Aerodynamic optimization method of high-speed elevator fairing shape based on digital twin

Abstract

The present invention discloses a method for aerodynamic optimization of the appearance of a high-speed elevator air deflector based on digital twins, and relates to the technical field of high-speed elevators. The elevator operation digital twin model is used to simulate and test the elevator operation, and abnormal areas are screened out on the surface of the car according to the simulated test data; the air deflector design and layout scheme is determined according to the abnormal area and the simulated test data, and the improvement degree of the air deflector design and layout scheme on the elevator operation is verified by the elevator operation digital twin model. If the improvement degree exceeds expectations, the performance value of the air deflector is constructed by the test data, and if the performance value does not exceed expectations, the air deflector design and layout scheme is reconstructed; the operation status of the car and the air deflector is monitored in real time, and the air deflector is predicted to be faulty according to the operation monitoring data, and the maintenance frequency of the air deflector is constrained according to the predicted data. The maintenance frequency is adapted to the operation and use status of the elevator car and the air deflector, and the safety hazards of the car and the air deflector are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of high-speed elevators, and in particular to a method for aerodynamic optimization of a high-speed elevator fairing shape based on digital twins. Background Art

[0002] High-speed elevators are efficient vertical transportation tools in modern buildings. They use advanced technology and design concepts to achieve fast, smooth and comfortable transportation between high floors in a very short time. They are usually equipped with high-performance drive devices, sophisticated control systems and optimized airflow designs to ensure that passengers can enjoy a smooth ride during high-speed operation. In addition, high-speed elevators also have multiple safety protection measures to ensure the safety of passengers.

[0003] The air deflector of a high-speed elevator is a carefully designed component. Through its unique curved and flat structure, it effectively reduces air resistance, reduces noise and improves running smoothness. It is widely used in various types of high-speed elevators, providing passengers with an efficient, energy-saving and comfortable riding experience.

[0004] The air deflector is mainly composed of a deflector plate, a baffle, a lower guide plate, etc. These components can be fixed to the guide frame of the elevator by bolts or welding. In the actual shaft, the distance between the elevator car and the shaft wall on the side of the landing door is small, so the design of the air deflector usually takes this into consideration. The side close to the landing door is designed to be flat to adapt to the shape of the shaft wall, while the other three sides are designed to be curved to better guide the airflow. In addition, the air deflector may also include structures such as a skeleton and a curved outer cover to increase its strength and stability.

[0005] In the Chinese invention patent with application publication number CN112749452A, a method for optimizing the aerodynamic shape of a shroud is disclosed, which belongs to the field of elevators. The method for optimizing the aerodynamic shape of a shroud comprises the following steps: taking the air resistance coefficient and the yaw moment coefficient of the high-speed elevator operation as the optimization targets, the geometric shape of the shroud of an ultra-high-speed elevator is optimized by taking the elevator operation resistance and the yaw moment as the optimization targets, and determining 6 design variables that control the change of the shroud shape, and using Latin hyper-vertical design to analyze the change relationship between the design variables and the aerodynamic loads on the elevator, and analyzing the influence of each design variable on the target value, and establishing an RBF proxy model, and finally using the NSGA-II multi-objective optimization algorithm to optimize the design within the feasible domain, and effectively obtaining the most optimized shroud to effectively improve the aerodynamic characteristics of the ultra-high-speed elevator, and effectively realize the passive vibration reduction and noise reduction of the ultra-high-speed elevator, and meet the existing requirements.

[0006] Combined with the above application and the contents of the prior art:

[0007] When the elevator car is running at high speed in the elevator shaft, the car movement resistance increases dramatically and various eddy current losses intensify, which can easily bring hidden dangers to the economy, safety and comfort of the elevator system. In order to increase the lifting speed of the elevator, it is usually necessary to install a deflector on the elevator car to effectively improve the flow field distribution and reduce the car resistance coefficient. At the same time, different deflector shapes and different installation positions have significant effects on the aerodynamic characteristics of the outer edge of the elevator car.

