CN117382426A - Vehicle-mounted pantograph self-adaptive control method and system - Google Patents
Vehicle-mounted pantograph self-adaptive control method and system Download PDFInfo
- Publication number
- CN117382426A CN117382426A CN202311278222.5A CN202311278222A CN117382426A CN 117382426 A CN117382426 A CN 117382426A CN 202311278222 A CN202311278222 A CN 202311278222A CN 117382426 A CN117382426 A CN 117382426A
- Authority
- CN
- China
- Prior art keywords
- pantograph
- contour
- straight line
- point
- distance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 32
- 238000005516 engineering process Methods 0.000 claims abstract description 12
- 230000011218 segmentation Effects 0.000 claims description 20
- 230000003044 adaptive effect Effects 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000005457 optimization Methods 0.000 claims description 10
- 239000013598 vector Substances 0.000 claims description 8
- 238000003709 image segmentation Methods 0.000 claims description 7
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 claims description 6
- 229910052799 carbon Inorganic materials 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 4
- 238000001514 detection method Methods 0.000 description 12
- 230000006870 function Effects 0.000 description 10
- 238000005286 illumination Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 4
- 238000013136 deep learning model Methods 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 230000002146 bilateral effect Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 206010039203 Road traffic accident Diseases 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000010891 electric arc Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000000758 substrate Substances 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60L—PROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
- B60L5/00—Current collectors for power supply lines of electrically-propelled vehicles
- B60L5/18—Current collectors for power supply lines of electrically-propelled vehicles using bow-type collectors in contact with trolley wire
- B60L5/22—Supporting means for the contact bow
- B60L5/28—Devices for lifting and resetting the collector
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Abstract
The invention provides a vehicle-mounted pantograph self-adaptive control method and a vehicle-mounted pantograph self-adaptive control system, which relate to the technical field of control systems, wherein the method comprises the following steps: acquiring a plurality of image data; dividing a pantograph contour and a catenary contour from each image data by an image dividing technology; the pantograph contour and the catenary contour with the largest area are reserved; acquiring a pantograph contour with the largest area and a minimum circumscribed rectangle of a contact net contour; performing linear fitting on the upper boundary of the pantograph contour to obtain a first line, and performing linear fitting on the contact net contour to obtain a second line; calculating an intersection point of the first straight line and the second straight line as a contact point of the pantograph and the contact net; calculating the midpoint of the upper boundary of the pantograph contour; calculating the distance between the contact point and the midpoint; judging whether the distance between the contact point and the midpoint is greater than a preset distance or not; if yes, actively controlling the pantograph, and correcting the position of the pantograph; otherwise, continuing to monitor the state of the pantograph.
Description
Technical Field
The invention relates to the technical field of control systems, in particular to a vehicle-mounted pantograph self-adaptive control method and system.
Background
Pantographs are the most commonly used components for transporting power from overhead lines to trains. The motorization of heavy trucks has become the heart of traffic industry carbon reduction, and many students introduce bownet systems in trains into heavy trucks. When the vehicle runs, the pantograph acquires power from the overhead contact system and transmits the power to the vehicle, so that the stability of the contact of the pantograph and the overhead contact system ensures the stability of the power of the vehicle, and has important significance for ensuring the running safety of the vehicle.
However, unlike rail traffic, because the heavy truck running on the road is not constrained by the rail, the direction of the heavy truck is completely controlled by a driver, and once the pantograph is separated from the overhead line, the power cannot be transmitted to the vehicle, so that the vehicle loses power to easily cause traffic accidents, and even when the carbon sliding plate of the pantograph is separated from the overhead line, spark or arc discharge can be caused, thereby generating security threat to passengers and goods. Therefore, in an electrified road transportation system, it is necessary to quickly and accurately detect the contact point position and determine whether or not the pantograph is in good contact with the overhead contact line.
The traditional contact point detection method mainly comprises the steps of comparing a template image with the template image, respectively detecting a pantograph and a contact net, and then calculating the intersection point of two lines of the pantograph and the contact net to obtain a contact point. The traditional template matching method has the advantages that the precision is influenced by factors such as image quality, illumination conditions, background interference and the like, false detection or missing detection is easy to generate, the contact point position estimation is inaccurate, the traditional method generally lacks self-adaptability, and timely correction cannot be performed according to the actual states of the pantograph and the overhead contact line.
