CN117554218A - Straight asphalt pouring type steel bridge surface composite beam test piece fatigue test device and method - Google Patents
Straight asphalt pouring type steel bridge surface composite beam test piece fatigue test device and method Download PDFInfo
- Publication number
- CN117554218A CN117554218A CN202410046160.3A CN202410046160A CN117554218A CN 117554218 A CN117554218 A CN 117554218A CN 202410046160 A CN202410046160 A CN 202410046160A CN 117554218 A CN117554218 A CN 117554218A
- Authority
- CN
- China
- Prior art keywords
- test
- data
- historical
- module
- scheme
- 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.)
- Granted
Links
- 238000012360 testing method Methods 0.000 title claims abstract description 272
- 238000000034 method Methods 0.000 title claims abstract description 41
- 239000002131 composite material Substances 0.000 title claims abstract description 27
- 229910000831 Steel Inorganic materials 0.000 title claims abstract description 25
- 239000010959 steel Substances 0.000 title claims abstract description 25
- 239000010426 asphalt Substances 0.000 title claims abstract description 23
- 238000009661 fatigue test Methods 0.000 title claims abstract description 22
- 238000012545 processing Methods 0.000 claims abstract description 24
- 230000008569 process Effects 0.000 claims abstract description 22
- 238000004458 analytical method Methods 0.000 claims abstract description 21
- 238000007405 data analysis Methods 0.000 claims abstract description 17
- 238000001514 detection method Methods 0.000 claims abstract description 11
- 238000005457 optimization Methods 0.000 claims description 23
- 238000005259 measurement Methods 0.000 claims description 18
- 230000002159 abnormal effect Effects 0.000 claims description 15
- 238000012544 monitoring process Methods 0.000 claims description 15
- 230000006870 function Effects 0.000 claims description 14
- 238000005266 casting Methods 0.000 claims description 12
- 238000013500 data storage Methods 0.000 claims description 12
- 230000005856 abnormality Effects 0.000 claims description 10
- 238000010801 machine learning Methods 0.000 claims description 7
- 230000002787 reinforcement Effects 0.000 claims description 5
- 230000007274 generation of a signal involved in cell-cell signaling Effects 0.000 claims description 4
- 230000002068 genetic effect Effects 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 238000010998 test method Methods 0.000 abstract description 2
- 230000007774 longterm Effects 0.000 description 5
- 239000000463 material Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000006399 behavior Effects 0.000 description 2
- 238000010219 correlation analysis Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/02—Details
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/02—Details
- G01N3/04—Chucks
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/32—Investigating strength properties of solid materials by application of mechanical stress by applying repeated or pulsating forces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/086—Learning methods using evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/0001—Type of application of the stress
- G01N2203/0005—Repeated or cyclic
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/0058—Kind of property studied
- G01N2203/0069—Fatigue, creep, strain-stress relations or elastic constants
- G01N2203/0073—Fatigue
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/02—Details not specific for a particular testing method
- G01N2203/04—Chucks, fixtures, jaws, holders or anvils
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Biophysics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Physiology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Investigating Strength Of Materials By Application Of Mechanical Stress (AREA)
Abstract
The invention relates to the technical field of steel bridge surface detection, in particular to a straight asphalt pouring type steel bridge surface composite beam test piece fatigue test device and method, wherein the test method comprises the following steps: clamping and positioning supporting are carried out on the test piece; applying a preset load to the test piece and collecting parameter data of the test; acquiring a data acquisition result and storing parameter data; and analyzing and processing the parameter data of the test, and obtaining a test conclusion. The invention effectively solves the subjectivity and one-sided problems of human factors on test loading parameters and test data analysis, avoids excessive control of a loading device by manpower, and improves the intelligent level of the whole test process and the accuracy of test data and analysis results.
Description
Technical Field
The invention relates to the technical field of steel bridge surface detection, in particular to a fatigue test device and method for a straight asphalt pouring type steel bridge surface composite beam test piece.
Background
At present, in order to discuss the influence of casting type straight asphalt mixture material parameters on the fatigue damage rule of a composite structure of a steel bridge during service, a composite beam fatigue test with a specific loading mode is often adopted, load and deformation parameters in the test process are collected, a composite Liang Sunshang variable is calculated, and the influence degree of material modulus, pavement thickness and load level on the fatigue damage of the composite beam is analyzed.
