CN113581244A - Intelligent iron shoe track identification system and method based on information fusion - Google Patents
Intelligent iron shoe track identification system and method based on information fusion Download PDFInfo
- Publication number
- CN113581244A CN113581244A CN202110821256.9A CN202110821256A CN113581244A CN 113581244 A CN113581244 A CN 113581244A CN 202110821256 A CN202110821256 A CN 202110821256A CN 113581244 A CN113581244 A CN 113581244A
- Authority
- CN
- China
- Prior art keywords
- track
- positioning
- identification
- data
- terminal
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 101
- 230000004927 fusion Effects 0.000 title claims abstract description 43
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 title claims description 212
- 229910052742 iron Inorganic materials 0.000 title claims description 106
- 238000001914 filtration Methods 0.000 claims abstract description 39
- 238000012544 monitoring process Methods 0.000 claims abstract description 35
- 238000007619 statistical method Methods 0.000 claims abstract description 26
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000004422 calculation algorithm Methods 0.000 claims description 10
- 238000013507 mapping Methods 0.000 claims description 9
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 7
- 238000004891 communication Methods 0.000 claims description 6
- 239000002184 metal Substances 0.000 claims description 4
- 229910052751 metal Inorganic materials 0.000 claims description 4
- 238000004080 punching Methods 0.000 claims description 3
- 239000000523 sample Substances 0.000 claims description 3
- 239000000126 substance Substances 0.000 claims description 3
- 239000013589 supplement Substances 0.000 claims description 3
- 240000007594 Oryza sativa Species 0.000 claims 1
- 235000007164 Oryza sativa Nutrition 0.000 claims 1
- 238000002715 modification method Methods 0.000 claims 1
- 235000009566 rice Nutrition 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 8
- 230000002411 adverse Effects 0.000 abstract description 2
- 230000008094 contradictory effect Effects 0.000 abstract 1
- 238000010586 diagram Methods 0.000 description 2
- 238000007792 addition Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000000689 upper leg Anatomy 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B61—RAILWAYS
- B61K—AUXILIARY EQUIPMENT SPECIALLY ADAPTED FOR RAILWAYS, NOT OTHERWISE PROVIDED FOR
- B61K9/00—Railway vehicle profile gauges; Detecting or indicating overheating of components; Apparatus on locomotives or cars to indicate bad track sections; General design of track recording vehicles
- B61K9/08—Measuring installations for surveying permanent way
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- Train Traffic Observation, Control, And Security (AREA)
Abstract
The invention discloses an intelligent skate track identification system based on information fusion, which comprises more than 4 positioning satellites, a reference station, a 4G private base station, a plurality of pairs of intelligent skates, a positioning terminal and a monitoring upper computer; and the positioning terminal fuses the recognition results of the two track recognition methods, namely the precision weight statistical method and the variance Gaussian filtering method, and the final track recognition result is obtained through comprehensive judgment so as to realize the accurate track recognition. When the accuracy weight statistical method is used for identifying the stock track, the accuracy weight of the positioning data is reasonably introduced, the effect of high-accuracy data on the identification effect is improved, the adverse effect of low-accuracy data on the identification effect is effectively reduced, and the identification result is more accurate and effective. The track identification method based on information fusion is provided, and the problem that results of two identification methods are contradictory is effectively solved.
Description
Technical Field
The invention relates to the technical field of railways, in particular to a system and a method for accurately identifying a railway track where an intelligent skate is located in the process of train anti-slip operation in a railway station yard.
Background
With the increase of railway lines and the widening of coverage areas, the intelligent iron shoes are increasingly widely applied, and become important equipment for protecting the safety of personnel and vehicles.
At present, most traditional skate do not have the station track recognition function of locating, but even partial intelligent skate can carry out station track recognition but the recognition accuracy is not high, and the main reason and the problem that exists are as follows:
because the GPS positioning of the intelligent skate is greatly influenced by various factors such as environment and the like, the railway station environment is severe, the electromagnetic environment is complex, a large amount of electromagnetic interference can reduce the positioning precision of the positioning terminal, and because human bodies, trains, buildings and the like shield satellite positioning signals, the positioning result of the positioning terminal generates deviation.
The position is confirmed to the high accuracy locating information that intelligence skate carried out the track identification and mainly provided through the intelligence skate, therefore the positioning deviation problem of GPS location can influence positioning terminal and obtain accurate positioning data, has certain deviation between the positioning data that makes the intelligence skate obtain and the true value, and the wrong positioning data is received to the intelligence skate even, makes intelligence skate track identification mistake, causes the confusion in the intelligent skate management.
Disclosure of Invention
The invention aims to solve the problems and provides an intelligent skate track identification system and method, which are suitable for accurately identifying a railway track where an intelligent skate is located in the process of train anti-slip operation in a railway station yard.
The technical scheme of the invention is as follows:
an intelligent skate track identification system based on information fusion comprises more than 4 positioning satellites, a reference station, a 4G private base station, a plurality of pairs of intelligent skates, a positioning terminal and a monitoring upper computer;
the satellite communication system comprises a satellite, a reference station, a positioning terminal and a satellite communication module, wherein the satellite is communicated with the reference station and the positioning terminal in the satellite north-seeking bucket positioning system, and sends positioning signals to the reference station and the positioning terminal;
the reference station receives a positioning signal of a positioning satellite to calculate to obtain self-positioning information, calculates with self-surveying and mapping position coordinates to obtain differential data, and sends the differential data to a positioning terminal through a 4G private base station for positioning correction;
the positioning terminal is placed beside the intelligent skate and is bound with the intelligent skate for use, the positioning terminal receives positioning signals of a positioning satellite to determine self-positioning information, and high-precision positioning information is provided for the intelligent skate on the basis of a differential data correction method; the positioning terminal fuses recognition results of the precision weight statistical method and the variance Gaussian filtering method, and the final track recognition result is obtained through comprehensive judgment, so that the track is accurately recognized; the positioning terminal sends the positioning result to the monitoring upper computer through the 4G private base station;
the 4G private base station receives the reference station differential data and forwards the reference station differential data to the positioning terminal on one hand, and receives positioning data corrected by the positioning terminal on the other hand; on the other hand, the 4G private base station interacts with the monitoring upper computer through the wired Ethernet interface, and transmits the received positioning data corrected by the positioning terminal to the upper computer.
Preferably, the difference data correction method includes: and correcting the current self-position observation value determined by the positioning terminal based on the differential data obtained from the reference station, namely adding the current self-position observation value and the differential data to obtain the high-precision positioning data corrected by the positioning terminal.
