Brake clearance prediction method and device, electronic equipment and readable storage medium

Abstract

The invention provides a brake clearance prediction method and device, electronic equipment and a readable storage medium, and belongs to the technical field of data prediction.The method comprises the steps that a fatigue backstepping model is determined based on simulation fatigue parameter data and historical fatigue parameter data, the fatigue back-stepping model is used for constructing a mapping relation between running state data and fatigue state data of the brake; determining a brake clearance-fatigue relation model based on the fatigue state data and the first brake clearance data; the brake clearance-fatigue relation model is used for constructing a mapping relation between brake clearance and fatigue state data of the brake; and the brake clearance of the target brake is predicted based on the fatigue backstepping model, the brake clearance-fatigue relation model and the target operation state data, and second brake clearance data are obtained. According to the brake clearance prediction method and device, the electronic equipment and the readable storage medium, the accuracy of brake clearance data prediction of the brake can be improved.

Description

Technical Field

[0001] The present disclosure belongs to the technical field of data prediction, and more specifically, relates to a brake clearance prediction method and device, an electronic device, and a readable storage medium. Background Art

[0002] With the acceleration of modern urbanization, high-rise buildings are increasing day by day. As a vertical transportation tool, the safety and reliability of elevators are directly related to the safety of people's lives and property. As a key safety component of elevators, the performance of brakes directly affects the safe operation of elevators. As one of the important indicators of brake performance, the brake clearance has an important impact on the braking effect and operating stability of elevators. Therefore, accurate prediction and real-time monitoring of the brake clearance of elevator brakes have become an important technical means to ensure the safe operation of elevators.

[0003] However, the current monitoring of the brake clearance of some elevator brakes still relies on manual regular inspections, which is not only inefficient but also difficult to ensure the accuracy and timeliness of monitoring. Some monitoring technologies have adopted some automated monitoring technologies, but there is still a problem of low data prediction accuracy. Summary of the invention

[0004] The purpose of the present disclosure is to provide a brake clearance prediction method and device, an electronic device, and a readable storage medium to improve the accuracy of brake clearance data prediction of a brake.

[0005] According to a first aspect of an embodiment of the present disclosure, a brake clearance prediction method is provided, comprising: Determine a fatigue back-calculation model based on simulated fatigue parameter data and historical fatigue parameter data, and the fatigue back-calculation model is used to construct a mapping relationship between the brake's operating state data and fatigue state data; Determine a brake clearance-fatigue relationship model based on fatigue state data and first brake clearance data; the first brake clearance data is historical brake clearance data; the brake clearance-fatigue relationship model is used to construct a mapping relationship between the brake clearance and fatigue state data of the brake; The brake clearance of the target brake is predicted based on the fatigue back-calculation model, the brake clearance-fatigue relationship model and the target operating state data to obtain second brake clearance data.

[0006] According to a second aspect of the embodiments of the present disclosure, a brake clearance prediction device is provided, comprising: A fatigue back-calculation model building module is used to determine a fatigue back-calculation model based on simulated fatigue parameter data and historical fatigue parameter data, and the fatigue back-calculation model is used to build a mapping relationship between the operating state data and fatigue state data of the brake; A brake clearance-fatigue relationship model building module is used to determine a brake clearance-fatigue relationship model based on fatigue state data and first brake clearance data; the first brake clearance data is historical brake clearance data; the brake clearance-fatigue relationship model is used to build a mapping relationship between the brake clearance and fatigue state data of the brake; The brake clearance prediction module is used to predict the brake clearance of the target brake based on the fatigue back-calculation model, the brake clearance-fatigue relationship model and the target operating state data to obtain second brake clearance data.

[0007] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the above-mentioned brake clearance prediction method when executing the computer program.

[0008] According to a fourth aspect of the embodiments of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned brake clearance prediction method are implemented.

[0009] The beneficial effects of the brake clearance prediction method and device, electronic device, and readable storage medium provided by the embodiments of the present disclosure are: the embodiments of the present disclosure accurately construct a fatigue inverse model by integrating simulation and historical fatigue parameter data, and realize accurate mapping between the brake operating state and the fatigue state. The embodiments of the present disclosure also construct a brake clearance-fatigue relationship model in combination with historical brake clearance data, and deeply reveal the intrinsic connection between the brake clearance and the fatigue state. On this basis, the embodiments of the present disclosure can analyze the brake clearance changes of the target brake under a specific operating state in real time or predictively, and provide accurate second brake clearance data (i.e., predicted brake clearance data). This prediction result not only helps to optimize the maintenance strategy of the brake system, but also effectively prevents potential risks caused by improper brake clearance, improves the safety and reliability of the equipment, and reduces failure rate and maintenance costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solutions in the embodiments of the present disclosure, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present disclosure. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0011] Figure 1 A schematic diagram of a flow chart of a brake clearance prediction method provided by an embodiment of the present disclosure; Figure 2 A schematic flow chart of another brake clearance prediction method provided by an embodiment of the present disclosure; Figure 3 A structural block diagram of a brake clearance prediction device provided by an embodiment of the present disclosure; Figure 4 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. DETAILED DESCRIPTION

