Sliding rail working condition evaluation method and system, electronic equipment, medium and program product

Abstract

The invention provides a sliding rail working condition evaluation method and system, electronic equipment, a medium and a program product, and the method comprises the steps: obtaining a vibration acceleration signal of a sliding rail load structure and the pose data of the sliding rail load structure; determining actually measured modal information of the slide rail load structure according to the vibration acceleration signal; inputting the pose data into the meta-model to output target modal information; and in response to the fact that the actually measured modal information is not in the preset range of the target modal information, determining that the working condition of the sliding rail is degraded. According to the method, the difference between the actually-measured constraint rigidity of the sliding rail to the sliding rail load structure and the healthy constraint rigidity of the healthy sliding rail to the sliding rail load structure is displayed through the comparison result of the actually-measured modal information and the target modal information, if the difference is larger than the preset range, it is indicated that the sliding rail is degraded, and therefore the accuracy of sliding rail working condition evaluation is improved.

Description

Technical Field

[0001] The present disclosure relates to the field of machine tool technology, and in particular to a slide rail working condition evaluation method, system, electronic equipment, medium and program product. Background Art

[0002] Common machine tool evaluation methods mainly rely on the collection of various sensor signals and the use of advanced technologies such as machine learning for data modeling. However, this method has a significant limitation, namely the lack of fault data. Usually, the data set used to build the model is mainly composed of data under normal operating conditions, which makes it difficult for the trained model to meet the needs in actual engineering applications. In addition, the method that relies solely on data-driven ignores the in-depth exploration of the fault mechanism to a certain extent, thereby reducing the model's ability to explain the fault phenomenon.

[0003] Traditional joint parameter identification of machine tool slide rail joint surfaces does not take into account the different degrees of wear and degradation at different positions of the slide rails. All of them are uniformly identified as the same set of parameters, resulting in a very large deviation between the performance of the machine tool and the identification results in severely degraded areas or very healthy areas. Summary of the invention

[0004] The technical problem to be solved by the present disclosure is to overcome the defect of inaccurate evaluation of machine tool slide rail faults in the prior art, and to provide a slide rail working condition evaluation method, system, electronic equipment, medium and program product.

[0005] The present invention solves the above technical problems through the following technical solutions:

[0006] The present disclosure provides a method for evaluating a slide rail working condition, the method comprising:

[0007] Acquire the vibration acceleration signal of the slide rail load structure and the position and posture data of the slide rail load structure;

[0008] Determining measured modal information of the slide rail load structure according to the vibration acceleration signal;

[0009] Inputting the posture data into a meta-model to output target modal information;

[0010] In response to the measured modal information being not within a preset range of the target modal information, it is determined that the working condition of the slide rail is deteriorated.

[0011] Preferably, the measured modal information includes a measured natural frequency, the target modal information includes a target natural frequency under a swing vibration mode, and the step of determining that the working condition of the slide rail is deteriorated in response to the measured modal information being not within a preset range of the target modal information includes:

[0012] In response to the absolute value of the difference between the measured natural frequency and the target natural frequency being greater than a preset threshold, it is determined that the operating condition of the slide rail is deteriorated.

[0013] Preferably, the step of determining the measured modal information of the slide rail load structure according to the vibration acceleration signal comprises:

[0014] Performing a fast Fourier transform on the vibration acceleration signal;

[0015] The measured natural frequencies are extracted from the transformation results by operational modal analysis.

[0016] Preferably, the meta-model is trained by the following steps:

[0017] Dividing the slide rail into a plurality of sections;

[0018] Get the working time ratio corresponding to each slide rail position;

[0019] Determine the proportion of working time for sampling;

[0020] Determine the position of the slide rail corresponding to the sampling working time ratio as the sampling position;

[0021] Obtaining the natural frequency of the slide rail load structure at the sampling position under the swing vibration mode;

[0022] Performing training based on the sampling position and the natural frequency to obtain a dynamic model of the slide rail;

[0023] A meta-model is established based on the numerically calculated modal parameter data of the dynamic model by using a multi-input Gaussian process regression method.

