A parking control method, control device and system for urban rail train

Abstract

The present application relates to the field of urban rail train control technology, and specifically to a parking control method, control device and system for an urban rail train, the control method comprising: determining the speed consistency coefficient of each carriage at the current moment based on the difference in speed data between each carriage and all other carriages at the current moment, and the difference in all historical speed data of each carriage between the current moment and its adjacent previous acquisition moment, and determining the data reliability coefficient of each carriage at the current moment in combination with the speed accuracy coefficient and the speed regularity coefficient, and performing parking control on the urban rail train in combination with the speed data of all carriages at the current moment and the actual position of the urban rail train. The present application comprehensively analyzes the differences in speed data in different carriages and at different times to improve the accuracy of parking control of urban rail trains.

Description

Technical Field

[0001] The present application relates to the technical field of urban rail train control, and in particular to a parking control method, control device and system for an urban rail train. Background Art

[0002] With the development of urban rail trains, urban rail transit train control gradually adopts ATO (Automatic tarin operation) to realize automatic driving of urban rail trains. The ATO system mainly relies on data acquisition equipment such as transponders and sensors in the track to obtain relevant data of urban rail trains. According to the distance, speed, acceleration, line information and speed curve generated by the system from the urban rail train to the parking point, the traction and braking force of the urban rail train are continuously adjusted to output the appropriate operating speed and realize automatic parking of the urban rail train.

[0003] However, in the actual operation of urban rail trains, due to the influence of the environment and equipment, the collected urban rail train speed may have certain errors (for example, vibration and noise may affect the measurement data during the high-speed operation of the urban rail train, or measurement errors may be generated during the installation and application of the speed sensor), which in turn causes the braking force applied to the urban rail train to be inconsistent with the target value, resulting in the final braking distance of the urban rail train being inconsistent with the distance the urban rail train should have traveled, reducing the accuracy of the automatic parking of the urban rail train. Summary of the invention

[0004] In a first aspect, an embodiment of the present application provides a parking control method for an urban rail train, the control method comprising the following steps: in each urban rail train, obtaining speed data of each carriage at the current time of each day and the actual position of the urban rail train, as well as speed data of each carriage at all collected times within a preset time period before the current time, and using the data as historical speed data of each carriage at the current time;

[0005] Based on the average distribution level of the similarity of the historical speed data between each carriage and all other carriages at the current moment, and the difference between the discrete degree of all elements in the first-order difference sequence of all historical speed data of each carriage and the discrete degree of all elements in the first-order difference sequence of all historical speed data of the other carriages, the speed normal coefficient of each carriage at the current moment is determined;

[0006] A mutation point detection algorithm is used to obtain mutation speed data from all historical speed data of each carriage at the current moment, and the average distribution of the differences in the acquisition time of all speed mutation data between each carriage and all other carriages, as well as the average distribution of the differences in mutation speed data, are analyzed to determine the interval smoothing coefficient of each carriage at the current moment, and the speed accuracy coefficient of each carriage at the current moment is determined in combination with the speed normal coefficient;

[0007] Based on the difference in speed data of each carriage between the current time and the same time of the previous day, and the difference in the change trend of all historical speed data, the speed regularity coefficient of each carriage at the current time is determined;

[0008] Based on the difference in speed data between each carriage and all other carriages at the current moment, and the difference in all historical speed data of each carriage between the current moment and its adjacent previous collection moment, the speed consistency coefficient of each carriage at the current moment is determined, and the data reliability coefficient of each carriage at the current moment is determined in combination with the speed accuracy coefficient and the speed regularity coefficient;

[0009] Based on the data reliability coefficient and in combination with the speed data of all carriages and the actual position of the urban rail train at the current moment, the urban rail train is controlled to stop.

[0010] Preferably, the method for determining the normal speed coefficient of each carriage at the current moment is:

[0011] In each urban rail train, the similarity of all historical speed data between each carriage and the other carriages at the current moment is analyzed, and the average level of the similarity between each carriage and all the other carriages is used as the speed similarity of each carriage at the current moment;

[0012] Analyze the discreteness of all elements in the first-order difference sequence of all historical speed data of each carriage at the current moment, and take the accumulated result of the difference between the discreteness of each carriage and the discreteness of all other carriages as the speed difference coefficient of each carriage at the current moment;

[0013] The normal coefficient of the speed of each carriage at the current moment is the ratio of the speed similarity of each carriage at the current moment to the speed difference coefficient.

[0014] Preferably, the method for determining the interval smoothing coefficient of each carriage at the current moment is:

[0015] Analyze the differences in the collection time corresponding to all the sudden speed data between each carriage and the other carriages at the current moment, and take the average of the differences in the collection time between each carriage and all the other carriages as the time difference coefficient of each carriage at the current moment;

[0016] Analyze the differences of all mutation speed data between each carriage and the other carriages at the current moment, and take the average of the differences of the mutation speed data between each carriage and all the other carriages as the mutation difference coefficient of each carriage at the current moment;

[0017] The interval smoothness coefficient of each carriage at the current moment is the reciprocal of the sum of the time difference coefficient and the mutation difference coefficient of each carriage at the current moment.

[0018] Preferably, the expression of the speed accuracy coefficient of each carriage at the current moment is: ; Indicates the speed accuracy coefficient of car j at the current moment; Indicates the normal coefficient of the speed of carriage j at the current moment; Indicates the interval smoothness coefficient of car j at the current moment.