[0008] Compared with the traditional symmetrical air deflector, generally speaking, the front-shaped air deflector has the best effect, with a drag reduction ratio of up to 80.21%. However, considering the speed and energy consumption requirements of high-speed elevators, the appearance of the air deflector still needs to be further optimized before installing it, considering that the operating environment conditions in the elevator operating area will have a great impact on the operating speed of the car, especially when the operating environment conditions frequently produce abnormalities, such as wind pressure, airflow changes, and temperature changes. When the frequency of abnormalities is high and the degree of abnormality is high, the operating speed of the high-speed elevator will also be greatly disturbed; and the existing air deflector optimization schemes usually focus on appearance optimization, mainly to reduce the drag coefficient, and there is a certain neglect of the installation area of ​​the air deflector, and because the main focus is on increasing the lifting speed, there is also a certain degree of neglect of the elevator operation safety.

[0009] To this end, the present invention provides a high-speed elevator fairing shape aerodynamic optimization method based on digital twin. Summary of the invention

[0010] 1. Technical issues to be resolved

[0011] In view of the deficiencies of the prior art, the present invention provides a method for aerodynamic optimization of the appearance of a high-speed elevator air deflector based on digital twins, by screening out abnormal areas on the surface of the car based on simulation test data; determining the air deflector design and layout scheme based on the abnormal areas and simulation test data, and verifying the degree of improvement of the elevator operation by the air deflector design and layout scheme based on the elevator operation digital twin model. If the degree of improvement exceeds expectations, the performance value of the air deflector is constructed based on the test data, and if the performance value does not exceed expectations, the air deflector design and layout scheme is reconstructed; the operating status of the car and the air deflector is monitored in real time, and the air deflector is predicted to have faults based on the operating monitoring data, and the maintenance frequency of the air deflector is constrained based on the predicted data. The maintenance frequency is adapted to the operating and use status of the elevator car and the air deflector, reducing the safety hazards of the car and the air deflector; thereby solving the technical problems raised in the background technology.

[0012] (II) Technical solution

[0013] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0014] The aerodynamic optimization method of the high-speed elevator fairing shape based on digital twins includes collecting environmental condition data in the elevator operation area. If there is an abnormality in the environmental condition data, the abnormality degree is constructed according to the abnormality degree, and when the abnormality degree exceeds expectations, a model building instruction is issued to the outside.

[0015] The elevator operation digital twin model is constructed based on the elevator specification attribute data. Under the selected test scenario, the elevator operation digital twin model is used to simulate the elevator operation and screen out abnormal areas on the car surface based on the simulated test data.

[0016] The design and layout of the air deflector is determined based on the abnormal area and simulation test data. The digital twin model of the elevator operation verifies the degree of improvement of the air deflector design and layout on the elevator operation. If the improvement exceeds expectations, an air deflector optimization instruction is issued to the outside.

[0017] After multiple iterations of optimization of the design and layout of the air deflector, the performance value of the air deflector is constructed from the test data. If the performance value does not exceed the expectation, the design and layout of the air deflector is reconstructed;

[0018] Monitor the operating status of the car and the air deflector in real time, predict the failure of the air deflector based on the operating monitoring data, and constrain the maintenance frequency of the air deflector based on the predicted data.

[0019] Furthermore, a sensor network is arranged in the elevator operation area, and the sensor network monitors the elevator operation environment conditions and obtains corresponding operation environment condition data, and generates an elevator operation environment data set after aggregation;

[0020] The real-time operating environment condition data is used as input, and the trained abnormal data recognition model is used to identify abnormal data. If abnormal data exists, the time node where the abnormal data is generated is obtained as the abnormal node, and the abnormal proportion of each abnormal data is obtained. The abnormality degree is constructed based on the distribution of abnormal nodes and the abnormal proportion.

[0021] Furthermore, after receiving the model building instruction, the elevator and related data are collected to generate a set of elevator specification attribute data; some data in the elevator specification attribute data set are extracted as sample data and labeled, and the machine learning algorithm is trained with the labeled sample data to generate a digital twin model of elevator operation.

[0022] Furthermore, after collecting the actual operation scenario data of the elevator, a test scenario library is pre-set, and test scenarios are extracted from the test scenario library. The elevator operation digital twin model simulates the operation of the elevator, and the simulated test data is recorded and aggregated to generate a simulated test data set for the elevator operation.

