CN114358593A - Bridge area track smoothness evaluation method based on PCA model - Google Patents
Bridge area track smoothness evaluation method based on PCA model Download PDFInfo
- Publication number
- CN114358593A CN114358593A CN202210004122.2A CN202210004122A CN114358593A CN 114358593 A CN114358593 A CN 114358593A CN 202210004122 A CN202210004122 A CN 202210004122A CN 114358593 A CN114358593 A CN 114358593A
- Authority
- CN
- China
- Prior art keywords
- track
- bridge
- value
- bridge area
- line
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000011156 evaluation Methods 0.000 title claims abstract description 50
- 238000012423 maintenance Methods 0.000 claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 16
- 238000007689 inspection Methods 0.000 claims abstract description 7
- 238000005070 sampling Methods 0.000 claims description 16
- 238000009418 renovation Methods 0.000 claims description 9
- 230000001186 cumulative effect Effects 0.000 claims description 7
- 239000011159 matrix material Substances 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 238000009966 trimming Methods 0.000 claims description 5
- 238000004590 computer program Methods 0.000 claims description 4
- 238000009419 refurbishment Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 3
- 238000012821 model calculation Methods 0.000 claims description 2
- 238000000513 principal component analysis Methods 0.000 abstract description 22
- 238000001514 detection method Methods 0.000 abstract description 15
- 238000007405 data analysis Methods 0.000 abstract description 2
- 230000007547 defect Effects 0.000 abstract description 2
- 201000010099 disease Diseases 0.000 abstract description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 abstract description 2
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 230000003449 preventive effect Effects 0.000 abstract description 2
- 238000007619 statistical method Methods 0.000 abstract description 2
- 238000007726 management method Methods 0.000 description 21
- 230000008439 repair process Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005489 elastic deformation Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06395—Quality analysis or management
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Machines For Laying And Maintaining Railways (AREA)
Abstract
The invention provides a bridge area track smoothness evaluation method based on a PCA (principal component analysis) model, which analyzes and evaluates the smoothness of a bridge area track by integrating the quality indexes of TQI tracks and combining the PCA model, overcomes the defects that the actual state of a line is difficult to reflect by the existing local irregularity amplitude overrun evaluation method and the single geometric parameter is outstanding because the track irregularity quality index evaluation method cannot be clear, and has the functions of independently dividing units aiming at the irregularity phenomenon between two holes of the bridge area track and at an abutment, comprehensively evaluating the quality of the bridge area track and providing objective guidance basis for a track maintenance plan. The method periodically detects the geometric smooth state of the track in the bridge area through the comprehensive detection vehicle, carries out data analysis on detection data, diagnoses damage based on threshold values in various indexes in the TQI track quality index in the bridge area, and evaluates the track state of the bridge area. And aiming at the statistical analysis result, performing key monitoring and inspection on the disease-prone area, and providing a basis for preventive and predictive management and maintenance.
Description
Technical Field
The invention belongs to the technical field of track detection and evaluation, and particularly relates to a bridge area track smoothness evaluation method based on a PCA (principal component analysis) model.
Background
The track is the main technical equipment of driving, and in daily operation process, along with time, vertical, horizontal dynamic elastic deformation and permanent deformation can appear in the track under the unstable repeated load effect of vehicle, generally known as track irregularity. The natural settlement phenomenon of the abutment of the bridge area leads the track near the abutment of the bridge area to have serious irregularity, and the irregularity between two holes of the bridge area is also serious, which is particularly obvious on the track of a super bridge of a high-speed rail (the span of a single hole is more than 150 m). The state of the track plays a decisive role in the safe operation of the train, the comfort of the passengers' journey, the service life of the equipment and the maintenance costs.
The bridge plays an important role and occupies an important position in modern transportation as a key and control part of a rail transportation system, and the maintenance and the renovation of the rail in a bridge area are the most important part in the maintenance of the rail. The method effectively manages the rail state of the bridge area, grasps the rail state of the bridge area in real time, keeps the integrity and the quality balance of line equipment, ensures that a train runs safely, stably and uninterruptedly at a specified speed, prolongs the service life of the rail of the bridge area as far as possible, and becomes an important research topic of railway workers at home and abroad gradually.
Along with the increase of the running speed of the train, the detection of the rail smoothness of the bridge area is changed from single rail detection to the combination of various detection modes such as rail detection, vehicle-mounted ride addition, manual ride addition and the like. Therefore, it is urgently needed to deeply research how to comprehensively utilize various detection data to accurately evaluate the smooth state of the track in the bridge area, so as to provide a reference for scientifically making a renovation plan and reasonably arranging daily maintenance. At present, the evaluation of the track quality state in China is mainly carried out by a track inspection vehicle, and the evaluation methods used in practice mainly comprise two methods: peak mark and Track Quality Index (TQI, Track Quality Index).
