A method and system for monitoring stress of guide beams in jacking construction

Abstract

The present invention provides a method and system for monitoring stress in a guide beam during jacking construction, relating to the technical field of stress monitoring. The method comprises: determining stress data and construction environment data at multiple moments during a monitoring cycle using a combination of sensors disposed at preset locations in the construction environment and at preset stress monitoring locations; processing the construction environment data according to a trained stress detection error prediction model to obtain a stress detection error; determining actual stress data based on the stress detection error and the stress data; obtaining construction material information; determining an allowable stress value based on the construction material information; determining real-time stress monitoring results based on the allowable stress value and actual stress data; determining dynamic impact stress monitoring results based on the actual stress data; and generating a monitoring report based on the real-time stress monitoring results and the dynamic impact stress monitoring results. According to the present invention, the accuracy and comprehensiveness of stress monitoring in guide beams during jacking construction can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of stress monitoring, and in particular to a method and system for monitoring the stress of a guide beam during jacking construction. Background Art

[0002] In related technologies, stress monitoring of guide beams in jacking construction mainly relies on stress sensor detection combined with manual monitoring, that is, it mainly relies on human factors. Excessive reliance on human factors may make it difficult to ensure the timeliness and accuracy of data processing, resulting in poor real-time performance of monitoring results and limited accuracy of monitoring results.

[0003] The information disclosed in the background technology section of this application is only intended to deepen the understanding of the general background technology of this application, and should not be regarded as an admission or any form of suggestion that the information constitutes the prior art already known to those skilled in the art. Summary of the Invention

[0004] The present invention provides a method and system for monitoring the stress of a guide beam in jacking construction, which can solve the technical problem that related technologies cannot ensure the timeliness and accuracy of monitoring results.

[0005] According to a first aspect of the present invention, a method for monitoring stress of a guide beam in a jacking construction is provided, comprising: determining stress data and construction environment data at multiple moments in a monitoring cycle by a combination of sensors arranged at preset positions and preset stress monitoring positions in the construction environment, wherein the construction environment data comprises temperature data and electromagnetic interference data; processing the construction environment data according to a trained stress detection error prediction model to obtain a stress detection error; determining actual stress data according to the stress detection error and the stress data; acquiring construction material information; determining an allowable stress value according to the construction material information; determining a real-time stress monitoring result according to the allowable stress value and the actual stress data; determining a dynamic impact stress monitoring result according to the actual stress data; and generating a monitoring report according to the real-time stress monitoring result and the dynamic impact stress monitoring result.

[0006] According to the present invention, the training steps of the stress detection error prediction model include: obtaining historical applied stress, historical detected stress, historical test temperature difference, historical test potential difference and historical test loop resistance in multiple historical test cycles; determining the historical actual stress detection error based on the historical applied stress and the historical detected stress; obtaining historical test current loop direction and historical sensor sensitive current direction in multiple historical test cycles; determining the electromagnetic deviation direction identification result based on the historical test current loop direction and the historical sensor sensitive current direction; obtaining the thermal expansion coefficient of the guide beam material and the thermal expansion coefficient of the sensor substrate; determining the temperature based on the thermal expansion coefficient of the guide beam material and the thermal expansion coefficient of the sensor substrate. Deviation direction identification result; processing the electromagnetic deviation direction identification result, the temperature deviation direction identification result, the historical test temperature difference, the historical test potential difference and the historical test loop resistance according to the stress detection error prediction model to determine the training stress detection error; determining the training loss function of the stress detection error prediction model according to the training stress detection error, the historical actual stress detection error, the electromagnetic deviation direction identification result, the temperature deviation direction identification result, the historical test temperature difference, the historical test potential difference and the historical test loop resistance; training the stress detection error prediction model according to the training loss function to obtain a trained stress detection error prediction model.

[0007] According to the present invention, the training loss function of the stress detection error prediction model is determined based on the training stress detection error, the historical actual stress detection error, the electromagnetic deviation direction identification result, the temperature deviation direction identification result, the historical test temperature difference, the historical test potential difference and the historical test loop resistance, including: according to the formula , determine the training loss function of the stress detection error prediction model , where if is a conditional function, is the training stress detection error of the k-th historical test cycle, is the historical actual stress detection error of the kth historical test cycle, is the temperature deviation direction identification result of the kth historical test cycle, , is the historical test temperature difference of the kth historical test cycle, is the preset temperature difference threshold, is the electromagnetic deviation direction identification result of the kth historical test cycle, , is the historical test potential difference of the kth historical test cycle, is the preset potential difference threshold, is the historical test loop resistance of the kth historical test cycle, is the preset loop resistance threshold, K is the number of historical test cycles, k≤K, and both k and K are positive integers.

[0008] According to the present invention, the construction environment data is processed according to a trained stress detection error prediction model to obtain a stress detection error, including: determining the temperature difference at a preset stress monitoring position according to the temperature data; determining the real-time potential difference and the real-time loop resistance according to the electromagnetic interference data; obtaining the real-time current loop direction and the real-time sensor sensitive current direction at multiple moments in a monitoring period; determining a real-time electromagnetic deviation direction identification result according to the real-time current loop direction and the real-time sensor sensitive current direction; and processing the real-time electromagnetic deviation direction identification result, the temperature deviation direction identification result, the temperature difference, the real-time potential difference and the real-time loop resistance according to the trained stress detection error prediction model to obtain a stress detection error.

[0009] According to the present invention, determining the allowable stress value according to the construction material information includes: determining the material yield strength according to the construction material information; and determining the allowable stress value according to the material yield strength.

[0010] According to the present invention, the dynamic impact stress monitoring result is determined based on the actual stress data, including: obtaining the monitoring coordinates of each preset stress monitoring position in a preset coordinate system, wherein the preset coordinate system is a coordinate system established based on a preset origin within the range of the construction target; determining the actual stress mutation amount based on the actual stress data; determining the overall impact stress anomaly coefficient based on the actual stress mutation amount and the monitoring coordinates; and determining the dynamic impact stress monitoring result based on the overall impact stress anomaly coefficient.

