Method for automatically evaluating track measurement data

Abstract

A method for the automatic evaluation of wavelet transformed track measurement data (1) of the track geometry and / or the ballast bed with a computing device is described. In order to enable automatic generation of suggestions for remedying track faults, according to the invention a measurement series of the track measurement data (1) to be evaluated, assigned to a track section, is first wavelet transformed with a plurality of wavelets of different wavelengths and, from these wavelet transforms, a type of thermal image, in which the wavelength above the position in a track and the wavelet transforms are provided as thermal information, and a wavelet power density spectrum (3) is formed and a signal strength diagram (4) is also calculated for different wavelength ranges (D0, D1, D2, D3), whereupon the local position (B, C, D, F), the extent (Δx) and the assigned wavelength ranges (E, D0, D1, D2, D3) of predominant track defects are determined from the thermal image, in particular from the contour lines of the thermal image, in order to determine the type, position, extent and size of the track defects.

Description

[0001] Method for automatic evaluation of track measurement data

[0002] Technical area

[0003] The invention relates to a method for the automatic evaluation of wavelet transformed track measurement data of the track geometry and / or the ballast bed using a computing device.

[0004] State of the art

[0005] The evaluation of measurement data obtained by track measuring vehicles using wavelet transformation is known from the prior art. CN 111979859 A discloses a system for detecting track irregularities, in which data obtained from acceleration sensors is evaluated using wavelet transformation. CN 104032629 B also discloses a method for detecting long-wavelength track irregularities, in which the data obtained from angular acceleration sensors is evaluated using wavelet transformation. CN 104947555 A shows another method for detecting track irregularities, which is determined using Fourier transformations of the wavelengths underlying the irregularities.

[0006] The vast majority of railway lines are constructed with ballasted track. The sleepers are embedded in the ballast. The wheel forces exerted by trains passing over them cause the ballast to become rounded, partially broken, and worn. This results in irregular settlements in the ballast and shifts in the lateral geometry of the track. Settlement of the ballast bed causes errors in the longitudinal height, superelevation (in curves), twist, gauge, and alignment. These errors, in turn, increase the acting forces, which in turn have a destructive effect on the ballast and the subsoil.

[0007] If certain limit values ​​or safety limits for these geometric dimensions, as defined by the railway authorities, are exceeded, maintenance work is planned and carried out. Track maintenance machines are used to eliminate and correct these geometric track defects. Before track maintenance work begins, the tracks are recorded for their geometric track position, and correction values ​​are derived from this data, which are then passed on to the machine to carry out the corrective measures.

[0008] To accept the corrective work, the machines are equipped with a trailing measuring system which checks the track position with regard to compliance with specified tolerances (AT516278A1).

[0009] Tamping machines with a fully hydraulic tamping drive (AT513973a1) record the ballast properties during operation using sensors integrated into the fully hydraulic tamping drive (AT515801 A1). By evaluating the force curve, the tamping speed, the tamping distance, and the time sequence, ballast bed parameters such as ballast bed hardness, compaction force, ballast bed stiffness, and ballast damping can be measured and specified for each tamped sleeper (AT520117A1).

[0010] The degree of ballast contamination can be determined using these parameters. When the contamination level exceeds 30% fines in the ballast, the track alignment can no longer be permanently corrected by tamping. The ballast must then be replaced or cleaned. Ballast bed cleaning machines are used for this purpose.

[0011] At significant differences in track stiffness (such as worn rail joints, transitions to bridges or tunnels), the high wheel-rail forces cause the sleepers to strike the ballast bed, resulting in destruction (and rounding) of the ballast. Such areas are often visible externally as white spots (emanating mineral dust). At these locations, driving dynamics cause the ballast to pulverize, and these spots are indicated by escaping mineral dust. These individual defects typically span a few meters, but tend to spread further and rapidly increase in error amplitude. This often results in safety-critical defects that require immediate or, better yet, preventative repair. These defects can be corrected by tamping machines operating in single-fault repair mode.