[0024] Preferably, the step of determining the sampling working time ratio comprises:

[0025] Determine the sampling working time ratio based on the sampling quantity, the highest working time ratio and the lowest working time ratio;

[0026] and / or,

[0027] The step of obtaining the natural frequency of the slide rail load structure at the sampling position under the swing vibration mode comprises:

[0028] Obtain stimulus and response signals;

[0029] The excitation and response signals are generated after the exciter applies excitation to the slide rail load structure; the suspension length of the exciter is greater than a preset length, and the preset length is negatively correlated with the square value of the first-order natural frequency of the slide rail load structure;

[0030] The natural frequency of the slide rail load structure in the swing vibration mode is extracted from the excitation and response signals.

[0031] Preferably, after the step of training based on the sampling position and the natural frequency to obtain the dynamic model of the slide rail, the step further includes:

[0032] Selecting the optimal spring unit parameters corresponding to the sampling position by support vector machine regression method;

[0033] Correcting the dynamic model by using the optimal spring unit parameters and the block Lanczos method;

[0034] The step of establishing a meta-model based on the numerically calculated modal parameter data of the dynamic model by using a multi-input Gaussian process regression method comprises:

[0035] The modified dynamic model is used to perform numerical modal analysis of the slide rail load with multiple posture combinations, and the numerically calculated modal parameter results are obtained.

[0036] The meta-model is established by using the multi-input Gaussian process regression method with the posture state parameters and the corresponding numerically calculated modal parameter results as input.

[0037] The present disclosure also provides a slide rail working condition evaluation system, the slide rail working condition evaluation system comprising:

[0038] An acquisition module is used to acquire a vibration acceleration signal of a slide rail load structure and position data of the slide rail load structure;

[0039] A first determination module, used to determine measured modal information of the slide rail load structure according to the vibration acceleration signal;

[0040] A meta-model module, used for inputting the posture data into a meta-model to output target modal information;

[0041] The second determination module is used to determine that the working condition of the slide rail is deteriorated in response to the measured modal information being not within a preset range of the target modal information.

[0042] The present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and used to run on the processor, and the processor implements the above-mentioned slide rail working condition evaluation method when executing the computer program.

[0043] The present disclosure also provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the above-mentioned slide rail working condition evaluation method when executed by a processor.

[0044] The present disclosure also provides a computer program product, including a computer program, which implements the above-mentioned slide rail working condition evaluation method when executed by a processor.

[0045] On the basis of being in accordance with the common sense in the art, the above-mentioned preferred conditions can be arbitrarily combined to obtain the preferred embodiments of the present disclosure.

[0046] The positive and progressive effects of this disclosure are:

[0047] The present disclosure displays the difference between the measured constraint stiffness of the slide rail on the slide rail load structure and the healthy constraint stiffness of the healthy slide rail on the slide rail load structure by comparing the measured modal information with the target modal information. If the difference is greater than a preset range, it indicates that the slide rail is deteriorated, thereby improving the accuracy of the slide rail working condition evaluation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A flow chart of a method for evaluating a slide rail working condition provided in Example 1 of the present disclosure;

[0049] Figure 2 A schematic diagram of the disassembly of the joint surface of a slide rail in an example of a slide rail working condition evaluation method provided in Example 1 of the present disclosure;

[0050] Figure 3 A schematic diagram of a two-dimensional mesh disassembly of a joint surface of a slide rail, which is an example of a slide rail working condition evaluation method provided in Example 1 of the present disclosure;

[0051] Figure 4 A schematic diagram of a spring unit of a slide rail according to an example of a method for evaluating a slide rail working condition provided in Embodiment 1 of the present disclosure;

[0052] Figure 5 A schematic diagram of the structure of a slide rail working condition evaluation system provided in Example 2 of the present disclosure;

[0053] Figure 6 A schematic diagram of the structure of an electronic device provided in Embodiment 3 of the present disclosure. DETAILED DESCRIPTION

[0054] The present disclosure is further described below by way of examples, but the present disclosure is not limited to the scope of the examples.

[0055] Example 1

[0056] This embodiment provides a method for evaluating the working condition of a slide rail. In a machine tool, the slide rail is responsible for supporting and guiding the slide rail load structure. The slide rail load structure refers to those components or assembly structures that rely on the slide rail for linear motion. Figure 1 , the slide rail working condition evaluation methods include:

[0057] S1. Obtain the vibration acceleration signal of the slide rail load structure and the position and posture data of the slide rail load structure.

[0058] The vibration acceleration signal can be collected by a plurality of vibration acceleration sensors installed on the slide rail load structure.

[0059] S2. Determine the measured modal information of the slide rail load structure according to the vibration acceleration signal.