Disclosure of Invention
In order to solve the technical problems that the precision of the traditional template matching method is influenced by factors such as image quality, illumination conditions, background interference and the like, false detection or missing detection is easy to generate, so that the contact point position estimation is inaccurate, the traditional method generally lacks self-adaption, and timely correction cannot be performed according to the actual states of a pantograph and a contact net, the invention provides a vehicle-mounted pantograph self-adaption control method and a vehicle-mounted pantograph self-adaption control system.
The technical scheme provided by the invention is as follows:
first aspect
The invention provides a vehicle-mounted pantograph self-adaptive control method, which comprises the following steps:
s1: acquiring a plurality of image data;
s2: dividing a pantograph contour and a catenary contour from each image data by an image dividing technology;
s3: calculating the area of each pantograph contour and each contact net contour, and reserving the pantograph contour and the contact net contour with the largest areas;
s4: acquiring a pantograph contour with the largest area and a minimum circumscribed rectangle of a contact net contour;
s5: performing linear fitting on the upper boundary of the pantograph outline to obtain a first line, and performing linear fitting on the catenary outline to obtain a second line;
s6: calculating an intersection point of the first straight line and the second straight line as a contact point of the pantograph and the contact net;
s7: calculating the midpoint of the upper boundary of the pantograph contour;
s8: calculating a distance between the contact point and the midpoint;
s9: judging whether the distance between the contact point and the midpoint is greater than a preset distance or not; if yes, actively controlling the pantograph, and correcting the position of the pantograph; otherwise, returning to the step S1, and continuing to monitor the pantograph state.
Second aspect
The invention provides a vehicle-mounted pantograph self-adaptive control system, which comprises:
an acquisition module for acquiring a plurality of image data;
the segmentation module is used for segmenting the pantograph contour and the catenary contour from each image data through an image segmentation technology;
the first calculation module is used for calculating the area of each pantograph contour and each contact net contour, and reserving the pantograph contour and the contact net contour with the largest areas;
the acquisition module is used for acquiring the pantograph contour with the largest area and the smallest circumscribed rectangle of the contact net contour;
the fitting module is used for performing linear fitting on the upper boundary of the pantograph outline to obtain a first straight line, and performing linear fitting on the catenary outline to obtain a second straight line;
the second calculation module is used for calculating an intersection point of the first straight line and the second straight line to serve as a contact point of the pantograph and the contact net;
the third calculation module is used for calculating the midpoint of the upper boundary of the pantograph outline;
a fourth calculation module for calculating a distance between the contact point and the midpoint;
the control module is used for judging whether the distance between the contact point and the midpoint is larger than a preset distance or not; if yes, actively controlling the pantograph, and correcting the position of the pantograph; otherwise, returning to the acquisition module, and continuing to monitor the pantograph state.
Compared with the prior art, the technical scheme has at least the following beneficial effects:
according to the invention, the pantograph contour and the overhead line contour are segmented from the acquired image by an image segmentation technology, so that the influence of factors such as image quality, illumination condition, background interference and the like is not easy, the accuracy of detecting the pantograph contour and the overhead line contour can be improved, false detection and omission are reduced, then the pantograph contour and the overhead line contour are subjected to straight line fitting, and the intersection point of the two straight lines is calculated as the contact point of the pantograph and the overhead line.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for adaptively controlling a vehicle-mounted pantograph;
fig. 2 is a schematic structural diagram of a vehicle-mounted pantograph adaptive control method according to the present invention;
fig. 3 is a schematic structural diagram of a vehicle-mounted pantograph adaptive control system according to the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by a person skilled in the art without creative efforts, based on the described embodiments of the present invention fall within the protection scope of the present invention.
Unless defined otherwise, technical or scientific terms used herein should be given the ordinary meaning as understood by one of ordinary skill in the art to which this invention belongs. The terms "first," "second," and the like, as used herein, do not denote any order, quantity, or importance, but rather are used to distinguish one element from another. Likewise, the terms "a," "an," or "the" and similar terms do not denote a limitation of quantity, but rather denote the presence of at least one. The word "comprising" or "comprises", and the like, means that elements or items preceding the word are included in the element or item listed after the word and equivalents thereof, but does not exclude other elements or items. The terms "connected" or "connected," and the like, are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect.
