Elevator digital twin virtual and physical sensor data calibration method

Abstract

The invention discloses an elevator digital twinning virtual and physical sensor data calibration method. The method comprises the steps that real-time data of multiple types of physical sensors in an elevator system and real-time data of virtual sensors in an elevator digital twinning model in a reference environment at the same moment are obtained; preprocessing the data, and comparing the acquired data of the physical sensor and the virtual sensor of the same category according to a distance function to obtain an error between the physical sensor and the virtual sensor at the moment t; comparing whether the error exceeds a set error threshold value or not; and if the error exceeds the threshold value, correcting the physical sensor data through linear regression calibration and an offset correction function, and updating the virtual sensor data at the next moment in the digital twin. The actual measurement data of the physical sensor and the measurement data of the virtual sensor of the digital twin are combined, the sensor deviation is calculated and calibrated in real time, and the problem of single sensor error can be effectively solved.

Description

Technical Field

[0001] The present invention relates to the technical field of elevator digital twins, and in particular to a method for calibrating virtual and physical sensor data of elevator digital twins. Background Art

[0002] With the rapid development of my country's economic construction and the rapid construction of high-rise buildings, elevators have become an indispensable facility in people's daily production and life. At present, with the widespread popularization of the Internet of Things, elevators have gradually applied the Internet of Things system, but due to various uncertainties in the system itself, the physical sensors of elevators are also unstable in long-term operation. Because the hardware unit, communication unit and surrounding environment of the physical sensor itself may cause the sensor to be abnormal and produce noise, offset, drift and other phenomena. For example, there is a sensor with intermittent drift error (traction machine temperature, vibration sensor) in the elevator sensing system. Due to the compact deployment space of the sensor and the thermal radiation interference of the surrounding control cabinet, the temperature sensor will produce temperature and vibration deviations due to electromagnetic interference, thermal radiation, hardware abnormalities and other factors. Therefore, when facing a limited and unreliable sensing environment, it will have a negative impact on the data-driven application in the elevator digital twin system. The digital twin technology integrates multi-physics, multi-disciplinary and multi-scale attributes, and has the characteristics of hyper-realism, real-time synchronization, full elements and uniqueness. It can realize the interactive integration of the physical world and the information world, thereby reflecting the corresponding full life cycle process of the physical equipment.

[0003] At present, the retrieved digital twin virtual-reality consistency method is the patent "Complex system-level digital twin operation virtual-reality consistency determination and interaction method" (application number 202211410916.5), which discloses a complex system-level digital twin operation virtual-reality consistency determination and interaction method, describes the subspaces in the physical space and virtual space of the complex system, proposes a virtual-reality consistency determination method based on dynamic operation, and proposes the specific operation and interaction method between virtual-reality subspaces; This method establishes the operation and interaction process of virtual space and physical space based on the association relationship of digital twins of complex systems, but there are still some shortcomings: 1. This technology has not yet considered how to ensure the accuracy and timeliness of data transmitted between physical sensors and virtual sensors, and cannot further guarantee the effectiveness of the mutual feedback between the digital twin virtual and real models.

[0004] 2. Traditional methods usually only focus on the error calibration of a single sensor and have not considered the sensor calibration optimization in the local or global environment of the digital twin.

[0005] Therefore, a data calibration method is needed to ensure the reliability of physical sensors and virtual sensors to ensure the accuracy and safety of elevator digital twins during their entire life cycle. To this end, the present invention proposes a data calibration method for virtual and physical sensors of elevator digital twins. Summary of the invention

[0006] Therefore, the purpose of the present invention is to provide a method and system for calibrating virtual and physical sensor data of an elevator digital twin, so as to solve the error problem between sensor data and ensure the consistency of virtual sensor and physical sensor data.

[0007] In order to achieve the above object, the present invention provides a method and system for calibrating virtual and physical sensor data of an elevator digital twin, comprising the following steps: S1. Obtain real-time data of multiple types of physical sensors in the elevator system under the reference environment at the same time t and real-time data of virtual sensors in the elevator digital twin model; S2. Preprocess the data, compare the collected physical sensor and virtual sensor data of the same category according to the distance function, and obtain the error between the physical sensor and the virtual sensor at time t. D fused (t); S3. Comparison error D fused (t) Whether it exceeds the set error threshold ; If the error exceeds the threshold, the physical sensor data is corrected through linear regression calibration and offset correction function, and the virtual sensor data at the next moment in the digital twin is updated.

[0008] Further preferably, in S3, the distance function includes a direct distance function and an indirect distance function. The direct distance function is used to calculate the error between the physical sensor data and the virtual sensor prediction value, and the indirect distance function is used to calculate and verify the matching relationship between each sensor and calibrate the transmission error.