The invention also discloses an intelligent skate track identification method based on information fusion, which is based on any system and comprises the following steps: the method comprises four steps of system initialization, terminal and skate identification matching, terminal positioning identification track and monitoring the update state of an upper computer, and the specific flow is as follows:
step 1: system initialization
The system initialization comprises the initialization of a Beidou positioning module in a positioning terminal and the initialization of station track information of a train station, wherein the latter comprises the geographical information of a track central line and the number k of station tracks obtained according to station track geographical mapping information, and the number i of groups of positioning data collected before and after the time of initial identification is 5;
step 2: terminal and skate recognition matching
Performing anti-slip operation by railway station staff, performing RFID (radio frequency identification) radio frequency identification on the intelligent iron shoe by using a positioning terminal after the intelligent iron shoe is placed, and matching the intelligent iron shoe with the positioning terminal;
and step 3: positioning terminal positioning and identifying track
After the positioning terminal is successfully matched with the intelligent iron shoe, high-precision positioning data of i seconds are respectively taken before and after the RFID matching time is taken as a reference time to form a data sequence with the length of 2 x i +1, the identification system utilizes the group of positioning data to sequentially carry out track identification by a precision weight statistical method and track identification by a variance Gaussian filter method, and track identification results are determined and output if the two identification results are consistent; if the identification results are inconsistent, the number i of the positioning data acquisition groups is made to be i +5, the step 3 is repeated, and after 3 times of circulation, the identification results of the two methods are still inconsistent, the two identification results are subjected to fusion judgment by using a DS evidence reasoning algorithm, and the information fusion judgment result is used as a final identification result;
and 4, step 4: monitoring update state of upper computer
After the identification of the iron shoe track is successful, the monitoring upper computer detects whether a car is in the track, if the monitoring upper computer displays that the car is in the track, the iron shoe is on line normally, and the monitoring upper computer updates the states of the train and the iron shoe in the track; and if the situation that the station track has no cars is displayed, whether the iron shoes are placed in place or not is confirmed again, and whether the upper computer needs to supplement and record car number information or replace the iron shoes is judged.
Specifically, the specific steps of the positioning terminal and the skate matching identification in the step 2 are as follows:
2-1), the field operator firstly takes the intelligent iron shoe and the positioning terminal out of the anti-slip appliance box, transfers the intelligent iron shoe to an anti-slip operation place, and places the intelligent iron shoe on a preset rail;
2-2), matching and binding the positioning terminal with the intelligent skate through RFID radio frequency identification;
2-3), judging whether the positioning terminal is successfully matched with the iron shoe: if the matching is not successful, executing the step 2-2); and if the matching is successful, entering the step 3.
Specifically, the specific steps of the positioning terminal positioning and identifying the track in step 3 are as follows:
3-1), after the positioning terminal is successfully matched with the iron shoe, placing the positioning terminal beside the iron shoe, taking the RFID time of the terminal and the iron shoe as a reference time, respectively taking i groups of high-precision positioning data in front and at back to form a positioning data sequence with the length of 2 x i +1, and executing the step 3-2);
3-2) identifying the track by using an accuracy weight statistical method: respectively identifying the tracks of the 2 x i +1 groups of positioning data, distributing the precision weights of the positioning data to the identified tracks, finally counting the precision weights of all the tracks, taking the track with the highest precision weight statistic value as a track identification result, and executing the step 3-3 after obtaining the track identification result;
3-3) identifying the tracks by using a variance-variable Gaussian filtering method: performing variance-variable Gaussian filtering calculation on the 2 x i +1 groups of positioning data to obtain coordinates (x ', y') after variance-variable Gaussian filtering, calculating the vertical distance between the coordinates after variance-variable Gaussian filtering and the central line of each track, wherein the track closest to the coordinates is a track identification result, and executing the step 3-4 after obtaining the track identification result;
3-4), judging whether the track identification results of the two methods are consistent: if the results are consistent, uploading the track identification result, and entering the step 4; if the results are not consistent, executing the step 3-5);
3-5), making i equal to i +5, expanding the range of the acquisition time of the positioning data, and judging whether i is less than or equal to 15; if i is less than or equal to 15, executing the step 3-1); if i >15, performing step 3-6);
3-6) respectively calculating the credibility of the two methods to different recognition results by adopting a recognition result fusion judgment method based on different recognition methods, carrying out fusion calculation to judge the track recognition result by utilizing a DS evidence reasoning algorithm, taking the fusion judgment result as a final result and uploading the final result, and entering the step 4.
Specifically, the specific steps of using the accuracy weight statistics method to identify the track in step 3-2) are as follows:
3-2-1), use the moment of punching the card as the benchmark, respectively take i group's locating data around, obtain a length and be 2 i + 1's locating data sequence, to 2 i +1 group's locating data according to the precision distribution weight, the weight distribution specifically sees the following table:
wherein deltajPositioning data accuracy, omega, for the jth positioning datajThe accuracy weight of the jth positioning data; let j equal 1, G1＝G2＝···＝Gk＝0，G1、G2···GkRespectively obtaining the precision weight statistics of k tracks, and executing the step 3-2-2);
3-2-2), fetching j group positioning data (x) in positioning data sequencej,yj) Calculating the anchor point (x)j,yj) Perpendicular distance L from the center line of each track1···LkExecuting step 3-2-3);
3-2-3), determining L1···LkMinimum and mean value Lm，m∈[1,k]I.e. the location point has the minimum distance from the track m and the accuracy weight of the location data is omegajCounting the precision weight on the corresponding track weight to order Gm＝Gm+ωjJ ═ j +1, perform steps 3-2-4);
3-2-4), judging whether j is less than or equal to 2 x i + 1: if j is less than or equal to 2 x i +1, executing the step 3-2-2); if j >2 x i +1, performing steps 3-2-5);
3-2-5), determination of G1、G2···GkMiddle maximum is GN，N∈[1,k]And the track identification result of the precision weight statistical method is track N, and the process is finished.
Specifically, the specific steps of using the variance-varying gaussian filtering method to identify the station track in step 3-3) are as follows:
3-3-1), taking the time of swiping card as a reference, and respectively taking i groups of positioning data in front and at back to obtain a positioning data sequence P with the length of (2 x i +1)1(x1,y1)、P2(x2,y2)、···、P2i+1(x, y), each group of data in the sequence is endowed with a Gaussian weight value, and the coordinate data after the variance Gaussian filtering is (x ', y'), wherein the calculation modes of x 'and y' are as follows:
wherein x isj、yjAnd sigma respectively correspond to the x coordinate, the y coordinate and the Gaussian distribution standard deviation of the j-th group of positioning data. For positioning data sequences with different lengths, different sigma values are selected, weight distribution is changed, when i is gradually increased and the length of the positioning data sequences is enlarged, the sigma value is reduced to improve the weight of the positioning data near the reference time, the weight of the positioning data at the edge time is reduced, and when i is 5, the sigma is 10; when i is 10, taking sigma as 4.5; when i is 15, taking sigma as 4;
performing variance Gaussian filtering on all positioning data in the sequence to obtain coordinates (x ', y'), and executing the step 3-3-2);
3-3-2), calculating the vertical distance L between the coordinate point (x ', y') and the central line of each track1···LkThen, executing the step 3-3-3);
3-3-3), determining L1···LkThe minimum value is LM，M∈[1,k]And the track identification result is the track M,
and (6) ending.