It should be noted that "upper", "lower", "left", "right", "front", "rear", and the like are used in the present invention only to indicate a relative positional relationship, and when the absolute position of the object to be described is changed, the relative positional relationship may be changed accordingly.
Referring to fig. 1 of the specification, a flow diagram of a vehicle-mounted pantograph adaptive control method provided by the invention is shown. Referring to fig. 2 of the specification, a schematic structural diagram of a vehicle-mounted pantograph adaptive control method provided by the invention is shown.
The embodiment of the invention provides a vehicle-mounted pantograph self-adaptive control method, which comprises the following steps:
s1: a plurality of image data is acquired.
Specifically, image acquisition is performed through a high-definition camera, and image data is obtained.
S2: the pantograph contour and the catenary contour are segmented from each image data by an image segmentation technique.
Optionally, preprocessing the image data, the preprocessing including: denoising, image enhancement, scale calibration and the like.
Specifically, a deep learning model such as U-Net or Mask R-CNN can be adopted to directly output semantic labels of each pixel point, wherein different labels can represent a pantograph contour, a catenary contour, a background and the like, and accurate segmentation at the pixel level is realized.
In one possible implementation, S2 specifically includes sub-steps S201 and S202:
s201: and performing semantic segmentation on the image data through a BiSeNet v2 semantic segmentation model to obtain a semantic label of each pixel point.
Among them, biSeNet v2 (Bilateral Segmentation Network version 2) is a deep learning model for image semantic segmentation, which is an upgraded version of BiSeNet, aiming at improving segmentation performance and efficiency. BiSeNet v2 adopts a bilateral segmentation strategy and combines global information and local information to obtain a high-quality semantic segmentation result.
S202: classifying the image data according to the semantic tags of each pixel point to respectively obtain a pantograph contour and a catenary contour.
In the invention, the deep learning model such as BiSeNet v2 is used for semantic segmentation, so that the influence of factors such as image quality, illumination condition, background interference and the like is not easy, the accuracy of detecting the contour of the pantograph and the contour of the overhead line can be improved, false detection and missing detection are reduced, the detection of the contour of the pantograph and the contour of the overhead line is more reliable, the stable contact between the pantograph and the overhead line is ensured, and the safety and reliability of the electric road transportation system are improved.
Optionally, the pantograph contour and the catenary contour are drawn in an image.
S3: and calculating the area of each pantograph contour and each catenary contour, and reserving the pantograph contour and the catenary contour with the largest areas.
Specifically, for each detected pantograph contour and catenary contour, an image processing library or a computer vision library may be used to calculate its area. In most libraries this can be done by the number of pixels of the outline. For example, in the OpenCV library of Python, the area of a contour may be calculated using a cv2.Contour function, where contour is a representation of the contour.
In the invention, the pantograph contour and the catenary contour with the largest area are reserved, other contours are filtered, redundant or unobvious contours possibly appearing can be eliminated, and the interference of noise (small contour) on straight line fitting can be reduced, thereby improving the stability and accuracy of subsequent processing.
S4: and acquiring the minimum circumscribed rectangle of the pantograph contour and the catenary contour with the largest area.
In the present invention, in the OpenCV library of Python, for each contour, a cv2.minarea rect (contour) function can be used to calculate the smallest bounding rectangle that encloses the contour.
S5: and performing linear fitting on the upper boundary of the pantograph contour to obtain a first line, and performing linear fitting on the contact net contour to obtain a second line.
In addition, for the pantograph contour, the direct use of straight line fitting will result in poor fitting result and generate large error due to the large area and the discrete distribution of contour points. The upper and lower boundaries of the segmented pantograph contour are smooth, so that the upper boundary of the minimum circumscribed rectangle of the pantograph contour is used as the surface of the pantograph belt, and the upper boundary is subjected to straight line fitting, so that the complexity of the contour can be reduced to a straight line, the influence of noise is reduced, and the contour is easier to express and analyze.
In one possible implementation, S5 specifically includes substeps S501 to S504:
s501: linear fitting is carried out through a least square method, and a straight line is fitted:
f(x)＝kx+b
where f (x) represents a straight line, k represents a slope, and b represents an intercept.