[0023] Furthermore, with the simulated test data as input, the trained abnormal region recognition model is used to identify the areas where the air resistance of the elevator car is greater than expected, and regard them as abnormal areas.

[0024] Furthermore, the deflector design and layout plan includes at least the preliminary size, shape, installation position, material and moisture-proof treatment process of the deflector, and the deflector model determined according to the deflector layout plan is added to the elevator operation digital twin model;

[0025] In the preset test scenario, the elevator operation digital twin model is used to test the car and the air deflector, obtain the corresponding air deflector test data, and generate the air deflector test data set after aggregation;

[0026] Based on the difference in simulation test data after installing the air deflector, the improvement degree is generated from the relevant data in the air deflector test data set.

[0027] Furthermore, after receiving the deflector optimization instruction, the elevator operation digital twin model is used to perform operation tests on the car and the deflector in different test scenarios to obtain corresponding operation test data;

[0028] Taking improving the degree of improvement as the optimization goal and running test data as feedback, a pre-trained genetic algorithm is used to adjust the design layout of the shroud, including at least the shape, size and position-related parameters of the shroud, to obtain the optimized design layout of the shroud.

[0029] Furthermore, after the arrangement of the air deflector is optimized for multiple iterations until the degree of improvement no longer increases, the corresponding air deflector design and layout scheme is used as the target scheme; in different test scenarios, the air deflector design and layout scheme of the elevator operation digital twin model is used to perform simulation tests to obtain corresponding target test data;

[0030] The performance value of the air deflector is constructed from the target test data. If the performance value does not exceed the expectation, the car air deflector is redesigned and the installation area is adjusted, and iterative optimization is performed.

[0031] Furthermore, after the air deflector is optimized and installed, the elevator with the air deflector installed is put into operation, and the sensor network monitors the elevator shaft environment and air deflector performance in real time, and obtains corresponding operation monitoring data, which are aggregated to generate an operation monitoring data set;

[0032] The real-time and historical data in the operation monitoring data set are used as input, and the trained fault prediction model is used to predict the fault of the air deflector. If the air deflector may have a fault, an alarm command is issued to the outside.

[0033] Furthermore, after receiving the alarm instruction, the corresponding time node is used as the warning node, the corresponding fault position is used as the warning position, and the maintenance frequency of the deflector is constrained according to the warning node and the warning position;

[0034] According to the maintenance frequency that meets the constraint conditions, the deflector cover of the elevator car is maintained at the corresponding maintenance node.

[0035] (III) Beneficial effects

[0036] The present invention provides a method for aerodynamic optimization of the shape of a high-speed elevator fairing based on digital twins, which has the following beneficial effects:

[0037] 1. When there are abnormal environmental conditions, the abnormality of the elevator operating environment in the current stage can be evaluated based on the abnormality degree. The necessity of adding a deflector to the elevator car can be evaluated based on the abnormality degree. If the necessity is high, the deflector can also be designed and optimized.

[0038] 2. After installing the deflector in the abnormal area, if there is a certain degree of abnormality in the environment in the operating area, the abnormal area can be targeted and the deflector can be installed in the abnormal area to improve the operating state of the elevator.

[0039] 3. Through simulation testing of the air deflector, the effectiveness of the air deflector can be judged and analyzed based on the obtained simulation test data, and it can be determined whether the air deflector needs to be redesigned or optimized to ensure the reliability of the air deflector design.

[0040] 4. Comprehensively evaluate the effects of the current air deflector design and layout based on the degree of improvement, determine whether the elevator's operating status is improved after the air deflector is installed on the elevator car, and quantitatively evaluate the degree of improvement. When further optimizing the appearance of the air deflector, improve the optimization's pertinence and efficiency.

[0041] 5. Use the obtained operation test data as feedback to continuously adjust and optimize the shape of the air deflector. Assisted by continuous simulation tests, the optimized air deflector can be better adapted to the operating environment in the operating area. Use performance values ​​to evaluate the performance of the designed air deflector. In the process of optimizing the air deflector, multiple judgments can be made on the air deflector to ensure the reliability of the optimized design of the air deflector.

