A method and system for modeling a remaining life prediction model of an elevator

By constructing a comprehensive model of elevator historical faults, equipment and maintenance data, the problem of inaccurate elevator life prediction in the existing technology is solved, and the accurate prediction and maintenance impact of important components of the elevator are achieved, and the elevator life prediction is improved. reliability and accuracy.

CN118821624BActive Publication Date: 2024-11-22CHANGSHU INSTITUTE OF TECHNOLOGY
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411300986.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-18
Publication Date
2024-11-22
Estimated Expiration
2044-09-18

AI Technical Summary

Technical Problem

The existing technology cannot accurately predict the remaining life of an elevator, and ignores the impact of the comprehensive elevator situation and maintenance on life, resulting in inaccurate predictions.

Method used

By obtaining the elevator’s historical fault data, real-time equipment data and maintenance data, a life prediction model for motors, steel cables and brakes is constructed, and aging coefficient and maintenance life extension score are combined to make comprehensive life prediction.

Benefits of technology

Accurate prediction of the life of an important part of the elevator is achieved, and the reliability and accuracy of the life prediction of the elevator is improved, taking into account the impact of maintenance on life.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118821624B_ABST
    Figure CN118821624B_ABST
Patent Text Reader

Abstract

The present invention provides a modeling method and system for predicting a remaining life of an elevator, and relates to the technical field of elevator safety monitoring. The present invention obtains historical fault data, maintenance data, elevator equipment data and elevator operation data of the elevator; constructs a motor life prediction model, a steel cable life prediction model and a brake life prediction model, trains and optimizes the above models, obtains the motor life, the steel cable life and the brake life through the optimized models, and generates a first predicted life of the elevator through the motor life, the steel cable life and the brake life; analyzes the aging of an electric control system, obtains an aging coefficient of an electric control cabinet and an aging coefficient of a relay, and corrects the first predicted life of the elevator through the aging coefficient of the electric control cabinet and the aging coefficient of the relay to generate a second predicted life of the elevator; analyzes maintenance data to generate a maintenance life extension score, and corrects the second predicted life of the elevator through the maintenance life extension score to generate a third predicted life of the elevator.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of elevator safety monitoring, and in particular to a modeling method and system for predicting a remaining life of an elevator. Background Art

[0002] As an important vertical transportation tool in modern urban buildings, the safety and reliability of elevators have always been a focus of attention. As the service life of elevators increases, the aging and wear of the equipment will gradually affect its operating status and increase the possibility of failures. At present, elevator maintenance mostly relies on regular inspections and emergency repairs, but this often cannot accurately judge the remaining service life of the equipment in advance, and cannot effectively prevent the elevator from suddenly shutting down or failing due to the aging of key components during operation. Therefore, it is of great practical significance to develop an elevator remaining life prediction model based on equipment data, operation data and maintenance data to predict the degradation of key components of the elevator in advance. In the prior art, although some elevator management systems can provide basic health assessments based on fault data, there are generally problems such as low model accuracy and inability to dynamically combine actual maintenance conditions for life correction, which limits its application effect in long-term maintenance of elevators.

[0003] In the prior art, the publication number CN113158362B discloses a method, system, device and storage medium for predicting the remaining life of an elevator by integrating physical failure and data drive, by establishing a braking torque and traction force degradation prediction model; based on a preset braking torque threshold, a measured braking torque, and a braking torque degradation prediction model, the remaining life of the first elevator is obtained; based on a preset traction force threshold, a measured traction force, and a traction force degradation prediction model, the remaining life of the second elevator is obtained; an elevator operation fault prediction model combining a PSO algorithm and a BP neural network is established to obtain the remaining life of the third elevator, and the remaining life of the first elevator and the remaining life of the second elevator are weighted with the remaining life of the third elevator, respectively, to obtain the remaining life of the fourth elevator caused by insufficient braking torque and the remaining life of the fifth elevator caused by insufficient traction force. The physical failure method and the data drive method are integrated, and the parameters of the estimation model are optimized to obtain a more accurate prediction result of the remaining life of the elevator. However, the prior art still has defects. The prior art converts the prediction of the life of the elevator into the prediction of the life of the braking system and the life of the traction system in the elevator, denies the comprehensiveness and unity of the elevator life, and lacks analysis of the comprehensive situation of the elevator life. Secondly, the prior art only considers the prediction of the life of the braking system and the life of the traction system of the elevator itself, and ignores the impact of human care and maintenance on the elevator life, which will lead to inaccurate prediction of the elevator life.

