CN111222189A - Efficient bridge structure health early warning control system and method - Google Patents
Efficient bridge structure health early warning control system and method Download PDFInfo
- Publication number
- CN111222189A CN111222189A CN201911406973.4A CN201911406973A CN111222189A CN 111222189 A CN111222189 A CN 111222189A CN 201911406973 A CN201911406973 A CN 201911406973A CN 111222189 A CN111222189 A CN 111222189A
- Authority
- CN
- China
- Prior art keywords
- data
- module
- bridge
- image
- register
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000036541 health Effects 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000000605 extraction Methods 0.000 claims abstract description 73
- 238000003745 diagnosis Methods 0.000 claims abstract description 47
- 238000011156 evaluation Methods 0.000 claims abstract description 32
- 238000013135 deep learning Methods 0.000 claims abstract description 29
- 238000012423 maintenance Methods 0.000 claims abstract description 19
- 238000003062 neural network model Methods 0.000 claims abstract description 8
- 230000015556 catabolic process Effects 0.000 claims description 15
- 238000006731 degradation reaction Methods 0.000 claims description 15
- 238000005303 weighing Methods 0.000 claims description 15
- 238000004140 cleaning Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 12
- 238000012545 processing Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 230000006399 behavior Effects 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 9
- 238000013461 design Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 9
- 238000010586 diagram Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 7
- 238000013524 data verification Methods 0.000 claims description 6
- 230000003862 health status Effects 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 239000008186 active pharmaceutical agent Substances 0.000 claims description 3
- 230000003321 amplification Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000003672 processing method Methods 0.000 claims description 3
- 230000009467 reduction Effects 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000004088 simulation Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000012795 verification Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 claims description 3
- 238000007418 data mining Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 abstract description 2
- 238000000105 evaporative light scattering detection Methods 0.000 abstract description 2
- 238000007689 inspection Methods 0.000 abstract description 2
- 230000007774 longterm Effects 0.000 abstract description 2
- 238000007726 management method Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
Images
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention belongs to the technical field of bridge structure health early warning, and discloses a high-efficiency bridge structure health early warning control system and method, wherein the high-efficiency bridge structure health early warning control system comprises the following components: the bridge image acquisition module, the bearing data acquisition module, the main control module, the image enhancement module, the feature extraction module, the crack identification module, the health diagnosis module, the performance evaluation module, the early warning module and the display module. According to the invention, the deep learning network is established through the health diagnosis module, so that the health states of various bridge structures can be rapidly and effectively diagnosed and checked; meanwhile, the performance evaluation module integrates a data mining technology, effectively and fully utilizes mass detection data accumulated in the long-term bridge inspection work, establishes a neural network model, converts the extracted data into valuable knowledge in the field of bridge management and maintenance, and realizes accurate evaluation prediction and management and maintenance guidance of the network-level bridge structure performance.
Description
Technical Field
The invention belongs to the technical field of bridge structure health early warning, and particularly relates to a high-efficiency bridge structure health early warning control system and method.
Background
The bridge is generally a structure which is erected on rivers, lakes and seas and allows vehicles, pedestrians and the like to smoothly pass through. In order to adapt to the modern high-speed developed traffic industry, bridges are also extended to be constructed to span mountain stream, unfavorable geology or meet other traffic needs, so that the buildings are convenient to pass. The bridge generally comprises an upper structure, a lower structure, a support and an auxiliary structure, wherein the upper structure is also called a bridge span structure and is a main structure for spanning obstacles; the lower structure comprises a bridge abutment, a bridge pier and a foundation; the support is a force transmission device arranged at the supporting positions of the bridge span structure and the bridge pier or the bridge abutment; the auxiliary structures refer to bridge end butt straps, tapered revetments, diversion works and the like. However, the existing efficient bridge structure health early warning control system cannot diagnose the bridge health quickly and effectively; meanwhile, the performance evaluation of the bridge structure is inaccurate.
In summary, the problems of the prior art are as follows: the existing high-efficiency bridge structure health early warning control system cannot quickly and effectively diagnose the health of the bridge; meanwhile, the performance evaluation of the bridge structure is inaccurate.
Disclosure of Invention
Aiming at the problems in the prior art, the invention provides a high-efficiency bridge structure health early warning control system and method.
The invention is realized in such a way, and provides an efficient bridge structure health early warning control method, which comprises the following steps:
firstly, acquiring bridge structure image data by using a camera through a bridge image acquisition module, and acquiring bridge structure weighing data by using a weighing detector through a bearing data acquisition module;
secondly, the main control module utilizes an image enhancement algorithm to enhance the acquired bridge image through an image enhancement module, and utilizes an extraction program to extract characteristic elements of the acquired bridge image through a characteristic extraction module; the image enhancement module enhancement method comprises the following steps: (1) the input interface unit transmits the received video signal collected by the camera to a video decoding unit electrically connected with the input interface unit, and the video decoding unit performs analog-to-digital conversion on the received video signal and then transmits the video signal to the image enhancement processing unit; (2) the image data processed by the image enhancement processing unit is transmitted to the video coding unit, the video coding unit carries out coding processing on the image data, then the image data is amplified by the video amplification unit, and finally the enhanced video signal is output by the output interface unit; the extraction method of the feature extraction module comprises the following steps: (1) when traversal starts, data in the feature extraction register array is invalid, and the data at the upper left of the image must be input into the feature extraction register array for feature extraction; because the feature extraction register array has no interface with the periphery, data is input through the lower buffer area; (2) inputting data into a lower buffer area, and then carrying out a downward movement operation, wherein the data is moved into two rows at the lowest part of the feature extraction register array and the right buffer area; (3) repeating the step (2) for 5 times in total until all the data at the upper left of the image are moved into the feature extraction register array; (4) performing image feature extraction once, and storing image data of two lines below the image into a lower buffer area simultaneously because the next operation is also a downward movement operation, and performing downward movement operation once after the feature extraction is completed; (5) repeating the step (4) until the image has no data below; at the moment, a right shift operation is carried out, and because the right buffer area continuously updates data during multiple downward shift operations, the right buffer area stores effective data at the moment, the right shift operation is directly carried out, and the data is not required to be written into the right buffer area; (6) after one right shift operation is carried out, the next operation is upward shift, the upper buffer area starts to work, and image data of two lines above the image are stored in the upper buffer area while the features are extracted; (7) carrying out image feature extraction after carrying out primary upward moving operation; meanwhile, the next operation is also an upward movement operation, so that the data of two lines above the image are stored in an upper buffer area; (8) repeating the step (7) until the image has no data above; at the moment, a right shift operation is carried out, and because the right buffer area continuously updates data during multiple times of shift operations, the right buffer area stores effective data at the moment, the right shift operation is directly carried out, and the data is not required to be written into the right buffer area; (9) repeating the previous steps (4) to (8) until the whole target image is traversed;
thirdly, identifying crack information of the extracted characteristic elements by using an identification program through a crack identification module, and diagnosing the health of the bridge structure by using a diagnostic program through a health diagnosis module;
fourthly, evaluating the performance of the bridge structure by a performance evaluation module by using an evaluation program;
and fifthly, timely alarming and informing according to the abnormal diagnosis result by using an alarm through an early warning module, and displaying the acquired bridge structure diagram, crack information, diagnosis result and evaluation result by using a display through a display module.
Further, the upward moving operation of the feature extraction module of the efficient bridge structure health early warning control method specifically includes:
(1) except the registers of the X rows below the feature extraction register array, other registers write the stored data into the register with the distance X from the register below;
(2) the register of the upper buffer area writes the stored data into a characteristic extraction register array connected with the register;
(3) the data stored by other registers except the registers of the X row at the lower part in the right buffer area are written into the register with the distance of X from the register at the lower part;
(4) the register in the upper buffer writes the stored data into the right buffer connected thereto.
Further, the downward movement operation of the feature extraction module of the efficient bridge structure health early warning control method specifically includes:
(1) except the registers of the upper X rows in the characteristic extraction register array, other registers write the stored data into the register with the upper distance of X from the register;
(2) the register in the lower buffer area writes the stored data into the register of the feature extraction register array connected with the register and the register of the right buffer area;
(3) the other registers in the right buffer, except the upper X rows of registers, write the stored data into the register that is X above the register.
Further, the right shift operation of the feature extraction module of the efficient bridge structure health early warning control method specifically includes:
(1) except the left Y-column register in the feature extraction register array, other registers write the stored data into a register with the distance of Y from the register on the left;
(2) the register in the right buffer writes the stored data into a register in the feature extraction register array connected thereto.
Further, the diagnosis method of the health diagnosis module of the efficient bridge structure health early warning control method is as follows:
(1) building a bridge data cloud server, collecting data of a plurality of bridges in four stages of design, construction, maintenance and monitoring through a monitoring terminal, sorting and sorting the data according to different data properties, and then performing data fusion by adopting a big data processing method to form various input data required by a deep learning network; the bridge comprises bridges of a certain type, different sizes and different regions, and contains the conditions of a normal state and various degradation states;
(2) drawing a visual graph by the fused bridge data for cloud storage;
(3) establishing an accurate finite element model of the bridge structure by using data in a design stage and a construction stage, respectively simulating the conditions of a normal state and various degradation states of the bridge structure, and storing related data as training input of a deep learning network;
(4) constructing a five-layer deep learning network DN, wherein a first layer SS adopts a sparse automatic encoder, a second layer and a third layer adopt a general automatic encoder, a fourth layer DS adopts a noise reduction automatic encoder, a fifth layer SVM adopts a support vector machine, input data of the fifth layer SVM is A [ i ] (i is 1,2, …, n), and the input data formed in the first step can be any matrix; the output data is S [ j ] (j ═ 1,2, …, m), which represents the specific health status of each region of the bridge structure and the health status of the whole bridge structure, and may be any matrix;
(5) the method comprises the steps of characteristic learning, namely inputting data of two stages of design and construction into a deep learning network DN, and acquiring the characteristics of various normal parameters of the bridge structure by adopting unsupervised training; inputting part of data of the maintenance stage and the monitoring stage and data of finite element simulation into the network, adopting supervised training to obtain the characteristics of various parameters of the structure in various degradation states, and finely adjusting the fifth layer of the deep learning network;
(6) data verification, namely inputting the other part of data in the monitoring stage into a network for data verification, and further optimizing the whole deep learning network according to a verification result to finally form a deep learning network which can be universally used for health diagnosis of various bridge structures;
(7) and D, performing structural health diagnosis on the bridge, preprocessing various data of the bridge by adopting a method similar to the step one for any bridge according to the deep learning network which is formed in the step five and can be used for structural health diagnosis, and inputting the preprocessed data into the successfully trained deep learning network for diagnosis after the formed data can be input, so that whether the structural health state of the bridge is normal or in which level of degradation state is accurately obtained.
Further, the performance evaluation module evaluation method of the efficient bridge structure health early warning control method is as follows:
1) collecting the detection report of each bridge in the past year, establishing a report and extracting the technical condition score, the bridge age, the structure type, the traffic volume and the maintenance behavior information of each year;
2) correcting and cleaning the acquired data, removing redundancy, and constructing a relational database through a database program;
3) training and checking the established neural network based on data in the relational database to obtain a neural network model for predicting structural performance degradation;
4) and acquiring the structure type and annual traffic volume of each bridge to be predicted by using the trained neural network model, and predicting the performance change trend of the whole structure and local components of the bridge in the regional road network.
Further, the step 1) specifically comprises:
acquiring a detection report of each bridge of a road network in a target area in the past year;
extracting technical condition score, bridge age, structure type, traffic volume and maintenance behavior information in each detection report;
cleaning the extracted data according to a preset data cleaning rule to remove invalid data;
and screening the bridge age, the structure type, the traffic volume, the maintenance behavior information and the annual technical condition scoring field of the bridge according to the structure type to be used as an attribute set of the relational database, and processing and storing the part subjected to data cleaning into the relational database.
Another object of the present invention is to provide an efficient bridge structure health warning control system for implementing the efficient bridge structure health warning control method, wherein the efficient bridge structure health warning control system includes:
the bridge image acquisition module is connected with the main control module and is used for acquiring bridge structure image data through the camera;
the load-bearing data acquisition module is connected with the main control module and is used for acquiring the weighing data of the bridge structure through the weighing detector;
the main control module is connected with the bridge image acquisition module, the bearing data acquisition module, the image enhancement module, the feature extraction module, the crack identification module, the health diagnosis module, the performance evaluation module, the early warning module and the display module and is used for controlling each module to normally work through the main control computer;
the image enhancement module is connected with the main control module and is used for enhancing the acquired bridge image through an image enhancement algorithm;
the characteristic extraction module is connected with the main control module and used for extracting characteristic elements of the acquired bridge image through an extraction program;
the crack identification module is connected with the main control module and used for identifying crack information of the extracted characteristic elements through an identification program;
the health diagnosis module is connected with the main control module and is used for diagnosing the health of the bridge structure through a diagnosis program;
the performance evaluation module is connected with the main control module and used for evaluating the performance of the bridge structure through an evaluation program;
the early warning module is connected with the main control module and used for carrying out alarm notification in time according to the abnormal diagnosis result through the alarm;
and the display module is connected with the main control module and used for displaying the acquired bridge structure diagram, crack information, diagnosis results and evaluation results through a display.
The invention has the advantages and positive effects that: according to the invention, the deep learning network is established through the health diagnosis module, so that the health states of various bridge structures can be rapidly and effectively diagnosed and checked; meanwhile, the performance evaluation module integrates a data mining technology, effectively and fully utilizes mass detection data accumulated in the long-term bridge inspection work, establishes a neural network model, converts the extracted data into valuable knowledge in the field of bridge management and maintenance, and realizes accurate evaluation prediction and management and maintenance guidance of the network-level bridge structure performance.
Drawings
Fig. 1 is a schematic structural diagram of an efficient bridge structure health early warning control system provided in an embodiment of the present invention;
in the figure: 1. a bridge image acquisition module; 2. a load-bearing data acquisition module; 3. a main control module; 4. an image enhancement module; 5. a feature extraction module; 6. a crack identification module; 7. a health diagnosis module; 8. a performance evaluation module; 9. an early warning module; 10. and a display module.
Fig. 2 is a flowchart of an efficient bridge structure health early warning control method provided by the embodiment of the invention.
Detailed Description
In order to further understand the contents, features and effects of the present invention, the following embodiments are illustrated and described in detail with reference to the accompanying drawings.
The structure of the present invention will be described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the efficient bridge structure health early warning control system provided by the embodiment of the present invention includes: the system comprises a bridge image acquisition module 1, a bearing data acquisition module 2, a main control module 3, an image enhancement module 4, a feature extraction module 5, a crack identification module 6, a health diagnosis module 7, a performance evaluation module 8, an early warning module 9 and a display module 10.
The bridge image acquisition module 1 is connected with the main control module 3 and is used for acquiring bridge structure image data through a camera;
the bearing data acquisition module 2 is connected with the main control module 3 and is used for acquiring the weighing data of the bridge structure through the weighing detector;
the main control module 3 is connected with the bridge image acquisition module 1, the bearing data acquisition module 2, the image enhancement module 4, the feature extraction module 5, the crack identification module 6, the health diagnosis module 7, the performance evaluation module 8, the early warning module 9 and the display module 10 and is used for controlling each module to normally work through a main control machine;
the image enhancement module 4 is connected with the main control module 3 and is used for enhancing the acquired bridge image through an image enhancement algorithm;
the characteristic extraction module 5 is connected with the main control module 3 and used for extracting characteristic elements of the acquired bridge image through an extraction program;
the crack identification module 6 is connected with the main control module 3 and used for identifying crack information of the extracted characteristic elements through an identification program;
the health diagnosis module 7 is connected with the main control module 3 and is used for diagnosing the health of the bridge structure through a diagnosis program;
the performance evaluation module 8 is connected with the main control module 3 and used for evaluating the performance of the bridge structure through an evaluation program;
the early warning module 9 is connected with the main control module 3 and is used for carrying out alarm notification in time according to the abnormal diagnosis result through an alarm;
and the display module 10 is connected with the main control module 3 and used for displaying the acquired bridge structure diagram, crack information, diagnosis results and evaluation results through a display.
The image enhancement module 4 provided by the invention has the following enhancement method:
(1) the input interface unit transmits the received video signal collected by the camera to a video decoding unit electrically connected with the input interface unit, and the video decoding unit performs analog-to-digital conversion on the received video signal and then transmits the video signal to the image enhancement processing unit;
(2) the image data processed by the image enhancement processing unit is transmitted to the video coding unit, the video coding unit performs coding processing on the image data, then the image data is amplified by the video amplification unit, and finally the enhanced video signal is output by the output interface unit.
The feature extraction module 5 provided by the invention has the following extraction method:
(1) when traversal starts, data in the feature extraction register array is invalid, and the data at the upper left of the image must be input into the feature extraction register array for feature extraction; because the feature extraction register array has no interface with the periphery, data is input through the lower buffer area;
(2) inputting data into a lower buffer area, and then carrying out a downward movement operation, wherein the data is moved into two rows at the lowest part of the feature extraction register array and the right buffer area;
(3) repeating the step (2) for 5 times in total until all the data at the upper left of the image are moved into the feature extraction register array;
(4) performing image feature extraction once, and storing image data of two lines below the image into a lower buffer area simultaneously because the next operation is also a downward movement operation, and performing downward movement operation once after the feature extraction is completed;
(5) repeating the step (4) until the image has no data below; at the moment, a right shift operation is carried out, and because the right buffer area continuously updates data during multiple downward shift operations, the right buffer area stores effective data at the moment, the right shift operation is directly carried out, and the data is not required to be written into the right buffer area;
(6) after one right shift operation is carried out, the next operation is upward shift, the upper buffer area starts to work, and image data of two lines above the image are stored in the upper buffer area while the features are extracted;
(7) carrying out image feature extraction after carrying out primary upward moving operation; meanwhile, the next operation is also an upward movement operation, so that the data of two lines above the image are stored in an upper buffer area;
(8) repeating the step (7) until the image has no data above; at the moment, a right shift operation is carried out, and because the right buffer area continuously updates data during multiple times of shift operations, the right buffer area stores effective data at the moment, the right shift operation is directly carried out, and the data is not required to be written into the right buffer area;
(9) and (5) repeating the previous steps (4) to (8) until the whole target image is traversed.
The upward moving operation of the feature extraction module 5 provided by the invention specifically includes:
(1) except the registers of the X rows below the feature extraction register array, other registers write the stored data into the register with the distance X from the register below;
(2) the register of the upper buffer area writes the stored data into a characteristic extraction register array connected with the register;
(3) the data stored by other registers except the registers of the X row at the lower part in the right buffer area are written into the register with the distance of X from the register at the lower part;
(4) the register in the upper buffer writes the stored data into the right buffer connected thereto.
The downward moving operation of the feature extraction module 5 provided by the invention specifically comprises the following steps:
(1) except the registers of the upper X rows in the characteristic extraction register array, other registers write the stored data into the register with the upper distance of X from the register;
(2) the register in the lower buffer area writes the stored data into the register of the feature extraction register array connected with the register and the register of the right buffer area;
(3) the other registers in the right buffer, except the upper X rows of registers, write the stored data into the register that is X above the register.
The right shift operation of the feature extraction module 5 provided by the invention specifically comprises:
(1) except the left Y-column register in the feature extraction register array, other registers write the stored data into a register with the distance of Y from the register on the left;
(2) the register in the right buffer writes the stored data into a register in the feature extraction register array connected thereto.
The diagnosis method of the health diagnosis module 7 provided by the invention comprises the following steps:
(1) building a bridge data cloud server, collecting data of a plurality of bridges in four stages of design, construction, maintenance and monitoring through a monitoring terminal, sorting and sorting the data according to different data properties, and then performing data fusion by adopting a big data processing method to form various input data required by a deep learning network; the bridge comprises bridges of a certain type, different sizes and different regions, and contains the conditions of a normal state and various degradation states;
(2) drawing a visual graph by the fused bridge data for cloud storage;
(3) establishing an accurate finite element model of the bridge structure by using data in a design stage and a construction stage, respectively simulating the conditions of a normal state and various degradation states of the bridge structure, and storing related data as training input of a deep learning network;
(4) constructing a five-layer deep learning network DN, wherein a first layer SS adopts a sparse automatic encoder, a second layer and a third layer adopt a general automatic encoder, a fourth layer DS adopts a noise reduction automatic encoder, a fifth layer SVM adopts a support vector machine, input data of the fifth layer SVM is A [ i ] (i is 1,2, …, n), and the input data formed in the first step can be any matrix; the output data is S [ j ] (j ═ 1,2, …, m), which represents the specific health status of each region of the bridge structure and the health status of the whole bridge structure, and may be any matrix;
(5) the method comprises the steps of characteristic learning, namely inputting data of two stages of design and construction into a deep learning network DN, and acquiring the characteristics of various normal parameters of the bridge structure by adopting unsupervised training; inputting part of data of the maintenance stage and the monitoring stage and data of finite element simulation into the network, adopting supervised training to obtain the characteristics of various parameters of the structure in various degradation states, and finely adjusting the fifth layer of the deep learning network;
(6) data verification, namely inputting the other part of data in the monitoring stage into a network for data verification, and further optimizing the whole deep learning network according to a verification result to finally form a deep learning network which can be universally used for health diagnosis of various bridge structures;
(7) and D, performing structural health diagnosis on the bridge, preprocessing various data of the bridge by adopting a method similar to the step one for any bridge according to the deep learning network which is formed in the step five and can be used for structural health diagnosis, and inputting the preprocessed data into the successfully trained deep learning network for diagnosis after the formed data can be input, so that whether the structural health state of the bridge is normal or in which level of degradation state is accurately obtained.
The performance evaluation module 8 provided by the invention has the following evaluation method:
1) collecting the detection report of each bridge in the past year, establishing a report and extracting the technical condition score, the bridge age, the structure type, the traffic volume and the maintenance behavior information of each year;
2) correcting and cleaning the acquired data, removing redundancy, and constructing a relational database through a database program;
3) training and checking the established neural network based on data in the relational database to obtain a neural network model for predicting structural performance degradation;
4) and acquiring the structure type and annual traffic volume of each bridge to be predicted by using the trained neural network model, and predicting the performance change trend of the whole structure and local components of the bridge in the regional road network.
The step 1) provided by the invention specifically comprises the following steps:
acquiring a detection report of each bridge of a road network in a target area in the past year;
extracting technical condition score, bridge age, structure type, traffic volume and maintenance behavior information in each detection report;
cleaning the extracted data according to a preset data cleaning rule to remove invalid data;
and screening the bridge age, the structure type, the traffic volume, the maintenance behavior information and the annual technical condition scoring field of the bridge according to the structure type to be used as an attribute set of the relational database, and processing and storing the part subjected to data cleaning into the relational database.
As shown in fig. 2, the early warning method of the high-efficiency bridge structure health early warning control system provided by the embodiment of the present invention specifically includes:
s101: the bridge structure weighing system comprises a bridge image acquisition module, a camera, a bearing data acquisition module, a weighing detector and a weighing detector.
S102: the main control module utilizes an image enhancement algorithm to enhance the acquired bridge image through the image enhancement module, and utilizes the extraction program to extract the characteristic elements of the acquired bridge image through the characteristic extraction module.
S103: and identifying crack information of the extracted characteristic elements by using an identification program through a crack identification module, and diagnosing the health of the bridge structure by using a diagnostic program through a health diagnosis module.
S104: and evaluating the performance of the bridge structure by using an evaluation program through a performance evaluation module.
S105: and the early warning module utilizes the alarm to timely give an alarm according to the abnormal diagnosis result, and the display module utilizes the display to display the acquired bridge structure diagram, crack information, diagnosis result and evaluation result.
When the bridge image acquisition system works, firstly, the bridge image acquisition module 1 acquires bridge structure image data by using a camera; the load-bearing data acquisition module 2 is used for acquiring the weighing data of the bridge structure by using a weighing detector; secondly, the main control module 3 utilizes an image enhancement algorithm to enhance the acquired bridge image through the image enhancement module 4; extracting characteristic elements of the acquired bridge image by using an extraction program through a characteristic extraction module 5; identifying crack information for the extracted characteristic elements by using an identification program through a crack identification module 6; diagnosing the health of the bridge structure by using a diagnostic program through a health diagnosis module 7; evaluating the performance of the bridge structure by a performance evaluation module 8 by using an evaluation program; then, the early warning module 9 utilizes the alarm to perform alarm notification in time according to the abnormal result of diagnosis; and finally, displaying the acquired bridge structure diagram, crack information, diagnosis result and evaluation result by using a display through the display module 10.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the present invention in any way, and all simple modifications, equivalent changes and modifications made to the above embodiment according to the technical spirit of the present invention are within the scope of the technical solution of the present invention.
Claims (8)
1. An efficient bridge structure health early warning control method is characterized by comprising the following steps:
firstly, acquiring bridge structure image data by using a camera through a bridge image acquisition module, and acquiring bridge structure weighing data by using a weighing detector through a bearing data acquisition module;
secondly, the main control module utilizes an image enhancement algorithm to enhance the acquired bridge image through an image enhancement module, and utilizes an extraction program to extract characteristic elements of the acquired bridge image through a characteristic extraction module; the image enhancement module enhancement method comprises the following steps: (1) the input interface unit transmits the received video signal collected by the camera to a video decoding unit electrically connected with the input interface unit, and the video decoding unit performs analog-to-digital conversion on the received video signal and then transmits the video signal to the image enhancement processing unit; (2) the image data processed by the image enhancement processing unit is transmitted to the video coding unit, the video coding unit carries out coding processing on the image data, then the image data is amplified by the video amplification unit, and finally the enhanced video signal is output by the output interface unit; the extraction method of the feature extraction module comprises the following steps: (1) when traversal starts, data in the feature extraction register array is invalid, and the data at the upper left of the image must be input into the feature extraction register array for feature extraction; because the feature extraction register array has no interface with the periphery, data is input through the lower buffer area; (2) inputting data into a lower buffer area, and then carrying out a downward movement operation, wherein the data is moved into two rows at the lowest part of the feature extraction register array and the right buffer area; (3) repeating the step (2) for 5 times in total until all the data at the upper left of the image are moved into the feature extraction register array; (4) performing image feature extraction once, and storing image data of two lines below the image into a lower buffer area simultaneously because the next operation is also a downward movement operation, and performing downward movement operation once after the feature extraction is completed; (5) repeating the step (4) until the image has no data below; at the moment, a right shift operation is carried out, and because the right buffer area continuously updates data during multiple downward shift operations, the right buffer area stores effective data at the moment, the right shift operation is directly carried out, and the data is not required to be written into the right buffer area; (6) after one right shift operation is carried out, the next operation is upward shift, the upper buffer area starts to work, and image data of two lines above the image are stored in the upper buffer area while the features are extracted; (7) carrying out image feature extraction after carrying out primary upward moving operation; meanwhile, the next operation is also an upward movement operation, so that the data of two lines above the image are stored in an upper buffer area; (8) repeating the step (7) until the image has no data above; at the moment, a right shift operation is carried out, and because the right buffer area continuously updates data during multiple times of shift operations, the right buffer area stores effective data at the moment, the right shift operation is directly carried out, and the data is not required to be written into the right buffer area; (9) repeating the previous steps (4) to (8) until the whole target image is traversed;
thirdly, identifying crack information of the extracted characteristic elements by using an identification program through a crack identification module, and diagnosing the health of the bridge structure by using a diagnostic program through a health diagnosis module;
fourthly, evaluating the performance of the bridge structure by a performance evaluation module by using an evaluation program;
and fifthly, timely alarming and informing according to the abnormal diagnosis result by using an alarm through an early warning module, and displaying the acquired bridge structure diagram, crack information, diagnosis result and evaluation result by using a display through a display module.
2. The efficient bridge structure health early warning control method according to claim 1, wherein the upward movement operation of the feature extraction module of the efficient bridge structure health early warning control method specifically comprises:
(1) except the registers of the X rows below the feature extraction register array, other registers write the stored data into the register with the distance X from the register below;
(2) the register of the upper buffer area writes the stored data into a characteristic extraction register array connected with the register;
(3) the data stored by other registers except the registers of the X row at the lower part in the right buffer area are written into the register with the distance of X from the register at the lower part;
(4) the register in the upper buffer writes the stored data into the right buffer connected thereto.
3. The efficient bridge structure health early warning control method according to claim 1, wherein the downward movement operation of the feature extraction module of the efficient bridge structure health early warning control method specifically comprises:
(1) except the registers of the upper X rows in the characteristic extraction register array, other registers write the stored data into the register with the upper distance of X from the register;
(2) the register in the lower buffer area writes the stored data into the register of the feature extraction register array connected with the register and the register of the right buffer area;
(3) the other registers in the right buffer, except the upper X rows of registers, write the stored data into the register that is X above the register.
4. The efficient bridge structure health early warning control method according to claim 1, wherein the right shift operation of the feature extraction module of the efficient bridge structure health early warning control method specifically comprises:
(1) except the left Y-column register in the feature extraction register array, other registers write the stored data into a register with the distance of Y from the register on the left;
(2) the register in the right buffer writes the stored data into a register in the feature extraction register array connected thereto.
5. The efficient bridge structure health early warning control method of claim 1, wherein the health diagnosis module diagnosis method of the efficient bridge structure health early warning control method is as follows:
(1) building a bridge data cloud server, collecting data of a plurality of bridges in four stages of design, construction, maintenance and monitoring through a monitoring terminal, sorting and sorting the data according to different data properties, and then performing data fusion by adopting a big data processing method to form various input data required by a deep learning network; the bridge comprises bridges of a certain type, different sizes and different regions, and contains the conditions of a normal state and various degradation states;
(2) drawing a visual graph by the fused bridge data for cloud storage;
(3) establishing an accurate finite element model of the bridge structure by using data in a design stage and a construction stage, respectively simulating the conditions of a normal state and various degradation states of the bridge structure, and storing related data as training input of a deep learning network;
(4) constructing a five-layer deep learning network DN, wherein a first layer SS adopts a sparse automatic encoder, a second layer and a third layer adopt a general automatic encoder, a fourth layer DS adopts a noise reduction automatic encoder, a fifth layer SVM adopts a support vector machine, input data of the fifth layer SVM is A [ i ] (i is 1,2, …, n), and the input data formed in the first step can be any matrix; the output data is S [ j ] (j ═ 1,2, …, m), which represents the specific health status of each region of the bridge structure and the health status of the whole bridge structure, and may be any matrix;
(5) the method comprises the steps of characteristic learning, namely inputting data of two stages of design and construction into a deep learning network DN, and acquiring the characteristics of various normal parameters of the bridge structure by adopting unsupervised training; inputting part of data of the maintenance stage and the monitoring stage and data of finite element simulation into the network, adopting supervised training to obtain the characteristics of various parameters of the structure in various degradation states, and finely adjusting the fifth layer of the deep learning network;
(6) data verification, namely inputting the other part of data in the monitoring stage into a network for data verification, and further optimizing the whole deep learning network according to a verification result to finally form a deep learning network which can be universally used for health diagnosis of various bridge structures;
(7) and D, performing structural health diagnosis on the bridge, preprocessing various data of the bridge by adopting a method similar to the step one for any bridge according to the deep learning network which is formed in the step five and can be used for structural health diagnosis, and inputting the preprocessed data into the successfully trained deep learning network for diagnosis after the formed data can be input, so that whether the structural health state of the bridge is normal or in which level of degradation state is accurately obtained.
6. The efficient bridge structure health early warning control method of claim 1, wherein the performance evaluation module evaluation method of the efficient bridge structure health early warning control method is as follows:
1) collecting the detection report of each bridge in the past year, establishing a report and extracting the technical condition score, the bridge age, the structure type, the traffic volume and the maintenance behavior information of each year;
2) correcting and cleaning the acquired data, removing redundancy, and constructing a relational database through a database program;
3) training and checking the established neural network based on data in the relational database to obtain a neural network model for predicting structural performance degradation;
4) and acquiring the structure type and annual traffic volume of each bridge to be predicted by using the trained neural network model, and predicting the performance change trend of the whole structure and local components of the bridge in the regional road network.
7. The efficient bridge structure health early warning control method of claim 6, wherein the step 1) specifically comprises:
acquiring a detection report of each bridge of a road network in a target area in the past year;
extracting technical condition score, bridge age, structure type, traffic volume and maintenance behavior information in each detection report;
cleaning the extracted data according to a preset data cleaning rule to remove invalid data;
and screening the bridge age, the structure type, the traffic volume, the maintenance behavior information and the annual technical condition scoring field of the bridge according to the structure type to be used as an attribute set of the relational database, and processing and storing the part subjected to data cleaning into the relational database.
8. An efficient bridge structure health early warning control system for implementing the efficient bridge structure health early warning control method according to any one of claims 1 to 7, wherein the efficient bridge structure health early warning control system comprises:
the bridge image acquisition module is connected with the main control module and is used for acquiring bridge structure image data through the camera;
the load-bearing data acquisition module is connected with the main control module and is used for acquiring the weighing data of the bridge structure through the weighing detector;
the main control module is connected with the bridge image acquisition module, the bearing data acquisition module, the image enhancement module, the feature extraction module, the crack identification module, the health diagnosis module, the performance evaluation module, the early warning module and the display module and is used for controlling each module to normally work through the main control computer;
the image enhancement module is connected with the main control module and is used for enhancing the acquired bridge image through an image enhancement algorithm;
the characteristic extraction module is connected with the main control module and used for extracting characteristic elements of the acquired bridge image through an extraction program;
the crack identification module is connected with the main control module and used for identifying crack information of the extracted characteristic elements through an identification program;
the health diagnosis module is connected with the main control module and is used for diagnosing the health of the bridge structure through a diagnosis program;
the performance evaluation module is connected with the main control module and used for evaluating the performance of the bridge structure through an evaluation program;
the early warning module is connected with the main control module and used for carrying out alarm notification in time according to the abnormal diagnosis result through the alarm;
and the display module is connected with the main control module and used for displaying the acquired bridge structure diagram, crack information, diagnosis results and evaluation results through a display.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911406973.4A CN111222189A (en) | 2019-12-31 | 2019-12-31 | Efficient bridge structure health early warning control system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911406973.4A CN111222189A (en) | 2019-12-31 | 2019-12-31 | Efficient bridge structure health early warning control system and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111222189A true CN111222189A (en) | 2020-06-02 |
Family
ID=70828003
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911406973.4A Pending CN111222189A (en) | 2019-12-31 | 2019-12-31 | Efficient bridge structure health early warning control system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111222189A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111626261A (en) * | 2020-06-05 | 2020-09-04 | 国网湖南省电力有限公司 | Intelligent inspection analysis early warning system for hydraulic buildings |
| CN114775457A (en) * | 2022-03-16 | 2022-07-22 | 浙江广厦建设职业技术大学 | Detection device for repairing ancient bridge and detection method thereof |
| CN116415507A (en) * | 2023-05-31 | 2023-07-11 | 四川省公路规划勘察设计研究院有限公司 | Big transportation bridge intelligent evaluation system based on big data and cloud computing |
| CN116776267A (en) * | 2023-06-13 | 2023-09-19 | 西南交通大学 | Unsupervised data processing method and system for bridge construction control |
| CN117572295A (en) * | 2024-01-12 | 2024-02-20 | 山东和兑智能科技有限公司 | Multi-mode on-line monitoring and early warning method for high-voltage sleeve |
| CN117664484A (en) * | 2024-01-31 | 2024-03-08 | 北京智城联合科技发展有限公司 | Smart city bridge safety monitoring and early warning method and system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201576307U (en) * | 2009-12-18 | 2010-09-08 | 广东省科学院自动化工程研制中心 | Image enhancement module |
| CN102867181A (en) * | 2012-07-27 | 2013-01-09 | 华南理工大学 | Characteristic extraction module for digital image processing and traversing method |
| CN106529062A (en) * | 2016-11-20 | 2017-03-22 | 重庆交通大学 | Bridge structure health diagnosis method based on deep learning |
| CN106556498A (en) * | 2016-10-31 | 2017-04-05 | 石家庄铁道大学 | Damage Identification Methods for Bridge Structures and system |
| CN109614669A (en) * | 2018-11-23 | 2019-04-12 | 同济大学 | Net grade Bridge performance assessment prediction method |
| CN109612427A (en) * | 2019-01-16 | 2019-04-12 | 兰州交通大学 | A kind of the unmanned plane highway bridge deformation detecting method and system of multi-sensor cooperation |
-
2019
- 2019-12-31 CN CN201911406973.4A patent/CN111222189A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN201576307U (en) * | 2009-12-18 | 2010-09-08 | 广东省科学院自动化工程研制中心 | Image enhancement module |
| CN102867181A (en) * | 2012-07-27 | 2013-01-09 | 华南理工大学 | Characteristic extraction module for digital image processing and traversing method |
| CN106556498A (en) * | 2016-10-31 | 2017-04-05 | 石家庄铁道大学 | Damage Identification Methods for Bridge Structures and system |
| CN106529062A (en) * | 2016-11-20 | 2017-03-22 | 重庆交通大学 | Bridge structure health diagnosis method based on deep learning |
| CN109614669A (en) * | 2018-11-23 | 2019-04-12 | 同济大学 | Net grade Bridge performance assessment prediction method |
| CN109612427A (en) * | 2019-01-16 | 2019-04-12 | 兰州交通大学 | A kind of the unmanned plane highway bridge deformation detecting method and system of multi-sensor cooperation |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111626261A (en) * | 2020-06-05 | 2020-09-04 | 国网湖南省电力有限公司 | Intelligent inspection analysis early warning system for hydraulic buildings |
| CN114775457A (en) * | 2022-03-16 | 2022-07-22 | 浙江广厦建设职业技术大学 | Detection device for repairing ancient bridge and detection method thereof |
| CN116415507A (en) * | 2023-05-31 | 2023-07-11 | 四川省公路规划勘察设计研究院有限公司 | Big transportation bridge intelligent evaluation system based on big data and cloud computing |
| CN116415507B (en) * | 2023-05-31 | 2023-08-08 | 四川省公路规划勘察设计研究院有限公司 | Big transportation bridge intelligent evaluation system based on big data and cloud computing |
| CN116776267A (en) * | 2023-06-13 | 2023-09-19 | 西南交通大学 | Unsupervised data processing method and system for bridge construction control |
| CN116776267B (en) * | 2023-06-13 | 2024-01-19 | 西南交通大学 | Unsupervised data processing method and system for bridge construction control |
| CN117572295A (en) * | 2024-01-12 | 2024-02-20 | 山东和兑智能科技有限公司 | Multi-mode on-line monitoring and early warning method for high-voltage sleeve |
| CN117572295B (en) * | 2024-01-12 | 2024-04-12 | 山东和兑智能科技有限公司 | Multi-mode on-line monitoring and early warning method for high-voltage sleeve |
| CN117664484A (en) * | 2024-01-31 | 2024-03-08 | 北京智城联合科技发展有限公司 | Smart city bridge safety monitoring and early warning method and system |
| CN117664484B (en) * | 2024-01-31 | 2024-04-05 | 北京智城联合科技发展有限公司 | Smart city bridge safety monitoring and early warning method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111222189A (en) | Efficient bridge structure health early warning control system and method | |
| CN109272123B (en) | Sucker-rod pump working condition early warning method based on convolution-circulation neural network | |
| CN108027301B (en) | Damage information extraction element, damage information extracting method and damage information extraction procedure | |
| CN111274737A (en) | Method and system for predicting remaining service life of mechanical equipment | |
| CN111737909B (en) | Structural health monitoring data anomaly identification method based on space-time graph convolutional network | |
| CN108764601B (en) | Structural health monitoring abnormal data diagnosis method based on computer vision and deep learning technology | |
| CN112258496A (en) | Underground drainage pipeline disease segmentation method based on full convolution neural network | |
| CN111797890A (en) | Method and system for detecting defects of power transmission line equipment | |
| Chen et al. | Convolutional neural networks (CNNs)-based multi-category damage detection and recognition of high-speed rail (HSR) reinforced concrete (RC) bridges using test images | |
| CN106980922A (en) | A kind of power transmission and transformation equipment state evaluation method based on big data | |
| CN111127465A (en) | Automatic generation method and system for bridge detection report | |
| CN115471487A (en) | Insulator defect detection model construction and insulator defect detection method and device | |
| CN110555477A (en) | municipal facility fault prediction method and device | |
| CN115186917A (en) | Active early warning type risk management and control system and method | |
| CN117034143B (en) | Distributed system fault diagnosis method and device based on machine learning | |
| Dogan et al. | Detection of damages caused by earthquake and reinforcement corrosion in RC buildings with Deep Transfer Learning | |
| CN115526515A (en) | Safety monitoring system of gate for water conservancy and hydropower | |
| CN109902800B (en) | Method for detecting general object by using multi-stage backbone network based on quasi-feedback neural network | |
| CN117629549B (en) | Bridge building health monitoring and safety early warning system | |
| CN104504265B (en) | A kind of method of servicing bridges monitoring information security evaluation | |
| CN116561670B (en) | Metal roof health state identification and alarm method | |
| CN116189802A (en) | Transformer fault early warning method based on gas concentration time sequence data | |
| Xu et al. | Concrete and steel bridge Structural Health Monitoring—Insight into choices for machine learning applications | |
| CN113267217B (en) | Bridge group monitoring system and bridge group monitoring method | |
| CN115438547A (en) | Overall evaluation method and system based on pavement service state |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200602 |