[0011] According to the present invention, the overall impact stress anomaly coefficient is determined based on the actual stress mutation amount and the monitoring coordinates, including: determining a plurality of stress monitoring position combinations based on preset stress monitoring positions, wherein a single stress monitoring position combination includes a plurality of preset stress monitoring positions in the same area; determining a structural continuous identification result for each stress monitoring position combination; determining an impact stress difference threshold based on the structural continuous identification result; determining adjacent monitoring positions of the preset stress monitoring position in the stress monitoring position combination; determining the impact stress anomaly coefficient of each stress monitoring position combination based on the impact stress difference threshold, the actual stress mutation amount and the monitoring coordinates; and determining the overall impact stress anomaly coefficient based on the impact stress anomaly coefficient of each stress monitoring position combination.

[0012] According to the present invention, the impact stress anomaly coefficient of each stress monitoring position combination is determined based on the impact stress difference threshold, the actual stress mutation amount and the monitoring coordinates, including: according to the formula , determine the impact stress anomaly coefficient of the jth stress monitoring position combination at the i-th moment of the monitoring period , where max is the maximum value function, is the actual stress mutation at the e-th preset stress monitoring position in the j-th stress monitoring position combination at the i-th moment of the monitoring period, is the preset stress mutation threshold, is the actual stress mutation at the i-th moment of the monitoring period at the adjacent monitoring position of the e-th preset stress monitoring position in the j-th stress monitoring position combination, is the impact stress difference threshold of the jth stress monitoring position combination, is the monitoring coordinate of the e-th preset stress monitoring position in the j-th stress monitoring position combination at the i-th moment of the monitoring period, is the monitoring coordinate of the adjacent monitoring position at the i-th moment of the monitoring period of the e-th preset stress monitoring position in the j-th stress monitoring position combination, is the preset point distance threshold, E is the number of preset stress monitoring positions in the stress monitoring position combination, e≤E, and both e and E are positive integers.

[0013] According to a second aspect of the present invention, a stress monitoring system for a guide beam in a jacking construction is provided, comprising: a data acquisition module for determining stress data and construction environment data at multiple moments in a monitoring cycle by means of a combination of sensors arranged at preset positions and preset stress monitoring positions in the construction environment, wherein the construction environment data comprises temperature data and electromagnetic interference data; a detection error module for processing the construction environment data according to a trained stress detection error prediction model to obtain a stress detection error; an actual stress module for determining actual stress data according to the stress detection error and the stress data; a material information module for acquiring construction material information; an allowable stress module for determining an allowable stress value according to the construction material information; a real-time monitoring module for determining a real-time stress monitoring result according to the allowable stress value and the actual stress data; an impact monitoring module for determining a dynamic impact stress monitoring result according to the actual stress data; and a monitoring report module for generating a monitoring report according to the real-time stress monitoring result and the dynamic impact stress monitoring result.

[0014] Technical effect: According to the present invention, the influence of the construction environment on the detection error of the stress sensor can be accurately analyzed, and the actual stress data can be determined based on the detection error. Furthermore, the stress abnormality and stress mutation abnormality during the jacking construction process are monitored based on the actual stress value, and corresponding monitoring information is generated, thereby improving the accuracy and comprehensiveness of the stress monitoring of the jacking construction guide beam. When determining the training loss function of the stress detection error prediction model, the training loss function of the stress detection error prediction model can be determined based on the training stress detection error, the historical actual stress detection error, the electromagnetic deviation direction recognition result, the temperature deviation direction recognition result, the historical test temperature difference, the historical test potential difference size and the historical test loop resistance size. During the calculation process, the influence of the above data on the training stress detection error can be determined based on the possible influence of the temperature difference, potential difference size and loop resistance size on the stress detection error, and the training loss function is set based on the influence and the relative error of the training stress detection error, so that the training loss function of the stress detection error prediction model is reduced during the training process, and the accuracy of the stress detection error prediction model is improved in a more targeted manner. When determining the impact stress anomaly coefficient, the impact stress anomaly coefficient of each stress monitoring position combination is determined according to the impact stress difference threshold, the actual stress mutation amount and the monitoring coordinates. During the calculation process, the stress mutation anomaly condition of the stress monitoring position combination can be evaluated based on whether the stress mutation amount at the preset stress monitoring position itself is abnormal and whether the difference in stress mutation amount between the preset stress monitoring position and its adjacent monitoring positions is abnormal, thereby improving the comprehensiveness and accuracy of the impact stress anomaly coefficient.

[0015] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and not limiting of the present invention. Other features and aspects of the present invention will become more apparent from the following detailed description of exemplary embodiments with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can derive other embodiments based on these drawings without inventive efforts.

[0017] Figure 1 A schematic flow chart of a method for monitoring stress of a guide beam during jacking construction according to an embodiment of the present invention is exemplarily shown;

[0018] Figure 2 A schematic diagram exemplarily illustrates a method for obtaining a stress detection error according to an embodiment of the present invention;

[0019] Figure 3 A schematic diagram illustrating, by way of example, determining an allowable stress value according to an embodiment of the present invention;

[0020] Figure 4 A schematic diagram illustrating, by way of example, determining an overall impact stress anomaly coefficient according to an embodiment of the present invention;

[0021] Figure 5 A block diagram of a guide beam stress monitoring system for jacking construction according to an embodiment of the present invention is exemplarily shown. DETAILED DESCRIPTION

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings 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 making creative efforts shall fall within the scope of protection of the present invention.

[0023] The following specific embodiments are used to describe the technical solution of the present invention in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0024] Figure 1 A flow chart of a method for monitoring stress of a guide beam in jacking construction according to an embodiment of the present invention is exemplarily shown, the method comprising: step S1, at multiple moments in a monitoring period, determining stress data and construction environment data by a combination of sensors arranged at preset positions and preset stress monitoring positions in the construction environment, wherein the construction environment data comprises temperature data and electromagnetic interference data; step S2, processing the construction environment data according to a trained stress detection error prediction model to obtain a stress detection error; step S3, determining actual stress data according to the stress detection error and the stress data; step S4, acquiring construction material information; step S5, determining an allowable stress value according to the construction material information; step S6, determining a real-time stress monitoring result according to the allowable stress value and the actual stress data; step S7, determining a dynamic impact stress monitoring result according to the actual stress data; step S8, generating a monitoring report according to the real-time stress monitoring result and the dynamic impact stress monitoring result.

