Grinding wheel cutting prediction method and device, storage medium and computer program

Abstract

The invention discloses a grinding wheel cutting prediction method and device, a storage medium and a computer program. The method comprises the steps that physical characteristic data of a grinding wheel and set values of grinding parameters are obtained; the grinding amount of the profile area, ground by the grinding wheel, of the steel rail is obtained when the set values of the different grinding parameters are obtained; constructing a grinding wheel cutting initial prediction model based on a machine learning algorithm, taking the physical characteristic data of the grinding wheel and the set value of the grinding parameter as the input of the grinding wheel cutting initial prediction model, taking the grinding amount as the output of the grinding wheel cutting initial prediction model, and training the grinding wheel cutting initial prediction model to obtain the grinding wheel cutting initial prediction model. Obtaining a grinding wheel cutting prediction model; and predicting a to-be-measured grinding wheel by using the grinding wheel cutting prediction model to obtain the predicted grinding amount of the to-be-measured grinding wheel. The grinding wheel is predicted through the grinding wheel cutting prediction model, quantitative evaluation of the cutting capacity of the grinding wheel is achieved, and the method is more objective and accurate.

Description

Technical Field

[0001] The present disclosure relates to the technical field of rail grinding, and in particular to a grinding wheel cutting prediction method, device, storage medium and computer program. Background Art

[0002] As the infrastructure of railway transportation, the durability and safety of rails are crucial to the normal operation of the entire railway system. However, due to the load of railway trains and environmental erosion, the surface of the rails will suffer from wear, deformation and defects. The existence of these rail damages will affect the stability and operating efficiency of the train, and may require more frequent replacement of rails, increasing line operating costs. In order to maintain the performance of the rails, extend their service life and reduce railway operating costs, the rails need to be polished and maintained regularly.

[0003] Rail grinding is a highly practical railway maintenance method. Its main purpose is to remove damage on the rail surface and restore the shape and smoothness of the rail to ensure the safe operation of the train. In the rail grinding process, the cutting ability of the grinding wheel has an important influence on the grinding efficiency and quality. The evaluation method of the cutting ability of the grinding wheel is related to its applicability in the grinding process, which is of great significance in the maintenance of railway infrastructure.

[0004] Currently, the evaluation of the cutting ability of grinding wheels is mainly based on experience and qualitative analysis. Specifically, the physical properties of the grinding wheel are usually examined, such as hardness, sand grain size, structure type, and performance during the grinding process, such as the degree of wear of the grinding wheel and the quality of the rail surface after grinding. However, this evaluation method has the following problems: First, the experience-based evaluation method is often highly subjective and difficult to quantify, resulting in poor reproducibility and comparability of the evaluation results. Second, the existing qualitative analysis methods are difficult to take into account all factors that may affect the cutting ability of the grinding wheel, which may lead to deviations in the evaluation results.

[0005] In addition, with the development of information technology, research on intelligent rail grinding technology has been carried out one after another. Intelligent rail grinding technology refers to the use of advanced technologies such as sensors, image processing, and data analysis to achieve intelligent control and optimization of the rail grinding process. Compared with the traditional grinding technology, which requires a lot of manpower and time, and it is difficult to ensure consistency and precision, intelligent grinding technology can automatically perform grinding operations, improve grinding efficiency and consistency, reduce downtime in operation, and improve the operating efficiency of the railway system. In the intelligent rail grinding technology, the capacity of the rail grinding wheel needs to be quantified. However, the results obtained by the existing evaluation methods are difficult to apply to the specific links of rail grinding, and the methods and technologies for quantifying the cutting capacity of the rail grinding wheel have not been realized. Proposing a quantitative evaluation method for the cutting capacity of the rail grinding wheel is of great engineering significance for studying the intelligent rail grinding technology and improving the efficiency and quality of maintenance and repair operations. Summary of the invention

[0006] Based on the above technical problems, the present disclosure provides a grinding wheel cutting prediction method, device, storage medium and computer program.

[0007] In a first aspect, the present disclosure provides a grinding wheel cutting prediction method, comprising:

[0008] Obtain physical characteristic data of the grinding wheel and setting values ​​of grinding parameters;

[0009] Obtaining the grinding amount of the profile area of ​​the rail ground by the grinding wheel when different grinding parameter setting values ​​are set;

[0010] Building a grinding wheel cutting initial prediction model based on a machine learning algorithm, taking the physical characteristic data of the grinding wheel and the set values ​​of the grinding parameters as inputs of the grinding wheel cutting initial prediction model, taking the grinding amount as output of the grinding wheel cutting initial prediction model, training the grinding wheel cutting initial prediction model, and obtaining a grinding wheel cutting prediction model;

[0011] The grinding wheel cutting prediction model is used to predict the grinding wheel to be measured, and the predicted grinding amount of the grinding wheel to be measured is obtained.

[0012] In some embodiments, the step of obtaining the grinding amount of the profile area of ​​the rail ground by the grinding wheel at different setting values ​​of the grinding parameters includes:

[0013] For each setting value of the grinding parameter, obtaining the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel;

[0014] The grinding amount of the rail profile area ground by the grinding wheel is determined according to the difference between the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel.

[0015] In some embodiments, for each setting value of the grinding parameter, the step of obtaining the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel comprises:

[0016] Dividing the rail profile into a plurality of sub-areas;

[0017] Obtaining the original profile area of ​​each of the sub-regions before the rail is ground by the grinding wheel;

[0018] For each setting value of the grinding parameter, obtaining the grinding profile area of ​​each sub-region after the rail is ground by the grinding wheel;

[0019] The step of determining the grinding amount of the profile area of ​​the rail ground by the grinding wheel according to the difference between the profile area of ​​the rail before the rail is ground by the grinding wheel and the profile area of ​​the rail after the rail is ground by the grinding wheel comprises:

[0020] Calculating the difference between the original contour area and the polished contour area of ​​each sub-region to obtain the polishing amount of the contour area of ​​each sub-region;

[0021] The grinding amount of the profile area of ​​the rail ground by the grinding wheel is determined based on the grinding amount of the profile area of ​​each of the sub-regions.

[0022] In some embodiments, the sub-region includes at least one of a gauge angle region, a wheel-rail contact region, a rail top center region, and a non-working edge region.

[0023] In some embodiments, the grinding parameters of the grinding wheel include at least one parameter of a grinding angle, a grinding speed, and a grinding power.