The least square method is a classical fitting method, and can minimize the vertical distance between the data points and the fitting straight line, so that the accuracy of straight line fitting is improved. This is important for accurately capturing the upper boundary of the pantograph contour, as the shape of the pantograph may have a certain curvature.
S502: constructing a target optimization function through Euclidean distance:
wherein d represents Euclidean distance, x i 、y i Respectively, two-point coordinates, and n represents the number of dimensions of the coordinate axes.
S503: determining the straight line with the best fitting effect by taking the minimum function value of the target optimization function as a target, and returning the output quantity, wherein the output quantity is expressed as (v) x ，v y ，x 0 ，y 0 ) Wherein, (v) x ，v y ) Representing normalized vectors collinear with a straight line, (x) 0 ，y 0 ) Represents any point on the fitted line and results in a normalized vector that is collinear with the line.
It should be noted that, by constructing the objective optimization function, the best fit straight line parameter can be automatically determined, so that the euclidean distance, that is, the distance from the data point to the fit straight line, is minimized. This helps to select the line with the best fit, thereby reducing the fit error and ensuring that the fit is more consistent with the actual data.
S504: and determining a point inclined analytic formula of the fitting straight line according to the output quantity:
wherein,represents the slope (x) 0 ，y 0 ) Representing any point on the fitted line.
In the invention, the straight line fitting of the upper boundary of the pantograph contour is realized through the least square method and the target optimization function, which is beneficial to improving the precision, the robustness and the reliability, and meanwhile, the key geometric information is extracted for the subsequent control and adjustment operation, so that the stable contact between the pantograph and the overhead line is ensured.
S6: and calculating an intersection point of the first straight line and the second straight line as a contact point of the pantograph and the contact net.
S7: the midpoint of the upper boundary of the pantograph contour is calculated.
S8: the distance between the contact point and the midpoint is calculated.
S9: and judging whether the distance between the contact point and the middle point is larger than a preset distance or not. If yes, the pantograph is actively controlled, and the position of the pantograph is corrected. Otherwise, returning to the step S1, and continuing to monitor the pantograph state.
In the invention, when the distance between the contact point and the midpoint of the pantograph is larger than the preset distance, the pantograph is actively controlled, and the position of the pantograph is corrected, so that the pantograph and the contact net always keep good contact, and the stability of the vehicle power is ensured.
The preset distance is specifically a safety distance of the carbon pantograph slide plate.
In one possible implementation manner, the active control on the pantograph specifically includes:
s901: the pantograph is driven to lift and move by the push rod motor.
S902: the pantograph is driven to move left and right through the stepping motor so as to correct the position of the pantograph, and the distance between the contact point and the midpoint is smaller than a preset distance.
According to the invention, the lifting and the left-right movement of the pantograph are actively controlled to correct the position and maintain the distance between the contact point and the middle point, so that the stability, the reliability and the safety of the electric road transportation system can be improved, the effective transmission of electric energy is ensured, and the sustainable electric traffic system is facilitated to be realized.
The vehicle-mounted pantograph self-adaptive control method provided by the invention has the following advantages:
(1) Improving the transportation safety: in real-world transportation, the distance between the pantograph and the catenary may vary. This will cause an interruption of the power supply to the heavy truck, which in turn may cause accidents, posing a threat to transportation safety. The real-time monitoring of the pantograph system can be realized by a pantograph-catenary monitoring technology, so that the driving safety of a road is improved.
(2) The operation efficiency is improved: the stability and reliability of the pantograph-catenary system has a critical impact on the operating efficiency and performance of the electric heavy truck. Through the computer vision detection of the pantograph, the position and the relative displacement between the pantograph and the contact net can be monitored in real time, so that problems can be found and adjusted in time, the running efficiency is improved, and the fault downtime is reduced.
(3) Pushing the development of the technology of the electric heavy truck: with the increasing demands for environmental protection and energy consumption, electric heavy trucks become an important trend. The stability and the reliability of the pantograph, which is an important component of power transmission, have a critical influence on the performance and the safety of the electric heavy truck. Through pantograph-contact net monitoring technology, can ensure the steady operation of electric heavy truck.