[0025] According to the stress monitoring method for the guide beam of jacking construction according to the embodiment of the present invention, the influence of the construction environment on the detection error of the stress sensor can be accurately analyzed, and the actual stress data can be determined based on the detection error. Furthermore, the abnormal stress conditions and abnormal stress mutation conditions during the jacking construction process are monitored based on the actual stress value, and corresponding monitoring information is generated, thereby improving the accuracy and comprehensiveness of the stress monitoring of the guide beam of jacking construction.

[0026] According to one embodiment of the present invention, in step S1, at multiple moments in the monitoring cycle, stress data and construction environment data are determined by a combination of sensors set at preset positions and preset stress monitoring positions in the construction environment, wherein the construction environment data includes: temperature data and electromagnetic interference data.

[0027] For example, due to the complex construction site environment, decentralized power supply of equipment, and differences in grounding paths and grounding quality of different equipment, there is a potential difference between different equipment. Electromagnetic interference data is detected by setting a dual-channel DC millivoltmeter, a four-wire micro-ohmmeter, and a wireless potential sensor at a preset position (e.g., the root of the guide beam). Stress sensors are set at preset stress monitoring positions (e.g., multiple positions at the root of the guide beam, multiple positions at the front cantilever end of the guide beam, multiple positions at the mid-span area of ​​the guide beam, multiple positions at the variable-section transition section, and multiple positions at the end of the stiffening rib and the weld area). The stress data at each preset stress monitoring position is detected. Corresponding temperature sensors are arranged closely next to each preset stress monitoring position, and corresponding temperature sensors are further arranged at positions where the longitudinal spacing between each preset stress monitoring position is less than 3m (e.g., 3m directly below the preset stress monitoring position). The temperature data at each temperature sensor is obtained through the temperature sensors.

[0028] According to one embodiment of the present invention, in step S2, the construction environment data is processed according to the trained stress detection error prediction model to obtain the stress detection error.

[0029] For example, the stress detection error prediction model is a deep learning neural network model, which can process the construction environment data according to the trained stress detection error prediction model to determine the stress detection error caused by the impact of the construction environment on the sensor.

[0030] According to one embodiment of the present invention, the step of training the stress detection error prediction model includes:

[0031] Obtain historical applied stress, historical detection stress, historical test temperature difference, historical test potential difference, and historical test loop resistance in multiple historical test cycles;

[0032] determining a historical actual stress detection error based on the historical applied stress and the historical detected stress;

[0033] Obtain historical test current loop directions and historical sensor sensitive current directions in multiple historical test cycles;

[0034] Determining an electromagnetic deviation direction identification result according to the historical test current loop direction and the historical sensor sensitive current direction;

[0035] Obtaining the thermal expansion coefficient of the guide beam material and the thermal expansion coefficient of the sensor substrate;

[0036] Determining a temperature deviation direction identification result according to the thermal expansion coefficient of the guide beam material and the thermal expansion coefficient of the sensor substrate;

[0037] Processing the electromagnetic deviation direction identification result, the temperature deviation direction identification result, the historical test temperature difference, the historical test potential difference, and the historical test loop resistance according to the stress detection error prediction model to determine a training stress detection error;

[0038] Determining a training loss function for a stress detection error prediction model based on the training stress detection error, the historical actual stress detection error, the electromagnetic deviation direction identification result, the temperature deviation direction identification result, the historical test temperature difference, the historical test potential difference, and the historical test loop resistance;

[0039] The stress detection error prediction model is trained according to the training loss function to obtain a trained stress detection error prediction model.

[0040] For example, in a historical test cycle, in a preset test environment (e.g., creating a certain temperature difference and potential difference), a certain stress (i.e., historical applied stress) is applied to the experimental material that is the same as the guide beam material in the current construction, and the stress of the experimental material is detected by a stress sensor (i.e., historical detection stress), and the historical applied stress, historical detection stress, historical test temperature difference, historical test potential difference and historical test loop resistance in multiple historical detection cycles are obtained; the historical actual stress detection error is determined based on the historical detection stress; the direction of the current loop formed by the potential difference is detected by a digital multimeter (i.e., the historical test current loop direction), and the direction of the sensitive current of the sensor is detected by the series microammeter orientation method (i.e., the historical sensor sensitive current direction); when the historical test current loop direction and the historical sensor sensitive current direction are in the same direction, the electromagnetic deviation direction recognition result is 1, and when the historical test current loop direction and the historical sensor sensitive current direction are in opposite directions, the electromagnetic deviation direction recognition result is 0; the thermal expansion coefficient of the guide beam material and the sensor substrate are obtained. Thermal expansion coefficient; when the thermal expansion coefficient of the guide beam material is less than the thermal expansion coefficient of the sensor substrate, the temperature deviation direction identification result is 1; when the thermal expansion coefficient of the guide beam material is greater than or equal to the thermal expansion coefficient of the sensor substrate, the temperature deviation direction identification result is 0; according to the stress detection error prediction model, the electromagnetic deviation direction identification result, the temperature deviation direction identification result, the historical test temperature difference, the historical test potential difference and the historical test loop resistance are processed to generate the error between the historical applied stress and the historical detection stress predicted by the stress detection error prediction model, that is, the training stress detection error; according to the training stress detection error, the historical actual stress detection error, the electromagnetic deviation direction identification result, the temperature deviation direction identification result, the historical test temperature difference, the historical test potential difference and the historical test loop resistance, the training loss function of the stress detection error prediction model is determined; according to the training loss function, the stress detection error prediction model is trained, so that the stress detection error prediction model improves the accuracy of stress detection error prediction during the training process, and a trained stress detection error prediction model is obtained.

