CN115144474B - Ultrasonic signal data quality detection method - Google Patents
Ultrasonic signal data quality detection method Download PDFInfo
- Publication number
- CN115144474B CN115144474B CN202210745314.9A CN202210745314A CN115144474B CN 115144474 B CN115144474 B CN 115144474B CN 202210745314 A CN202210745314 A CN 202210745314A CN 115144474 B CN115144474 B CN 115144474B
- Authority
- CN
- China
- Prior art keywords
- data
- detection
- abnormal
- judging
- detection interval
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 75
- 230000002159 abnormal effect Effects 0.000 claims abstract description 18
- 206010000117 Abnormal behaviour Diseases 0.000 claims abstract description 8
- 238000002604 ultrasonography Methods 0.000 claims description 3
- 208000027418 Wounds and injury Diseases 0.000 abstract description 9
- 230000006378 damage Effects 0.000 abstract description 9
- 208000014674 injury Diseases 0.000 abstract description 9
- 238000000034 method Methods 0.000 abstract description 4
- 229910000831 Steel Inorganic materials 0.000 description 7
- 239000010959 steel Substances 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 4
- 238000005299 abrasion Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N29/00—Investigating or analysing materials by the use of ultrasonic, sonic or infrasonic waves; Visualisation of the interior of objects by transmitting ultrasonic or sonic waves through the object
- G01N29/44—Processing the detected response signal, e.g. electronic circuits specially adapted therefor
- G01N29/4472—Mathematical theories or simulation
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Algebra (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Mathematical Physics (AREA)
- Pure & Applied Mathematics (AREA)
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The method for detecting the quality of ultrasonic signal data comprises the steps of collecting historical data of ultrasonic detection data of each detection point in a detection interval, calculating a predicted ultrasonic value of the detection point, obtaining real ultrasonic data in the detection interval, and judging that data suspected abnormal behaviors occur when the number of data abnormal windows in the detection interval is larger than a set first judgment threshold value. When the suspected abnormal behavior of the data occurs in the detection interval, the positions of the abnormal windows are subjected to injury detection, and when injury is detected, the detection position attribute is modified to be normal. Counting the number of the abnormal windows in the processed detection interval, and judging that the data of the detection interval is abnormal when the number is larger than a set first judgment threshold value; otherwise, judging that the detection section data is normal.
Description
Technical Field
The invention relates to the fields of rail transit and rail flaw detection, in particular to a quality detection method for ultrasonic signal data of rail flaw detection.
Background
In recent years, as railway logistics are increased, the density of the train is increased, the railway load is gradually increased, the abrasion of the steel rail is accelerated, and the health state of the steel rail seriously influences the safety of railway traffic, so that the detection work of the steel rail is particularly important. The industrial flaw detection is an important work for preventing the steel rail from being broken, the existing flaw detection work mainly adopts an ultrasonic steel rail flaw detection vehicle to detect the steel rail, ultrasonic data are collected, and the data are brought back to a workshop to finish data playback analysis work. After the analyst makes basic determination of the injury, uploading injury data to the corresponding station section, and checking once by the station section analyst; after the analysis of the station section analyst is finished, the analysis is submitted to the working place of the group company to carry out secondary rechecking of the injury, and whether the collected data accurately and effectively influence the subsequent working links. In the ultrasonic flaw detection process, the conditions of inaccurate detection data and the like caused by the reasons of ageing failure of a probe, uneven surface of a rail, irregular operation of flaw detectors and the like are easy to occur, the efficiency of data playback is reduced, the health judgment of a steel rail is influenced, the conditions of missed judgment, misjudgment and the like are easy to occur, and traffic safety is threatened. Thus, how to ensure the accuracy of ultrasonic signal data is particularly critical in the whole rail flaw detection work. According to the invention, the wave-out characteristics of the ultrasonic signals can be more accurately analyzed by using a texture analysis method, so that the ultrasonic signal interval with abnormal waves can be automatically screened out, the blank of ultrasonic signal quality detection in the current flaw detection field is made up, and the accuracy of flaw judgment can be improved.
Disclosure of Invention
In view of the above, the present invention provides a method for detecting quality of ultrasonic signal data of rail flaw detection, which solves the above-mentioned drawbacks in the background art, and aims at solving the problems existing in the existing ultrasonic rail flaw data acquisition process.
The aim of the invention is achieved by the following technical scheme.