(4) Technical support is provided for intelligent transportation: with the continuous development of artificial intelligence and the internet of things, intelligent transportation has become a trend of future development. By applying the pantograph-catenary monitoring technology, the real-time monitoring and adjustment of a pantograph system can be realized, and further technical support is provided for the realization of intelligent transportation.
Compared with the prior art, the technical scheme has at least the following beneficial effects:
according to the invention, the pantograph contour and the overhead line contour are segmented from the acquired image by an image segmentation technology, so that the influence of factors such as image quality, illumination condition, background interference and the like is not easy, the accuracy of detecting the pantograph contour and the overhead line contour can be improved, false detection and omission are reduced, then the pantograph contour and the overhead line contour are subjected to straight line fitting, and the intersection point of the two straight lines is calculated as the contact point of the pantograph and the overhead line.
Referring to fig. 3 of the specification, a schematic structural diagram of a vehicle-mounted pantograph adaptive control system provided by the invention is shown.
The present invention also provides a vehicle-mounted pantograph adaptive control system 30, comprising:
an acquisition module 301, configured to acquire a plurality of image data;
a segmentation module 302, configured to segment a pantograph contour and a catenary contour from each image data by using an image segmentation technique;
a first calculation module 303, configured to calculate an area of each of the pantograph contour and the catenary contour, and reserve a pantograph contour and a catenary contour with the largest areas;
the acquiring module 304 is configured to acquire a pantograph contour with a largest area and a smallest circumscribed rectangle of a catenary contour;
the fitting module 305 is configured to perform straight line fitting on an upper boundary of the pantograph contour to obtain a first straight line, and perform straight line fitting on the catenary contour to obtain a second straight line;
a second calculating module 306, configured to calculate an intersection point of the first straight line and the second straight line as a contact point of the pantograph and the catenary;
a third calculation module 307 for calculating a midpoint of an upper boundary of the pantograph contour;
a fourth calculation module 308 for calculating a distance between the contact point and the midpoint;
a control module 309, configured to determine whether a distance between the contact point and the midpoint is greater than a preset distance; if yes, actively controlling the pantograph, and correcting the position of the pantograph; otherwise, returning to the acquisition module, and continuing to monitor the pantograph state.
In one possible implementation, the segmentation module 302 is specifically configured to:
performing semantic segmentation on the image data through a BiSeNet v2 semantic segmentation model to obtain a semantic label of each pixel;
classifying the image data according to the semantic tags of each pixel point to respectively obtain a pantograph contour and a catenary contour.
In one possible implementation, the fitting module 305 is specifically configured to:
linear fitting is carried out through a least square method, and a straight line is fitted:
f(x)＝kx+b
wherein f (x) represents a straight line, k represents a slope, and b represents an intercept;
constructing a target optimization function through Euclidean distance:
wherein d represents Euclidean distance, x i 、y i Respectively representing two-point coordinates, wherein n represents the dimension number of the coordinate axis;
determining a line with the best fitting effect by taking the minimum function value of the target optimization function as a target, and returning an output quantity, wherein the output quantity is expressed as (v) x ，v y ，x 0 ，y 0 ) Wherein, (v) x ，v y ) Representing normalized vectors collinear with a straight line, (x) 0 ，y 0 ) Representing any point on the fitting straight line, and obtaining a normalized vector collinear with the straight line;
and determining a point inclined analytic formula of the fitting straight line according to the output quantity:
wherein,represents the slope (x) 0 ，y 0 ) Representing any point on the fitted line.
In one possible implementation, the control module 309 is specifically configured to:
the pantograph is driven to move up and down through a push rod motor;
the pantograph is driven to move left and right through the stepping motor so as to correct the position of the pantograph, and the distance between the contact point and the midpoint is smaller than the preset distance.
In one possible embodiment, the preset distance is specifically a safety distance of the carbon slide plate of the pantograph
The vehicle-mounted pantograph self-adaptive control system provided by the invention can execute the vehicle-mounted pantograph self-adaptive control method and realize the same or similar technical effects, and the invention is not repeated for avoiding repetition.
Compared with the prior art, the technical scheme has at least the following beneficial effects:
according to the invention, the pantograph contour and the overhead line contour are segmented from the acquired image by an image segmentation technology, so that the influence of factors such as image quality, illumination condition, background interference and the like is not easy, the accuracy of detecting the pantograph contour and the overhead line contour can be improved, false detection and omission are reduced, then the pantograph contour and the overhead line contour are subjected to straight line fitting, and the intersection point of the two straight lines is calculated as the contact point of the pantograph and the overhead line.