[0024] In some embodiments, the physical characteristic data of the grinding wheel includes at least one of hardness, size, and material composition of the grinding wheel.

[0025] In some embodiments, the step of constructing an initial prediction model for grinding wheel cutting based on a machine learning algorithm, taking the physical characteristic data of the grinding wheel and the set values ​​of the grinding parameters as inputs of the initial prediction model for grinding wheel cutting, taking the grinding amount as outputs of the initial prediction model for grinding wheel cutting, and training the initial prediction model for grinding wheel cutting to obtain the prediction model for grinding wheel cutting comprises:

[0026] Constructing different initial prediction models for grinding wheel cutting according to the categories and quantities of the physical characteristics of the grinding wheel and the categories and quantities of the grinding parameters;

[0027] For any of the grinding wheel cutting initial prediction models, the physical characteristic data of the grinding wheel and the grinding parameter value are used as inputs of the grinding wheel cutting initial prediction model, and the corresponding grinding amount is used as output of the grinding wheel cutting initial prediction model, and the grinding wheel cutting initial prediction model is trained to obtain a grinding wheel cutting prediction model;

[0028] The step of predicting the cutting ability of the grinding wheel by using the grinding wheel cutting evaluation model comprises:

[0029] According to the categories and quantities of the physical characteristics of the grinding wheel to be tested and the categories and quantities of the grinding parameters, the corresponding grinding wheel cutting prediction model is selected for prediction.

[0030] In a second aspect, the present disclosure provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the method described in the above aspect when executing the computer program.

[0031] In a third aspect, the present disclosure provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the method described in the above aspects when executed by a processor.

[0032] In a fourth aspect, the present disclosure provides a computer program product, including a computer program, which implements the steps of the method described in the above aspects when executed by a processor.

[0033] The present invention provides a grinding wheel cutting prediction method, device, storage medium and computer program. The initial grinding wheel cutting prediction model is trained based on the physical characteristic data of the grinding wheel, the set values ​​of the grinding parameters and the grinding amount of the profile area of ​​the rail grinded by the grinding wheel to obtain the grinding wheel cutting prediction model. The grinding wheel is predicted by the grinding wheel cutting prediction model to achieve a quantitative evaluation of the cutting ability of the grinding wheel, which is more objective and accurate. Moreover, by accurately evaluating the cutting ability of the grinding wheel, it is convenient to select a suitable grinding method to grind the rail, which can improve the efficiency and quality of rail grinding. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The present disclosure will be described in more detail below based on embodiments and with reference to the accompanying drawings:

[0035] Figure 1 A schematic diagram of a process flow of a grinding wheel cutting prediction method provided in an embodiment of the present disclosure;

[0036] Figure 2 A schematic diagram of a process flow of a grinding wheel cutting prediction method provided in an embodiment of the present disclosure;

[0037] Figure 3A simplified flow chart of a grinding wheel cutting prediction method provided in an embodiment of the present disclosure;

[0038] Figure 4 A profile diagram of a rail before being ground by a grinding wheel provided in an embodiment of the present disclosure;

[0039] Figure 5 A diagram showing the difference in rail profiles before and after the rail is ground by a grinding wheel according to an embodiment of the present disclosure.

[0040] In the drawings, the same reference numerals are used for the same components, and the drawings are not drawn to scale. DETAILED DESCRIPTION

[0041] In order to enable those skilled in the art to better understand the technical solution of the present disclosure, and to fully understand and implement how the present disclosure applies technical means to solve technical problems and achieve the corresponding technical effects, the technical solution in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only embodiments of a part of the present disclosure, not all of the embodiments. The embodiments of the present disclosure and the various features in the embodiments can be combined with each other without conflict, and the technical solutions formed are all within the scope of protection of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present disclosure.

[0042] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0043] It should be noted that the steps shown in the flowcharts of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and that, although a logical order is shown in the flowcharts, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0044] Embodiment 1

[0045] Figure 1 A schematic diagram of a grinding wheel cutting prediction method provided in an embodiment of the present disclosure. Figure 1 As shown, a grinding wheel cutting prediction method comprises:

[0046] Step 110, obtaining physical characteristic data of the grinding wheel and setting values ​​of grinding parameters.

[0047] In this embodiment, the type or specification of the grinding wheel is determined to be different according to the different physical characteristic data of the grinding wheel. The physical characteristics of the grinding wheel are used to describe the physical properties of the grinding wheel, which may include the size, shape, quality, weight, hardness, material composition, etc. of the grinding wheel.

[0048] In one embodiment, the physical characteristic data of the grinding wheel includes hardness, size, material composition and design characteristics of the grinding wheel.

[0049] The set value of the grinding parameter refers to the set value of each grinding parameter of the grinding wheel when the grinding wheel is used for grinding operations. The grinding parameters may include the angle setting, motion trajectory, grinding speed, grinding power, and number of grinding passes of the grinding wheel. Among them, the grinding mode can be determined according to the combination of multiple grinding parameters and different set values ​​of each grinding parameter. That is, different grinding modes refer to different set values ​​of grinding parameters such as the angle setting, motion trajectory, grinding speed, grinding power, and number of grinding passes of the grinding wheel when the grinding wheel is used for processing operations.

[0050] Furthermore, the setting values ​​of the grinding parameters of the grinding wheel can be pre-set with several preset values, and the various grinding modes are determined according to the free combination of the setting values ​​of the grinding parameters. For example, the grinding parameters include grinding angle, grinding speed and grinding power, wherein the specific setting values ​​of the grinding angle include those located in the gauge angle area, in the wheel-rail contact area, in the center area of ​​the rail top and in the non-working edge area; the specific setting values ​​of the grinding speed include values ​​such as 12km / h, 14km / h, 16km / h, 18km / h, 20km / h, etc.; the specific setting values ​​of the grinding power include values ​​such as 60%, 65%, 70%, 75%, 80% of the rated power, which are not listed in this article.

[0051] Step 120, obtaining the grinding amount of the profile area of ​​the rail ground by the grinding wheel when different grinding parameter setting values ​​are set.

[0052] Rail profile refers to the cross-sectional profile of the rail. However, the profile area of ​​the rail refers to the plane area occupied by the shape of the rail in the cross section.

[0053] In one embodiment, the profile of the railway rail is an I-shape, and the profile area thereof includes the sum of the areas of the rail head, the rail waist and the rail bottom.