[0019] Preferably, the method for determining the speed regularity coefficient of each carriage at the time of the day is:

[0020] Analyze the difference in speed data of each carriage between the current time and the same time of the previous day as the speed difference of each carriage at the current time;

[0021] All historical speed data of each carriage at the current moment are used as the input of the trend detection algorithm, and the trend strength is output. The difference in the trend strength of each carriage between the current moment and the same moment of the previous day is analyzed as the trend difference of each carriage at the current moment;

[0022] The speed regularity coefficient of car j at the current moment The expression is: ; In the formula, represents the speed difference of car j at the current moment; represents the trend difference of car j at the current moment; Indicates a preset constant greater than 0.

[0023] Preferably, the method for determining the speed consistency coefficient of each carriage at the current moment is:

[0024] Calculate the average of the speed data differences between each carriage and all other carriages at the current moment as the speed difference between each carriage at the current moment;

[0025] Calculate the absolute value of the sum of the differences of all speed data of each carriage between the current moment and the previous acquisition moment, as the consistency index of each carriage at the current moment;

[0026] The speed consistency coefficient of each carriage at the current moment is the ratio of the consistency index of each carriage at the current moment to the speed difference between the carriages.

[0027] Preferably, the expression of the data reliability coefficient of each carriage at the current moment is: ; In the formula, represents the data reliability coefficient of car j at the current moment; represents the speed regularity coefficient of car j at the current moment; It represents the speed consistency coefficient of car j at the current moment.

[0028] Preferably, the stopping control of the urban rail train includes:

[0029] The data reliability coefficient of all carriages at the current moment is used as the input of the threshold segmentation algorithm, and the segmentation threshold is output. The speed data greater than or equal to the segmentation threshold is averaged among the speed data of all carriages at the current moment as the actual speed data of the urban rail train at the current moment;

[0030] The distance between the preset ideal parking position and the actual position of the urban rail train at the current moment, as well as the difference between 0 and the actual speed data of the urban rail train at the current moment are used as the input of the PID controller, and the output control signal controls the urban rail train to stop.

[0031] In a second aspect, an embodiment of the present application further provides a parking control device for an urban rail train, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of a parking control method for an urban rail train described in any one of the above items are implemented.

[0032] In a third aspect, an embodiment of the present application provides a parking control system for an urban rail train, the control system comprising:

[0033] The speed data collection module is used to obtain the speed data of each carriage at the current time of each day and the actual position of the urban rail train, as well as the speed data of each carriage at all collection times within a preset time before the current time in each urban rail train, and use it as the historical speed data of each carriage at the current time;

[0034] The speed weight acquisition module is used to determine the normal speed coefficient of each carriage at the current moment based on the similarity of all historical speed data between each carriage and the other carriages at the current moment, and the discrete degree of all elements in the first-order difference sequence of all historical speed data of each carriage;

[0035] Based on the difference in the mutation of all historical speed data between each carriage at the current moment and the rest of the carriages, determine the interval smoothness coefficient of each carriage at the current moment, and determine the speed accuracy coefficient of each carriage at the current moment in combination with the speed normality coefficient;

[0036] Based on the difference in speed data of each carriage between the current time and the same time of the previous day, and the difference in the change trend of all historical speed data, the speed regularity coefficient of each carriage at the current time is determined;

[0037] Based on the difference in speed data between each carriage and all other carriages at the current moment, and the difference in all historical speed data of each carriage between the current moment and its adjacent previous collection moment, the speed consistency coefficient of each carriage at the current moment is determined, and the data reliability coefficient of each carriage at the current moment is determined in combination with the speed accuracy coefficient and the speed regularity coefficient;

[0038] The parking control module is used to control the parking of the urban rail train based on the data reliability coefficient and in combination with the speed data of all carriages and the actual position of the urban rail train at the current moment.

[0039] It can be seen from the above embodiments that the parking control method for urban rail trains provided in the embodiments of the present application has at least the following beneficial effects:

[0040] The present application determines the normal speed coefficient of each carriage at the current moment by analyzing the similarity of all historical speed data between each carriage and the other carriages at the current moment, as well as the discreteness of all elements in the first-order difference sequence of all historical speed data of each carriage. The beneficial effect is that the influence of environmental vibration and noise on the measurement accuracy of the speed sensor can be eliminated, and the authenticity and accuracy of the collected urban rail train speed data can be ensured, thereby improving the accuracy and safety of parking control;

[0041] The present application determines the interval smoothing coefficient of each carriage at the current moment based on the difference in the mutation of all historical speed data between each carriage and the other carriages at the current moment, and determines the speed accuracy coefficient of each carriage at the current moment in combination with the speed normal coefficient. The beneficial effect is that the normal speed coefficient and the interval smoothing coefficient are comprehensively considered to more comprehensively evaluate the accuracy and reliability of the speed data, distinguish the speed change during normal operation and the abnormal data caused by the speed sensor measurement force error, thereby improving the accuracy and safety of parking control;

[0042] The present application determines the speed regularity coefficient of each carriage at the current moment based on the difference in speed data of each carriage between the same time of each day and the previous day, and the difference in the change trend of all historical speed data. The beneficial effect is that it can ensure that the urban rail train can accurately adjust the speed and brake when encountering resistance, avoid inaccurate parking due to data errors, and improve the accuracy and safety of parking control;