The following points need to be described:
(1) The drawings of the embodiments of the present invention relate only to the structures related to the embodiments of the present invention, and other structures may refer to the general designs.
(2) In the drawings for describing embodiments of the present invention, the thickness of layers or regions is exaggerated or reduced for clarity, i.e., the drawings are not drawn to actual scale. It will be understood that when an element such as a layer, film, region or substrate is referred to as being "on" or "under" another element, it can be "directly on" or "under" the other element or intervening elements may be present.
(3) The embodiments of the invention and the features of the embodiments can be combined with each other to give new embodiments without conflict.
The present invention is not limited to the above embodiments, but the scope of the invention is defined by the claims.
Claims (10)
1. The vehicle-mounted pantograph self-adaptive control method is characterized by comprising the following steps of:
s1: acquiring a plurality of image data;
s2: dividing a pantograph contour and a catenary contour from each image data by an image dividing technology;
s3: calculating the area of each pantograph contour and each contact net contour, and reserving the pantograph contour and the contact net contour with the largest areas;
s4: acquiring a pantograph contour with the largest area and a minimum circumscribed rectangle of a contact net contour;
s5: performing linear fitting on the upper boundary of the pantograph outline to obtain a first line, and performing linear fitting on the catenary outline to obtain a second line;
s6: calculating an intersection point of the first straight line and the second straight line as a contact point of the pantograph and the contact net;
s7: calculating the midpoint of the upper boundary of the pantograph contour;
s8: calculating a distance between the contact point and the midpoint;
s9: judging whether the distance between the contact point and the midpoint is greater than a preset distance or not; if yes, actively controlling the pantograph, and correcting the position of the pantograph; otherwise, returning to the step S1, and continuing to monitor the pantograph state.
2. The vehicle-mounted pantograph adaptive control method according to claim 1, wherein the S2 specifically includes:
s201: performing semantic segmentation on the image data through a BiSeNet v2 semantic segmentation model to obtain a semantic label of each pixel;
s202: classifying the image data according to the semantic tags of each pixel point to respectively obtain a pantograph contour and a catenary contour.
3. The vehicle-mounted pantograph self-adaptive control method according to claim 1, wherein the S5 specifically includes:
s501: linear fitting is carried out through a least square method, and a straight line is fitted:
f(x)＝kx+b
wherein f (x) represents a straight line, k represents a slope, and b represents an intercept;
s502: constructing a target optimization function through Euclidean distance:
wherein d represents Euclidean distance, x i 、y i Respectively representing two-point coordinates, wherein n represents the dimension number of the coordinate axis;
s503: determining a line with the best fitting effect by taking the minimum function value of the target optimization function as a target, and returning an output quantity, wherein the output quantity is expressed as (v) x ，v y ，x 0 ，y 0 ) Wherein, (v) x ，v y ) Representing normalized vectors collinear with a straight line, (x) 0 ，y 0 ) Representing any point on the fitting straight line, and obtaining a normalized vector collinear with the straight line;
s504: and determining a point inclined analytic formula of the fitting straight line according to the output quantity:
wherein,represents the slope (x) 0 ，y 0 ) Representing any point on the fitted line.
4. The vehicle-mounted pantograph adaptive control method according to claim 1, wherein the actively controlling the pantograph specifically includes:
s901: the pantograph is driven to move up and down through a push rod motor;
s902: the pantograph is driven to move left and right through the stepping motor so as to correct the position of the pantograph, and the distance between the contact point and the midpoint is smaller than the preset distance.
5. The vehicle-mounted pantograph self-adaptive control method according to claim 1, wherein the preset distance is specifically a safety distance of a pantograph carbon slide plate.