[0041] According to one embodiment of the present invention, the training loss function of the stress detection error prediction model is determined based on the training stress detection error, the historical actual stress detection error, the electromagnetic deviation direction identification result, the temperature deviation direction identification result, the historical test temperature difference, the historical test potential difference and the historical test loop resistance, including: determining the training loss function of the stress detection error prediction model according to formula (1): ,

[0042] (1)

[0043] Among them, if is a conditional function, is the training stress detection error of the k-th historical test cycle, is the historical actual stress detection error of the kth historical test cycle, is the temperature deviation direction identification result of the kth historical test cycle, , is the historical test temperature difference of the kth historical test cycle, is the preset temperature difference threshold, is the electromagnetic deviation direction identification result of the kth historical test cycle, , is the historical test potential difference of the kth historical test cycle, is the preset potential difference threshold, is the historical test loop resistance of the kth historical test cycle, is the preset loop resistance threshold, K is the number of historical test cycles, k≤K, and both k and K are positive integers.

[0044] According to one embodiment of the present invention, in formula (1), the conditional function The value of includes the following two cases, when satisfying When the condition is , it means that when the thermal expansion coefficient of the guide beam material is smaller than that of the sensor substrate, the sensor expansion caused by the temperature difference is greater than the structural expansion, resulting in a larger reading of the stress sensor and a positive drift. The value of the condition function is , The ratio of the historical test temperature difference of the kth historical test cycle to the preset temperature difference threshold. The larger the ratio, the greater the historical test temperature difference of the kth historical test cycle. The preset temperature difference threshold can be set to 1 degree Celsius. It means that the training stress detection error of the kth historical test cycle is positively correlated with the historical test temperature difference of the kth historical test cycle. The larger the temperature difference, the larger the reading drift, and the positive drift of the reading leads to a larger training stress detection error. When the condition is , it means that when the thermal expansion coefficient of the guide beam material is greater than or equal to the thermal expansion coefficient of the sensor substrate, the sensor expansion caused by the temperature difference is less than or equal to the structural expansion, resulting in a small reading of the stress sensor and a negative drift. The value of the condition function is , , It indicates that the training stress detection error of the kth historical test cycle is negatively correlated with the historical test temperature difference of the kth historical test cycle. The larger the temperature difference, the larger the reading drift, and the negative drift of the reading leads to a smaller training stress detection error. Among them, the smaller the training stress detection error, the larger the negative drift of the reading, and the smaller the value of the historical detection stress, which does not mean that the historical applied stress is closer to the historical detection stress.

[0045] According to one embodiment of the present invention, in formula (1), the conditional function The value of includes the following two cases, when satisfying When the condition is , it means that the direction of the historical test current loop is the same as the direction of the historical sensor sensitive current, and the interference voltage polarity is positively superimposed, resulting in a larger measured value. The value of the condition function is , , The ratio of the historical test potential difference of the kth historical test cycle to the preset potential difference threshold value. The larger the ratio is, the larger the historical test potential difference of the kth historical test cycle is. The preset potential difference threshold value can be set to 1V. It indicates that the training stress detection error of the k-th historical test cycle is positively correlated with the size of the historical test potential difference of the k-th historical test cycle. The larger the size of the historical test potential difference, the faster the drift speed and the larger the drift amplitude, resulting in a larger training stress detection error. The ratio of the historical test loop resistance of the kth historical test cycle to the preset loop resistance threshold. The larger the ratio, the larger the historical test loop resistance of the kth historical test cycle. The preset loop resistance threshold can be set to 1 ohm. It means that the training stress detection error of the kth historical test cycle is positively related to the historical test loop resistance of the kth historical test cycle. Under the same potential difference, the larger the historical test loop resistance, the larger the drift, resulting in a larger training stress detection error. When the condition is , it means that the direction of the historical test current loop and the direction of the historical sensor sensitive current are different, and the polarity of the interference voltage is reversed, resulting in a smaller measurement value. The value of the condition function is , , It indicates that the training stress detection error of the kth historical test cycle is negatively correlated with the size of the historical test potential difference of the kth historical test cycle. The larger the size of the historical test potential difference, the faster the drift speed and the larger the drift amplitude. However, since the direction of the historical test current loop and the direction of the historical sensor sensitive current are in opposite directions, the polarity of the interference voltage is reversed and the measured value is small, resulting in negative drift, which leads to a smaller training stress detection error. It indicates that the training stress detection error of the kth historical test cycle is negatively related to the historical test loop resistance of the kth historical test cycle. Under the same potential difference, the larger the historical test loop resistance, the larger the drift. However, since the direction of the historical test current loop and the direction of the historical sensor sensitive current are in opposite directions, the polarity of the interference voltage is reversed, the measured value is small, and a negative drift occurs, resulting in a smaller training stress detection error.

[0046] According to one embodiment of the present invention, is the relative error between the training stress detection error of the kth historical test cycle and the historical actual stress detection error, using and The training loss function is obtained by taking a weighted average of the relative errors between the training stress detection error and the historical actual stress detection error for the kth historical test cycle. During training, this training loss function is reduced, thereby reducing the error between the training stress detection error and the historical actual stress detection error. This improves the stress detection error prediction model's prediction accuracy, thereby increasing the accuracy of the stress detection error prediction model.

[0047] In this way, the training loss function of the stress detection error prediction model can be determined based on the training stress detection error, the historical actual stress detection error, the electromagnetic deviation direction identification result, the temperature deviation direction identification result, the historical test temperature difference, the historical test potential difference and the historical test loop resistance. During the calculation process, the influence of the above data on the training stress detection error can be determined based on the possible influence of the temperature difference, potential difference and loop resistance on the stress detection error. Based on the influence and the relative error of the training stress detection error, the training loss function is set to reduce the training loss function of the stress detection error prediction model during the training process, and to improve the accuracy of the stress detection error prediction model in a more targeted manner.

[0048] Figure 2 A schematic diagram of obtaining a stress detection error according to an embodiment of the present invention is exemplarily shown.