[0054] The grinding amount of the profile area of ​​the rail when it is ground by a grinding wheel having the same physical characteristic data but different setting values ​​of the grinding parameters is different; and the grinding amount of the profile area of ​​the rail when it is ground by multiple grinding wheels having different physical characteristic data but the same setting values ​​of the grinding parameters is also different.

[0055] In this embodiment, the grinding amount of the profile area of ​​the rail ground by the grinding wheel at different setting values ​​of the grinding parameters is obtained.

[0056] In one embodiment, the physical characteristic data of the grinding wheel, the setting values ​​of the grinding parameters and the corresponding grinding amount are taken as a set of sample data, and multiple sets of physical characteristic data of the grinding wheel, the setting values ​​of the grinding parameters and the corresponding grinding amount are obtained to obtain multiple sets of sample data.

[0057] Step 130, constructing an initial prediction model for grinding wheel cutting based on a machine learning algorithm, taking the physical characteristic data of the grinding wheel and the set values ​​of the grinding parameters as inputs of the initial prediction model for grinding wheel cutting, taking the grinding amount as output of the initial prediction model for grinding wheel cutting, training the initial prediction model for grinding wheel cutting, and obtaining a grinding wheel cutting prediction model.

[0058] In one embodiment, different grinding wheel cutting initial prediction models are constructed based on different types of machine learning algorithms. For example, the grinding wheel cutting initial prediction model can be constructed based on machine learning algorithms such as multivariate linear regression algorithm, neural network, etc. Among them, based on the same type of machine learning algorithm, the constructed grinding wheel cutting initial prediction model is also different according to the physical characteristics of the grinding wheel and the number of grinding parameters.

[0059] In this embodiment, an initial prediction model for grinding wheel cutting is constructed based on a machine learning algorithm, the physical characteristic data of the grinding wheel and the set values ​​of the grinding parameters are used as the input of the initial prediction model for grinding wheel cutting, the grinding amount is used as the output of the initial prediction model for grinding wheel cutting, and the initial prediction model for grinding wheel cutting is trained using corresponding sample data to obtain a grinding wheel cutting prediction model.

[0060] Step 140: predicting the grinding wheel to be measured by using the grinding wheel cutting prediction model to obtain a predicted grinding amount of the grinding wheel to be measured.

[0061] In this embodiment, the trained grinding wheel cutting prediction model is used to predict the grinding wheel to be tested, so as to obtain the predicted grinding amount of the grinding wheel to be tested, and then the cutting ability of the grinding wheel to be tested is quantitatively evaluated.

[0062] In this embodiment, the initial prediction model for grinding wheel cutting is trained based on the physical characteristic data of the grinding wheel, the set values ​​of the grinding parameters and the grinding amount of the profile area of ​​the rail ground by the grinding wheel to obtain a grinding wheel cutting prediction model. The grinding wheel is predicted by the grinding wheel cutting prediction model to achieve a quantitative evaluation of the cutting ability of the grinding wheel, which is more objective and accurate. By accurately evaluating the cutting ability of the grinding wheel, it is convenient to select a suitable grinding method to grind the rail, which can improve the efficiency and quality of rail grinding.

[0063] Embodiment 2

[0064] On the basis of the above embodiment, the step of obtaining the grinding amount of the profile area of ​​the rail ground by the grinding wheel when different grinding parameter setting values ​​are set includes:

[0065] For each setting value of the grinding parameter, obtaining the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel;

[0066] The grinding amount of the rail profile area ground by the grinding wheel is determined according to the difference between the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel.

[0067] In this embodiment, first, the rail profile area before the rail is ground by the grinding wheel is obtained; after the rail is ground by the grinding wheel with a preset grinding parameter setting value, the rail profile area after the rail is ground by the grinding wheel is obtained; according to the difference between the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel, the grinding amount of the rail profile area ground by the grinding wheel is determined.

[0068] In one embodiment, the rail profile data before the rail is ground by the grinding wheel and the rail profile data after the rail is ground by the grinding wheel are measured using a vehicle-mounted profile meter.

[0069] Embodiment 3

[0070] On the basis of the above embodiment, the step of obtaining the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel for each setting value of the grinding parameter comprises:

[0071] Dividing the rail profile into a plurality of sub-areas;

[0072] Obtaining the original profile area of ​​each of the sub-regions before the rail is ground by the grinding wheel;

[0073] For each setting value of the grinding parameter, obtaining the grinding profile area of ​​each sub-region after the rail is ground by the grinding wheel;

[0074] The step of determining the grinding amount of the profile area of ​​the rail ground by the grinding wheel according to the difference between the profile area of ​​the rail before the rail is ground by the grinding wheel and the profile area of ​​the rail after the rail is ground by the grinding wheel comprises:

[0075] Calculating the difference between the original contour area and the polished contour area of ​​each sub-region to obtain the polishing amount of the contour area of ​​each sub-region;

[0076] The grinding amount of the profile area of ​​the rail ground by the grinding wheel is determined based on the grinding amount of the profile area of ​​each of the sub-regions.

[0077] In this embodiment, the rail profile is divided into a plurality of sub-areas, and the grinding amount of the profile area of ​​each sub-area after being ground by the grinding wheel is calculated respectively, so as to obtain the grinding amount of the profile area of ​​the entire rail after being ground by the grinding wheel. In this embodiment, by dividing the rail profile into a plurality of areas, it is convenient to count the grinding amount of the profile area of ​​the rail.

[0078] In one embodiment, the rail profiles are classified based on the design characteristics of the rails or the wear degree of the rails.

[0079] In this embodiment, the original profile area of ​​each sub-region of the rail before being ground by a grinding wheel and the polished profile area of ​​each sub-region of the rail after being ground by a grinding wheel are obtained respectively, and the difference between the original profile area and the polished profile area is calculated, so that the grinding amount of the profile area of ​​the sub-region of the rail can be determined, and then the grinding amount of the profile area of ​​the entire rail ground by the grinding wheel can be determined.

[0080] Embodiment 4

[0081] Based on the above embodiment, the sub-region includes at least one region among the gauge angle region, the wheel-rail contact region, the rail top center region and the non-working edge region.