[0009] Further preferably, the direct distance function is expressed by the following formula: ; in, is the error between the physical sensor and the virtual sensor calculated at time t; is the physical sensor data, is virtual sensor data.

[0010] Further preferably, the indirect distance function is expressed by the following formula: ; in: Based on virtual sensor For physical sensors The predicted value; n is the number of physical sensors, m is the number of virtual sensors; It is the calculation of the predicted value and the physical sensor at time t The error between them; i is the actual physical sensor dataset index, and j is the corresponding virtual sensor dataset index.

[0011] Further preferably, it also includes establishing a neural network to predict the data collected by various physical sensors according to the correlation between the sensors, and obtaining Among them, NN represents neural network, is the predicted value; V 1 (t), V 2 (t),V m (t) is the input value.

[0012] Further preferably, in S3, when updating the virtual sensor data of the digital twin at the next moment, the virtual sensor model is adjusted using a weighted average method according to the error calculated by the indirect distance function: ; in: is the weight of the physical sensor, is the weight of the virtual sensor, and the error between the physical sensor and the virtual sensor is minimized by optimizing the weight coefficient. It is the weighted average of virtual sensors and physical sensors.

[0013] Further preferably, in S2, when the comparison is performed according to the distance function, the distance function is a result of weighted fusion of the direct distance function and the indirect distance function, which is expressed according to the following formula: ; in: is the error function after fusion; is the weight coefficient; is the direct distance function, is the error of the indirect distance function.

[0014] Further preferably, a dynamic adjustment mechanism of the weight coefficients of the next moment and the current moment is set according to the following formula; in, is the learning rate, is the weight factor of the direct error, is the weight factor of indirect error; is the historical RMS error of the sensor; is the coefficient of variation of the working environment; are historical errors and environmental changes. Impact factor; Further preferably, the learning rate Dynamically adjust based on historical error feedback as the sensor's historical stability changes; in is the initial learning rate; is the historical RMS error of the sensor; is the parameter that controls the learning rate decay. The larger the value, the worse the sensor stability. To avoid frequent adjustments; The smaller the value, the better the stability of the sensor. Improve adjustment speed.

[0015] The elevator digital twin virtual and physical sensor data calibration method disclosed in this application has at least the following advantages over the prior art: 1. This application combines the measured data of physical sensors with the measured data of virtual sensors of digital twins. Real-time calculation and calibration of sensor deviation can effectively solve the problem of single sensor error. This method achieves comprehensive coordination of different sensor types by dynamically selecting distance functions and adaptively adjusting calibration tolerances, ensuring the accuracy of sensor data during elevator operation.

[0016] 2. The present invention uses direct distance function and indirect distance function to perform fusion calibration. By monitoring the status of key components of the elevator, the calibration can be automatically adjusted according to the deviation of sensor data. This method not only improves the fault tolerance of the elevator, but also can discover potential problems in advance through historical data analysis and trend prediction, reduce downtime and sudden failures, and improve the reliability of long-term monitoring of the elevator. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 It is a structural schematic diagram of a method for calibrating virtual and physical sensor data of an elevator digital twin according to the present invention.

[0018] Figure 2 It is a schematic diagram of the process of correcting the virtual data of the digital twin by the indirect distance function in the present invention. DETAILED DESCRIPTION

[0019] The present invention is further described in detail below through the accompanying drawings and specific embodiments.

[0020] like Figure 1As shown, an embodiment of the present invention provides a method for calibrating virtual and physical sensor data of an elevator digital twin, comprising the following steps: First, perform a reference environment calibration; define the reference environment: During the normal operation of the elevator, select a standard operating condition as the calibration reference environment. The reference environment should meet the following conditions: The elevator is in a stable operating state and there are no abnormal faults.

[0021] Both physical and virtual sensors are within the working range and the data are stable.

[0022] Environmental factors (such as temperature, humidity, vibration, etc.) should be close to normal operating conditions to avoid excessive interference with sensor data.

[0023] Data collection: It is necessary to arrange multiple types of sensors (such as temperature sensors, current sensors, acceleration sensors, etc.) in the elevator system to collect sensor data under the reference environment. Based on the above data, a calibration benchmark model is constructed to provide a standard reference for subsequent error calibration.

[0024] S1. Obtain real-time data of multiple types of physical sensors in the elevator system under the reference environment at the same time t and real-time data of virtual sensors in the elevator digital twin model; Physical sensors include temperature sensors, acceleration sensors, current sensors, etc., while virtual sensors are based on data calculated by the elevator simulation model.