[0004] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0005] The purpose of the present invention is to provide a method and system for modeling an elevator remaining life prediction model to solve the problems raised in the above background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A method and system for modeling a remaining life prediction model for an elevator, the specific steps comprising:

[0008] Step 1: Obtain historical fault data of the elevator, wherein the historical fault data includes time data of motor fault, time data of cable fault and time data of brake fault, and the time data includes total running time, normal running time and frequent running time before the fault occurs;

[0009] Step 2: Construct motor life prediction models, cable life prediction models, and brake life prediction models, use the ratio of normal operation time to frequent operation time as input, and use the total operation time as the output life label to train and optimize the above models;

[0010] Step 3: respectively obtain the normal operation time and frequent operation time of the motor, steel cable and brake in the elevator to be predicted before the failure occurs, and input them into the corresponding model to generate the motor life, steel cable life and brake life, and perform mathematical analysis on the motor life, steel cable life and brake life to generate the first elevator predicted life;

[0011] Step 4: Obtain the real-time elevator equipment data and elevator operation data of the elevator to be predicted, analyze the elevator equipment data and elevator operation data to generate an electric control cabinet aging coefficient and a relay aging coefficient; use the electric control cabinet aging coefficient and the relay aging coefficient to correct the predicted life of the first elevator to generate a second elevator predicted life;

[0012] Step 5: Obtain real-time maintenance data of the elevator to be predicted, analyze the maintenance data to generate a maintenance life extension score, and modify the predicted life of the second elevator using the maintenance life extension score to generate a predicted life of the third elevator.

[0013] Furthermore, the specific logic for distinguishing the running time is as follows: the running time with a time interval of no more than 2 minutes between two running times is defined as frequent running time, and the other running times are defined as normal running time;

[0014] Furthermore, the specific logic for generating the first elevator predicted life is: performing mathematical analysis on the motor life, the steel cable life and the brake life to generate the elevator predicted life; the specific formula for generating the first elevator predicted life is:

[0015] ;

[0016] in, Predict the life of the first elevator, For the motor life, For the life of the steel cable, For brake life.

[0017] Furthermore, the specific logic for generating the electric control cabinet aging coefficient and the relay aging coefficient is as follows: the elevator equipment data and the elevator operation data are analyzed to generate the electric control cabinet aging coefficient and the relay aging coefficient; the specific formula for generating the electric control cabinet aging coefficient is as follows:

[0018] ;

[0019] ;

[0020] in, is the aging coefficient of the electric control cabinet, For abnormal temperature, is the actual temperature, is the baseline temperature, is the leakage current, is the actual current, is the actual voltage, Rated current, Rated voltage.

[0021] The specific formula on which the relay aging factor is based is:

[0022] ;

[0023] in, is the relay aging coefficient, is the material constant of the relay, is the material index of the relay, is the maximum magnetic flux density of the relay, is the operating frequency of the relay, is the noise voltage of the relay, is the reference noise voltage of the relay.

[0024] Furthermore, the specific logic for generating the second elevator predicted life is: the first elevator predicted life is corrected by the electric control system aging coefficient to generate the second elevator predicted life; the specific formula for generating the second elevator predicted life is:

[0025] ;

[0026] in, Predict the life of the second elevator, Predict the life of the first elevator, is the aging coefficient of the electric control cabinet, is the relay aging coefficient, For Perform a round-down operation.

[0027] Furthermore, the specific logic for generating the third elevator predicted life is: analyzing the maintenance data to generate a maintenance life extension score, and correcting the second elevator predicted life by the maintenance life extension score to generate the third elevator predicted life; the specific formula for analyzing the maintenance data to generate the maintenance life extension score is:

[0028] ;

[0029] in, To maintain the life extension score, is the number of elevator inspections, is the number of component repairs, is the number of component replacements;

[0030] The specific formula for generating the predicted life of the third elevator is:

[0031] in, Predict the life of the third elevator, Predict the life span for the second elevator.