An ultrasonic signal data quality detection method comprises the following steps:
(1) Collecting historical data of ultrasonic detection data of each detection point in a detection interval, and for a historical data set { s i,j } at any point i, wherein j represents a sequence number of the historical data, the number of elements of the set is n i,mi＝int(ni/3), wherein int () is a rounding function;
(2) Calculating predicted ultrasound values for detection points
wi＝c1g1+(1-c1)g2
Wherein c 1 is the first correction constant for historical data training
g1＝k1(ni+1)+b1
g2＝k2(mi+1)+b2
Obtaining a prediction data set { w i } in the detection interval;
(3) Obtaining real ultrasonic data { s i } in a detection interval, taking a time window with the length of N 1, traversing detection point data according to the fixed length s, and adding the difference d i＝|si-wi | between the real data and the predicted data of each detection point in each step of time window to obtain a window difference value in the time window Where k is the starting number of the window, and when D k is greater than the set first judgment threshold ts 1, the judgment window k is a data anomaly window. When the number of the data abnormal windows in the detection interval is larger than a set first judging threshold ts 2, judging that data suspected abnormal behaviors occur;
(4) When the suspected abnormal behavior of the data occurs in the detection interval, the positions of the abnormal windows are subjected to injury detection, and when injury is detected, the detection position attribute is modified to be normal. Counting the number of the abnormal windows in the processed detection interval, and judging that the data of the detection interval is abnormal when the number is larger than a set first judgment threshold ts 2; otherwise, judging that the detection section data is normal.
Detailed Description
The invention relates to an ultrasonic signal data quality detection method, which comprises (1) collecting historical data of ultrasonic detection data of each detection point in a detection interval, and for a historical data set { s i,j } at any point i, wherein j represents a serial number of the historical data, the number of elements of the set is n i,mi＝int(ni/3), wherein int () is a rounding function;
(2) Calculating predicted ultrasound values for detection points
wi＝c1g1+(1-c1)g2
Wherein c 1 is the first correction constant for historical data training
g1＝k1(ni+1)+b1
g2＝k2(mi+1)+b2
Obtaining a prediction data set { w i } in the detection interval;
(3) Obtaining real ultrasonic data { s i } in a detection interval, taking a time window with the length of N 1, traversing detection point data according to the fixed length s, and adding the difference d i＝|si-wi | between the real data and the predicted data of each detection point in each step of time window to obtain a window difference value in the time window Where k is the starting number of the window, and when D k is greater than the set first judgment threshold ts 1, the judgment window k is a data anomaly window. When the number of the data abnormal windows in the detection interval is larger than a set first judging threshold ts 2, judging that data suspected abnormal behaviors occur;
(4) When the suspected abnormal behavior of the data occurs in the detection interval, the positions of the abnormal windows are subjected to injury detection, and when injury is detected, the detection position attribute is modified to be normal. Counting the number of the abnormal windows in the processed detection interval, and judging that the data of the detection interval is abnormal when the number is larger than a set first judgment threshold ts 2; otherwise, judging that the detection section data is normal.
Claims (1)
1. The ultrasonic signal data quality detection method is characterized by comprising the following steps of:
(1) Collecting historical data of ultrasonic detection data of each detection point in a detection interval, and for a historical data set { s i,j } at any point i, wherein j represents a sequence number of the historical data, the number of elements of the set is n i,mi＝int(ni/3), wherein int () is a rounding function;
(2) Calculating predicted ultrasound values for detection points
wi＝c1g1+(1-c1)g2
Wherein c 1 is the first correction constant for historical data training
g1＝k1(ni+1)+b1
g2＝k2(mi+1)+b2
Obtaining a prediction data set { w i } in the detection interval;
(3) Obtaining real ultrasonic data { s i } in a detection interval, taking a time window with the length of N 1, traversing detection point data according to the fixed length s, and adding the difference d i＝|si-wi | between the real data and the predicted data of each detection point in each step of time window to obtain a window difference value in the time window Wherein k is the starting point sequence number of the window, and when D k is larger than a set first judgment threshold ts 1, the window k is judged to be a data abnormal window; when the number of the data abnormal windows in the detection interval is larger than a set first judging threshold ts 2, judging that data suspected abnormal behaviors occur;
(4) When the suspected abnormal behavior of the data occurs in the detection interval, performing flaw detection on the positions of the abnormal windows, and when no flaw is detected, modifying the attribute of the detection position to be normal; counting the number of the abnormal windows in the processed detection interval, and judging that the data of the detection interval is abnormal when the number is larger than a set first judgment threshold ts 2; otherwise, judging that the detection section data is normal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210745314.9A CN115144474B (en) | 2022-06-27 | 2022-06-27 | Ultrasonic signal data quality detection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210745314.9A CN115144474B (en) | 2022-06-27 | 2022-06-27 | Ultrasonic signal data quality detection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115144474A CN115144474A (en) | 2022-10-04 |