6. An on-vehicle pantograph self-adaptation control system, characterized by comprising:
an acquisition module for acquiring a plurality of image data;
the segmentation module is used for segmenting the pantograph contour and the catenary contour from each image data through an image segmentation technology;
the first calculation module is used for calculating the area of each pantograph contour and each contact net contour, and reserving the pantograph contour and the contact net contour with the largest areas;
the acquisition module is used for acquiring the pantograph contour with the largest area and the smallest circumscribed rectangle of the contact net contour;
the fitting module is used for performing linear fitting on the upper boundary of the pantograph outline to obtain a first straight line, and performing linear fitting on the catenary outline to obtain a second straight line;
the second calculation module is used for calculating an intersection point of the first straight line and the second straight line to serve as a contact point of the pantograph and the contact net;
the third calculation module is used for calculating the midpoint of the upper boundary of the pantograph outline;
a fourth calculation module for calculating a distance between the contact point and the midpoint;
the control module is used for judging whether the distance between the contact point and the midpoint is larger than a preset distance or not; if yes, actively controlling the pantograph, and correcting the position of the pantograph; otherwise, returning to the acquisition module, and continuing to monitor the pantograph state.
7. The vehicle-mounted pantograph adaptive control system of claim 6, wherein the segmentation module is specifically configured to:
performing semantic segmentation on the image data through a BiSeNet v2 semantic segmentation model to obtain a semantic label of each pixel;
classifying the image data according to the semantic tags of each pixel point to respectively obtain a pantograph contour and a catenary contour.
8. The vehicle-mounted pantograph adaptive control system of claim 6, wherein the fitting module is specifically configured to:
linear fitting is carried out through a least square method, and a straight line is fitted:
f(x)＝kx+b
wherein f (x) represents a straight line, k represents a slope, and b represents an intercept;
constructing a target optimization function through Euclidean distance:
wherein d represents Euclidean distance, x i 、y i Respectively representing two-point coordinates, wherein n represents the dimension number of the coordinate axis;
determining fitting efficiency by taking the minimum function value of the target optimization function as a targetThe best straight line is obtained and returned to the output, which is expressed as (v) x ，v y ，x 0 ，y 0 ) Wherein, (v) x ，v y ) Representing normalized vectors collinear with a straight line, (x) 0 ，y 0 ) Representing any point on the fitting straight line, and obtaining a normalized vector collinear with the straight line;
and determining a point inclined analytic formula of the fitting straight line according to the output quantity:
wherein,represents the slope (x) 0 ，y 0 ) Representing any point on the fitted line.
9. The vehicle-mounted pantograph adaptive control system of claim 6, wherein the control module is specifically configured to:
the pantograph is driven to move up and down through a push rod motor;
the pantograph is driven to move left and right through the stepping motor so as to correct the position of the pantograph, and the distance between the contact point and the midpoint is smaller than the preset distance.
10. The vehicle-mounted pantograph adaptive control system of claim 6, wherein the preset distance is specifically a safety distance of a pantograph carbon slide plate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311278222.5A CN117382426A (en) | 2023-09-28 | 2023-09-28 | Vehicle-mounted pantograph self-adaptive control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311278222.5A CN117382426A (en) | 2023-09-28 | 2023-09-28 | Vehicle-mounted pantograph self-adaptive control method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117382426A true CN117382426A (en) | 2024-01-12 |
Family
ID=89471091
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311278222.5A Pending CN117382426A (en) | 2023-09-28 | 2023-09-28 | Vehicle-mounted pantograph self-adaptive control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117382426A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117781878A (en) * | 2024-02-28 | 2024-03-29 | 四川拓及轨道交通设备股份有限公司 | Empty rail contact net state detection method |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103759658A (en) * | 2014-01-27 | 2014-04-30 | 成都国铁电气设备有限公司 | Method for detecting contact net geometrical parameters based on infrared image processing |