[0042] 6. Determine whether there is a fault in the air deflector based on the acquired monitoring data. If there is a fault, it can be processed in advance to prevent actual failure during elevator operation, thereby reducing safety hazards; judge and evaluate the safety of the car and the air deflector based on the warning value, and determine whether it needs to be repaired; constrain the maintenance frequency through the warning value, so that the maintenance frequency is consistent with the operating status of the elevator car and the air deflector, reducing the safety hazards of the car and its air deflector. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 The figure is a schematic flow chart of the aerodynamic optimization method for the high-speed elevator fairing shape according to the present invention. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0045] See also Figure 1 The present invention provides a method for aerodynamic optimization of a high-speed elevator fairing shape based on digital twin, comprising:

[0046] Step 1: Collect environmental condition data in the elevator operation area. If there is an abnormality in the environmental condition data, build an abnormality degree according to the abnormality degree, and send a model building instruction to the outside when the abnormality degree exceeds expectations;

[0047] The step 1 includes the following contents:

[0048] Step 101: After determining the operation area of ​​the elevator, a sensor network including a temperature sensor, an air pressure sensor, and a humidity sensor is arranged in the operation area, such as in the elevator shaft; the sensor network monitors the elevator operation environment conditions and obtains corresponding operation environment condition data, such as air resistance, wind pressure, air flow change, temperature change, humidity, dust concentration, etc.; and the obtained environmental condition data are aggregated to generate an elevator operation environment data set;

[0049] Step 102: Train a neural network with the labeled sample data to obtain a trained abnormal data recognition model; use the real-time operating environment condition data as input, use the trained abnormal data recognition model to perform abnormal recognition, if there is abnormal data, obtain the time node where the abnormal data is generated as the abnormal node, and obtain the abnormal proportion of each abnormal data;

[0050] When in use, when the elevator is in operation, the environmental condition data is monitored and collected in the operating area to identify abnormal environmental parameters. When there are abnormal environmental conditions, considering that the abnormal environmental conditions may affect the safe operation of the elevator, the operating status of the elevator can be adjusted in time to ensure the safety of the elevator operation.

[0051] Step 103: Under dimensionless conditions, construct the abnormality degree according to the distribution of abnormal nodes and abnormal proportion , as follows:

[0052]

[0053] Where: and are the starting point and end point of the monitoring interval of the elevator operating environment conditions, is the number of abnormal nodes, is the abnormal proportion of environmental conditions on the i-th abnormal node; The value can be 2.718; weight coefficient: ， ,and ;

[0054] Based on historical data and expectations for abnormal management of the elevator operating environment, abnormal thresholds are set in advance; if the abnormality is If the abnormal threshold is exceeded, it means that the current operating environment of the elevator is abnormal, which may have a certain impact on the operating status of the elevator. At this time, a model building instruction is issued to the outside;

[0055] When using, combine the contents in steps 101 to 103:

[0056] Under the current operating environment conditions, after the elevator has been running continuously in the operating area, the abnormal environmental conditions are continuously monitored, and the abnormality degree is generated by the corresponding monitoring results. According to the abnormality degree, the abnormality degree of the elevator operating environment in the current stage can be evaluated. According to the abnormality degree, the necessity of adding a deflector to the elevator car can be evaluated. If the necessity is high, the deflector can also be designed and optimized.

[0057] Compared with the traditional symmetrical air deflector, generally speaking, the front-shaped air deflector has the best effect, with a drag reduction ratio of up to 80.21%. However, considering the speed and energy consumption requirements of high-speed elevators, the appearance of the air deflector still needs to be further optimized before installing it, considering that the operating environment conditions in the elevator operating area will have a great impact on the operating speed of the car, especially when the operating environment conditions frequently produce abnormalities, such as wind pressure, airflow changes, and temperature changes. When the frequency of abnormalities is high and the degree of abnormality is high, the operating speed of the high-speed elevator will also be greatly disturbed; and the existing air deflector optimization schemes usually focus on appearance optimization, mainly to reduce the drag coefficient, and there is a certain neglect of the installation area of ​​the air deflector, and because the main focus is on increasing the lifting speed, there is also a certain degree of neglect of the elevator operation safety.

[0058] Step 2: Build a digital twin model of elevator operation based on elevator specification attribute data. Use the digital twin model to simulate the elevator operation in the selected test scenario, and screen out abnormal areas on the car surface based on the simulated test data.