Aiming at the fatigue test of the composite beam, the current loading process of a test piece and the processing after test data acquisition are often realized in a manual mode, namely, in the test process, the loading parameters are manually set and the control of the loading process is carried out based on the parameters, and meanwhile, the conclusion of the test is obtained through manual analysis and comparison and the equivalent mode on the data acquired in the loading process; the following problems often exist in the above manner:
the loading parameters and analysis data are set manually in the test, which may introduce subjectivity and operator dependence, and different operators may have different judgments and decisions, thereby affecting the consistency of the test results. During the test, the complex loading mode often requires high-precision control, and the manual mode may not meet the requirement, which may result in failure to explore fatigue performance under complex load conditions. For data processing, human errors may be introduced by manual mode, including data recording errors and analysis deviation.
Disclosure of Invention
The invention provides a straight asphalt pouring type steel bridge surface composite beam test piece fatigue test device and a method, and the test device and the method are used for effectively solving the problems pointed out in the background art.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
straight-run asphalt pouring type steel bridge deck composite beam test piece fatigue test device includes:
a loading system for applying a load to the test piece;
the test piece system is positioned below the loading system and comprises a test clamp and a positioning support table, wherein the test clamp is arranged on the positioning support table and is used for clamping and positioning the supported test piece;
the control system comprises a parameter measurement module and a control algorithm module, wherein the parameter measurement module is used for collecting parameters of a test piece in a test according to a test scheme, and the control algorithm module is used for controlling the loading system according to the test scheme;
the data acquisition system comprises a sensor interface, a data acquisition module and a data storage module, wherein the sensor interface is connected with the parameter measurement module, the data acquisition module acquires parameter data through the sensor interface, and the data storage module is used for storing the acquired parameter data;
and the data analysis module is used for analyzing and processing the parameter data to obtain a test conclusion corresponding to the test scheme.
Further, the system also comprises a monitoring system for monitoring each parameter data in the test process and outputting an alarm signal when abnormal data are judged to occur.
Further, the system also comprises a test scheme optimization adjustment system, wherein the test scheme optimization adjustment system comprises:
the historical data analysis module is used for acquiring a historical test scheme, historical test data and a historical test conclusion through the data storage module, and analyzing the relevance of the historical test scheme, the historical test data and the historical test conclusion to obtain a first relevance result;
the current data analysis module is used for obtaining the latest device state data through the device test record, obtaining current test data and a current test conclusion through the data storage module, and analyzing the relevance of the device state data, the current test data and the current test conclusion to obtain a second relevance result;
and the test scheme optimization algorithm module revises the test scheme according to the first association result and the second association result and outputs the revised scheme for the next test.
Further, the historical data analysis module and the current data module unit both adopt a long-short-time memory network model for carrying out relevance analysis, and the long-short-time memory network model comprises:
the first input layer receives the historical test scheme, the historical test data and the historical test conclusion as inputs;
the second input layer is used for receiving the device state data, the current test data and the current test conclusion as inputs;
sharing an LSTM layer, capturing a time dependence of data from the first input layer and the second input layer;
sharing a full connection layer, and respectively processing the output of the data of the first input layer and the second input layer;
the output layer is used for respectively outputting the first association result and the second association result;
and the loss function is used for measuring the performance of the model, calculating the gap between the prediction of the model and the actual test conclusion, and carrying out model training and parameter adjustment.
Further, the test scheme optimization algorithm module comprises:
the input parameter unit is used for receiving the first association result, the second association result and the current test scheme as inputs;
the objective function unit is used for defining an optimization objective function of the test scheme and defining a performance measurement standard to be optimized;
an initialization unit, which initializes the current test scheme as a starting point of optimization;
an optimization algorithm unit for adjusting test parameters by a genetic algorithm to improve the objective function;
a stop condition unit defining a condition for stopping the algorithm;
and a revised version output unit for generating a revised test version as an output.