The peak deduction evaluation method judges whether the measured value exceeds the specified limit by measuring the amplitude of each measuring point of each parameter of the track of the bridge area, generally divided into four levels of management, and divided into different deduction standards for different overrun levels. The peak management method only uses the size of the peak value of the overrun point, the overrun quantity and the deduction quantity, cannot comprehensively, scientifically and reasonably evaluate the average quality state of the bridge area track section, and is difficult to objectively reflect the actual state of the bridge area track. Meanwhile, when the track state is evaluated by using a peak value management method, the influence of the dynamic inspection standard on the detection result is large; thirdly, the weight of the over-limit deduction of the fourth grade is larger than that of the first grade and the second grade; the influence of detection system errors is large; the influence of the overrun length cannot be reflected; the influence of harmonic waves generated by the change rate of the track irregularity of the bridge area and the periodic continuous irregularity cannot be reflected.
The track quality index generally takes a bridge area track section of 200m as a unit section, the standard deviation of 7 geometric irregularity amplitude values such as left and right height, left and right track direction, track gauge, level, triangular pit and the like on the unit section is respectively calculated, the standard deviation of each single geometric irregularity amplitude value is called a single index, the sum of the 7 single indexes is taken as a bridge area track quality index TQI for evaluating the comprehensive quality state of the bridge area track smoothness of the section, the real bridge area track quality state is reflected by utilizing the TQI, and the integral smoothness of each bridge area track section is clearly represented by numerical values. The evaluation method of the quality index of the track in the bridge area can only reflect the comprehensive quality index of the track system in the bridge area, the degree of influence on the TQI in each single index cannot be determined, and the limited local limit points exist in the track but the integral TQI is deviated from the smoothness, so that the limit points are ignored; it is difficult to purposefully provide maintenance and repair for the rails in the bridge area and to determine a reasonable repair and repair sequence.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: a bridge area track smoothness evaluation method based on a PCA model is provided and is used for evaluating the smoothness of a track and making a line maintenance and repair plan.
The technical scheme adopted by the invention for solving the technical problems is as follows: a bridge region orbit smoothness evaluation method based on a PCA model comprises the following steps: s1: dividing a line unit of a bridge area track;
s2: acquiring original data of the track smoothness of a bridge area;
s3: measuring and calculating a management value T of a track quality index TQI by adopting a track smoothness quality index evaluation method;
s4: a PCA model calculation unit is adopted to comprehensively evaluate the value Z;
s5: determining a trimming sequence of each section according to the T value, determining a trimming sequence of geometric parameters in the sections according to the Z value, and comprehensively evaluating the irregularity of the rail; determining whether to refurbish the rail according to the evaluation result; if yes, determining a refurbishment sequence and executing the step S6; if not, executing step S2;
s6: a refurbishment sequence is determined.
According to the scheme, in the step S1, the specific steps are as follows:
s11: the length of the section for dividing the line unit is 200 m;
s12: the method for dividing the track unit of the track comprises the following steps:
dividing according to the line type of the bridge area track: the line type comprises a straight line type, a curve line type and a turnout line type;
dividing the track into different bridge areas according to the structure of the track;
dividing the bridge span tracks into all the rest bridge span tracks every 200m according to the front and back division of the central axis of each bridge pier and each platform;
dividing the front and back of the intersection point of the two bridge holes and the rest of all the tracks into 200 m;
and dividing the maintenance force according to the maintenance force distribution situation of the operation unit.
Further, in step S2, the specific steps include: detecting and recording original data of the track of the bridge area on the line unit through a track inspection vehicle; the geometrical parameters of the original data of the bridge area track comprise left height, right height, left track direction, right track direction, track gauge, level and triangular pits.
Further, in step S3, the specific steps include:
s31: let sigmaiAs standard deviation of individual geometric parameters (i ═ 1,2, …,7, j ═ 1,2 …, n); n is the number of sampling points in the line unit section; x is the number ofijThe amplitude of each parameter at the sampling point in the line unit section;
continuous spot amplitude x in line cell section for each parameterijAverage value of (d); the management value of the track quality index TQI of the unit track is:
s32: and calculating a management value T of the section track quality index TQI.
Further, in step S4, the specific steps include:
s41: carrying out standardization processing on the unit data; let n be the number of sampling points in the cell segment, xnFor the original amplitude of the sampling point in the line unit section, i is 1,2, …,7 to represent the geometric parameters of left high and low, right high and low, left track, right track, track pitch, horizontal, triangular pit, i term geometric parameter xnAre respectively marked as i ═ ai1,ai2…,ain]；
Sample mean μ for the jth sample pointjComprises the following steps:
sample standard deviation s of jth sample pointjComprises the following steps:
the geometric parameter x of the i-th itemnOf the original amplitude of
Comprises the following steps:
normalized sampling point variable
Comprises the following steps:
s42: establishing a PCA model, and acquiring a unit comprehensive evaluation value Z;
let rijFor the correlation coefficient between the ith geometric parameter and the jth sampling point (i, j ═ 1,2 …, n), then:
the correlation coefficient matrix R of the geometric parameters is:
R＝(rij)n×n；
calculating the eigenvalue and eigenvector of the geometric parameter correlation coefficient matrix, solving the eigen equation | λ I-R | ═ 0, and solving the eigenvalue λiAnd arranged in size order as lambda1≥λ2≥…≥λnNot less than 0; let uj＝[u1j,u2j,…,unj]TSolving for the corresponding eigenvalues λiNormalized feature vector u ofi(i ═ 1,2, …, n); let y1Is the 1 st main component, y2…, y is the 2 nd principal componentnIs the n-th principal component, and is composed of feature vectors uiMake up n new sample point variables:
if p is less than or equal to 5, p principal components are selected to calculate the comprehensive evaluation value Z and the contribution rate b of the principal componentsj：
The cumulative contribution rate is:
the comprehensive evaluation value Z is:
s43: and respectively substituting the main component values of the geometric parameters of left height, right height, left track direction, right track direction, track gauge, level and triangular pit into the formula to obtain respective comprehensive evaluation values Z.
Further, in step S42, the specific steps of selecting the main component are:
s421: when the cumulative contribution rate reaches more than 85 percent, the characteristic value lambda is taken1,λ2,…λiThe corresponding 1 st, 2 nd, … th, ith principal component;
if the trend of the rubble graph is stable, selecting the quantity of the main components to meet the requirement;
and selecting the main components with the characteristic values larger than 1.
Further, in step S5, the specific steps include:
s51: evaluating the state quality of the track in each kilometer of the bridge area according to the T value, and formulating a large road maintenance mechanical maintenance or comprehensive maintenance plan of the track in the bridge area in three modes of balance, plan and priority:
for the line with T being more than or equal to 100, the line is evaluated as priority, and then the line is preferentially listed in a maintenance plan and is arranged to be maintained in sections as soon as possible;
for lines with 0 ≦ T ≦ 100, the evaluation is a plan, based on T200Reasonably arranging maintenance or repair of the value, and timely repairing the line:
for the line with the T being 0, the line is evaluated as balanced, the track bed is prevented from being disturbed in sections, and only the position of the overrun peak value is renovated;
s52: and determining the renovation sequence of the left height, the right height, the left rail direction, the right rail direction, the rail distance, the level and the triangular pit according to the size of the comprehensive evaluation value Z of the geometric parameters.
A computer storage medium having stored therein a computer program executable by a computer processor, the computer program executing a PCA model-based bridge orbit smoothness evaluation method.
The invention has the beneficial effects that:
1. according to the bridge area track smoothness evaluation method based on the PCA model, the smoothness of the bridge area track is analyzed and evaluated by combining the quality indexes of the synthetic TQI bridge area track and the PCA model, the defects that the actual state of a line is difficult to reflect by the existing local irregularity amplitude overrun evaluation method and the local severe irregularity of the track is easy to ignore by the track irregularity quality index evaluation method are overcome, and the functions of comprehensively evaluating the track quality and providing objective guidance basis for a track maintenance plan are realized.
2. The method periodically detects the geometric smooth state of the track in the bridge area through the comprehensive detection vehicle, carries out data analysis on detection data, diagnoses damage based on threshold values in various indexes in the TQI track quality index in the bridge area, and evaluates the track state of the bridge area. According to the statistical analysis result, the occurrence time of abnormal data is focused, the reason of the abnormal data is analyzed, the principal and secondary of analysis is analyzed by integrating a PCA model, and the important monitoring and inspection are carried out on the disease prone area, so that a basis is provided for preventive and predictive management.
Drawings
FIG. 1 is a flow chart of an embodiment of the present invention.
FIG. 2 is a diagram of a raw data space distribution according to an embodiment of the present invention.
FIG. 3 is a cell track state diagram of an embodiment of the present invention.
Fig. 4 is a lithotripsy of an embodiment of the present invention.
FIG. 5 is a TQI bridge section track state diagram of an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and specific embodiments.
Referring to fig. 1, a bridge region orbit smoothness evaluation method based on a PCA model according to an embodiment of the present invention includes the following steps:
(1) and dividing the line unit.
On the basis of combining the length of the TQI unit of 200m, the division is carried out according to the following principle: the method is divided by the line type of the bridge area track, or divided according to the maintenance force distribution condition of different bridge area track structures or operation units, or divided by a front right amount and a rear right amount of the central axis of each pier and each abutment and every 200m of all the rest bridge span tracks, or divided by a front right amount and a rear right amount of the intersection point of two bridge holes and every 200m of the rest all tracks. The line units can be divided according to line type, different bridge area track structures and maintenance force distribution of operation units. At present, the railway is mainly divided according to the line straight line, the curve and the basic line type of the turnout in China, and meanwhile, the maintenance force distribution characteristics of all the station sections are considered for dividing, and the attention of the railway unit near the abutment and between the bridge holes is paid to the railway in the bridge area.
(2) And measuring the line unit.
The geometric parameters of the bridge track are detected and recorded on the line unit by the rail inspection vehicle. The geometric parameters of the bridge area track comprise seven geometric parameters of left and right height, left and right track direction, track gauge, level, triangular pits and the like.
(3) And calculating the line unit.
Calculating a TQI management value:
in the formula, σiAs standard deviation of individual geometric parameters (i ═ 1,2, …,7, j ═ 1,2 …, n); n is the number of sampling points in the unit section; x is the number ofijThe amplitude of each parameter at the sampling point in the unit section;
continuous spot amplitude x in unit zone for each parameterijAverage value of (a).
Secondly, determining a comprehensive evaluation value of the influence of the geometric parameters on the track smoothness of the bridge area through a PCA model
1) Firstly, different geometric parameters are subjected to data standardization processing, so that the influence of different dimensions and different orders of magnitude on the evaluation result of the track smoothness of the bridge area is avoided. By xnThe original amplitude of the sample points in the cell bin is shown (n 4000 in 1km cell bin). The geometric parameters of the item i are 1,2, … and 7 respectively representing the geometric parameters of left and right height, left and right track direction, track gauge, level and triangular pit, and the geometric parameter x of the item inRespectively, the values of (a) are expressed asi1,ai2…,ain]。
Wherein the content of the first and second substances,
i.e. mujAnd sjThe sample mean and sample standard deviation of the jth sample point.
At the same time, call
To normalize the sample point variables.
2) Calculating a correlation coefficient matrix R of the geometric parameters
R＝(rij)n×n；
Wherein the content of the first and second substances,
in the formula rijIs the correlation coefficient between the ith geometric parameter and the jth sampling point (i, j ═ 1,2 …, n).
Calculating the eigenvalue and eigenvector of the geometric parameter correlation coefficient matrix, firstly solving the eigen equation | λ I-R | ═ 0, and solving the eigenvalue λiAnd arranged in order of magnitude, λ1≥λ2≥…≥λnNot less than 0; then, a normalized feature vector ui (i ═ 1,2, …, n) is determined for each feature value, u ═ 1,2, …, nj＝[u1j,u2j,…,unj]TAnd n new sampling point variables are formed by the feature vectors.
Wherein, y1Is the 1 st main component; y is2Is the 2 nd main component; … …, respectively; y isnIs the nth main component.
3) Selecting p (p is less than or equal to 5) main components to calculate comprehensive evaluation value
Contribution ratio of principal component:
cumulative contribution rate:
the main component selection method comprises the following steps:
I. when the accumulated influence rate reaches more than 85 percent, the lambda corresponding to the characteristic value1，λ2，...λiThe corresponding 1 st, 2 nd, … th principal component.
And II, observing a lithotripsy graph, and when the trend becomes stable, indicating that the quantity of the main component is more suitable to be selected.
And III, selecting the main component with the characteristic value larger than 1.
And (3) comprehensive influence score:
and substituting the principal component values of the geometric parameters into the formula to obtain the comprehensive ranking of the geometric parameters.
(4) And (6) evaluating the line unit.