[0059] The step 2 includes the following contents:

[0060] Step 201: After receiving the model building instruction, the elevator and related data are collected, including the shaft dimensions, car parameters, shaft layout, environmental conditions and operation data, etc., and the elevator specification attribute data set is generated after being summarized;

[0061] Extract some data from the elevator specification attribute data set as sample data and annotate them. Use the annotated sample data to train the machine learning algorithm and generate a digital twin model of elevator operation.

[0062] Step 202: After collecting the actual operation scenario data of the elevator, a test scenario library is pre-set. After extracting the test scenario from the test scenario library, under the selected test scenario, such as different operation loads and operation speeds, the elevator operation digital twin model simulates the operation of the elevator and records the simulation test data, including the size of air resistance, wind pressure distribution, air flow speed and direction, etc., and generates a simulation test data set of the elevator operation after aggregation;

[0063] When in use, considering that the operating environment conditions and elevator operation scenarios in the operating area will have many changes, therefore, several different test scenarios are set before testing the elevator operation. When the elevator operation is tested under different test scenarios, comprehensive coverage of the elevator operation test can be achieved;

[0064] Step 203: After training the convolutional neural network with the labeled sample data, a trained abnormal area recognition model is obtained; using the simulated test data as input, the trained abnormal area recognition model is used to identify areas where the air resistance of the elevator car is greater than expected, such as the shaft wall and the car surface, and the location and range of the high wind pressure area and the air flow turbulence area are determined, which are taken as abnormal areas. After constructing the three-dimensional car model, the abnormal areas are marked on the three-dimensional car model;

[0065] When using, combine the contents in steps 201 to 203:

[0066] After obtaining the simulation test data of the elevator, the abnormal area on the surface of the car is determined by analyzing and identifying the simulation test data. After the air deflector is installed in the abnormal area, if there is a certain degree of abnormality in the environment in the operating area, the operating state of the elevator car can be improved by targeted treatment of the abnormal area. The operating state of the elevator can also be improved by installing the air deflector in the abnormal area;

[0067] Step 3: Determine the design and layout of the air deflector based on the abnormal area and simulation test data, and use the digital twin model of the elevator operation to verify the degree of improvement of the air deflector design and layout on the elevator operation. If the degree of improvement exceeds expectations, issue an air deflector optimization instruction to the outside.

[0068] The step three includes the following contents:

[0069] Step 301: Determine the design layout of the air deflector according to the abnormal area and the simulation test data, including at least the preliminary size, shape, installation position, material and moisture-proof treatment process of the air deflector, and add the air deflector model determined according to the air deflector layout plan to the elevator operation digital twin model;

[0070] Step 302: In a preset test scenario, the elevator operation digital twin model is used to test the car and the air deflector, and the corresponding air deflector test data is obtained, including the air resistance, wind pressure and air flow turbulence data of the car during operation after the air deflector is added, and the air deflector test data set is generated after being summarized;

[0071] When in use, after the design of the air deflector is preliminarily completed based on the simulation test data, the air deflector is simulated tested and the effectiveness of the air deflector can be judged and analyzed based on the obtained simulation test data. When the air deflector is effective, it can be judged whether the improvement effect can reach the expected effect, and then it can be determined whether the air deflector needs to be redesigned or optimized to ensure the reliability of the air deflector design.

[0072] Step 303: Based on the difference in the simulated test data after the air deflector is installed, under dimensionless conditions, the improvement degree is generated from the relevant data in the air deflector test data set. , as follows:

[0073]

[0074] Where: and The noise before and after the air deflector is installed are: is the mean of the noise, is the standard deviation of the noise; and They are the energy consumption before and after the installation of the deflector cover, is the mean value of energy consumption, is the standard deviation of energy consumption; and are the drag coefficients before and after the deflector is installed, is the mean value of the resistance coefficient, is the standard deviation of the drag coefficient; , and is the weight coefficient, which can be obtained by referring to the hierarchical analysis method. The values ​​of the three fall into , and the sum of the weight coefficients is 1; is the test time interval of the deflector;

[0075] Based on historical data and the effect management of the deflector, the improvement threshold is expected to be set; if the improvement If the improvement threshold is exceeded, it means that after adding the deflector to the car, the operation status of the elevator has been improved, and the effect and effectiveness of the deflector have been confirmed. If the operation status of the elevator needs to be further improved, the deflector can be adjusted and optimized. At this time, a deflector optimization instruction is issued to the outside.