| CN115144474B true CN115144474B (en) | 2024-05-28 |
Family
ID=83410277
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210745314.9A Active CN115144474B (en) | 2022-06-27 | 2022-06-27 | Ultrasonic signal data quality detection method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115144474B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003210458A (en) * | 2002-01-21 | 2003-07-29 | Toshiba Corp | Ultrasonograph |
| JP2006242770A (en) * | 2005-03-03 | 2006-09-14 | Japan Nuclear Cycle Development Inst States Of Projects | Electromagnetic ultrasonic flaw detection/measurement method and device |
| CN109856241A (en) * | 2019-02-15 | 2019-06-07 | 中国铁道科学研究院集团有限公司 | The steel rail ultrasonic flaw detecting method and system automatically controlled based on threshold value |
| CN111538897A (en) * | 2020-03-16 | 2020-08-14 | 北京三快在线科技有限公司 | Recommended abnormality detection method and device, electronic equipment and readable storage medium |
| CN111896625A (en) * | 2020-08-17 | 2020-11-06 | 中南大学 | Real-time monitoring method and monitoring system for rail damage |
| CN113720910A (en) * | 2021-08-25 | 2021-11-30 | 深圳市比一比网络科技有限公司 | Steel rail defect intelligent detection method and system based on ultrasonic signals |
| WO2022047658A1 (en) * | 2020-09-02 | 2022-03-10 | 大连大学 | Log anomaly detection system |
| CN114330429A (en) * | 2021-12-21 | 2022-04-12 | 中国国家铁路集团有限公司 | Steel rail scratch recognition method, device, system, equipment and storage medium |
-
2022
- 2022-06-27 CN CN202210745314.9A patent/CN115144474B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003210458A (en) * | 2002-01-21 | 2003-07-29 | Toshiba Corp | Ultrasonograph |
| JP2006242770A (en) * | 2005-03-03 | 2006-09-14 | Japan Nuclear Cycle Development Inst States Of Projects | Electromagnetic ultrasonic flaw detection/measurement method and device |
| CN109856241A (en) * | 2019-02-15 | 2019-06-07 | 中国铁道科学研究院集团有限公司 | The steel rail ultrasonic flaw detecting method and system automatically controlled based on threshold value |
| CN111538897A (en) * | 2020-03-16 | 2020-08-14 | 北京三快在线科技有限公司 | Recommended abnormality detection method and device, electronic equipment and readable storage medium |
| CN111896625A (en) * | 2020-08-17 | 2020-11-06 | 中南大学 | Real-time monitoring method and monitoring system for rail damage |
| WO2022047658A1 (en) * | 2020-09-02 | 2022-03-10 | 大连大学 | Log anomaly detection system |
| CN113720910A (en) * | 2021-08-25 | 2021-11-30 | 深圳市比一比网络科技有限公司 | Steel rail defect intelligent detection method and system based on ultrasonic signals |
| CN114330429A (en) * | 2021-12-21 | 2022-04-12 | 中国国家铁路集团有限公司 | Steel rail scratch recognition method, device, system, equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115144474A (en) | 2022-10-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110533229B (en) | Track maintenance time prediction method and device | |
| CN102175768A (en) | Method and device for detecting defects and failures of high-speed rail based on vibration signals | |
| CN112173636B (en) | Method for detecting faults of belt conveyor carrier roller by inspection robot | |
| CN116644373A (en) | Automobile flow data analysis management system based on artificial intelligence | |
| CN112380992B (en) | Method and device for evaluating and optimizing accuracy of monitoring data in machining process | |
| CN112160761A (en) | Hard rock TBM cutter disc hob abrasion real-time evaluation method based on field parameters | |
| CN114330429B (en) | Rail scratch identification method, device, system, equipment and storage medium | |
| CN115220396A (en) | Intelligent monitoring method and system for numerical control machine tool | |
| CN115144474B (en) | Ultrasonic signal data quality detection method | |
| CN117367845B (en) | Health diagnosis method for army equipment maintenance equipment | |
| CN112528753B (en) | Pretreatment method for impact vibration signal in rolling mill rolling process | |
| CN112215307B (en) | Method for automatically detecting signal abnormality of earthquake instrument by machine learning | |
| CN117540331A (en) | Grinding roller abrasion degree monitoring and analyzing system for roller type medium-speed coal mill | |
| CN110458824B (en) | Drill bit wear detection method | |
| CN111624261A (en) | Method for detecting quality of ultrasonic signal data for steel rail flaw detection | |
| CN109212601B (en) | Method for detecting abnormal measuring points of seismic data | |
| EP3418705B1 (en) | Method for clamped joint seating detection | |
| CN110530631A (en) | A kind of gear list type fault detection method based on hybrid classifer | |
| CN113672859B (en) | Fault acoustic diagnosis system for switch machine | |
| CN115307939A (en) | Method, device, equipment and storage medium for detecting wheel circumferential surface of rail vehicle | |
| EP3925850A1 (en) | Method for monitoring a railway track and monitoring system for monitoring a railway track | |
| CN117195068B (en) | PIND detection signal classification judgment system based on space-time correlation algorithm | |
| CN111123356A (en) | Abnormal track intelligent identification method based on first arrival information | |
| CN118465452A (en) | Cable local fault positioning method based on discharge detection | |
| CN115042835B (en) | Acoustic detection method and system for wheel damage of railway vehicle |
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 |