Further, the monitoring system comprises:
the data acquisition module acquires various test data in a test process in real time;
the data processing module is used for processing and analyzing the test data;
the abnormality detection module is used for detecting abnormal data according to the comparison of the data and an expected mode by using a machine learning algorithm;
and the alarm signal generation module is used for generating an alarm signal when the abnormality detection module detects abnormal data.
Further, the machine learning algorithm used in the abnormality detection unit is a deep reinforcement learning algorithm.
A fatigue test method for a straight asphalt pouring type steel bridge surface composite beam test piece comprises the following steps:
clamping and positioning supporting are carried out on the test piece;
applying a preset load to the test piece according to a test scheme and collecting parameter data of the test;
acquiring a data acquisition result and storing the parameter data;
and analyzing and processing the parameter data of the test, and obtaining a test conclusion corresponding to the test scheme.
Further, the method further comprises the following steps:
monitoring each parameter data of the test process;
and judging abnormal data in the parameter data and outputting an alarm signal.
Further, the method further comprises the following steps:
acquiring historical comprehensive data, and carrying out relevance analysis of each data to obtain a first relevance result, wherein the historical comprehensive data comprises: historical test schemes, historical test data and historical test conclusions;
acquiring current comprehensive data, and carrying out relevance analysis of each data to obtain a second relevance result, wherein the current comprehensive data comprises: latest device state data, current test data and current test conclusion;
and revising the test scheme according to the first association result and the second association result, and outputting the revised scheme for the next test.
By the technical scheme of the invention, the following technical effects can be realized:
the method effectively solves the subjectivity and one-sided problems of human factors on test loading parameters and test data analysis, avoids excessive control of a loading device by manpower, and improves the intelligent level of the whole test process and the accuracy of test data and analysis results.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments described in the present invention, and other drawings may be obtained according to the drawings without inventive effort to those skilled in the art.
FIG. 1 is a frame diagram of a straight asphalt pouring type steel bridge deck composite beam test piece fatigue test device;
FIG. 2 is an optimized frame diagram of a straight asphalt casting type steel bridge deck composite beam test piece fatigue test device;
FIG. 3 is a schematic flow chart of a fatigue test method for a straight asphalt pouring type steel bridge deck composite beam test piece;
FIG. 4 is a schematic diagram of a process for monitoring and alerting a test procedure;
FIG. 5 is a schematic flow chart of revising the test protocol.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. The terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and/or" as used herein includes any and all combinations of one or more of the associated listed items.
Example 1
As shown in fig. 1, a fatigue test device for a straight asphalt casting type steel bridge surface composite beam test piece is provided, which comprises:
a loading system for applying a load to the test piece;
the test piece system is positioned below the loading system and comprises a test clamp and a positioning support table, wherein the test clamp is arranged on the positioning support table and is used for clamping and positioning the supported test piece;
the control system comprises a parameter measurement module and a control algorithm module, wherein the parameter measurement module is used for collecting parameters of a test piece in a test according to a test scheme, and the control algorithm module is used for controlling the loading system according to the test scheme;
the data acquisition system comprises a sensor interface, a data acquisition module and a data storage module, wherein the sensor interface is connected with the parameter measurement module, the data acquisition module acquires parameter data through the sensor interface, and the data storage module is used for storing the acquired parameter data;
and the data analysis system is used for analyzing and processing the parameter data to obtain a test conclusion corresponding to the test scheme.
The test piece is arranged on the test fixture and is positioned by using a positioning support table, wherein the positioning support table is used for ensuring the position stability of the test piece during the test, and if the clamping of the test piece is realized by a clamping mechanism, the positioning support table can keep the fixed position of the test piece; the loading system applies preset load according to a test scheme to simulate the load condition in actual use, and meanwhile, each sensor acquires parameter data in a test to capture key information in the test process; the data collected during the test is transmitted to a data collection system which is responsible for recording the data, which helps to build a data record of the test for later analysis. Once the test is completed, the results of the data acquisition are sent to a data analysis system for analysis and processing, which may include visualization of the data, chart generation, application of mathematical models, and statistical and engineering analysis of the parameter data; from the results of the analysis, conclusions can be drawn regarding the performance, durability, fatigue behavior, and the like of the test piece.
Preferably, the embodiment further comprises a monitoring system for monitoring each parameter data in the test process and outputting an alarm signal when abnormal data is determined.