[0025] S2. Preprocess the data. Compare the collected physical sensor and virtual sensor data of the same category according to the distance function to obtain the error between the physical sensor and the virtual sensor at time t. D fused (t); Preprocessing includes: removing noise, filling missing values, and performing time synchronization; comparing the data of the acquired physical sensor and virtual sensor at the same timestamp; and error type identification: depending on the sensor type, possible errors include drift error, system error, error caused by environmental changes, etc. When calculating the error, it is necessary to combine the working characteristics of the sensor to identify the error type.

[0026] Compare the physical sensor and virtual sensor data of the same category collected at the same time t according to the distance function to obtain the error between the physical sensor and the virtual sensor at time t D fused (t); Definition of direct distance function: It is used to calculate the error difference between physical sensor and virtual sensor under the same operating conditions. It is applicable to sensors in the same or similar working environment.

[0027] Definition of indirect distance function: It is used to process the scenario of data fusion between multiple physical sensors and virtual sensors, and calculate the overall error by analyzing the error transmission relationship between multiple sensors.

[0028] The direct distance function focuses on solving the error of physical sensors. By calculating the error between the physical sensor data and the virtual sensor prediction value, the direct distance function helps to identify and correct the deviation of the physical sensor. Because physical sensors are easily affected by external factors (such as temperature changes, electromagnetic interference, etc.), drift or error may occur. The specific process is as follows Figure 1 shown.

[0029] The direct distance function is expressed as follows: in, is the error between the physical sensor and the virtual sensor calculated at time t; is the physical sensor data, is virtual sensor data.

[0030] Collect data from the physical sensor and the virtual sensor at the same time point; calculate the difference between the two and obtain the error between the physical sensor and the virtual sensor calculated at time 𝑡 ; and compare the error Whether it exceeds the set error threshold If the error exceeds a threshold, a calibration operation is performed to adjust the physical sensor data through linear regression and an offset correction function.

[0031] S3. Comparison error D fused (t) Whether it exceeds the set error threshold ; If the error exceeds the threshold, the physical sensor data is corrected through linear regression calibration and offset correction function, and the virtual sensor data at the next moment in the digital twin is updated.

[0032] Linear regression calibration: Correct the error of the physical sensor by establishing a linear relationship between the physical sensor data and the virtual sensor data: ; in, and is the regression coefficient estimated by the least squares method. This calibration function adjusts the physical sensor data Bringing it closer to virtual sensor data .

[0033] Offset correction: If the error is mainly offset error (such as long-term drift of the sensor), the offset correction function can be used to correct the offset; ; Select the linear regression calibration method or the offset correction method based on the gradient of the difference between the previous and next acquisition moments. Because the gradient change reflects the state evolution of the sensor between consecutive moments, if the sensor error presents a stable offset, the gradient change is small, and offset correction can be used first. If the gradient changes significantly and shows a linear trend, it may be caused by gain error or external disturbance, and linear regression is more suitable at this time. If the gradient changes dramatically and irregularly, it indicates that there may be external noise, interference or hardware failure.

[0034] Real-time feedback: Confirm that the physical sensor data calibration is complete, and the corrected data will be fed back to the elevator system in real time.

[0035] When updating the virtual sensor data at the next moment in the digital twin, the virtual sensor model is adjusted using the weighted average method based on the error calculated by the indirect distance function: ; in: is the weight of the physical sensor, is the weight of the virtual sensor, and the error between the physical sensor and the virtual sensor is minimized by optimizing the weight coefficient. It is the weighted average of virtual sensors and physical sensors.

[0036] The focus of the indirect distance function is to globally optimize all sensors in the system by analyzing the data of multiple sensors (a combination of physical sensors and virtual sensors). Even if the error of each sensor is relatively small, the combined error between multiple sensors may affect the accuracy of the entire elevator system. Therefore, the indirect distance function can find the error transmission relationship between multiple sensors and further optimize the entire system. The specific process is as follows Figure 2 As shown. The obtained multiple physical sensor data and virtual sensor data, as well as the predicted values ​​of the virtual sensors, are used to establish a multi-sensor error model based on the indirect distance function, and the obtained errors are weighted averaged to minimize the errors. Finally, the elevator digital twin system is updated with real-time feedback to update the virtual data.

[0037] The indirect distance function is expressed by the following formula: ; in: Based on virtual sensor For physical sensors The predicted value; n is the number of physical sensors, m is the number of virtual sensors; It is the calculation of the predicted value and the physical sensor at time t The error between them; i is the actual physical sensor dataset index, and j is the corresponding virtual sensor dataset index.

[0038] The prediction value is obtained by using a neural network to predict the data collected by various physical sensors based on the correlation between sensors. Among them, NN() represents a neural network; the input value V 1 (t) After being input into the neural network, is the predicted value obtained.