[0043] Based on the difference in speed data between each car and all other cars at the current moment, and the difference in all historical speed data of each car between the current moment and its adjacent previous collection moment, the speed consistency coefficient of each car at the current moment is determined, and combined with the speed accuracy coefficient and the speed regularity coefficient, the data reliability coefficient of each car at the current moment is determined. Based on the data reliability coefficient and combined with the speed data of all cars at the current moment and the actual position of the urban rail train, the urban rail train is stopped. The beneficial effect is that the speed consistency coefficient, the speed accuracy coefficient and the speed regularity coefficient are comprehensively considered, so that the reliability and accuracy of the speed data can be more comprehensively evaluated, and the accuracy of the urban rail train stop control can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0045] Figure 1 A flowchart of a parking control method for an urban rail train provided in one embodiment of the present application;

[0046] Figure 2 A schematic diagram of a data reliability coefficient extraction process provided by an embodiment of the present application;

[0047] Figure 3 A block diagram of a parking control system for an urban rail train provided in accordance with an embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to further explain the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following is a detailed description of the parking control method, control device and system of a city rail train proposed in the present application, its specific implementation method, structure, features and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0049] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

[0050] The following is a detailed description of a parking control method, control device and system for an urban rail train provided by the present application in conjunction with the accompanying drawings.

[0051] See also Figure 1 , which shows a flowchart of a parking control method for a city rail train provided by an embodiment of the present application, the control method comprises the following steps:

[0052] Step S1: In each urban rail train, obtain the speed data of each carriage at the current time of each day and the actual position of the urban rail train, as well as the speed data of each carriage at all collected times within a preset time period before the current time, and use it as the historical speed data of each carriage at the current time.

[0053] Speed ​​sensors are installed on all carriages of each urban rail train. From the start of the operation of the urban rail train to the stop of the operation every day, for each urban rail train, the speed data of all collected times of each carriage within a preset time length t before the current time and the speed data of each carriage at the current time are obtained, wherein the data sampling interval is set to T, and the speed data of all collected times of each carriage within the preset time length before the current time are used as the historical speed data of each carriage at the current time; the actual position of the urban rail train at the current time is obtained in the ATO system of the urban rail train.

[0054] It should be noted that the values ​​of the preset time length t and the data sampling interval T are both manually set. In this embodiment, the value of the preset time length t is 5 minutes, and the value of the data sampling interval T is 0.5 seconds. The implementer can also set them according to the specific situation. This embodiment does not impose any special restrictions.

[0055] Step S2: Based on the similarity of all historical speed data between each car and the other cars at the current moment, and the discreteness of all elements in the first-order difference sequence of all historical speed data of each car, determine the normal speed coefficient of each car at the current moment.

[0056] When parking control is required during the high-speed running of a rail train, it is usually necessary to frequently determine the speed of the rail train and adjust the parking brake force of the rail train according to the actual situation. When the rail train starts to brake, the rail train pipe starts to reduce pressure and exhaust air, the pressure of the rail train brake cylinder increases, the braking force at the front of the rail train will be greater than that at the rear, and the rear car pushes forward. As the braking progresses, the pressure of the brake cylinder of the rail train head increases to the maximum, and then the braking force of each car slowly increases to the same level until the rail train stops. In this process, the speed of the rail train head begins to decrease continuously, and the speed of the rail train in the other cars follows closely. After a period of time, the speed decrease rate tends to be the same until the speed is 0.

[0057] In the speed data of the urban rail train, it is mainly manifested that the speed data of the urban rail train head begins to decrease, and the other carriages also begin to descend after a short time interval. The descent speed of the urban rail train head is faster, and the descent speed of the other carriages is relatively slow, and the descent speed gradually increases, and the descent speed is the same after a period of time. The overall decline trend is relatively similar, and the decline range is similar. When the speed measurement is inaccurate (such as the urban rail train will generate environmental vibration and noise during high-speed driving, which will affect the measurement accuracy of the speed sensor), the collected speed data of the urban rail train may change irregularly, with a faster change speed and a shorter duration, showing a sudden change trend in the speed data of the urban rail train, which will cause a large change in the speed decline trend of a certain carriage, increase volatility, and there will be large differences in the degree of decline in the short term.

[0058] Therefore, based on the similarity of all historical speed data between each carriage and the other carriages at the current moment, and the discreteness of all elements in the first-order difference sequence of all historical speed data of each carriage, the normal speed coefficient of each carriage at the current moment is determined to eliminate the influence of environmental vibration and noise generated by the urban rail train during high-speed driving on the measurement accuracy of the speed sensor, specifically:

[0059] (1) In each urban rail train, the similarity of all historical speed data between each carriage and the other carriages at the current moment is analyzed, and the average level of the similarity between each carriage and all the other carriages is taken as the speed similarity of each carriage at the current moment;

[0060] It should be noted that there are many methods for measuring the similarity between data groups. In this embodiment, the cosine similarity of all historical speed data between each car and the other cars at the current moment is calculated to measure the similarity of the speeds between different cars in the same urban rail train. The implementer may also use other methods for measuring the similarity between data groups, such as the inverse of the Euclidean distance. This embodiment does not impose any special restrictions on the selection of methods for measuring the similarity between data groups.

[0061] The calculation process of cosine similarity is a well-known technology, and its specific calculation steps are not repeated here.

[0062] In addition, it should be understood that there are many ways to measure the average level of a set of data. In this embodiment, the average level of the similarities between each car and all other cars is measured by calculating the mean of the similarities between each car and all other cars. The implementer may also use other methods such as the geometric mean. This embodiment does not impose any special restrictions on the selection of the method for measuring the average level of data.