| CN104848792A (en) * | 2015-04-24 | 2015-08-19 | 苏州华兴致远电子科技有限公司 | Vehicle-mounted contact net measuring method and system |
| US20170243357A1 (en) * | 2014-09-15 | 2017-08-24 | Dti Group Limited | Identification of a contact point between a pantograph and a power supply line in an image |
| CN109141255A (en) * | 2018-10-18 | 2019-01-04 | 北京华开领航科技有限责任公司 | A kind of bow net monitoring method |
| CN109318718A (en) * | 2018-09-20 | 2019-02-12 | 青岛四方法维莱轨道制动有限公司 | A kind of pantograph control method judging contact rising bow height based on image procossing |
| CN112132789A (en) * | 2020-08-30 | 2020-12-25 | 南京理工大学 | Pantograph online detection device and method based on cascade neural network |
| CN112985263A (en) * | 2021-02-09 | 2021-06-18 | 中国科学院上海微系统与信息技术研究所 | Method, device and equipment for detecting geometrical parameters of bow net |
| CN114973089A (en) * | 2022-05-30 | 2022-08-30 | 福州大学 | Contact net and pantograph contact point detection method based on image vision algorithm |
-
2023
- 2023-09-28 CN CN202311278222.5A patent/CN117382426A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103759658A (en) * | 2014-01-27 | 2014-04-30 | 成都国铁电气设备有限公司 | Method for detecting contact net geometrical parameters based on infrared image processing |
| US20170243357A1 (en) * | 2014-09-15 | 2017-08-24 | Dti Group Limited | Identification of a contact point between a pantograph and a power supply line in an image |
| CN104848792A (en) * | 2015-04-24 | 2015-08-19 | 苏州华兴致远电子科技有限公司 | Vehicle-mounted contact net measuring method and system |
| CN109318718A (en) * | 2018-09-20 | 2019-02-12 | 青岛四方法维莱轨道制动有限公司 | A kind of pantograph control method judging contact rising bow height based on image procossing |
| CN109141255A (en) * | 2018-10-18 | 2019-01-04 | 北京华开领航科技有限责任公司 | A kind of bow net monitoring method |
| CN112132789A (en) * | 2020-08-30 | 2020-12-25 | 南京理工大学 | Pantograph online detection device and method based on cascade neural network |
| CN112985263A (en) * | 2021-02-09 | 2021-06-18 | 中国科学院上海微系统与信息技术研究所 | Method, device and equipment for detecting geometrical parameters of bow net |
| CN114973089A (en) * | 2022-05-30 | 2022-08-30 | 福州大学 | Contact net and pantograph contact point detection method based on image vision algorithm |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117781878A (en) * | 2024-02-28 | 2024-03-29 | 四川拓及轨道交通设备股份有限公司 | Empty rail contact net state detection method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109635685B (en) | Target object 3D detection method, device, medium and equipment | |
| US20200353932A1 (en) | Traffic light detection method and apparatus, intelligent driving method and apparatus, vehicle, and electronic device | |
| US10552982B2 (en) | Method for automatically establishing extrinsic parameters of a camera of a vehicle | |
| CN107463890B (en) | A kind of Foregut fermenters and tracking based on monocular forward sight camera | |
| CN111801711A (en) | Image annotation | |
| CN107609486A (en) | To anti-collision early warning method and system before a kind of vehicle | |
| CN111563412B (en) | Rapid lane line detection method based on parameter space voting and Bessel fitting | |
| CN111598952B (en) | Multi-scale cooperative target design and online detection identification method and system | |
| CN117382426A (en) | Vehicle-mounted pantograph self-adaptive control method and system | |
| CN111667512A (en) | Multi-target vehicle track prediction method based on improved Kalman filtering | |
| CN110059683A (en) | A kind of license plate sloped antidote of wide-angle based on end-to-end neural network | |
| CN109753841B (en) | Lane line identification method and device | |
| CN113370977B (en) | Intelligent vehicle forward collision early warning method and system based on vision | |
| CN112085024A (en) | Tank surface character recognition method | |
| CN105279770A (en) | Target tracking control method and device | |
| CN114120075A (en) | Three-dimensional target detection method integrating monocular camera and laser radar | |
| Muthalagu et al. | Vehicle lane markings segmentation and keypoint determination using deep convolutional neural networks | |
| CN114693716A (en) | Driving environment comprehensive identification information extraction method oriented to complex traffic conditions | |
| Li et al. | Real-time accurate deep learning-based edge detection for 3-D pantograph pose status inspection | |
| CN116206263B (en) | Logistics vehicle monitoring method and system | |
| CN105760876A (en) | Vehicle logo location method based on radiator grid background ablation | |
| CN116311136A (en) | Lane line parameter calculation method for driving assistance | |
| CN107292282B (en) | A kind of vehicle checking method updated based on semantic reasoning and space-time memory | |
| CN110827240B (en) | Positioning method and device for steel rail profile | |
| Tian et al. | An improved lane boundaries detection based on dynamic ROI |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |