situation on the platform opposite the platform shielding door.

6. The drive system according to claim 5, characterized in that: The method includes running a deep neural network model to calculate crowd density; wherein the deep neural network model includes: A preprocessing module for graying the captured image and extracting low-level feature maps; The first-level sub-network consists of multiple convolutional layers and pooling layers, which are used to extract high-level semantic feature maps from low-level feature maps; The fully connected layer is used to determine the crowd density level based on the high-level semantic feature map and select the corresponding second sub-network configuration; The secondary sub-network contains multiple sub-columns with different convolution kernel sizes. Each sub-column corresponds to a specific crowd density level, which is used to adapt to the image scale of different scenes and extract the main feature map for crowd density estimation; The crowd location mask module is used to generate crowd location information masks based on high-level semantic feature maps; The feature map weighted linking module is used to weight the crowd location information mask and the main feature map and link them on the channel to generate a feature map with added crowd location information; The dimension transformation layer is used to convert the feature map with added crowd location information into a crowd density measurement map and number calculation result at a specific distance from the shielding door.

Images