Specifically, the monitoring system can monitor real-time data of the test process, and once abnormal data are found, the monitoring system can give an alarm in time to ensure the safety and efficiency of the whole test process.
As a preference of the above embodiment, as shown in fig. 2, the test plan optimization adjustment system further includes:
the historical data analysis module is used for acquiring a historical test scheme, historical test data and a historical test conclusion through the data storage module, and analyzing the relevance of the historical test scheme, the historical test data and the historical test conclusion to obtain a first relevance result;
the current data analysis module is used for obtaining the latest device state data through the device test record, obtaining current test data and a current test conclusion through the data storage module, and analyzing the relevance of the device state data, the current test data and the current test conclusion to obtain a second relevance result;
and the test scheme optimization algorithm module revises the test scheme according to the first association result and the second association result and outputs the revised scheme for the next test.
In the preferred scheme, the historical test data and the historical test conclusion are utilized through the first association result, the past test experience is fully considered, valuable references are provided based on the past success factors and the failure experience, and complex relations between a plurality of test parameters and conditions can be identified through analyzing the association between the historical test scheme and the data and the test conclusion; the historical data generally reflects test conditions over a longer time frame, so the first correlation results can provide information of long-term stability and trends, helping to identify potential material behavior and performance changes.
The second association result provides real-time feedback by analyzing the current device state data, the current test data and the real-time test conclusion, so that the problem or abnormality in the current test can be immediately identified; the second association result can adjust the test scheme according to the current test condition and the change of the real-time data, so that the adaptability is stronger, and the second association result can more pertinently solve the specific problems possibly occurring in the current test because the second association result is based on the ongoing test, thereby improving the efficiency and the reliability of the test. In the second association result, the latest device state data acquired through the device check record is participated in the current data association analysis, and the invention has the following specific advantages:
the device state data are real-time, can timely reflect the state and performance of the test device and whether the equipment is normally operated, have high timeliness, and are helpful for immediately identifying abnormality or problem in the operation of the device so as to maintain the stability of the test. The fusion device state data into the data correlation analysis can provide more comprehensive background information for test data, including test environmental conditions, which can help better understand test results and accurately evaluate material properties, particularly properties under simulated actual use conditions. Device status data including but not limited to temperature data, humidity data, vibration data, voltage and current data, mechanical status data and other environmental parameters and the like,
in summary, the first correlation results focus mainly on historical data and long-term trends, providing suggestions based on accumulated experience, while the second correlation results focus on real-time and adaptability to cope with specific challenges and situations in the current test, and the two results are used in combination to comprehensively consider the historical experience and real-time requirements to optimize the test scheme.
As a preferable mode of the above embodiment, the history data analysis module and the current data analysis module both use a long-short-time memory network model to perform relevance analysis, where the long-short-time memory network model includes:
the first input layer receives a historical test scheme, historical test data and a historical test conclusion as inputs;
the second input layer is used for receiving device state data, current test data and current test conclusion as inputs;
sharing the LSTM layer, capturing a time dependence of data from the first input layer and the second input layer;
sharing the full connection layer, and respectively processing the output of the data of the first input layer and the second input layer;
the output layer is used for respectively outputting a first association result and a second association result;
and the loss function is used for measuring the performance of the model, calculating the gap between the prediction of the model and the actual test conclusion, and carrying out model training and parameter adjustment.
The long-short time memory network model (LSTM) is a circular neural network (RNN) architecture specially designed for processing time series data, can capture time dependence and sequence patterns in the data, is very important for processing time dependence in historical test data and current test data, has an internal memory unit, can memorize long-term dependence, is very helpful for analyzing trend and long-term stability in the historical data, and can better capture complex relations and patterns in the historical data. In addition, the LSTM model allows analysis in real-time streaming data, and through the second correlation result, it can provide real-time feedback, identifying problems or anomalies in the current trial, which is critical for timely intervention and adjustment in the ongoing trial.
In the above preferred approach, by passing the historical data and current data into the LSTM model, the model is able to take into account both long-term trends and real-time requirements within a single architecture, which enables the model to provide experimental plan optimization suggestions that take into account both historical experience and real-time conditions.