[0082] In this embodiment, the rail is divided into multiple sub-areas based on the relationship between the rail and the wheel-rail. The multiple sub-areas divided into the rail include at least one of the gauge angle area, the wheel-rail contact area, the rail top center area and the non-working edge area. The gauge angle area refers to the connection position area between the rail top and the rail side, the wheel-rail contact area refers to the area where the wheel flange root contacts the rail gauge angle during the wheel-rail contact, the rail top center area refers to the central part of the rail top, that is, the area where the wheel tread center contacts the rail top surface, and the non-working edge area refers to the non-working edge of the rail, that is, the non-contact side and its vicinity.

[0083] Of course, in other embodiments, the rails may be divided into regions according to other division principles, which is not limited herein.

[0084] In one embodiment, the gauge angle area, the wheel-rail contact area, the rail top center area and the non-working edge area are all defined as fan-shaped areas determined with the rail top center of the rail as the center of the circle. Specifically, the position of the gauge angle area is determined by two rays with angles of 15° and 60° with the center of the circle; the position of the wheel-rail contact area is determined by two rays with angles of 5° and 15° with the center of the circle; the position of the rail top center area is determined by two rays with angles of 0° and 5° with the center of the circle; and the position of the non-working edge area is determined by two rays with angles of -20° and 0° with the center of the circle.

[0085] Embodiment 5

[0086] Based on the above embodiment, the grinding parameters of the grinding wheel include at least one parameter of a grinding angle, a grinding speed and a grinding power.

[0087] The grinding parameters of the grinding wheel directly affect the cutting effect of the grinding wheel and the processing quality of the workpiece to be ground. In one embodiment, the grinding parameters of the grinding wheel include grinding angle, grinding speed, grinding power, number of grinding passes and grinding time, etc., wherein the grinding angle refers to which surface of the rail is ground by the grinding wheel, and the grinding power refers to the percentage of the power used by the grinding wheel during grinding relative to the rated power.

[0088] In this embodiment, the grinding parameters of the grinding wheel include grinding angle, grinding speed and grinding power. The rail is divided into multiple areas, including at least one of the gauge angle area, wheel-rail contact area, rail top center area and non-working edge area; the gauge angle area, wheel-rail contact area, rail top center area and non-working edge area are defined as fan-shaped areas with the center of the rail top of the rail as the center of the circle. Specifically, the position of the gauge angle area is determined by two rays with angles of 15° and 60° with the center of the circle; the position of the wheel-rail contact area is determined by two rays with angles of 5° and 15° with the center of the circle; the position of the rail top center area is determined by two rays with angles of 0° and 5° with the center of the circle; the position of the non-working edge area is determined by two rays with angles of -20° and 0° with the center of the circle. Correspondingly, the grinding angle refers to the area in which the grinding wheel is grinding.

[0089] Embodiment 6

[0090] Based on the above embodiment, the physical characteristic data of the grinding wheel includes at least one of the hardness, size and material composition of the grinding wheel.

[0091] The physical characteristics of the grinding wheel are used to describe the physical properties of the grinding wheel. The physical characteristic data may include the size, shape, mass, weight, hardness, material composition, etc. of the grinding wheel.

[0092] In one embodiment, the physical characteristic data of the grinding wheel includes the hardness, size and material composition of the grinding wheel.

[0093] In one embodiment, the hardness of the grinding wheel is measured by a grinding wheel hardness tester, and the diameter, width and other dimensional information of the grinding wheel are measured by a grinding wheel size measuring instrument and other equipment; and the material composition of the grinding wheel is obtained by a material analysis instrument.

[0094] Embodiment 7

[0095] On the basis of the above embodiment, the initial prediction model for grinding wheel cutting is constructed based on the machine learning algorithm, the physical characteristic data of the grinding wheel and the set value of the grinding parameter are used as the input of the initial prediction model for grinding wheel cutting, the grinding amount is used as the output of the initial prediction model for grinding wheel cutting, the initial prediction model for grinding wheel cutting is trained, and the steps of obtaining the prediction model for grinding wheel cutting include:

[0096] Constructing different initial prediction models for grinding wheel cutting according to the categories and quantities of the physical characteristics of the grinding wheel and the categories and quantities of the grinding parameters;

[0097] For any of the grinding wheel cutting initial prediction models, the physical characteristic data of the grinding wheel and the grinding parameter value are used as inputs of the grinding wheel cutting initial prediction model, and the corresponding grinding amount is used as output of the grinding wheel cutting initial prediction model, and the grinding wheel cutting initial prediction model is trained to obtain a grinding wheel cutting prediction model;

[0098] The step of predicting the cutting ability of the grinding wheel by using the grinding wheel cutting evaluation model comprises:

[0099] According to the categories and quantities of the physical characteristics of the grinding wheel to be tested and the categories and quantities of the grinding parameters, the corresponding grinding wheel cutting prediction model is selected for prediction.

[0100] In this embodiment, the constructed initial prediction model for grinding wheel cutting is different according to the category and quantity of the physical characteristics of the grinding wheel and the category and quantity of the grinding parameters. For example, the number of physical characteristics of the grinding wheel is 3, including hardness, size and material; the number of grinding parameters of the grinding wheel is 3, including grinding angle, grinding speed and grinding power. Based on the category and quantity of the physical characteristics of the grinding wheel and the category and quantity of the grinding parameters, a first initial prediction model for grinding wheel cutting is established. The number of physical characteristics of the grinding wheel with the same category and number of physical characteristics and the set values ​​of the grinding parameters with the same category and number of grinding parameters are used as the input of the first initial prediction model for grinding wheel cutting, and the corresponding grinding amount is used as the output of the first initial prediction model for grinding wheel cutting. The first initial prediction model for grinding wheel cutting is trained to obtain a grinding wheel cutting prediction model. When the number of physical characteristics of the grinding wheel is There are 3 of them, including hardness, size and material; there are 4 grinding parameters of the grinding wheel, including grinding angle, grinding speed, grinding power and number of grinding passes. Based on the category and quantity of the physical characteristics of the grinding wheel and the category and quantity of the grinding parameters, a second grinding wheel cutting initial prediction model is established. The category and number of physical characteristics of the grinding wheel with the same physical characteristics and the category and number of the grinding parameters and the set values ​​of the grinding parameters are used as the input of the second grinding wheel cutting initial prediction model, and the corresponding grinding amount is used as the output of the second grinding wheel cutting initial prediction model. The first grinding wheel cutting initial prediction model is trained to obtain a grinding wheel cutting prediction model. By analogy, multiple grinding wheel cutting prediction models can be obtained.