[0049] According to one embodiment of the present invention, step S2 includes: step S21, determining the temperature difference at a preset stress monitoring position based on the temperature data; step S22, determining the real-time potential difference and the real-time loop resistance based on the electromagnetic interference data; step S23, obtaining the real-time current loop direction and the real-time sensor sensitive current direction at multiple moments in the monitoring period; step S24, determining the real-time electromagnetic deviation direction identification result based on the real-time current loop direction and the real-time sensor sensitive current direction; step S25, processing the real-time electromagnetic deviation direction identification result, the temperature deviation direction identification result, the temperature difference, the real-time potential difference and the real-time loop resistance according to the trained stress detection error prediction model to obtain the stress detection error.

[0050] For example, the temperature difference at the preset stress monitoring position is determined based on the temperature data collected by the corresponding temperature sensors arranged closely next to the preset stress monitoring position and the corresponding temperature sensors arranged at positions with a longitudinal spacing of less than 3m at each preset stress monitoring position. For example, the temperature data of the temperature sensor located directly below the preset stress monitoring position is subtracted from the temperature data of the corresponding temperature sensor arranged closely next to the position; the real-time potential difference and the real-time loop resistance are detected in real time through a dual-channel DC millivoltmeter, a four-wire micro-ohmmeter and a wireless potential sensor; the real-time current loop direction is detected through a wireless phase current clamp, and the real-time sensor is detected through a three-terminal differential probe method. sensitive current direction; if the real-time current loop direction and the real-time sensor sensitive current direction are in the same direction, the electromagnetic deviation direction identification result is 1, otherwise, the electromagnetic deviation direction identification result is 0; since the test materials and stress sensors used in the detection cycle are the same as the materials and sensors used in the actual monitoring of the guide beam, the temperature deviation direction identification result in the monitoring cycle is the same as the temperature deviation direction identification result in the historical test cycle. According to the trained stress detection error prediction model, the real-time electromagnetic deviation direction identification result, temperature deviation direction identification result, temperature difference, real-time potential difference and real-time loop resistance are processed to obtain the stress detection error.

[0051] According to one embodiment of the present invention, in step S3, actual stress data is determined based on the stress detection error and the stress data.

[0052] For example, actual stress data is determined based on stress data plus stress detection error.

[0053] According to one embodiment of the present invention, in step S4, construction material information is acquired.

[0054] For example, obtain construction material information through construction documents (such as material lists and material certificates).

[0055] According to one embodiment of the present invention, in step S5, the allowable stress value is determined based on the construction material information.

[0056] Figure 3 A schematic diagram for exemplarily illustrating determination of an allowable stress value according to an embodiment of the present invention is shown.

[0057] According to one embodiment of the present invention, step S5 includes: step S51, determining the material yield strength according to the construction material information; step S52, determining the allowable stress value according to the material yield strength.

[0058] For example, the material yield strength of the guide beam is determined based on the strength of the construction material obtained from the material certificate; the allowable stress value is determined based on the ratio of the material yield strength and the safety factor, where the safety factor can be set to 1.67 according to the specifications.

[0059] According to one embodiment of the present invention, in step S6, a real-time stress monitoring result is determined based on the allowable stress value and the actual stress data.

[0060] For example, when the actual stress data at the first preset stress monitoring position is greater than 0.85 times the allowable stress value, it indicates that the danger level at the preset stress monitoring position is serious, and the real-time stress monitoring result at the preset stress monitoring position is 3. When the actual stress data at the first preset stress monitoring position is between 0.75-0.85 times the allowable stress value, it indicates that there is a high risk of hidden danger at the preset stress monitoring position, and the real-time stress monitoring result at the preset stress monitoring position is 2. When the actual stress data at the first preset stress monitoring position is between 0.65-0.75 times the allowable stress value, it indicates that there is a certain risk of hidden danger at the preset stress monitoring position, and the real-time stress monitoring result at the preset stress monitoring position is 1. When the actual stress data at the first preset stress monitoring position is less than 0.65 times the allowable stress value, it indicates that there is a small possibility of safety hazard at the preset stress monitoring position, and the real-time stress monitoring result at the preset stress monitoring position is 0.

[0061] According to one embodiment of the present invention, in step S7, a dynamic impact stress monitoring result is determined based on the actual stress data.

[0062] Figure 4 A schematic diagram of determining the overall impact stress anomaly coefficient according to an embodiment of the present invention is exemplarily shown.

[0063] According to one embodiment of the present invention, step S7 includes: step S71, obtaining the monitoring coordinates of each preset stress monitoring position in a preset coordinate system, wherein the preset coordinate system is a coordinate system established based on a preset origin within the range of the construction target; step S72, determining the actual stress mutation amount based on the actual stress data; step S73, determining the overall impact stress anomaly coefficient based on the actual stress mutation amount and the monitoring coordinates; step S74, determining the dynamic impact stress monitoring result based on the overall impact stress anomaly coefficient.

[0064] For example, a preset coordinate system is established by taking the projection of the centroid of the guide beam on the ground as the preset origin, taking the ground as the xoy plane of the coordinate system, and taking the vertical upward direction as the z axis of the coordinate system. The monitoring coordinates of each preset stress monitoring position in the preset coordinate system are obtained by setting wireless ranging sensors at three preset points in the preset coordinate system. The actual stress mutation amount at the preset stress monitoring position is determined based on the actual stress data at the current moment at each preset stress monitoring position minus the actual stress data at the previous adjacent moment. The stress mutation abnormality condition of the guide beam is evaluated based on the actual stress mutation amount and the monitoring coordinates, and the overall impact stress abnormality coefficient is determined. If the overall impact stress abnormality coefficient is greater than 0, it indicates that there is a position with stress mutation abnormality, and the dynamic impact stress monitoring result is 1. If the overall impact stress abnormality coefficient is equal to 0, it indicates that there is no position with stress mutation abnormality, and the dynamic impact stress monitoring result is 0.

[0065] According to one embodiment of the present invention, step S73 includes: step S731, determining multiple stress monitoring position combinations based on preset stress monitoring positions, wherein a single stress monitoring position combination includes multiple preset stress monitoring positions in the same area; step S732, determining the structural continuous identification results of each stress monitoring position combination; step S733, determining the impact stress difference threshold based on the structural continuous identification results; step S734, determining the adjacent monitoring positions of the preset stress monitoring positions in the stress monitoring position combination; step S735, determining the impact stress anomaly coefficient of each stress monitoring position combination based on the impact stress difference threshold, the actual stress mutation amount and the monitoring coordinates; step S736, determining the overall impact stress anomaly coefficient based on the impact stress anomaly coefficients of each stress monitoring position combination.

[0066] For example, all preset stress monitoring positions set in the same area (such as the root area of ​​the guide beam, the front cantilever end area of ​​the guide beam, the mid-span area of ​​the guide beam, the variable-section transition section and the end of the stiffener and the weld area) are determined as a stress monitoring position combination; the structural continuity identification results of each stress monitoring position combination are determined. For example, if the first stress monitoring position combination is located in a structural discontinuity area (such as the connection between the guide beam and the main beam, and the area where the cross-section changes sharply), the structural continuity identification result is 0, otherwise, the structural continuity identification result is 1; if the structural continuity identification result is 0, it means that it is located in a structural discontinuity area, the inherent stress concentration coefficient of the structural discontinuity area is high, and the corresponding impact stress The force difference threshold is set to 10%. If the structural continuity identification result is 1, it means that it is located in the structural continuity area, and the corresponding impact stress difference threshold can be set to 30%. In the stress monitoring position combination, the other preset stress monitoring position closest to a preset stress monitoring position is set as the adjacent monitoring position of the preset stress monitoring position. According to the impact stress difference threshold, the actual stress mutation amount and the monitoring coordinates, the stress mutation abnormality of each stress monitoring position combination is evaluated to determine the impact stress anomaly coefficient of each stress monitoring position combination. The impact stress anomaly coefficient of each stress monitoring position combination is summed to determine the overall impact stress anomaly coefficient.

[0067] According to one embodiment of the present invention, step S735 includes: determining the impact stress anomaly coefficient of the jth stress monitoring position combination at the i-th moment of the monitoring period according to formula (2): ,

[0068] (2)

[0069] Among them, max is the maximum value function, is the actual stress mutation at the e-th preset stress monitoring position in the j-th stress monitoring position combination at the i-th moment of the monitoring period, is the preset stress mutation threshold, is the actual stress mutation at the i-th moment of the monitoring period at the adjacent monitoring position of the e-th preset stress monitoring position in the j-th stress monitoring position combination, is the impact stress difference threshold of the jth stress monitoring position combination, is the monitoring coordinate of the e-th preset stress monitoring position in the j-th stress monitoring position combination at the i-th moment of the monitoring period, is the monitoring coordinate of the adjacent monitoring position at the i-th moment of the monitoring period of the e-th preset stress monitoring position in the j-th stress monitoring position combination, is the preset point distance threshold, E is the number of preset stress monitoring positions in the stress monitoring position combination, e≤E, and both e and E are positive integers.

[0070] According to one embodiment of the present invention, In order to obtain the maximum value of the actual stress mutation at the E preset stress monitoring positions in the j-th stress monitoring position combination, the above-mentioned maximum value-taking process can be used to determine the most abnormal stress mutation in the area corresponding to the j-th stress monitoring position combination.

[0071] According to one embodiment of the present invention, in formula (2), the conditional function The value of includes the following two cases, when satisfying When the condition is met, the maximum value of the actual stress mutation at the E preset stress monitoring positions in the j-th stress monitoring position combination is greater than or equal to the preset stress mutation threshold, indicating that the area corresponding to the j-th stress monitoring position combination has an abnormal stress mutation condition, wherein the preset stress mutation threshold It can be set to 20MPa, the value of the condition function is 1, if it does not meet When the condition is, the value of the condition function is the inner condition function value.

[0072] According to one embodiment of the present invention, It is the relative difference between the actual stress mutation at the e-th preset stress monitoring position in the j-th stress monitoring position combination and the adjacent monitoring position of the e-th preset stress monitoring position at the i-th moment of the monitoring period. The larger the ratio, the greater the difference in stress mutation between the e-th preset stress monitoring position and the adjacent monitoring position, and the greater the risk of local buckling, cracking or fatigue damage at this position. It represents the distance between the e-th preset stress monitoring position in the j-th stress monitoring position combination and its adjacent monitoring position in the monitoring cycle, It is the ratio of the distance between the e-th preset stress monitoring position in the j-th stress monitoring position combination and its adjacent monitoring position in the monitoring period to the preset point distance threshold. The larger the ratio, the farther the distance between the e-th preset stress monitoring position in the j-th stress monitoring position combination and its adjacent monitoring position. The larger the point distance, the greater the stress mutation difference gradient may exist at the e-th preset stress monitoring position in the j-th stress monitoring position combination. For example, the distance between the first preset stress monitoring position and its adjacent monitoring position is 1m, and the stress mutation difference is 5MPa. There may be a point with an impact stress difference of 4MPa at a distance of 10cm from the first preset stress monitoring position. The stress mutation difference gradient is larger and the danger is greater. Can be set to 1% of the guide beam length. It represents the difference in relative stress mutation between the e-th preset stress monitoring position and its adjacent monitoring positions in the j-th stress monitoring position combination after weighting by point distance. In order to obtain the maximum value of the relative stress mutation difference between the E preset stress monitoring positions in the jth stress monitoring position combination after point distance weighting and their adjacent monitoring positions, the above-mentioned maximum value-taking process can be used to determine the position with the greatest danger in the jth stress monitoring position combination.

[0073] According to one embodiment of the present invention, the inner condition function The value of includes the following two cases, when satisfying When the condition is met, it means that there is a position in the jth stress monitoring position combination with a large difference in stress mutation between the adjacent monitoring positions, which is more dangerous, and the value of the condition function is 1. When the condition is met, it means that there is no position in the j-th stress monitoring position combination with a large difference in stress mutation between the adjacent monitoring positions, the danger is small, and the value of the condition function is 0.

[0074] In this way, the impact stress anomaly coefficient of each stress monitoring position combination can be determined based on the impact stress difference threshold, the actual stress mutation amount and the monitoring coordinates. During the calculation process, the stress mutation anomaly condition of the stress monitoring position combination can be evaluated based on whether the stress mutation amount at the preset stress monitoring position itself is abnormal and whether the difference between the stress mutation amounts at the preset stress monitoring position and its adjacent monitoring positions is abnormal, thereby improving the comprehensiveness and accuracy of the impact stress anomaly coefficient.

[0075] According to an embodiment of the present invention, in step S8, a monitoring report is generated based on the real-time stress monitoring result and the dynamic impact stress monitoring result.

[0076] For example, when the real-time stress monitoring result at the preset stress monitoring position is 3, it indicates that the danger level at the preset stress monitoring position is serious, construction is immediately suspended, and structural review is started. When the real-time stress monitoring result at the preset stress monitoring position is 2, it indicates that there is a high risk of hidden danger at the preset stress monitoring position, and the pushing speed is reduced by 50%. When the real-time stress monitoring result at the preset stress monitoring position is 1, it indicates that there are certain risk of hidden danger at the preset stress monitoring position, and an early warning is generated. When the real-time stress monitoring result at the preset stress monitoring position is 0, the possibility of safety hazards at the preset stress monitoring position is small, and monitoring continues. When the dynamic impact stress monitoring result is 1, it indicates that there is a preset stress monitoring position with dynamic impact abnormality, and an early warning message for the corresponding position is generated. When the dynamic impact stress monitoring result is 0, monitoring continues.

[0077] According to the embodiment of the present invention, the stress monitoring method for the jacking construction guide beam can accurately analyze the impact of the construction environment on the detection error of the stress sensor and determine the actual stress data based on the detection error. Furthermore, based on the actual stress value, the stress abnormality and stress mutation abnormality during the jacking construction process are monitored to generate corresponding monitoring information, thereby improving the accuracy and comprehensiveness of the jacking construction guide beam stress monitoring. When determining the training loss function of the stress detection error prediction model, the training loss function of the stress detection error prediction model can be determined based on the training stress detection error, the historical actual stress detection error, the electromagnetic deviation direction identification result, the temperature deviation direction identification result, the historical test temperature difference, the historical test potential difference size, and the historical test loop resistance size. During the calculation process, the influence of the above data on the training stress detection error can be determined based on the possible influence of the temperature difference, potential difference size, and loop resistance size on the stress detection error. Based on this influence and the relative error of the training stress detection error, the training loss function is set to reduce the training loss function of the stress detection error prediction model during the training process, thereby more specifically improving the accuracy of the stress detection error prediction model. When determining the impact stress anomaly coefficient, the impact stress anomaly coefficient of each stress monitoring position combination is determined according to the impact stress difference threshold, the actual stress mutation amount and the monitoring coordinates. During the calculation process, the stress mutation anomaly condition of the stress monitoring position combination can be evaluated based on whether the stress mutation amount at the preset stress monitoring position itself is abnormal and whether the difference in stress mutation amount between the preset stress monitoring position and its adjacent monitoring positions is abnormal, thereby improving the comprehensiveness and accuracy of the impact stress anomaly coefficient.

[0078] Figure 5 A block diagram of a stress monitoring system for a guide beam in a jacking construction according to an embodiment of the present invention is exemplarily shown, wherein the system includes: a data acquisition module for determining stress data and construction environment data at multiple moments in a monitoring cycle by a combination of sensors arranged at preset positions and preset stress monitoring positions in the construction environment, wherein the construction environment data includes temperature data and electromagnetic interference data; a detection error module for processing the construction environment data according to a trained stress detection error prediction model to obtain a stress detection error; an actual stress module for determining actual stress data according to the stress detection error and the stress data; a material information module for acquiring construction material information; an allowable stress module for determining an allowable stress value according to the construction material information; a real-time monitoring module for determining a real-time stress monitoring result according to the allowable stress value and the actual stress data; an impact monitoring module for determining a dynamic impact stress monitoring result according to the actual stress data; and a monitoring report module for generating a monitoring report according to the real-time stress monitoring result and the dynamic impact stress monitoring result.

[0079] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0080] Those skilled in the art will appreciate that the embodiments of the present invention described above and shown in the accompanying drawings are intended to be illustrative only and are not intended to limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functional and structural principles of the present invention have been demonstrated and illustrated in the embodiments. Any variations or modifications may be made to the embodiments of the present invention without departing from the principles described.

Claims

1. A method for monitoring stress of a guide beam during jacking construction, characterized in that: include: At multiple moments in the monitoring cycle, stress data and construction environment data are determined by a combination of sensors set at preset positions and preset stress monitoring positions in the construction environment, wherein the construction environment data includes: temperature data and electromagnetic interference data; the construction environment data is processed according to a trained stress detection error prediction model to obtain a stress detection error; actual stress data is determined based on the stress detection error and the stress data; construction material information is obtained; an allowable stress value is determined based on the construction material information; a real-time stress monitoring result is determined based on the allowable stress value and the actual stress data; and a dynamic impact stress monitoring result is determined based on the actual stress data; Generate a monitoring report based on the real-time stress monitoring results and the dynamic impact stress monitoring results; the training steps of the stress detection error prediction model include: obtaining historical applied stress, historical detected stress, historical test temperature difference, historical test potential difference and historical test loop resistance in multiple historical test cycles; determining the historical actual stress detection error based on the historical applied stress and the historical detected stress; obtaining historical test current loop direction and historical sensor sensitive current direction in multiple historical test cycles; determining the electromagnetic deviation direction identification result based on the historical test current loop direction and the historical sensor sensitive current direction; obtaining the thermal expansion coefficient and The thermal expansion coefficient of the sensor substrate is determined; the temperature deviation direction identification result is determined according to the thermal expansion coefficient of the guide beam material and the thermal expansion coefficient of the sensor substrate; the electromagnetic deviation direction identification result, the temperature deviation direction identification result, the historical test temperature difference, the historical test potential difference and the historical test loop resistance are processed according to the stress detection error prediction model to determine the training stress detection error; the stress detection error is determined according to the training stress detection error, the historical actual stress detection error, the electromagnetic deviation direction identification result, the temperature deviation direction identification result, the historical test temperature difference, the historical test potential difference and the historical test loop resistance. A training loss function of a stress detection error prediction model; training the stress detection error prediction model according to the training loss function to obtain a trained stress detection error prediction model; processing the construction environment data according to the trained stress detection error prediction model to obtain a stress detection error, including: determining the temperature difference at a preset stress monitoring position according to the temperature data; determining the real-time potential difference and the real-time loop resistance according to the electromagnetic interference data; obtaining the real-time current loop direction and the real-time sensor sensitive current direction at multiple moments in the monitoring period; and determining a real-time electromagnetic deviation direction recognition result according to the real-time current loop direction and the real-time sensor sensitive current direction.The real-time electromagnetic deviation direction identification result, the temperature deviation direction identification result, the temperature difference, the real-time potential difference, and the real-time loop resistance are processed according to the trained stress detection error prediction model to obtain a stress detection error.