As a preference to the above embodiment, the trial optimization algorithm module includes:
the input parameter unit is used for receiving the first association result, the second association result and the current test scheme as inputs;
the objective function unit is used for defining an optimization objective function of the test scheme and defining a performance measurement standard to be optimized;
an initialization unit for initializing the current test scheme as a starting point of optimization;
an optimization algorithm unit for adjusting the test parameters by a genetic algorithm to improve the objective function;
a stop condition unit defining a condition for stopping the algorithm;
and a revised version output unit for generating a revised test version as an output.
In the optimization scheme, the whole optimization process is decomposed into different functional units by adopting a multi-modular design, so that the understandability, maintainability and expandability of the algorithm are improved. The objective function module defines an optimized objective function of the test scheme, which is very critical, defines the performance measurement standard to be optimized by the algorithm, and ensures the directionality and the target consistency of the algorithm.
In particular, performance metrics may measure consistency and stability of test data that should have a high degree of consistency across operators, across test times, and under different conditions, which helps reduce the impact of subjectivity and operator dependency; in the preferred scheme, the performance measurement standard also comprises control precision of test parameters, and parameters such as load, deformation and the like which need to be controlled in the test are controlled within a specified precision range, and can be evaluated by measuring parameter deviation and analyzing the control range; in the implementation process, the performance measurement standard can also comprise a test which can accurately simulate and evaluate the performance under different load conditions, and the performance measurement standard can be realized by comparing the performance measurement standard with a theoretical model or simulation data; and, performance metrics may be concerned with the repeatability of test results, similar conclusions should be able to be drawn between different tests, to verify the reliability of the test, etc.
As a preference to the above embodiment, the monitoring system comprises:
the data acquisition module acquires various test data in the test process in real time, including load data, deformation data, temperature data, test time and the like;
the data processing module is used for processing and analyzing the test data;
the abnormality detection module is used for detecting abnormal data according to the comparison of the data and an expected mode by using a machine learning algorithm;
and the alarm signal generation module is used for generating an alarm signal when the abnormality detection module detects the abnormal data.
The method can help identify problems in the test in advance by detecting abnormal data through the scheme, and the existence of the alarm signal generation module also ensures that measures can be taken in time when abnormal conditions occur so as to solve potential problems early, and the improvement is helpful for improving the reliability and efficiency of the test.
The data processing and analysis performed for the data processing module includes:
data cleaning: outliers, missing values, and noise data that may be present are identified and processed, which may include data interpolation, outlier removal, or noise reduction by smoothing techniques.
Data calibration: the data are calibrated to ensure that the measurement results of different sensors have consistency under the same conditions, thereby improving the comparability and accuracy of the data.
Data format conversion: data of different sources or formats is converted to a consistent data format for unified processing and analysis.
Data correlation analysis: correlations between the different data are analyzed to determine interactions and relationships between them, thereby helping to understand interactions between multiple factors during the course of the trial.
And (3) data characteristic extraction: key features relating to trial parameters and performance are extracted from the raw data for use by subsequent machine learning algorithms.
As a preferable example of the above embodiment, the machine learning algorithm used in the abnormality detection module is a deep reinforcement learning algorithm.
The algorithm is generally used for controlling a continuous motion space, in the invention, setting and controlling test parameters can be regarded as continuous motion, fatigue performance of a test is taken as a reward signal, a deep reinforcement learning algorithm can simulate a plurality of motion schemes in the test, compare the simulation schemes with actual test data and gradually learn and improve the motion strategy so as to enable damage variables to meet expected performance as much as possible.
Advantages of the deep reinforcement learning algorithm include applicability to continuous motion space, ability to operate under high precision control requirements while reducing human intervention, and the algorithm is also capable of adaptively adjusting test conditions to explore fatigue performance under different load conditions without introducing human error.
Example two
As shown in fig. 3, the application provides a fatigue test method for a straight asphalt casting type steel bridge surface composite beam test piece, which comprises the following steps:
s1: clamping and positioning supporting are carried out on the test piece;
s2: applying a preset load to the test piece according to the test scheme and collecting the parameter data of the test;
s3: acquiring a data acquisition result and storing parameter data;
s4: and analyzing and processing the parameter data of the test, and obtaining a test conclusion.