[0039] In the elevator system, single sensor error and multi-sensor error may have different influence weights. In order to integrate these two error models, in S4, the error compared with the threshold is the final fused error obtained by weighted fusion of the direct distance function and the indirect distance function. D fused ; ; in: is the error function after fusion; is the weight coefficient; is the direct distance function, is the error of the indirect distance function.

[0040] Further preferably, a dynamic adjustment mechanism for the weight coefficients of the next moment and the current moment is set according to the following formula: in, is the learning rate, is the weight factor of the direct error, is the weight factor of indirect error; is the historical RMS error of the sensor; is the coefficient of variation of the working environment; are historical errors and environmental changes. Impact factor; Further preferably, the learning rate As the sensor's historical stability changes dynamically, it is dynamically adjusted based on historical error feedback.

[0041] in is the initial learning rate; is the historical RMS error of the sensor; is the parameter that controls the learning rate decay. The larger the value, the worse the sensor stability. To avoid frequent adjustments; The smaller the value, the better the stability of the sensor. Improve adjustment speed.

[0042] Obviously, the above embodiments are only examples for clear explanation, and are not intended to limit the implementation methods. For ordinary technicians in the relevant field, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the implementation methods here. The obvious changes or modifications derived from them are still within the protection scope of the invention.

Claims

1. A method for calibrating virtual and physical sensor data of an elevator digital twin, characterized in that: include: S1. Obtain real-time data of multiple types of physical sensors in the elevator system under the reference environment at the same time t and real-time data of virtual sensors in the elevator digital twin model; S2. Preprocess the data, compare the collected physical sensor and virtual sensor data of the same category according to the distance function, and obtain the error between the physical sensor and the virtual sensor at time t. D fused (t); S3. Comparison error D fused (t) Whether it exceeds the set error threshold ; If the error exceeds the threshold, the physical sensor data is corrected through linear regression calibration and offset correction function, and the virtual sensor data at the next moment in the digital twin is updated.

2. The elevator digital twin virtual and physical sensor data calibration method according to claim 1 is characterized in that: In S3, the distance function includes a direct distance function and an indirect distance function. The direct distance function is used to calculate the error between the physical sensor data and the virtual sensor prediction value, and the indirect distance function is used to calculate and verify the matching relationship between each sensor and calibrate the transmission error.

3. The elevator digital twin virtual and physical sensor data calibration method according to claim 2 is characterized in that: The direct distance function is expressed by the following formula: ； in, is the error between the physical sensor and the virtual sensor calculated at time t; is the physical sensor data, is virtual sensor data.

4. The elevator digital twin virtual and physical sensor data calibration method according to claim 2 is characterized in that: The indirect distance function is expressed by the following formula: ； in: Based on virtual sensor For physical sensors The predicted value; n is the number of physical sensors, m is the number of virtual sensors; It is the calculation of the predicted value and the physical sensor at time t The error between them; i is the actual physical sensor dataset index, and j is the corresponding virtual sensor dataset index.

5. The elevator digital twin virtual and physical sensor data calibration method according to claim 4 is characterized in that: It also includes building a neural network to predict the data collected by various physical sensors based on the correlation between sensors. ； Among them, NN represents neural network, is the predicted value; V1(t), V2(t), V m (t) is the input value.

6. The elevator digital twin virtual and physical sensor data calibration method according to claim 4 is characterized in that: In S3, when updating the virtual sensor data at the next moment in the digital twin, the virtual sensor model is adjusted using the weighted average method based on the error calculated by the indirect distance function: ; in: is the weight of the physical sensor, is the weight of the virtual sensor, and the error between the physical sensor and the virtual sensor is minimized by optimizing the weighting coefficient; It is the weighted average of virtual sensors and physical sensors.

7. The elevator digital twin virtual and physical sensor data calibration method according to claim 4, characterized in that: In S2, when the comparison is performed according to the distance function, the distance function is a result of weighted fusion of the direct distance function and the indirect distance function, which is expressed as follows: ； in: is the error function after fusion; is the weight coefficient; is the direct distance function, is the error of the indirect distance function.

8. The elevator digital twin virtual and physical sensor data calibration method according to claim 7, characterized in that: The dynamic adjustment mechanism of the weight coefficient between the next moment and the current moment is set according to the following formula; ； in, is the learning rate, is the weight factor of the direct error, is the weight factor of indirect error; is the historical RMS error of the sensor; is the coefficient of variation of the working environment; are historical errors and environmental changes. The impact factor.

9. The elevator digital twin virtual and physical sensor data calibration method according to claim 8, characterized in that: The learning rate Dynamically adjust based on historical error feedback as the sensor's historical stability changes; ； in is the initial learning rate; is the historical RMS error of the sensor; is the parameter that controls the learning rate decay. The larger the value, the worse the sensor stability. To avoid frequent adjustments; The smaller the value, the better the stability of the sensor. Improve adjustment speed.

Images