[0101] When the cutting ability of the grinding wheel to be tested needs to be predicted, the corresponding grinding wheel cutting prediction model is selected for prediction according to the category and quantity of the physical characteristics of the grinding wheel to be tested and the category and quantity of the grinding parameters.

[0102] Embodiment 8

[0103] Based on the above embodiments, this embodiment provides an application example. Figures 2 to 5 shown.

[0104] like Figures 2 to 3 As shown, the grinding wheel cutting prediction method includes:

[0105] Step 1: Measure the grinding wheel and record its physical properties.

[0106] In this embodiment, the grinding wheel is measured and its physical properties are recorded, wherein the physical properties of the grinding wheel are used to describe the physical attributes of the grinding wheel, including but not limited to hardness, size, material, and design characteristics.

[0107] Among them, the physical property measurement of the grinding wheel is mainly carried out by using equipment such as a grinding wheel hardness tester and a grinding wheel size measuring instrument, so as to obtain the correlation data between the cutting ability and the physical properties of the grinding wheel. For example, the hardness of the grinding wheel is measured by a hardness tester, the diameter, width and other dimensional information of the grinding wheel is measured by a measuring instrument, and the material composition of the grinding wheel is obtained by a material analysis instrument.

[0108] Step 2, setting the rail grinding mode, including different combinations of setting values ​​for each grinding parameter, and using a grinding wheel to grind the rail.

[0109] The grinding mode refers to the setting of grinding parameters such as the angle setting, motion trajectory, grinding speed, grinding power and number of grinding passes of the grinding wheel when the grinding wheel is used for processing. That is, the rail grinding mode is a different combination of the values ​​of each grinding parameter, and the rail is ground based on each rail grinding mode.

[0110] In this embodiment, the grinding parameters include grinding angle, grinding speed and grinding power. The values ​​of each grinding parameter are combined based on the orthogonal test method, so that the optimal combination of multiple factors can be obtained through a small number of experiments. Specifically, several possible values ​​of each parameter are pre-set. For example, the specific setting values ​​of the grinding angle include those located in the gauge angle area, the wheel-rail contact area, the center area of ​​the rail top and the non-working edge area; the specific setting values ​​of the grinding speed include values ​​such as 12km / h, 14km / h, 16km / h, 18km / h, and 20km / h; the specific setting values ​​of the grinding power include values ​​such as 60%, 65%, 70%, 75%, and 80% of the rated power, which are not listed in this article. Then, the experiment is designed based on the orthogonal table, and the main factors affecting the grinding effect and the optimal level combination of these factors are found through the experimental results.

[0111] Step 3: Use the vehicle-mounted profiler to record the rail profile data before and after grinding.

[0112] Rail profile refers to the cross-sectional profile of the rail. However, the profile area of ​​the rail refers to the plane area occupied by the shape of the rail in the cross section.

[0113] In one embodiment, the profile of the railway rail is an I-shape, and the profile area thereof includes the sum of the areas of the rail head, the rail waist and the rail bottom.

[0114] The grinding amount of the profile area of ​​the rail when it is ground by a grinding wheel having the same physical characteristic data but different setting values ​​of the grinding parameters is different; and the grinding amount of the profile area of ​​the rail when it is ground by multiple grinding wheels having different physical characteristic data but the same setting values ​​of the grinding parameters is also different.

[0115] In this embodiment, a vehicle-mounted profiler is used to record the rail profile data before and after grinding. Figure 4The figure shows the profile of the rail before it is ground by a grinding wheel.

[0116] Specifically, the rails before grinding are measured using a vehicle-mounted profilometer to obtain original rail profile data; the rails are ground based on a grinding wheel in any grinding mode; after grinding, the rails are measured again using the vehicle-mounted profilometer to obtain the rail profile data after grinding.

[0117] Step 4: Calculate the difference in rail profile area before and after grinding based on the data from the on-board profilometer.

[0118] like Figure 5 The figure shows the difference in rail profile before and after the rail is ground by the grinding wheel.

[0119] In this embodiment, the rail profile before and after grinding is determined based on data provided by the on-board profiler;

[0120] The rail profile is divided into the gauge angle area A (15°-60°), the wheel-rail contact area B (5°-15°), the rail top center area C (0°-5°), and the non-working edge area D (-20°-0°);

[0121] For each area, calculate the difference in area before and after polishing.

[0122] In this embodiment, the rail is divided into multiple sub-areas based on the relationship between the rail and the wheel-rail. The multiple sub-areas divided into the rail include the gauge angle area, the wheel-rail contact area, the rail top center area and the non-working edge area. The gauge angle area refers to the connection position area between the rail top and the rail side, the wheel-rail contact area refers to the area where the wheel flange root contacts the rail gauge angle during the wheel-rail contact, the rail top center area refers to the central part of the rail top, that is, the area where the wheel tread center contacts the rail top surface, and the non-working edge area refers to the non-working edge of the rail, that is, the non-contact side and its vicinity.

[0123] In one embodiment, the gauge angle area, the wheel-rail contact area, the rail top center area and the non-working edge area are all defined as fan-shaped areas determined with the rail top center of the rail as the center of the circle. Specifically, the position of the gauge angle area is determined by two rays with angles of 15° and 60° with the center of the circle; the position of the wheel-rail contact area is determined by two rays with angles of 5° and 15° with the center of the circle; the position of the rail top center area is determined by two rays with angles of 0° and 5° with the center of the circle; and the position of the non-working edge area is determined by two rays with angles of -20° and 0° with the center of the circle.

[0124] Step 5, modify the grinding mode to obtain corresponding data of multiple groups of rail profile area differences.

[0125] In this embodiment, the above steps are repeated, and during the repetition process, the grinding angle, grinding speed and grinding power of the grinding wheel are modified.

[0126] Specifically, the grinding mode is modified, that is, the data of the grinding parameters are modified to obtain corresponding data of multiple groups of rail profile area differences.

[0127] In this embodiment, multiple rounds of grinding operations are performed based on different grinding angles, grinding speeds and grinding powers set by the orthogonal test method, and the corresponding rail profile area difference data are collected and calculated through steps three and four, respectively, to obtain multi-source data under different grinding modes.

[0128] Step 6, record the grinding wheel measurement data, grinding mode and rail profile area difference.

[0129] In this embodiment, the measurement data of the grinding wheel, the grinding mode and the corresponding rail profile area difference are recorded to obtain multiple sets of data. Specifically, the measurement data of the grinding wheel, the setting data of the grinding mode and the rail profile area difference data before and after grinding are collected and integrated. These data will be used as inputs for subsequent models for training and validating the models.

[0130] As shown in Table 1 below, it is a record table of the collected grinding wheel measurement data, grinding mode and rail profile area difference in this embodiment, wherein the grinding mode is set to 1, and the grinding parameters of the grinding mode include grinding power, grinding speed, number of grinding passes and grinding angle, and the setting values ​​of the specific grinding parameters of each grinding parameter are that the grinding power is 60% of the rated power, the grinding speed is 12 km / h, the number of grinding passes is 2 times, and the grinding angle is the rail bottom slope, that is, it is located in the gauge angle area; the rail profile area difference is reflected in the profile comparison before and after grinding and the grinding area, wherein the grinding area is the grinding area of ​​each area of ​​the rail, and specifically, each area of ​​the rail includes the gauge angle area A, the wheel-rail contact area B, the rail top center area C, and the non-working edge area D.

[0131] Table 1 Collection data record table

[0132]

[0133] Step 7: Establish a quantitative evaluation model for the cutting ability of rail grinding wheels.

[0134] In this embodiment, a quantitative evaluation model of the cutting ability of the rail grinding wheel can be constructed based on machine learning algorithms such as multivariate linear regression and neural network.

[0135] Furthermore, the model is trained using the data collected in step 6. Training the model means dividing the data collected in step 6 into a training set and a validation set according to a certain ratio, and using the training set data to train the selected machine learning model. During the training process, the model will continuously learn the patterns or relationships in the data.

[0136] And use the validation data set to verify the predictive ability of the model. Specifically, use the validation set or test set to evaluate the performance of the model. The evaluation indicators depend on the type of problem, such as accuracy, precision, recall, mean square error, and root mean square error.

[0137] Finally, according to the verification results, the model parameters are optimized to obtain the optimal quantitative evaluation model. Specifically, the model parameters (such as learning rate, tree depth, etc.) are adjusted or different algorithms are used according to the evaluation results.

[0138] Different grinding wheel cutting initial prediction models are constructed based on different types of machine learning algorithms. For example, the grinding wheel cutting initial prediction model can be constructed based on machine learning algorithms such as multivariate linear regression algorithm and neural network. Based on the same type of machine learning algorithm, the constructed grinding wheel cutting initial prediction model is different according to the physical characteristics of the grinding wheel and the number of grinding parameters.

[0139] In this embodiment, the constructed initial prediction model for grinding wheel cutting is different according to the category and quantity of the physical characteristics of the grinding wheel and the category and quantity of the grinding parameters. For example, the number of physical characteristics of the grinding wheel is 3, including hardness, size and material; the number of grinding parameters of the grinding wheel is 3, including grinding angle, grinding speed and grinding power. Based on the category and quantity of the physical characteristics of the grinding wheel and the category and quantity of the grinding parameters, a first initial prediction model for grinding wheel cutting is established. The number of physical characteristics of the grinding wheel with the same category and number of physical characteristics and the set values ​​of the grinding parameters with the same category and number of grinding parameters are used as the input of the first initial prediction model for grinding wheel cutting, and the corresponding grinding amount is used as the output of the first initial prediction model for grinding wheel cutting. The first initial prediction model for grinding wheel cutting is trained to obtain a grinding wheel cutting prediction model. When the number of physical characteristics of the grinding wheel is There are 3 of them, including hardness, size and material; there are 4 grinding parameters of the grinding wheel, including grinding angle, grinding speed, grinding power and number of grinding passes. Based on the category and quantity of the physical characteristics of the grinding wheel and the category and quantity of the grinding parameters, a second grinding wheel cutting initial prediction model is established. The category and number of physical characteristics of the grinding wheel with the same physical characteristics and the category and number of the grinding parameters and the set values ​​of the grinding parameters are used as the input of the second grinding wheel cutting initial prediction model, and the corresponding grinding amount is used as the output of the second grinding wheel cutting initial prediction model. The first grinding wheel cutting initial prediction model is trained to obtain a grinding wheel cutting prediction model. By analogy, multiple grinding wheel cutting prediction models can be obtained.

[0140] When the cutting ability of the grinding wheel to be tested needs to be predicted, the corresponding grinding wheel cutting prediction model is selected for prediction according to the category and quantity of the physical characteristics of the grinding wheel to be tested and the category and quantity of the grinding parameters.

[0141] In this embodiment, by directly measuring the physical properties of the grinding wheel, setting a specific grinding mode, and directly measuring the rail profile data before and after grinding, the difference in rail profile area before and after grinding is calculated, and a quantitative evaluation model is established based on the measurement data and the grinding mode, the cutting ability of the grinding wheel can be quantitatively evaluated; compared with the existing evaluation method based on experience and qualitative analysis, it is more objective and accurate; in this way, it can not only provide a scientific evaluation of the performance of the grinding wheel, but also provide an optimization strategy for the grinding operation to achieve more efficient and high-quality rail grinding, improve grinding efficiency, and reduce the wear of the grinding wheel, thereby extending its service life and reducing operating costs. This method provides effective tools and methods for intelligent rail grinding technology, provides important technical support for its further research and application, and helps to improve the operating efficiency and quality of the railway system.

[0142] Embodiment 9

[0143] Based on the above embodiments, this embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory, wherein the processor executes the computer program to implement the following steps:

[0144] Obtain physical characteristic data of the grinding wheel and setting values ​​of grinding parameters;

[0145] Obtaining the grinding amount of the profile area of ​​the rail ground by the grinding wheel when different grinding parameter setting values ​​are set;

[0146] Building a grinding wheel cutting initial prediction model based on a machine learning algorithm, taking the physical characteristic data of the grinding wheel and the set values ​​of the grinding parameters as inputs of the grinding wheel cutting initial prediction model, taking the grinding amount as output of the grinding wheel cutting initial prediction model, training the grinding wheel cutting initial prediction model, and obtaining a grinding wheel cutting prediction model;

[0147] The grinding wheel cutting prediction model is used to predict the grinding wheel to be measured, and the predicted grinding amount of the grinding wheel to be measured is obtained.

[0148] In one embodiment, when the processor executes the computer program, the following steps are implemented:

[0149] For each setting value of the grinding parameter, obtaining the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel;

[0150] The grinding amount of the rail profile area ground by the grinding wheel is determined according to the difference between the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel.

[0151] In one embodiment, when the processor executes the computer program, the following steps are implemented:

[0152] Dividing the rail profile into a plurality of sub-areas;

[0153] Obtaining the original profile area of ​​each of the sub-regions before the rail is ground by the grinding wheel;

[0154] For each setting value of the grinding parameter, obtaining the grinding profile area of ​​each sub-region after the rail is ground by the grinding wheel;

[0155] Calculating the difference between the original contour area and the polished contour area of ​​each sub-region to obtain the polishing amount of the contour area of ​​each sub-region;

[0156] The grinding amount of the profile area of ​​the rail ground by the grinding wheel is determined based on the grinding amount of the profile area of ​​each of the sub-regions.

[0157] In one embodiment, when the processor executes the computer program, the following steps are implemented:

[0158] Constructing different initial prediction models for grinding wheel cutting according to the categories and quantities of the physical characteristics of the grinding wheel and the categories and quantities of the grinding parameters;

[0159] For any of the grinding wheel cutting initial prediction models, the physical characteristic data of the grinding wheel and the grinding parameter value are used as inputs of the grinding wheel cutting initial prediction model, and the corresponding grinding amount is used as output of the grinding wheel cutting initial prediction model, and the grinding wheel cutting initial prediction model is trained to obtain a grinding wheel cutting prediction model;

[0160] According to the categories and quantities of the physical characteristics of the grinding wheel to be tested and the categories and quantities of the grinding parameters, the corresponding grinding wheel cutting prediction model is selected for prediction.

[0161] In some implementations of this embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0162] Obtain physical characteristic data of the grinding wheel and setting values ​​of grinding parameters;

[0163] Obtaining the grinding amount of the profile area of ​​the rail ground by the grinding wheel when different grinding parameter setting values ​​are set;

[0164] Building a grinding wheel cutting initial prediction model based on a machine learning algorithm, taking the physical characteristic data of the grinding wheel and the set values ​​of the grinding parameters as inputs of the grinding wheel cutting initial prediction model, taking the grinding amount as output of the grinding wheel cutting initial prediction model, training the grinding wheel cutting initial prediction model, and obtaining a grinding wheel cutting prediction model;

[0165] The grinding wheel cutting prediction model is used to predict the grinding wheel to be measured, and the predicted grinding amount of the grinding wheel to be measured is obtained.

[0166] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0167] For each setting value of the grinding parameter, obtaining the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel;

[0168] The grinding amount of the rail profile area ground by the grinding wheel is determined according to the difference between the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel.

[0169] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0170] Dividing the rail profile into a plurality of sub-areas;

[0171] Obtaining the original profile area of ​​each of the sub-regions before the rail is ground by the grinding wheel;

[0172] For each setting value of the grinding parameter, obtaining the grinding profile area of ​​each sub-region after the rail is ground by the grinding wheel;

[0173] Calculating the difference between the original contour area and the polished contour area of ​​each sub-region to obtain the polishing amount of the contour area of ​​each sub-region;

[0174] The grinding amount of the profile area of ​​the rail ground by the grinding wheel is determined based on the grinding amount of the profile area of ​​each of the sub-regions.

[0175] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0176] Constructing different initial prediction models for grinding wheel cutting according to the categories and quantities of the physical characteristics of the grinding wheel and the categories and quantities of the grinding parameters;

[0177] For any of the grinding wheel cutting initial prediction models, the physical characteristic data of the grinding wheel and the grinding parameter value are used as inputs of the grinding wheel cutting initial prediction model, and the corresponding grinding amount is used as output of the grinding wheel cutting initial prediction model, and the grinding wheel cutting initial prediction model is trained to obtain a grinding wheel cutting prediction model;

[0178] According to the categories and quantities of the physical characteristics of the grinding wheel to be tested and the categories and quantities of the grinding parameters, the corresponding grinding wheel cutting prediction model is selected for prediction.

[0179] In some implementations of this embodiment, a computer program product is provided, including a computer program / instruction, and when the computer program is executed by a processor, the following steps are implemented:

[0180] Obtain physical characteristic data of the grinding wheel and setting values ​​of grinding parameters;

[0181] Obtaining the grinding amount of the profile area of ​​the rail ground by the grinding wheel when different grinding parameter setting values ​​are set;

[0182] Building a grinding wheel cutting initial prediction model based on a machine learning algorithm, taking the physical characteristic data of the grinding wheel and the set values ​​of the grinding parameters as inputs of the grinding wheel cutting initial prediction model, taking the grinding amount as output of the grinding wheel cutting initial prediction model, training the grinding wheel cutting initial prediction model, and obtaining a grinding wheel cutting prediction model;

[0183] The grinding wheel cutting prediction model is used to predict the grinding wheel to be measured, and the predicted grinding amount of the grinding wheel to be measured is obtained.

[0184] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0185] For each setting value of the grinding parameter, obtaining the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel;

[0186] The grinding amount of the rail profile area ground by the grinding wheel is determined according to the difference between the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel.

[0187] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0188] Dividing the rail profile into a plurality of sub-areas;

[0189] Obtaining the original profile area of ​​each of the sub-regions before the rail is ground by the grinding wheel;

[0190] For each setting value of the grinding parameter, obtaining the grinding profile area of ​​each sub-region after the rail is ground by the grinding wheel;

[0191] Calculating the difference between the original contour area and the polished contour area of ​​each sub-region to obtain the polishing amount of the contour area of ​​each sub-region;

[0192] The grinding amount of the profile area of ​​the rail ground by the grinding wheel is determined based on the grinding amount of the profile area of ​​each of the sub-regions.

[0193] In one embodiment, the computer program, when executed by a processor, implements the following steps:

[0194] Constructing different initial prediction models for grinding wheel cutting according to the categories and quantities of the physical characteristics of the grinding wheel and the categories and quantities of the grinding parameters;

[0195] For any of the grinding wheel cutting initial prediction models, the physical characteristic data of the grinding wheel and the grinding parameter value are used as inputs of the grinding wheel cutting initial prediction model, and the corresponding grinding amount is used as output of the grinding wheel cutting initial prediction model, and the grinding wheel cutting initial prediction model is trained to obtain a grinding wheel cutting prediction model;

[0196] According to the categories and quantities of the physical characteristics of the grinding wheel to be tested and the categories and quantities of the grinding parameters, the corresponding grinding wheel cutting prediction model is selected for prediction.

[0197] The processor may include, but is not limited to, one or more processors or microprocessors. Each processor may be an application specific integrated circuit (ASIC), a digital signal processor (DSP), a digital signal processing device (DSPD), a programmable logic device (PLD), a field programmable gate array (FPGA), a controller, a microcontroller, a microprocessor or other electronic components to execute the method in the above embodiments.

[0198] The computer-readable storage medium may be implemented by any type of volatile or non-volatile storage device or a combination thereof, and the computer-readable storage medium may include but is not limited to, for example, random access memory (RAM), read-only memory (ROM), flash memory, EPROM memory, EEPROM memory, registers, computer storage media (e.g., hard disk, floppy disk, solid-state drive, removable disk, CD-ROM, DVD-ROM, Blu-ray disc, etc.).

[0199] The computer-readable storage medium may also store at least one computer executable program / instruction, which may be, for example, a computer-readable instruction. The computer-readable storage medium includes, but is not limited to, for example, a volatile memory and / or a non-volatile memory. The volatile memory may include, for example, a random access memory (RAM) and / or a cache memory (cache), etc. The computer-readable storage medium may include, for example, a read-only memory (ROM), a hard disk, a flash memory, etc. For example, a non-transitory computer-readable storage medium may be connected to a computing device such as a computer, and then, when the computing device runs the computer-readable instructions stored on the computer-readable storage medium, the various methods described above may be performed.

[0200] In addition, the computer device may also include (but not limited to) a data bus, an input / output (I / O) bus, a display, and input / output devices (eg, keyboard, mouse, speaker, etc.), etc.

[0201] The processor may communicate with external devices via an I / O bus via a wired or wireless network.

[0202] In one embodiment, the at least one computer executable instruction may also be compiled into or constitute a software product / computer program product, wherein one or more computer executable instructions are executed by a processor to perform the various functions and / or method steps in the embodiments described in the present technology.

[0203] In the embodiments provided in the present disclosure, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present disclosure. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the above-mentioned module, program segment or a part of the code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.

[0204] It should be noted that in the present disclosure, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element limited by the sentence "includes a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0205] Although the embodiments disclosed in the present disclosure are as above, the above contents are only embodiments adopted for facilitating the understanding of the present disclosure and are not intended to limit the present disclosure. Any technician in the technical field to which the present disclosure belongs can make any modifications and changes in the form and details of the implementation without departing from the spirit and scope disclosed in the present disclosure, but the scope of patent protection of the present disclosure shall still be subject to the scope defined in the attached claims.

Claims

1. A grinding wheel cutting prediction method, characterized in that: include: Obtain physical characteristic data of the grinding wheel and setting values ​​of grinding parameters; Obtaining the grinding amount of the profile area of ​​the rail ground by the grinding wheel when different grinding parameter setting values ​​are set; Building a grinding wheel cutting initial prediction model based on a machine learning algorithm, taking the physical characteristic data of the grinding wheel and the set values ​​of the grinding parameters as inputs of the grinding wheel cutting initial prediction model, taking the grinding amount as output of the grinding wheel cutting initial prediction model, training the grinding wheel cutting initial prediction model, and obtaining a grinding wheel cutting prediction model; The grinding wheel cutting prediction model is used to predict the grinding wheel to be measured, and the predicted grinding amount of the grinding wheel to be measured is obtained.

2. The grinding wheel cutting prediction method according to claim 1, characterized in that: The step of obtaining the grinding amount of the profile area of ​​the rail ground by the grinding wheel when different grinding parameter setting values ​​are set includes: For each setting value of the grinding parameter, obtaining the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel; The grinding amount of the rail profile area ground by the grinding wheel is determined according to the difference between the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel.

3. The grinding wheel cutting prediction method according to claim 2, characterized in that: The step of obtaining the rail profile area before the rail is ground by the grinding wheel and the rail profile area after the rail is ground by the grinding wheel for each setting value of the grinding parameter comprises: Dividing the rail profile into a plurality of sub-areas; Obtaining the original profile area of ​​each of the sub-regions before the rail is ground by the grinding wheel; For each setting value of the grinding parameter, obtaining the grinding profile area of ​​each sub-region after the rail is ground by the grinding wheel; The step of determining the grinding amount of the profile area of ​​the rail ground by the grinding wheel according to the difference between the profile area of ​​the rail before the rail is ground by the grinding wheel and the profile area of ​​the rail after the rail is ground by the grinding wheel comprises: Calculating the difference between the original contour area and the polished contour area of ​​each sub-region to obtain the polishing amount of the contour area of ​​each sub-region; The grinding amount of the profile area of ​​the rail ground by the grinding wheel is determined based on the grinding amount of the profile area of ​​each of the sub-regions.

4. The grinding wheel cutting prediction method according to claim 3, characterized in that: The sub-region includes at least one of a gauge angle region, a wheel-rail contact region, a rail top center region, and a non-working edge region.

5. The grinding wheel cutting prediction method according to claim 1, characterized in that: The grinding parameters of the grinding wheel include at least one parameter of a grinding angle, a grinding speed and a grinding power.

6. The grinding wheel cutting prediction method according to claim 1, characterized in that: The physical characteristic data of the grinding wheel includes at least one of hardness, size and material composition of the grinding wheel.

7. The grinding wheel cutting prediction method according to claim 1, characterized in that: The steps of constructing a grinding wheel cutting initial prediction model based on a machine learning algorithm, taking the physical characteristic data of the grinding wheel and the setting value of the grinding parameter as the input of the grinding wheel cutting initial prediction model, taking the grinding amount as the output of the grinding wheel cutting initial prediction model, training the grinding wheel cutting initial prediction model, and obtaining the grinding wheel cutting prediction model include: Constructing different initial prediction models for grinding wheel cutting according to the categories and quantities of the physical characteristics of the grinding wheel and the categories and quantities of the grinding parameters; For any of the grinding wheel cutting initial prediction models, the physical characteristic data of the grinding wheel and the grinding parameter value are used as inputs of the grinding wheel cutting initial prediction model, and the corresponding grinding amount is used as output of the grinding wheel cutting initial prediction model, and the grinding wheel cutting initial prediction model is trained to obtain a grinding wheel cutting prediction model; The step of predicting the cutting ability of the grinding wheel by using the grinding wheel cutting evaluation model comprises: According to the categories and quantities of the physical characteristics of the grinding wheel to be tested and the categories and quantities of the grinding parameters, the corresponding grinding wheel cutting prediction model is selected for prediction.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images