As a preference to the above embodiment, as shown in fig. 4, the method further includes:
a1: monitoring each parameter data of the test process;
a2: and judging abnormal data in the parameter data and outputting an alarm signal.
As a preference to the above embodiment, as shown in fig. 5, the method further includes:
b1: acquiring historical comprehensive data, and carrying out relevance analysis on each data to obtain a first relevance result, wherein the historical comprehensive data comprises: historical test schemes, historical test data and historical test conclusions;
b2: acquiring current comprehensive data, and performing relevance analysis to obtain a second relevance result, wherein the current comprehensive data comprises: latest device state data, current test data and current test conclusion;
b3: and revising the test scheme according to the first correlation result and the second correlation result.
The technical effects achieved in this embodiment are the same as those in the first embodiment, and will not be described here again.
The foregoing has outlined and described the basic principles, features, and advantages of the present invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (10)
1. Straight-run asphalt pouring type steel bridge deck composite beam test piece fatigue test device, which is characterized by comprising:
a loading system for applying a load to the test piece;
the test piece system is positioned below the loading system and comprises a test clamp and a positioning support table, wherein the test clamp is arranged on the positioning support table and is used for clamping and positioning the supported test piece;
the control system comprises a parameter measurement module and a control algorithm module, wherein the parameter measurement module is used for collecting parameters of a test piece in a test according to a test scheme, and the control algorithm module is used for controlling the loading system according to the test scheme;
the data acquisition system comprises a sensor interface, a data acquisition module and a data storage module, wherein the sensor interface is connected with the parameter measurement module, the data acquisition module acquires parameter data through the sensor interface, and the data storage module is used for storing the acquired parameter data;
and the data analysis system is used for analyzing and processing the parameter data to obtain a test conclusion corresponding to the test scheme.
2. The straight asphalt casting type steel bridge deck composite beam test piece fatigue test device according to claim 1, further comprising a monitoring system for monitoring each parameter data in the test process and outputting an alarm signal when abnormal data are determined.
3. The straight asphalt casting type steel bridge deck composite beam test piece fatigue test apparatus according to claim 1, further comprising a test scheme optimization adjustment system, the test scheme optimization adjustment system comprising:
the historical data analysis module is used for acquiring a historical test scheme, historical test data and a historical test conclusion through the data storage module, and analyzing the relevance of the historical test scheme, the historical test data and the historical test conclusion to obtain a first relevance result;
the current data analysis module is used for acquiring the latest device state data through the device test record, acquiring the current test data and the current test conclusion through the data storage module, and analyzing the relevance of the device state data, the current test data and the current test conclusion to obtain a second relevance result;
and the test scheme optimization algorithm module revises the test scheme according to the first association result and the second association result and outputs the revised scheme for the next test.
4. The straight asphalt casting type steel bridge deck composite beam test piece fatigue test device according to claim 3, wherein the historical data analysis module and the current data analysis module both adopt long-short-term memory network models for carrying out relevance analysis, and the long-short-term memory network models comprise:
the first input layer receives the historical test scheme, the historical test data and the historical test conclusion as inputs;
the second input layer is used for receiving the device state data, the current test data and the current test conclusion as inputs;
sharing an LSTM layer, capturing a time dependence of data from the first input layer and the second input layer;
sharing a full connection layer, and respectively processing the output of the data of the first input layer and the second input layer;
the output layer is used for respectively outputting the first association result and the second association result;
and the loss function is used for measuring the performance of the model, calculating the gap between the prediction of the model and the actual test conclusion, and carrying out model training and parameter adjustment.
5. The straight asphalt casting type steel bridge deck composite beam test piece fatigue test apparatus according to claim 3 or 4, wherein the test scheme optimization algorithm module comprises:
the input parameter unit is used for receiving the first association result, the second association result and the current test scheme as inputs;
the objective function unit is used for defining an optimization objective function of the test scheme and defining a performance measurement standard to be optimized;
an initialization unit, which initializes the current test scheme as a starting point of optimization;
an optimization algorithm unit for adjusting test parameters by a genetic algorithm to improve the objective function;
a stop condition unit defining a condition for stopping the algorithm;
and a revised version output unit for generating a revised test version as an output.