[0060] In an optional embodiment, step S2 includes:

[0061] S21. Perform fast Fourier transform (FFT transform) on the vibration acceleration signal.

[0062] S22. Extract the measured natural frequencies from the transformation results through operational modal analysis (OMA).

[0063] Among them, fast Fourier transform is an algorithm for efficiently calculating discrete Fourier transform; operational modal analysis is a modal analysis method performed under the operating state of the structure.

[0064] S3. Input the pose data into the meta-model to output the target modal information.

[0065] Among them, the meta-model is a mapping model of the posture data and modal information of the continuous slide rail load structure, and is the healthy working condition benchmark of the slide rail.

[0066] In an optional implementation, the meta-model is trained by the following steps:

[0067] S01. Divide the slide rail into several sections.

[0068] The lengths of each section of the slide rail may be the same or different.

[0069] S02. Obtain the working time ratio corresponding to each slide rail position.

[0070] The working time ratio is the ratio of the working time of each slide rail position to the total working time.

[0071] In this embodiment, the working time ratio corresponding to each slide rail position can be obtained through the historical processing data of the machine tool, or the posture data of the slide rail load structure over a period of time can be statistically analyzed based on a statistical method, and the corresponding relationship between each slide rail position and the working time ratio can be determined based on the posture data.

[0072] S03. Determine the proportion of sampling working time.

[0073] In an optional implementation, step S03 includes:

[0074] The sampling working time ratio is determined based on the sampling quantity, the highest working time ratio and the lowest working time ratio.

[0075] Here is a method to determine the sampling working time ratio through a formula:

[0076]

[0077] Among them, P(i) is used to represent the sampling working time ratio, P(min) is used to represent the minimum working time ratio, P(max) is used to represent the maximum working time ratio, m is used to represent the sampling quantity, i is used to represent the sampling sequence number, and i is less than or equal to m.

[0078] S04. Determine the slide rail position corresponding to the sampling working time ratio as the sampling position.

[0079] In this embodiment, the working time of each section of the slide rail is used as a sampling reference, which is in line with the mechanism of evaluating the degree of slide rail wear. It can ensure that the slide rail positions with different working time ratios are covered by sampling as much as possible, avoiding the sampling unevenness problem caused by only considering the geometric position sampling.

[0080] S05. Obtain the natural frequency of the slide rail load structure at the sampling position under the swing vibration mode.

[0081] In an optional implementation, step S05 includes:

[0082] S051. Obtain excitation and response signals.

[0083] The excitation and response signals are generated after the exciter applies excitation to the slide rail load structure. The suspension length of the exciter is greater than a preset length, and the preset length is negatively correlated with the square value of the first-order natural frequency of the slide rail load structure.

[0084] The following is a specific method of applying excitation:

[0085] In order to prevent the vibration of the exciter from transmitting vibration interference to the machine tool through the ground, the exciter can be suspended by a rigid rope and tooling. By controlling the suspension length, the natural frequency of the exciter in the suspended state can be prevented from interfering with the test: the suspension length is greater than the preset length L(Susp), and the excitation direction of the excitation rod is adjusted to be 45 degrees to the three coordinate axes of the sensor.

[0086]

[0087] Among them, L(Susp) is used to characterize the preset length of the exciter, g is used to characterize the gravitational acceleration, and ω1 is used to characterize the first-order natural frequency of the slide rail load structure.

[0088] S052. Extract the natural frequency of the slide rail load structure under the swing vibration mode from the excitation and response signals.

[0089] The excitation and response signals are step sine signals. In this embodiment, the natural frequencies extracted include at least the first three natural frequencies of the slide rail load structure under the swing vibration mode.

[0090] S06. Perform training based on the sampling positions and natural frequencies to obtain a dynamic model of the slide rail.

[0091] S07. A meta-model is established based on the numerically calculated modal parameter data of the dynamic model through a multi-input Gaussian process regression method.

[0092] This implementation method uses a machine tool that has been installed and is in operation as a meta-model training benchmark, avoiding the problem that the machine tool is inconsistent with the factory data due to inconsistent installation and other problems, thereby affecting the accuracy of the slide rail health benchmark.

[0093] In an optional implementation, step S06 further includes:

[0094] S061. Select the optimal spring unit parameters corresponding to the sampling position through support vector machine regression method.

[0095] Among them, the support vector machine regression method is a regression algorithm based on support vector machine, which is used to solve the regression problem. The spring unit parameters are the parameters of the spring unit. The spring unit is a commonly used unit type in finite element analysis, mainly used to describe the mechanical behavior of elastic structures.

[0096] S062. Modify the dynamic model by using the optimal spring unit parameters and the block Lanczos method.

[0097] Among them, the block Lanczos method is a numerical method for solving the eigenvalue problem of large sparse matrices, and is particularly suitable for modal analysis in structural dynamics analysis.

[0098] Step S07 includes:

[0099] S071. Perform numerical modal analysis of the slide rail load with multiple posture combinations using the modified dynamic model to obtain numerically calculated modal parameter results.

[0100] S072. A meta-model is established by using a multi-input Gaussian process regression method with posture state parameters and corresponding numerically calculated modal parameter results as input.

[0101] In this embodiment, the modified dynamic model obtained by using the optimal spring unit parameters and the block Lanczos method can make the data output by the meta-model more accurate, thereby further improving the accuracy of the slide rail evaluation.

[0102] S4. In response to the measured modal information not being within a preset range of the target modal information, it is determined that the working condition of the slide rail is deteriorated.

[0103] S5. In response to the measured modal information being within a preset range of the target modal information, determining that the slide rail is in a healthy condition.

[0104] Among them, the preset range is set according to the actual situation.

[0105] In an optional embodiment, the measured modal information includes the measured natural frequency, the target modal information includes the target natural frequency under the swing vibration mode, and step S4 includes:

[0106] In response to the absolute value of the difference between the measured natural frequency and the target natural frequency being greater than a preset threshold, it is determined that the operating condition of the slide rail is deteriorated.

[0107] Among them, the preset threshold is set according to the actual situation.

[0108] This embodiment shows the difference between the measured constraint stiffness of the slide rail to the slide rail load structure and the healthy constraint stiffness of the healthy slide rail to the slide rail load structure by comparing the measured modal information with the target modal information. If the difference is greater than a preset range, it indicates that the slide rail is deteriorated, thereby improving the accuracy of the slide rail working condition evaluation. This embodiment can effectively obtain the deterioration of the slide rail, promptly remind maintenance, avoid unplanned downtime, and effectively evaluate the deterioration of different positions of the slide rail, help improve the machine tool operation process, avoid using the deteriorated slide rail area, and extend the service life of the machine tool.

[0109] The slide rail evaluation method of the horizontal boring and milling machine is taken as a specific example below to describe in detail the slide rail working condition evaluation method of the present embodiment.

[0110] It should be noted that in this example, the horizontal boring and milling machine has four axes, namely, X, Y, Z, and W, wherein the W axis is parallel to the Y axis, and each axis is equipped with a slide rail.

[0111] The specific slide rail working condition evaluation method is:

[0112] Step 1: Select sampling samples. Based on historical processing data, if there is no historical processing data, the position states of the slide rail load structure on the X, Y, Z, and W axes of the horizontal boring and milling machine are statistically analyzed within a certain period of time to select sampling samples. Specifically:

[0113] Step 1.1. Select the slide rail of any axis among the X, Y, Z, and W axes to be evaluated as the slide rail evaluation object. Divide the slide rail evaluation object into n sections of equal length, and the position points corresponding to each section of the slide rail are recorded as pos(1), pos(2), pos(3)...pos(n).

[0114] Step 1.2: According to the historical processing data, the proportion of working time when the slide rail load is located at each position point of the slide rail evaluation object is calculated, and the proportion of working time corresponding to each position point is recorded as P(pos_1), P(pos_2), P(pos_3)...P(pos_n).

[0115] Step 1.3: Determine the sampling working time ratio according to the following formula.

[0116]

[0117] Among them, P(i) is used to represent the sampling working time ratio, P(min) is used to represent the minimum working time ratio, P(max) is used to represent the maximum working time ratio, m is used to represent the sampling quantity, i is used to represent the sampling sequence number, and i is less than or equal to m.

[0118] Step 1.4: According to the corresponding relationship between P(pos_n) and pos(n) obtained by historical processing data or statistical methods, determine the position pos(sam_i) of the slide rail load structure corresponding to P(i), and use pos(sam_i) as the sampling position.

[0119] The sampling method in step 1 uses the working time of the slide rail as the main reference parameter for sampling, which is more in line with the mechanism of evaluating the degree of wear of the slide rail. It can ensure that the positions of the slide rails with different working time ratios are covered by sampling as much as possible, avoiding the problem of uneven sampling caused by conventional sampling that only considers geometric position sampling.

[0120] Step 2: Perform a modal test on the slide rail load structure. Operate the moving parts of the machine tool to run to pos(sam_i), and perform a modal test on the slide rail load structure at each sampling position to obtain modal information such as the natural frequency of the slide rail load structure under the swing vibration mode. The specific method is:

[0121] Step 2.1. Design the slide rail load structure (for example, for the slide rail between the base and the column, the corresponding slide rail load structure is the column) to present the envelope point of the swing vibration mode, which is used as the measurement point and excitation point of the sensor, and install a three-directional vibration acceleration sensor at the measurement point. The sensor's X-axis and Y-axis (or W-axis) are parallel to the horizontal direction and one of the axes is consistent with the direction of the track, and the Z-axis is the vertical direction.

[0122] Step 2.2, move the slide rail load structure to the first sampling position pos(samp_1), use the exciter to apply excitation to the slide rail load structure, and the specific excitation application method is as follows: in order to prevent the vibration of the exciter from transmitting vibration interference to the machine tool through the ground, a rigid rope is used in conjunction with a tooling to suspend the exciter; in order to prevent the natural frequency of the exciter in the suspended state from interfering with the test, the suspension length is controlled to avoid this problem, that is, the suspension length is greater than the preset length L(Susp), and the excitation direction of the excitation rod is adjusted to be 45 degrees to the three coordinate axes of the sensor.

[0123] The following is the calculation formula for the preset length:

[0124]

[0125] Among them, L(Susp) is used to characterize the preset length of the exciter, g is used to characterize the gravitational acceleration, and ω1 is used to characterize the first-order natural frequency of the slide rail load structure.

[0126] Step 2.3: Use the step sine signal as the excitation and response signal, and extract the modal information of the slide rail load structure. The extracted natural frequencies are the first three natural frequencies of the slide rail load structure corresponding to the swing vibration mode.

[0127] Step 2.4: When the slide rail load structure is moved to the sampling positions of pos(samp_2), pos(samp_3), ... pos(samp_m) in sequence, step 2.3 is repeated to obtain the modal information of the slide rail load structure at different sampling positions.

[0128] Step 3: Establish the slideway dynamics model of the horizontal boring and milling machine sampling position by cutting the contact surface. By cutting the contact surface, the nodes of the two parts of the finite element model on the contact surface can be one-to-one correspondence. The specific method is:

[0129] Step 3.1: Initially model the horizontal boring and milling machine and perform dynamic model processing on the initial model.

[0130] Step 3.2: Cut the joint surface of the slide rail. The specific cutting method is as follows: Figure 2 As shown, a projection surface of the contact surface is established for the area where the two parts contact each other, and the contact surfaces of the two solid parts of the slide rail and the slider are cut according to the projection surface, respectively, and an area with the same shape as the contact surface is obtained on each of the two solid parts.

[0131] Step 3.3, extract the contact surface plane of the two parts, divide the plane two-dimensional grid on the plane, and map the grid to the corresponding surface area of ​​the two parts of the contacting solid structure respectively, so that the grid nodes of the two parts in contact can be corresponding. For the two parts of the entity, use the two-dimensional grid of the contact surface as a constraint, and extend to establish the solid grid. And establish the solid grid model for other structures of the machine tool, such as Figure 3 shown.

[0132] Step 3.4: Create spring units at the mesh nodes corresponding to the contact surface, such as Figure 4 shown.

[0133] Step 3.5, perform dynamic model correction and calculate modal information of multiple sampling positions. The specific method is: optimize the spring unit parameters in step 3.4 based on the support vector machine regression method, so as to determine the optimal spring unit parameters at different sampling positions on the X, Y, Z, and W axes. Then, based on the optimal spring unit parameters and the block Lanczos method, calculate the modal information corresponding to different sampling positions on the X, Y, Z, and W axes, and then complete the correction of the dynamic model.

[0134] In this step, different sampling positions of the X, Y, Z, and W axes are characterized by different finite element model joint surface parameters through different optimal spring unit parameters, avoiding the traditional model from applying a set of data to models of different slide rail positions, thereby improving the prediction accuracy of the dynamic model.

[0135] Step 4: Based on the dynamic model established in step 3, numerical simulation calculations are performed on the pose combination data of different sampling positions on the X, Y, Z, and W axes using the block Lanczos method for numerical modal analysis. The number of X, Y, Z, and W axis pose data can be determined according to specific computing resources. The X, Y, Z, and W axis pose data are input, and the modal information is output. A meta-model is established based on multi-input Gaussian process regression, that is, a mapping model between the continuous machine tool X, Y, Z, and W axis pose data and modal information is formed, and it serves as a health benchmark for subsequent slideway evaluation.

[0136] This step introduces the finite element dynamics model and performs numerical calculations, which replaces a large number of physical tests while ensuring data accuracy, saving test costs and time costs. The machine tool posture area calculated by the finite element is encrypted with the metamodel, saving calculation costs and time. The metamodel is directly established based on a small amount of experimental data, and the introduction of numerical simulation improves the accuracy of the data source.

[0137] Step 5: Conduct real-time online evaluation.

[0138] Install 1 to 2 vibration acceleration sensors on the slide rail load structure corresponding to the slide rail that needs to be evaluated to collect the real-time vibration acceleration signal of the slide rail load structure. Perform FFT transformation on the collected vibration acceleration signal, and then extract the natural frequency based on the operational modal analysis (OMA) method. At the same time, collect the posture data of the slide rail load structure on the X, Y, Z, and W axes of the machine tool, compare the posture data and the extracted measured natural frequency with the target natural frequency output by the meta-model established in step 4, and determine the degradation of the slide rail based on the size of the difference. The larger the difference between the measured natural frequency and the target natural frequency, the more serious the degradation of the slide rail working condition.

[0139] In this example, when evaluating the working condition of the horizontal boring and milling machine slide rail based on the dynamic characteristic mechanism, it is taken into account that the degree of wear of the slide rail at different positions during the operation of the machine tool will vary. Based on the dynamic characteristic mechanism and combined with the specific structural characteristics of the horizontal boring and milling machine, this example reveals the important correlation between the dynamic characteristic data of the slide rail load structure and the wear degradation state of the slide rail. By analyzing and comparing the mechanism of dynamic characteristic data during the actual operation of the machine tool, effective perception of the wear degradation state of the slide rail is achieved.

[0140] Example 2

[0141] Corresponding to the aforementioned slide rail working condition evaluation method embodiment, the present disclosure also provides an embodiment of a slide rail working condition evaluation system.

[0142] See also Figure 5 , the slide rail working condition evaluation system includes:

[0143] The acquisition module 1 is used to acquire the vibration acceleration signal of the slide rail load structure and the position and posture data of the slide rail load structure.

[0144] The first determination module 2 is used to determine the measured modal information of the slide rail load structure according to the vibration acceleration signal.

[0145] The meta-model module 3 is used to input the posture data into the meta-model to output the target modal information.

[0146] The second determination module 4 is configured to determine that the working condition of the slide rail is deteriorated in response to the measured modal information not being within a preset range of the target modal information.

[0147] In an optional embodiment, the measured modal information includes the measured natural frequency, the target modal information includes the target natural frequency under the swing vibration mode, and the second determination module 4 is further used to determine that the working condition of the slide rail is deteriorated in response to the absolute value of the difference between the measured natural frequency and the target natural frequency being greater than a preset threshold.

[0148] In an alternative embodiment, see Figure 5 , the slide rail working condition evaluation system also includes:

[0149] The transformation module 5 is used to perform fast Fourier transformation on the vibration acceleration signal.

[0150] The extraction module 6 is used to extract the measured natural frequency from the transformation result by using the operational modal analysis method.

[0151] In an alternative embodiment, see Figure 5 , the slide rail working condition evaluation system also includes:

[0152] Training module 7 is used to divide the slide rail into several sections; it is also used to obtain the working time ratio corresponding to the position of each slide rail section; it is also used to determine the sampling working time ratio; it is also used to determine the slide rail position corresponding to the sampling working time ratio as the sampling position; it is also used to obtain the natural frequency of the slide rail load structure at the sampling position under the swing vibration mode; it is also used to train based on the sampling position and the natural frequency to obtain the dynamic model of the slide rail; it is also used to establish a meta-model based on the numerical calculation modal parameter data of the dynamic model through a multi-input Gaussian process regression method.

[0153] In an optional implementation, the training module 7 is further used to determine the sampling working time ratio according to the sampling quantity, the maximum working time ratio and the minimum working time ratio.

[0154] In an optional embodiment, the training module 7 is also used to obtain excitation and response signals.

[0155] Among them, the excitation and response signals are generated after the exciter applies excitation to the slide rail load structure; the suspension length of the exciter is greater than the preset length, and the preset length is negatively correlated with the square value of the first-order natural frequency of the slide rail load structure.

[0156] The training module 7 is also used to extract the natural frequency of the slide rail load structure under the swing vibration mode from the excitation and response signals.

[0157] In an optional embodiment, the training module 7 is also used to select the optimal spring unit parameters corresponding to the sampling position through the support vector machine regression method; it is also used to correct the dynamic model through the optimal spring unit parameters and the block Lanczos method; it is also used to perform numerical modal analysis of the slide rail load with multiple posture combinations through the corrected dynamic model to obtain numerically calculated modal parameter results; it is also used to establish a meta-model through the multi-input Gaussian process regression method, with the posture state parameters and the corresponding numerically calculated modal parameter results as input.

[0158] As for the system embodiment, since it basically corresponds to the method embodiment, the relevant parts can refer to the partial description of the method embodiment. The system embodiment described above is only illustrative, in which the units described as separate components may or may not be physically separated, and the components as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the disclosed solution.

[0159] Example 3

[0160] Figure 6 This is a schematic diagram of the structure of an electronic device showing an example embodiment of the present disclosure, wherein the electronic device includes a memory, a processor, and a computer program stored in the memory and used to run on the processor, and when the processor executes the computer program, a method for evaluating the working condition of a slide rail according to any of the above embodiments is implemented. Figure 6 The electronic device 60 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present disclosure.

[0161] like Figure 6 As shown, the electronic device 60 may be in the form of a general-purpose computing device, for example, it may be a server device. The components of the electronic device 60 may include, but are not limited to: at least one processor 61, at least one memory 62, and a bus 63 connecting different system components (including the memory 62 and the processor 61).

[0162] The bus 63 includes a data bus, an address bus, and a control bus.

[0163] The memory 62 may include a volatile memory, such as a random access memory (RAM) 621 and / or a cache memory 622 , and may further include a read-only memory (ROM) 623 .

[0164] The memory 62 may also include a program tool 625 (or utility) having a set (at least one) of program modules 624, such program modules 624 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0165] The processor 61 executes various functional applications and data processing by running the computer program stored in the memory 62, such as the slide rail working condition evaluation method provided in any of the above embodiments.

[0166] The electronic device 60 may also communicate with one or more external devices 64 (e.g., keyboards, pointing devices, etc.). Such communication may be performed via an input / output (I / O) interface 65. Furthermore, the electronic device 60 may also communicate with one or more networks (e.g., local area networks (LANs), wide area networks (WANs), and / or public networks, such as the Internet) via a network adapter 66. As shown, the network adapter 66 communicates with other modules of the electronic device 60 via a bus 63. It should be understood that, although not shown in the figure, other hardware and / or software modules may be used in conjunction with the electronic device 60, including but not limited to: microcode, device drivers, redundant processors, external disk drive arrays, RAID (disk array) systems, tape drives, and data backup storage systems, etc.

[0167] It should be noted that although several units / modules or sub-units / modules of the electronic device are mentioned in the above detailed description, this division is merely exemplary and not mandatory. In fact, according to the embodiments of the present disclosure, the features and functions of two or more units / modules described above can be embodied in one unit / module. Conversely, the features and functions of one unit / module described above can be further divided into multiple units / modules to be embodied.

[0168] Example 4

[0169] The embodiments of the present disclosure further provide a computer-readable storage medium having a computer program stored thereon, and when the program is executed by a processor, the method for evaluating the working condition of a slide rail provided in any of the above embodiments is implemented.

[0170] The readable storage medium may include but is not limited to: a portable disk, a hard disk, a random access memory, a read-only memory, an erasable programmable read-only memory, an optical storage device, a magnetic storage device or any suitable combination of the above.

[0171] Example 5

[0172] The embodiments of the present disclosure also provide a computer program product, including a computer program, which implements any of the above-mentioned slide rail working condition evaluation methods when executed by a processor.

[0173] Among them, the program code for executing the computer program product of the present disclosure can be written in any combination of one or more programming languages, and the program code can be executed completely on the user device, partially on the user device, as an independent software package, partially on the user device and partially on a remote device, or completely on the remote device.

[0174] Although the specific embodiments of the present disclosure are described above, those skilled in the art should understand that this is only an example, and the protection scope of the present disclosure is defined by the appended claims. Those skilled in the art may make various changes or modifications to these embodiments without departing from the principles and essence of the present disclosure, but these changes and modifications all fall within the protection scope of the present disclosure.

Claims

1. A method for evaluating the working condition of a slide rail, characterized in that: The slide rail working condition evaluation method comprises: Acquire the vibration acceleration signal of the slide rail load structure and the position and posture data of the slide rail load structure; Determining measured modal information of the slide rail load structure according to the vibration acceleration signal; Inputting the posture data into a meta-model to output target modal information; In response to the measured modal information being not within a preset range of the target modal information, it is determined that the working condition of the slide rail is deteriorated.

2. The method for evaluating the working condition of a slide rail according to claim 1, characterized in that: The measured modal information includes a measured natural frequency, the target modal information includes a target natural frequency under a swing vibration mode, and the step of determining that the working condition of the slide rail is deteriorated in response to the measured modal information being not within a preset range of the target modal information includes: In response to the absolute value of the difference between the measured natural frequency and the target natural frequency being greater than a preset threshold, it is determined that the operating condition of the slide rail is deteriorated.

3. The method for evaluating the working condition of a slide rail according to claim 2, characterized in that: The step of determining the measured modal information of the slide rail load structure according to the vibration acceleration signal comprises: Performing a fast Fourier transform on the vibration acceleration signal; The measured natural frequencies are extracted from the transformation results by operational modal analysis.

4. The method for evaluating the working condition of a slide rail according to claim 2, characterized in that: The meta-model is trained by the following steps: Dividing the slide rail into a plurality of sections; Get the working time ratio corresponding to each slide rail position; Determine the proportion of working time for sampling; Determine the position of the slide rail corresponding to the sampling working time ratio as the sampling position; Obtaining the natural frequency of the slide rail load structure at the sampling position under the swing vibration mode; Performing training based on the sampling position and the natural frequency to obtain a dynamic model of the slide rail; A meta-model is established based on the numerically calculated modal parameter data of the dynamic model by using a multi-input Gaussian process regression method.

5. The method for evaluating the working condition of a slide rail according to claim 4, characterized in that: The step of determining the sampling working time ratio comprises: Determine the sampling working time ratio based on the sampling quantity, the highest working time ratio and the lowest working time ratio; and / or, The step of obtaining the natural frequency of the slide rail load structure at the sampling position under the swing vibration mode comprises: Obtain stimulus and response signals; The excitation and response signals are generated after the exciter applies excitation to the slide rail load structure; the suspension length of the exciter is greater than a preset length, and the preset length is negatively correlated with the square value of the first-order natural frequency of the slide rail load structure; The natural frequency of the slide rail load structure in the swing vibration mode is extracted from the excitation and response signals.

6. The method for evaluating the working condition of a slide rail according to claim 4, characterized in that: After the step of training based on the sampling position and the natural frequency to obtain the dynamic model of the slide rail, the method further includes: Selecting the optimal spring unit parameters corresponding to the sampling position by support vector machine regression method; Correcting the dynamic model by using the optimal spring unit parameters and the block Lanczos method; The step of establishing a meta-model based on the numerically calculated modal parameter data of the dynamic model by using a multi-input Gaussian process regression method comprises: The modified dynamic model is used to perform numerical modal analysis of the slide rail load with multiple posture combinations, and the numerically calculated modal parameter results are obtained. The meta-model is established by using the multi-input Gaussian process regression method with the posture state parameters and the corresponding numerically calculated modal parameter results as input.

7. A slide rail working condition evaluation system, characterized in that: The slide rail working condition evaluation system comprises: An acquisition module is used to acquire a vibration acceleration signal of a slide rail load structure and position data of the slide rail load structure; A first determination module, used to determine measured modal information of the slide rail load structure according to the vibration acceleration signal; A meta-model module, used for inputting the posture data into a meta-model to output target modal information; The second determination module is used to determine that the working condition of the slide rail is deteriorated in response to the measured modal information being not within a preset range of the target modal information.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and used to run on the processor, characterized in that: When the processor executes the computer program, the slide rail working condition evaluation method described in any one of claims 1 to 6 is 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 slide rail working condition evaluation method described in any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the slide rail working condition evaluation method according to any one of claims 1 to 6 is implemented.

Images