CN117309159A - Train cabinet flame early warning method based on infrared thermal imaging - Google Patents
Train cabinet flame early warning method based on infrared thermal imaging Download PDFInfo
- Publication number
- CN117309159A CN117309159A CN202311128805.XA CN202311128805A CN117309159A CN 117309159 A CN117309159 A CN 117309159A CN 202311128805 A CN202311128805 A CN 202311128805A CN 117309159 A CN117309159 A CN 117309159A
- Authority
- CN
- China
- Prior art keywords
- temperature
- matrix
- flame
- measurement
- value
- 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
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000001931 thermography Methods 0.000 title claims abstract description 15
- 239000011159 matrix material Substances 0.000 claims abstract description 37
- 238000005259 measurement Methods 0.000 claims abstract description 32
- 238000001914 filtration Methods 0.000 claims abstract description 10
- 238000012545 processing Methods 0.000 claims abstract description 10
- 230000001419 dependent effect Effects 0.000 claims abstract description 4
- 238000012417 linear regression Methods 0.000 claims description 9
- 238000004458 analytical method Methods 0.000 claims description 7
- 238000009499 grossing Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000009529 body temperature measurement Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000013178 mathematical model Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000005457 Black-body radiation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000003331 infrared imaging Methods 0.000 description 1
- 238000004393 prognosis Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000012552 review Methods 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/70—Passive compensation of pyrometer measurements, e.g. using ambient temperature sensing or sensing of temperature within housing
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/48—Thermography; Techniques using wholly visual means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/80—Calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B17/00—Fire alarms; Alarms responsive to explosion
- G08B17/12—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions
- G08B17/125—Actuation by presence of radiation or particles, e.g. of infrared radiation or of ions by using a video camera to detect fire or smoke
-
- 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
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T30/00—Transportation of goods or passengers via railways, e.g. energy recovery or reducing air resistance
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Fire-Detection Mechanisms (AREA)
Abstract
The invention discloses a train cabinet flame early warning method based on infrared thermal imaging, which comprises the following steps: acquiring a measurement temperature through a camera; performing a filtering process to eliminate measurement noise; executing temperature compensation processing, and establishing a temperature compensation model which takes a measurement error as a dependent variable and takes an ambient temperature and a device temperature as independent variables; eliminating measurement noise from the acquired measurement temperature, and then performing temperature compensation to obtain a temperature matrix; and carrying out early warning judgment on the flame occurrence condition of the cabinet based on the temperature matrix. The method can realize noise reduction and temperature compensation on the measured temperature, ensure the authenticity of the measured temperature data as much as possible, and improve the accuracy of judging the flame of the cabinet.
Description
Technical Field
The invention belongs to the technical field of fire early warning, and particularly relates to a train cabinet flame early warning method based on infrared thermal imaging.
Background
Due to the existence of blackbody radiation, any object radiates electromagnetic waves to the outside according to the difference of temperature. The portion having a wavelength of 2.0 to 1000 μm is called thermal infrared. The thermal infrared imaging images the object through the thermal infrared sensitive CCD, and can reflect the temperature field on the surface of the object.
Since the results of electromagnetic wave radiation to the outside are different at different temperatures, there are studies in the prior art to conduct fire prognosis by infrared thermal imaging technology.
According to the method, an infrared image in a long and narrow space acquired by the infrared thermal imager is preprocessed, then image segmentation is carried out in a connected domain mode, a high-temperature object, a suspected high-temperature object and a low-temperature object are primarily judged according to absolute temperature, a suspected high-temperature object area with the segmented target image temperature of 70-100 ℃ is acquired, continuous multi-frame video images are acquired, further image segmentation and binarization are carried out on the multi-frame video images, the dispersity, sharp angle number and height change characteristics of the segmented target area are calculated to serve as flame shape characteristics, and flame monitoring judgment is carried out on flames of the suspected high-temperature target area according to the flame shape characteristics by adopting a judgment algorithm based on a probability statistical model.
As disclosed in chinese patent application No. 201780023835.0, an intelligent flame detection device and method using infrared thermal imaging is disclosed, which combines an infrared thermal imaging camera and an infrared thermal imaging processing technology with an existing flame sensor, so that whether a flame signal received from the flame sensor is an allowable flame or an artificial flame can be accurately identified, thereby improving the accuracy of fire alarm.
However, when fire disaster early warning is carried out by infrared thermal imaging, early warning judgment is directly carried out by the temperature acquired by the equipment, however, the original temperature measured by the camera has a certain deviation from the actual temperature of the equipment, and on one hand, the measured temperature may drift due to the ambient temperature and the temperature of the camera equipment; on the other hand, randomly generated outliers (measurement noise) can also affect the temperature measurement and even cause erroneous flame judgment.
Disclosure of Invention
According to the technical problem, the temperature compensation is added to the measured value by using the ambient temperature, the measured temperature data is optimized by adopting the Kalman filtering algorithm, so that the measured temperature value is as close to the real temperature of the equipment as possible, and the self-adaption to the environment is realized, and the specific technical scheme is as follows:
a train cabinet flame early warning method based on infrared thermal imaging comprises the following steps:
acquiring a measurement temperature through a camera;
performing a filtering process to eliminate measurement noise;
executing temperature compensation processing, and establishing a temperature compensation model which takes a measurement error as a dependent variable and takes an ambient temperature and a device temperature as independent variables;
eliminating measurement noise from the acquired measurement temperature, and then performing temperature compensation to obtain a temperature matrix;
and carrying out early warning judgment on the flame occurrence condition of the cabinet based on the temperature matrix.
Further, the method for performing filtering processing to eliminate measurement noise includes:
at time k, determining a correction relation:
T c (k)＝T r (k)+βT e (k)+d(k)+n(k)；
in the above, the true temperature of the equipment is T r The ambient temperature is T e The temperature measured by the camera is T c The measurement noise is n, beta is an influence factor, and d is a temperature drift constant;
and assuming that the measured temperatures at the k moment and the k-1 moment are only affected by the measured noise, determining a system state equation as follows:
in the above, X k ＝[T c (k)T e (k)d(k)] T ，W k For process noise, Δt is the sampling time, T c (k) And T e (k) All can be measured;
the observation equation is determined as:
in the above, Z k For the measured value of the moment k of the camera, H is an observation matrix, N k For measuring noise; the mean value of the process noise W is 0, and the variance is Q; the mean value of the measurement noise N is 0, and the variance is R;
optimization is carried out by adopting a Kalman filtering iterative algorithm:
step1.k=0, and the estimated value X is initialized k Namely X 0 ；
Step2, update the predicted value
Step3. Updating covariance matrix P of predicted value and true value k ′ +1 ＝φP k φ T +Q；
Step4 update kalman gain matrix G k ＝P k ′ +1 H T (HP k ′ +1 H T +R) -1 ；
Step5 further update the estimated value X k+1 ＝X k ′ +1 +G k (Z k+1 -HX k ′ +1 )；
Step6. Updating covariance matrix P of estimated value and true value k+1 ＝(I-G k H)P k+1 ；
Step7.k=k+1, repeating step2 to step7;
obtaining an optimized state value X k ＝[T r (k)T e (k)d(k)] T I.e. as the final measurement of the present system.
Further, the method for performing the temperature compensation process includes:
establishing a temperature compensation model: measurement error = α1 ambient temperature + α2 device temperature + epsilon;
in the above formula, alpha 1 and alpha 2 are coefficients of a linear regression model, and epsilon is an error term;
different environment temperatures, equipment temperatures, corresponding actual temperature data and measured temperatures are collected, and a temperature compensation model is trained to obtain optimal values of alpha 1, alpha 2 and epsilon.
Further, new temperature data is collected periodically, and the compensation model is updated and calibrated.
Further, the method for carrying out early warning judgment on the flame occurrence condition of the cabinet based on the temperature matrix comprises the following steps:
determining an alarm threshold;
dividing a temperature matrix by adopting threshold distribution;
processing the temperature matrix by adopting a Canny edge algorithm to obtain a temperature edge distribution map in the image;
adopting a minimum surrounding rectangle to measure the temperature of the rectangle to obtain the maximum temperature, the minimum temperature and the average temperature in the matrix;
judging whether the rectangle meets the following two conditions simultaneously:
(1) Based on the analysis of the minimum bounding rectangle, judging whether the rectangular area is larger than a set alarm threshold value;
(2) Adopting historical data analysis, calculating an average value in a period of time in a data sequence, smoothing the data, capturing a trend, judging whether the trend exceeds an alarm threshold, and if so, judging whether the maximum temperature is greater than the alarm threshold;
when the two conditions are met simultaneously, the cabinet is judged to generate flame.
The beneficial effects of the invention are as follows:
(1) The influence of the external environment on the measured temperature is eliminated, and the erroneous judgment influence of the randomly generated abnormal points on the measured temperature can be effectively avoided by eliminating the measured noise and then compensating the measured temperature, meanwhile, the measured temperature is further compensated on the basis, the unstable influence of the external environment and the temperature of the measuring instrument on the measured temperature is avoided, and the authenticity of the measured temperature data is ensured as much as possible;
(2) The accuracy of judging the flame of the cabinet is improved, after the imaging processing of the temperature test, the minimum bounding rectangle is adopted to judge the generation of the flame of the cabinet, misjudgment of the flame caused by a few abnormal small-area pixel points can be avoided, and the accuracy of judgment is further enhanced by further combining with the analysis of historical data and through the trend of the historical data.
Drawings
FIG. 1 shows a temperature image judged in a minimum bounding rectangle in the embodiment;
FIG. 2 shows another temperature image judged in the minimum bounding rectangle in the embodiment;
FIG. 3 is a schematic diagram of a process for using historical data analysis in an embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the embodiments.
Examples
The original temperature measured by the camera and the real temperature of the equipment have certain deviation, and the factors causing the deviation are mainly that the camera can generate heat to form a certain temperature environment when working, and meanwhile, abnormal points (measuring noise) randomly generated in the temperature measuring process can also influence the temperature measurement.
Assuming the real temperature of the equipment is T r The ambient temperature is T e The temperature measured by the camera is T c When the measured noise is n, the k moment is the following correction relation:
T c (k)＝T r (k)+βT e (k)+d(k)+n(k)
in the above formula, β is an influence factor, and d is a temperature drift constant.
Firstly, a Kalman filtering algorithm is adopted to process measurement noise n (k), and assuming that the measured temperature at the moment k and the moment k-1 is only affected by the measurement noise, a system state equation can be written into the following form:
wherein X is k ＝[T c (k)T e (k)d(k)] T ，W k As process noise, Δt is the sampling time, due to T c (k) And T e (k) All can be measured, so the observation equation is:
in the above, Z k For the measured value of the moment k of the camera, H is an observation matrix, N k To measure noise.
After a state equation and an observation equation of the system are obtained, wherein the mean value of the process noise W is 0, and the variance is Q; the mean value of the measurement noise N is 0 and the variance is R.
Optimization is carried out by adopting a Kalman filtering iterative algorithm:
step1.k=0, and the estimated value X is initialized k Namely X 0 ；
Step2, update the predicted value
Step3. Updating covariance matrix P of predicted value and true value k ′ +1 ＝φP k φ T +Q；
Step4 update kalman gain matrix G k ＝P k ′ +1 H T (HP k ′ +1 H T +R) -1 ；
Step5 further update the estimated value X k+1 ＝X k ′ +1 +G k (Z k+1 -HX k ′ +1 )；
Step6. Updating covariance matrix P of estimated value and true value k+1 ＝(I-G k H)P k+1 ；
Step7.k=k+1, repeating step2 to step7;
optimized by the algorithm to obtainTo the optimized state value X k ＝[T r (k)T e (k)d(k)] T I.e. as the final measurement of the present system.
Secondly, temperature compensation is performed by using the ambient temperature and the equipment temperature under the condition of eliminating measurement noise, and the method is as follows:
the equipment temperature can be obtained by a temperature sensor arranged in the infrared camera, meanwhile, the environment temperature of the cabinet can be obtained through an external sensor or an environment monitoring system, and a temperature compensation model is built by collecting a series of calibration data at different temperatures.
A linear regression mathematical model is used to establish the relationship between the ambient temperature and the device temperature and the measurement error.
Establishing a linear regression mathematical model: a linear regression model is built using the temperature matrix as a dependent variable (predicted variable) and the ambient temperature and the device temperature as independent variables (predicted variables).
The linear regression model may be expressed as: temperature matrix = α1 ambient temperature + α2 device temperature + epsilon;
in the above equation, α1 and α2 are coefficients of a linear regression model, and ε is an error term.
Collecting different environment temperatures, equipment temperatures, corresponding actual temperature data and measured temperatures, wherein the actual temperature data is an object to be measured with known temperature which is set in the environment as a training model, the measured temperatures are measured temperatures of the object to be measured in the environment, and the measured temperatures are temperature values obtained by removing measured noise; through a large number of model training, the acquired data are used for training the linear regression model, and the optimal estimated values of alpha 1 and alpha 2 are obtained.
After the estimated values of alpha 1 and alpha 2 are obtained, the validity and the accuracy of the model are verified by evaluating the fitting degree and the prediction capability of the model, a trained linear regression model is used for predicting a temperature matrix corresponding to the future environmental temperature and the equipment temperature, and the accuracy and the reliability of temperature measurement are ensured by comparing the error between the predicted value and the actual measured value.
However, since the environment and the equipment temperature may change, calibration of the temperature compensation model needs to be performed regularly, and the compensation model is updated by collecting new calibration data so as to ensure the accuracy of temperature compensation.
In the technology, the flame occurrence of the cabinet is further pre-warned based on the temperature matrix.
Because the cabinet flame and the equipment in the cabinet which normally operates have larger temperature difference, once the cabinet flame event occurs, the system can immediately send alarm information to a crew member, and an administrator can obtain the alarm information from the background and perform corresponding treatment. The system is also a core function, so that a crew can know the existence of the flame of the cabinet in time, the subsequent loss is reduced, and the safety of the cabinet and the personnel safety of the rail transit train can be effectively ensured.
The core idea is to determine an appropriate alarm threshold value in advance according to
And then carrying out related operation on the temperature matrix updated in real time, judging whether cabinet flame is actually generated when data exceeding a threshold value appears, if so, immediately triggering an alarm, generating a temperature detection chart, and specifically processing the temperature matrix as follows:
and adopting Smoothing Filter to remove the influence of noise on the temperature treatment. And the temperature matrix is visualized, and the temperature distribution is displayed in an image form through automatic temperature measurement of the matrix, so that a user can conveniently and intuitively observe and analyze data. The temperature matrix is divided by adopting threshold distribution, then the temperature matrix is processed by adopting a Canny edge algorithm to obtain a temperature edge distribution map in an image, and the rectangle is measured by adopting a minimum bounding rectangle to obtain the maximum temperature, the minimum temperature and the average temperature in the matrix.
The following will apply various judgments to enhance the certainty of the judgment result:
first kind: based on the analysis of the minimum bounding rectangle, judging that the cabinet flame is generated when the rectangular area is larger than a certain threshold value, thereby avoiding misjudgment of some abnormal pixel points, as shown in fig. 1 and 2;
second kind: for analysis with historical data (i.e., instant analysis algorithm), moving Average (Moving Average), an Average over a period of time in the data sequence is calculated for smoothing the data and capturing trends. When the trend is too large, the maximum temperature is analyzed to determine whether it is a cabinet flame occurrence, as shown in fig. 3, the trend of the temperature data significantly exceeds the threshold.
When both judgment results are considered as cabinet flames, an alarm prompt is adopted, and when an alarm is triggered, the program sends the alarm prompt to operators through popup windows, sounds and the like so as to timely draw attention. The program will record the events triggering the alarm in a log file, including time, location, temperature data, etc., for subsequent review and analysis.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting.
Claims (5)
1. The train cabinet flame early warning method based on infrared thermal imaging is characterized by comprising the following steps of:
acquiring a measurement temperature through a camera;
performing a filtering process to eliminate measurement noise;
executing temperature compensation processing, and establishing a temperature compensation model which takes a measurement error as a dependent variable and takes an ambient temperature and a device temperature as independent variables;
eliminating measurement noise from the acquired measurement temperature, and then performing temperature compensation to obtain a temperature matrix;
and carrying out early warning judgment on the flame occurrence condition of the cabinet based on the temperature matrix.
2. The infrared thermal imaging-based train cabinet flame warning method according to claim 1, wherein the method for performing filtering processing to eliminate measurement noise is as follows:
at time k, determining a correction relation:
T c (k)＝T r (k)+βT e (k)+d(k)+n(k)；
in the above, the true temperature of the equipment is T r The ambient temperature is T e The temperature measured by the camera is T c The measurement noise is n, beta is an influence factor, and d is a temperature drift constant;
and assuming that the measured temperatures at the k moment and the k-1 moment are only affected by the measured noise, determining a system state equation as follows:
in the above, X k ＝[T c (k)T e (k)d(k)] T ，W k For process noise, Δt is the sampling time, T c (k) And T e (k) All can be measured;
the observation equation is determined as:
Z k+1 ＝HX k +N k ,
in the above, Z k For the measured value of the moment k of the camera, H is an observation matrix, N k For measuring noise; the mean value of the process noise W is 0, and the variance is Q; the mean value of the measurement noise N is 0, and the variance is R;
optimization is carried out by adopting a Kalman filtering iterative algorithm:
step1.k=0, and the estimated value X is initialized k Namely X 0 ；
Step2, update the predicted value
Step3. Updating covariance matrix P of predicted value and true value k ′ +1 ＝φP k φ T +Q；
Step4 update kalman gain matrix G k ＝P k ′ +1 H T (HP k ′ +1 H T +R) -1 ；
Step5 further update the estimated value X k+1 ＝X k ′ +1 +G k (Z k+1 -HX k ′ +1 )；
Step6. Updating covariance matrix P of estimated value and true value k+1 ＝(I-G k H)P k+1 ；
Step7.k=k+1, repeating step2 to step7;
obtaining an optimized state value X k ＝[T r (k)T e (k)d(k)] T I.e. as the final measurement of the present system.
3. The infrared thermal imaging-based train cabinet flame warning method according to claim 2, wherein the method for performing the temperature compensation process is as follows:
establishing a temperature compensation model: measurement error = α1 ambient temperature + α2 device temperature + epsilon;
in the above formula, alpha 1 and alpha 2 are coefficients of a linear regression model, and epsilon is an error term;
different environment temperatures, equipment temperatures, corresponding actual temperature data and measured temperatures are collected, and a temperature compensation model is trained to obtain optimal values of alpha 1, alpha 2 and epsilon.
4. The infrared thermal imaging-based train cabinet flame warning method according to claim 3, wherein new temperature data is collected periodically, and the compensation model is updated and calibrated.
5. The train cabinet flame early warning method based on infrared thermal imaging according to claim 3, wherein the method for early warning and judging the occurrence condition of the cabinet flame based on the temperature matrix is as follows:
determining an alarm threshold;
dividing a temperature matrix by adopting threshold distribution;
processing the temperature matrix by adopting a Canny edge algorithm to obtain a temperature edge distribution map in the image;
adopting a minimum surrounding rectangle to measure the temperature of the rectangle to obtain the maximum temperature, the minimum temperature and the average temperature in the matrix;
judging whether the rectangle meets the following two conditions simultaneously:
(1) Based on the analysis of the minimum bounding rectangle, judging whether the rectangular area is larger than a set alarm threshold value;
(2) Adopting historical data analysis, calculating an average value in a period of time in a data sequence, smoothing the data, capturing a trend, judging whether the trend exceeds an alarm threshold, and if so, judging whether the maximum temperature is greater than the alarm threshold;
when the two conditions are met simultaneously, the cabinet is judged to generate flame.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311128805.XA CN117309159A (en) | 2023-09-04 | 2023-09-04 | Train cabinet flame early warning method based on infrared thermal imaging |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311128805.XA CN117309159A (en) | 2023-09-04 | 2023-09-04 | Train cabinet flame early warning method based on infrared thermal imaging |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117309159A true CN117309159A (en) | 2023-12-29 |
Family
ID=89272827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311128805.XA Pending CN117309159A (en) | 2023-09-04 | 2023-09-04 | Train cabinet flame early warning method based on infrared thermal imaging |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117309159A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117848515A (en) * | 2024-03-07 | 2024-04-09 | 国网吉林省电力有限公司长春供电公司 | Switch cabinet temperature monitoring method and system |
| CN117907790A (en) * | 2024-03-19 | 2024-04-19 | 青岛中微创芯电子有限公司 | IPM module aging monitoring method |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0949767A (en) * | 1995-08-09 | 1997-02-18 | Nippon Avionics Co Ltd | Infrared ray thermal image device |
| US20090262012A1 (en) * | 2008-04-16 | 2009-10-22 | Paul Carlson | Radiometer and temperature compensation system |
| KR20140017318A (en) * | 2012-07-31 | 2014-02-11 | 서울과학기술대학교 산학협력단 | Fire image recognition and pursuit method using kalman filter |
| CN104853064A (en) * | 2015-04-10 | 2015-08-19 | 海视英科光电（苏州）有限公司 | Electronic image-stabilizing method based on infrared thermal imager |
| US20150312488A1 (en) * | 2011-06-10 | 2015-10-29 | Flir Systems, Inc. | Techniques to compensate for calibration drifts in infrared imaging devices |
| CN105046868A (en) * | 2015-06-16 | 2015-11-11 | 苏州华启智能科技股份有限公司 | Fire early warning method based on infrared thermal imager in narrow environment |
| CN108998608A (en) * | 2018-07-24 | 2018-12-14 | 中南大学 | A kind of blast furnace iron notch molten iron temperature measurement method and system based on infrared machine vision |
| CN109061341A (en) * | 2018-07-10 | 2018-12-21 | 杭州安脉盛智能技术有限公司 | Kalman filtering transformer fault prediction technique and system neural network based |
| CN109871591A (en) * | 2019-01-24 | 2019-06-11 | 武汉大学 | A kind of method of IGBT power module estimation on line junction temperature |
| CN111366245A (en) * | 2020-03-12 | 2020-07-03 | 深圳达温技术服务有限公司 | Method for improving detection capability of infrared temperature measurement on abnormal heating |
| CN111982302A (en) * | 2020-08-24 | 2020-11-24 | 广东工业大学 | Temperature measurement method with noise filtering and environment temperature compensation |
| CN112798110A (en) * | 2020-12-29 | 2021-05-14 | 杭州晨安科技股份有限公司 | Calibration fitting-based temperature detection method for infrared thermal imaging equipment |
| CN113177467A (en) * | 2021-04-27 | 2021-07-27 | 上海鹰觉科技有限公司 | Flame identification method, system, device and medium |
| CN113758580A (en) * | 2021-09-27 | 2021-12-07 | 国网上海市电力公司 | Power transmission line on-line monitoring method and system based on infrared matrix monitoring |
| CN113959565A (en) * | 2021-09-29 | 2022-01-21 | 浙江双视红外科技股份有限公司 | Temperature measuring method of thermal infrared imager |
| WO2022087783A1 (en) * | 2020-10-26 | 2022-05-05 | 深圳市大疆创新科技有限公司 | Temperature drift correction method and apparatus for infrared thermal imager, infrared thermal imager, movable platform and computer-readable storage medium |
| CN115265806A (en) * | 2022-05-17 | 2022-11-01 | 蒙东协合扎鲁特旗风力发电有限公司 | Infrared thermal imaging temperature measurement compensation method, device and equipment |
| CN116007761A (en) * | 2022-09-15 | 2023-04-25 | 苏州世利安科技有限公司 | Intelligent infrared temperature measurement compensation method based on ambient temperature |
-
2023
- 2023-09-04 CN CN202311128805.XA patent/CN117309159A/en active Pending
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0949767A (en) * | 1995-08-09 | 1997-02-18 | Nippon Avionics Co Ltd | Infrared ray thermal image device |
| US20090262012A1 (en) * | 2008-04-16 | 2009-10-22 | Paul Carlson | Radiometer and temperature compensation system |
| US20150312488A1 (en) * | 2011-06-10 | 2015-10-29 | Flir Systems, Inc. | Techniques to compensate for calibration drifts in infrared imaging devices |
| KR20140017318A (en) * | 2012-07-31 | 2014-02-11 | 서울과학기술대학교 산학협력단 | Fire image recognition and pursuit method using kalman filter |
| CN104853064A (en) * | 2015-04-10 | 2015-08-19 | 海视英科光电（苏州）有限公司 | Electronic image-stabilizing method based on infrared thermal imager |
| CN105046868A (en) * | 2015-06-16 | 2015-11-11 | 苏州华启智能科技股份有限公司 | Fire early warning method based on infrared thermal imager in narrow environment |
| CN109061341A (en) * | 2018-07-10 | 2018-12-21 | 杭州安脉盛智能技术有限公司 | Kalman filtering transformer fault prediction technique and system neural network based |
| CN108998608A (en) * | 2018-07-24 | 2018-12-14 | 中南大学 | A kind of blast furnace iron notch molten iron temperature measurement method and system based on infrared machine vision |
| CN109871591A (en) * | 2019-01-24 | 2019-06-11 | 武汉大学 | A kind of method of IGBT power module estimation on line junction temperature |
| CN111366245A (en) * | 2020-03-12 | 2020-07-03 | 深圳达温技术服务有限公司 | Method for improving detection capability of infrared temperature measurement on abnormal heating |
| CN111982302A (en) * | 2020-08-24 | 2020-11-24 | 广东工业大学 | Temperature measurement method with noise filtering and environment temperature compensation |
| WO2022087783A1 (en) * | 2020-10-26 | 2022-05-05 | 深圳市大疆创新科技有限公司 | Temperature drift correction method and apparatus for infrared thermal imager, infrared thermal imager, movable platform and computer-readable storage medium |
| CN112798110A (en) * | 2020-12-29 | 2021-05-14 | 杭州晨安科技股份有限公司 | Calibration fitting-based temperature detection method for infrared thermal imaging equipment |
| CN113177467A (en) * | 2021-04-27 | 2021-07-27 | 上海鹰觉科技有限公司 | Flame identification method, system, device and medium |
| CN113758580A (en) * | 2021-09-27 | 2021-12-07 | 国网上海市电力公司 | Power transmission line on-line monitoring method and system based on infrared matrix monitoring |
| CN113959565A (en) * | 2021-09-29 | 2022-01-21 | 浙江双视红外科技股份有限公司 | Temperature measuring method of thermal infrared imager |
| CN115265806A (en) * | 2022-05-17 | 2022-11-01 | 蒙东协合扎鲁特旗风力发电有限公司 | Infrared thermal imaging temperature measurement compensation method, device and equipment |
| CN116007761A (en) * | 2022-09-15 | 2023-04-25 | 苏州世利安科技有限公司 | Intelligent infrared temperature measurement compensation method based on ambient temperature |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117848515A (en) * | 2024-03-07 | 2024-04-09 | 国网吉林省电力有限公司长春供电公司 | Switch cabinet temperature monitoring method and system |
| CN117848515B (en) * | 2024-03-07 | 2024-05-07 | 国网吉林省电力有限公司长春供电公司 | Switch cabinet temperature monitoring method and system |
| CN117907790A (en) * | 2024-03-19 | 2024-04-19 | 青岛中微创芯电子有限公司 | IPM module aging monitoring method |
| CN117907790B (en) * | 2024-03-19 | 2024-05-24 | 青岛中微创芯电子有限公司 | IPM module aging monitoring method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117309159A (en) | Train cabinet flame early warning method based on infrared thermal imaging | |
| CN111094956B (en) | Processing thermal imaging images with neural networks to identify subsurface erosion on insulation (CUI) | |
| US20220259947A1 (en) | Monitoring system and method for wellsite equipment | |
| US20070258807A1 (en) | Infrared-based method and apparatus for online detection of cracks in steam turbine components | |
| KR20130100266A (en) | Method for inspecting the quality of a solder joint | |
| CN115862259B (en) | Fire alarm early warning system based on temperature monitoring | |
| CN117274722B (en) | Intelligent detection method for distribution box based on infrared image | |
| CN111458036A (en) | Human body temperature measurement correction method and system based on multiple regression | |
| Guan et al. | Automatic fault diagnosis algorithm for hot water pipes based on infrared thermal images | |
| CN113056665A (en) | Detection and fault detection of corrosion under fire-resistant insulation using hybrid sensing system | |
| CN109900363A (en) | A kind of object infrared measurement of temperature method and apparatus based on contours extract | |
| Xu et al. | A lof-based method for abnormal segment detection in machinery condition monitoring | |
| CN109596226B (en) | Black body abnormity detection method, device, equipment and system for infrared thermal imaging temperature measurement system | |
| CN112927223A (en) | Glass curtain wall detection method based on infrared thermal imager | |
| CN116962669A (en) | Foreign matter removal system for monitoring equipment | |
| CN116630327B (en) | Boiler state abnormity monitoring system based on thermodynamic diagram | |
| CN116563283A (en) | Steam boiler gas leakage detection method and detection device based on image processing | |
| JP5279236B2 (en) | Target imaging detector | |
| CN113074651B (en) | Single-path laser ranging tunnel deformation monitoring system and method | |
| JPH06201625A (en) | Apparatus and method for searching defect | |
| CN111971581A (en) | Device, method and computer program product for verifying data provided by a rain sensor | |
| CN113405664B (en) | Temperature measurement method, temperature measurement equipment and machine-readable storage medium | |
| US20230125890A1 (en) | Image analysis system, image analysis method, and image analysis program | |
| KR102032481B1 (en) | Apparatus and method for radar system diagnosis using terrestrial echo | |
| TWI662509B (en) | Development of a disdrometer and particle tracking process thereof |
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 |