Based on the recognition methods of equipment Leakage Gas and the device of infrared detection
Technical field
The present invention relates to power equipment fortune inspection industry, particularly relate to a kind of equipment Leakage Gas recognition methods based on infrared detection and device.
Background technology
Due to SF
6gas has excellent arc extinguishing and insulating property, has been widely used at present, in high-voltage switch (isolating switch, on-load switch), playing arc extinguishing effect.But due to factors such as aging, manufactures, SF
6leakage Gas has become one of defect common in Cubicle Gas-Insulated Switchgear operational process.SF
6the leakage of gas not only can affect the dielectric strength of equipment, also produces stronger greenhouse effect by atmospheric environment.In addition, gas leakage also causes potentially danger to field personnel, threatens the safety and health of personnel, even causes major accident.Therefore SF
6leakage inspection identification work is extremely important.
Along with the development of detection technique, according to SF
6the self-characteristic of gas extends multiple leakage detection method.But, adopt the various leak detection technologies of different operating principle to have self advantage and deficiency in prior art.The device structure of negative corona detection technique is simple, cost is low, but test disturbing factor is more, poor anti jamming capability and sensor life-time is short.Electron capture detection technology is very effective to possessing electronegative species analysis, but this kind of technology uses radioactive source and high pressure carrier gas bottle, cannot meet quick and safe test request.Negative ion Acquisition Detection technology and electron capture know-why similar, but its cost is high, reaction is slow.Though ultraviolet ionization detection technology structure is simple, corresponding speed is fast, poor to leakage position positioning performance, and metrical error is large with environmental change, is difficult to accomplish accurate orientational and quantificational detection.Infrared absorption technology is based on SF
6gas, to the characteristic absorption principle of infrared spectrum, is a kind of method of direct measure gas concentrations, can reflects SF
6the real content of gas.But detection sensitivity is not high, response speed is slow, and this also just constrains its widespread use in electric system is quantitatively hunted leak.
The SF6 Leakage Gas optical imagery detection technique being representative with laser imaging detection technique and IR Thermograph, utilizes SF
6gas is to the strong absorption characteristic of infrared spectrum, the SF6 gas that naked eyes can not be observed directly is visible on infrared video, for testing staff provides a kind of technology of quick identified leakage source, this technology has now become a kind of ripe effective live testing means and has at home and abroad been widely applied.But simple employing infrared imaging detects, and cannot carry out online Macro or mass analysis, can not play the value of data to failure message.
Summary of the invention
For solving the deficiency that prior art exists, the invention discloses the equipment Leakage Gas recognition methods based on infrared detection and device, the method is by infrared detection means, acquisition equipment infrared detection image, upload to main website analysis platform on the spot, analysis platform processes data, identify, analyze, identification equipment Leakage Gas and position thereof, and then reports to the police.
For achieving the above object, concrete scheme of the present invention is as follows:
Based on the equipment Leakage Gas recognition methods of infrared detection, comprise the following steps:
Step one: detecting unit adopts infrared detection technology to obtain the infrared imaging image of electrical equipment;
Step 2: to the SF of generation collected
6the equipment drawing picture of Leakage Gas carries out gradation conversion, obtains the accumulation histogram that Leakage Gas original image occurs;
Step 3: adopt mean filter to SF
6the accumulation histogram filtering of Leakage Gas original image, replaces SF by average
6each pixel value in Leakage Gas original image;
Step 4: adopt frame differential method that every two two field pictures in the filtered image sequence obtained in step 3 are carried out difference, this grey scale difference image of binaryzation is to extract movable information, setting threshold value, the pixel meeting threshold value the most at last highlights, and identifies SF
6leakage Gas feature, with dynamic-form by SF
6leakage Gas movement locus shows.
Further, in step one, infrared radiation detection apparatus is adopted to detect electrical equipment image information.
Further, in step 2, gradation conversion method is: establish n
ifor i-th gray-level pixels number in original image, n is pixel count all in original image, to be then the probability of occurrence of the pixel of i be gray scale:
P(i)=n
i/n,i=0,1,…,N-1;
In formula, P (i) is the histogrammic probability distribution of original image, and N is all number of greyscale levels in original image, N≤256;
Histogram equalization is, by cumulative distribution function, the gray level i of original image is mapped to the accumulation histogram that new gray level C (i) namely defines original graph;
parameter j is progressive whole number from 0.
Further, in step 3, the method that mean filter adopts is neighborhood averaging: be the template of point selection centered by current pixel point (x, y), this template is made up of its adjacent some pixels, the average of all pixels in seeking template, current pixel point (x, y) is given again, as image gray scale g (x at that point after process this average, y), namely
In formula, s is template, and M is the total number of pixel comprising current pixel in this template, and f function is that the two-dimensional matrix of image represents, f (x, y) is each matrix element.
Further, in step 4, frame differential method: the gray-scale value of two two field picture corresponding pixel points before and after in movement images sequence, by two frame subtract, if subtract each other difference to be less than difference binary-state threshold, thinks that this point passes through without moving object; Otherwise difference is greater than difference binary-state threshold, then think there is object process, kth frame and k+1 two field picture f
k(x, y), f
k+lchange between (x, y) represents with two-value difference image D (x, y):
In formula, T is difference binary-state threshold.
A kind of equipment Leakage Gas recognition device based on infrared detection, comprise infrared detection unit, described infrared detection unit is for detecting power equipment infrared data, and the data message utilizing infrared detection unit to get wirelessly transfers to the main website of supervisory system;
Described main website comprises main control unit, described main control unit comprises signal processor, pattern recognition module and leaks warning module, in signal processor, the infrared imaging information uploaded by infrared detection unit is according to color or gray shade scale, convert it into thermal-induced imagery, pattern recognition module adopts image processing techniques to thermal-induced imagery further, utilizes gray proces, mean filter denoising, inter-frame difference method to original SF
6leakage Gas infrared detection image carries out digitized image feature extraction, the video image of gas leakage region will produce changes in contrast, thus produce smoke-like shade, leak warning module and source of leaks and moving direction are carried out alarm and shown at display unit.
Further, described infrared detection unit comprises optical system and infrared eye, wherein, the infrared radiation that optical system in infrared detection unit mainly sends in order to receiving target object is also focused on infrared eye, infrared eye induction through the infrared radiation of optical system, and is converted into electric signal.
Beneficial effect of the present invention:
1. the invention provides monitoring method real-time online, avoid fortune inspection personnel on site operation, and keep enough distances with high voltage alive equipment, ensure that personal safety.
2. infrared detection can detect and avoid traditional pointwise detection method in the blind spot position that classic method cannot be touched simultaneously, improves fortune inspection efficiency.
3. detection data are carried out Macro or mass analysis comparison in main website by the present invention, can find leakage position, improve fault propagation graph.
Accompanying drawing explanation
Fig. 1 workflow diagram;
Fig. 2 SF
6leak infrared detection image;
Histogram after Fig. 3 image equilibration;
The average of Fig. 4 neighbor replaces the schematic diagram of original pixel value;
Fig. 5 identification Leakage Gas collection of illustrative plates;
Fig. 6 device workflow diagram.
Embodiment:
Below in conjunction with accompanying drawing, the present invention is described in detail:
Workflow diagram of the present invention as shown in Figure 1, adopts the SF based on image procossing
6the recognition methods of Leakage Gas line model, extract Leakage Gas feature, ONLINE RECOGNITION Leakage Gas and leakage point thereof, realize SF
6leakage Gas on-line automatic identification.
The ultimate principle of image recognition adopts gray proces, mean filter denoising, inter-frame difference method to original SF
6leakage Gas optical detection image carries out digitized image feature extraction, with dynamic-form by SF
6leakage Gas movement locus shows, and realizes, by the transformation of artificial cognition to identification automatically, increasing work efficiency and diagnosis accuracy.
As shown in Figure 2, SF
6the background colour of Leakage Gas original video is darker, the contrast of object and background is less, signal to noise ratio (S/N ratio) is lower, follow the tracks of if directly carry out, catch often more difficult, so first carry out the process such as gradation conversion and medium filtering to picture signal, to reach Background suppression Noise enhancement target strength, to improve the object of signal noise ratio (snr) of image.
Gradation conversion adopts the method for histogram equalization, the form that the histogram transformation of original image uniformly distributes, adds the dynamic range of grey scale pixel value, thus makes the intensity profile of image even, and contrast increases, and details is more clear.If n
ifor i-th gray-level pixels number in original image, n is pixel count all in original image, then gray scale is the probability of occurrence of the pixel of i is P (i)=n
i/ n, in formula, P (i) is the histogrammic probability distribution of original image.Histogram equalization the gray level i of original image is mapped to the accumulation histogram that namely new gray level defines original graph, shown in Fig. 3 by cumulative distribution function.
Mean filter is also referred to as linear filtering, and its main method adopted is neighborhood averaging.Its ultimate principle is each pixel value substituted by average in original image, namely to pending current pixel point (x, y), select a template, this template is made up of some pixels of its neighbour, the average of all pixels in seeking template, current pixel point (x, y) is given again, as image gray scale g (x at that point after process this average, y), namely
wherein, s is template, and M is the total number of pixel comprising current pixel in this template.
When template refers to a certain pixel in processing array, formulate centered by this pending pixel, comprise the little N*N matrix of of adjacent pixels, a template that Here it is, replaces the method for original pixel value, as shown in Figure 4 by the average of the entire pixels in template.
Frame differential method carries out difference with the two continuous frames image in image sequence, and then this grey scale difference image of binaryzation extracts movable information.It is the difference by front and back two two field picture corresponding pixel points gray-scale values in movement images sequence, by two frame subtract, if gray-scale value is very little, can think that this point passes through without moving object; Otherwise grey scale change is very large, then think and have object to pass through.Kth frame and k+1 two field picture f
k(x, y), f
k+lchange between (x, y) represents with two-value difference image D (x, y).
t is difference binary-state threshold.
As shown in Figure 5, the pixel meeting threshold value the most at last highlights, and identifies SF
6leakage Gas feature.
As shown in Figure 6, be the structural representation of apparatus of the present invention, information receiver, for receiving the power equipment infrared detection data that infrared sensor is uploaded.The infrared radiation that optical system wherein in infrared detection unit mainly sends in order to receiving target object is also focused on infrared eye.Infrared eye induction through the infrared radiation of optical system, and is converted into electric signal.The information utilizing infrared detection unit to get wirelessly is connected with the main website of supervisory system, and wherein radio communication adopts ModBus-RTU communication protocol.
Detection data are carried out Macro or mass analysis in main website by the analytic unit of main website, find to identify Leakage Gas.Wherein the main control unit of main website is provided with information receiver, information-storing device, signal processing apparatus, and line model identification module and leak prior-warning device.By the infrared imaging information that information receiver reception infrared detection unit is uploaded, and be stored in information-storing device, by signal processing apparatus (signal processor) according to color or gray shade scale, convert it into thermal-induced imagery.The pattern recognition module of main control unit, adopts image processing techniques, utilizes gray proces, mean filter denoising, inter-frame difference method to original SF
6leakage Gas infrared detection image carries out digitized image feature extraction, and the video image of gas leakage region will produce changes in contrast, thus produces smoke-like shade.Gas concentration is larger, and absorption intensity is larger, and smoke-like shade is more obvious, thus makes sightless SF
6leakage Gas becomes visible, and then determines its source of leaks and moving direction, leaks prior-warning device alarm and is shown by display unit, making testing staff find leakage point fast and accurately, realize long-range monitoring.
By reference to the accompanying drawings the specific embodiment of the present invention is described although above-mentioned; but not limiting the scope of the invention; one of ordinary skill in the art should be understood that; on the basis of technical scheme of the present invention, those skilled in the art do not need to pay various amendment or distortion that creative work can make still within protection scope of the present invention.