[0012] Varying settlement of the ballast bed results in hollow sleepers. These typically occur at intervals of 2-5 m (D0 band). They can also be remedied with track tamping machines.

[0013] Defect wavelengths in the range (D1 band) from 3 to 25 m typically indicate track defects caused by interaction with the vehicles (axle spacing in the bogies, bogie spacing or individual axle spacing, suspension and damping behavior of the running gear). The settlements are caused by the redistribution, abrasion, and breakage of the ballast grains. Track geometry defects in this wavelength range can be corrected using track tamping machines. It is known that a highly contaminated ballast bed exhibits high compaction forces. There is no movement space between the ballast grains because they are filled with fine material. This increases the compaction forces that must be applied to move and compact the ballast. At the same time, such contaminated track beds exhibit reduced durability of the corrected track geometry due to the low friction forces and interlocking between the ballast grains.

[0014] Longer-wave defects (D2 band) between 25 and 70 m are defects in the subgrade adjacent to the ballast. The cause is typically inadequate drainage or poor load-bearing capacity (waterlogged loam or clay, etc.), which is why longer-wave settlements occur. Drainage can be obstructed, for example, by the construction of a noise barrier that prevents water from flowing out of the ballast. The longer the wavelength of the defects, the more likely their cause is to be found further beneath the ballast layer. Although these defects can be leveled out using track tamping machines, they do not permanently correct the cause of the defect. Permanent correction is only possible through track bed cleaning or subgrade rehabilitation. For this purpose, a subgrade protection layer is introduced using a subgrade improvement machine (or other non-mechanized methods). If the track defects are due to inadequate drainage, then this must be improved.This can be done by dredging the railway ditches or by cleaning and flushing the drainage channels.

[0015] Defects with wavelengths greater than 70 m (D3 band) are due to inadequate subsoil bearing capacity. In these cases, the use of subgrade improvement machines to install a load-distributing subgrade protection layer or soil replacement can help. Experience has shown that this type of defect is often manifested by long-wave distortions.

[0016] The railway classifies track sections into line classes. These line classes are differentiated by the speed range within which they operate. Each line class is assigned its own limits for the standard deviations of track errors. This allocation is made for the track geometry parameters of direction, elevation, cross slope, twist, and gauge. There are limit values ​​that are used to plan track work (which should be carried out within a certain time frame) and critical limit values ​​that require immediate correction or restriction of operations (up to and including closure).

[0017] Measuring ballast bed properties using fully hydraulic tamping drives, on the other hand, records the properties of the ballast in great detail and with sleeper precision (AT515801 B1), thus allowing an objective assessment. Currently, track maintenance is planned based on track geometry measurements. Track measuring vehicles travel over the tracks at regular intervals and record their geometric position. The track position is usually divided into sections of around 200 m in length, and the standard deviation of the elevation, direction, cant, and twist are recorded. In addition to these statistical values, singular individual defects are also measured. If the statistical values ​​exceed certain comfort tolerances, maintenance work is planned and carried out.

[0018] The assessment of track defects is based on standard deviations or moving averages of the measurement signals. Determining the exact location, extent, type, and cause of the track defects remains uncertain or imprecise. The planning and execution of track work is usually based on predefined regulations or the experience of the responsible party. Ballast bed and subsurface properties are generally rarely considered in the assessment, as objective measurement data are usually unavailable.

[0019] Typically, 200-meter-long sections are evaluated, for which a track quality index (TQI) is specified. This is usually calculated from a weighted composite of the standard deviations of the various track geometry parameters or the longitudinal height alone.

[0020] The disadvantage of these methods is that they are not based on an analysis of the causes of the track defects and therefore often use unsuitable methods for correction. This leads to increased maintenance costs. For example, an incorrect method can lead to an increased and rapidly rising number of tamping operations. The correct method would have been to clean the ballast bed. This not only increases maintenance costs but also has a negative impact on the service life of the track components (ballast, rails, sleepers, etc.) and increases the LCC. The ballast can become extremely damaged after long periods of deposition. A large proportion of fines and organic material or soil pressed up from the subsoil may have filled the spaces between the ballast grains. Experience has shown that the track geometry of such ballast structures cannot be permanently corrected with track tamping machines.

[0021] It is also known from practice that isolated defects occur randomly distributed along the track. Approximately 40% of these localized defects can be permanently repaired. 60% of these defects recur within a short period of time. Tracks with good ballast condition are tamped on average approximately every four years. Isolated defects indicating ballast deterioration require maintenance approximately every one to three months. With each tamping, a portion of the ballast is damaged by the tamping tools due to the high compaction forces. Therefore, long work cycles are of great economic importance.

[0022] Areas of high bedding hardness (high stiffness) form high points in the track. The greater the stiffness fluctuations in the track bed, the greater the force interaction between wheel and rail, the higher the track load, and the faster the track geometry deteriorates. Singular, short faults in the track tend to expand longitudinally under the high dynamic forces acting on the track, increasing the height of the track fault and producing subsequent faults due to the excited track vehicles.

[0023] The application of artificial intelligence methods is state-of-the-art. The applied AI models can be divided into various categories. A distinction is made between artificial neural networks (ANNs), adaptive neural fuzzy interference systems (ANFIS), decision support systems (DSS), and artificial learning models. Artificial intelligence models have the ability to accurately model complex track geometry deterioration behavior, i.e., the type, location, extent, and wavelength of track geometry defects. AI models must be trained using training data sets. They are then tested using test data sets.

[0024] Using a comparative LCC analysis of various maintenance methods (tamping with increasingly shorter maintenance cycles instead of actually necessary track cleaning), their costs can be compared. To compare different maintenance strategies, so-called standard elements or standard kilometers are determined. This is done using, for example, the expert knowledge of railway engineers or actual determined figures and costs. The standard kilometers are divided into categories such as substructure quality, radii, traffic load, track beam shape, and number of tracks.

[0025] Description of the invention

[0026] The invention is based on the object of providing a method for the automatic evaluation and analysis of a series of measured track data, in particular a track geometry parameter and / or the ballast bed. The analysis should automatically determine the type, location, extent, and size of the track defects. The method should also be able to automatically generate suggestions for correcting the track defects and provide a general assessment of the track condition.

[0027] The invention solves the stated problem with the features of independent claim 1. Advantageous developments of the invention are presented in the subclaims.

[0028] The invention is characterized in that first a series of measurements of the track measurement data to be evaluated, which is assigned to a track section, is wavelet transformed with a plurality of wavelets of different wavelengths, and from these wavelet transforms a type of thermal image is created in which the wavelength over the position in a track and the wavelet transforms are provided as thermal information, and a wavelet power density spectrum is formed and, in addition, a signal strength diagram is calculated for different wavelength ranges, after which the local position, the extent and the assigned wavelength ranges of predominant track defects are determined from the thermal image in order to determine the type, position, extent and size of the track defects.

[0029] For this purpose, a series of measured track data (e.g., longitudinal height, direction, torsion, transverse height, ballast hardness, compaction force, ballast stiffness, ballast damping) is analyzed using the wavelet method and, if necessary, the fractal method with regard to its location and extent, as well as its wavelength content. It is important that, unlike Fourier transformations, wavelet transformations preserve the position information of the defects, allowing individual defects to be assigned unique positions on the track. In addition, a wavelet power density spectrum is calculated, and a type of thermal image is generated in which the location, extent, and size of the track defects are visible either in color or through (contour) lines of equal intensity.

[0030] In addition, a double-logarithmic fractal diagram can be generated, from which the track defects can be calculated wavelength-dependently (from the gradient and position within the wavelength range). Based on the analyzed wavelength range contained in the measurement series, the type, location, and extent of the track defects are automatically calculated. The intensity and size of the track defects are determined from the integral over the corresponding wavelength band of the wavelet power density spectrum. All of this serves to automatically evaluate the measured measurement series of a track geometry parameter and automatically determine the type, location, extent, and size of the track defects. The analysis automatically generates suggestions for correcting the track defects. The analysis also leads to a general assessment of the condition of the track in question.The invention creates an expert system that, using objective data, automatically allows the type, location, and extent of track defects to be classified. However, in addition to track position measurements, information about the ballast is also available for this evaluation. A possible mutual influence of the various measured variables is likely not captured by this expert system.

[0031] Therefore, this expert system is intended to train an artificial intelligence that integrates and takes these hidden relationships into the evaluation, thus leading to greater precision.

[0032] Wavelets were born from the idea of ​​dividing a track into shorter sections and using the Fourier transform to find the locations where short-wave track errors occur (short-path Fourier transform).

[0033] In contrast to the sine and cosine functions of the Fourier transform, wavelets exhibit locality in both the wavelength spectrum and the spatial spectrum. Put simply, the wavelet transform acts as if the signal were filtered piecewise using a bandpass filter of a specific bandwidth. This results in specific, locally limited error wavelength ranges. A simple track error signal yields a two-dimensional representation of the wavelengths over the space. Various wavelet functions are used. Typical examples are the Morlet wavelet and the Mexican hat.

[0034] For example, the Mexican hat wavelet is mathematically described as follows:

[0035] The wavelet transform is calculated as: and is called the wavelet transform of F(x) with respect to.

[0036] Using b as the shift factor, the wavelet is shifted through the function F(x) (e.g., the course of the measured bedding hardness along the track's length). Using a (scale factor) as the wavelength parameter, the wavelet's wavelength is varied. This results in a two-dimensional representation (the detected wavelengths are plotted against b, the position in the track).

[0037] By applying fractal theory, the so-called fractal number can be calculated from track measurement data. For this purpose, for a specific section of a railway line, for example, 200 m, the length of a polygonal line fitted into the measurement data is calculated with ever-decreasing increments. The length of this polygonal line is calculated as follows:

[0038] L(d) = n ■ d 1-Dr

[0039] L(d) = length of the polygon; d = polygon pitch; and Dr = fractal dimension.

[0040] If you take the logarithm of the equation, then: logL(d) = (1 - D r ) ■ log(d) + log(n)

[0041] In a double logarithmic representation, regression lines are calculated (section by section). The gradients are always negative (the finer the subdivision, the longer the polygon length) and result in k=1-Dr k ... fractal number

[0042] Studies show that the different gradients of the regression lines can be assigned to wavelength ranges and their causes. According to European standards, the typical wavelength ranges are divided into four categories. These can be assigned to the causes of track defects based on practical experience and measurements.

[0043] Table 1: Wavelength ranges and assignment of track properties The table shows the classification of the wavelength ranges and the assignment that causes the waviness.

[0044] The DO wavelength range is currently not usually recorded and evaluated by electronic inspection test runs. It is primarily caused by sleeper hollows and reactions between the sleeper and the rail fastening. Sleepers striking the ballast are most likely to form at 1.2 m and between 3 and 3.6 m (i.e., 2 and 5-6 times the usual sleeper pitch of 0.6 m).

[0045] Area D1 is the typical area where quasi-periodic track defects develop due to car body and bogie movements. The dynamic loads acting on the rail lead to ballast degradation. The result: ballast abrasion and ballast grain breakage. Maintenance measures include tamping or cleaning the ballast, and replacing the overburden with new ballast. Area D2 occurs in the mixed zone between ballast and subsoil and in the subsoil. This area can also be improved by tamping and track cleaning.

[0046] Area D3 is due to subsurface problems; the long-wave fluctuations are often characterized by torsional fluctuations. Area D3 is characterized by insufficient load-bearing capacity. Possible causes include inadequate drainage, poor underlying soil (loam, clay, peat), unsuitable subgrade material, or a missing or insufficiently weak subgrade protection layer. This track defect can be remedied by correcting the drainage problem, improving and rehabilitating the subgrade, or replacing the soil.

[0047] According to the invention, wavelet and fractal analysis is applied to the recorded measurement series. The resulting expert system is used to train an artificial intelligence system.

[0048] The Kl model then automatically provides the location, extent, and type of track defect. It also provides information on the overall quality of the track and suggests the optimal maintenance method based on technical and economic calculations.

[0049] Brief description of the invention

[0050] The invention is illustrated schematically in an exemplary embodiment in the drawing. It shows:

[0051] Fig. 1 Representation of the Mexican hat wavelet,

[0052] Fig. 2 a fractal plot of the track defect spectrum before and after track bed cleaning

[0053] Fig. 3 an evaluation of a track error measurement series using wavelet analysis Ways to implement the invention

[0054] Fig. 1 shows an example of the shape of a wavelet—the so-called Mexican hat. For analysis, the wavelet is moved through the measurement series. Equal wavelength components of the signal match and generate a corresponding signal. Since this analysis is performed with consecutive passes of different wavelengths, a two-dimensional plot results.

[0055] Fig. 2 shows the result of the fractal analysis of a track section before and after track cleaning. The influence is clearly visible in the medium-wave range 5, 6 (2-15 m), while in the long-wave range it remains virtually unaffected by the ballast bed cleaning. The shallow gradient in the long-wave range 7 indicates that the subsoil has sufficient load-bearing capacity and is sound. Track cleaning did result in an improvement. However, it had no influence on the long-wave range. By tracking the change in the fractal number over the track load or operating time, conclusions can be drawn about the remaining service life of the ballast or the rate of deterioration. Likewise, larger gradients in the long-wave range indicate subsoil problems. A characteristic feature is that the fractal analysis can be performed for any length of track, for example, even for entire routes or an entire track network.It provides numerical values ​​that are independent of the length of the analyzed pattern.

[0056] Contaminated ballast remains contaminated even after tamping, and the subsurface conditions remain unchanged. Individual lines 5, 6, and 7 indicate defects in the corresponding wavelength range. The steeper the lines 5 and 6, the greater the influence of the defects. Fractal analysis is used as a second independent method for determining the defect wavelength bands. While it provides the type and intensity of the defects, it does not provide any indication of their location. It can only determine this information for the analyzed section and state that track defects with this defect wavelength component are prioritized in this section. Fig. 3 shows the evaluation of a measurement signal using wavelet analysis.Measurement signal 1 (upper image area) can be a geometric measurement (longitudinal height, direction, torsion, track gauge, transverse height) or a physical one (rail temperature, ballast bed hardness, ballast bed stiffness, ballast damping, or compaction force at the end of tamping). The image shows the TQI (track quality index), which was calculated, for example, from weighted standard deviations of the track geometric and physical measurement parameters. The higher the TQI, the poorer the track. The TQI values ​​must also be specified for each track class. A high-speed track operated at 300 km / h has tighter tolerances than a freight car track with a maximum speed of 80 km / h.

[0057] Below the signal curve, the two-dimensional thermal image 2 calculated using wavelets (Morlet) is shown. If this is displayed in color, the location and extent of the defect intensities can be clearly seen. The wavelength is plotted vertically and the position on the track horizontally. As an example, 400m sections are evaluated so that defect wavelengths up to 200m can still be analyzed. The analysis in the image shown takes into account defect wavelengths up to 150m and thus covers all four wavelength bands of interest from D0 to D3. The intensity of the defects is shown in the thermal image as contour lines or in the form of color gradations. For example, defect J in area G of signal 1 appears in thermal image 2 in the D1 band at a wavelength of around 20m. This is typically a defect caused by the condition of the ballast, which can be corrected by tamping.The fault can be located in the range of 250 to 350 m. Since a fault also occurs at 220 m, a plugging of 200 to 350 m is the best choice. In the D2 and D3 bands, components can be seen that indicate a drainage problem and a load-bearing capacity problem in this area. This can be seen as the actual cause of the track faults occurring in this area. The lower diagram shows the fault intensities for the three wavelength bands D0 to D2. This makes it easier to assign the location and extent as well as the fault intensity. To the right of the thermal image, the wavelet power density spectrum LD is shown. The wavelength is plotted vertically and the power density horizontally. The wavelength bands are plotted in the diagram. To determine the average power density in a wavelength band, the integral (plotted as A) is calculated. This is carried out for all four bands.The detection of the maximum values ​​is also important because they indicate the dominant track defect wavelengths. Using this method, individual defects (in the image, for example, with an extension of Ax) can also be detected and their location and extent can be specified.

[0058] According to Table 1 above, the type of defects can be assigned and, based on this, the optimal maintenance can be determined. Using comparative LCC analysis, it can be explained why, for example, tamping (as in this case) is more cost-effective than track cleaning over this short section.

[0059] Mark B, for example, shows a short-wavelength track defect in the 40m range, which is due to hollow sleepers. At the same time, an image of the PSD spectrum shows that the intensity is low, and therefore tamping is not yet necessary in this area. Mark F identifies a weakness in the boundary layer at a wavelength of approximately 35m. It would be advisable to examine this section for effective drainage.

Claims

Patent claims 1 . Method for the automatic evaluation of wavelet-transformed track measurement data (1) of the track geometry and / or the ballast bed with a computing device, characterized in that firstly a measurement series of the track measurement data (1) to be evaluated, which is assigned to a track section, is wavelet-transformed with a plurality of wavelets of different wavelengths, and from these wavelet-transformed data, a type of thermal image is created in which the wavelength over the position in a track and the wavelet-transformed data are provided as thermal information, and a wavelet power density spectrum (3) is formed, and in addition a signal strength diagram (4) is calculated for different wavelength ranges (D0, D1, D2, D3), after which the local position (B, C, D, F), the extent and the assigned wavelength ranges (E, D0, D1, D2, D3) of predominant track defects are determined from the thermal image in order to determine the type, position, extent and size of the track defects,in particular from the contour lines of the thermal image.

2. Method according to claim 1, characterized in that, in order to determine the intensity of the track errors, integrals (A) of the power densities over the wavelength, in particular over wavelength ranges (D0 - D3), are formed in the wavelet power density spectrum (3).

3. Method according to claim 1 or 2, characterized in that determined track errors are assigned to wavelength ranges (D0 - D3).

4. Method according to claim 2 or 3, characterized in that the intensity (signal strength, A) of the track defects is also determined according to the local extent and position of the thermal information in the thermal image (2, C, D, E).

5. Method according to one of claims 1 to 4, characterized in that the position and size of individual defects (D, AX ) are determined from the thermal image.

6. Method according to one of claims 1 to 5, characterized in that the series of track measurement data (1) is analyzed with regard to its wavelength content by means of the fractal analysis method (Fig. 2), track defects being automatically classified with regard to the wavelength ranges (D0, D1, D2, D3) in accordance with the analyzed range of wavelengths, the size and intensity of the track defects being determined and the condition of the track (TQI) being calculated in accordance with the gradient of the fractal lines (5, 6, 7).

7. Method according to one of claims 1 to 6, characterized in that an artificial intelligence is trained with the expert system thus formed, which automatically learns to determine track errors from the data provided (1, 2, 3, 4, TQI).

8. Method according to claims 1 to 7, characterized in that suggestions for correcting the track defects are generated as a result of the evaluation.

9. Method according to claims 1 to 8, characterized in that the results of the evaluation and suggestions for correcting the track errors are automatically summarized in a report (Fig. 3).

10. Method according to claims 1 to 9, characterized in that the expected durability of tamping work is calculated and estimated from the results of the evaluation.

Images