[0032] The present invention further provides a system for modeling a remaining life prediction model of an elevator, the system being used to implement any step of the modeling method for modeling a remaining life prediction model of an elevator, specifically comprising:

[0033] A data acquisition module is used to obtain historical fault data of the elevator, wherein the historical fault data includes time data of motor faults, time data of steel cable faults and time data of brake faults, and the time data includes total running time, normal running time and frequent running time before the fault occurs;

[0034] A model building module is used to build a motor life prediction model, a steel cable life prediction model and a brake life prediction model, taking the ratio of normal operation time to frequent operation time as input and the total operation time as an output life label to train and optimize the above models;

[0035] The initial life prediction module is used to obtain the normal operation time and frequent operation time of the motor, steel cable and brake in the elevator to be predicted before the failure occurs, and input them into the corresponding model to generate the motor life, steel cable life and brake life, and perform mathematical analysis on the motor life, steel cable life and brake life to generate the first elevator predicted life;

[0036] The life calibration module is used to obtain the real-time elevator equipment data and elevator operation data of the elevator to be predicted, analyze the elevator equipment data and the elevator operation data to generate the electric control cabinet aging coefficient and the relay aging coefficient; the electric control cabinet aging coefficient and the relay aging coefficient are used to correct the predicted life of the first elevator to generate the predicted life of the second elevator;

[0037] The final prediction module is used to obtain the real-time maintenance data of the elevator to be predicted, analyze the maintenance data to generate a maintenance life extension score, and correct the predicted life of the second elevator through the maintenance life extension score to generate a third elevator predicted life.

[0038] Compared with the prior art, the present invention has the following beneficial effects:

[0039] The present invention accurately predicts the life of the important components of the elevator, such as the motor, steel cable and brake, by establishing a model. The elevator system is comprehensively predicted for its life by analyzing the life of the motor, steel cable, brake and the aging of the elevator electronic control system. This multi-parameter, comprehensive life prediction method is more reliable and accurate than the prediction of a single elevator system.

[0040] Taking into account the impact of equipment maintenance on life, the present invention also corrects the predicted elevator life by introducing a maintenance life extension score, making the prediction of the remaining life of the elevator more accurate and reliable, while also enhancing the practicability of the model. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 It is a schematic diagram of the overall method flow of the present invention.

[0042] Figure 2 It is a schematic diagram of the overall system structure of the present invention. DETAILED DESCRIPTION

[0043] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0044] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0045] Example:

[0046] See also Figure 1 , the present invention provides a technical solution:

[0047] A method for modeling an elevator remaining life prediction model, the specific steps comprising:

[0048] Step 1: Obtain historical fault data of the elevator, wherein the historical fault data includes time data of motor fault, time data of cable fault and time data of brake fault, and the time data includes total running time, normal running time and frequent running time before the fault occurs;

[0049] The specific logic for distinguishing the running time is as follows: the running time with a time interval of no more than 2 minutes between two running times is defined as frequent running time, and the other running times are defined as normal running time;

[0050] Step 2: Construct motor life prediction models, cable life prediction models, and brake life prediction models, use the ratio of normal operation time to frequent operation time as input, and use the total operation time as the output life label to train and optimize the above models;

[0051] The time data of motor failure is the total running time, normal running time and frequent running time before the motor failure. The ratio of the normal running time and frequent running time before the motor failure is used as input, and the corresponding total running time is used as the output life label to train the motor life prediction model. The same is true for steel cables and brakes.

[0052] A feedforward neural network is used to form a motor fault data set with the ratio of the normal operation time and the frequent operation time of the motor fault; the total operation time of the motor fault is used as a label, and the motor life prediction model is trained and optimized using the motor fault data set. It should be noted that the total operation time of the motor fault is used as a label, and the motor life prediction model is trained and optimized using the motor fault data set. Existing technologies can be used, including: input layer, hidden layer, output layer and activation function, and the root mean square error loss function is used; the input data is calculated once through the network to obtain the output result, and the loss function is calculated based on the predicted value and the true value. The gradient of the loss function for each weight and bias is calculated by the chain rule, and the weights and biases of the network are updated using the gradient descent algorithm to minimize the loss function. The same is true for cables and brakes;

[0053] In lifespan prediction, the predicted value is a continuous value (i.e., the remaining running days), which makes this problem a regression problem. Feedforward neural networks can handle regression tasks well because they are able to learn a continuous mapping relationship from input features to outputs.

[0054] Step 3: respectively obtain the normal operation time and frequent operation time of the motor, steel cable and brake in the elevator to be predicted before the failure occurs, and input them into the corresponding model to generate the motor life, steel cable life and brake life, and perform mathematical analysis on the motor life, steel cable life and brake life to generate the first elevator predicted life;

[0055] The specific logic for generating the predicted life of the first elevator is: mathematically analyzing the motor life, the steel cable life, and the brake life to generate the predicted life of the elevator; the specific formula for generating the predicted life of the first elevator is:

[0056] ;

[0057] in, Predict the life of the first elevator, For the motor life, For the life of the steel cable, The motor, cable and brake are the three most important parts of the elevator. Their lifespan is directly related to the lifespan of the entire elevator. The longer the motor lifespan, cable lifespan and brake lifespan, the longer the elevator lifespan. The first elevator predicted lifespan is generated by analyzing the motor lifespan, cable lifespan and brake lifespan. It reflects the life of the main parts of the elevator and can roughly assess the life of the elevator. Its generation can provide an important basis for the accurate prediction of the life of the elevator.

[0058] Step 4: Obtain the real-time elevator equipment data and elevator operation data of the elevator to be predicted, analyze the elevator equipment data and elevator operation data to generate an electric control cabinet aging coefficient and a relay aging coefficient; use the electric control cabinet aging coefficient and the relay aging coefficient to correct the predicted life of the first elevator to generate a second elevator predicted life;

[0059] The elevator equipment data includes the rated current, rated voltage and baseline temperature of the electric control cabinet; the material constant, material index, maximum magnetic flux density and reference noise voltage of the relay; the elevator operation data includes the leakage current, actual current, actual voltage and actual temperature of the electric control cabinet, the operating frequency and noise voltage of the relay;

[0060] The specific logic for generating the electric control cabinet aging coefficient and the relay aging coefficient is as follows: the elevator equipment data and the elevator operation data are analyzed to generate the electric control cabinet aging coefficient and the relay aging coefficient; the specific formula for generating the electric control cabinet aging coefficient is as follows:

[0061] ;

[0062] ;

[0063] in, is the aging coefficient of the electric control cabinet, For abnormal temperature, is the actual temperature, is the baseline temperature, is the leakage current, is the actual current, is the actual voltage, Rated current, Rated voltage. Aging coefficient of electric control cabinet Reflects the aging of the electric control cabinet. The larger the value, the more serious the aging of the electric control cabinet. As an important component of the elevator electric control system, the aging coefficient of the electric control cabinet can provide an important basis for evaluating the aging of the electric control system and thus the life of the elevator. Reflects the abnormal degree of temperature when the electric control cabinet is working. Generally, the more serious the aging of the electric control cabinet, the worse the heat dissipation capacity, and the abnormal temperature during operation. The larger the leakage current Reflects the leakage condition of the electric control cabinet. The larger the value, the more serious the aging condition of the electric control cabinet. is the current ratio, which is normally 1. The greater the deviation between the value and 1, the more serious the aging of the electric control cabinet. It is the voltage ratio, which is normally 1. The greater the deviation between the value and 1, the more serious the aging of the electric control cabinet.

[0064] The specific formula on which the relay aging factor is based is:

[0065] ;

[0066] in, is the relay aging coefficient, is the material constant of the relay, is the material index of the relay, is the maximum magnetic flux density of the relay, is the operating frequency of the relay, is the noise voltage of the relay, is the reference noise voltage of the relay. Relay aging coefficient Reflects the aging of the relay. The larger the value, the more serious the aging of the relay. The relay aging coefficient It can provide an important basis for evaluating the aging of the electronic control system and thus the life of the elevator. The hysteresis loss is the relay's aging. The aging of the relay will be accompanied by hysteresis loss. The greater the hysteresis loss, the more serious the aging of the relay. It indicates the existence of unwanted signals in the operating environment of the level noise relay. The larger the value is, the more unwanted signals exist in the operating environment of the relay and the more serious the aging is.

[0067] The predicted life of the first elevator is corrected by the aging coefficient of the electric control system to generate the predicted life of the second elevator;

[0068] ;

[0069] in, Predict the life of the second elevator, Predict the life of the first elevator, is the aging coefficient of the electric control cabinet, is the relay aging coefficient, For Perform a round-down operation. The second elevator predicted life reflects the elevator life taking into account the aging of the electric control system, which can provide an important basis for the prediction of the elevator life. Reflects the aging of the electric control cabinet. The larger the value, the more serious the aging of the electric control cabinet and the shorter the life of the elevator; Relay aging coefficient Reflects the aging of the relay. The larger the value, the more serious the aging of the relay and the shorter the life of the elevator. Reflects the impact of the aging of the electric control system on the life of the elevator. The larger the value, the shorter the elevator life.

[0070] Step 5: Obtain real-time maintenance data of the elevator to be predicted, analyze the maintenance data to generate a maintenance life extension score, and modify the predicted life of the second elevator using the maintenance life extension score to generate a predicted life of the third elevator.

[0071] The maintenance data includes the number of elevator inspections, component repairs, and component replacements;

[0072] The maintenance data is analyzed to generate a maintenance life extension score, and the predicted life of the second elevator is corrected by the maintenance life extension score to generate the predicted life of the third elevator; the specific formula for analyzing the maintenance data to generate the maintenance life extension score is:

[0073] ;

[0074] in, To maintain the life extension score, is the number of elevator inspections, is the number of component repairs, Number of component replacements; maintenance life extension score Reflects the impact of elevator maintenance on the life of the elevator. The higher the value, the longer the elevator life. Elevator maintenance can significantly increase the life of the elevator. The more maintenance times, the more obvious the improvement in the life of the elevator. Among them, the number of component replacements has the greatest impact on the improvement of the elevator life, followed by component repairs, and then elevator inspections. The elevator inspection itself will not increase the life of the elevator, but the elevator will be stopped during the inspection, which indirectly increases the life of the elevator by reducing the elevator running time.

[0075] The specific formula for generating the predicted life of the third elevator is:

[0076] ;

[0077] in, Predict the life of the third elevator, Predicted lifespan for the second elevator. Predicted lifespan for the third elevator It can accurately reflect the remaining life of the elevator. The larger the value, the longer the elevator life is. Reflects the impact of elevator maintenance on elevator life. The higher the value, the longer the elevator life.

[0078] See also Figure 2 The present invention further provides a system for modeling a remaining life prediction model of an elevator, the system being used to implement any step of the modeling method for modeling a remaining life prediction model of an elevator, specifically comprising:

[0079] The data collection module is used to distinguish the specific logic based on the running time: the running time with a time interval of no more than 2 minutes between two running times is defined as frequent running time, and the other running time is defined as normal running time;

[0080] A model building module is used to build a motor life prediction model, a steel cable life prediction model and a brake life prediction model, taking the ratio of normal operation time to frequent operation time as input and the total operation time as an output life label to train and optimize the above models;

[0081] The initial life prediction module is used to obtain the normal operation time and frequent operation time of the motor, steel cable and brake in the elevator to be predicted before the failure occurs, and input them into the corresponding model to generate the motor life, steel cable life and brake life, and perform mathematical analysis on the motor life, steel cable life and brake life to generate the first elevator predicted life;

[0082] The life calibration module is used to obtain the real-time elevator equipment data and elevator operation data of the elevator to be predicted, analyze the elevator equipment data and the elevator operation data to generate the electric control cabinet aging coefficient and the relay aging coefficient; the electric control cabinet aging coefficient and the relay aging coefficient are used to correct the predicted life of the first elevator to generate the predicted life of the second elevator;

[0083] The final prediction module is used to obtain the real-time maintenance data of the elevator to be predicted, analyze the maintenance data to generate a maintenance life extension score, and correct the predicted life of the second elevator through the maintenance life extension score to generate a third elevator predicted life.

[0084] 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 in the formula are set by technicians in this field according to actual conditions.

[0085] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software methods depends on the specific application and design constraints of the technical solution.

[0086] 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, and 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.

[0087] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A modeling method for predicting the remaining life of an elevator. It is characterized in that The specific steps include: Step 1: Obtain historical fault data of the elevator, wherein the historical fault data includes time data of motor fault, time data of cable fault and time data of brake fault, and the time data includes total running time, normal running time and frequent running time before the fault occurs; Step 2: Construct motor life prediction models, cable life prediction models, and brake life prediction models, use the ratio of normal operation time to frequent operation time as input, and use the total operation time as the output life label to train and optimize the above models; Step 3: respectively obtain the normal operation time and frequent operation time of the motor, steel cable and brake in the elevator to be predicted before the failure occurs, and input them into the corresponding model to generate the motor life, steel cable life and brake life, and perform mathematical analysis on the motor life, steel cable life and brake life to generate the first elevator predicted life; Step 4: Obtain the real-time elevator equipment data and elevator operation data of the elevator to be predicted, analyze the elevator equipment data and the elevator operation data to generate an electric control cabinet aging coefficient and a relay aging coefficient; generate an electric control system aging coefficient according to the electric control cabinet aging coefficient and the relay aging coefficient, and correct the first elevator predicted life by the electric control system aging coefficient to generate a second elevator predicted life; Step 5: Obtain real-time maintenance data of the elevator to be predicted, analyze the maintenance data to generate a maintenance life extension score, and modify the predicted life of the second elevator by the maintenance life extension score to generate a predicted life of the third elevator; The specific logic for generating the predicted life of the first elevator is: mathematically analyzing the motor life, the steel cable life, and the brake life to generate the predicted life of the elevator; the specific formula for generating the predicted life of the first elevator is: Among them, L 1 Predict the life of the first elevator, T E is the motor life, T S is the life of the steel cable, T P For brake life; The specific logic for generating the second elevator predicted life is: the first elevator predicted life is corrected by the electric control system aging coefficient to generate the second elevator predicted life; the specific formula for generating the second elevator predicted life is: Among them, L 2 Predict the life of the second elevator, L 1 is the predicted life of the first elevator, Eo is the aging coefficient of the electric control cabinet, H O is the relay aging coefficient, For Eo*H O Perform a rounding down operation; The specific logic for generating the predicted life of the third elevator is: analyzing the maintenance data to generate a maintenance life extension score, and correcting the predicted life of the second elevator by the maintenance life extension score to generate the predicted life of the third elevator; the specific formula for analyzing the maintenance data to generate the maintenance life extension score is: S=CH+2RE+3UP Among them, S is the maintenance life extension score, CH is the number of elevator inspections, RE is the number of component repairs, and UP is the number of component replacements; The specific formula for generating the predicted life of the third elevator is: L 3 =L 2 *(1+S%) Among them, L 3 Predict the life of the third elevator, L 2 Predict the life span for the second elevator.

2. A method for modeling an elevator remaining life prediction model according to claim 1, Features: The specific logic for distinguishing the running time is as follows: the running time with a time interval of no more than 2 minutes between two running times is defined as frequent running time, and the other running times are defined as normal running time.

3. The method for modeling an elevator remaining life prediction model according to claim 1, Features: The specific logic for generating the electric control cabinet aging coefficient and the relay aging coefficient is as follows: the elevator equipment data and the elevator operation data are analyzed to generate the electric control cabinet aging coefficient and the relay aging coefficient; the specific formula for generating the electric control cabinet aging coefficient is as follows: Among them, Eo is the aging coefficient of the electric control cabinet, T B is the abnormal temperature, T is the actual temperature, T O is the baseline temperature, I k is the leakage current, I is the actual current, V is the actual voltage, I 0 Rated current, V O Rated voltage; The specific formula on which the relay aging factor is based is: Among them, H O is the relay aging coefficient, k is the material constant of the relay, n is the material index of the relay, B max is the maximum magnetic flux density of the relay, f is the operating frequency of the relay, V N is the noise voltage of the relay, V B is the reference noise voltage of the relay.

4. A modeling system for predicting the remaining life of an elevator. Features: The system is used to implement the elevator remaining life prediction model modeling method according to any one of claims 1 to 3, specifically comprising: A data acquisition module is used to obtain historical fault data of the elevator, wherein the historical fault data includes time data of motor faults, time data of steel cable faults and time data of brake faults, and the time data includes total running time, normal running time and frequent running time before the fault occurs; A model building module is used to build a motor life prediction model, a steel cable life prediction model and a brake life prediction model, taking the ratio of normal operation time to frequent operation time as input and the total operation time as an output life label to train and optimize the above models; The initial life prediction module is used to obtain the normal operation time and frequent operation time of the motor, steel cable and brake in the elevator to be predicted before the failure occurs, and input them into the corresponding model to generate the motor life, steel cable life and brake life, and perform mathematical analysis on the motor life, steel cable life and brake life to generate the first elevator predicted life; the life calibration module is used to obtain the real-time elevator equipment data and elevator operation data of the elevator to be predicted, analyze the elevator equipment data and elevator operation data to generate the electric control cabinet aging coefficient and the relay aging coefficient; generate the electric control system aging coefficient according to the electric control cabinet aging coefficient and the relay aging coefficient, and correct the first elevator predicted life by the electric control system aging coefficient to generate the second elevator predicted life; The final prediction module is used to obtain the real-time maintenance data of the elevator to be predicted, analyze the maintenance data to generate a maintenance life extension score, and correct the predicted life of the second elevator through the maintenance life extension score to generate a third elevator predicted life.