A health monitoring system and method for bridge substructure

Abstract

The embodiments of this specification provide a health monitoring system and method for a bridge substructure, the system comprising a raw material monitoring module, a process monitoring module, a health regulation module, a remote communication module, a data synchronization module, an early warning module, and a processor; the raw material monitoring module is configured to collect raw material monitoring data; the process monitoring module comprises a sensor; the health regulation module is configured to perform health regulation; the remote communication module is configured to implement remote communication; the data synchronization module is configured to synchronously upload the transmitted communication data to a cloud platform; the early warning module is configured to control the alarm device at the corresponding position of the bridge substructure to issue an audible and visual alarm based on the early warning parameters; the processor is configured to: control the raw material storage and distribution parameters according to the raw material monitoring data; regulate the health parameters of the bridge substructure according to the raw material storage and distribution parameters and the process monitoring data; and determine the early warning parameters, and control the early warning module to issue an early warning based on the early warning parameters.

Description

Technical Field

[0001] This specification relates to the field of concrete operations, and in particular to a health monitoring system and method for a bridge substructure. Background Art

[0002] Bridge structures have a profound impact on traffic. Poor bridge structure quality can disrupt traffic flow and driving safety, leading to major accidents such as bridge collapse and threatening people's daily travel safety. Therefore, real-time monitoring of bridge structure status and appropriate maintenance measures are crucial to extend the service life of bridge structures.

[0003] To address the issue of monitoring the status of bridge structures, CN102979307B provides a temperature-controlled, crack-preventing construction method for concrete structures. This method generates a preset construction plan by monitoring the temperature of the concrete units and various parameters of the construction environment. However, this method does not continuously monitor the concrete units. During the maintenance process of the bridge structure, if the state of the concrete units changes due to environmental factors or other issues, the subsequent maintenance plan cannot be dynamically updated based on the changed state of the concrete units, and remedial measures cannot be taken in a timely manner. This may result in unstable maintenance quality of the concrete units, creating quality risks for the bridge substructure.

[0004] Therefore, it is urgent to propose a health monitoring system for bridge substructures to monitor the bridge substructures in real time, detect problems in a timely manner, and take remedial measures. Summary of the Invention

[0005] One or more embodiments of the present specification provide a health monitoring system for a bridge substructure, comprising a raw material monitoring module, a process monitoring module, a health control module, a remote communication module, a data synchronization module, an early warning module, and a processor; the raw material monitoring module is configured to collect raw material monitoring data corresponding to concrete of the bridge substructure; the process monitoring module includes a sensor, and the sensor is configured to monitor process monitoring data of the curing process of the concrete; the health control module is configured to perform health control on the bridge based on health parameters; the remote communication module is configured to implement remote communication among the raw material monitoring module, the process monitoring module, the health control module, the data synchronization module, the early warning module, and the processor; the data synchronization module is configured to synchronously upload communication data transmitted by the remote communication module to a cloud platform, so as to send the communication data to at least one user terminal based on the cloud platform; the early warning module is configured to control an alarm device at a corresponding position of the bridge substructure to issue an audible and visual alarm based on the early warning parameters; the processor is configured to: control raw material storage and distribution parameters according to the raw material monitoring data; regulate the health parameters of the bridge substructure according to the raw material storage and distribution parameters and the process monitoring data; and determine early warning parameters, and control the early warning module to issue an early warning based on the early warning parameters.

[0006] One of the embodiments of this specification provides a health monitoring method for a bridge substructure, which is executed based on a processor of the aforementioned bridge substructure health monitoring system, including: controlling raw material storage and distribution parameters based on raw material monitoring data; regulating the health parameters of the bridge substructure based on the raw material storage and distribution parameters and process monitoring data; and determining early warning parameters to achieve early warning based on the early warning parameters.

[0007] One or more embodiments of the present specification provide a health monitoring device for a bridge substructure, including a processor configured to execute a health monitoring method for a bridge substructure.

[0008] One or more embodiments of this specification provide a computer-readable storage medium that stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes a method for monitoring the health of a bridge substructure. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] This specification will be further described in the form of exemplary embodiments, which will be described in detail with reference to the accompanying drawings. These embodiments are not limiting, and in these embodiments, like numbers represent like structures, wherein:

[0010] Figure 1 is a schematic diagram of system modules of a health monitoring system for a bridge substructure according to some embodiments of this specification;

[0011] Figure 2 is an exemplary flow chart of a bridge substructure health monitoring method according to some embodiments of this specification;

[0012] Figure 3 is a schematic diagram of a sequence prediction model according to some embodiments of this specification;

[0013] Figure 4 This is a schematic diagram of determining warning parameters according to some embodiments of this specification. DETAILED DESCRIPTION

[0014] To more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly describes the drawings required for describing the embodiments. Obviously, the drawings described below are merely examples or embodiments of this specification. Those skilled in the art can apply this specification to other similar scenarios based on these drawings without inventive effort. Unless otherwise apparent from the context or otherwise noted, the same reference numerals in the figures represent the same structure or operation.

[0015] It should be understood that the terms "system," "device," "unit," and / or "module" used herein are a method for distinguishing different components, elements, parts, portions, or assemblies at different levels. However, if other terms can achieve the same purpose, the terms may be replaced by other expressions.

[0016] As used in this specification and claims, unless the context clearly indicates otherwise, the words "a," "an," "an," and / or "the" do not refer to the singular but also include the plural. Generally speaking, the terms "comprises" and "include" only indicate the inclusion of the steps and elements specifically identified, and these steps and elements do not constitute an exclusive list. A method or apparatus may also include other steps or elements.

[0017] Flowcharts are used throughout this specification to illustrate the operations performed by systems according to embodiments of this specification. It should be understood that preceding or following operations do not necessarily need to be performed in exact order. Instead, the steps may be processed in reverse order or simultaneously. Furthermore, other operations may be added to these processes, or one or more operations may be removed from these processes.

[0018] Figure 1 Schematic diagram of system modules of a health monitoring system for a bridge substructure according to some embodiments of this specification.

[0019] In some embodiments, the health monitoring system 100 for the bridge substructure may include a raw material monitoring module 110 , a process monitoring module 120 , a health control module 130 , a remote communication module 140 , a data synchronization module 150 , an early warning module 160 , and a processor 170 .

[0020] The raw material monitoring module is a module used to collect raw material monitoring data corresponding to the concrete of the bridge substructure.

[0021] The bridge substructure refers to the structure below the bridge, such as the different construction locations of the piers.

[0022] Raw material monitoring data refers to data obtained by monitoring concrete raw materials. For example, the temperature and humidity of concrete raw materials. Concrete raw materials may include sand, stone, water, etc. Concrete raw materials are stored in raw material storage and distribution equipment.

[0023] A raw material storage device is a device used to store raw materials. It can store concrete raw materials based on raw material storage parameters. These parameters can include temperature and humidity within the raw material storage. By regulating these parameters within the raw material storage device, the status of the concrete raw material storage space can be managed.

[0024] In some embodiments, raw material monitoring data may be acquired based on sensors, such as temperature sensors, humidity sensors, and the like.

[0025] The process monitoring module is a module for acquiring process monitoring data. In some embodiments, the process monitoring module may include a sensor.

[0026] The sensor may include a temperature sensor, a humidity sensor, etc. There may be multiple sensors. In some embodiments, the sensor may be used to monitor process monitoring data of the concrete curing process.

[0027] In some embodiments, the sensor's location can be adjusted based on the construction site's network environment. For example, when the sensor is located in an elevated work area, its placement should be adjusted as construction progresses. For example, when pouring concrete on a 60-meter-high bridge pier, the higher the pouring height, the higher the sensor's height should be adjusted. For example, the user adjusts the sensor's position every three meters of concrete.

[0028] Curing refers to the maintenance of the construction site after concrete pouring. This can include covering, watering, moistening, windproofing, and heat preservation to ensure that the newly poured concrete in the construction area hardens normally or accelerates its hardening and strength growth.

[0029] Process monitoring data refers to data collected from monitoring concrete products during the curing process. Concrete products are products cast from concrete raw materials, such as precast beams. Process monitoring data can include information such as concrete product temperature and ambient temperature and humidity.

[0030] The health regulation module is a module used to regulate the health of bridges based on health parameters.

[0031] Curing parameters refer to parameters related to the curing control of concrete products. For example, curing parameters include parameters used during bridge curing. In some embodiments, curing parameters may include parameters such as the amount of water applied during watering curing and the power of insulation or cooling equipment; and parameters such as the amount of steam applied during steam curing and the power of insulation or cooling equipment. In some embodiments, curing parameters may be preset based on prior knowledge.

[0032] Health regulation refers to the process of adjusting health parameters. Health regulation can include the direction and value of the adjustment of health parameters. The adjustment direction can include increasing or decreasing the parameter.

[0033] The remote communication module is a module used to realize remote communication between the raw material monitoring module, process monitoring module, health control module, data synchronization module, early warning module, and processor.

[0034] In some embodiments, the mode of remote communication can be adjusted based on the network environment of the construction site. For example, when the network at the construction site is poor and remote communication is difficult to achieve, the user can regularly go to the vicinity of the sensor and collect monitoring data obtained by the sensor through Bluetooth or other means. For another example, when the construction site achieves full network coverage, the user can adjust the monitoring points based on the construction progress. For example, when pouring a bridge pier with a total height of 60 meters, the user can adjust the monitoring point higher for every 3 meters poured to ensure smooth communication.

[0035] The data synchronization module is a module used to synchronously upload the communication data transmitted by the remote communication module to the cloud platform, so as to send the communication data to at least one user terminal based on the cloud platform.

[0036] In some embodiments, data synchronization can also be achieved based on sensors and user terminals. For example, users can use sensors with built-in traffic cards (e.g., NBIOT sensors), which can upload monitoring data to the cloud platform via the network. Users can view monitoring data through user terminals based on the cloud platform. For example, users can view monitoring data in real time through computer web pages, mobile applets, or mobile software, and can also configure warning parameters and receive or send warning-related information through user terminals.

[0037] Communication data refers to the data transmitted between modules. Communication data can include raw material monitoring data, process monitoring data, health parameters, and early warning parameters.

[0038] A cloud platform is a service that provides computing, networking, and storage capabilities based on hardware and software resources. In some embodiments, a cloud platform can be used to deliver communication data to at least one user terminal. Cloud platforms can include private clouds, public clouds, hybrid clouds, community clouds, distributed clouds, internal clouds, multi-layer clouds, and any combination thereof.

[0039] A user terminal refers to one or any combination of devices having input and / or output functions, such as a mobile device. In some embodiments, one or more users may use the user terminal, including users who directly use the service or other related users.

[0040] In some embodiments, the user terminal can receive communication data sent by the cloud platform.

[0041] The warning module is a module for controlling the alarm device at the corresponding bridge substructure location to generate an audible and visual alarm based on the warning parameters. In some embodiments, the warning module can be installed at each preset warning location. For detailed description of the warning location, please refer to Figure 4 and its related contents.

[0042] Warning parameters are parameters related to the warning issued by the alarm device. Warning parameters may include warning location, warning frequency and warning method. Warning methods may include separate sound warning, separate light effect warning and sound and light warning, etc. In some embodiments, the warning parameters can be determined based on historical data. The processor can analyze historical data and use the historical warning parameters with the highest historical frequency as the current warning parameters. For example, when construction time is during the day, sound warnings are often issued with a horn sound effect at a fixed frequency; when construction time is at night, due to low visibility, it is necessary to further improve the visibility of the warning, and red lights are often used to flash at a fixed frequency to warn users.

[0043] In some embodiments, the processor can be used to control raw material storage and distribution parameters based on raw material monitoring data; regulate the health parameters of the bridge substructure based on the raw material storage and distribution parameters and process monitoring data; and determine early warning parameters, and control the early warning module to issue early warnings based on the early warning parameters.

[0044] For detailed instructions on controlling raw material storage and distribution parameters, please refer to Figure 2 For detailed instructions on regulating health parameters, please refer to Figure 2 and Figure 3 For detailed instructions on early warning, please refer to Figure 4 and its related contents.

[0045] Some embodiments of this specification utilize multiple system modules to work together to monitor the maintenance process of the bridge substructure in real time, thereby promptly identifying problems that arise during the maintenance process and reminding users to take remedial measures to prevent maintenance failures and potential risks such as future bridge structure collapse.

[0046] It should be understood that Figure 1 The illustrated system and its modules may be implemented in various ways.

[0047] It should be noted that the above description of the health monitoring system and its modules for the bridge substructure is for convenience only and does not limit this specification to the scope of the embodiments. It is understandable that those skilled in the art, after understanding the principles of the system, may arbitrarily combine the modules or form a subsystem connected with other modules without deviating from the principles. In some embodiments, Figure 1The raw material monitoring module, process monitoring module, health control module, remote communication module, data synchronization module, early warning module, and processor disclosed herein can be different modules within a system, or a single module can implement the functions of two or more of the aforementioned modules. For example, each module can share a storage module, or each module can have its own storage module. Such variations are within the scope of protection of this specification.

[0048] Figure 2 FIG2 is an exemplary flow chart of a bridge substructure maintenance monitoring method according to some embodiments of the present disclosure. In some embodiments, process 200 may be executed by a processor of a bridge substructure maintenance monitoring system 100 .

[0049] Step 210: Control raw material storage and distribution parameters based on raw material monitoring data.

[0050] For detailed descriptions of raw material monitoring data and raw material storage and distribution parameters, please refer to Figure 1 and its related contents.

[0051] In some embodiments, the processor may determine raw material storage and distribution parameters based on raw material monitoring data and standard storage and distribution data. Standard storage and distribution data refers to preset standard temperatures and humidity levels for raw materials during storage. In response to a value of a certain indicator in the raw material monitoring data being higher than a corresponding indicator value in the standard storage and distribution data, the processor may adjust the value of the indicator in the raw material storage and distribution parameters downward. For example only, if the temperature monitored in the raw material monitoring data is higher than the temperature in the standard storage and distribution data, the temperature item in the raw material storage and distribution parameters may be adjusted downward.

[0052] Step 220: Adjust the curing parameters of the bridge substructure based on the raw material storage and distribution parameters and process monitoring data.

[0053] Detailed descriptions of process monitoring data, bridge substructure, and curing parameters can be found in Figure 1 and its related contents.

[0054] In some embodiments, the processor can regulate the curing parameters of the bridge substructure through vector matching based on the raw material storage and distribution parameters and process monitoring data.

[0055] In some embodiments, the processor may construct a feature vector based on current raw material storage and distribution parameters and current process monitoring data.

[0056] In some embodiments, the processor can cluster the historical raw material storage and distribution parameters, historical process monitoring data, and historical health parameters in the historical data with good final maintenance effects (for example, some evaluation indicators of the maintenance effects meet preset requirements) through a clustering algorithm, and construct multiple reference vectors based on the historical raw material storage and distribution parameters and historical process monitoring data corresponding to the multiple cluster centers formed by clustering, so that each reference vector corresponds to a historical health parameter. There are many types of clustering algorithms, for example, clustering algorithms can include K-Means clustering, density-based clustering method (DBSCAN), etc.

[0057] In some embodiments, the processor can calculate the similarity between the feature vector and at least one reference vector to determine the target health parameters. The target health parameters refer to the health parameters obtained after regulation. The similarity between the feature vector and the reference vector can be represented by the vector distance between the feature vector and the reference vector. The similarity is negatively correlated with the vector distance. The processor can use the reference vector with the smallest vector distance to the feature vector as the target vector, and the health parameters corresponding to the target vector as the target health parameters. The processor can adjust the current health parameters to the target health parameters to complete the regulation.

[0058] In some embodiments, the processor can estimate the matching degree of the preset health parameters based on the raw material storage and distribution parameters and process monitoring data; in response to the matching degree not meeting the preset matching conditions, the preset health parameters are adjusted.

[0059] Preset health parameters are preset health parameters that need to be executed. Preset health parameters can be determined based on historical data or prior knowledge. For example, the most commonly used health parameters in history can be used as preset health parameters.

[0060] The matching degree refers to the degree of adaptability between the preset curing parameters and the construction conditions. The construction conditions may include the construction time, construction location and construction progress.

[0061] In some embodiments, the processor can estimate the degree of match of the current preset health parameters based on the raw material storage and matching parameters and process monitoring data in various ways. For example, the processor can construct a feature vector based on the current raw material storage and matching parameters and process monitoring data, and construct a standard vector based on the preset standard raw material storage and matching parameters and preset standard process monitoring data corresponding to the preset health parameters, and determine the degree of match by calculating the cosine value between the feature vector and the standard vector. The degree of match is positively correlated with the cosine value between the feature vector and the standard vector.

[0062] The preset standard raw material storage and distribution parameters and preset standard process monitoring data corresponding to the preset health parameters can be determined based on historical data or historical experience. For example, the raw material storage and distribution parameters and process monitoring data corresponding to the historical use of the preset health parameters when the maintenance effect is good can be averaged and used as the preset standard raw material storage and distribution parameters and preset standard process monitoring data under the preset health parameters.

[0063] For example, the matching degree can be determined based on the following formula (1):

[0064] γ=k×cos(α i ,α0) (1)

[0065] Among them, γ is the matching degree of the preset health parameters, k is a preset parameter greater than 0, α i represents the eigenvector, and α0 represents the standard vector.

[0066] In some embodiments, the matching degree further includes a matching degree sequence of preset health parameters over a period of time in the future.

[0067] The matching degree sequence refers to a sequence of matching degrees corresponding to preset health parameters at multiple reference time points within a future period of time. In some embodiments, the length of the future period of time and the multiple reference time points within the future period of time can be manually preset.

[0068] In some embodiments, the processor may further divide the length of a future period of time into multiple sub-periods of equal duration, and use the end time of each sub-period as a reference time point. For example, when the future period of time is 16:30-17:00, the processor may divide the 30 minutes from 16:30-17:00 into three sub-periods of 16:30-16:40, 16:40-16:50, and 16:50-17:00 at intervals of 10 minutes, wherein 16:40, 16:50, and 17:00 are the end times of the three sub-periods, i.e., the three reference time points.

[0069] Preset matching conditions refer to conditions where the degree of matching meets the requirements. Preset matching conditions may include a degree of matching greater than a matching threshold. The matching threshold refers to the minimum matching threshold required for the current preset curing parameters and the current construction situation to be considered a match. The matching threshold can be manually preset.

[0070] In some embodiments, in response to the matching degree satisfying a preset matching condition, ie, the matching degree is greater than a matching threshold, the processor may not adjust the preset health parameters.