[0063] (2) Further, the discreteness of all elements in the first-order difference sequence of all historical speed data of each car at the current moment is analyzed, and the cumulative result of the difference between the discreteness of each car and the discreteness of all other cars is taken as the speed difference coefficient of each car at the current moment;

[0064] It should be noted that there are many methods for measuring the degree of discreteness of a set of data. In this embodiment, the degree of discreteness of all elements in the first-order difference sequence of all historical speed data of each car is measured by calculating the variance of all elements in the first-order difference sequence. The implementer may also use other methods for measuring the degree of discreteness of data, such as dispersion coefficient or standard deviation. This embodiment does not impose any special restrictions on the selection of methods for measuring the degree of discreteness of a set of data.

[0065] In addition, it should be understood that there are many ways to measure the differences between data. In this embodiment, the difference in the degree of discreteness between different carriages is measured by calculating the absolute value of the difference between the degree of discreteness of each carriage and the degree of discreteness of all other carriages. The implementer may also use other methods of measuring the differences, such as ratios. This embodiment does not impose any special restrictions on the selection of methods for measuring the differences.

[0066] Among them, the method for obtaining the first-order difference sequence is a well-known technology, and its specific acquisition process will not be described in detail in this embodiment.

[0067] (3) Further, based on the speed similarity and the speed difference coefficient, a normal speed coefficient of each carriage at the current moment is determined, where the normal speed coefficient of each carriage at the current moment is the ratio of the speed similarity of each carriage at the current moment to the speed difference coefficient.

[0068] Further, according to the normal speed coefficient of each carriage in each urban rail train at the current moment, it can be understood that if the speed data collected by the current carriage at the current moment is normal and accurate data, the greater the mean of the similarity between the historical speed data of the urban rail train and the historical speed data of the urban rail trains in other carriages, that is, the greater the speed similarity, and the smaller the speed data change gap, the smaller the difference between the discrete degree of the current carriage and the discrete degree of all other carriages, that is, the smaller the speed difference coefficient, the greater the speed normal coefficient, indicating that the possibility of speed measurement error in the urban rail train speed data collected at the current moment is lower, and the speed data is more normal;

[0069] On the contrary, if the speed data collected by the current car at the current moment is abnormal, the smaller the mean of the similarity between the historical speed data of the urban rail train and the historical speed data of the urban rail trains in other cars, that is, the smaller the speed similarity, and the greater the difference in speed data change, the greater the difference between the discrete degree of the current car and the discrete degree of all other cars, that is, the larger the speed difference coefficient, the smaller the speed normal coefficient, indicating that the possibility of speed measurement error in the urban rail train speed data collected at the current moment is higher.

[0070] Step S3: Based on the difference in the mutation of all historical speed data between each car and the other cars at the current moment, determine the interval smoothness coefficient of each car at the current moment, and determine the speed accuracy coefficient of each car at the current moment in combination with the speed normal coefficient.

[0071] After the urban rail train has been braking for a period of time, the descending speed of all carriages tends to be consistent, and the speed data of the urban rail train gradually tends to be the same. In this process, due to the difference in the initial braking force of each carriage (for example, the braking force of the head carriage of the urban rail train is larger at the beginning of braking, and its speed begins to decrease first, while the other carriages gradually decrease), there is a certain time interval between the start of the speed data change of each carriage. Specifically, the overall trend of the speed data of the urban rail train is similar, but the starting time of the speed data change is different, and there is a similar interval between the starting times. When the speed measurement of the carriage is inaccurate, it may cause the starting time of the speed change of a certain carriage to change, and due to the randomness of the measurement error, when the error occurs, the speed data of the urban rail train measured in the current carriage is different from the speed data of the other carriages.

[0072] Therefore, based on the difference in the mutation of all historical speed data between each carriage and the other carriages at the current moment, the interval smoothness coefficient of each carriage at the current moment is determined, and combined with the speed normality coefficient, the speed accuracy coefficient of each carriage at the current moment is determined to determine whether there is abnormal data in the speed data caused by the speed sensor measurement error, specifically:

[0073] (1) All historical speed data of each carriage at the current moment is used as the input of the mutation point detection algorithm, and all mutation speed data is output;

[0074] Analyze the differences in the collection time corresponding to all the sudden speed data between each carriage and the other carriages at the current moment, and take the average of the differences in the collection time between each carriage and all the other carriages as the time difference coefficient of each carriage at the current moment;

[0075] It should be noted that there are many commonly used mutation point detection methods. In this embodiment, the Pettitt mutation point detection algorithm is used to obtain mutation rate data. The implementer may also use other mutation point detection methods such as the random forest algorithm. Regarding the selection of the mutation point detection method, this embodiment does not impose any special restrictions.

[0076] Among them, the Pettitt mutation point detection algorithm is a formula technology, and the specific process of detecting mutation data is not repeated here.

[0077] (2) Further, the differences of all the sudden change speed data between each car and the other cars at the current moment are analyzed, and the differences of the sudden change speed data between each car and all the other cars are averaged as the sudden change difference coefficient of each car at the current moment;

[0078] It should be noted that there are many methods for measuring the difference between data. In this embodiment, the absolute value of the difference between the sampling times corresponding to all sudden change speed data between each car and the other cars at the current moment is calculated to measure the difference in the collection times corresponding to the sudden change speed data between different cars; the absolute value of the difference between all sudden change speed data between each car and the other cars at any sampling moment is calculated to measure the difference in sudden change speed data between different cars. The implementer may also use other methods for measuring the difference, such as ratio. This embodiment does not impose any special restrictions on the selection of methods for measuring data differences.

[0079] (3) Further, based on the time difference coefficient and the mutation difference coefficient, the interval smoothness coefficient of each carriage at the current moment is determined, specifically:

[0080] The interval smoothness coefficient of each carriage at the current moment is the reciprocal of the sum of the time difference coefficient and the mutation difference coefficient of each carriage at the current moment.

[0081] Further, according to the interval smoothness coefficient of each carriage in each urban rail train at the current moment, it can be understood that if the speed data of the urban rail train collected at the current moment is the speed change data during the normal operation of the urban rail train, the time intervals of the speed data of the urban rail train in each carriage are similar, and the difference between the speed data is small, that is, the smaller the time difference coefficient of the carriage and the smaller the mutation difference coefficient, the larger the interval smoothness coefficient, indicating that the urban rail train speed data collected at the current moment is normal speed data; conversely, if the speed data of the urban rail train collected at the current moment is abnormal, the time intervals of the speed data of the urban rail train in each carriage are relatively different, and the difference between the speed data is relatively large, that is, the larger the time difference coefficient of the carriage and the larger the mutation difference coefficient, the smaller the interval smoothness coefficient, indicating that the possibility of the urban rail train speed data collected at the current moment being abnormal is greater.

[0082] (4) Further, based on the speed normal coefficient and the interval smooth coefficient, the speed accuracy coefficient of each carriage in each urban rail train at the current moment is determined, specifically:

[0083] The speed accuracy coefficient of car j at the current moment The expression is: ; Indicates the normal coefficient of the speed of carriage j at the current moment; Indicates the interval smoothness coefficient of car j at the current moment.

[0084] According to the speed accuracy coefficient of each car in each urban rail train at the current moment, it can be understood that during the operation of the urban rail train, if the speed data of the urban rail train collected by the speed sensor at a single moment is the speed data of the urban rail train when it is operating normally, the greater the trend similarity of the speed data of each car, and the more similar the degree of change of the speed data, the greater the speed normal coefficient, and the more similar the time intervals when the speed changes in the cars, that is, the greater the interval smoothness coefficient, the greater the speed accuracy coefficient, indicating that the possibility of error in the currently collected urban rail train speed data is smaller; conversely, during the operation of the urban rail train, if the speed data of the urban rail train collected by the speed sensor at a single moment is the speed data affected by the vibration of the train or the environment during the operation of the urban rail train, the smaller the trend similarity of the speed data of each car, and the greater the difference in the degree of change of the speed data, the smaller the speed normal coefficient, and the smaller the similarity of the time intervals when the speed changes in the cars, that is, the smaller the interval smoothness coefficient, the smaller the speed accuracy coefficient, indicating that the possibility of error in the currently collected urban rail train speed data is greater.

[0085] Step S4: Based on the difference in speed data of each carriage between the current time and the same time of the previous day, and the difference in the change trend of all historical speed data, determine the speed regularity coefficient of each carriage at the current time.

[0086] When the urban rail train is running uphill or downhill, the resistance of the urban rail train will change instantly, which will also cause the speed data of the urban rail train to change rapidly. Since the resistance change lasts for a short time, the speed change lasts for a short time. The speed change of this urban rail train is similar to the speed data characteristics when the speed measurement has errors. It is difficult to distinguish the speed change caused by resistance from the speed data when the measurement has errors when calculating only by the above method, so further analysis is needed.

[0087] Normally, the same urban rail train runs the same route every day. When the urban rail train is on time, the speed at the same time is relatively close, and the time when the urban rail train encounters resistance is usually relatively close. Therefore, under normal circumstances, the speed change of the urban rail train caused by the change of resistance has a certain regularity. Specifically, the speed data of the urban rail train is similar to the speed data of the urban rail train at the same time of the previous day, and the change trend is also relatively similar.

[0088] Therefore, based on the difference in speed data of each carriage between the current time and the same time of the previous day, and the difference in the change trend of all historical speed data, the speed regularity coefficient of each carriage at the current time is determined to distinguish the normal speed change caused by resistance and the abnormal data change caused by the speed sensor measurement error. Specifically:

[0089] (1) In each urban rail train, the difference in speed data of each carriage between the current time and the same time of the previous day is analyzed as the speed difference of each carriage at the current time;

[0090] (2) All historical speed data of each car at the current moment is used as the input of the trend detection algorithm, and the trend strength is output. The difference in the trend strength of each car between the current moment and the same moment of the previous day is analyzed as the trend difference of each car at the current moment;

[0091] It should be noted that there are many commonly used trend test algorithms. In this embodiment, the Mann-Kendall trend test algorithm is used to obtain the trend strength of all historical speed data of each car at the current moment. The implementer may also use other trend test algorithms such as the Kendall rank correlation coefficient algorithm. This embodiment does not impose any special restrictions on the selection of the trend test algorithm.

[0092] Among them, the Mann-Kendall trend test algorithm is a well-known technology, and its specific principle is not repeated here.

[0093] (3) Further, based on the speed difference and the trend difference, the speed regularity coefficient of each carriage at the current moment is determined, specifically:

[0094] The speed regularity coefficient of car j at the current moment The expression is: ; In the formula, represents the speed difference of car j at the current moment; represents the trend difference of car j at the current moment; Indicates a constant greater than 0 to prevent the denominator from being 0. The value of is artificially set. The value of is 0.01. Under the premise of ensuring that the denominator is not 0 and does not excessively affect the calculation result, the implementer can also set it according to the specific situation. This embodiment does not impose any special restrictions.

[0095] According to the speed regularity coefficient of each carriage at the current moment, it can be understood that if the urban rail train speed data collected at the current moment is a change caused by a change in resistance during the normal operation of the urban rail train, the size of the urban rail train speed data is relatively close to the urban rail train speed data at the same time of the previous day, that is, the smaller the speed difference, and the change trend of the urban rail train speed data at the current moment and the same time of the previous day is also relatively similar, that is, the smaller the trend difference, the larger the speed regularity coefficient, indicating that the urban rail train speed data collected at the current moment is more likely to be speed data caused by resistance change; conversely, if the urban rail train speed data collected at the current moment is a change caused by a change in resistance during the normal operation of the urban rail train, the size of the urban rail train speed data is greatly different from the urban rail train speed data at the same time of the previous day, that is, the larger the speed difference, and the similarity of the change trend of the urban rail train speed data at the current moment and the same time of the previous day is smaller, that is, the larger the trend difference, the smaller the speed regularity coefficient, indicating that the urban rail train speed data collected at the current moment is more likely to be speed data caused by measurement error.

[0096] Step S5: Based on the difference in speed data between each car and all other cars at the current moment, and the difference in all historical speed data of each car between the current moment and its adjacent previous collection moment, determine the speed consistency coefficient of each car at the current moment, and combine the speed accuracy coefficient and speed regularity coefficient to determine the data reliability coefficient of each car at the current moment.

[0097] If the speed of the urban rail train changes due to resistance during its operation, the speed data collected by the speed sensors in each carriage of the urban rail train will change due to the change in resistance, and the change direction is consistent (that is, the speed data of the urban rail train will increase or decrease), which is specifically manifested as the larger the absolute value of the sum of the difference between the data collected by all speed sensors at a single moment and the previous moment. If the change in the speed data of the urban rail train is caused by speed measurement errors, then only the speed data of one or more carriages may change, and the amount of change may be quite different.

[0098] Therefore, based on the difference in speed data between each carriage and all other carriages at the current moment, and the difference in all historical speed data of each carriage between the current moment and its adjacent previous acquisition moment, the speed consistency coefficient of each carriage at the current moment is determined to further distinguish the normal speed change caused by resistance and the abnormal speed change caused by speed sensor measurement error, specifically:

[0099] (1) Calculate the mean of the speed data differences between each car and all other cars at the current moment as the speed difference between each car at the current moment;

[0100] (2) Further, the absolute value of the sum of the differences of all speed data of each carriage between the current moment and its previous collection moment is calculated as the consistency index of each carriage at the current moment;

[0101] (3) The speed consistency coefficient of each carriage at the current moment is the ratio of the consistency index of each carriage at the current moment to the speed difference between the carriages.

[0102] According to the speed consistency coefficient of each carriage at the current moment, it can be understood that if the speed data of the urban rail train collected by a single sensor at a single moment is a change caused by resistance, then the smaller the difference between the speed data of the urban rail train and the data collected by other sensors, that is, the smaller the speed difference between the cars, and the more consistent the data change direction, that is, the larger the consistency index, the larger the speed consistency coefficient, indicating that the speed data is more likely to be the speed change data caused by the change of the resistance of the urban rail train; conversely, if the speed data of the urban rail train collected by a single sensor at a single moment is a change caused by measurement error, then the larger the difference between the speed data of the urban rail train and the speed data collected by other sensors, that is, the larger the speed difference between the cars, and the more inconsistent the data change direction, that is, the smaller the consistency index, the smaller the speed consistency coefficient, indicating that the speed data is more likely to be the speed change data caused by measurement error.

[0103] Further, based on the speed consistency coefficient of each carriage at the current moment, and in combination with the speed accuracy coefficient and the speed regularity coefficient, the data reliability coefficient of each carriage at the current moment is determined, specifically:

[0104] The data reliability coefficient of car j at the current moment The expression is: ; In the formula, represents the speed regularity coefficient of car j at the current moment; It represents the speed consistency coefficient of car j at the current moment.

[0105] According to the data reliability coefficient of each carriage at the current moment, it can be understood that if the speed data of the urban rail train collected by the speed sensor at a single moment is a normal speed change caused by the change in resistance of the urban rail train, then the higher the regularity of the change of the data, that is, the higher the speed regularity coefficient, and the greater the consistency of the change in each sensor, that is, the larger the speed consistency coefficient, it means that the speed data of the urban rail train is the speed data generated by the normal change of the urban rail train speed; and the higher the accuracy of the speed data, that is, the higher the speed accuracy coefficient, the greater the data reliability coefficient, at this time, if the urban rail train needs to be stopped, it can be controlled in combination with the collected data; on the contrary, if the regularity of the change of the speed data at a single moment is lower, that is, the lower the speed regularity coefficient, and the smaller the consistency of the change in each sensor, that is, the smaller the speed consistency coefficient, it means that the urban rail train speed data is more likely to be an abnormal change caused by the speed sensor measurement error of the urban rail train speed; and the lower the accuracy of the speed data, that is, the lower the speed accuracy coefficient, the smaller the data reliability coefficient.

[0106] Preferably, the data reliability coefficient extraction process diagram provided in this embodiment is as follows: Figure 2 shown.

[0107] Step S6: Based on the data reliability coefficient of each carriage at the current moment, combined with the speed data of all carriages at the current moment and the actual position of the urban rail train, the urban rail train is stopped.

[0108] The data reliability coefficient of all carriages at the current moment is used as the input of the threshold segmentation algorithm, and the segmentation threshold is output. The speed data less than the segmentation threshold is eliminated from the speed data of all carriages at the current moment, and the average of the speed data of the remaining carriages is used as the actual speed data of the urban rail train at the current moment;

[0109] The distance between the preset ideal parking position and the actual position of the urban rail train at the current moment, as well as the difference between 0 and the actual speed data of the urban rail train at the current moment are used as the input of the PID controller, and the output control signal controls the urban rail train to stop. Among them, 0 means that the speed is 0, and the speed of 0 means that the urban rail train stops.

[0110] It should be noted that there are many commonly used threshold segmentation algorithms. The Otsu threshold segmentation algorithm is used in this embodiment, and the implementer may also use other threshold segmentation algorithms. Regarding the selection of the threshold segmentation algorithm, this embodiment does not impose any special restrictions.

[0111] Among them, the principles of Otsu threshold segmentation algorithm and PID controller are well-known technologies, and their specific implementation processes will not be repeated here.

[0112] Based on the same inventive concept as the above control method, the embodiment of the present application also provides a parking control system for an urban rail train, comprising:

[0113] The speed data collection module is used to obtain the speed data of each carriage at the current time of each day and the actual position of the urban rail train, as well as the speed data of each carriage at all collection times within a preset time before the current time in each urban rail train, and use it as the historical speed data of each carriage at the current time;

[0114] The speed weight acquisition module is used to determine the normal speed coefficient of each carriage at the current moment based on the similarity of all historical speed data between each carriage and the other carriages at the current moment, and the discrete degree of all elements in the first-order difference sequence of all historical speed data of each carriage;

[0115] Based on the difference in the mutation of all historical speed data between each carriage at the current moment and the rest of the carriages, determine the interval smoothness coefficient of each carriage at the current moment, and determine the speed accuracy coefficient of each carriage at the current moment in combination with the speed normality coefficient;

[0116] Based on the difference in speed data of each carriage between the current time and the same time of the previous day, and the difference in the change trend of all historical speed data, the speed regularity coefficient of each carriage at the current time is determined;

[0117] Based on the difference in speed data between each carriage and all other carriages at the current moment, and the difference in all historical speed data of each carriage between the current moment and its adjacent previous collection moment, the speed consistency coefficient of each carriage at the current moment is determined, and the data reliability coefficient of each carriage at the current moment is determined in combination with the speed accuracy coefficient and the speed regularity coefficient;

[0118] The parking control module is used to control the parking of the urban rail train based on the data reliability coefficient and in combination with the speed data of all carriages and the actual position of the urban rail train at the current moment.

[0119] The present application provides a block diagram of a parking control system for a city rail train, such as Figure 3 shown.

[0120] Based on the same inventive concept as the above-mentioned control method, an embodiment of the present application also provides a parking device for an urban rail train, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, wherein when the processor executes the computer program, the steps of any one of the control methods described in the above-mentioned parking control method for an urban rail train are implemented.

[0121] It should be noted that the above sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above is a description of a specific embodiment of this specification. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0122] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0123] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present application should be included in the protection scope of the present application.

Claims

1. A parking control method for an urban rail train, characterized in that: The control method comprises the following steps: In each urban rail train, obtain the speed data of each carriage at the current time of each day and the actual position of the urban rail train, as well as the speed data of each carriage at all collected times within a preset time before the current time, and use it as the historical speed data of each carriage at the current time; Based on the average distribution level of the similarity of the historical speed data between each carriage and all other carriages at the current moment, and the difference between the discrete degree of all elements in the first-order difference sequence of all historical speed data of each carriage and the discrete degree of all elements in the first-order difference sequence of all historical speed data of the other carriages, the speed normal coefficient of each carriage at the current moment is determined; A mutation point detection algorithm is used to obtain mutation speed data from all historical speed data of each carriage at the current moment, and the average distribution of the differences in the acquisition time of all speed mutation data between each carriage and all other carriages, as well as the average distribution of the differences in mutation speed data, are analyzed to determine the interval smoothing coefficient of each carriage at the current moment, and the speed accuracy coefficient of each carriage at the current moment is determined in combination with the speed normal coefficient; Based on the difference in speed data of each carriage between the current time and the same time of the previous day, and the difference in the change trend of all historical speed data, the speed regularity coefficient of each carriage at the current time is determined; Based on the difference in speed data between each carriage and all other carriages at the current moment, and the difference in all historical speed data of each carriage between the current moment and its adjacent previous collection moment, the speed consistency coefficient of each carriage at the current moment is determined, and the data reliability coefficient of each carriage at the current moment is determined in combination with the speed accuracy coefficient and the speed regularity coefficient; Based on the data reliability coefficient and in combination with the speed data of all carriages and the actual position of the urban rail train at the current moment, the urban rail train is controlled to stop.

2. A parking control method for an urban rail train as claimed in claim 1, characterized in that: The method for determining the normal coefficient of speed of each carriage at the current moment is: In each urban rail train, the similarity of all historical speed data between each carriage and the other carriages at the current moment is analyzed, and the average level of the similarity between each carriage and all the other carriages is used as the speed similarity of each carriage at the current moment; Analyze the discreteness of all elements in the first-order difference sequence of all historical speed data of each carriage at the current moment, and take the accumulated result of the difference between the discreteness of each carriage and the discreteness of all other carriages as the speed difference coefficient of each carriage at the current moment; The normal coefficient of the speed of each carriage at the current moment is the ratio of the speed similarity of each carriage at the current moment to the speed difference coefficient.

3. A parking control method for an urban rail train as claimed in claim 2, characterized in that: The method for determining the interval smoothing coefficient of each carriage at the current moment is: Analyze the differences in the collection time corresponding to all the sudden speed data between each carriage and the other carriages at the current moment, and take the average of the differences in the collection time between each carriage and all the other carriages as the time difference coefficient of each carriage at the current moment; Analyze the differences of all mutation speed data between each carriage and the other carriages at the current moment, and take the average of the differences of the mutation speed data between each carriage and all the other carriages as the mutation difference coefficient of each carriage at the current moment; The interval smoothness coefficient of each carriage at the current moment is the reciprocal of the sum of the time difference coefficient and the mutation difference coefficient of each carriage at the current moment.

4. A parking control method for an urban rail train as claimed in claim 3, characterized in that: The expression of the speed accuracy coefficient of each carriage at the current moment is: ; Indicates the speed accuracy coefficient of car j at the current moment; Indicates the normal coefficient of the speed of carriage j at the current moment; Indicates the interval smoothness coefficient of car j at the current moment.

5. The parking control method for an urban rail train according to claim 1, characterized in that: The method for determining the speed regularity coefficient of each carriage at the time of the day is: Analyze the difference in speed data of each carriage between the current time and the same time of the previous day as the speed difference of each carriage at the current time; All historical speed data of each carriage at the current moment are used as the input of the trend detection algorithm, and the trend strength is output. The difference in the trend strength of each carriage between the current moment and the same moment of the previous day is analyzed as the trend difference of each carriage at the current moment; The speed regularity coefficient of car j at the current moment The expression is: ; In the formula, represents the speed difference of car j at the current moment; represents the trend difference of car j at the current moment; Indicates a preset constant greater than 0.

6. A parking control method for an urban rail train as claimed in claim 1, characterized in that: The method for determining the speed consistency coefficient of each carriage at the current moment is: Calculate the average of the speed data differences between each carriage and all other carriages at the current moment as the speed difference between each carriage at the current moment; Calculate the absolute value of the sum of the differences of all speed data of each carriage between the current moment and the previous acquisition moment, as the consistency index of each carriage at the current moment; The speed consistency coefficient of each carriage at the current moment is the ratio of the consistency index of each carriage at the current moment to the speed difference between the carriages.

7. A parking control method for an urban rail train as claimed in claim 1, characterized in that: The expression of the data reliability coefficient of each carriage at the current moment is: ; In the formula, represents the data reliability coefficient of car j at the current moment; represents the speed regularity coefficient of car j at the current moment; It represents the speed consistency coefficient of car j at the current moment.

8. The parking control method for an urban rail train according to claim 1, characterized in that: The stopping control of the urban rail train comprises: The data reliability coefficient of all carriages at the current moment is used as the input of the threshold segmentation algorithm, and the segmentation threshold is output. The speed data greater than or equal to the segmentation threshold is averaged among the speed data of all carriages at the current moment as the actual speed data of the urban rail train at the current moment; The distance between the preset ideal parking position and the actual position of the urban rail train at the current moment, as well as the difference between 0 and the actual speed data of the urban rail train at the current moment are used as the input of the PID controller, and the output control signal controls the urban rail train to stop.

9. A parking control device for an urban rail train, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the parking control method for an urban rail train as described in any one of claims 1-8 are implemented.

10. A parking control system for an urban rail train, implementing the parking control method for an urban rail train as claimed in claim 1, characterized in that: The control system comprises: The speed data collection module is used to obtain the speed data of each carriage at the current time of each day and the actual position of the urban rail train, as well as the speed data of each carriage at all collection times within a preset time before the current time in each urban rail train, and use it as the historical speed data of each carriage at the current time; The speed weight acquisition module is used to determine the normal speed coefficient of each carriage at the current moment based on the similarity of all historical speed data between each carriage and the other carriages at the current moment, and the discrete degree of all elements in the first-order difference sequence of all historical speed data of each carriage; Based on the difference in the mutation of all historical speed data between each carriage at the current moment and the other carriages, determine the interval smoothness coefficient of each carriage at the current moment, and determine the speed accuracy coefficient of each carriage at the current moment in combination with the speed normality coefficient; Based on the difference in speed data of each carriage between the current time and the same time of the previous day, and the difference in the change trend of all historical speed data, the speed regularity coefficient of each carriage at the current time is determined; Based on the difference in speed data between each carriage and all other carriages at the current moment, and the difference in all historical speed data of each carriage between the current moment and its adjacent previous collection moment, the speed consistency coefficient of each carriage at the current moment is determined, and the data reliability coefficient of each carriage at the current moment is determined in combination with the speed accuracy coefficient and the speed regularity coefficient; The parking control module is used to control the parking of the urban rail train based on the data reliability coefficient and in combination with the speed data of all carriages and the actual position of the urban rail train at the current moment.

Images