[0012] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present disclosure. However, it should be clear to those skilled in the art that the present disclosure may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obstructing the description of the present disclosure with unnecessary details.

[0013] In order to make the purpose, technical solutions and advantages of the present disclosure more clear, specific embodiments will be described below in conjunction with the accompanying drawings.

[0014] Please refer to Figure 1 , Figure 1 A schematic flow chart of a brake clearance prediction method provided in an embodiment of the present disclosure, the method may include S101 to S103.

[0015] S101: Determine a fatigue back-estimation model based on simulated fatigue parameter data and historical fatigue parameter data, where the fatigue back-estimation model is used to construct a mapping relationship between the operating state data and fatigue state data of the brake.

[0016] In this embodiment, the simulated fatigue parameter data is the fatigue parameter data of the brake simulated in the simulation environment. The historical fatigue parameter data is the actual fatigue parameter data detected and recorded during the historical operation and use of the elevator brake. Both the simulated fatigue parameter data and the historical fatigue parameter data may include stress-related parameters (such as stress amplitude, stress mean, number of stress cycles, etc.), brake performance parameters (such as brake response time, brake current, etc.) and elevator operating condition parameters (such as number of operations, operating vibration frequency, elevator operating speed, etc.). The operating status data of the brake may include the operating status data of the elevator brake under complex working conditions, specifically, it may include operating vibration frequency, brake response time, brake current, number of operations and elevator operating speed.

[0017] Exemplarily, fatigue state data may be obtained by inputting the operating state data into a fatigue inverse model.

[0018] In this embodiment, the brake clearance prediction method further includes: The fatigue state data is determined based on the simulated fatigue parameter data, and a mapping relationship between the operating state data of the brake and the fatigue state data is constructed.

[0019] In this embodiment, the fatigue state data is an evaluation value or grade calculated based on the simulated fatigue parameter data, which can indicate the fatigue degree of the brake. For example, the fatigue state data of the brake calculated based on the simulated fatigue parameter data is 80 points. The fatigue state of the brake can be determined based on the evaluation value.

[0020] For example, for the operating status data of the elevator brake under complex working conditions, five key indicators are introduced using the ANSYS (Analysis Systems) simulation platform: operating vibration frequency, braking response time, braking current, number of operations and elevator operating speed. These five key indicators are used as input parameters and simulated in the ANSYS simulation environment. Through models such as material mechanics and structural dynamics, the fatigue data of the brake under different working conditions, that is, the simulated fatigue parameter data, are calculated. Furthermore, the calculation of simulated fatigue parameter data can be achieved through stress analysis and fatigue life prediction models. In the ANSYS simulation environment, the stress-life (Stress - Number of Cycles, SN) curve or fatigue damage accumulation theory (such as Miner's law) can be used to predict fatigue data.

[0021] S102: Determine a brake clearance-fatigue relationship model based on the fatigue state data and the first brake clearance data. The first brake clearance data is historical brake clearance data. The brake clearance-fatigue relationship model is used to construct a mapping relationship between the brake clearance of the brake and the fatigue state data.

[0022] In this embodiment, the first brake clearance data is the actual brake clearance data detected and recorded in the history of the elevator brake. The change of the brake clearance will affect the working state of the brake, and then affect its fatigue state. By analyzing the correspondence between a large number of brake clearances and fatigue states, the laws and patterns therein can be found to determine the internal connection between the two, thereby constructing a model that can describe this mapping relationship - the brake clearance-fatigue relationship model.

[0023] For example, the elevator brake can be tested regularly, the actual brake clearance data can be recorded as the first brake clearance data, and the fatigue state data of the brake at that moment can be obtained at the same time. The fatigue state data can include various information reflecting fatigue, such as wear degree, crack condition, performance degradation index, etc. A regression analysis method can be used to establish a brake clearance-fatigue relationship model between the brake clearance as an independent variable and the fatigue state related index as a dependent variable.

[0024] S103: predicting the brake clearance of the target brake based on the fatigue back-calculation model, the brake clearance-fatigue relationship model and the target operating state data to obtain second brake clearance data.

[0025] In this embodiment, the second brake clearance data is the predicted brake clearance data. The target brake is the elevator brake to be detected, and the target operating state data is the operating state data of the elevator brake to be detected.

[0026] Exemplarily, the fatigue inverse model is used to infer the fatigue state of the brake based on known brake operation state data (such as operation vibration frequency, brake response time, etc.). The brake clearance-fatigue relationship model establishes the connection between the fatigue state and the brake clearance. When the target operation state data (a new set of operation-related data) of the target brake is obtained, the corresponding fatigue state data is first obtained through the fatigue inverse model, and then based on the brake clearance-fatigue relationship model, the corresponding brake clearance is determined according to the fatigue state, and the second brake clearance data (predicted brake clearance data) can be obtained.

[0027] For example, before the regular maintenance of the elevator, the maintenance personnel can first collect the recent operation status data of the elevator as the target operation status data through relevant sensors and monitoring equipment. Then use the above method to predict the brake clearance of the target brake. If the predicted brake clearance exceeds the reasonable range, the maintenance personnel can adjust the brake clearance or check the relevant components in a targeted manner during the actual maintenance. For example, when the predicted brake clearance is greater than or equal to the preset first brake clearance threshold (that is, the brake clearance is too large), it is necessary to check the wear of the brake pad to see if it needs to be replaced; if the predicted clearance is less than or equal to the second brake clearance threshold (that is, the brake clearance is too small), it is necessary to check whether there is a problem with the installation of the brake or whether there is any foreign object obstruction, so as to prepare for maintenance in advance and improve maintenance efficiency and the safety of elevator operation. The first brake clearance threshold is greater than the second brake clearance threshold.

[0028] It can be concluded from the above that this embodiment improves the comprehensiveness, accuracy and efficiency of elevator brake monitoring and prediction. On the one hand, this embodiment builds a fatigue inverse model by integrating simulation and historical data, and combines the brake clearance-fatigue relationship model to achieve comprehensive analysis and prediction of the brake operating status and brake clearance changes, overcome the limitations of a single monitoring method, and ensure the comprehensiveness and accuracy of monitoring.

[0029] On the other hand, this embodiment enhances data processing capabilities, can efficiently mine the patterns behind the data, effectively reduce prediction errors and uncertainties, and improve prediction accuracy.

[0030] On the other hand, this embodiment fully considers the actual operating environment and working conditions of the brake, enhances the model's ability to handle complex problems such as nonlinearity and time-varying, and ensures that the brake clearance prediction result is closer to the actual situation.

[0031] In summary, the brake clearance prediction method constructed in this embodiment reduces the maintenance difficulty of the elevator brake, improves the accuracy of the brake clearance prediction, and further promotes the intelligent development of elevator brake monitoring and prediction technology.

[0032] In one embodiment of the present disclosure, the brake clearance prediction method further includes: The operating status data includes brake performance data and brake operating condition data.

[0033] The brake performance data and brake operating condition data are input into the simulation environment for calculation to obtain simulation fatigue parameter data.

[0034] In this embodiment, the simulation environment can be understood as a virtual platform built based on computer software and related technologies, in which various working conditions and performances of elevator brakes in actual operation can be simulated. In the simulation environment, by inputting relevant parameters of brake operation, the operation state of the brake can be simulated and analyzed using pre-established mathematical models and algorithms to obtain results similar to those produced in actual operation, such as fatigue parameter data. It can integrate theories and models of multiple disciplines such as material mechanics, structural dynamics, and thermodynamics to accurately simulate the complex behavior of the brake.

[0035] For example, the performance data (such as braking response time, braking current) and operating condition data (such as operating vibration frequency, number of operations, elevator operating speed) of the elevator brake can be collected through sensors and monitoring equipment. After preprocessing the collected performance data and operating condition data of the brake, they are input into the simulation environment as input information. In the simulation environment, an elevator brake operation mathematical model has been established, which can reflect the operating characteristics and fatigue generation mechanism of the brake under different parameter combinations. After inputting the performance data and operating condition data into the simulation environment, the elevator brake operation mathematical model can be calculated according to the built-in algorithm and logic, considering factors such as friction, energy loss, stress distribution, etc., and finally obtain the simulated fatigue parameter data. The calculated simulated fatigue parameter data will be output for subsequent analysis and application. These simulated fatigue parameter data can be used to evaluate the current state of the brake, predict its remaining life, analyze the impact of different working conditions on fatigue, etc., and provide a basis for maintenance and management decisions.

[0036] In this embodiment, the brake performance data may include: brake response time and brake current, etc., and the brake operating condition data may include: operating vibration frequency, operating times and elevator operating speed, etc.

[0037] Input the brake performance data and brake operating condition data into the simulation environment for calculation, and obtain the simulated fatigue parameter data, which may include: The running vibration frequency, braking response time, braking current, running times and elevator running speed are input into the simulation environment for calculation to obtain the simulation fatigue parameter data.

[0038] For example, elevator maintenance company A is responsible for elevator maintenance in multiple communities. They regularly collect various data of elevator brakes and input them into the simulation environment. By analyzing the simulated fatigue parameter data, it is found that after a certain number of times of operation, the simulated fatigue parameters of the brake of a certain elevator show that the braking response time has a tendency to gradually increase, and the fatigue level increases to the preset safety threshold. Maintenance personnel can arrange to inspect and maintain the brake in advance, such as adjusting the brake clearance, checking the wear of the brake pads, etc., to avoid brake failures in actual operation and ensure the safe operation of the elevator. At the same time, through simulation analysis under different operating conditions, the operation strategy of the elevator can also be optimized, such as adjusting the operating speed and start-stop frequency of the elevator to reduce the fatigue of the brake, extend its service life, reduce maintenance costs and improve the reliability of the elevator.

[0039] This embodiment constructs a simulation environment to simulate the actual operation of the elevator brake, and combines multi-dimensional performance and working condition data to effectively predict the fatigue state of the brake and the change in brake clearance. This embodiment not only improves the accuracy of the prediction, but also realizes early warning and maintenance optimization of the elevator brake, significantly improves the safety and operation efficiency of the elevator, reduces maintenance costs, and provides technical support for elevator maintenance management.

[0040] In one embodiment of the present disclosure, determining a fatigue inverse model based on simulated fatigue parameter data and historical fatigue parameter data includes: The initial fatigue inverse model is determined based on the simulation fatigue parameter data and operating status data.

[0041] The initial fatigue inverse model is updated based on the loss function and historical fatigue parameter data to obtain the fatigue inverse model.

[0042] In this embodiment, the fatigue back-calculation model is a model used to construct a mapping relationship between the operating status data and the fatigue status data of the brake.

[0043] Fatigue state data can be obtained based on the simulated fatigue parameter data.

[0044] For example, the fatigue inverse model can be determined based on data-driven technologies such as the nonlinear autoregressive network (NARX) model and inverse iterative technologies such as the algebraic reconstruction technique (ART), combined with simulation fatigue parameter data and operating status data. The NARX model can be expressed as: y(t)=F(y(t−1),…,y(t−n),x(t),…,x(t−m)) Among them, y(t) represents the fatigue state data at time t, x(t) represents the operating state data at time t, n represents the order of the NARX model, m represents the order of the NARX model, and F(•) represents the function.

[0045] In this embodiment, y(t-1), ..., y(tn) may represent a series of brake fatigue state data at moments (t-1 to tn). The reason why the fatigue state in the past is considered in the NARX model is that the fatigue process is a memory process. For example, the fatigue state of the brake at the current moment may be affected by the fatigue state data at the previous moment (y(t-1)), the previous two moments (y(t-2)), and so on until the previous n moments (y(tn)). n represents the order of the fatigue state data considered in the past by the NARX model, that is, looking back at the fatigue state data of the past n time steps to predict the current state.

[0046] x(t-1),…,x(tm) represent the operating status data of a series of moments before moment t (t to tm). The past operating status data will have an impact on the current fatigue state. m represents the order of the past operating status data considered by the NARX model, that is, looking back at the operating status of the past m time steps to predict the current fatigue state data. These data reflect the cumulative impact of historical changes in the operating status on the fatigue state.

[0047] For example, if m=2, then x(t-1) and x(t-2) represent the operating status data of the first two time steps. Assuming that the elevator ran faster or braked more times in the previous few times, these historical operating status data will have a cumulative effect on the fatigue state of the current brake. The model takes these data into account to better understand the development process of fatigue and thus more accurately predict y(t).

[0048] F(•) is a functional relationship, which indicates how to calculate the fatigue state data y(t) at the current time t based on the past fatigue state data (y(t-1), ..., y(tn)) and the current and past operating state data (x(t), ..., x(tm)). The F(•) function can be a nonlinear function, which reflects the interaction between various factors in the fatigue process. When building a model based on data-driven technology, F(•) can be trained by methods such as neural networks. Its specific form and parameters are determined by the training data, with the aim of establishing an accurate mapping relationship between operating state data and fatigue state data.

[0049] The ART algorithm can be used to iteratively adjust the parameters of the NARX model, minimize the error between the predicted fatigue state data value and the actual fatigue state data, and establish a mapping relationship from the brake operating state data to the fatigue state data.

[0050] In this embodiment, the loss function is:

[0051] Among them, L represents the loss value, N represents the number of samples, represents the jth actual fatigue state data, represents the j-th predicted fatigue state data.

[0052] This embodiment can accurately map the operating status data of the brake to its fatigue state by establishing a fatigue back-calculation model based on simulated fatigue parameters and historical data, thereby improving prediction accuracy.

[0053] In one embodiment of the present disclosure, determining an initial fatigue inverse model based on simulated fatigue parameter data and operating status data includes: The simulated fatigue parameter data is preprocessed and feature extracted to obtain a fatigue feature set, which includes stress feature data and external fatigue feature data.

[0054] The initial fatigue inverse model is determined based on stress characteristic data, external fatigue characteristic data and operating status data.

[0055] In this embodiment, the stress characteristic data may include data related to various stresses that the brake is subjected to during operation. For example, the contact stress caused by the friction force generated during elevator braking, the stress distribution caused by the deformation of the components, etc. Specifically, for example, the average stress on the contact surface between the brake pad and the brake disc, the maximum stress value, and the change pattern of stress over time or the number of operations. The stress characteristic data reflects the performance of the brake in terms of mechanical properties and is one of the important factors in evaluating fatigue.

[0056] External fatigue characteristic data may include characteristic data corresponding to external factors that can affect the fatigue state of the brake, in addition to those characteristics directly related to stress. For example, the influence of vibration characteristics reflected by the operating vibration frequency on brake fatigue, the cumulative effect characteristics reflected by the number of operations, and the characteristics of external conditions such as ambient temperature and humidity on brake material performance and fatigue.

[0057] Exemplarily, statistical methods and filtering techniques, such as mean filtering and median filtering, are used to clean the simulated fatigue parameter data, remove outliers and noise, and perform other data preprocessing to ensure the accuracy and reliability of the data. Through mathematical analysis methods, such as principal component analysis (PCA) and wavelet transform, a fatigue feature set that can reflect the nature of fatigue is extracted. For stress data, statistical features such as stress amplitude, stress frequency, stress mean, and local features such as stress concentration sites can be calculated. For external fatigue features, relevant feature quantities are extracted from the operating status data, such as quantifying the number of operations and performing spectral analysis on the vibration frequency to obtain relevant features.

[0058] This embodiment constructs a fatigue feature set including stress features and external fatigue features by preprocessing and extracting features from the simulated fatigue parameter data. This embodiment not only improves the accuracy and reliability of the data, but also extracts key fatigue features through scientific methods, laying a solid foundation for the establishment of the initial fatigue inverse model. The model's predictive ability and adaptability are enhanced, so that the model can more accurately reflect the actual fatigue state of the brake.

[0059] In one embodiment of the present disclosure, determining a brake clearance-fatigue relationship model based on fatigue state data and first brake clearance data includes: A brake clearance-fatigue relationship model is determined based on the fatigue state data, the first brake clearance data and the first formula.

[0060] The first formula is:

[0061]

[0062] in, Indicates the fatigue state data of the brake, Gap indicates the first brake clearance data, Stress indicates the structural stress, S N Curve represents the stress-cycle number curve, and a, b, c, and d represent preset parameters.

[0063] In this embodiment, fatigue state data can be obtained based on the fatigue back-calculation model. The fatigue state data is combined with the first brake clearance data, the American Society of Mechanical Engineers (ASME) structural stress (i.e., Stress) and the main SN curve (i.e., S N Curve) data, a model of the relationship between brake clearance and fatigue can be constructed.

[0064] For example, the brake clearance-fatigue relationship model can use the brake clearance data as input and the fatigue state data obtained by the fatigue inverse model as output for training to establish a mathematical relationship between the brake clearance data and the fatigue state data. The preset parameter values ​​can be: a=0.5, b=2, c=1, d=0.

[0065] This embodiment constructs a brake clearance-fatigue relationship model, combines fatigue state data, brake clearance data, structural stress and SN curve, and effectively quantifies the complex relationship between brake clearance and fatigue. This embodiment improves the accuracy of prediction, enhances the applicability of the model, provides a scientific basis for the maintenance and life prediction of elevator brakes, helps reduce maintenance costs, and improves the safety and reliability of equipment operation.

[0066] In one embodiment of the present disclosure, the brake clearance prediction method further includes: The brake clearance-fatigue relationship model is updated based on the particle swarm optimization algorithm to obtain an updated brake clearance-fatigue relationship model.

[0067] In this embodiment, the particle swarm optimization (PSO) algorithm is: vi(t+1)=w*vi(t)+cl*r1*(pi−xi(t))+c2*r2*(pg−xi(t)) xi(t+1)=xi(t)+vi(t+1) Among them, vi(t) represents the velocity of particle i at time t, xi(t) represents the position of particle i at time t, w represents the inertia weight, c1 and c2 represent learning factors, r1 and r2 represent random numbers, pi represents the historical optimal position of particle i, and pg represents the global optimal position of all particles.

[0068] In this embodiment, the PSO algorithm optimizes the brake clearance-fatigue relationship model to evaluate the accuracy and reliability of the predicted brake clearance. The PSO algorithm optimizes the problem solution by simulating the predation behavior of bird flocks. By iteratively updating the speed and position of the particles through the PSO algorithm, the prediction error of the brake clearance-fatigue relationship model can be minimized.

[0069] For example, particle i at time t has velocity vi(t)=3, position xi(t)=5, inertia weight w=0.8, learning factor c1=c2=2, random number r1=r2=0.5, historical optimal position pi=8 of particle i, and global optimal position pg=10 of all particles. Then vi(t+1)=10.4. xi(t+1)=15.4.

[0070] This embodiment introduces a particle swarm optimization algorithm to update the brake clearance-fatigue relationship model, which improves the accuracy and reliability of model prediction. By simulating the natural optimization process, the PSO algorithm effectively reduces the prediction error, making the prediction result of the brake clearance and fatigue relationship closer to the actual situation. This embodiment not only enhances the scientific nature of brake performance evaluation, but also provides more accurate data support for the maintenance and management of equipment such as elevators, which helps to discover and solve potential problems in advance and ensure the safe operation of equipment.

[0071] In one embodiment of the present disclosure, the brake clearance prediction method further includes: The fatigue life of the target brake is calculated based on the second brake clearance data.

[0072] A durability result of the target brake is determined based on the fatigue life of the target brake.

[0073] In this embodiment, the target brake may represent the elevator brake to be tested. The fatigue life may include the time during which the brake can be used and operated normally in the future, or the time until the next failure, etc. Determining the durability result of the target brake based on the fatigue life of the target brake may include: The durability result of the target brake is determined based on the fatigue life and durability calculation formula of the target brake.

[0074] The durability calculation formula is: Durability=H(Fatigue,Time)= *Fatigue+ *Time+

[0075] Among them, Durability represents the durability result of the brake, H represents the fatigue state data-fatigue life function, Time represents the fatigue life, Indicates fixed parameters.

[0076] In this embodiment, the fatigue life of the brake can be calculated based on the predicted second brake clearance data combined with the fatigue inverse model and the ASME structural stress data. By repeating the above operation, the fatigue life of the brake under different brake clearances can be obtained, and the prediction result of the brake durability can be obtained based on the fatigue life.

[0077] Exemplarily, the value of the fixed parameter may be: =0.5, =0.2, =10.

[0078] For example, Figure 2 As shown, the process of the brake clearance prediction method may include: firstly, simulation calculation of fatigue data is performed to obtain simulated fatigue data. Then, data preprocessing and feature extraction are performed on the simulated fatigue data, and a fatigue back-calculation method is established based on the data obtained in the first two steps. At the same time, a model of the relationship between brake clearance and fatigue is constructed based on the established fatigue back-calculation method. Finally, the brake clearance is predicted and evaluated, and the durability of the brake is predicted based on the fatigue back-calculation method and the model of the relationship between brake clearance and fatigue.

[0079] This embodiment can accurately calculate and predict the fatigue life of the elevator brake by combining the second brake clearance data, the fatigue back-calculation model and the ASME structural stress data, and then evaluate its durability. This embodiment not only improves the accuracy and scientificity of the prediction, but also realizes the forward-looking management of the brake performance. By setting fixed parameters, the calculation process is simplified, and the reliability of the prediction results is guaranteed.

[0080] Corresponding to the brake clearance prediction method of the above embodiment, Figure 3 This is a structural block diagram of a brake clearance prediction device provided by an embodiment of the present disclosure. For ease of explanation, only the parts related to the embodiment of the present disclosure are shown. Figure 3 The brake clearance prediction device 20 includes: a fatigue reverse inference model building module 21, a brake clearance-fatigue relationship model building module 22 and a brake clearance prediction module 23.

[0081] The fatigue back-calculation model building module 21 is used to determine the fatigue back-calculation model based on the simulated fatigue parameter data and the historical fatigue parameter data. The fatigue back-calculation model is used to build a mapping relationship between the operating status data and the fatigue status data of the brake.

[0082] The brake clearance-fatigue relationship model building module 22 is used to determine the brake clearance-fatigue relationship model based on the fatigue state data and the first brake clearance data. The first brake clearance data is the historical brake clearance data. The brake clearance-fatigue relationship model is used to build a mapping relationship between the brake clearance of the brake and the fatigue state data.

[0083] The brake clearance prediction module 23 is used to predict the brake clearance of the target brake based on the fatigue back-calculation model, the brake clearance-fatigue relationship model and the target operating state data to obtain second brake clearance data.

[0084] In one embodiment of the present disclosure, the brake clearance prediction device 20 further includes: The first calculation module is used for operating status data including brake performance data and brake operating condition data.

[0085] The brake performance data and brake operating condition data are input into the simulation environment for calculation to obtain simulation fatigue parameter data.

[0086] In one embodiment of the present disclosure, the fatigue inverse model building module 21 is specifically used to determine an initial fatigue inverse model based on simulation fatigue parameter data and operation status data.

[0087] The initial fatigue inverse model is updated based on the loss function and historical fatigue parameter data to obtain the fatigue inverse model.

[0088] In one embodiment of the present disclosure, the fatigue inverse model building module 21 is further used to perform data preprocessing and feature extraction on the simulated fatigue parameter data to obtain a fatigue feature set. The fatigue feature set includes stress feature data and external fatigue feature data.

[0089] The initial fatigue inverse model is determined based on stress characteristic data, external fatigue characteristic data and operating status data.

[0090] In an embodiment of the present disclosure, the brake clearance-fatigue relationship model building module 22 is specifically used to determine the brake clearance-fatigue relationship model based on fatigue state data, first brake clearance data and a first formula.

[0091] The first formula is:

[0092]

[0093] in, Indicates the fatigue state data of the brake, Gap indicates the first brake clearance data, Stress indicates the structural stress, S N Curve represents the stress-cycle number curve, and a, b, c, and d represent preset parameters.

[0094] In one embodiment of the present disclosure, the brake clearance prediction device 20 further includes: The model optimization module is used to update the brake clearance-fatigue relationship model based on a particle swarm optimization algorithm to obtain an updated brake clearance-fatigue relationship model.

[0095] In one embodiment of the present disclosure, the brake clearance prediction device 20 further includes: The fatigue life of the target brake is calculated based on the second brake clearance data.

[0096] A durability result of the target brake is determined based on the fatigue life of the target brake.

[0097] See also Figure 4 , Figure 4 A schematic block diagram of an electronic device provided by an embodiment of the present disclosure. Figure 4 The electronic device 300 in the embodiment shown may include: one or more processors 301, one or more input devices 302, one or more output devices 303 and one or more memories 304. The processors 301, input devices 302, output devices 303 and memories 304 communicate with each other via a communication bus 305. The memory 304 is used to store computer programs, which include program instructions. The processor 301 is used to execute the program instructions stored in the memory 304. The processor 301 is configured to call the program instructions to execute the functions of the modules in the above-mentioned device embodiments, such as Figure 3 The functions of modules 21 to 23 are shown.

[0098] It should be understood that in the embodiment of the present disclosure, the processor 301 may be a central processing unit (CPU), and the processor may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0099] The input device 302 may include a touch panel, a fingerprint collection sensor (for collecting the user's fingerprint information and fingerprint direction information), a microphone, etc., and the output device 303 may include a display (LCD, etc.), a speaker, etc.

[0100] The memory 304 may include a read-only memory and a random access memory, and provide instructions and data to the processor 301. A portion of the memory 304 may also include a non-volatile random access memory. For example, the memory 304 may also store information about the device type.

[0101] In a specific implementation, the processor 301, input device 302, and output device 303 described in the embodiments of the present disclosure can execute the implementation methods described in the first and second embodiments of the brake clearance prediction method provided in the embodiments of the present disclosure, and can also execute the implementation methods of the electronic device 300 described in the embodiments of the present disclosure, which will not be repeated here.

[0102] In another embodiment of the present disclosure, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program, wherein the computer program includes program instructions, and when the program instructions are executed by the processor, all or part of the processes in the above-mentioned embodiment method are implemented, and the computer program can also be completed by instructing the relevant hardware through the computer program. The computer program can be stored in a computer-readable storage medium, and when the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. The computer-readable medium can include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0103] The computer-readable storage medium may be an internal storage unit of the electronic device of any of the aforementioned embodiments, such as a hard disk or memory of the electronic device. The computer-readable storage medium may also be an external storage device of the electronic device, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (SecureDigital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Furthermore, the computer-readable storage medium may also include both an internal storage unit of the electronic device and an external storage device. The computer-readable storage medium is used to store computer programs and other programs and data required by the electronic device. The computer-readable storage medium may also be used to temporarily store data that has been output or is to be output.

[0104] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in terms of function in the above description. 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 this disclosure.

[0105] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the electronic devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0106] In the several embodiments provided in the present application, it should be understood that the disclosed electronic devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of units is only a logical function division, 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. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces or units, or it can be an electrical, mechanical or other form of connection.

[0107] 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 embodiments of the present disclosure.

[0108] In addition, each functional unit in each embodiment of the present disclosure 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0109] The above are only specific embodiments of the present disclosure, but the protection scope of the present disclosure is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present disclosure, and these modifications or replacements should be included in the protection scope of the present disclosure. Therefore, the protection scope of the present disclosure should be based on the protection scope of the claims.

Claims

1. A brake clearance prediction method, characterized in that: include: Determine a fatigue back-calculation model based on the simulated fatigue parameter data and the historical fatigue parameter data, wherein the fatigue back-calculation model is used to construct a mapping relationship between the operating state data and the fatigue state data of the brake; determining a brake clearance-fatigue relationship model based on the fatigue state data and the first brake clearance data; The first brake clearance data is historical brake clearance data; the brake clearance-fatigue relationship model is used to construct a mapping relationship between the brake clearance and fatigue state data of the brake; The brake clearance of the target brake is predicted based on the fatigue inverse model, the brake clearance-fatigue relationship model and the target operating state data to obtain second brake clearance data.

2. The brake clearance prediction method according to claim 1, characterized in that: Also includes: The operating status data includes brake performance data and brake operating condition data; The brake performance data and the brake operating condition data are input into a simulation environment for calculation to obtain the simulated fatigue parameter data.

3. The brake clearance prediction method according to claim 2, characterized in that: The method of determining the fatigue inverse model based on the simulated fatigue parameter data and the historical fatigue parameter data includes: Determine an initial fatigue inverse model based on the simulated fatigue parameter data and the operating status data; The initial fatigue inverse model is updated based on the loss function and the historical fatigue parameter data to obtain the fatigue inverse model.

4. The brake clearance prediction method according to claim 3, characterized in that: The determining of the initial fatigue inverse model based on the simulated fatigue parameter data and the operating status data comprises: Performing data preprocessing and feature extraction on the simulated fatigue parameter data to obtain a fatigue feature set; the fatigue feature set includes stress feature data and external fatigue feature data; The initial fatigue inverse model is determined based on the stress characteristic data, the external fatigue characteristic data and the operating status data.

5. The brake clearance prediction method according to claim 1, characterized in that: The determining of the brake clearance-fatigue relationship model based on the fatigue state data and the first brake clearance data comprises: Determine a brake clearance-fatigue relationship model based on the fatigue state data, the first brake clearance data and a first formula; The first formula is: in, Indicates the fatigue state data of the brake, Gap indicates the first brake clearance data, Stress indicates the structural stress, S N Curve represents the stress-cycle number curve, and a, b, c, and d represent preset parameters.

6. The brake clearance prediction method according to claim 5, characterized in that: Also includes: The brake clearance-fatigue relationship model is updated based on a particle swarm optimization algorithm to obtain an updated brake clearance-fatigue relationship model.

7. The brake clearance prediction method according to claim 1, characterized in that: Also includes: calculating a fatigue life of a target brake based on the second brake clearance data; A durability result of the target brake is determined based on the fatigue life of the target brake.

8. A brake clearance prediction device, characterized in that: include: A fatigue back-calculation model building module, used to determine a fatigue back-calculation model based on simulated fatigue parameter data and historical fatigue parameter data, wherein the fatigue back-calculation model is used to build a mapping relationship between the operating state data and the fatigue state data of the brake; a brake clearance-fatigue relationship model building module, used for determining a brake clearance-fatigue relationship model based on the fatigue state data and the first brake clearance data; The first brake clearance data is historical brake clearance data; the brake clearance-fatigue relationship model is used to construct a mapping relationship between the brake clearance and fatigue state data of the brake; The brake clearance prediction module is used to predict the brake clearance of the target brake based on the fatigue inverse model, the brake clearance-fatigue relationship model and the target operating state data to obtain second brake clearance data.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

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

Images