6. The straight asphalt casting type steel bridge deck composite beam test piece fatigue test apparatus according to claim 2, wherein the monitoring system comprises:
the data acquisition module acquires various test data in a test process in real time;
the data processing module is used for processing and analyzing the test data;
the abnormality detection module is used for detecting abnormal data according to the comparison of the data and an expected mode by using a machine learning algorithm;
and the alarm signal generation module is used for generating an alarm signal when the abnormality detection unit detects abnormal data.
7. The straight asphalt casting type steel bridge deck composite beam test piece fatigue test apparatus according to claim 6, wherein the machine learning algorithm used in the anomaly detection module is a deep reinforcement learning algorithm.
8. The fatigue test method for the straight asphalt pouring type steel bridge deck composite beam test piece is characterized by comprising the following steps of:
clamping and positioning supporting are carried out on the test piece;
applying a preset load to the test piece according to a test scheme and collecting parameter data of the test;
acquiring a data acquisition result and storing the parameter data;
and analyzing and processing the parameter data of the test, and obtaining a test conclusion.
9. The method for testing fatigue of a straight asphalt casting type steel bridge deck composite beam test piece according to claim 8, further comprising:
monitoring each parameter data of the test process;
and judging abnormal data in the parameter data and outputting an alarm signal.
10. The method for testing fatigue of a straight asphalt casting type steel bridge deck composite beam test piece according to claim 8, further comprising:
acquiring historical comprehensive data, and carrying out relevance analysis of each data to obtain a first relevance result, wherein the historical comprehensive data comprises: historical test schemes, historical test data and historical test conclusions;
acquiring current comprehensive data, and carrying out relevance analysis of each data to obtain a second relevance result, wherein the current comprehensive data comprises: latest device state data, current test data and current test conclusion;
and revising the test scheme according to the first association result and the second association result, and outputting the revised scheme for the next test.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410046160.3A CN117554218B (en) | 2024-01-12 | 2024-01-12 | Straight asphalt pouring type steel bridge surface composite beam test piece fatigue test device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410046160.3A CN117554218B (en) | 2024-01-12 | 2024-01-12 | Straight asphalt pouring type steel bridge surface composite beam test piece fatigue test device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117554218A true CN117554218A (en) | 2024-02-13 |
| CN117554218B CN117554218B (en) | 2024-03-22 |
Family
ID=89823715
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410046160.3A Active CN117554218B (en) | 2024-01-12 | 2024-01-12 | Straight asphalt pouring type steel bridge surface composite beam test piece fatigue test device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117554218B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104897491A (en) * | 2015-03-31 | 2015-09-09 | 南京交通职业技术学院 | Testing apparatus and method for fatigue cracking of pavement on steel bridge |
| CN106097819A (en) * | 2016-07-31 | 2016-11-09 | 重庆交通大学 | Bridge for experimental teaching emulates detection method and system |
| CN208621340U (en) * | 2018-07-16 | 2019-03-19 | 北京交通大学 | A kind of ballastless track of high-speed railway complex environment simulation experiment system |
| CN111238927A (en) * | 2019-12-30 | 2020-06-05 | 中汽检测技术有限公司 | Fatigue durability evaluation method and device, electronic equipment and computer readable medium |
| CN111896398A (en) * | 2020-07-14 | 2020-11-06 | 江苏方天电力技术有限公司 | Fatigue performance assessment test loading device and test method for special welding structure |
| CN114689429A (en) * | 2022-03-01 | 2022-07-01 | 合肥富煌君达高科信息技术有限公司 | Self-feedback-based fatigue strength testing method and system for collected image |
| CN116952748A (en) * | 2023-08-01 | 2023-10-27 | 苏交科集团股份有限公司 | System and method for monitoring service performance degradation of node plate |
| CN117191613A (en) * | 2023-06-12 | 2023-12-08 | 方盛车桥（柳州）有限公司 | Pull-press fatigue test device for transverse pull rod |