Taking the magnitude of the irregularity quality index TQI of the bridge area track in the 200m section exceeding the management value as a deduction T200Value, deduct fraction T of 5 cell segments per kilometer200The sum of the values is referred to as the "T value". The T value is determined based on the extent to which the TQI value exceeds the corresponding management value within the cell segment.
For T200The calculated 200m section bridge area track irregularity quality index TQI management value standard is shown in Table 1.
TABLE 1 for T200Bridge area track irregularity quality index TQI management value standard
For T200A value defined as the value not exceeding (less than or equal to) the management value of the speed class, the 200m section is deducted T200A value of 0; if the value is greater than the management value but less than or equal to the management value of "more than 10%", the 200m section is deducted to be T200The value was 40 points; if the value is greater than the management value of "more than 10%" but less than or equal to the management value of "more than 20%", the 200m section is deducted200The value was 50 minutes; if the value is greater than the management value of "more than 20%", the 200m section is deducted to be T200The value was 61 points, see Table 2.
Table 2200 m cell segment T200Value deduction score definition
| TQI value | Not exceeding the management value | Exceeding the regulatory value | More than 10 percent | More than 20 percent |
| T200Value of | 0 | 40 | 50 | 61 |
Taking each kilometer as a management length, the sum of TQI deduction values of 5 200m unit sections contained in each kilometer is T, and a calculation formula of the T value is as follows:
and evaluating the state quality of the track in each kilometer of the bridge area according to the T value, and formulating a large road maintenance machine maintenance or comprehensive maintenance plan of the track in the bridge area in three modes of balance, plan and priority, wherein the meanings of the maintenance plan are shown in a table 3.
TABLE 3 Whole kilometer T value evaluation definition table
| Definition of evaluation | Equalization | Plan for | Priority of |
| T value per kilometer | T＝0 | 0≤T≤100 | T≥100 |
For the line with T being more than or equal to 100, a maintenance plan is preferably listed, and section maintenance is arranged as soon as possible; for the line with T being more than or equal to 0 and less than or equal to 100, the overall consideration should be given to the line according to T200The value is reasonably arranged for maintenance, and the line is timely repaired: for a line with T being 0, the track bed is prevented from being disturbed in sections, and only the position of the overrun peak is renovated. And simultaneously, determining the renovation sequence of the left and right height, the left and right track direction, the track gauge, the level and the triangular pit according to the magnitude of the comprehensive evaluation value Z of the 7 geometric parameters.
The examples of the invention are as follows:
(1) and dividing the line unit.
And selecting a whole kilometer section of a railway single line as five line units according to the division details, wherein the five line units are named as a1, a2, a3, a4 and a5 respectively.
TABLE 4 track smoothness geometric parameter data of each unit bridge area at a certain time interval
| Unit cell | Track gauge | Level of | High and low at the left | High and low at the right side | Left track is to | Right track direction | Triangular pit | TQI value |
| a1 | 0.85 | 1.34 | 1.78 | 1.9 | 1.93 | 1.98 | 1.5 | 11.28 |
| a2 | 1.92 | 1.79 | 2.66 | 2.42 | 4.31 | 4.34 | 1.97 | 19.41 |
| a3 | 1.2 | 1.71 | 1.82 | 1.74 | 1.53 | 1.55 | 1.98 | 11.53 |
| a3 | 0.92 | 1.71 | 2.44 | 2.28 | 1.33 | 1.34 | 1.97 | 11.99 |
| a5 | 1.2 | 1.72 | 2.04 | 1.88 | 1.76 | 1.75 | 1.86 | 12.21 |
(2) And calculating the line unit.
TQI management value calculation is shown in fig. 2.
The PCA model calculates principal component analysis characteristic values, contribution rates and cumulative contribution rates as shown in Table 5, and a lithograph is shown in FIG. 4.
TABLE 5 principal Components analysis results
| Number of principal component | Characteristic value | Rate of contribution | |
| 1 | 4.4130 | 0.6905 | 0.6905 |
| 2 | 1.6491 | 0.2748 | 0.9654 |
| 3 | 0.1664 | 0.0277 | 0.9931 |
| 4 | 0.0321 | 0.0054 | 0.9985 |
| 5 | 0.0090 | 0.0015 | 0.9999 |
| 6 | 0.0003 | 0.0001 | 1.0000 |
According to the three selection modes, the accumulated contribution rate of the first two characteristic roots reaches more than 96 percent; the lithotripsy pattern started to be obviously slowed down at the third component; characteristic values above 1 also have only the first two components. The results of the three selection modes are the same, and the principal component analysis effect is good. The first two principal components are selected for comprehensive evaluation, and the influence degree ranking and comprehensive evaluation result table 6 are shown.