[0076] When using, combine the contents in steps 301 to 303:

[0077] After several consecutive tests, the improvement degree is constructed through the test data obtained. Based on the improvement degree, a comprehensive evaluation can be made on the effect of the current air deflector design and layout, to determine whether the operating status of the elevator is improved after the air deflector is installed on the elevator car, and a quantitative evaluation can be made on the improvement degree, so as to further optimize the shape of the air deflector and improve the targetedness and efficiency of the optimization.

[0078] Step 4: After multiple iterations of optimization of the air deflector design and layout, the performance value of the air deflector is constructed from the test data. If the performance value does not exceed the expectation, the air deflector design and layout is reconstructed;

[0079] The step 4 includes the following contents:

[0080] Step 401: After receiving the air deflector optimization instruction, use the elevator operation digital twin model to perform operation tests on the car and the air deflector in different test scenarios to obtain corresponding operation test data;

[0081] Taking the improvement degree as the optimization goal and the running test data as feedback, the pre-trained genetic algorithm is used to adjust the design and layout of the shroud, including at least the shape, size and position-related parameters of the shroud, to obtain the optimized design and layout of the shroud;

[0082] When in use, the shape of the air deflector can be continuously adjusted and optimized based on continuous simulation tests on the air deflector and the obtained operation test data as feedback. With the assistance of continuous simulation tests, the optimized air deflector can be better adapted to the operating environment in the operating area.

[0083] Step 402: After performing multiple iterations of optimization on the arrangement of the air deflector, until the degree of improvement no longer increases, the corresponding air deflector design and arrangement scheme is used as the target scheme; in different test scenarios, such as different speeds, loads, and environmental conditions, the air deflector design and arrangement scheme of the elevator operation digital twin model is used to perform simulation tests to obtain corresponding target test data;

[0084] Step 403: Construct the performance value of the air deflector from the target test data , the comprehensive performance of the fairing is evaluated by performance value, among which the speed increase Perform linear normalization and map the corresponding data values ​​to the interval In the following way:

[0085]

[0086] Weight coefficient: ， ,and ; is the number of test scenarios, It is i The speed improvement of each test scenario is is the average value of the speed improvement;

[0087] Based on historical data and performance expectations of the air deflector, a performance threshold is pre-set; if the obtained performance value exceeds expectations, it means that the current design and layout of the air deflector can meet the expected use, and the optimization process of the air deflector of the elevator car is completed; if the performance value does not exceed expectations, the car air deflector is redesigned and the installation area is adjusted, and iterative optimization is performed;

[0088] When used, combine the contents in steps 401 to 403:

[0089] After completing the optimization process of the air deflector, the performance value is constructed according to the obtained target test data, and the performance of the designed air deflector is evaluated with the performance value to confirm whether it is necessary to redesign the layout. If the performance value can meet the requirements, the current optimization process can be terminated. If not, it is necessary to continue the optimization. In the process of optimizing the air deflector, multiple judgments can be made on the air deflector to ensure the reliability of the optimized design of the air deflector.

[0090] Step 5: monitor the operating status of the car and the air deflector in real time, predict the failure of the air deflector according to the operating monitoring data, and restrict the maintenance frequency of the air deflector according to the predicted data;

[0091] The step five includes the following contents:

[0092] Step 501: After the air deflector is optimized and installed, the elevator with the air deflector installed enters the running state, and the sensor network monitors the elevator shaft environment and the air deflector performance in real time, and obtains corresponding operation monitoring data, including air resistance, wind pressure, air flow distribution, temperature and humidity, etc., and generates an operation monitoring data set after aggregation;

[0093] The machine learning algorithm is trained with the labeled sample data to obtain the trained fault prediction model. The real-time and historical data in the operation monitoring data set are used as input, and the trained fault prediction model is used to predict the fault of the air deflector. If the air deflector may have a fault, an alarm instruction is issued to the outside.

[0094] When in use, after the air deflector is optimized, the operating status of the elevator and the car is monitored, and whether there is a fault in the air deflector is determined based on the acquired monitoring data. If a fault exists, it can be processed in advance to prevent actual failures during elevator operation, thereby reducing safety hazards.

[0095] Step 502: After receiving the alarm instruction, the corresponding time node is used as the warning node, the corresponding fault location is used as the warning location, and the maintenance frequency of the deflector is determined according to the warning node and the warning location. Constraints are performed. According to the maintenance frequency that meets the constraint conditions, the deflector cover of the elevator car is maintained at the corresponding maintenance node. The constraint method is as follows:

[0096]

[0097] in, is the warning value, is the number of alarm instructions, It is i Alert nodes to j The time interval of the alert nodes, is the average value of the time interval; It is i Warning position to j The shortest distance between the warning positions, is the average value of the shortest distance; weight coefficient: ， ,and ;The value of the weight coefficient remains consistent with the previous value;

[0098] When using, combine the contents in steps 501 and 502:

[0099] During the current stage, the time and location of possible failure of the air deflector are recorded, and an alert value is constructed based on this. Before the elevator and the air deflector fail, the safety of the car and the air deflector is judged and evaluated by the constructed alert value, and whether they need to be repaired is determined based on this. The maintenance frequency is constrained by the alert value to make the maintenance frequency consistent with the operating status of the elevator car and the air deflector, thereby reducing the safety hazards of the car and the air deflector.

[0100] The Analytic Hierarchy Process (AHP) is a decision-making method that decomposes decision-related elements into levels such as goals, criteria, and plans, and conducts qualitative and quantitative analysis on this basis. It is particularly suitable for dealing with target systems with hierarchical and staggered evaluation indicators, and when the target value is difficult to describe quantitatively, the AHP is an effective decision-making tool.

[0101] The core of the hierarchical analysis method is to decompose the decision problem into multiple levels to form a hierarchical structure, which usually includes the target level, the criterion level, the sub-criterion level and the solution level. By solving the eigenvector of the judgment matrix, the priority weight of each element of each level to an element of the previous level is obtained, and the final weight of each alternative solution to the total goal is recursively merged by the weighted sum method, so as to find the optimal solution.

[0102] 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, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0103] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0104] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only some logical function divisions. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0105] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0106] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present 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. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A high-speed elevator fairing shape aerodynamic optimization method based on digital twin, characterized by: include, Collect environmental condition data in the elevator operation area. If there is an abnormality in the environmental condition data, build an abnormality degree based on the degree of abnormality. When the abnormality exceeds expectations, issue a model building instruction to the outside. Under dimensionless conditions, build an abnormality degree based on the distribution of abnormal nodes and abnormal proportions. , as follows: Where: and are the starting point and end point of the monitoring interval of the elevator operating environment conditions, is the number of abnormal nodes, is the abnormal proportion of environmental conditions on the i-th abnormal node; The value can be 2.718; weight coefficient: ， ,and ; The elevator operation digital twin model is constructed based on the elevator specification attribute data. Under the selected test scenario, the elevator operation digital twin model is used to simulate the elevator operation and screen out abnormal areas on the car surface based on the simulated test data. The deflector design and layout scheme is determined based on the abnormal area and simulation test data. The elevator operation digital twin model verifies the improvement degree of the deflector design and layout scheme on the elevator operation. If the improvement degree exceeds expectations, a deflector optimization instruction is issued to the outside. The improvement degree is generated by the relevant data in the deflector test data set. , as follows: Where: and The noise before and after the air deflector is installed are: is the mean of the noise, is the standard deviation of the noise; and They are the energy consumption before and after the installation of the deflector cover, is the mean value of energy consumption, is the standard deviation of energy consumption; and are the drag coefficients before and after the deflector is installed, is the mean value of the resistance coefficient, is the standard deviation of the drag coefficient; , and is the weight coefficient, and the values ​​of the three fall into , and the sum of the weight coefficients is 1; is the test time interval of the deflector; After multiple iterations of optimization of the design and layout of the air deflector, the performance value of the air deflector is constructed from the test data. If the performance value does not exceed the expectation, the design and layout of the air deflector is reconstructed; Monitor the operating status of the car and the air deflector in real time, predict the failure of the air deflector based on the operating monitoring data, and constrain the maintenance frequency of the air deflector based on the predicted data.

2. The aerodynamic optimization method for the high-speed elevator fairing shape according to claim 1, characterized in that: A sensor network is arranged in the elevator operation area, and the sensor network monitors the elevator operation environment conditions and obtains corresponding operation environment condition data, which are then aggregated to generate an elevator operation environment data set; The real-time operating environment condition data is used as input, and the trained abnormal data recognition model is used to identify abnormal data. If abnormal data exists, the time node where the abnormal data is generated is obtained as the abnormal node, and the abnormal proportion of each abnormal data is obtained. The abnormality degree is constructed based on the distribution of abnormal nodes and the abnormal proportion.

3. The aerodynamic optimization method for the high-speed elevator fairing shape according to claim 2, characterized in that: After receiving the model building instruction, the elevator and related data are collected to generate a set of elevator specification attribute data; Some data is extracted from the elevator specification attribute data set as sample data and labeled. The labeled sample data is used to train the machine learning algorithm to generate a digital twin model of elevator operation.

4. The aerodynamic optimization method for the high-speed elevator fairing shape according to claim 3, characterized in that: After collecting the actual operation scenario data of the elevator, a test scenario library is pre-set, and test scenarios are extracted from the test scenario library. The elevator operation digital twin model is used to simulate the elevator operation, record the simulated test data, and summarize them to generate a simulated test data set for the elevator operation.

5. The aerodynamic optimization method for the high-speed elevator fairing shape according to claim 4, characterized in that: Taking the simulated test data as input, the trained abnormal region recognition model is used to identify the areas where the air resistance of the elevator car is greater than expected, and regard them as abnormal areas.

6. The aerodynamic optimization method for the high-speed elevator fairing shape according to claim 5, characterized in that: The design and layout plan of the air deflector shall at least include the preliminary size, shape, installation location, material and moisture-proof treatment process of the air deflector. The air deflector model determined according to the air deflector layout plan shall be added to the elevator operation digital twin model; In the preset test scenario, the elevator operation digital twin model is used to test the car and the air deflector, and the corresponding air deflector test data is obtained. After aggregation, the air deflector test data set is generated, and the improvement degree is generated from the relevant data in the air deflector test data set.

7. The aerodynamic optimization method for the high-speed elevator fairing shape according to claim 6, characterized in that: After receiving the deflector optimization instruction, the elevator operation digital twin model is used to perform operation tests on the car and deflector in different test scenarios to obtain the corresponding operation test data; Taking improving the degree of improvement as the optimization goal and running test data as feedback, the pre-trained genetic algorithm is used to adjust the design layout of the shroud to obtain the optimized design layout of the shroud.

8. The aerodynamic optimization method for the high-speed elevator fairing shape according to claim 7, characterized in that: After the arrangement of the air deflector is optimized for multiple iterations until the degree of improvement no longer increases, the corresponding air deflector design arrangement scheme is taken as the target scheme; In different test scenarios, the elevator operation digital twin model is used to simulate the design and layout of the fairing to obtain the corresponding target test data; The performance value of the air deflector is constructed from the target test data. If the performance value does not exceed the expectation, the car air deflector is redesigned and the installation area is adjusted, and iterative optimization is performed.

9. The aerodynamic optimization method for the high-speed elevator fairing shape according to claim 8, characterized in that: After the air deflector is optimized and installed, the elevator with the air deflector installed is put into operation. The sensor network monitors the elevator shaft environment and air deflector performance in real time, obtains corresponding operation monitoring data, and generates an operation monitoring data set after aggregation; The real-time and historical data in the operation monitoring data set are used as input, and the trained fault prediction model is used to predict the fault of the air deflector. If the air deflector may have a fault, an alarm command is issued to the outside.

10. The aerodynamic optimization method for the high-speed elevator fairing shape according to claim 9, characterized in that: After receiving the alarm instruction, the corresponding time node is used as the warning node, the corresponding fault location is used as the warning location, and the maintenance frequency of the deflector is constrained according to the distribution of the warning nodes and the warning locations; According to the maintenance frequency that meets the constraint conditions, the deflector cover of the elevator car is maintained at the corresponding maintenance node.

Images