[0071] In some embodiments, the processor adjusts the preset health parameters in response to the matching degree not satisfying the preset matching condition, that is, the matching degree is not greater than the matching threshold.

[0072] In some embodiments, the processor can adjust the preset health parameters in a variety of ways. For example, the processor can send a reminder to the user terminal, notifying the user that the current preset health parameters are inappropriate, and prompting the user to re-enter the preset health parameters, thereby completing the adjustment of the preset health parameters based on the preset health parameters entered by the user.

[0073] In some embodiments, the processor can determine a target future time point based on a sequence of matching levels of preset health parameters over a period of time in the future, and the matching level of the target future time point does not meet the preset matching conditions; and adjust the preset health parameters in advance based on the first target future time point.

[0074] The target future time point refers to at least one time point in the future when the matching degree of the preset health parameters does not meet the preset matching conditions. In some embodiments, the processor can calculate the matching degree of the preset health parameters at each time point in the future (the specific calculation method is shown in the table). Figure 3 and its related instructions) and compares it with the preset matching conditions. The time point that does not meet the preset matching conditions is used as the target future time point. The first target future time point is the first time point in the future period that does not meet the preset matching conditions.

[0075] In some embodiments, the processor can send a reminder to the user terminal in advance based on the first target future time point, reminding the user to re-enter the preset health parameters, and control the health regulation module to perform maintenance according to the newly input preset health parameters before the first target future time point.

[0076] In some embodiments, the processor can also adjust the preset health parameters based on weather data, raw material storage parameters and process monitoring data. Figure 3 and related instructions.

[0077] Some embodiments of this specification make advance estimates and judgments on the matching degree of preset health parameters in the future period, and timely screen out preset health parameters that do not meet the requirements, so that staff can check and adjust in advance and make preparations for relevant maintenance and adjustment.

[0078] Some embodiments of this specification estimate the matching degree of preset curing parameters based on raw material storage and distribution parameters and process monitoring data, with reference to multiple sets of historical data. This can improve the accuracy of the estimated matching degree of preset curing parameters and ensure that the maintenance process of the bridge substructure can proceed stably.

[0079] Step 230: determining warning parameters to implement warning based on the warning parameters.

[0080] For detailed description of warning parameters, please refer to Figure 1 and its related contents.

[0081] In some embodiments, the processor may determine, based on the current construction stage and historical data, warning parameters corresponding to the current construction stage. For example, warning parameters for different construction stages may be preset in advance based on historical experience. The processor may then determine the warning parameters based on the current construction stage and issue a warning based on the warning parameters.

[0082] In some embodiments, the processor can also determine warning parameters based on process monitoring data and ideal data. For detailed instructions on this part, please refer to Figure 4 and its related contents.

[0083] In some embodiments, the processor may issue a warning to the user in response to the warning parameter. The warning method may include sound, light effect, etc.

[0084] Some embodiments of this specification regulate the curing parameters of the bridge substructure based on raw material storage and distribution parameters and process monitoring data, not only monitoring the status of the concrete product during the curing process, but also monitoring the status of the raw materials before pouring, ensuring that the quality of the concrete product obtained after each construction is the same, thereby achieving higher quality construction. In addition, some embodiments of this specification can dynamically regulate the curing parameters based on the real-time status of the concrete before and during curing, and can achieve adaptive adjustments for different construction conditions to ensure smooth construction. In addition, some embodiments of this specification can also achieve early warning based on early warning parameters, and promptly inform the user of possible faults, so that the problem can be remedied in a timely manner to ensure normal construction.

[0085] Figure 3 is a schematic diagram of a sequence prediction model according to some embodiments of this specification.

[0086] In some embodiments, the processor can estimate the matching degree sequence 350 for a period of time in the future based on weather data 310, raw material storage and distribution parameters 320 and process monitoring data 330 through a sequence prediction model 340; in response to the matching degree sequence not meeting the preset matching conditions, the preset health parameters are adjusted.

[0087] For detailed descriptions of raw material storage and matching parameters, process monitoring data, matching degree sequence for a period of time, preset matching conditions and preset health parameters, please refer to Figure 1 and Figure 2 and its related contents.

[0088] Weather data refers to data related to the weather. Weather data may include temperature, humidity, etc. for a period of time in the future. In some embodiments, weather data may be obtained based on a third-party platform. For example, the processor may obtain weather data through a weather forecast based on a network platform.

[0089] A sequence prediction model is a model used to estimate the degree of matching over a period of time in the future. The sequence prediction model can be a machine learning model, such as a deep neural network (DNN) model.

[0090] The input of the sequence prediction model may include process monitoring data, raw material storage and distribution parameters, and weather data; the output may include a matching degree sequence for a period of time in the future. For example, the matching degree sequence includes the matching degree of the preset health parameters at each monitoring time point in the future period of time.

[0091] In some embodiments, the input of the sequence prediction model also includes ideal data at multiple monitoring time points in the future.

[0092] The monitoring time point refers to the time point at which concrete-related data is monitored. Multiple monitoring time points can be included in the future. The monitoring time point can be based on manual presets. For example, the monitoring time point can be the same as the reference time point. For an explanation of the reference time point, see Figure 2 The corresponding content.

[0093] Ideal data refers to ideal parameters during the curing process. Ideal data may include ideal temperature and ideal humidity, among others. In some embodiments, the ideal data may be user-preset. The processor may obtain the user-preset ideal data via a cloud platform or a user terminal. For example, a user may set the ideal temperature during the curing process to 36°C.

[0094] Some embodiments of this specification add ideal data to the input of the sequence prediction model, taking into account the user's expectations of the maintenance process, to obtain a more humane and user-friendly match, thereby improving the user experience.

[0095] In some embodiments, the processor may train a sequence prediction model based on a large number of first samples with first labels. The first samples may include sample process monitoring data of sample concrete at a first historical time, sample raw material storage and distribution parameters, and sample weather data at a second historical time. The first labels may include a sequence of actual matching levels corresponding to the sample curing parameters corresponding to the first samples. The first samples and first labels may be acquired based on historical data. The first historical time may be before the second historical time.

[0096] In some embodiments, the actual matching degree sequence corresponding to the sample curing parameters may be determined based on the actual performance of the sample concrete in the second historical time.

[0097] In some embodiments, the processor may determine a mismatch sequence based on the first sample and the actual maintenance condition corresponding to the first sample. The mismatch sequence includes the mismatch degree of the preset health parameters at each monitoring time point in a future period of time.

[0098] In some embodiments, the processor may determine a matching degree sequence based on a mismatch degree sequence. For example, the processor may first determine a mismatch time point in the mismatch degree sequence, where the mismatch time point may refer to a time point in the mismatch degree sequence at which the mismatch degree is greater than a preset threshold. The processor may then use a monitoring time point other than the mismatch time point in the mismatch degree sequence as a matching time point, and set the matching degree value of the time point corresponding to the matching time point in the matching degree sequence to a value greater than or equal to the matching threshold. This may be determined based on the time interval between the matching time point and its most recent mismatch time point, such that the greater the interval, the greater the matching degree value. Furthermore, the matching degree value of the time point corresponding to the mismatch time point in the matching degree sequence may be set to a value less than the matching threshold and negatively correlated with the mismatch degree.

[0099] Mismatch refers to the degree of deviation between the actual environmental conditions and the preset curing parameters. In some embodiments, the processor can assess the mismatch based on the severity of problems encountered during the curing process and the degree of environmental deviation. Problems encountered during the curing process can include the number of blisters, collapses, collapses at blisters, and other types of problems.

[0100] Environmental deviation refers to the degree of deviation between the actual environmental parameters causing various issues and the preset environmental parameters. Actual environmental parameters can be obtained through field measurements, while preset environmental parameters can be determined based on preset health parameters. Due to factors such as weather and environmental factors, actual environmental parameters may differ from preset parameters to a certain extent. This difference is considered the environmental deviation. Actual environmental parameters may also vary between different pier construction sites.

[0101] The environmental deviation can be expressed as a percentage. The environmental deviation can include the environmental deviation of temperature and the environmental deviation of humidity, as well as the environmental deviation of both temperature and humidity (which can be collectively referred to as environmental deviation in this case). For example, the environmental deviation of both temperature and humidity (i.e., environmental deviation) can be the weighted sum or mean of the environmental deviation of temperature and humidity. For example, when bubbles are generated, the actual temperature at the bubble location is 18°C ​​and the preset temperature is 20°C. The actual temperature is offset by 10% compared to the preset temperature. It can be considered that the environmental deviation of the temperature corresponding to the bubble location is 10%.

[0102] Based on the problems that arise during the maintenance process, the processor can determine the environmental deviation and severity corresponding to the problem by querying the first preset table. The first preset table includes the correspondence between the problems that arise during the maintenance process and the environmental deviation and severity. The first preset table can be determined based on historical data or prior knowledge. The severity of the problem can be represented by a number from 0 to 10. As an example only, the first preset table may store the occurrence of a bubbling problem, the number of bubbles does not exceed 10, and the environmental deviation does not exceed 10%, and the corresponding severity of the bubbling problem is 2.

[0103] In some embodiments, the processor may determine the mismatch sequence in a variety of ways. For example, the processor may determine based on the following formula (2):

[0104] β=sum{θ×D i ×S i} (2)

[0105] Where β is the mismatch degree, θ is a preset parameter greater than 0, for example, θ can be 1; D i is the environmental deviation corresponding to problem i, S i is the severity of problem i.

[0106] For example, a temperature deviation at a certain point in the second historical time (e.g., the first monitoring time point) causes blistering, and the corresponding environmental deviation for the blistering is 10%, with a severity of 2. For example, assuming θ is 1, the mismatch corresponding to the first monitoring time point is (10% × 2) = 0.2.

[0107] At another historical point in the second historical time (e.g., the second monitoring time point), two problems occurred. The first problem was caused by a temperature and humidity offset, resulting in collapse at the bubbled area. The corresponding environmental deviation for this problem was 5%, with a severity of 9. The second problem was caused by a humidity offset, resulting in collapse at the non-bubbled area. The corresponding humidity environmental offset for this problem was 10%, with a severity of 8. The mismatch corresponding to the second monitoring time point is (5% × 9 + 10% × 8) = 1.25.

[0108] If the first and second monitoring time points are the first two monitoring time points in the second historical period, and the second historical period includes a total of five monitoring time points, then the mismatch sequence is {0.2, 1.25, 0, 0, 0}. If the preset threshold is 0.1, then the first and second monitoring time points are mismatched time points, and the third, fourth, and fifth monitoring time points are matched time points. Correspondingly, if the matching threshold is 0.6, then according to the aforementioned specific method for determining a matching sequence based on a mismatch sequence, it can be seen that in the first label, the actual matching sequence corresponding to the sample health parameters of the first sample can be {0.1, 0, 0.7, 0.8, 0.9}.

[0109] Among them, the conversion relationship between the matching degree value of the mismatching time point in the matching degree sequence and its mismatching degree in the mismatching degree sequence is based on a preset, for example, the matching degree value is negatively correlated with the mismatching degree; the conversion relationship between the matching degree value of the matching time point in the matching degree sequence and the time interval between the matching time point and its most recent mismatching time point is based on a preset, for example, the matching degree value is positively correlated with the time interval.

[0110] In some embodiments, the processor can adjust preset health parameters in response to the matching degree sequence not meeting the preset matching conditions. The matching degree sequence not meeting the preset matching conditions can mean that there are elements in the matching degree sequence that do not meet the preset matching conditions, such as when the matching degree at a monitoring time point is less than a matching threshold. In some embodiments, the processor can send the time point at which the preset matching conditions are not met to the user terminal, which can then re-enter the health parameters for the corresponding time point to adjust the preset health parameters.

[0111] In some embodiments, the processor may determine a comprehensive matching degree based on the matching degree sequence; and in response to the comprehensive matching degree not satisfying a preset matching condition, adjust the preset health parameters.

[0112] The comprehensive match degree is a parameter used to measure the matching degree sequence. A higher comprehensive match degree indicates a higher overall matching degree of the preset health parameters over the future period. In some embodiments, the comprehensive match degree can be determined based on the matching degree sequence. The comprehensive match degree can be positively correlated with each matching degree in the matching degree sequence.

[0113] In some embodiments, the comprehensive matching degree can be determined based on the following formula (3):

[0114]

[0115] in, is the comprehensive matching degree, n is the total number of monitoring time points in the matching degree sequence, γi is the matching degree at monitoring time point i in the matching degree sequence, and Δt refers to the time length corresponding to monitoring time point i in the matching degree sequence.

[0116] The time length corresponding to the monitoring time point can be determined based on the time point i, the current time point, and the fixed time length. As an example only, the time length corresponding to the monitoring time point can be determined based on the following formula (4):

[0117]

[0118] Among them, Δt refers to the time length corresponding to time point i, t i Refers to time point i, t0 refers to the current time point, Refers to a fixed time length. If the time length corresponding to time point i is less than 1, the processor sets the time length corresponding to time point i to 1. A fixed time length is the length of time corresponding to a preset trustworthy time period. This means that the predictions made during this time period are highly reliable, meaning that all predicted values ​​for this period are retained.

[0119] In some embodiments, the processor can compare the comprehensive matching degree with the preset matching condition, and in response to the comprehensive matching degree not meeting the preset matching condition, adjust the preset health parameters corresponding to the future period. Figure 2 and its related contents.

[0120] Since the longer the time, the more variables there are, and the lower the accuracy of the estimated matching degree, some embodiments of this specification further consider the credibility of the matching degree by considering the time length factor in the comprehensive matching degree. The longer the time, the lower the prediction accuracy may be, which is reflected in the comprehensive matching degree as the smaller the value, that is, the more likely it is that regulation is needed to ensure the accuracy of the matching degree in a future period of time and ensure the normal progress of construction.

[0121] Some embodiments of this specification predict the matching degree sequence based on weather data, raw material storage and distribution parameters, and process monitoring data using machine learning technology. This can be based on more and richer historical data, making the estimated matching degree sequence more accurate and better ensuring the smooth progress of the maintenance process.

[0122] Figure 4 This is a schematic diagram of determining warning parameters according to some embodiments of this specification.

[0123] In some embodiments, the processor can obtain ideal data 410 for multiple future monitoring time points from the cloud platform; determine the monitoring frequency 430 and the number of monitoring points 440 for process monitoring based on the interval 420 between the construction completion time of the bridge substructure and the current time; obtain process monitoring data 330 through the process monitoring module based on the monitoring frequency 430 and the number of monitoring points 440; and determine the early warning parameters 460 in response to the process monitoring data 330 and the ideal data 410 satisfying the first preset condition 450.

[0124] For detailed descriptions of the cloud platform, bridge substructure, process monitoring model, process monitoring data, and warning parameters, please refer to Figure 1 For details on monitoring time points and ideal data, please refer to Figure 3 and related instructions.

[0125] In some embodiments, the processor may obtain ideal data for multiple monitoring time points preset by the user through a cloud platform or a user terminal.

[0126] Monitoring frequency refers to the frequency and number of times monitoring data is acquired. The number of monitoring points refers to the number of monitoring points used to monitor data. There can be multiple monitoring points. The number of monitoring points refers to the number of monitoring points enabled during this monitoring session.

[0127] In some embodiments, the processor may determine the monitoring frequency and number of monitoring points by querying a second preset table based on the interval between the current construction completion time of the bridge substructure and the current time. The second preset table includes a correspondence between the interval between the construction completion time and the current time that has shown good monitoring results, the monitoring frequency, and the number of monitoring points in historical data. The second preset table may be determined based on historical data.

[0128] In some embodiments, the processor may determine the monitoring frequency and the number of monitoring points for process monitoring based on the first target future time point, the interval between the construction completion time of the bridge substructure and the current time.

[0129] For details on the target future time point, please refer to Figure 2 and related instructions.

[0130] The monitoring frequency and number of monitoring points are positively correlated with the interval between the construction completion time of the concrete product (e.g., bridge substructure) and the current time. For example, the monitoring frequency and number of monitoring points can be determined using the following formulas (5-1) and (5-2), respectively:

[0131]

[0132]

[0133] Among them, f is the monitoring frequency, f0 is the preset standard monitoring frequency, is the interval between the construction completion time of the bridge substructure and the current time, t g1 is the first target future time point, t0 is the current time point, Δt0 is the preset standard time interval, j is the number of monitoring points, and p is the preset coefficient.

[0134] In some embodiments, the processor can determine the estimated risk through a risk estimation model based on the first target future time point, the interval between the completion time of the bridge substructure construction and the current time, the candidate monitoring frequency and the number of candidate monitoring points; and determine the monitoring frequency and the number of monitoring points for process monitoring based on the estimated risk.

[0135] Candidate monitoring frequencies and candidate numbers of monitoring points refer to the monitoring frequencies and numbers of monitoring points that may be determined as the final monitoring frequencies and numbers of monitoring points. Candidate monitoring frequencies and candidate numbers of monitoring points can be determined based on historical data that have shown good monitoring results.

[0136] The risk prediction model is a model used to determine the estimated risk. The risk prediction model can be a machine learning model, such as a deep neural network (DNN) model.

[0137] Estimated risk refers to the combined risk of all potential problems that may arise with concrete products during the curing process, and can be expressed numerically. These problems can include blistering, collapse, and other potential problems with concrete products.

[0138] In some embodiments, the input of the risk prediction model may include the first target future time point, the interval between the completion time of the bridge substructure construction and the current time, the candidate monitoring frequency and the number of candidate monitoring points; the output may include the estimated risk corresponding to the candidate monitoring frequency and the number of candidate monitoring points.

[0139] In some embodiments, the processor may train a risk prediction model based on a second sample with a second label. The second sample may include the first target future time point of the sample, the interval between the completion time of the sample bridge substructure construction and the current time, the sample candidate monitoring frequency, and the number of sample candidate monitoring points. The second label may include the actual risk corresponding to the sample bridge substructure of the second sample. The second sample and the second label may be obtained based on historical data.

[0140] The actual risk can be determined by the severity of the actual problems in the sample bridge substructure. The method for determining the severity of the actual problems can be achieved by querying the first preset table, for example. Figure 3The processor can sum up the severity of all actual problems that occurred in the sample bridge substructure to determine the actual risk.

[0141] In some embodiments, the processor may use the candidate monitoring frequency and the candidate monitoring point quantity corresponding to the minimum estimated risk as the target monitoring frequency and the target monitoring point quantity.

[0142] Some embodiments of this specification estimate the risks of different problems occurring during the maintenance process to the overall maintenance process, and determine a more accurate monitoring frequency and number of monitoring points for process monitoring through machine learning. This can ensure the quality of process monitoring as much as possible, allowing users to promptly detect signs of problems, determine remedial measures, ensure maintenance quality, and improve maintenance efficiency.

[0143] Some embodiments of this specification determine the monitoring frequency and the number of monitoring points for process monitoring based on the interval between the first target future time point, the construction completion time of the bridge substructure and the current time. When the maintenance parameters do not match the environmental conditions, the monitoring frequency and the number of monitoring points for process monitoring can be adjusted in a timely manner so that the maintenance parameters can be adjusted as soon as possible to improve the matching degree and ensure maintenance efficiency.

[0144] In some embodiments, the processor may obtain process monitoring data through sensors at monitoring points through the process monitoring module according to a determined monitoring frequency and number of monitoring points.

[0145] In some embodiments, the processor may determine the early warning parameter in response to the process monitoring data and the ideal data satisfying a first preset condition.

[0146] The first preset condition is that the deviation between the process monitoring data and the ideal data is greater than a deviation threshold. The deviation threshold is the maximum value when the deviation between the process monitoring data and the ideal data is within an acceptable range.

[0147] In some embodiments, the deviation between the process monitoring data and the ideal data is negatively correlated with the cosine value of the process monitoring data and the ideal data. For example, the deviation between the process monitoring data and the ideal data can be the difference between 1 and the cosine value of the process monitoring data and the ideal data.

[0148] In some embodiments, in response to the process monitoring data and the ideal data satisfying the first preset condition, the processor may determine an early warning frequency based on the deviation between the process monitoring data and the ideal data. The early warning frequency is positively correlated with the deviation between the process monitoring data and the ideal data. For example, the early warning frequency may be determined based on the following formula (6):

[0149]

[0150] Among them, f wis the warning frequency, m is the preset parameter, f w0 is the preset warning frequency, which can be determined manually, e0 is the deviation threshold, e w Deviation between process monitoring data and ideal data.

[0151] In some embodiments, the processor may determine the warning method based on the warning frequency and a first warning threshold and a second warning threshold. The first warning threshold is the critical warning frequency for using light effect warning and sound warning. The second warning threshold is the critical warning frequency for using sound warning and using sound and light warning.

[0152] In response to the warning frequency being less than the first warning threshold, the processor may control the warning module to issue a light effect warning. For example, the light effect warning may include emitting a laser or performing continuous flashing.

[0153] In response to the warning frequency being not less than the first warning threshold and not greater than the second warning threshold, the processor may control the warning module to issue a sound warning. For example, the sound warning may include issuing a specific sound segment.

[0154] In response to the warning frequency being greater than the second warning threshold, the processor may control the warning module to issue an audible and visual warning. An audible and visual warning is a warning that occurs simultaneously with both an audible warning and a visual warning. For example, an audible and visual warning may include a flashing light and a sound clip.

[0155] In some embodiments, the processor may further determine an early warning location based on the process monitoring data. The processor may use the source location of the process monitoring data as the early warning location.

[0156] Some embodiments of this specification determine warning parameters based on the determined monitoring frequency and number of monitoring points, process monitoring data and ideal data. They can evaluate the gap between the data in the maintenance process and the user's expectations, and issue warnings to the user in a timely manner, reminding the user to take corresponding measures to adjust the health parameters, etc.; in addition, different warnings can be issued based on the degree of gap, showing different situations more intuitively, so that users can judge the current situation more quickly, make adjustments as soon as possible, and improve maintenance efficiency.

[0157] Some embodiments of this specification provide a health monitoring device for a bridge substructure, comprising at least one memory and at least one processor, wherein the memory is used to store computer instructions; and the processor is used to execute the above-mentioned health monitoring method for a bridge substructure.

[0158] Some embodiments of this specification provide a computer-readable storage medium, which stores computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the above-mentioned bridge substructure health monitoring method.

[0159] While the basic concepts have been described above, it will be apparent to those skilled in the art that the detailed disclosure is merely illustrative and does not limit this specification. Although not explicitly stated herein, various modifications, improvements, and revisions to this specification may be made by those skilled in the art. Such modifications, improvements, and revisions are suggested in this specification and remain within the spirit and scope of the exemplary embodiments of this specification.

[0160] This specification also uses specific terms to describe the embodiments of this specification. For example, "one embodiment," "an embodiment," and / or "some embodiments" refer to a feature, structure, or characteristic associated with at least one embodiment of this specification. Therefore, it should be emphasized and noted that references to "one embodiment," "an embodiment," or "an alternative embodiment" two or more times in different locations in this specification do not necessarily refer to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of this specification may be appropriately combined.

[0161] In addition, unless expressly stated in the claims, the order of the processing elements and sequences, the use of alphanumeric characters, or the use of other names described in this specification are not intended to limit the order of the processes and methods of this specification. Although the above disclosure discusses some of the invention embodiments currently considered useful through various examples, it should be understood that such details are for illustrative purposes only, and the appended claims are not limited to the disclosed embodiments. On the contrary, the claims are intended to cover all modifications and equivalent combinations that are consistent with the spirit and scope of the embodiments of this specification. For example, although the system components described above can be implemented by hardware devices, they can also be implemented only by software solutions, such as installing the described system on an existing server or mobile device.

[0162] Similarly, it should be noted that, in order to simplify the presentation of this specification and thus facilitate understanding of one or more embodiments of the invention, the foregoing descriptions of the embodiments of this specification sometimes combine multiple features into a single embodiment, figure, or description thereof. However, this disclosure method does not imply that the subject matter of this specification requires more features than those recited in the claims. In fact, an embodiment may have fewer features than all of the features of a single disclosed embodiment.

[0163] In some embodiments, numbers are used to describe the quantity of components and attributes. It should be understood that such numbers used in the description of the embodiments are modified by the modifiers "about", "approximately" or "substantially" in some examples. Unless otherwise stated, "about", "approximately" or "substantially" indicate that the numbers are allowed to vary by ±20%. Accordingly, in some embodiments, the numerical parameters used in the description and claims are approximate values, which may change according to the required characteristics of individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and adopt the general method of retaining digits. Although the numerical domains and parameters used to confirm the breadth of their range in some embodiments of this specification are approximate values, in specific embodiments, the settings of such numerical values ​​are as accurate as possible within the feasible range.

[0164] Each patent, patent application, patent application publication, and other materials, such as articles, books, specifications, publications, and documents, cited in this specification is hereby incorporated by reference in its entirety. This includes application history documents that are inconsistent with or conflict with the content of this specification, as well as documents (currently or subsequently attached to this specification) that limit the broadest scope of the claims of this specification. It should be noted that if the descriptions, definitions, and / or terminology used in the accompanying materials are inconsistent or conflicting with the content of this specification, the descriptions, definitions, and / or terminology used in this specification will control.

[0165] Finally, it should be understood that the embodiments described in this specification are intended only to illustrate the principles of the embodiments of this specification. Other variations may also fall within the scope of this specification. Therefore, by way of example and not limitation, alternative configurations of the embodiments of this specification may be considered consistent with the teachings of this specification. Accordingly, the embodiments of this specification are not limited to the embodiments explicitly described and illustrated in this specification.

Claims

1. A bridge substructure health monitoring system, comprising a raw material monitoring module, a process monitoring module, a health control module, a remote communication module, a data synchronization module, an early warning module, and a processor; The raw material monitoring module is configured to collect raw material monitoring data corresponding to the concrete of the bridge substructure; The process monitoring module includes a sensor configured to monitor process monitoring data of the curing process of the concrete; The curing control module is configured to perform curing control on the bridge based on curing parameters, wherein the curing parameters refer to parameters for curing and controlling the concrete product, and the curing parameters are preset based on prior knowledge; The remote communication module is configured to implement remote communication among the raw material monitoring module, the process monitoring module, the health regulation module, the data synchronization module, the early warning module, and the processor; The data synchronization module is configured to synchronously upload the communication data transmitted by the remote communication module to the cloud platform, so as to send the communication data to at least one user terminal based on the cloud platform; The warning module is configured to control the alarm device at the corresponding position of the bridge substructure to generate an audible and visual alarm based on the warning parameter; The processor is configured to: Controlling raw material storage and distribution parameters according to the raw material monitoring data; Regulating the curing parameters of the bridge substructure according to the raw material storage and distribution parameters and the process monitoring data; and Determine warning parameters, and control the warning module to issue a warning based on the warning parameters, wherein the warning parameters include a warning location, a warning frequency, and a warning method. Determining the warning parameters includes: Obtain ideal data at multiple future monitoring time points from the cloud platform; Based on a first target future time point, the interval between the completion time of the bridge substructure construction and the current time, the candidate monitoring frequency and the number of monitoring points, an estimated risk is determined by a risk estimation model, and the monitoring frequency and the number of monitoring points for process monitoring are determined based on the estimated risk; wherein the first target future time point is the first time point in a future period of time at which a preset health parameter does not meet a preset matching condition; Based on the monitoring frequency and the number of monitoring points, obtaining the process monitoring data through the process monitoring module; In response to the process monitoring data and the ideal data satisfying a first preset condition, determining the early warning parameter; The processor is further configured to: Based on the raw material storage and distribution parameters and the process monitoring data, the matching degree of the preset health parameters is estimated, and the matching degree includes a matching degree sequence of the preset health parameters over a period of time in the future; including: Based on weather data, the raw material storage and distribution parameters, ideal data at multiple monitoring time points in a future period, and the process monitoring data, a sequence prediction model is used to estimate the matching degree sequence in the future period; the sequence prediction model is a machine learning model; the sequence prediction model is obtained through model training, and the labels of the model training include an actual matching degree sequence, and the actual matching degree sequence is determined based on a mismatch degree sequence, where the mismatch degree refers to the degree of deviation between the actual environmental conditions and the preset health parameters; In response to the matching degree sequence not satisfying the preset matching condition, the preset health parameters are adjusted.

2. A bridge substructure health monitoring method, executed by a processor of the bridge substructure health monitoring system according to claim 1, comprising: Control raw material storage and distribution parameters based on raw material monitoring data; According to the raw material storage and distribution parameters and the process monitoring data, regulating the curing parameters of the bridge substructure, including: estimating the degree of matching of preset curing parameters according to the raw material storage and distribution parameters and the process monitoring data; in response to the degree of matching not satisfying a preset matching condition, regulating the preset curing parameters; wherein the curing regulation refers to the process of adjusting the curing parameters, including the adjustment direction and adjustment value of the curing parameters; the curing parameters refer to parameters used for curing and controlling the concrete product, and the curing parameters are preset based on prior knowledge; and Determining warning parameters to implement warning based on the warning parameters, wherein the warning parameters include warning location, warning frequency, and warning mode. Determining the warning parameters includes: Obtain ideal data at multiple future monitoring time points from the cloud platform; Based on a first target future time point, the interval between the completion time of the bridge substructure construction and the current time, the candidate monitoring frequency and the number of monitoring points, an estimated risk is determined by a risk estimation model, and the monitoring frequency and the number of monitoring points for process monitoring are determined based on the estimated risk; wherein the first target future time point is the first time point in a future period of time at which a preset health parameter does not meet a preset matching condition; Based on the monitoring frequency and the number of monitoring points, obtaining the process monitoring data through the process monitoring module; In response to the process monitoring data and the ideal data satisfying a first preset condition, determining the early warning parameter; Based on the raw material storage and distribution parameters and the process monitoring data, the matching degree of the preset health parameters is estimated, and the matching degree includes a matching degree sequence of the preset health parameters over a period of time in the future; including: Based on weather data, the raw material storage and distribution parameters, ideal data at multiple monitoring time points in a future period, and the process monitoring data, a sequence prediction model is used to estimate the matching degree sequence in the future period; the sequence prediction model is a machine learning model; the sequence is obtained through model training, and the labels of the model training include an actual matching degree sequence, and the actual matching degree sequence is determined based on a mismatch degree sequence, where the mismatch degree refers to the degree of deviation between the actual environmental conditions and the preset health parameters; In response to the matching degree sequence not satisfying the preset matching condition, the preset health parameters are adjusted.

3. A health monitoring device for a bridge substructure, comprising a processor, characterized in that: The processor is used to execute the health monitoring method for a bridge substructure as claimed in claim 2.

4. A computer-readable storage medium storing computer instructions. When a computer reads the computer instructions in the storage medium, the computer executes the health monitoring method for a bridge substructure according to claim 2.

Images