2. The method for monitoring stress of a guide beam during jacking construction according to claim 1, wherein: According to the training stress detection error, the historical actual stress detection error, the electromagnetic deviation direction identification result, the temperature deviation direction identification result, the historical test temperature difference, the historical test potential difference and the historical test loop resistance, the training loss function of the stress detection error prediction model is determined, including: according to the formula , determine the training loss function of the stress detection error prediction model , where if is a conditional function, is the training stress detection error of the k-th historical test cycle, is the historical actual stress detection error of the kth historical test cycle, is the temperature deviation direction identification result of the kth historical test cycle, , is the historical test temperature difference of the kth historical test cycle, is the preset temperature difference threshold, is the electromagnetic deviation direction identification result of the kth historical test cycle, , is the historical test potential difference of the kth historical test cycle, is the preset potential difference threshold, is the historical test loop resistance of the kth historical test cycle, is the preset loop resistance threshold, K is the number of historical test cycles, k≤K, and both k and K are positive integers.

3. The method for monitoring stress of guide beams in jacking construction according to claim 1, characterized in that: Determining the allowable stress value according to the construction material information includes: determining the material yield strength according to the construction material information; and determining the allowable stress value according to the material yield strength.

4. The method for monitoring stress of a guide beam in jacking construction according to claim 1, wherein: Determining a dynamic impact stress monitoring result based on the actual stress data includes: obtaining monitoring coordinates of each preset stress monitoring position in a preset coordinate system, wherein the preset coordinate system is a coordinate system established based on a preset origin within the range of the construction target; determining an actual stress mutation amount based on the actual stress data; determining an overall impact stress anomaly coefficient based on the actual stress mutation amount and the monitoring coordinates; and determining a dynamic impact stress monitoring result based on the overall impact stress anomaly coefficient.

5. The method for monitoring stress of guide beams in jacking construction according to claim 4, characterized in that: An overall impact stress anomaly coefficient is determined based on the actual stress mutation amount and the monitoring coordinates, including: determining a plurality of stress monitoring position combinations based on preset stress monitoring positions, wherein a single stress monitoring position combination includes a plurality of preset stress monitoring positions in the same area; determining a structural continuous identification result for each stress monitoring position combination; determining an impact stress difference threshold based on the structural continuous identification result; determining adjacent monitoring positions of the preset stress monitoring position in the stress monitoring position combination; determining an impact stress anomaly coefficient of each stress monitoring position combination based on the impact stress difference threshold, the actual stress mutation amount, and the monitoring coordinates; and determining an overall impact stress anomaly coefficient based on the impact stress anomaly coefficients of each stress monitoring position combination.

6. The method for monitoring stress of a guide beam in jacking construction according to claim 5, characterized in that: According to the impact stress difference threshold, the actual stress mutation amount and the monitoring coordinates, the impact stress anomaly coefficient of each stress monitoring position combination is determined, including: according to the formula , determine the impact stress anomaly coefficient of the jth stress monitoring position combination at the i-th moment of the monitoring period , where max is the maximum value function, is the actual stress mutation at the e-th preset stress monitoring position in the j-th stress monitoring position combination at the i-th moment of the monitoring period, is the preset stress mutation threshold, is the actual stress mutation at the i-th moment of the monitoring period at the adjacent monitoring position of the e-th preset stress monitoring position in the j-th stress monitoring position combination, is the impact stress difference threshold of the jth stress monitoring position combination, is the monitoring coordinate of the e-th preset stress monitoring position in the j-th stress monitoring position combination at the i-th moment of the monitoring period, is the monitoring coordinate of the adjacent monitoring position at the i-th moment of the monitoring period of the e-th preset stress monitoring position in the j-th stress monitoring position combination, is the preset point distance threshold, E is the number of preset stress monitoring positions in the stress monitoring position combination, e≤E, and both e and E are positive integers.

7. A system for monitoring stress of a guide beam in a jacking construction process for executing the method according to any one of claims 1 to 6, characterized in that: include: A data acquisition module is used to determine stress data and construction environment data at multiple moments in a monitoring cycle through a combination of sensors set at preset positions and preset stress monitoring positions in the construction environment, wherein the construction environment data includes: temperature data and electromagnetic interference data; a detection error module is used to process the construction environment data according to a trained stress detection error prediction model to obtain a stress detection error; an actual stress module is used to determine actual stress data based on the stress detection error and the stress data; a material information module is used to obtain construction material information; an allowable stress module is used to determine an allowable stress value based on the construction material information; a real-time monitoring module is used to determine a real-time stress monitoring result based on the allowable stress value and the actual stress data; an impact monitoring module is used to determine a dynamic impact stress monitoring result based on the actual stress data; and a monitoring report module is used to generate a monitoring report based on the real-time stress monitoring result and the dynamic impact stress monitoring result.

Images