Specifically, the algorithm for calculating the vertical distance between the positioning coordinate point and the central line of each track specifically comprises:
(1) according to train stationGeographical mapping data of field track, determining the geographical position of central line of track, and determining the coordinates of two end points of central line of track as A (X)1,Y1)，B(X2,Y2)；
(2) And (3) coordinates P (X, Y) of the positioning point, wherein the vertical distance between the positioning point P and the central line of the femoral track is as follows:
specifically, in the identification result fusion judgment method based on the two track identification methods in step 3-6), the track identification is respectively performed by the precision weight statistical method and the variance gaussian filtering method, and the track identification result is judged by fusion calculation under the condition that the track identification results are inconsistent, wherein the fusion judgment process specifically comprises the following steps:
recording the identification result of the precision weight statistical method as p and the identification result of the variance Gaussian filtering method as q; p, q belongs to [1, k ] and p is not equal to q, namely the two identification methods have different identification results;
the credibility of the accuracy weight statistical method for the track identification results p and q is respectively as follows:
wherein the content of the first and second substances,
is the sum of the precision weight statistics, G, of all tracksp，GqRespectively obtaining precision weight statistics values of a p track and a q track;
the credibility of the variance-variable Gaussian filtering method for the station track identification result p and q is respectively as follows:
calculating the credibility m (p) of the matching track p and the credibility m (q) of the matching track q based on the recognition results of the two track recognition methods in a fusion manner, wherein:
comparing m (p) with m (q), if m (p) > m (q), judging that the fusion is matched with the track p; if m (p) < m (q), the fusion is judged to be matched with the track q; if m (p) ═ m (q), the possibility of matching the track p and the track q is prompted.
Specifically, the step 4 of monitoring the update state of the upper computer specifically comprises the following steps:
4-1), whether this track of host computer has the car according to intelligence skate track of the track recognition result monitoring: if the upper computer shows that the station track has no vehicles, executing the step 4-2); if the upper computer displays that the station track has the car, executing the step 4-4);
4-2), detecting whether the iron shoe is placed in place: the iron shoe in place includes two conditions: 1. determining that the iron shoe is in the rail by a metal detector on the iron shoe; 2. detecting the distance between the iron shoe and the wheel by a sound wave distance measuring probe on the iron shoe, and determining that the iron shoe is placed in the anti-slip range; when the iron shoes are in the rail and in the anti-skid range and the iron shoes are placed in place, executing the step 4-3); if any condition is not met, the iron shoes are not placed in place, the iron shoes need to be placed again, and the step 2 is executed;
4-3), if the skate is placed in place, the upper computer does not timely input the train number information, and the step 4-4 is executed after the train number information is additionally recorded;
4-4), the normal online of the iron shoes, the monitoring upper computer updates the states of the trains and the intelligent iron shoes on the track, and the process is finished.
The invention has the advantages of
By adopting the technical means, compared with the prior art, the invention has the following beneficial effects:
1. the intelligent skate track identification system and method based on information fusion are suitable for carrying out intelligent track identification by applying intelligent skates in a railway station yard; according to the invention, the intelligent iron shoe positioning system and the station track identification method are optimized, so that the problems of large positioning deviation and inaccurate station track identification of the intelligent iron shoes in a complex train station environment are solved, and the station track identification accuracy of the intelligent iron shoes is effectively improved.
2. The positioning terminal is bound with the intelligent skate and used, and the positioning terminal corrects the positioning data of the positioning terminal through acquiring the differential correction data of the reference station, so that high-precision positioning data are provided for the intelligent skate.
3. According to the track identification method, the matching time of the positioning terminal and the RFID (radio frequency identification) of the intelligent iron shoe is taken as a reference time, i groups of positioning data are collected respectively in front and at the back to form a positioning data sequence with the length of (2 x i +1), track identification is carried out by using the group of data, and the reliability of data is high.
4. The track identification method provided by the invention is used for obtaining track identification results by reasonably fusing a precision weight statistical method and a variance Gaussian filtering method, and when the identification results of the two methods are consistent, the identification results are used as final identification results; and if the results are inconsistent, the acquisition range of the positioning data is expanded, the track identification is carried out for multiple times in a circulating manner, and the probability of track identification errors is reduced.
5. When the accuracy weight statistical method is used for identifying the stock track, the accuracy weight of the positioning data is reasonably introduced, the effect of high-accuracy data on the identification effect is improved, the adverse effect of low-accuracy data on the identification effect is effectively reduced, and the identification result is more accurate and effective.
6. When the variable variance Gaussian filtering method is used for identifying the tracks, the selected length (2 x i +1) positioning data sequence is used as a basis, the data sequence is processed according to Gaussian weight, the weight distribution can be dynamically and automatically changed for the positioning data sequences with different (2 x i +1) lengths, when i is gradually increased and the length of the positioning data sequence is enlarged, the sigma value is reduced to improve the weight of the positioning data near the reference moment, the weight of the positioning data at the edge moment is reduced, and the error caused by the low-reliability data at the edge moment can be effectively reduced; when i is gradually reduced and the length of the positioning data sequence is reduced, the useful information of the edge moment can be effectively utilized by improving the sigma value, and finally the purpose of improving the accuracy of the stock path identification by the variance Gaussian filtering method is achieved.
7. A track identification method based on information fusion is provided, if the acquisition range of the positioning data exceeds a set maximum value, namely, the identification results obtained by an accuracy weight statistical method and a variance Gaussian filtering method when i is more than 15 are still inconsistent, a DS evidence reasoning algorithm is adopted for fusion judgment, the credibility of the two identification results is respectively calculated, the result with higher credibility is used as a final identification result, the problem that the results of the two identification methods are inconsistent is effectively solved, in the process of calculating the credibility, information in multiple aspects is fused, and the final identification result is more credible.
8. After the control host computer obtains the station track recognition result, detect this station track train state, through metal detection device, sound wave range unit on the intelligent skate, confirm whether intelligent skate places and targets in place, further judge whether need carry out the operation such as supplementary recording train number or place the skate again, can effectively prevent to place the mistake and cause the train accident because of the skate, guarantee train operation safety.
Drawings
Fig. 1 is an overall architecture diagram of an intelligent track identification system for iron shoes in the invention.
FIG. 2 is a flowchart of the overall work flow of the intelligent track identification method for the iron shoe of the present invention.
FIG. 3 is a flow chart of the accuracy weight statistics track identification process of the present invention.
FIG. 4 is a flow chart of the operation of channel identification by variance Gaussian filtering method in the present invention.
FIG. 5 is a schematic diagram of calculating the distance between the location coordinate point and the center line of the track according to the present invention.
Detailed Description
As shown in fig. 1, an intelligent skate track identification system comprises more than 4 positioning satellites, a reference station, a 4G private base station, a plurality of pairs of intelligent skates, a positioning terminal and a monitoring upper computer.
The satellite communication with the reference station and the positioning terminal is established in the satellite north-seeking bucket positioning system, and the satellite communication with the reference station and the positioning terminal is established and the positioning signal is sent to the reference station and the positioning terminal.
The reference station receives positioning signals of 4 or more satellites, can calculate to obtain self-positioning information, calculates with self-surveying and mapping position coordinates to obtain differential data, and sends the differential data to the positioning terminal through the 4G private base station for positioning correction.
The positioning terminal is placed beside the intelligent skate and used in a binding mode with the intelligent skate, the positioning terminal receives positioning signals of more than 4 satellites to determine self positioning information, difference data obtained from a reference station corrects a self position observation value, and the two are added to obtain high-precision positioning data corrected by the positioning terminal. The high accuracy positioning data of positioning terminal with self is as the high accuracy positioning data of intelligence skate, provides high accuracy locating information for the intelligence skate, realizes functions such as the judgement of the place thigh of intelligence skate, stolen warning, and positioning terminal sends the location result for the control host computer through 4G private basic station, finally realizes the high accuracy location of intelligence skate to the monitoring function of swift current system is prevented to the intelligence has been perfected.
The intelligence skate includes intelligent box and skate body, and intelligence skate adds intelligent box realization intelligence on traditional mechanical type skate basis and prevents swift current.
On one hand, the 4G private base station receives the differential data of the reference station and forwards the differential data to the positioning terminal, and meanwhile receives positioning data corrected by the positioning terminal (used for expanding the signal coverage); on the other hand, the 4G private base station interacts with the monitoring upper computer through the wired Ethernet interface, and transmits the received positioning data corrected by the positioning terminal to the upper computer.
And the monitoring upper computer continuously monitors the state of the placed iron shoes for 24 hours and displays the station where the iron shoes are located.
The positioning terminal is bound with the intelligent iron shoe for use, and when an on-site operator performs anti-slip operation, the intelligent iron shoe and the positioning terminal are taken out of the anti-slip appliance box and then transferred to an anti-slip operation position; then, placing iron shoes and other anti-slip operations are carried out, after the anti-slip operations are finished, the positioning terminal is matched and bound with the intelligent iron shoes through RFID radio frequency identification, the intelligent iron shoes are hung on a train carriage and then pressed down by a button on equipment, and then the positioning terminal can upload high-precision positioning data to a server to finish the positioning function of the iron shoe track; after the anti-slip operation is finished, an operator removes the skate from the wheels, takes down the positioning terminal from the train compartment, pops up the key, and finally puts the positioning terminal back into the anti-slip appliance box, so that the operation is finished.
As shown in fig. 2, an intelligent method for identifying a track of an iron shoe comprises the following steps: the method comprises four steps of system initialization, terminal and skate identification matching, terminal positioning identification track and monitoring the update state of an upper computer, and the specific flow is as follows:
step 1: system initialization
The system initialization comprises the initialization of a Beidou positioning module in a positioning terminal and the initialization of station track information of a train station, wherein the latter comprises the geographical information of a track central line obtained according to station track geographical mapping information and the number k (the k value is maximum 8) of station tracks, and the number i of the collected positioning data sets before and after the first time of identification is 5;
step 2: terminal and skate recognition matching
Performing anti-slip operation by railway station staff, performing RFID (radio frequency identification) radio frequency identification on the intelligent iron shoe by using a positioning terminal after the intelligent iron shoe is placed, and matching the intelligent iron shoe with the positioning terminal;
the specific steps of the positioning terminal and the iron shoe matching identification in the step 2 are as follows:
2-1), the field operator firstly takes the intelligent iron shoe and the positioning terminal out of the anti-slip appliance box, transfers the intelligent iron shoe to an anti-slip operation place, and places the intelligent iron shoe on a preset rail;
2-2), matching and binding the positioning terminal with the intelligent skate through RFID radio frequency identification;
2-3), judging whether the positioning terminal is successfully matched with the iron shoe: if the matching is not successful, executing the step 2-2); if the matching is successful, entering the step 3;
and step 3: positioning terminal positioning and identifying track
After the positioning terminal is successfully matched with the intelligent iron shoe, high-precision positioning data of i seconds are respectively taken before and after the RFID matching time is taken as a reference time to form a data sequence with the length of (2 x i +1), the identification system utilizes the group of positioning data to sequentially carry out track identification by a precision weight statistical method and track identification by a variance Gaussian filter method, and track identification results are determined and output if the two identification results are consistent; if the identification results are inconsistent, the number i of the positioning data acquisition groups is made to be i +5, the step 3 is repeated, and after 3 times of circulation, the identification results of the two methods are still inconsistent, the two identification results are subjected to fusion judgment by using a DS evidence reasoning algorithm, and the information fusion judgment result is used as a final identification result;
the specific steps of the positioning terminal positioning and identifying the track are as follows:
3-1), after the positioning terminal is successfully matched with the iron shoe, placing the positioning terminal beside the iron shoe, taking the RFID time of the terminal and the iron shoe as a reference time, respectively taking i groups of high-precision positioning data in front and at back to form a positioning data sequence with the length of (2 x i +1), and executing the step 3-2);
3-2) identifying the track by using an accuracy weight statistical method: respectively identifying the tracks of the (2 x i +1) group positioning data, distributing the precision weights of the positioning data to the identified tracks, finally counting the total weight of each track, taking the track with the highest total weight as a track identification result, and executing the step 3-3 after obtaining the track identification result;
3-3) identifying the tracks by using a variance-variable Gaussian filtering method: performing variance-variable Gaussian filtering calculation on the (2 x i +1) group positioning data to obtain coordinates (x ', y') after variance-variable Gaussian filtering, calculating the vertical distance between the coordinates after variance-variable Gaussian filtering and the central line of each track, wherein the track closest to the coordinates is a track identification result, and executing the step 3-4 after obtaining the track identification result;
3-4), judging whether the track identification results of the two methods are consistent: if the results are consistent, uploading the track identification result, and entering the step 4; if the results are not consistent, executing the step 3-5);
3-5), making i equal to i +5, expanding the range of the acquisition time of the positioning data, and judging whether i is less than or equal to 15; if i is less than or equal to 15, executing the step 3-1); if i >15, perform step 3-6).
3-6), respectively calculating the credibility of the two methods to different recognition results by adopting a recognition result fusion judgment method based on different recognition methods, carrying out fusion calculation to judge a track recognition result by utilizing a DS evidence reasoning algorithm, taking the fusion judgment result as a final result and uploading the final result, and entering step 4;
and 4, step 4: monitoring update state of upper computer
After the identification of the iron shoe track is successful, the monitoring upper computer detects whether a car is in the track, if the monitoring upper computer displays that the car is in the track, the iron shoe is on line normally, and the monitoring upper computer updates the states of the train and the iron shoe in the track; if the current share is displayed without the train, whether the iron shoes are placed in place or not is confirmed again, and whether the upper computer needs to supplement and record train number information or replace the iron shoes is judged.
The specific steps of monitoring the update state of the upper computer in the step 4 are as follows:
4-1), whether this track of host computer has the car according to intelligence skate track of the track recognition result monitoring: if the upper computer shows that the station track has no vehicles, executing the step 4-2); if the upper computer displays that the station track has the car, executing the step 4-4);
4-2), detecting whether the iron shoe is placed in place: the iron shoe in place includes two conditions: 1. determining that the iron shoe is in the rail by a metal detector on the iron shoe; 2. the distance between the iron shoe and the wheel is detected by the sound wave distance measuring probe on the iron shoe, and the iron shoe is placed in the anti-slip range. When the iron shoes are in the rail and in the anti-skid range and the iron shoes are placed in place, executing the step 4-3); if any condition is not met, the iron shoes are not placed in place, the iron shoes need to be placed again, and the step 2-1) is executed;
4-3), if the skate is placed in place, the upper computer does not timely input the train number information, and the step 4-4 is executed after the train number information is additionally recorded;
4-4), the normal online of the iron shoes, the monitoring upper computer updates the states of the trains and the intelligent iron shoes on the track, and the process is finished.
As shown in fig. 3, the method for performing track identification by using the accuracy weight statistical method in step 3-2) is to assign accuracy weights to (2 × i +1) groups of positioning data, perform track identification respectively, count the accuracy weight statistics of each track, and use the track with the highest accuracy weight statistics as a track identification result, where the specific steps of performing track identification by using the accuracy weight statistical method are as follows:
3-2-1), use the moment of punching the card as the benchmark, each take i group's locating data before and after, obtain a length (2 x i +1) locating data sequence, to (2 x i +1) group's locating data according to the precision distribution weight, the weight formula is:
wherein deltajPositioning data accuracy, omega, for the jth positioning datajThe accuracy weight of the jth positioning data. Let j equal 1, G1＝G2＝···＝Gk＝0，G1、G2···GkRespectively carrying out step 3-2-2) for the identification weight statistics of k tracks;
3-2-2), fetching j group positioning data (x) in positioning data sequencej,yj) Calculating the anchor point (x)j,yj) Perpendicular distance L from the center line of each track1···Lk. Performing step 3-2-3);
3-2-3), determining L1···LkMinimum and mean value Lm，m∈[1,k]I.e. the location point is closest to track m and the accuracy weight of the location data is deltajCounting the precision weight on the corresponding track weight to order Gm＝Gm+δjJ ═ j +1, perform steps 3-2-4);
3-2-4), judging whether j is less than or equal to 2 x i + 1: if j is less than or equal to 2 x i +1, executing the step 3-2-2); if j >2 x i +1, performing steps 3-2-5);
3-2-5), determination of G1、G2···GkMiddle maximum is GN，N∈[1,k]And the track identification result of the precision weight statistical method is track N, and the process is finished.
As shown in fig. 4, the method for identifying the track using the variance gaussian filtering method in step 3-3) is to perform variance gaussian filtering calculation on the (2 × i +1) group positioning data to obtain the coordinates (x ', y') after the variance gaussian filtering, calculate the vertical distance between the coordinates of the variance gaussian filtering and the centerline of each track, and determine the track closest to the coordinate as the track identification result, wherein the specific steps of identifying the track using the variance gaussian filtering method are as follows:
3-3-1), taking the time of swiping card as a reference, and respectively taking i groups of positioning data in front and at back to obtain a positioning data sequence P with the length of (2 x i +1)1(x1,y1)、P2(x2,y2)、···、P2i+1(x, y), each group of data in the sequence is endowed with a Gaussian weight value, and the coordinate data after the variance Gaussian filtering is (x ', y'), wherein the calculation modes of x 'and y' are as follows:
wherein x isj、yjAnd sigma respectively correspond to the x coordinate, the y coordinate and the Gaussian distribution standard deviation of the j-th group of positioning data. For positioning data sequences with different lengths, different sigma values are selected, weight distribution is changed, when i is gradually increased and the length of the positioning data sequences is enlarged, the sigma value is reduced to improve the weight of the positioning data near the reference time, the weight of the positioning data at the edge time is reduced, and when i is 5, the sigma is 10; when i is 10, taking sigma as 4.5; when i is 15, σ is 4.
Performing variance Gaussian filtering on all positioning data in the sequence to obtain coordinates (x ', y'), and executing the step 3-3-2);
3-3-2), calculating the vertical distance L between the coordinate point (x ', y') and the central line of each track1···LkThen, executing the step 3-3-3);
3-3-3), determining L1···LkThe minimum value is LM，M∈[1,k]And the track identification result is the track M,
and (6) ending.
Step 3-6) an identification result fusion judgment method based on the two track identification methods, wherein the specific fusion judgment process is as follows:
and recording the identification result of the precision weight statistical method as p, and recording the identification result of the variable variance Gaussian filter method as q. p, q belongs to [1, k ] and p is not equal to q, namely the two identification methods have different identification results.
The credibility of the accuracy weight statistical method for the track identification results p and q is respectively as follows:
wherein the content of the first and second substances,
is the sum of the precision weight statistics, G, of all tracksP，GqThe precision weight statistics values of the p track and the q track are respectively.
The credibility of the variance-variable Gaussian filtering method for the station track identification result p and q is respectively as follows:
calculating the credibility m (p) of the matching track p and the credibility m (q) of the matching track q based on the recognition results of the two track recognition methods in a fusion manner, wherein:
comparing m (p) with m (q), if m (p) > m (q), judging that the fusion is matched with the track p; if m (p) < m (q), the fusion is judged to be matched with the track q; if m (p) ═ m (q), the possibility of matching the track p and the track q is prompted.
As shown in fig. 5, the algorithm for calculating the vertical distance between the positioning coordinate point and the central line of each track specifically includes:
(1) according to the track geographic mapping data of the train station yard, determining the geographic position of the center line of the track, and determining the coordinates of two end points of the center line of the track to be A (X)1,Y1)，B(X2,Y2)；
(2) And (3) coordinates P (X, Y) of the positioning point, wherein the vertical distance between the positioning point P and the central line of the femoral track is as follows:
the specific embodiments described herein are merely illustrative of the spirit of the invention. Various modifications or additions may be made to the described embodiments or alternatives may be employed by those skilled in the art without departing from the spirit or ambit of the invention as defined in the appended claims.
Claims (10)
1. An intelligent skate track identification system based on information fusion is characterized by comprising more than 4 positioning satellites, a reference station, a 4G private base station, a plurality of pairs of intelligent skates, a positioning terminal and a monitoring upper computer;
the satellite communication system comprises a satellite, a reference station, a positioning terminal and a satellite communication module, wherein the satellite is communicated with the reference station and the positioning terminal in the satellite north-seeking bucket positioning system, and sends positioning signals to the reference station and the positioning terminal;
the reference station receives a positioning signal of a positioning satellite to calculate to obtain self-positioning information, calculates with self-surveying and mapping position coordinates to obtain differential data, and sends the differential data to a positioning terminal through a 4G private base station for positioning correction;
the positioning terminal is placed beside the intelligent skate and is bound with the intelligent skate for use, the positioning terminal receives positioning signals of a positioning satellite to determine self-positioning information, and high-precision positioning information is provided for the intelligent skate on the basis of a differential data correction method; the positioning terminal fuses recognition results of the precision weight statistical method and the variance Gaussian filtering method, and the final track recognition result is obtained through comprehensive judgment, so that the track is accurately recognized; the positioning terminal sends the positioning result to the monitoring upper computer through the 4G private base station;
the 4G private base station receives the reference station differential data and forwards the reference station differential data to the positioning terminal on one hand, and receives positioning data corrected by the positioning terminal on the other hand; on the other hand, the 4G private base station interacts with the monitoring upper computer through the wired Ethernet interface, and transmits the received positioning data corrected by the positioning terminal to the upper computer.
2. The system of claim 1, wherein the differential data modification method comprises: and correcting the current self-position observation value determined by the positioning terminal based on the differential data obtained from the reference station, namely adding the current self-position observation value and the differential data to obtain the high-precision positioning data corrected by the positioning terminal.
3. An intelligent skate track identification method based on information fusion, which is based on the system of any one of claims 1-2, and is characterized in that the intelligent skate track identification method comprises the following steps: the method comprises four steps of system initialization, terminal and skate identification matching, terminal positioning identification track and monitoring the update state of an upper computer, and the specific flow is as follows:
step 1: system initialization
The system initialization comprises the initialization of a Beidou positioning module in a positioning terminal and the initialization of station track information of a train station, wherein the latter comprises the geographical information of a track central line and the number k of station tracks obtained according to station track geographical mapping information, and the number i of groups of positioning data collected before and after the time of initial identification is 5;
step 2: terminal and skate recognition matching
Performing anti-slip operation by railway station staff, performing RFID (radio frequency identification) radio frequency identification on the intelligent iron shoe by using a positioning terminal after the intelligent iron shoe is placed, and matching the intelligent iron shoe with the positioning terminal;
and step 3: positioning terminal positioning and identifying track
After the positioning terminal is successfully matched with the intelligent iron shoe, high-precision positioning data of i seconds are respectively taken before and after the RFID matching time is taken as a reference time to form a data sequence with the length of 2 x i +1, the identification system utilizes the group of positioning data to sequentially carry out track identification by a precision weight statistical method and track identification by a variance Gaussian filter method, and track identification results are determined and output if the two identification results are consistent; if the identification results are inconsistent, the number i of the positioning data acquisition groups is made to be i +5, the step 3 is repeated, and after 3 times of circulation, the identification results of the two methods are still inconsistent, the two identification results are subjected to fusion judgment by using a DS evidence reasoning algorithm, and the information fusion judgment result is used as a final identification result;
and 4, step 4: monitoring update state of upper computer
After the identification of the iron shoe track is successful, the monitoring upper computer detects whether a car is in the track, if the monitoring upper computer displays that the car is in the track, the iron shoe is on line normally, and the monitoring upper computer updates the states of the train and the iron shoe in the track; and if the situation that the station track has no cars is displayed, whether the iron shoes are placed in place or not is confirmed again, and whether the upper computer needs to supplement and record car number information or replace the iron shoes is judged.
4. The method as claimed in claim 3, wherein the positioning terminal and the skate matching identification in the step 2 comprises the following specific steps:
2-1), the field operator firstly takes the intelligent iron shoe and the positioning terminal out of the anti-slip appliance box, transfers the intelligent iron shoe to an anti-slip operation place, and places the intelligent iron shoe on a preset rail;
2-2), matching and binding the positioning terminal with the intelligent skate through RFID radio frequency identification;
2-3), judging whether the positioning terminal is successfully matched with the iron shoe: if the matching is not successful, executing the step 2-2); and if the matching is successful, entering the step 3.
5. The method as claimed in claim 3, wherein the step 3 of locating the identified track by the locating terminal comprises the following steps:
3-1), after the positioning terminal is successfully matched with the iron shoe, placing the positioning terminal beside the iron shoe, taking the RFID time of the terminal and the iron shoe as a reference time, respectively taking i groups of high-precision positioning data in front and at back to form a positioning data sequence with the length of 2 x i +1, and executing the step 3-2);
3-2) identifying the track by using an accuracy weight statistical method: respectively identifying the tracks of the 2 x i +1 groups of positioning data, distributing the precision weights of the positioning data to the identified tracks, finally counting the precision weights of all the tracks, taking the track with the highest precision weight statistic value as a track identification result, and executing the step 3-3 after obtaining the track identification result;
3-3) identifying the tracks by using a variance-variable Gaussian filtering method: performing variance-variable Gaussian filtering calculation on the 2 x i +1 groups of positioning data to obtain coordinates (x ', y') after variance-variable Gaussian filtering, calculating the vertical distance between the coordinates after variance-variable Gaussian filtering and the central line of each track, wherein the track closest to the coordinates is a track identification result, and executing the step 3-4 after obtaining the track identification result;
3-4), judging whether the track identification results of the two methods are consistent: if the results are consistent, uploading the track identification result, and entering the step 4; if the results are not consistent, executing the step 3-5);
3-5), making i equal to i +5, expanding the range of the acquisition time of the positioning data, and judging whether i is less than or equal to 15; if i is less than or equal to 15, executing the step 3-1); if i >15, performing step 3-6);
3-6) respectively calculating the credibility of the two methods to different recognition results by adopting a recognition result fusion judgment method based on different recognition methods, carrying out fusion calculation to judge the track recognition result by utilizing a DS evidence reasoning algorithm, taking the fusion judgment result as a final result and uploading the final result, and entering the step 4.
6. The method as claimed in claim 5, wherein the step 3-2) of using accuracy weighted statistics for track identification comprises the following steps:
3-2-1), use the moment of punching the card as the benchmark, respectively take i group's locating data around, obtain a length and be 2 i + 1's locating data sequence, to 2 i +1 group's locating data according to the precision distribution weight, the weight distribution specifically sees the following table:
Wherein deltajPositioning data accuracy, omega, for the jth positioning datajThe accuracy weight of the jth positioning data; let j equal 1, G1＝G2＝…＝Gk＝0，G1、G2…GkRespectively obtaining the precision weight statistics of k tracks, and executing the step 3-2-2);
3-2-2), fetching j group positioning data (x) in positioning data sequencej,yj) Calculating the anchor point (x)j,yj) Perpendicular distance L from the center line of each track1…LkExecuting step 3-2-3);
3-2-3), determining L1…LkMinimum and mean value Lm，m∈[1,k]I.e. the location point has the minimum distance from the track m and the accuracy weight of the location data is omegajThe extract is prepared byThe degree weight is counted on the corresponding track weight, and G is orderedm＝Gm+ωjJ ═ j +1, perform steps 3-2-4);
3-2-4), judging whether j is less than or equal to 2 x i + 1: if j is less than or equal to 2 x i +1, executing the step 3-2-2); if j >2 x i +1, performing steps 3-2-5);
3-2-5), determination of G1、G2…GkMiddle maximum is GN，N∈[1,k]And the track identification result of the precision weight statistical method is track N, and the process is finished.
7. The method as claimed in claim 5, wherein the step 3-3) of using the variance-varying Gaussian filter method for identifying the tracks comprises the following steps:
3-3-1), taking the time of swiping card as a reference, and respectively taking i groups of positioning data in front and at back to obtain a positioning data sequence P with the length of (2 x i +1)1(x1,y1)、P2(x2,y2)、…、P2i+1(x, y), each group of data in the sequence is endowed with a Gaussian weight value, and the coordinate data after the variance Gaussian filtering is (x ', y'), wherein the calculation modes of x 'and y' are as follows:
wherein x isj、yjAnd sigma respectively correspond to the x coordinate, the y coordinate and the Gaussian distribution standard deviation of the j-th group of positioning data. For positioning data sequences with different lengths, different sigma values are selected, weight distribution is changed, when i is gradually increased and the length of the positioning data sequences is enlarged, the sigma value is reduced to improve the weight of the positioning data near the reference time, the weight of the positioning data at the edge time is reduced, and when i is 5, the sigma is 10; when i is 10, taking sigma as 4.5; when i is 15, taking sigma as 4;
performing variance Gaussian filtering on all positioning data in the sequence to obtain coordinates (x ', y'), and executing the step 3-3-2);
3-3-2), calculating the vertical distance L between the coordinate point (x ', y') and the central line of each track1…LkThen, executing the step 3-3-3);
3-3-3), determining L1…LkThe minimum value is LM，M∈[1,k]And the track identification result is the track M,
and (6) ending.
8. The method as claimed in claims 6 and 7, wherein the algorithm for calculating the vertical distance between the locating coordinate point and the centerline of each track is specifically:
(1) according to the track geographic mapping data of the train station yard, determining the geographic position of the center line of the track, and determining the coordinates of two end points of the center line of the track to be A (X)1,Y1)，B(X2,Y2)；
(2) And (3) coordinates P (X, Y) of the positioning point, wherein the vertical distance between the positioning point P and the central line of the femoral track is as follows:
9. the method as claimed in claim 5, wherein the method for fusion judgment of recognition results based on two track recognition methods in step 3-6) respectively performs track recognition by using a precision weight statistical method and a variance gaussian filtering method, and performs fusion calculation to judge the track recognition result when the track recognition results are inconsistent, wherein the specific fusion judgment process is as follows:
recording the identification result of the precision weight statistical method as p and the identification result of the variance Gaussian filtering method as q; p, q belongs to [1, k ] and p is not equal to q, namely the two identification methods have different identification results;
the credibility of the accuracy weight statistical method for the track identification results p and q is respectively as follows:
wherein the content of the first and second substances,
is the sum of the precision weight statistics, G, of all tracksp，GqRespectively obtaining precision weight statistics values of a p track and a q track;
the credibility of the variance-variable Gaussian filtering method for the station track identification result p and q is respectively as follows:
calculating the credibility m (p) of the matching track p and the credibility m (q) of the matching track q based on the recognition results of the two track recognition methods in a fusion manner, wherein:
comparing m (p) with m (q), if m (p) > m (q), judging that the fusion is matched with the track p; if m (p) < m (q), the fusion is judged to be matched with the track q; if m (p) ═ m (q), the possibility of matching the track p and the track q is prompted.
10. The method as claimed in claim 3, wherein the step 4 of monitoring the update state of the upper computer comprises the following specific steps:
4-1), whether this track of host computer has the car according to intelligence skate track of the track recognition result monitoring: if the upper computer shows that the station track has no vehicles, executing the step 4-2); if the upper computer displays that the station track has the car, executing the step 4-4);
4-2), detecting whether the iron shoe is placed in place: the iron shoe in place includes two conditions: 1. determining that the iron shoe is in the rail by a metal detector on the iron shoe; 2. detecting the distance between the iron shoe and the wheel by a sound wave distance measuring probe on the iron shoe, and determining that the iron shoe is placed in the anti-slip range; when the iron shoes are in the rail and in the anti-skid range and the iron shoes are placed in place, executing the step 4-3); if any condition is not met, the iron shoes are not placed in place, the iron shoes need to be placed again, and the step 2 is executed;
4-3), if the skate is placed in place, the upper computer does not timely input the train number information, and the step 4-4 is executed after the train number information is additionally recorded;
4-4), the normal online of the iron shoes, the monitoring upper computer updates the states of the trains and the intelligent iron shoes on the track, and the process is finished.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110821256.9A CN113581244B (en) | 2021-07-20 | 2021-07-20 | Intelligent skate track recognition system and method based on information fusion |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110821256.9A CN113581244B (en) | 2021-07-20 | 2021-07-20 | Intelligent skate track recognition system and method based on information fusion |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113581244A true CN113581244A (en) | 2021-11-02 |
| CN113581244B CN113581244B (en) | 2024-04-26 |
Family
ID=78248540
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110821256.9A Active CN113581244B (en) | 2021-07-20 | 2021-07-20 | Intelligent skate track recognition system and method based on information fusion |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113581244B (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104765814A (en) * | 2015-04-03 | 2015-07-08 | 中铁第四勘察设计院集团有限公司 | Multi-time-scale coexisting type management method for railway yard plan station tracks |
| CN105398474A (en) * | 2015-12-16 | 2016-03-16 | 郑州北斗七星通讯科技有限公司 | Beidou technology based intelligent real-time monitoring visualization management system for railway anti-slip iron brake shoe |
| CN205220706U (en) * | 2015-12-16 | 2016-05-11 | 郑州北斗七星通讯科技有限公司 | Visual management system of swift current skate real time monitoring is prevented to big dipper intelligence railway |
| US20170109644A1 (en) * | 2015-10-19 | 2017-04-20 | Ford Global Technologies, Llc | Probabilistic Inference Using Weighted-Integrals-And-Sums-By-Hashing For Object Tracking |
| CN108001477A (en) * | 2018-01-03 | 2018-05-08 | 伊军庆 | A kind of skate remote monitoring and management system and its method |
| CN109552365A (en) * | 2019-01-15 | 2019-04-02 | 兰州运通铁路科技有限责任公司 | A kind of anti-slip remote monitoring system of rolling stock |
| CN110406565A (en) * | 2019-08-01 | 2019-11-05 | 南京富岛信息工程有限公司 | The positioning and rectifying of Intelligent iron shoe and stolen determination method and device |
| CN111003026A (en) * | 2019-12-30 | 2020-04-14 | 中国铁道科学研究院集团有限公司通信信号研究所 | In-station vehicle protection method based on intelligent iron shoes and STP |
| CN111055877A (en) * | 2019-12-24 | 2020-04-24 | 南京富岛信息工程有限公司 | Wide-temperature-range intelligent iron shoe and anti-slip state judgment method thereof |
| CN210573918U (en) * | 2019-10-30 | 2020-05-19 | 中国神华能源股份有限公司神朔铁路分公司 | Railway anti-running management system |
| US20200405223A1 (en) * | 2015-07-17 | 2020-12-31 | Chao-Lun Mai | Method, apparatus, and system for automatic and adaptive wireless monitoring and tracking |
| WO2021063136A1 (en) * | 2019-09-30 | 2021-04-08 | 江苏大学 | Data-driven high-precision integrated navigation data fusion method |
| CN112793616A (en) * | 2021-02-08 | 2021-05-14 | 南京富岛信息工程有限公司 | Novel intelligent skate and in-place distance acquisition method thereof |
-
2021
- 2021-07-20 CN CN202110821256.9A patent/CN113581244B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104765814A (en) * | 2015-04-03 | 2015-07-08 | 中铁第四勘察设计院集团有限公司 | Multi-time-scale coexisting type management method for railway yard plan station tracks |
| US20200405223A1 (en) * | 2015-07-17 | 2020-12-31 | Chao-Lun Mai | Method, apparatus, and system for automatic and adaptive wireless monitoring and tracking |
| US20170109644A1 (en) * | 2015-10-19 | 2017-04-20 | Ford Global Technologies, Llc | Probabilistic Inference Using Weighted-Integrals-And-Sums-By-Hashing For Object Tracking |
| CN105398474A (en) * | 2015-12-16 | 2016-03-16 | 郑州北斗七星通讯科技有限公司 | Beidou technology based intelligent real-time monitoring visualization management system for railway anti-slip iron brake shoe |
| CN205220706U (en) * | 2015-12-16 | 2016-05-11 | 郑州北斗七星通讯科技有限公司 | Visual management system of swift current skate real time monitoring is prevented to big dipper intelligence railway |
| CN108001477A (en) * | 2018-01-03 | 2018-05-08 | 伊军庆 | A kind of skate remote monitoring and management system and its method |
| CN109552365A (en) * | 2019-01-15 | 2019-04-02 | 兰州运通铁路科技有限责任公司 | A kind of anti-slip remote monitoring system of rolling stock |
| CN110406565A (en) * | 2019-08-01 | 2019-11-05 | 南京富岛信息工程有限公司 | The positioning and rectifying of Intelligent iron shoe and stolen determination method and device |
| WO2021063136A1 (en) * | 2019-09-30 | 2021-04-08 | 江苏大学 | Data-driven high-precision integrated navigation data fusion method |
| CN210573918U (en) * | 2019-10-30 | 2020-05-19 | 中国神华能源股份有限公司神朔铁路分公司 | Railway anti-running management system |
| CN111055877A (en) * | 2019-12-24 | 2020-04-24 | 南京富岛信息工程有限公司 | Wide-temperature-range intelligent iron shoe and anti-slip state judgment method thereof |
| CN111003026A (en) * | 2019-12-30 | 2020-04-14 | 中国铁道科学研究院集团有限公司通信信号研究所 | In-station vehicle protection method based on intelligent iron shoes and STP |
| CN112793616A (en) * | 2021-02-08 | 2021-05-14 | 南京富岛信息工程有限公司 | Novel intelligent skate and in-place distance acquisition method thereof |
Non-Patent Citations (3)
| Title |
|---|
| 刘鑫鹏: "车辆防溜铁鞋智能管理系统的研究和设计", 中国优秀硕士学位论文全文数据库, 15 January 2019 (2019-01-15), pages 11 - 12 * |
| 叶彦斐: "智能铁鞋定位纠偏及被盗判定的设计与实现", 工业控制计算机, vol. 54, 31 December 2020 (2020-12-31), pages 54 - 55 * |
| 叶彦斐;黄家辉;胡文杰;徐涛;陈天石;: "智能铁鞋定位纠偏及被盗判定的设计与实现", 工业控制计算机, no. 01, 25 January 2020 (2020-01-25), pages 57 - 58 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113581244B (en) | 2024-04-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105741546B (en) | The intelligent vehicle Target Tracking System and method that roadside device is merged with vehicle sensor | |
| CN109215347B (en) | Traffic data quality control method based on crowdsourcing trajectory data | |
| CN105809126B (en) | The intelligent vehicle Target Tracking System and method that DSRC is merged with onboard sensor | |
| JPH05196718A (en) | Moving-body positioning system having emphasized position determining and processing means | |
| CN110406565B (en) | Method and device for positioning, correcting and judging theft of intelligent iron shoe | |
| CN105241465B (en) | A kind of method of road renewal | |
| CN108454652A (en) | A kind of method, apparatus and system of safe and reliable real time speed measuring and consecutive tracking | |
| CN102088769B (en) | Wireless location method for directly estimating and eliminating non-line-of-sight (NLOS) error | |
| JP4669971B2 (en) | How to detect the use of at least one toll road part | |
| CN103379619A (en) | Method and system for positioning | |
| CN111224710B (en) | Virtual transponder capturing method and system based on satellite space distribution inspection | |
| CN104760607A (en) | Train track occupation detection method and device based on satellite positioning | |
| CN105116391A (en) | Marine radar error calibration-oriented valid target sequence set combined analysis method | |
| CN110736999A (en) | Railway turnout detection method based on laser radar | |
| CN106922176A (en) | Lane detection | |
| CN115795332A (en) | User travel mode identification method | |
| CN103678925A (en) | Flight path classification method based on auxiliary information source | |
| CN113353124B (en) | Intelligent iron shoe track identification system and method | |
| CN113581244A (en) | Intelligent iron shoe track identification system and method based on information fusion | |
| CN110203254A (en) | The safety detection method of Kalman filter in train positioning system | |
| CN105022358B (en) | Railway large-scale maintenance machinery self-con-tained unit and method and corresponding vehicle based on GPS | |
| CN113324560A (en) | Method, system and computer readable medium for obtaining vehicle mileage | |
| CN110081890B (en) | Dynamic k nearest neighbor map matching method combined with deep network | |
| CN110647877B (en) | Three-dimensional traffic facility positioning and deviation rectifying method and device based on neural network | |
| CN112085034A (en) | Rail transit train positioning method and system based on machine vision |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |