Guide rail flatness detection and prediction system based on 2D laser sensor
Through the guide rail plane detection and prediction system based on 2D laser sensor, the problems of insufficient static guide rail detection and lack of dynamic guide rail prediction in the prior art are solved, and the accurate detection and prediction of dynamic guide rail plane is realized, which improves the operation of the elevator Comfort and safety.
Patent Information
- Application Number
- CN202410974812.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-19
- Publication Date
- 2024-11-08
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
In the prior art, the plane degree detection of guide rails is mainly concentrated in the static state, ignoring the plane degree of dynamic guide rails, and failing to effectively predict the plane degree changes caused by guide rail wear, affecting the operating comfort and safety of the elevator.
The guide rail plane detection and prediction system based on 2D laser sensor is adopted. By obtaining static plane and planar errors, calculating guide rail running data and base working data, constructing guide rail compensation model and prediction model to achieve accurate detection of dynamic plane degree and predict.
Accurate detection and prediction of dynamic guide rail planes is achieved, and the guide rail wear factor is taken into account, which improves the guide rail straightening effect and the comfort and safety of elevator operation.
Smart Images

Figure CN118913157A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of guide rail flatness detection, and more specifically, to a guide rail flatness detection and prediction system based on a 2D laser sensor. Background Art
[0002] An elevator is a box that is driven by power and runs along a rigid guide rail or an electromechanical device that runs along a fixed line. As the height of buildings increases, the operating speed of elevators continues to increase. With the development of high-speed elevator technology, how to ensure the safety and comfort of elevators during operation has become one of the important topics in the current research on high-speed elevator technology. The vibration problem of the elevator system directly affects the comfort and stability of its operation, and the guide system is closely related to the horizontal vibration of the elevator. The guide rail is an important part of the elevator guide system, and its flatness is one of the key factors affecting the horizontal vibration of the elevator. Although there is relevant content about the guide rail flatness detection in the existing technology, there are still some problems that need to be solved.
[0003] For example, the Chinese patent with publication number CN106643579A provides an automatic detection system and method for the flatness of elevator T-type guide rails. The patent replaces the detection of straightness with the detection of flatness, which can better guide the subsequent guide rail straightening work and more significantly improve the guide rail straightening effect.
[0004] Although the above patent realizes the automated detection of the guide rail flatness, the above patent only detects the flatness of the static guide rail, and ignores the significant difference between the flatness of the dynamic guide rail and the flatness of the static guide rail. In addition, the longer the guide rail runs, the more the guide rail flatness changes due to factors such as guide rail wear. In the prior art, there are few methods that can predict the subsequent guide rail flatness.
[0005] In view of this, the present invention proposes a guide rail flatness detection and prediction system based on a 2D laser sensor to solve the above problems. Summary of the invention
[0006] In order to overcome the above-mentioned defects of the prior art, the present invention provides a guide rail flatness detection and prediction system based on a 2D laser sensor.
[0007] To achieve the above object, the present invention provides the following technical solutions:
[0008] Guide rail flatness detection and prediction system based on 2D laser sensor, including:
[0009] Obtaining the static flatness and flatness error of the guide rail to be inspected, and determining corresponding guide rail operation data based on the static flatness and flatness error;
[0010] The guide rail to be inspected is simulated according to the guide rail operation data to obtain the guide rail working data and the base working data;
[0011] The vibration coefficient of the base is calculated based on the base working data, and the static flatness and the base vibration coefficient are input into the pre-built guide rail compensation model to obtain the dynamic flatness;
[0012] The guide rail working coefficient is calculated based on the guide rail working data, and the dynamic flatness and the guide rail working coefficient are input into the pre-built guide rail prediction model to obtain the predicted flatness.
[0013] Furthermore, the method for obtaining the flatness error of the guide rail to be detected includes:
[0014] The initial errors corresponding to the M detection points are obtained, and the average value of the M initial errors is used as the flatness error. The M detection points are all points on the guide rail to be detected.
[0015] Furthermore, the method for obtaining the initial errors corresponding to the M detection points includes:
[0016]
[0017] Where x is the initial error corresponding to the detection point, x′ is the image displacement in the detector, a is the straight-line distance from point O to the receiving lens, b is the straight-line distance from the receiving lens to the detector, and α, β, and γ are all angle constants.
[0018] Further, the method for determining the corresponding guide rail operation data includes:
[0019] Determine the corresponding flatness interval based on static flatness, obtain the corresponding initial operation data based on the flatness interval, determine the corresponding error interval based on the flatness error, obtain the corresponding operation adjustment data based on the error interval, and calculate the initial operation data and the operation adjustment data to obtain the guide rail operation data.
[0020] Furthermore, the base working data includes a maximum vibration amplitude, a vibration rate value, and a maximum acceleration value. The method for calculating the base vibration coefficient based on the base working data includes:
[0021]
[0022] Where BVC is the base vibration coefficient, MVA is the maximum vibration amplitude, VBE is the vibration rate value, MAE is the maximum acceleration value, log3(·) is the logarithmic function with base 3, cot- 1 (·) is the inverse cotangent function.
[0023] Furthermore, the method for constructing the guide rail compensation model includes:
[0024] A sample data set is obtained, wherein the sample data set includes a historical base vibration coefficient, a historical static flatness, and a historical dynamic flatness. The sample data set is divided into a sample training set and a sample test set, and a regression network is constructed. The historical base vibration coefficient and the historical static flatness in the sample training set are used as input data of the regression network, and the historical dynamic flatness in the sample training set is used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting real-time dynamic flatness. The initial regression network is tested using the sample test set, and the initial regression network that satisfies a preset error value is output as a guide rail compensation model.
[0025] Furthermore, the guide rail working data includes the guide rail grounding resistance, the guide rail temperature value and the operating decibel value. The method for calculating the guide rail working coefficient based on the guide rail working data includes:
[0026]
[0027] Where, RWC is the rail working coefficient, RGC is the rail grounding resistance, RTP is the rail temperature, ODV is the operating decibel value, cosh(·) is the hyperbolic cosine function, and k and R are both constants greater than 0.
[0028] Furthermore, the method for constructing the guide rail prediction model includes:
[0029] A historical data set, a sliding step size L and a sliding window length are preset, and the historical data set includes historical dynamic flatness and historical guide rail working coefficients. The historical data set is converted into multiple training samples using a sliding window method, and the training samples are used as the input of the guide rail prediction model. The historical dynamic flatness after the predicted sliding step size L is used as the output, and the subsequent historical dynamic flatness of each training sample is used as the prediction target. The guide rail prediction model is trained with the prediction accuracy as the training target. A guide rail prediction model is generated that predicts the dynamic flatness at future moments based on the real-time dynamic flatness and the guide rail working coefficient.
[0030] A guide rail flatness detection and prediction method based on a 2D laser sensor, which is used to implement the above-mentioned guide rail flatness detection and prediction system based on a 2D laser sensor, includes:
[0031] Data acquisition module: used to obtain the static flatness and flatness error of the guide rail to be tested, and determine the corresponding guide rail operation data based on the static flatness and flatness error;
[0032] Simulation module: used to simulate the guide rail to be inspected according to the guide rail operation data, and obtain the guide rail working data and the base working data;
[0033] Compensation module: used to calculate the base vibration coefficient based on the base working data, input the static flatness and base vibration coefficient into the pre-built guide rail compensation model to obtain the dynamic flatness;
[0034] Prediction module: used to calculate the guide rail working coefficient based on the guide rail working data, input the dynamic flatness and the guide rail working coefficient into the pre-built guide rail prediction model to obtain the predicted flatness.
[0035] A computer-readable storage medium having a computer program stored thereon, wherein the computer program, when executed, implements the above-mentioned guide rail flatness detection and prediction system based on a 2D laser sensor.
[0036] Compared with the prior art, the present invention has the following beneficial effects:
[0037] The present invention first determines the corresponding guide rail operation data based on the static flatness and flatness error, simulates the guide rail to be detected according to the guide rail operation data, obtains the guide rail working data and the base working data, calculates the base vibration coefficient based on the base working data, inputs the static flatness and the base vibration coefficient into a pre-constructed guide rail compensation model to obtain dynamic flatness, calculates the guide rail working coefficient based on the guide rail working data, inputs the dynamic flatness and the guide rail working coefficient into a pre-constructed guide rail prediction model to obtain predicted flatness. The present invention not only realizes the precise detection of the flatness of the dynamic guide rail, but also takes into account the influencing factors of the guide rail wear, and realizes the prediction of the subsequent guide rail flatness. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] Figure 1 It is a schematic diagram of a guide rail flatness detection and prediction system based on a 2D laser sensor in the present invention;
[0039] Figure 2 It is a flow chart of the guide rail flatness detection and prediction method based on 2D laser sensor in the present invention;
[0040] Figure 3 Schematic diagram of the principle of the laser triangulation method in the present invention;
[0041] Figure 4 A schematic diagram of a computer-readable storage medium in the present invention. DETAILED DESCRIPTION
[0042] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0043] Example 1
[0044] See also Figure 1 As shown, this embodiment discloses a guide rail flatness detection and prediction system based on a 2D laser sensor, including:
[0045] S10: Obtaining the static flatness and flatness error of the guide rail to be inspected, and determining corresponding guide rail operation data based on the static flatness and flatness error;
[0046] In this embodiment, static flatness refers to the flatness value of the static lower guide rail, and the static flatness in this embodiment can be the side flatness of the guide rail or the top flatness of the guide rail. This embodiment is not limited to this. The method for obtaining the guide rail to be detected can be to use a two-dimensional laser sensor as a detection element to detect the flatness of the side and top surfaces of the elevator guide rail. The computer obtains the detection data of the side and top surfaces of the guide rail transmitted by the two-dimensional laser sensor in real time, and calculates and processes these detection data to obtain the flatness data. Obtaining the static flatness of the guide rail is in the prior art. Specifically, it can be seen that the Chinese patent with publication number CN106643579A mentioned in the background technology of the present invention, and this embodiment will not go into too much detail.
[0047] Methods for obtaining the flatness error of the guide rail to be inspected include:
[0048] The initial errors corresponding to the M detection points are obtained, and the average value of the M initial errors is used as the flatness error. The M detection points are all points on the guide rail to be detected.
[0049] It should be noted that the initial error refers to the error between the detection point and the reference plane. There are several methods for obtaining the initial error, such as the gap method, indicator method, optical axis method and laser triangulation method. This embodiment takes the laser triangulation method as an example.
[0050] like Figure 3 As shown, Figure 3 FIG. 1 shows a detection point O1, a laser sensor 10, a converging lens 20, an incident laser beam 30, a guide rail surface 40, a reference plane 50, a detector 60 and a receiving lens 70. Figure 3 The following formula can be obtained:
[0051]
[0052] Combining the above formulas, we can get:
[0053]
[0054] Where OO1 is the straight-line distance between point O and point O1.
[0055] Then the method of obtaining the initial errors corresponding to the M detection points includes:
[0056]
[0057] Where x is the initial error corresponding to the detection point, x′ is the image displacement in the detector, a is the straight-line distance from point O to the receiving lens, b is the straight-line distance from the receiving lens to the detector, and α, β, and γ are all angle constants.
[0058] Methods for determining corresponding guide rail operation data include:
[0059] Determine the corresponding flatness interval based on static flatness, obtain the corresponding initial operation data based on the flatness interval, determine the corresponding error interval based on the flatness error, obtain the corresponding operation adjustment data based on the error interval, and calculate the initial operation data and the operation adjustment data to obtain the guide rail operation data.
[0060] It should be noted that the guide rail operation data in this embodiment represents the data when the guide rail is in a working state. The guide rail operation data includes but is not limited to the operation pressure value and the operation speed value. The operation pressure value refers to the pressure value exerted on the guide rail surface, and the operation speed value refers to the speed value of the object sliding on the guide rail surface. Taking the guide rails in the elevator system as an example, the car guide shoes and counterweight guide shoes in the elevator system will slide on the guide rail surface, and the guide rail surface will be subjected to pressure during the sliding process.
[0061] It can be understood that the smaller the static flatness mentioned above, the smoother the guide rail surface, and the larger the corresponding initial operating data can be set. Similarly, the smaller the flatness error, the smaller the height change of each point on the guide rail surface, and the smaller the operating adjustment data can be set. The initial operating data mentioned above is converted into guide rail operating data after adjustment, and adjustment refers to the adjustment of the numerical value. Taking the above-mentioned operating speed value as an example, the operating speed value in the initial operating data is 1.2m / S, the adjustment speed value in the operating adjustment data is -0.2m / S, and finally the operating speed value in the guide rail operating data is 1m / S.
[0062] S20: simulating the guide rail to be inspected according to the guide rail operation data to obtain guide rail working data and base working data;
[0063] It can be understood that in this embodiment, simulating the guide rail to be tested refers to simulating the working state of the guide rail during the experiment. Taking the guide rail in the elevator system as an example, the guide rail is moved on the guide rail through a test bench or a simulator, and the same operating pressure value and operating speed value are set.
[0064] In this embodiment, the guide rail working data includes but is not limited to the guide rail grounding resistance, the guide rail temperature value and the operating decibel value. The guide rail grounding resistance refers to the grounding resistance detected by the guide rail to be tested during the simulated operation process. The guide rail grounding resistance can be directly obtained through a grounding resistance tester. The guide rail temperature value refers to the surface temperature value of the guide rail to be tested during the simulated operation process. Similarly, the operating decibel value refers to the decibel value detected by the guide rail to be tested during the simulated operation process. The above-mentioned guide rail temperature values and operating decibel values can be obtained through corresponding sensors.
[0065] In this embodiment, the base refers to a device used to fix the guide rail to be tested. For example, in an elevator system, the device used to fix the guide rail is a guide rail bracket. Therefore, in this embodiment, the base can be a guide rail bracket. The base working data includes but is not limited to the maximum vibration amplitude, vibration rate value and maximum acceleration value. The maximum vibration amplitude refers to the maximum amplitude of the vibration signal generated by the base, the vibration rate value refers to the average rate value during the vibration process of the base, and the maximum acceleration value refers to the maximum acceleration value during the vibration process of the base. The above-mentioned maximum acceleration value can be directly obtained through an acceleration sensor, the vibration rate value can be directly obtained through a vibration rate measuring instrument, and the maximum vibration amplitude is obtained through existing analysis software, such as ANSYS or MATLAB.
[0066] It should be added that, since there is a difference between the flatness of the dynamic guide rail and the flatness of the static guide rail, the main reason is that the dynamic guide rail will generate vibration. However, since the vibration data of the guide rail to be detected cannot be accurately obtained during the dynamic simulation of the guide rail to be detected, the vibration data of its base is obtained accordingly, that is, the base working data in this embodiment. The vibration degree of the base is approximately characterized by the base working data, which can also reflect the vibration degree of the guide rail to be detected.
[0067] It is understandable that the guide rail will be worn during operation, and the wear of the guide rail causes its flatness to increase. Therefore, this embodiment obtains the guide rail working data, which can characterize the degree of guide rail wear and thus be used for subsequent predictions.
[0068] S30: Calculate the vibration coefficient of the base based on the base working data, input the static flatness and the base vibration coefficient into a pre-built guide rail compensation model to obtain the dynamic flatness;
[0069] The methods for calculating the vibration coefficient of the foundation based on the foundation working data include:
[0070]
[0071] Where BVC is the base vibration coefficient, MVA is the maximum vibration amplitude, VBE is the vibration rate value, MAE is the maximum acceleration value, log3(·) is the logarithmic function with base 3, and cot -1 (·) is the inverse cotangent function.
[0072] It should be added that, taking the maximum vibration amplitude as an example, the larger the maximum vibration amplitude, the more severe the vibration degree of the base, and the correspondingly more severe the vibration degree of the guide rail to be detected on the base. Therefore, from the above content, it can be seen that in this implementation, the base vibration coefficient is positively correlated with the vibration degree of the guide rail to be detected.
[0073] The construction method of the guide rail compensation model includes:
[0074] A sample data set is obtained, wherein the sample data set includes a historical base vibration coefficient, a historical static flatness, and a historical dynamic flatness. The sample data set is divided into a sample training set and a sample test set, and a regression network is constructed. The historical base vibration coefficient and the historical static flatness in the sample training set are used as input data of the regression network, and the historical dynamic flatness in the sample training set is used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting real-time dynamic flatness. The initial regression network is tested using the sample test set, and the initial regression network that satisfies a preset error value is output as a guide rail compensation model. The initial regression network is preferably a deep neural network model.
[0075] It should be noted that the historical dynamic flatness mentioned above is the historical flatness obtained during the operation of the guide rail. The technical personnel in this field first simulates the operation process of the guide rail. During the simulation, the flatness of the guide rail is detected by an automatic detection system to obtain the historical dynamic flatness. The automatic detection system refers to a system that can complete the guide rail flatness detection without manual labor. For example, the detection system disclosed in the Chinese patent with publication number CN106643579A proposed in the above content of this embodiment can avoid the occurrence of accidents during the operation of the guide rail.
[0076] S40: Calculate the guide rail working coefficient based on the guide rail working data, input the dynamic flatness and the guide rail working coefficient into a pre-built guide rail prediction model to obtain the predicted flatness.
[0077] The methods for calculating the guide rail working coefficient based on the guide rail working data include:
[0078]
[0079] Where, RWC is the rail working coefficient, RGC is the rail grounding resistance, RTP is the rail temperature, ODV is the operating decibel value, cosh(·) is the hyperbolic cosine function, and k and R are both constants greater than 0.
[0080] It should be noted that, taking the guide rail temperature value as an example, the larger the guide rail temperature value, the greater the degree of wear of the guide rail during operation. Therefore, from the above content, it can be seen that in this example, the guide rail working coefficient is positively correlated with the degree of guide rail wear.
[0081] The method for constructing the guide rail prediction model includes:
[0082] A historical data set, a sliding step length L, and a sliding window length are preset. The historical data set includes historical dynamic flatness and historical guide rail working coefficients. The historical data set is converted into multiple training samples using a sliding window method. The training samples are used as inputs of a guide rail prediction model. The historical dynamic flatness after the sliding step length L is predicted as output. The subsequent historical dynamic flatness of each training sample is used as a prediction target. The prediction accuracy is used as a training target to train the guide rail prediction model. A guide rail prediction model is generated that predicts the dynamic flatness at future moments based on the real-time dynamic flatness and the guide rail working coefficient. The guide rail prediction model is an LSTM model.
[0083] It should be noted that the sliding window method is a conventional technical means of the LSTM model, and the present invention will not be further explained in principle here; however, in order to facilitate the implementation of the present invention, the present invention provides the following example of the sliding window method:
[0084] Assume that we want to use the historical data [1,2,3,4,5,6] to train an LSTM model. In this embodiment, we take the prediction time step as 1 as an example, set the sliding step to 1, and set the sliding window length to 3; then 3 groups of training samples and corresponding prediction target data are generated: [1,2,3], [2,3,4] and [3,4,5] as training samples, and [4], [5] and [6] as prediction targets respectively.
[0085] The prediction accuracy can be measured using mean square error or mean absolute error as the loss function, and the weights and biases of the model are updated through the back-propagation algorithm to generate a guide rail prediction model.
[0086] It can be understood that the LSTM model is a variant of a recurrent neural network model commonly used to process and predict time series data. The above historical data set is obtained from experiments by those skilled in the art. For example, those skilled in the art can conduct a guide rail operation simulation experiment for one or several months, and record the dynamic flatness of the guide rail every day as historical data for subsequent training models.
[0087] In this embodiment, the corresponding guide rail operation data is first determined based on the static flatness and flatness error, the guide rail to be inspected is simulated according to the guide rail operation data to obtain the guide rail working data and the base working data, the base vibration coefficient is calculated based on the base working data, the static flatness and the base vibration coefficient are input into a pre-constructed guide rail compensation model to obtain dynamic flatness, the guide rail working coefficient is calculated based on the guide rail working data, the dynamic flatness and the guide rail working coefficient are input into a pre-constructed guide rail prediction model to obtain predicted flatness. In this way, this embodiment not only realizes the precise detection of the flatness of the dynamic guide rail, but also takes into account the influencing factors of the guide rail wear, and realizes the prediction of the subsequent guide rail flatness.
[0088] Example 2
[0089] like Figure 2 As shown, this embodiment provides a guide rail flatness detection and prediction method based on a 2D laser sensor on the basis of Embodiment 1, including:
[0090] Data acquisition module: used to obtain the static flatness and flatness error of the guide rail to be tested, and determine the corresponding guide rail operation data based on the static flatness and flatness error;
[0091] In this embodiment, static flatness refers to the flatness value of the static lower guide rail, and the static flatness in this embodiment can be the side flatness of the guide rail or the top flatness of the guide rail. This embodiment is not limited to this. The method for obtaining the guide rail to be detected can be to use a two-dimensional laser sensor as a detection element to detect the flatness of the side and top surfaces of the elevator guide rail. The computer obtains the detection data of the side and top surfaces of the guide rail transmitted by the two-dimensional laser sensor in real time, and calculates and processes these detection data to obtain the flatness data. Obtaining the static flatness of the guide rail is in the prior art. Specifically, it can be seen that the Chinese patent with publication number CN106643579A mentioned in the background technology of the present invention, and this embodiment will not go into too much detail.
[0092] Methods for obtaining the flatness error of the guide rail to be inspected include:
[0093] The initial errors corresponding to the M detection points are obtained, and the average value of the M initial errors is used as the flatness error. The M detection points are all points on the guide rail to be detected.
[0094] It should be noted that the initial error refers to the error between the detection point and the reference plane. There are several methods for obtaining the initial error, such as the gap method, indicator method, optical axis method and laser triangulation method. This embodiment takes the laser triangulation method as an example.
[0095] like Figure 3 As shown, Figure 3FIG. 1 shows a detection point O1, a laser sensor 10, a converging lens 20, an incident laser beam 30, a guide rail surface 40, a reference plane 50, a detector 60 and a receiving lens 70. Figure 3 The following formula can be obtained:
[0096]
[0097] Combining the above formulas, we can get:
[0098]
[0099] Where OO1 is the straight-line distance between point O and point O1.
[0100] Then the method of obtaining the initial errors corresponding to the M detection points includes:
[0101]
[0102] Where x is the initial error corresponding to the detection point, x′ is the image displacement in the detector, a is the straight-line distance from point O to the receiving lens, b is the straight-line distance from the receiving lens to the detector, and α, β, and γ are all angle constants.
[0103] Methods for determining corresponding guide rail operation data include:
[0104] Determine the corresponding flatness interval based on static flatness, obtain the corresponding initial operation data based on the flatness interval, determine the corresponding error interval based on the flatness error, obtain the corresponding operation adjustment data based on the error interval, and calculate the initial operation data and the operation adjustment data to obtain the guide rail operation data.
[0105] Simulation module: used to simulate the guide rail to be inspected according to the guide rail operation data, and obtain the guide rail working data and the base working data;
[0106] It can be understood that in this embodiment, simulating the guide rail to be tested refers to simulating the working state of the guide rail during the experiment. Taking the guide rail in the elevator system as an example, the guide rail is moved on the guide rail through a test bench or a simulator, and the same operating pressure value and operating speed value are set.
[0107] In this embodiment, the guide rail working data includes but is not limited to the guide rail grounding resistance, the guide rail temperature value and the operating decibel value. The guide rail grounding resistance refers to the grounding resistance detected by the guide rail to be tested during the simulated operation process. The guide rail grounding resistance can be directly obtained through a grounding resistance tester. The guide rail temperature value refers to the surface temperature value of the guide rail to be tested during the simulated operation process. Similarly, the operating decibel value refers to the decibel value detected by the guide rail to be tested during the simulated operation process. The above-mentioned guide rail temperature values and operating decibel values can be obtained through corresponding sensors.
[0108] In this embodiment, the base refers to a device used to fix the guide rail to be tested. For example, in an elevator system, the device used to fix the guide rail is a guide rail bracket. Therefore, in this embodiment, the base can be a guide rail bracket. The base working data includes but is not limited to the maximum vibration amplitude, vibration rate value and maximum acceleration value. The maximum vibration amplitude refers to the maximum amplitude of the vibration signal generated by the base, the vibration rate value refers to the average rate value during the vibration process of the base, and the maximum acceleration value refers to the maximum acceleration value during the vibration process of the base. The above-mentioned maximum acceleration value can be directly obtained through an acceleration sensor, the vibration rate value can be directly obtained through a vibration rate measuring instrument, and the maximum vibration amplitude is obtained through existing analysis software, such as ANSYS or MATLAB.
[0109] Compensation module: used to calculate the base vibration coefficient based on the base working data, input the static flatness and base vibration coefficient into the pre-built guide rail compensation model to obtain the dynamic flatness;
[0110] The methods for calculating the vibration coefficient of the foundation based on the foundation working data include:
[0111]
[0112] Where BVC is the base vibration coefficient, MVA is the maximum vibration amplitude, VBE is the vibration rate value, MAE is the maximum acceleration value, log3(·) is the logarithmic function with base 3, cot- 1 (·) is the inverse cotangent function.
[0113] It should be added that, taking the maximum vibration amplitude as an example, the larger the maximum vibration amplitude, the more severe the vibration degree of the base, and the correspondingly more severe the vibration degree of the guide rail to be detected on the base. Therefore, from the above content, it can be seen that in this implementation, the base vibration coefficient is positively correlated with the vibration degree of the guide rail to be detected.
[0114] The construction method of the guide rail compensation model includes:
[0115] A sample data set is obtained, wherein the sample data set includes a historical base vibration coefficient, a historical static flatness, and a historical dynamic flatness. The sample data set is divided into a sample training set and a sample test set, and a regression network is constructed. The historical base vibration coefficient and the historical static flatness in the sample training set are used as input data of the regression network, and the historical dynamic flatness in the sample training set is used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting real-time dynamic flatness. The initial regression network is tested using the sample test set, and the initial regression network that satisfies a preset error value is output as a guide rail compensation model. The initial regression network is preferably a deep neural network model.
[0116] Prediction module: used to calculate the guide rail working coefficient based on the guide rail working data, input the dynamic flatness and the guide rail working coefficient into the pre-built guide rail prediction model to obtain the predicted flatness.
[0117] The methods for calculating the guide rail working coefficient based on the guide rail working data include:
[0118]
[0119] Where, RWC is the rail working coefficient, RGC is the rail grounding resistance, RTP is the rail temperature, ODV is the operating decibel value, cosh(·) is the hyperbolic cosine function, and k and R are both constants greater than 0.
[0120] It should be noted that, taking the guide rail temperature value as an example, the larger the guide rail temperature value, the greater the degree of wear of the guide rail during operation. Therefore, from the above content, it can be seen that in this example, the guide rail working coefficient is positively correlated with the degree of guide rail wear.
[0121] The method for constructing the guide rail prediction model includes:
[0122] A historical data set, a sliding step length L, and a sliding window length are preset. The historical data set includes historical dynamic flatness and historical guide rail working coefficients. The historical data set is converted into multiple training samples using a sliding window method. The training samples are used as inputs of a guide rail prediction model. The historical dynamic flatness after the sliding step length L is predicted as output. The subsequent historical dynamic flatness of each training sample is used as a prediction target. The prediction accuracy is used as a training target to train the guide rail prediction model. A guide rail prediction model is generated that predicts the dynamic flatness at future moments based on the real-time dynamic flatness and the guide rail working coefficient. The guide rail prediction model is an LSTM model.
[0123] It can be understood that the LSTM model is a variant of a recurrent neural network model commonly used to process and predict time series data. The above historical data set is obtained from experiments by those skilled in the art. For example, those skilled in the art can conduct a guide rail operation simulation experiment for one or several months, and record the dynamic flatness of the guide rail every day as historical data for subsequent training models.
[0124] Example 3
[0125] The present embodiment discloses an electronic device, including a power supply, an interface, a keyboard, a memory, a central processing unit, and a computer program stored in the memory and executable on the central processing unit. When the central processing unit executes the computer program, the guide rail flatness detection and prediction system based on a 2D laser sensor provided by the above-mentioned methods is implemented. The interface includes a network interface and a data interface. The network interface includes a wired or wireless interface, and the data interface includes an input or output interface.
[0126] Since the electronic device introduced in this embodiment is an electronic device used to implement the guide rail flatness detection and prediction system based on 2D laser sensors in the embodiments of this application, based on the guide rail flatness detection and prediction system based on 2D laser sensors introduced in the embodiments of this application, a person skilled in the art can understand the specific implementation of the electronic device of this embodiment and its various variations, so how the electronic device implements the method in the embodiments of this application will not be described in detail here. As long as a person skilled in the art implements the electronic device used by the guide rail flatness detection and prediction system based on 2D laser sensors in the embodiments of this application, it belongs to the scope of protection of this application.
[0127] Example 4
[0128] like Figure 4 As shown, the present embodiment discloses a computer-readable storage medium, on which a computer program is stored. When the computer program is executed, the guide rail flatness detection and prediction system based on the 2D laser sensor is implemented.
[0129] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters, weights and thresholds in the formula are set by technicians in this field according to actual conditions.
[0130] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present invention is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website site, computer, server or data center to another website site, computer, server or data center through a wired network or a wireless network. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD) or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.
[0131] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed in the present invention can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.
[0132] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0133] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.
[0134] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0135] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
[0136] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.
[0137] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. The guide rail flatness detection and prediction system based on 2D laser sensor is characterized by: include: Obtaining the static flatness and flatness error of the guide rail to be inspected, and determining corresponding guide rail operation data based on the static flatness and flatness error; The guide rail to be inspected is simulated according to the guide rail operation data to obtain the guide rail working data and the base working data; The vibration coefficient of the base is calculated based on the base working data, and the static flatness and the base vibration coefficient are input into the pre-built guide rail compensation model to obtain the dynamic flatness; The guide rail working coefficient is calculated based on the guide rail working data, and the dynamic flatness and the guide rail working coefficient are input into the pre-built guide rail prediction model to obtain the predicted flatness.
2. The guide rail flatness detection and prediction system based on 2D laser sensor according to claim 1 is characterized in that: Methods for obtaining the flatness error of the guide rail to be inspected include: The initial errors corresponding to the M detection points are obtained, and the average value of the M initial errors is used as the flatness error. The M detection points are all points on the guide rail to be detected.
3. The guide rail flatness detection and prediction system based on 2D laser sensor according to claim 2 is characterized in that: The method of obtaining the initial errors corresponding to the M detection points includes: Where x is the initial error corresponding to the detection point, x' is the image displacement in the detector, a is the straight-line distance from point O to the receiving lens, b is the straight-line distance from the receiving lens to the detector, and α, β, and γ are all angle constants.
4. The guide rail flatness detection and prediction system based on 2D laser sensor according to claim 2, characterized in that: Methods for determining corresponding guide rail operation data include: Determine the corresponding flatness interval based on static flatness, obtain the corresponding initial operation data based on the flatness interval, determine the corresponding error interval based on the flatness error, obtain the corresponding operation adjustment data based on the error interval, and calculate the initial operation data and the operation adjustment data to obtain the guide rail operation data.
5. The guide rail flatness detection and prediction system based on 2D laser sensor according to claim 1, characterized in that: The base working data includes the maximum vibration amplitude, vibration rate value and maximum acceleration value. The method for calculating the base vibration coefficient based on the base working data includes: Where BVC is the base vibration coefficient, MVA is the maximum vibration amplitude, VBE is the vibration rate value, MAE is the maximum acceleration value, log3(·) is the logarithmic function with base 3, and cot -1 (·) is the inverse cotangent function.
6. The guide rail flatness detection and prediction system based on 2D laser sensor according to claim 1, characterized in that: The construction method of the guide rail compensation model includes: A sample data set is obtained, wherein the sample data set includes a historical base vibration coefficient, a historical static flatness, and a historical dynamic flatness. The sample data set is divided into a sample training set and a sample test set, and a regression network is constructed. The historical base vibration coefficient and the historical static flatness in the sample training set are used as input data of the regression network, and the historical dynamic flatness in the sample training set is used as output data of the regression network. The regression network is trained to obtain an initial regression network for predicting real-time dynamic flatness. The initial regression network is tested using the sample test set, and the initial regression network that satisfies a preset error value is output as a guide rail compensation model.
7. The guide rail flatness detection and prediction system based on 2D laser sensor according to claim 1, characterized in that: The guide rail working data includes the guide rail grounding resistance, the guide rail temperature value and the operating decibel value. The method for calculating the guide rail working coefficient based on the guide rail working data includes: Where, RWC is the rail working coefficient, RGC is the rail grounding resistance, RTP is the rail temperature, ODV is the operating decibel value, cosh(·) is the hyperbolic cosine function, and k and R are both constants greater than 0.
8. The guide rail flatness detection and prediction system based on 2D laser sensor according to claim 1, characterized in that: The construction method of the guide rail prediction model includes: A historical data set, a sliding step size L and a sliding window length are preset, and the historical data set includes historical dynamic flatness and historical guide rail working coefficients. The historical data set is converted into multiple training samples using a sliding window method, and the training samples are used as the input of the guide rail prediction model. The historical dynamic flatness after the predicted sliding step size L is used as the output, and the subsequent historical dynamic flatness of each training sample is used as the prediction target. The guide rail prediction model is trained with the prediction accuracy as the training target. A guide rail prediction model is generated that predicts the dynamic flatness at future moments based on the real-time dynamic flatness and the guide rail working coefficient.
9. A guide rail flatness detection and prediction method based on a 2D laser sensor, which is used to implement a guide rail flatness detection and prediction system based on a 2D laser sensor as described in any one of claims 1 to 8, characterized in that: include: Data acquisition module: used to obtain the static flatness and flatness error of the guide rail to be tested, and determine the corresponding guide rail operation data based on the static flatness and flatness error; Simulation module: used to simulate the guide rail to be inspected according to the guide rail operation data, and obtain the guide rail working data and the base working data; Compensation module: used to calculate the base vibration coefficient based on the base working data, input the static flatness and base vibration coefficient into the pre-built guide rail compensation model to obtain the dynamic flatness; Prediction module: used to calculate the guide rail working coefficient based on the guide rail working data, input the dynamic flatness and the guide rail working coefficient into the pre-built guide rail prediction model to obtain the predicted flatness.
10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed, the guide rail flatness detection and prediction system based on a 2D laser sensor according to any one of claims 1 to 8 is implemented.
Citation Information
Patent Citations
Flatness real-time calibration compensation measurement method based on multiple PSDs
CN112325808A
Modeling method for predicting vertical straightness and angle error of linear shaft of machine tool
CN115455611A
Workpiece surface roughness prediction method
CN116523865A
Non-contact valve plate flatness detection device
CN210773947U
Installation error measuring device for elevator guide rail
JP1992028686A
Cited By
Photo-thermal backboard flatness detection method and device based on multi-source sensor
CN120831084A