| WO2024001467A1 (en) * | 2022-07-01 | 2024-01-04 | 湖南大学 | Fatigue crack propagation rate test method and device based on deep learning |
| CN117368000A (en) * | 2023-10-13 | 2024-01-09 | 昆山美仑工业样机有限公司 | Static torsion test stand provided with self-adaptive clamping mechanism |
-
2024
- 2024-01-12 CN CN202410046160.3A patent/CN117554218B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104897491A (en) * | 2015-03-31 | 2015-09-09 | 南京交通职业技术学院 | Testing apparatus and method for fatigue cracking of pavement on steel bridge |
| CN106097819A (en) * | 2016-07-31 | 2016-11-09 | 重庆交通大学 | Bridge for experimental teaching emulates detection method and system |
| CN208621340U (en) * | 2018-07-16 | 2019-03-19 | 北京交通大学 | A kind of ballastless track of high-speed railway complex environment simulation experiment system |
| CN111238927A (en) * | 2019-12-30 | 2020-06-05 | 中汽检测技术有限公司 | Fatigue durability evaluation method and device, electronic equipment and computer readable medium |
| CN111896398A (en) * | 2020-07-14 | 2020-11-06 | 江苏方天电力技术有限公司 | Fatigue performance assessment test loading device and test method for special welding structure |
| CN114689429A (en) * | 2022-03-01 | 2022-07-01 | 合肥富煌君达高科信息技术有限公司 | Self-feedback-based fatigue strength testing method and system for collected image |
| WO2024001467A1 (en) * | 2022-07-01 | 2024-01-04 | 湖南大学 | Fatigue crack propagation rate test method and device based on deep learning |
| CN117191613A (en) * | 2023-06-12 | 2023-12-08 | 方盛车桥（柳州）有限公司 | Pull-press fatigue test device for transverse pull rod |
| CN116952748A (en) * | 2023-08-01 | 2023-10-27 | 苏交科集团股份有限公司 | System and method for monitoring service performance degradation of node plate |
| CN117368000A (en) * | 2023-10-13 | 2024-01-09 | 昆山美仑工业样机有限公司 | Static torsion test stand provided with self-adaptive clamping mechanism |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117554218B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112384924B (en) | Method and device for establishing product performance prediction model, computer equipment, computer readable storage medium, product performance prediction method and prediction system | |
| US7275018B2 (en) | Method of condition monitoring | |
| US10521490B2 (en) | Equipment maintenance management system and equipment maintenance management method | |
| US6694286B2 (en) | Method and system for monitoring the condition of an individual machine | |
| CN113077172A (en) | Equipment state trend analysis and fault diagnosis method | |
| EP2045673A2 (en) | Method and apparatus for intelligent control and monitoring in a process control system | |
| JP2015011722A (en) | Non-intrusive data analytics in process control system | |
| KR20190021560A (en) | Failure prediction system using big data and failure prediction method | |
| JP2009053938A (en) | Equipment diagnosing system and equipment-diagnosing method on the basis of multiple model | |
| CN111860839A (en) | Shore bridge fault monitoring method based on multi-signal fusion and Adam optimization algorithm | |
| CN118408582A (en) | Method and system for detecting qualification of contact encoder | |
| JP2004505364A (en) | Remote diagnosis method of industrial technical process | |
| US20220414555A1 (en) | Prediction system, information processing apparatus, and information processing program | |
| CN117129698B (en) | Abnormality alarm and retest system and method for full-automatic coagulation tester | |
| CN117554218B (en) | Straight asphalt pouring type steel bridge surface composite beam test piece fatigue test device and method | |
| CN117591949A (en) | Equipment abnormality identification method, equipment and medium | |
| US7698245B2 (en) | Applying rules to validating data for a machine arrangement | |
| CN117435894A (en) | Cloud edge cooperation-based intelligent GIS equipment fault positioning detection method and system | |
| EP3640751A1 (en) | Apparatus for gas analysis and emission prediction | |
| CN114611701A (en) | Monitoring system and method for nuclear chemical process | |
| KR20060125590A (en) | Data processing system and method for regulating an installation | |
| Williams et al. | Digital Twin of Cyber-Physical CNC for Smart Manufacturing | |
| CN117272844B (en) | Method and system for predicting service life of distribution board | |
| RU2779795C1 (en) | Method and apparatus for predictive diagnostics of the technical condition of industrial facilities | |
| CN118246905B (en) | Small molecule detection equipment maintenance management system based on data analysis |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |