BE1029794B1 - Process for automatic wear monitoring and anomaly detection of refractory linings in coke ovens - Google Patents

Abstract

The present invention relates to a method for detecting defects in a refractory lining in a chemical reaction chamber, in particular a coke oven, the method having the following steps: a) acquiring at least one first image of the inside of the refractory lining, b) performing an image analysis at least a first image for detecting defects, c) outputting potential defects.

Description

' BE2021/5752

Process for automatic wear monitoring and anomaly detection of refractory linings in coke ovens

The invention relates to a method for detecting defects in the refractory

Lining of a coke oven.

Coke ovens have chambers that are several 10 cm wide, for example 40 to 50 cm, and several meters long and several meters high

meters. These chambers are operated in a temperature range of up to 1800 °C, for example. The walls are made of refractory bricks. This

Walls can show a variety of damage over time. In the worst case, holes, cracks or gaps can lead to an undesired gas exchange between the oven chamber and heating wall, which occurs during the process, and this gas could then be released into the environment unintentionally and uncontrolled. It is important to prevent this. In addition, repairs become disproportionately more complex and expensive when the defects become larger. It is therefore expedient to identify defects at an early stage and rectify them before substances reach the

Environment are given or the repair effort is disproportionately high.

EP 2 113 552 A1 discloses a device for inspecting wall surfaces

known coke ovens.

From JP 2016 065 225 A is a device for the automatic detection of

Carbon buildup known in a coke oven.

From the subsequently published DE 10 2021 101 102 is an aircraft and a method for

Inspection of facilities of coking plants for the detection of sources of error known.

Wall damage can only be inspected when the coke oven door is open.

For operational reasons, the coke oven cannot be switched off, which means that an inspection takes place when the coke oven is hot. one of the

Problems with visual inspection is the temperature inside the

coke oven chamber. For a person standing in front of an opening, this already represents one

Exposure. There is also exposure to escaping chemical substances.

At the same time, the tunnel-shaped character makes visual inspection difficult. A qualified inspection usually requires a great deal of experience, which in turn reduces the number of people with the necessary qualifications. If then still

Travel restrictions, for example due to a pandemic, can be added

Verification can be extremely difficult.

The object of the invention is to provide a method for the reliable and early diagnosis of

to provide defects in a refractory lining. The same should

Occupational safety for the people involved is increased and delays in the ongoing operating process are kept as short as possible by inspection.

This object is achieved by the method specified in claim 1

characteristics. Advantageous developments result from the dependent claims, the following description and the drawings.

The method according to the invention serves to detect defects in a refractory

Cladding in a chemical reaction chamber, in particular a coke oven. The

However, the process is also applicable to other chemical reaction spaces with a refractory

lining applicable. Examples are rotary kilns, steam reformers,

Syngas reformers, reactors, boilers, steam and off-gas lines, after-treatment furnaces,

called melting furnaces, fireplaces and chimneys. The method is particularly suitable for a reactor for continuous operation. After emptying and before renewed

Filling can be performed at operating temperature, eliminating the need to shut down and cool down the reactor for inspection. The coke oven is particularly suitable for this process. On the one hand, a coke oven is usually made of masonry, which can result in different types of damage than, for example, a refractory-lined oven case. On the other hand, several coke ovens are usually set up next to each other in a battery, so that the failure and repair of one

coke oven can have an immediate impact on all other coke ovens in the battery. Furthermore, the geometry of the coke ovens is such that the individual

Coke oven chambers are comparatively long, tall and narrow, for example one

More than 10 m in length and half a meter wide. At an operating temperature in the range of 1000 °C to 2000 °C, there is a difficulty in inspection due to the geometry and the temperature load, but at the same time there is also a need for regular inspection of the system for the reasons already discussed above.

The method comprises the following steps: a) acquiring at least a first photograph of the inside of the refractory

Disguise, b) performing an image analysis of at least one first image for the detection of

defects, c) outputting potential defects

The detection in step a) takes place from outside the chemical reaction space.

The detection preferably takes place through an opening, in particular through an opening which is used in regular operation, for example to introduce educt,

to deploy product or to bring in or deploy work equipment. At the

In the example of the coke oven, two openings are particularly relevant for the implementation of the method. Firstly, the opening through which the coke is removed from the coke oven (coke side). On the other hand, the opening through which the coke is pressed out of the coke oven (machine side). The openings for supplying the educt coal, which are arranged above, are not suitable because they are through the located there

Coal are not accessible in regular operation. Alternatively, of course, you can

maintenance hatches or windows are used. It is better, however, if openings are used, which are used in regular operation anyway, as this

operation is less disturbed.

The detection in step a) can take place by taking a picture with a camera. But it can also be a plurality of recordings with a camera or a recording of a

majority of recordings with multiple cameras are used. Will a multi-

Camera system used, so these are preferably fixed to each other, for example, with a tripod in a fixed spatial arrangement, thereby superimposing the

' BE2021/5752

Recordings for generating an image of the chemical reaction space, in particular the coke oven, is simplified.

The detection in step a) can be done by taking a picture with a light field camera.

A light field camera, also known as a plenoptic camera, has the advantage that a

Focusing does not take place before the recording, but the different focal planes can be calculated from the captured recording. As a result, in chemical reaction spaces at great depths, such as in particular coke ovens, rapid and consistently sharp detection can be carried out in a simple manner.

The detection in step a) can be done by recording with a laser scan system. Here, the surface is usually scanned line by line and column by column. Therefore, recording with such a scanning system is comparatively slow compared to a camera that records all information at the same time. On the other hand, the size of the laser point allows more precise scanning and, if necessary, more information can be obtained.

Capturing in step a) can take place by means of a freehand recording with a camera. This has the advantage that it is comparatively simple. But the spatial arrangement is not reproducible. Therefore, in the case of freehand photography, it is advantageous to take more photographs and then stitch them together to obtain an image of the entire refractory lining.

The detection in step a) can take place by taking a picture with a camera which is reproducibly positioned in a predefined position in front of an opening, for example by means of a tripod. This has the advantage that the spatial arrangement of the

Image and thus the determination of the position of defects is simplified. For this purpose, at the opening or near the opening, attachment points for the tripod and

Installation marks for the tripod can be arranged.

The capturing in step a) can take place in particular with a focal length between 25 mm and 75 mm based on the 35mm format. Correspondingly shorter focal lengths result for smaller sensors, and correspondingly longer focal lengths for larger sensors. As

In terms of sensor size, a sensor with 20 to 200 megapixels is preferred, on the one hand

) BE2021/5752 to have sufficient resolution and on the other hand to limit the amount of data to be processed.

Does the chemical reaction room, especially the coke oven, have two or more

openings, photographs are preferably taken of both or all openings.

For the purposes of the invention, the image includes at least two-dimensional information of at least one intensity distribution. An image created using a commercially available

camera has three color channels, each of which has a two-dimensional intensity distribution (brightness). In order to expand the range of information, more than just three color channels can also be recorded, for example through additional recordings with an IR camera (usually commercially available cameras without

IR blocking filter and a VIS blocking filter) or a thermal imaging camera. However, images can also be composed of individual recordings (which also represent images within the meaning of the invention). For example, through

Composing (stitching) a larger panorama image can be assembled from several shots. Likewise, for example, from a variety of

A three-dimensional image can be generated from recordings by means of photogrammetry, with such an image strictly speaking only showing a two-dimensional surface, but with the spatial structure in three-dimensional space. In the context of the invention, the term recording is therefore used for an unchanged image (image from the camera,

Original image, unprocessed image) is used.

Thus, the first image in step b) can be the same as the first recording in step a) if the first recording is used unchanged as the first image. Alternatively, the first

Image can be generated from the first recording, for example by combining it with other recordings. Thus, the first picture is equal to the first shot or the first

Image is generated from the first shot.

An image analysis is carried out with the help of a self-learning algorithm.

Carrying out an image analysis has the following partial steps: b1) a feature map is created with a first neural network

° BE2021/5752 b2) the areas of potential interest in the feature map with a

area proposal network are examined, identifying areas which could contain an anomaly, generating anchor boxes, b3) with a second neural network in the anchor boxes, an alignment of a

target area is performed in each anchor box, b4) using a multivariate clustering algorithm, the severity of each anomaly in each anchor box is analyzed and it is recognized which anomalies are defects.

Instead of the term feature map, the terms feature mapping or

Feature tableau familiar, but especially the English term feature map.

To put it very simply, the creation of the feature map in step b1) is a selection of potentially interesting areas, for example rectangular areas within the image, which can contain “something”. No statement is made here as to whether the potentially interesting area actually contains something or what it contains. It just becomes potentially interesting

Areas selected, which are subjected to further, more detailed analysis.

As a result, areas that obviously contain nothing are the first to be removed from further evaluation, thus reducing the amount of data. At the same time, the size of the potentially interesting areas in the feature map is smaller than the image itself, so that you only have to work with a significantly reduced amount of data in each potentially interesting area. The feature map therefore only contains the potentially interesting areas.

In step b2), the potentially interesting areas of the feature map are now examined. An area proposal network is used for this. Instead of

The term area proposal network is also known as region proposal network, network for the proposal of regions, but especially the English term

Region Proposal Network.

An anchor box is an area, such as a rectangular area, containing a

contains anomaly. In this step, all potentially interesting areas of the feature map are sorted out, which ultimately do not contain any anomalies.

' BE2021/5752

The alignment performed with a second neural network in the

Anchor boxes of a target area in each anchor box in step b3), put simply, is the selection of the pixels of the image that belong to the anomaly. This eliminates all pixels that show something else within the anchor box, i.e. in particular undamaged refractory cladding. This will create a final

Achieved focusing solely on the anomaly.

After the anomalies have been clearly delimited in this way, the severity of each anomaly in each anchor box is analyzed in step b4) using a multivariate clustering algorithm. This also recognizes which anomalies are defects. Here is the

position of the anomaly. An anomaly with, for example, 100 pixels

A size that is very close to the opening and thus to the camera is of course to be assessed differently in terms of severity than the same anomaly that is in the same image but at a position, for example 5 m deep inside the chemical reaction chamber , in particular the coke oven, and their real

Size is correspondingly larger with the same size in the image of 100 pixels, for example. This would significantly increase the severity of the defect inside.

In a refractory lining in the form of masonry, for example, the

Structure of the masonry in the image can be used to scale the size. This is particularly possible if the recordings are always from a reproducible

Location can be made and there is a first recording without defects, for example after construction or renovation. In this way, for example, in the case of buildup, the size of the area can be easily estimated by the size of the bricks visible in the "original image".

In a further embodiment of the invention, the detection in step a) and the image analysis in step b) are carried out separately. In particular, before the analysis, the image data is sent to a

Transfer server, which is designed to carry out the image analysis in step b).

Other transmission methods, for example via satellite communication or Bluetooth, can also be used, as well as transmission via USB stick or

CD/DVD. To avoid transport times, digital transmission methods are preferred as far as possible.

° BE2021/5752

In a further embodiment of the invention, the detection in step a) takes place with different focal lengths. For example, the areas close to the capture device (the camera) are recorded with a focal length between 20 mm and 50 mm in relation to the 35mm format. The areas further from the recording device (the camera) are recorded with a longer focal length, for example between 75 mm and 300 mm in relation to the 35mm format. Correspondingly shorter focal lengths result for smaller sensors, for larger ones

Sensors correspondingly longer. The different focal lengths result in different angular resolutions, which are preferably due to the different

Distance to the sensor then returns to a comparable resolution of the refractory

lead disguise.

In a further embodiment of the invention, the first neural network is a convolution-based neural network. The common English-language term for a convolution-based neural network is convolutional neuronal network. Compared to conventional neural networks, the convolution-based neural

Network for the creation of the feature map due to the high accuracy and

Processing speed turned out to be particularly suitable.

In a further embodiment of the invention, the first neural network is by means

A priori knowledge trained. For this purpose, images are used which have been evaluated by a specialist, where defects are marked, labeled and given their severity. The larger this starting data situation is, the more reliable the first neural

network work. This also applies to the second neural network and the multivariate clustering algorithm. Everyone is preferably trained with this a priori knowledge. This training enables the system to reliably identify and classify defects right from the start.

Alternatively, the system can also be integrated into a new or newly renovated system, for example, and the first recordings can thus be classified as free of defects. It is true that the system is then initially unable to identify defects and assess their severity. However, images in which deviations occur are then presented to an expert, for example, who then carries out the assessment. On

) BE2021/5752 in this way then learns the system with the appearance of the first anomalies. The disadvantage is that the system is heavily dependent on support at the beginning, but no a priori knowledge is required for this, but regular intervention by the specialist.

In a further embodiment of the invention, the detection in step a) takes place in the

Operating temperature of the chemical reaction chamber, especially the coke oven.

Fluctuations are of course possible. If, for example, a coke oven is opened and the coke is ejected, ambient air naturally reaches the walls and cools them down, in contrast to the time when the coke oven is closed. such

Fluctuations, however, occur during normal operation with each opening and are therefore understood as the operating temperature within the meaning of the invention.

In a further embodiment of the invention, the detection in step a) takes place in a spectral range from 350 nm to 1700 nm, preferably in a spectral range from 350 nm to 1100 nm, particularly preferably in a spectral range from 350 nm to 800 nm. For the range from 350 nm to 1100 nm, a Si

semiconductors are used, for the range from 1100 nm to 1700 nm an InGaAs

Semiconductor. For example and preferably, the detection can take place by means of a CCD sensor or a CMOS sensor. In this case, the detection does not have to take place completely over the entire spectral range and it does not have to take place in a spectrally resolved manner.

It can be captured as a pure black and white image. However, one is preferred

Detection as in commercially available camera systems in the three primary colors with overlapping sensitivity ranges and thus completely over the visible

spectrum performed. To make matters worse, however, that, for example, at a

Temperature around 2000 °C the maximum of the black beam is between 1200 and 1300 nm. Especially a spectrally non-resolving sensor in the NIR range may have difficulties in capturing details if the

dynamic range of the sensor reaches its limits.

In a further embodiment of the invention, the detection in step a) takes place with a multi-camera system. As already explained above, it is advantageous if the multiple cameras are in a fixed spatial relationship to one another. This can be done, for example, by mounting it on a common tripod.

In a further embodiment of the invention, the detection in step a) takes place with a moving image camera, for example a video camera. By using a

The moving image camera has the advantage that, due to the large number of images, a good

There is an overlap between two consecutively recorded images. In this case, the film sequence consists of the recordings. Therefore, from such

Film sequence easily a first image can be generated. Since it is so easy to create comparatively easy-to-combine recordings, this can also be easily done by those who are not trained

personnel are recorded. Advantageously, a first conversion takes place

Recordings then as soon as possible after the recording, especially if the first image is then sent to a

Server for carrying out step b) is transmitted. This allows a significant

data reduction can be achieved.

In a further embodiment of the invention, a large number of images are recorded in step a) and these are combined by means of photogrammetry to form a virtual image of the chemical reaction space, in particular of the coke oven.

In addition to the recordings, a model of the chemical

Reaction space, in particular the coke oven, are used. As a result, a particularly good spatial assignment of the pixels is generated, resulting in a subsequent

Localization, an indication of the position of the defects is facilitated. That means

Virtual image created by photogrammetry is then analyzed in step b).

In a further embodiment of the invention, the detection in step a) takes place through at least one first opening and one second opening of the chemical

Reaction space, in particular the coke oven. In the case of the coke oven, one opening is the so-called machine side, on which the coke is pushed out of the oven by a machine. The other opening is this opposite the opening from which the

Coke exits the coke oven. By recording from both sides, the distance between the camera and the defect is halved at most, especially for the inner area

limited in length, which makes sense given the tunnel-like geometry of the coke ovens.

In a further embodiment of the invention, each image in which a specific defect cannot be clearly identified in step b4) is sent to a person skilled in the art

decision submitted. On the one hand, this allows the system to continuously learn. On the other hand, this eliminates the need for manual intervention by the

Expert reduced to a minimum. This step is inherently slow and on the

Limited availability of a specialist. Accordingly, this is preferred by the

Expert classified image used to train the multivariate clustering algorithm. Usually only the trained anomalies can be recognized by the a priori knowledge. A specific effect is therefore presented, for example, if it cannot be clearly assigned to a type of anomaly, for example if the probabilities for two different types are of the same order of magnitude. By resorting to the expert, a clear assignment can then be made. However, if a new type of defect is actually found, it can also be trained on this basis.

In a further embodiment of the invention, the output in step c) takes place in the case of minor defects with a prognosis as to when a serious defect is to be expected. In this way, in particular, a decision can be made as to whether an immediate repair is necessary or whether it is necessary to wait until the next repair

maintenance cycle is still possible. This prognosis is all the more reliable the more regularly this method is carried out on the device in question, so that a development over time is preferably already known, which is

Data basis can be used for the forecast.

In a further embodiment of the invention, the outputting in step c) comprises the

Type of defect, the severity of the defect, and the location of the defect. This information can be provided in tabular form, but preferably also graphically. More preferably, there is one

Output in such a way that the chemical reaction space, in particular the coke oven, is divided into different segments and all defects for each segment are output cumulatively. This results in segments that also contain smaller ones

Defects accumulate and thus indicate a possibly larger problem overall.

In a further embodiment of the invention, the severity of the

defect in step c) in three to five degrees of severity. If three degrees of severity are distinguished, these can be, for example, good, moderate and critical. Will be five

Different degrees of severity, these can be, for example, good, easy, moderate, critical and fatal. Critical means, for example, that an immediate repair is necessary, fatal that further operation is impossible for safety reasons.

However, the classification of the degrees of severity can, for example, also be based on a forecast of the remaining operating time, ie for example >1 year, >1 month, >1 week and <1 week.

In a further embodiment of the invention, the output in step c) takes place cumulatively for all defects within the chemical reaction space, in particular the

coke oven, and an assessment is made on the basis of any defects detected for one

identified repair needs.

In a further embodiment of the invention, the outputting includes defects selected from the list of broken edge, spalling, deposit, breakthrough point, ceramic weld point, joint widening.

In a further embodiment of the invention, a

Feature map in step b1) on the one hand on the basis of simple structures, such as

Color intensity, shading, geometry, corners and edges. On the other hand, more complex features are also taken into account that can be characteristic of the respective anomalies, such as alignment, extent, or recurring patterns.

In a further embodiment of the invention, the method is repeated, wherein the repetition interval is selected from the group at each opening, daily, weekly, monthly, quarterly, annually. On the one hand, a continuous check makes it easier to find changes, on the other hand, a forecast for the remaining operating time can be made more well-founded the shorter the interval is.

In a further embodiment of the invention, the image analysis in step b) takes into account other images which were previously from the same location of the chemical

Reaction space, in particular the coke oven, were recorded.

The method according to the invention is explained in more detail below with reference to an exemplary embodiment illustrated in the drawings.

1 wall

Fig. 2 Wall with first defects

Fig. 3 Wall with first defects and anchor boxes

Fig. 4 Wall with anchor boxes and analyzed anomalies

Fig. 5 Wall with second defects

Fig. 6 Wall with second defects and anchor boxes

Fig. 7 Wall with anchor boxes and analyzed anomalies

For the sake of simplicity, a piece of masonry is shown in the figures as a section of a refractory lining. Defects are shown very large for clarity. The figures are therefore only to be understood as sketchy and schematic.

In Fig. 1 a perfect refractory lining without defects is shown. This picture would emerge, for example, immediately after the construction of a coke oven. This image is an example of a side wall in a coke oven, where the angle would be even steeper towards the back. For clarification, however, the angle is chosen here so that the

The principle of the method can be seen better. For convenience, ceiling and

Floor and opposite wall omitted. A real recording would create a tunnel-like impression.

Fig. 2 shows the same wall with first defects. In the rear area, a breakthrough is indicated schematically by the omission of four bricks, in the front area attachment to the wall in the form of a hatched circle. 3 shows the wall with the first defects after step b2). Two anchor boxes show the two

Regions where defects are located. After step b3) the image shown in FIG. 4 results. The second neural network detects the two defects down to the pixel, indicated by the overlying small shaded areas.

5 shows the wall with second defects. The only difference is that these are closer together. As a result, the anchor boxes are partially overlapping, as shown in FIG. Nevertheless, in step b3) the pixel-precise analysis of the

Defects as shown in Fig. 7.

Claims (19)

patent claims 1. A method for detecting defects in a refractory lining in a chemical reaction chamber, in particular a coke oven, the method having the following steps: a) acquiring at least one first recording of the inside of the refractory lining, b) performing an image analysis of at least one first image for detecting defects, Cc) outputting potential defects, with the detection in step a) being carried out from outside the chemical reaction chamber, with carrying out an image analysis using a self-learning algorithm, with carrying out an image analysis having the following sub-steps: b1) with a first neural network a feature map is created b2) the areas of potential interest in the feature map are examined with an area suggestion network, with areas being identified which could contain an anomaly, with anchor boxes being generated, b3) with a second neural network in the anchor boxes an alignment of a target area is performed in each anchor box, b4) using a multivariate clustering algorithm, analyzing the severity of each anomaly in each anchor box and identifying which anomalies are defects. 2. The method according to claim 1, characterized in that the first neural network is a convolution-based neural network. 3. The method according to claim 2, characterized in that the first neural network is trained using a priori knowledge. 4. The method according to any one of the preceding claims, characterized in that the detection in step a) takes place at the operating temperature of the chemical reaction chamber, in particular the coke oven. 5. The method as claimed in any of the preceding claims, characterized in that the detection in step a) takes place in a spectral range from 350 nm to 1700 nm, preferably in a spectral range from 350 nm to 1100 nm. 6. The method according to any one of the preceding claims, characterized in that the detection in step a) takes place with a multi-camera system. 7. The method according to any one of the preceding claims, characterized in that the detection in step a) is carried out with a video camera. 8. The method according to any one of the preceding claims, characterized in that in step a) a large number of recordings are recorded and these are combined by means of photogrammetry to form a virtual image of the chemical reaction space, in particular of the coke oven, the virtual image created by means of photogrammetry in Step b) is analyzed. 9. The method according to any one of the preceding claims, characterized in that the detection in step a) takes place through at least a first opening and a second opening of the chemical reaction chamber, in particular the coke oven. 10. The method as claimed in one of the preceding claims, characterized in that each image in which a specific defect cannot be clearly identified in step b4) is presented to a specialist for a decision. 11. The method as claimed in claim 10, characterized in that the image classified by the expert is used to train the multivariate clustering algorithm. 12. The method according to any one of the preceding claims, characterized in that the output in step c) in the case of minor defects takes place with a prognosis as to when a serious defect is to be expected. 13. The method according to any one of the preceding claims, characterized in that the output in step c) includes the type of defect, the severity of the defect and the position of the defect. 14. The method according to any one of the preceding claims, characterized in that the output of the severity of the defect in step c) takes place in three to five degrees of severity. 15. The method according to any one of the preceding claims, characterized in that the output in step c) is carried out cumulatively for all defects within the chemical reaction space, in particular the coke oven, and an evaluation based on all detected defects for a need for repair is determined. 16. The method according to any one of the preceding claims, characterized in that the output includes defects selected from the list of broken edge, spalling, deposit, breakthrough point, ceramic weld point. 17. The method as claimed in one of the preceding claims, characterized in that a feature map is created in step b1) on the basis of color intensity, shading and geometry. 18. Method according to one of the preceding claims, characterized in that the method is repeated, the repetition interval being selected from the group on each opening, daily, weekly, monthly, quarterly, annually. 19. The method as claimed in one of the preceding claims, characterized in that the image analysis in step b) takes into account other images which were previously captured from the same location in the chemical reaction space, in particular the coke oven.