TABLE 6 comprehensive scoring and ranking of influence degree of track smoothness of bridge area
(4) And (6) evaluating the line unit.
As can be seen from the TQI bridge area track state diagram, in the detected time period a2, the unit TQI exceeds 20%, the T value of the whole kilometer bridge area track is 61, a maintenance plan is required, and the unit a2 is paid attention to; when the comprehensive influence of the track irregularity parameters of each bridge area on the TQI is evaluated on the whole based on the line unit comprehensive detection vehicle data, the comprehensive evaluation value Z can be used for evaluation. In the selected line units, the comprehensive evaluation values Z of the units are 2.5459, 2.3244, 1.7427, 0.7274, -1.9267, -2.0225 and-3.3911 in sequence from table 6, so that the influence of the left height, the triangular pit, the right height and the level on the smoothness of the track of the bridge area is large, and the influence of the track distance on the smoothness of the track of the bridge area is minimum. From this analysis, the high and low levels of the a1 unit and the triangular pits should be maintained preferentially, and other parameters having a large influence on the track smoothness of the bridge area should be emphasized particularly.
On the basis of analyzing the evaluation method of the rail state of the domestic and foreign bridge area, the invention uses the advantages of the research to analyze the development trend of the rail state of the domestic bridge area by utilizing comprehensive detection data aiming at the current situation of the domestic existing research; by means of modern information technology, how to analyze the state of the track in the bridge area by using detection data is provided, and a bridge area track state evaluation model is determined from the angles of irregularity of a bridge area track unit, integral irregularity of a track section, key influence factors and the like.
The invention introduces the quality index of the track of the TQI bridge area, combines with Principal Component Analysis (PCA), realizes the Analysis of the geometric irregularity of the track of each section bridge area in a targeted manner, firstly determines the value of the whole kilometer T on the unit section, determines whether the section is listed in a renovation plan, then determines the influence degree of 7 geometric irregularity indexes such as left and right height, left and right track direction, track distance, level, triangular pits and the like on the smooth state of the track of the bridge area through a PCA model, so as to clearly influence the main reason of the smoothness of the track of the bridge area, and finally determines a specific renovation plan through the statistical characteristics of data, thereby improving the renovation efficiency and reducing the renovation cost.
The above embodiments are only used for illustrating the design idea and features of the present invention, and the purpose of the present invention is to enable those skilled in the art to understand the content of the present invention and implement the present invention accordingly, and the protection scope of the present invention is not limited to the above embodiments. Therefore, all equivalent changes and modifications made in accordance with the principles and concepts disclosed herein are intended to be included within the scope of the present invention.
Claims (8)
1. A bridge region orbit smoothness evaluation method based on a PCA model is characterized by comprising the following steps: the method comprises the following steps:
s1: dividing a line unit of a bridge area track;
s2: acquiring original data of the track smoothness of a bridge area;
s3: measuring and calculating a management value T of a track quality index TQI by adopting a track smoothness quality index evaluation method;
s4: a PCA model calculation unit is adopted to comprehensively evaluate the value Z;
s5: determining a trimming sequence of each section according to the T value, determining a trimming sequence of geometric parameters in the sections according to the Z value, and comprehensively evaluating the irregularity of the rail; determining whether to refurbish the rail according to the evaluation result; if yes, determining a refurbishment sequence and executing the step S6; if not, executing step S2;
s6: a refurbishment sequence is determined.
2. The method for evaluating the smoothness of a bridge track based on a PCA model as claimed in claim 1, wherein: in the step S1, the specific steps are as follows:
s11: the length of the section for dividing the line unit is 200 m;
s12: the method for dividing the track unit of the track comprises the following steps:
dividing according to the line type of the bridge area track: the line type comprises a straight line type, a curve line type and a turnout line type;
dividing the track into different bridge areas according to the structure of the track;
dividing the bridge span tracks into all the rest bridge span tracks every 200m according to the front and back division of the central axis of each bridge pier and each platform;
dividing the front and back of the intersection point of the two bridge holes and the rest of all the tracks into 200 m;
and dividing the maintenance force according to the maintenance force distribution situation of the operation unit.
3. The method for evaluating the smoothness of a bridge track based on a PCA model as claimed in claim 2, wherein: in the step S2, the specific steps are as follows: detecting and recording original data of the track of the bridge area on the line unit through a track inspection vehicle; the geometrical parameters of the original data of the bridge area track comprise left height, right height, left track direction, right track direction, track gauge, level and triangular pits.
4. The method for evaluating the smoothness of a bridge track based on a PCA model as claimed in claim 3, wherein: in the step S3, the specific steps are as follows:
s31: let sigmaiAs standard deviation of individual geometric parameters (i ═ 1,2, …,7, j ═ 1,2 …, n); n is the number of sampling points in the line unit section; x is the number ofijThe amplitude of each parameter at the sampling point in the line unit section;
continuous spot amplitude x in line cell section for each parameterijAverage value of (d); the management value of the track quality index TQI of the unit track is:
s32: and calculating a management value T of the section track quality index TQI.
5. The method of claim 4, wherein the evaluation method of bridge region orbit smoothness based on the PCA model is characterized in that: in the step S4, the specific steps are as follows:
s41: carrying out standardization processing on the unit data; let n be the number of sampling points in the cell segment, xnFor the original amplitude of the sampling point in the line unit section, i is 1,2, …,7 to represent the geometric parameters of left high and low, right high and low, left track, right track, track pitch, horizontal, triangular pit, i term geometric parameter xnAre respectively marked as i ═ ai1,ai2…,ain]；
Sample mean μ for the jth sample pointjComprises the following steps:
sample standard deviation s of jth sample pointjComprises the following steps:
the geometric parameter x of the i-th itemnOf the original amplitude of
Comprises the following steps:
normalized sampling point variable
Comprises the following steps:
s42: establishing a PCA model, and acquiring a unit comprehensive evaluation value Z;
let rijFor the correlation coefficient between the ith geometric parameter and the jth sampling point (i, j ═ 1,2 …, n), then:
the correlation coefficient matrix R of the geometric parameters is:
R＝(rij)n×n；
calculating the eigenvalue and eigenvector of the geometric parameter correlation coefficient matrix, solving the eigen equation | λ I-R | ═ 0, and solving the eigenvalue λiAnd arranged in size order as lambda1≥λ2≥…≥λnNot less than 0; let uj＝[u1j,u2j,…,unj]TSolving for the corresponding eigenvalues λiNormalized feature vector u ofi(i ═ 1,2, …, n); let y1Is the 1 st main component, y2…, y is the 2 nd principal componentnIs the n-th principal component, and is composed of feature vectors uiMake up n new sample point variables:
if p is less than or equal to 5, p principal components are selected to calculate the comprehensive evaluation value Z and the contribution rate b of the principal componentsj：
The cumulative contribution rate is:
the comprehensive evaluation value Z is:
s43: and respectively substituting the main component values of the geometric parameters of left height, right height, left track direction, right track direction, track gauge, level and triangular pit into the formula to obtain respective comprehensive evaluation values Z.
6. The method of claim 5, wherein the evaluation method of bridge region orbit smoothness based on PCA model is characterized in that: in step S42, the specific steps of selecting the main component are as follows:
s421: when the cumulative contribution rate reaches more than 85 percent, the characteristic value lambda is taken1,λ2,…λiThe corresponding 1 st, 2 nd, … th, ith principal component;
if the trend of the rubble graph is stable, selecting the quantity of the main components to meet the requirement;
and selecting the main components with the characteristic values larger than 1.
7. The method of claim 5, wherein the evaluation method of bridge region orbit smoothness based on PCA model is characterized in that: in the step S5, the specific steps are as follows:
s51: evaluating the state quality of the track in each kilometer of the bridge area according to the T value, and formulating a large road maintenance mechanical maintenance or comprehensive maintenance plan of the track in the bridge area in three modes of balance, plan and priority:
for the line with T being more than or equal to 100, the line is evaluated as priority, and then the line is preferentially listed in a maintenance plan and is arranged to be maintained in sections as soon as possible;
for lines with 0 ≦ T ≦ 100, the evaluation is a plan, based on T200Reasonably arranging maintenance or service of value at proper timeAnd (3) trimming the line:
for the line with the T being 0, the line is evaluated as balanced, the track bed is prevented from being disturbed in sections, and only the position of the overrun peak value is renovated;
s52: and determining the renovation sequence of the left height, the right height, the left rail direction, the right rail direction, the rail distance, the level and the triangular pit according to the size of the comprehensive evaluation value Z of the geometric parameters.
8. A computer storage medium, characterized in that: a computer program executable by a computer processor is stored therein, the computer program executing a method for evaluating bridge orbit smoothness based on a PCA model according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210004122.2A CN114358593A (en) | 2022-01-05 | 2022-01-05 | Bridge area track smoothness evaluation method based on PCA model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210004122.2A CN114358593A (en) | 2022-01-05 | 2022-01-05 | Bridge area track smoothness evaluation method based on PCA model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114358593A true CN114358593A (en) | 2022-04-15 |
Family
ID=81107953
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210004122.2A Pending CN114358593A (en) | 2022-01-05 | 2022-01-05 | Bridge area track smoothness evaluation method based on PCA model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114358593A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114818998A (en) * | 2022-06-28 | 2022-07-29 | 浙江大学 | Method for judging mud pumping disease state of ballastless track foundation bed during slurry turning |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358339A (en) * | 2017-06-20 | 2017-11-17 | 西安交通大学 | A kind of track quality state evaluating method based on big data |
-
2022
- 2022-01-05 CN CN202210004122.2A patent/CN114358593A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107358339A (en) * | 2017-06-20 | 2017-11-17 | 西安交通大学 | A kind of track quality state evaluating method based on big data |
Non-Patent Citations (6)
| Title |
|---|
| 李再帏等: "线路轨道状态时域与频域评价方法关系分析", 《铁道建筑》 * |
| 杨翠平等: "基于多时域特征量的轨道不平顺状态综合评估", 《铁道标准设计》 * |
| 林怀青等: "基于PCA和SVM的轨道不平顺状态识别", 《测控技术》 * |
| 王志鹏等: "基于机器学习的地铁轨道几何劣化规律个性化建模研究", 《都市快轨交通》 * |
| 田新宇等: "轨道几何不平顺幅值管理与均值管理的相关性分析", 《中国铁路》 * |
| 白磊: "铁路轨道健康管理网格化分析决策模型研究", 《中国优秀博硕士学位论文全文数据库(博士)工程科技Ⅱ辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114818998A (en) * | 2022-06-28 | 2022-07-29 | 浙江大学 | Method for judging mud pumping disease state of ballastless track foundation bed during slurry turning |
| CN114818998B (en) * | 2022-06-28 | 2022-09-13 | 浙江大学 | Method for judging mud pumping disease state of ballastless track foundation bed during slurry turning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2016029590A1 (en) | Fault prediction and condition-based maintenance method for urban rail train bogie | |
| CN110222437B (en) | Method and device for evaluating health status of train, and storage medium | |
| CN111222259B (en) | Multi-component preventive maintenance decision optimization model for metro vehicle bogie | |
| CN110197588A (en) | A kind of truck driving behavior appraisal procedure and device based on GPS track data | |
| Berawi et al. | Evaluating track geometrical quality through different methodologies | |
| CN112766556B (en) | Automatic railway track historical maintenance identification method based on Bayesian information criterion | |
| CN107908879B (en) | Method for evaluating fatigue performance of concrete beam bridge | |
| CN110210161B (en) | Method and device for evaluating health state of train and storage medium | |
| CN110203249B (en) | Train repair process method, device and storage medium | |
| CN113420367B (en) | Subway steel rail wave grinding detection method and device based on vibration and noise response | |
| CN109117536A (en) | The detection method of track irregularity evaluation parameter | |
| Braga et al. | Multivariate statistical aggregation and dimensionality reduction techniques to improve monitoring and maintenance in railways: The wheelset component | |
| CN114358593A (en) | Bridge area track smoothness evaluation method based on PCA model | |
| Gao et al. | Estimation of rail renewal period in small radius curves: A data and mechanics integrated approach | |
| CN116245278A (en) | Vibration control performance evaluation method for whole life cycle of subway vibration reduction track | |
| Ma et al. | A prediction method based on stepwise regression analysis for train axle temperature | |
| Jia et al. | Influence of pavement condition data variability on network-level maintenance decision | |
| Maljaars et al. | Systematic derivation of safety factors for the fatigue design of steel bridges | |
| CN114117687A (en) | Method and system for building and predicting life prediction model of key parts of wheel set | |
| CN114065358A (en) | Deformation monitoring-based method for evaluating operation comfort of large-span public rail same-layer cable-stayed bridge | |
| CN110143217B (en) | Track state measuring method, system and device | |
| CN114547796B (en) | Ball mill feature fusion fault diagnosis method based on optimized BN network | |
| Alsahli et al. | Investigation of the correlation between track geometry defect occurrence and wood tie condition | |
| CN113158403B (en) | Method for evaluating smoothness of rigid contact wires of subway based on kneeded | |
| CN111444658B (en) | Groove-type rail geometric parameter trend prediction method and system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20220415 |
|
| RJ01 | Rejection of invention patent application after publication |