CN117168630A

CN117168630A - Fault detection method and system for air pressure sintering furnace

Info

Publication number: CN117168630A
Application number: CN202311442474.7A
Authority: CN
Inventors: 姚尚兵; 张光远
Original assignee: Jiangsu Haoyue Vacuum Equipment Co ltd
Current assignee: Jiangsu Haoyue Vacuum Equipment Co ltd
Priority date: 2023-11-01
Filing date: 2023-11-01
Publication date: 2023-12-05
Anticipated expiration: 2043-11-01
Also published as: CN117168630B

Abstract

The application provides a fault detection method and a fault detection system for an air pressure sintering furnace, and relates to the technical field of fault detection, wherein the method comprises the following steps: obtaining a heating area thermal image sequence of a first time zone; receiving desired temperature information for a first time zone; obtaining a first temperature anomaly region and a first temperature health region; carrying out temperature fluctuation analysis on the first temperature health area to generate a temperature fluctuation coefficient; when the temperature fluctuation coefficient is greater than or equal to the temperature fluctuation coefficient threshold value, generating a second temperature abnormal region; the temperature control elements in the first temperature abnormal region and the second temperature abnormal region are subjected to fault identification and sent to the air pressure sintering furnace control terminal, the technical problems that the traditional fault detection needs to be stopped for element-by-element fault detection and the detection efficiency is poor are solved, the air pressure sintering furnace is subjected to temperature deviation analysis, the temperature control elements with the fault identification are provided for fault detection, and the technical effect of improving the fault detection efficiency is achieved.

Description

Fault detection method and system for air pressure sintering furnace

Technical Field

The application relates to the technical field of fault detection, in particular to a fault detection method and system of an air pressure sintering furnace.

Background

A gas pressure sintering furnace is an apparatus for sintering mineral powder, in which mineral particles are combined with each other to form a solid substance by the action of high temperature and high pressure. The principle of the air pressure sintering furnace is to use high temperature and high pressure to promote the bonding between mineral particles, and during the sintering process, heat energy and chemical energy are input into the mineral particles, causing melting and recrystallization of the surfaces thereof, and finally forming a solid substance. If the air pressure sintering furnace malfunctions during operation, the final crystallization effect is poor, and therefore, the malfunction detection has an important influence on the operation of the air pressure sintering furnace. However, the traditional fault detection needs to be stopped for element-by-element fault detection, and the problem of poor detection efficiency exists.

Disclosure of Invention

The application provides a fault detection method and system of an air pressure sintering furnace, which are used for solving the technical problems that the traditional fault detection needs to be stopped for element-by-element fault detection and the detection efficiency is poor.

According to a first aspect of the present application, there is provided a fault detection method of a gas pressure sintering furnace, comprising: setting the air pressure sintering furnace as a working state, starting an infrared thermal imager to scan a heating area of the air pressure sintering furnace, and obtaining a heating area thermal image sequence in a first time zone; receiving expected temperature information of a first time zone from a control terminal of the air pressure sintering furnace; based on the expected temperature information, activating a temperature deviation analysis channel of a temperature abnormality analysis component, and carrying out abnormality analysis on the heating region thermal image sequence to obtain a first temperature abnormality region and a first temperature health region; activating a temperature fluctuation analysis channel of the temperature abnormality analysis component, and carrying out temperature fluctuation analysis on the first temperature health area to generate a temperature fluctuation coefficient; when the temperature fluctuation coefficient is larger than or equal to a temperature fluctuation coefficient threshold value, a second temperature abnormal region is generated; and carrying out fault identification on the temperature control elements in the first temperature abnormal region and the second temperature abnormal region, and sending the fault identification to the control terminal of the air pressure sintering furnace.

According to a second aspect of the present application, there is provided a fault detection system of a gas pressure sintering furnace, comprising: the heating area scanning module is used for setting the air pressure sintering furnace to be in a working state, and starting the thermal infrared imager to scan the heating area of the air pressure sintering furnace to obtain a heating area thermal image sequence in a first time zone; the expected temperature receiving module is used for receiving expected temperature information of the first time zone from the air pressure sintering furnace control terminal; the temperature anomaly analysis module is used for activating a temperature deviation analysis channel of the temperature anomaly analysis component based on the expected temperature information, and carrying out anomaly analysis on the heating region thermal image sequence to obtain a first temperature anomaly region and a first temperature health region; the temperature fluctuation analysis module is used for activating a temperature fluctuation analysis channel of the temperature abnormality analysis component, carrying out temperature fluctuation analysis on the first temperature health area and generating a temperature fluctuation coefficient; the second temperature abnormal region generation module is used for generating a second temperature abnormal region when the temperature fluctuation coefficient is greater than or equal to a temperature fluctuation coefficient threshold value; the fault identification module is used for carrying out fault identification on the temperature control elements in the first temperature abnormal region and the second temperature abnormal region and sending the fault identification to the air pressure sintering furnace control terminal.

According to one or more technical solutions adopted by the present application, the following beneficial effects are achieved:

1. the method comprises the steps of setting an air pressure sintering furnace as a working state, starting an infrared thermal imager to scan a heating area of the air pressure sintering furnace, obtaining a heating area thermal image sequence of a first time zone, receiving expected temperature information of the first time zone from an air pressure sintering furnace control terminal, activating a temperature deviation analysis channel of a temperature abnormality analysis component based on the expected temperature information, carrying out abnormality analysis on the heating area thermal image sequence, obtaining a first temperature abnormality area and a first temperature health area, activating a temperature fluctuation analysis channel of the temperature abnormality analysis component, carrying out temperature fluctuation analysis on the first temperature health area, generating a temperature fluctuation coefficient, generating a second temperature abnormality area when the temperature fluctuation coefficient is larger than or equal to a temperature fluctuation coefficient threshold value, carrying out fault identification on temperature control elements of the first temperature abnormality area and the second temperature abnormality area, and sending the fault identification to the air pressure sintering furnace control terminal. Therefore, by carrying out abnormal analysis on the temperature distribution of the air pressure sintering furnace, identifying a temperature abnormal region, carrying out fault identification on a temperature control element in the temperature abnormal region, and facilitating troubleshooting and maintenance of faults by staff according to the fault identification, the technical effects of improving the fault detection efficiency and guaranteeing the detection accuracy are achieved.

2. The method comprises the steps of performing digital processing on a first heating region thermal image of a heating region thermal image sequence, randomly extracting first pixel points, setting the first pixel points as reference pixel points, judging whether the gray value deviation between the gray value of second pixel points and the gray value of the reference pixel points is smaller than or equal to preset gray value deviation, adding the second pixel points into a first gray growth region of the first pixel points if the gray value deviation is smaller than or equal to preset gray value deviation, adding the second pixel points into the reference pixel points at the same time, performing neighborhood gray growth based on the second pixel points if the gray value deviation is larger than the preset gray value deviation, obtaining the second gray growth region, stopping neighborhood gray growth when all pixel points of the first heating region thermal image are traversed, setting the gray value of a central pixel of each gray growth region as the gray value of a corresponding gray growth region, outputting the gray growth image of the first heating region, and adding the gray growth image into the heating region gray growth image sequence, so that temperature zone analysis of an inner furnace region is realized, abnormal region detection efficiency is improved, and further technical effects of fault detection efficiency are improved.

3. Obtaining a first temperature mark and a second temperature mark of a first temperature health area until an Mth temperature mark, performing full-distance analysis on the first temperature mark and the second temperature mark until the Mth temperature mark to generate a full-distance coefficient, setting the temperature fluctuation coefficient of the first temperature health area to be zero when the full-distance coefficient is smaller than or equal to a full-distance coefficient threshold, performing average difference analysis on the first temperature mark and the second temperature mark until the Mth temperature mark when the full-distance coefficient is larger than the full-distance coefficient threshold to generate an average difference coefficient, setting the temperature fluctuation coefficient of the first temperature health area to be zero when the average difference coefficient is smaller than or equal to the average difference coefficient threshold, performing local outlier analysis on the first temperature mark and the second temperature mark until the Mth temperature mark when the average difference coefficient is larger than the average difference coefficient threshold, generating local outlier temperature proportion, setting the temperature fluctuation coefficient of the first temperature health area to be zero when the local outlier temperature proportion is smaller than or equal to a preset proportion threshold, and setting the temperature fluctuation coefficient of the first temperature health area to be 1 when the local outlier temperature proportion is larger than the preset proportion threshold. Therefore, through carrying out temperature fluctuation analysis on the temperature health area, the technical effects of improving the detection precision of the abnormal area and further improving the fault detection precision are achieved.

Drawings

In order to more clearly illustrate the technical solutions of the present application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. The accompanying drawings, which are included to provide a further understanding of the application, illustrate and explain the present application, and together with the description serve to explain the principle of the application, if not to limit the application, and to enable others skilled in the art to make and use the application without undue effort.

FIG. 1 is a schematic flow chart of a fault detection method for a pneumatic sintering furnace according to an embodiment of the present application;

fig. 2 is a schematic structural diagram of a fault detection system of a gas pressure sintering furnace according to an embodiment of the present application.

Reference numerals illustrate: a heating region scanning module 11, a desired temperature receiving module 12, a temperature abnormality analysis module 13, a temperature fluctuation analysis module 14, a second temperature abnormality region generating module 15, and a fault identification module 16.

Detailed Description

In order to make the objects, technical solutions and advantages of the present application more apparent, exemplary embodiments of the present application will be described in detail below with reference to the accompanying drawings. It should be apparent that the described embodiments are only some embodiments of the present application and not all embodiments of the present application, and it should be understood that the present application is not limited by the example embodiments described herein.

The terminology used in the description is for the purpose of describing embodiments only and is not intended to be limiting of the application. As used in this specification, the singular terms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. The terms "comprises" and/or "comprising," when used in this specification, specify the presence of steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other steps, operations, elements, components, and/or groups thereof.

Unless defined otherwise, all terms (including technical and scientific terms) used in this specification should have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. Terms, such as those defined in commonly used dictionaries, should not be interpreted in an idealized or overly formal sense unless expressly so defined herein. Like numbers refer to like elements throughout.

It should be noted that, the user information (including, but not limited to, user equipment information, user personal information, etc.) and the data (including, but not limited to, data for presentation, analyzed data, etc.) related to the present application are information and data authorized by the user or sufficiently authorized by each party.

Example 1

Fig. 1 is a diagram of a fault detection method of a gas pressure sintering furnace according to an embodiment of the present application, where the method includes:

setting the air pressure sintering furnace as a working state, starting an infrared thermal imager to scan a heating area of the air pressure sintering furnace, and obtaining a heating area thermal image sequence in a first time zone;

the application is characterized in that the air pressure sintering furnace is set to be in a working state, the infrared thermal imager is started to scan a heating area of the air pressure sintering furnace, the infrared thermal imager images the whole object in real time in a 'face' mode, and the heating condition and the heating position can be primarily judged through the image color and the hot spot tracking display function displayed by a screen. The heating area of the air pressure sintering furnace refers to a specific area of the sintered crystal in the air pressure sintering furnace, and the specific area needs to be determined by combining with an actual scene. The thermal infrared imager scans the heating area of the air pressure sintering furnace to obtain a thermal image sequence of the heating area in a first time zone, wherein the first time zone generally refers to any time period of the sintered crystal, namely, the thermal infrared image obtained by scanning in the time period, and conventionally, when the crystal is sintered by the air pressure sintering furnace, the set sintering temperature is different along with the time change, for example, organic matters in slurry are volatilized at the early stage, then the synthesis of silicon-aluminum alloy is carried out, the sintering temperatures required at different stages are different, and each time zone is used. The above is merely illustrative, and in practice, there may be a plurality of time zones, which need to be determined according to the actual situation.

Receiving expected temperature information of a first time zone from a control terminal of the air pressure sintering furnace;

the air pressure sintering furnace control terminal refers to a terminal controller capable of controlling operation (including temperature, time and the like) of the air pressure sintering furnace, and receives expected temperature information of a first time zone from the air pressure sintering furnace control terminal, namely, the air pressure sintering furnace control terminal takes a temperature parameter set by the air pressure sintering furnace control terminal for the first time zone as the expected temperature information of the first time zone.

Based on the expected temperature information, activating a temperature deviation analysis channel of a temperature abnormality analysis component, and carrying out abnormality analysis on the heating region thermal image sequence to obtain a first temperature abnormality region and a first temperature health region;

in a preferred embodiment, further comprising:

traversing the heating region thermal image sequence to perform neighborhood gray scale growth, and generating a heating region gray scale growth image sequence, wherein the heating region gray scale growth image sequence corresponds to the heating region thermal image sequence one by one; traversing the heating region gray scale growth map sequence to perform central gray scale temperature analysis, and generating a plurality of groups of thermal image map temperature identification results; performing region intersection on the multiple groups of thermal image temperature identification results to generate thermal image temperature identification results; and activating a temperature deviation analysis channel of a temperature abnormality analysis component based on the expected temperature information, and carrying out abnormality analysis on the thermal image temperature identification result to obtain the first temperature abnormality region and the first temperature health region.

In a preferred embodiment, further comprising:

performing digital processing on a first heating region thermal image of the heating region thermal image sequence, randomly extracting a first pixel point, and setting the first pixel point as a reference pixel point, wherein the reference pixel point has a reference pixel point gray value; judging whether the gray value deviation of the gray value of the second pixel point and the gray value of the reference pixel point is smaller than or equal to the preset gray value deviation, wherein the second pixel point is an adjacent pixel point of the first pixel point; if the first gray scale growth area is smaller than or equal to the second gray scale growth area, adding the second pixel point into the first gray scale growth area of the first pixel point, and simultaneously adding the second pixel point into the reference pixel point; if the gray scale is larger than the first gray scale, performing neighborhood gray scale growth based on the second pixel point to obtain a second gray scale growth area; and when all pixel points of the first heating region thermal image are traversed, stopping neighborhood gray scale growth, setting the gray scale value of the central pixel of each gray scale growth region as the gray scale value of the corresponding gray scale growth region, outputting a gray scale growth image of the first heating region, and adding the gray scale growth image into the gray scale growth image sequence of the heating region.

In a preferred embodiment, further comprising:

Obtaining a first temperature mark and a second temperature mark of the first furnace region until an Mth temperature mark according to the thermal image temperature mark result; performing deviation analysis on the first temperature mark and the second temperature mark until the Mth temperature mark based on the expected temperature information to generate a temperature deviation distance mean value and a temperature deviation time proportion; when the temperature deviation distance average value is greater than or equal to a temperature deviation distance threshold value, or/and the temperature deviation moment proportion is greater than or equal to a deviation moment proportion threshold value, adding the first furnace region into the first temperature abnormal region; and when the temperature deviation distance average value is smaller than the temperature deviation distance threshold value and the temperature deviation moment proportion is smaller than the deviation moment proportion threshold value, adding the first furnace region into the first temperature health region.

Based on the expected temperature information, a temperature deviation analysis channel of a temperature abnormality analysis component is activated to perform abnormality analysis on the heating region thermal image sequence, that is, in an ideal case, that is, in a case that no fault occurs in the air pressure sintering furnace, the expected temperature information and the temperature displayed by the heating region thermal image sequence should be the same, otherwise, a fault may occur, so that the heating region thermal image sequence can be performed to perform abnormality analysis based on the expected temperature information to obtain a first temperature abnormality region and a first temperature health region, and the specific process is as follows:

Traversing the heating region thermal image sequence to perform neighborhood gray scale growth, and generating a heating region gray scale growth image sequence, wherein the heating region gray scale growth image sequence corresponds to the heating region thermal image sequence one by one, and the method for generating the heating region gray scale growth image sequence comprises the following steps: the image digitization is a process of sampling and quantizing analog images with continuous spatial distribution and brightness values into digital images which can be processed by a computer, namely, in the imaging process, sampling a continuous distributed image to obtain discrete pixels after discretizing spatial position coordinates, converting pixel gray scales into discrete integer values through quantization, and then carrying out encoding, wherein the image digitization is a common technical means for a person skilled in the art, so that the image digitization is not unfolded. Therefore, any pixel point of any image in the heating area gray scale growth map sequence can be randomly extracted and marked as a first pixel point, and the first pixel point is set as a reference pixel point, wherein the reference pixel point has a reference pixel point gray scale value, namely the gray scale value of the pixel point is marked.

The second pixel point is any pixel point adjacent to the first pixel point, and the second pixel point also has a mark of a gray value, so that whether the gray value deviation between the gray value of the second pixel point and the gray value of the reference pixel point is smaller than or equal to a preset gray value deviation is judged, wherein the preset gray value deviation is set by a person skilled in the art, and the gray value deviation corresponding to the temperature deviation allowed to exist in the temperature control process of the air pressure sintering furnace can be obtained as the preset gray value deviation by combining practical experience. If the gray value deviation between the gray value of the second pixel point and the gray value of the reference pixel point is smaller than or equal to the preset gray value deviation, the first pixel point and the second pixel point can be considered to belong to the same type of temperature, the second pixel point is added into the first gray growth area of the first pixel point, that is to say, the first pixel point and the second pixel point are combined, and meanwhile, the second pixel point is added into the reference pixel point; if the difference is larger than the preset threshold value, performing neighborhood gray scale growth based on the second pixel point, namely considering that the temperature difference between the first pixel point and the second pixel point is larger, and respectively using the first pixel point and the second pixel point as two gray scale growth areas to obtain a second gray scale growth area. Based on the above, all the pixels of the first heating region thermal image are traversed, that is, other adjacent pixels of the first pixel and adjacent pixels of the second pixel are sequentially acquired, the gray values are compared, the corresponding gray growth regions are acquired until the comparison of all the pixels is completed, the neighborhood gray growth is stopped, a plurality of gray growth regions can be obtained, the gray value of the central pixel of each gray growth region is set as the gray value of the corresponding gray growth region, and conventionally, the gray value of the pixel in each gray growth region is subjected to large-scale median, compared with the traditional median, the gray value of the pixel in each gray growth region is higher, the gray value of the adjacent region is set as the same gray value, the temperature partition analysis is facilitated, and the abnormal region detection efficiency is improved. And outputting a first heating region gray scale growth map, and adding the first heating region gray scale growth map into the heating region gray scale growth map sequence, wherein the heating region gray scale growth map sequence and the heating region thermal image map sequence are in one-to-one correspondence, that is, each heating region thermal image map corresponds to one heating region gray scale growth map.

And further traversing the heating region gray scale growth map sequence to perform central gray scale temperature analysis, namely, marking different gray scale values and corresponding temperature values in a one-to-one correspondence manner, and generating a plurality of groups of thermal image map temperature marking results, specifically, a person skilled in the art can obtain the gray scale values of the infrared thermal image maps corresponding to different temperatures through actual tests, construct a corresponding table of the gray scale values and the temperatures, then, based on the central pixel gray scale value of each gray scale growth region in the heating region gray scale growth map sequence, obtain the corresponding temperatures in the corresponding table in a matching manner, and mark the corresponding temperatures to the heating region gray scale growth map sequence, so that a plurality of groups of thermal image map temperature marking results can be generated.

The temperature identification results of the multiple groups of thermal image images are intersected in areas, in short, the temperature identification results of the multiple groups of thermal image images refer to the temperature identification results of each image in the thermal image sequence of the heating area acquired by the first time zone, so that gray scale growth areas in different images can be different, the temperature identification results of the areas at the same position in the images can be different, and comparison analysis is performed on the temperature identification results of the multiple groups of thermal image images in pairs to acquire multiple temperature identification results of the areas in the furnace. For example, an image is a temperature identification result in a certain coordinate range of the image at a first moment, but the coordinate range of the image at another moment has two partitions, that is, has temperature identification results corresponding to two gray scale growth areas, the coordinate range is divided into two furnace areas, then, the two furnace areas have two temperature identification results, one is the same temperature identification result at the first moment, the other is a different temperature identification result at another moment, or in the first moment, temperature identification is carried out on each area continuously for multiple times according to the moment of image acquisition, so that a thermal image temperature identification result is generated, wherein the thermal image temperature identification result comprises a plurality of furnace areas, and each furnace area has a plurality of temperature identification results.

Further, based on the expected temperature information, a temperature deviation analysis channel of a temperature abnormality analysis component is activated, abnormal analysis is performed on the thermal image temperature identification result, the first temperature abnormality region and the first temperature health region are obtained, the first temperature abnormality region is a temperature abnormality region, the first temperature health region is a temperature normal region, and the process of performing abnormal analysis through the temperature deviation analysis channel is as follows:

and according to the thermal image temperature identification result, obtaining a first temperature identification and a second temperature identification of the first furnace region until an Mth temperature identification, wherein M is the number of images in the thermal image sequence of the heating region and is also the number of the temperature identifications of each furnace region. And carrying out deviation analysis on the first temperature mark and the second temperature mark until the Mth temperature mark based on the expected temperature information, namely calculating M deviation values of the first temperature mark and the second temperature mark until the Mth temperature mark and the expected temperature information respectively, carrying out average calculation on the M deviation values to obtain a temperature deviation distance average value, wherein the temperature deviation moment proportion refers to the ratio of the time length of generating the temperature deviation to the time length of a first time zone, specifically, firstly, acquiring a temperature deviation distance threshold value, wherein the temperature deviation distance threshold value refers to the temperature deviation which is determined by combining historical experience of a person skilled in the art and is allowed to exist, comparing the M deviation values with the temperature deviation distance threshold value, and calculating the ratio of the time length corresponding to the temperature mark with the deviation value larger than or equal to the temperature deviation distance threshold value to the time length of the first time zone as the temperature deviation moment proportion.

And when the temperature deviation distance average value is greater than or equal to a temperature deviation distance threshold value, or/and the temperature deviation moment proportion is greater than or equal to a deviation moment proportion threshold value, adding the first furnace region into the first temperature abnormal region, wherein the deviation moment proportion threshold value is also determined by a person skilled in the art in combination with practical experience. In colloquial terms, the temperature deviation distance average value is greater than or equal to a temperature deviation distance threshold value and the temperature deviation time proportion is greater than or equal to a deviation time proportion threshold value are taken as two conditions for abnormality determination, and the first furnace region is considered to be an abnormal region as long as one of the conditions is satisfied. And when the temperature deviation distance average value is smaller than the temperature deviation distance threshold value and the temperature deviation moment proportion is smaller than the deviation moment proportion threshold value, adding the first furnace region into the first temperature health region. That is, if the average value of the temperature deviation distance is the average value of the M deviation values, the abnormal analysis result is inaccurate if the abnormal temperature mark is too small, so that the abnormal analysis is performed simultaneously according to the temperature deviation time proportion, the accuracy of the temperature abnormal analysis can be effectively improved, and the accuracy of fault detection of the air pressure sintering furnace is ensured.

Activating a temperature fluctuation analysis channel of the temperature abnormality analysis component, and carrying out temperature fluctuation analysis on the first temperature health area to generate a temperature fluctuation coefficient;

in a preferred embodiment, further comprising:

obtaining a first temperature mark and a second temperature mark of the first temperature health area until an Mth temperature mark; performing full-distance analysis on the first temperature mark and the second temperature mark until the Mth temperature mark to generate a full-distance coefficient; setting the temperature fluctuation coefficient of the first temperature health area to zero when the full-distance coefficient is less than or equal to a full-distance coefficient threshold; when the full-distance coefficient is larger than the full-distance coefficient threshold, carrying out average difference analysis on the first temperature mark and the second temperature mark until the Mth temperature mark to generate an average difference coefficient; setting the temperature fluctuation coefficient of the first temperature health area to zero when the average difference coefficient is less than or equal to an average difference coefficient threshold; when the average difference coefficient is larger than the average difference coefficient threshold, carrying out local outlier analysis on the first temperature mark and the second temperature mark until the Mth temperature mark to generate local outlier temperature proportion; when the local outlier temperature proportion is smaller than or equal to a preset proportion threshold value, setting the temperature fluctuation coefficient of the first temperature health area to be zero; and when the local outlier temperature proportion is larger than the preset proportion threshold, setting the temperature fluctuation coefficient of the first temperature health area to be 1.

In a preferred embodiment, further comprising:

selecting k adjacent temperature marks from the first temperature mark and the second temperature mark to the Mth temperature mark based on the temperature deviation distance, wherein the ith temperature mark belongs to the first temperature mark and the second temperature mark to the Mth temperature mark, k is more than 2, and k is an integer; solving a temperature deviation distance average value of the k adjacent temperature identifiers and the ith temperature identifier, and setting the temperature deviation distance average value as an ith temperature identifier outlier parameter; traversing the first temperature mark and the second temperature mark until the Mth temperature mark to obtain an outlier parameter mean; the mean value of the i-th temperature identification outlier parameter and the outlier parameter is compared to set as an i-th temperature identification outlier coefficient; when the i-th temperature mark outlier coefficient is larger than or equal to an outlier coefficient threshold value, adding the i-th temperature mark into a local outlier; and counting the duty ratio of the local outlier in the first temperature mark, the second temperature mark and the Mth temperature mark, and setting the duty ratio as the local outlier temperature proportion.

And activating a temperature fluctuation analysis channel of the temperature abnormality analysis component, carrying out temperature fluctuation analysis on the first temperature health area to generate a temperature fluctuation coefficient, namely, the temperature deviation of the first temperature health area is smaller than a temperature deviation distance threshold value, but the first temperature health area cannot be determined to be fault-free, so that the temperature distribution deviation analysis needs to be carried out on the first temperature health area, and if the temperature deviation is large, the temperature of the first temperature health area is abnormal. The temperature fluctuation coefficient is used for reflecting the temperature distribution deviation of the first temperature health area, and the specific acquisition process is as follows:

And obtaining a first temperature mark and a second temperature mark of the first temperature health area until an Mth temperature mark, wherein M is the number of images in a thermal image sequence of the heating area and is also the number of temperature marks of each furnace area. And carrying out full-distance analysis on the first temperature mark and the second temperature mark until the Mth temperature mark, namely subtracting the minimum value from the maximum value in the first temperature mark and the second temperature mark until the Mth temperature mark, and obtaining a result which is a full-distance coefficient. The full-distance coefficient threshold is set by the person skilled in the art in combination with practical experience, and refers to the full-distance range allowed to exist when the air pressure sintering furnace has no fault. And when the full-distance coefficient is smaller than or equal to a full-distance coefficient threshold, indicating that the full-distance coefficient is smaller, enabling deviation between a first temperature mark and a second temperature mark of a first temperature health area to be smaller until an Mth temperature mark is smaller, and setting the temperature fluctuation coefficient of the first temperature health area to be zero.

When the full-distance coefficient is larger than the full-distance coefficient threshold, carrying out average difference analysis on the first temperature mark and the second temperature mark until the Mth temperature mark, firstly calculating the average value of the first temperature mark and the second temperature mark until the Mth temperature mark, wherein the average difference coefficient is the arithmetic average of the absolute values of the differences of the first temperature mark and the second temperature mark until the Mth temperature mark and the average value, and generating the average difference coefficient. The smaller the average difference coefficient is, the smaller the deviation between the first temperature mark and the second temperature mark up to the Mth temperature mark is, and when the average difference coefficient is smaller than or equal to an average difference coefficient threshold value, the temperature fluctuation coefficient of the first temperature health area is set to be zero, wherein the average difference coefficient threshold value is set by a person skilled in the art in combination with practical experience.

The full distance coefficient and the average difference coefficient are used for judging the degree of dispersion of the whole temperature distribution from the first temperature mark to the second temperature mark to the Mth temperature mark, and the degree of dispersion is also the deviation between the temperature marks. When the average difference coefficient is larger than the average difference coefficient threshold, the overall temperature distribution deviation is larger, at the moment, local outlier analysis is carried out on the first temperature mark and the second temperature mark until the Mth temperature mark, local outlier temperature proportion is generated, and more comprehensive temperature fluctuation analysis is realized through the local outlier analysis.

The process of generating the local outlier temperature ratio is as follows: and selecting k adjacent temperature marks from the first temperature mark and the second temperature mark to the Mth temperature mark based on the temperature deviation distance, wherein the ith temperature mark belongs to the first temperature mark and the second temperature mark to the Mth temperature mark, k is more than 2, and k is an integer, wherein the selection standard of the adjacent temperature marks is automatically set by a person skilled in the art in combination with practical experience, and the k adjacent temperature marks nearest to the ith temperature mark are ensured to be selected. And solving an average value of K temperature deviations between the K adjacent temperature identifications and the ith temperature identification as a temperature deviation distance average value, and setting the average value as an ith temperature identification outlier parameter. Traversing the first temperature mark and the second temperature mark until the Mth temperature mark, respectively selecting k adjacent temperature marks corresponding to the first temperature mark and the second temperature mark until the Mth temperature mark, calculating and obtaining M temperature mark outlier parameters, and averaging to obtain an outlier parameter mean.

Setting the ratio of the i-th temperature identification outlier parameter to the mean value of the outlier parameter as an i-th temperature identification outlier coefficient, wherein the larger the i-th temperature identification outlier coefficient is, the larger the deviation between the i-th temperature identification and the adjacent temperature identification is, and adding the i-th temperature identification into a local outlier when the i-th temperature identification outlier coefficient is larger than or equal to an outlier coefficient threshold, wherein the outlier coefficient threshold is set by a person skilled in the art in combination with actual experience. And the local outlier comprises one or more of the first temperature mark and the second temperature mark until the Mth temperature mark, the proportion of the local outlier in the first temperature mark and the second temperature mark until the Mth temperature mark is counted, and the proportion is set as the local outlier temperature proportion. The distribution state of each temperature mark is judged through local outlier analysis, so that comprehensive temperature fluctuation analysis is realized, and the accuracy of fault analysis is improved conveniently.

And when the local outlier temperature proportion is smaller than or equal to a preset proportion threshold value, setting the temperature fluctuation coefficient of the first temperature health area to be zero. The preset proportion threshold is set by the person skilled in the art, and is not suitable for being too large, so that faults are missed; too small a setting is not desirable, which can lead to false positives, can be set by those skilled in the art in combination with actual experience, and can be updated in real time by those skilled in the art. And when the local outlier temperature proportion is larger than the preset proportion threshold, setting the temperature fluctuation coefficient of the first temperature health area to be 1.

When the temperature fluctuation coefficient is larger than or equal to a temperature fluctuation coefficient threshold value, a second temperature abnormal region is generated;

as is clear from the above analysis, when the temperature fluctuation coefficient is 0 or 1 and is 0, the fluctuation is small, and therefore, in the present embodiment, the temperature fluctuation coefficient threshold may be set to 1, and when the temperature fluctuation coefficient is greater than or equal to the temperature fluctuation coefficient threshold, the first temperature health area is updated to the second temperature abnormality area.

And carrying out fault identification on the temperature control elements in the first temperature abnormal region and the second temperature abnormal region, and sending the fault identification to the control terminal of the air pressure sintering furnace.

In a preferred embodiment, further comprising:

the temperature control element comprises a cooling water pipeline and a heating element; matching adjacent cooling water pipes and adjacent heating elements based on the first temperature anomaly region and/or the second temperature anomaly region; obtaining inlet and outlet flow rates of the adjacent cooling water pipe; when the flow deviation of the inlet flow and the outlet flow is larger than the preset flow deviation, performing fault identification on the adjacent cooling water pipelines to generate a first fault identification; judging whether the temperature of the first temperature abnormal region and/or the second temperature abnormal region of the adjacent cooling water pipeline in a closed state is abnormal or not; if so, performing fault identification on the adjacent heating element to generate a second fault identification; and sending the first fault identification and the second fault identification to the control terminal of the air pressure sintering furnace.

The temperature control elements in the first temperature abnormal region and the second temperature abnormal region are subjected to fault identification and sent to the control terminal of the air pressure sintering furnace, workers are reminded of overhauling the temperature control elements with the fault identification, and the specific process is as follows:

the temperature control element comprises a cooling water pipeline and a heating element, wherein the cooling water pipeline is used for cooling control, the heating element is used for heating control, and the abnormal operation of any element can lead to the abnormal temperature of the air pressure sintering furnace. The cooling water pipeline and the heating element are distributed on the air pressure sintering furnace, and the cooling water pipeline and the heating element are possibly arranged at different positions. And based on the first temperature abnormal region and/or the second temperature abnormal region, matching and acquiring a cooling water pipeline and a heating element closest to the first temperature abnormal region and/or the second temperature abnormal region as a nearby cooling water pipeline and a nearby heating element.

The inlet flow and the outlet flow of the adjacent cooling water pipeline are further acquired through an existing pipeline flow tester, the flow deviation between the inlet flow and the outlet flow is calculated, when the flow deviation between the inlet flow and the outlet flow is larger than the preset flow deviation, the difference between the inlet flow and the outlet flow is larger, the adjacent cooling water pipeline is larger, the temperature of the air pressure sintering furnace is abnormal due to the fact that the adjacent cooling water pipeline is faulty, at the moment, fault identification is carried out on the adjacent cooling water pipeline, and a first fault identification is generated. The preset flow deviation refers to a deviation range which can be allowed to occur when the cooling water pipeline normally operates, and can be determined by a person skilled in the art in combination with practical situations. Otherwise, when the flow deviation of the inlet flow and the outlet flow is smaller than or equal to the preset flow deviation, the adjacent cooling water pipeline is considered to be normal without faults.

Judging whether the first temperature abnormal region and/or the second temperature abnormal region of the adjacent cooling water pipeline in the closed state is abnormal or not, in short, if the temperature deviation between the temperature of the first temperature abnormal region and/or the second temperature abnormal region and the expected temperature information is greater than or equal to a temperature deviation distance threshold, in short, judging that the temperature of the first temperature abnormal region and/or the second temperature abnormal region is abnormal when the adjacent cooling water pipeline is in the closed state because the cooling water pipeline is not opened in the whole process, namely, acquiring the temperature of the first temperature abnormal region and/or the second temperature abnormal region when the adjacent cooling water pipeline is in the closed state, judging that whether the deviation temperature between the temperature of the first temperature abnormal region and/or the second temperature abnormal region and the expected temperature information is greater than or equal to the temperature deviation distance threshold, if the deviation temperature of the first temperature abnormal region and/or the second temperature abnormal region is considered, judging that the adjacent heating element is faulty, and performing fault identification on the adjacent heating element to generate a second fault identification. The first fault identification and the second fault identification are sent to the air pressure sintering furnace control terminal, so that workers are conveniently reminded of overhauling the heating element or the cooling water pipeline with the fault identification, and the accuracy of fault detection is improved.

Based on the analysis, the one or more technical schemes provided by the application can achieve the following beneficial effects:

Example two

Based on the same inventive concept as the fault detection method of the air pressure sintering furnace in the foregoing embodiment, as shown in fig. 2, the present application further provides a fault detection system of the air pressure sintering furnace, the system comprising:

the heating area scanning module 11 is used for setting the air pressure sintering furnace into a working state, and starting the thermal infrared imager to scan the heating area of the air pressure sintering furnace to obtain a heating area thermal image sequence in a first time zone;

a desired temperature receiving module 12, wherein the desired temperature receiving module 12 is used for receiving desired temperature information of a first time zone from a gas pressure sintering furnace control terminal;

the temperature anomaly analysis module 13 is configured to activate a temperature deviation analysis channel of a temperature anomaly analysis component based on the expected temperature information, perform anomaly analysis on the heating region thermal image sequence, and obtain a first temperature anomaly region and a first temperature health region;

the temperature fluctuation analysis module 14 is configured to activate a temperature fluctuation analysis channel of the temperature anomaly analysis component, perform temperature fluctuation analysis on the first temperature health area, and generate a temperature fluctuation coefficient;

A second temperature anomaly region generation module 15, where the second temperature anomaly region generation module 15 is configured to generate a second temperature anomaly region when the temperature fluctuation coefficient is greater than or equal to a temperature fluctuation coefficient threshold;

the fault identification module 16 is configured to perform fault identification on the temperature control elements in the first temperature abnormal region and the second temperature abnormal region, and send the fault identification result to the air pressure sintering furnace control terminal.

Further, the temperature anomaly analysis module 13 further includes:

traversing the heating region thermal image sequence to perform neighborhood gray scale growth, and generating a heating region gray scale growth image sequence, wherein the heating region gray scale growth image sequence corresponds to the heating region thermal image sequence one by one;

traversing the heating region gray scale growth map sequence to perform central gray scale temperature analysis, and generating a plurality of groups of thermal image map temperature identification results;

performing region intersection on the multiple groups of thermal image temperature identification results to generate thermal image temperature identification results;

and activating a temperature deviation analysis channel of a temperature abnormality analysis component based on the expected temperature information, and carrying out abnormality analysis on the thermal image temperature identification result to obtain the first temperature abnormality region and the first temperature health region.

Further, the temperature anomaly analysis module 13 further includes:

performing digital processing on a first heating region thermal image of the heating region thermal image sequence, randomly extracting a first pixel point, and setting the first pixel point as a reference pixel point, wherein the reference pixel point has a reference pixel point gray value;

judging whether the gray value deviation of the gray value of the second pixel point and the gray value of the reference pixel point is smaller than or equal to the preset gray value deviation, wherein the second pixel point is an adjacent pixel point of the first pixel point;

if the first gray scale growth area is smaller than or equal to the second gray scale growth area, adding the second pixel point into the first gray scale growth area of the first pixel point, and simultaneously adding the second pixel point into the reference pixel point;

if the gray scale is larger than the first gray scale, performing neighborhood gray scale growth based on the second pixel point to obtain a second gray scale growth area;

and when all pixel points of the first heating region thermal image are traversed, stopping neighborhood gray scale growth, setting the gray scale value of the central pixel of each gray scale growth region as the gray scale value of the corresponding gray scale growth region, outputting a gray scale growth image of the first heating region, and adding the gray scale growth image into the gray scale growth image sequence of the heating region.

Further, the temperature anomaly analysis module 13 further includes:

Obtaining a first temperature mark and a second temperature mark of the first furnace region until an Mth temperature mark according to the thermal image temperature mark result;

performing deviation analysis on the first temperature mark and the second temperature mark until the Mth temperature mark based on the expected temperature information to generate a temperature deviation distance mean value and a temperature deviation time proportion;

when the temperature deviation distance average value is greater than or equal to a temperature deviation distance threshold value, or/and the temperature deviation moment proportion is greater than or equal to a deviation moment proportion threshold value, adding the first furnace region into the first temperature abnormal region;

and when the temperature deviation distance average value is smaller than the temperature deviation distance threshold value and the temperature deviation moment proportion is smaller than the deviation moment proportion threshold value, adding the first furnace region into the first temperature health region.

Further, the temperature fluctuation analysis module 14 further includes:

obtaining a first temperature mark and a second temperature mark of the first temperature health area until an Mth temperature mark;

performing full-distance analysis on the first temperature mark and the second temperature mark until the Mth temperature mark to generate a full-distance coefficient;

Setting the temperature fluctuation coefficient of the first temperature health area to zero when the full-distance coefficient is less than or equal to a full-distance coefficient threshold;

when the full-distance coefficient is larger than the full-distance coefficient threshold, carrying out average difference analysis on the first temperature mark and the second temperature mark until the Mth temperature mark to generate an average difference coefficient;

setting the temperature fluctuation coefficient of the first temperature health area to zero when the average difference coefficient is less than or equal to an average difference coefficient threshold;

when the average difference coefficient is larger than the average difference coefficient threshold, carrying out local outlier analysis on the first temperature mark and the second temperature mark until the Mth temperature mark to generate local outlier temperature proportion;

when the local outlier temperature proportion is smaller than or equal to a preset proportion threshold value, setting the temperature fluctuation coefficient of the first temperature health area to be zero;

and when the local outlier temperature proportion is larger than the preset proportion threshold, setting the temperature fluctuation coefficient of the first temperature health area to be 1.

Further, the temperature fluctuation analysis module 14 further includes:

selecting k adjacent temperature marks from the first temperature mark and the second temperature mark to the Mth temperature mark based on the temperature deviation distance, wherein the ith temperature mark belongs to the first temperature mark and the second temperature mark to the Mth temperature mark, k is more than 2, and k is an integer;

Solving a temperature deviation distance average value of the k adjacent temperature identifiers and the ith temperature identifier, and setting the temperature deviation distance average value as an ith temperature identifier outlier parameter;

traversing the first temperature mark and the second temperature mark until the Mth temperature mark to obtain an outlier parameter mean;

the mean value of the i-th temperature identification outlier parameter and the outlier parameter is compared to set as an i-th temperature identification outlier coefficient;

when the i-th temperature mark outlier coefficient is larger than or equal to an outlier coefficient threshold value, adding the i-th temperature mark into a local outlier;

and counting the duty ratio of the local outlier in the first temperature mark, the second temperature mark and the Mth temperature mark, and setting the duty ratio as the local outlier temperature proportion.

Further, the fault identification module 16 further includes:

the temperature control element comprises a cooling water pipeline and a heating element;

matching adjacent cooling water pipes and adjacent heating elements based on the first temperature anomaly region and/or the second temperature anomaly region;

obtaining inlet and outlet flow rates of the adjacent cooling water pipe;

when the flow deviation of the inlet flow and the outlet flow is larger than the preset flow deviation, performing fault identification on the adjacent cooling water pipelines to generate a first fault identification;

Judging whether the temperature of the first temperature abnormal region and/or the second temperature abnormal region of the adjacent cooling water pipeline in a closed state is abnormal or not;

if so, performing fault identification on the adjacent heating element to generate a second fault identification;

and sending the first fault identification and the second fault identification to the control terminal of the air pressure sintering furnace.

The specific example of the fault detection method of the air pressure sintering furnace in the first embodiment is also applicable to the fault detection system of the air pressure sintering furnace in the present embodiment, and the detailed description of the fault detection method of the air pressure sintering furnace in the present embodiment is clearly known to those skilled in the art, so that the detailed description thereof is omitted herein for brevity.

It should be understood that the various forms of flow shown above, reordered, added or deleted steps may be used, as long as the desired results of the disclosed embodiments are achieved, and are not limiting herein.

Note that the above is only a preferred embodiment of the present application and the technical principle applied. It will be understood by those skilled in the art that the present application is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the application. Therefore, while the application has been described in connection with the above embodiments, the application is not limited to the embodiments, but may be embodied in many other equivalent forms without departing from the spirit or scope of the application, which is set forth in the following claims.

Claims

1. A fault detection method for a gas pressure sintering furnace, comprising:

2. The method of claim 1, wherein activating a temperature deviation analysis channel of a temperature anomaly analysis component based on the desired temperature information, performing anomaly analysis on the heating region thermographic sequence to obtain a first temperature anomaly region and a first temperature health region, comprises:

3. The method of claim 2, wherein traversing the heating region thermal image sequence for neighborhood gray scale growth generates a heating region gray scale growth image sequence, wherein the heating region gray scale growth image sequence and the heating region thermal image sequence are in one-to-one correspondence, comprising:

4. The method of claim 2, wherein activating a temperature deviation resolution channel of a temperature anomaly resolution component based on the desired temperature information, performing anomaly resolution on the thermographic temperature identification result, obtaining the first temperature anomaly region and the first temperature health region, comprises:

5. The method of claim 1, wherein activating a temperature fluctuation analysis channel of a temperature anomaly analysis component, performing temperature fluctuation analysis on the first temperature health region, generating a temperature fluctuation coefficient, comprises:

6. The method of claim 5, wherein when the average difference coefficient is greater than the average difference coefficient threshold, performing local outlier analysis on the first temperature signature, the second temperature signature, and up to the mth temperature signature, generating a local outlier temperature ratio comprises:

7. The method of claim 1, wherein fault identification of temperature control elements of the first and second temperature anomaly regions is transmitted to the gas pressure sintering furnace control terminal, comprising:

obtaining inlet and outlet flow rates of the adjacent cooling water pipe;

8. A fault detection system for a gas pressure sintering furnace, characterized by the steps for performing any one of the fault detection methods for a gas pressure sintering furnace as set forth in claims 1 to 7, the system comprising:

the heating area scanning module is used for setting the air pressure sintering furnace to be in a working state, and starting the thermal infrared imager to scan the heating area of the air pressure sintering furnace to obtain a heating area thermal image sequence in a first time zone;

The expected temperature receiving module is used for receiving expected temperature information of the first time zone from the air pressure sintering furnace control terminal;

the temperature anomaly analysis module is used for activating a temperature deviation analysis channel of the temperature anomaly analysis component based on the expected temperature information, and carrying out anomaly analysis on the heating region thermal image sequence to obtain a first temperature anomaly region and a first temperature health region;

the temperature fluctuation analysis module is used for activating a temperature fluctuation analysis channel of the temperature abnormality analysis component, carrying out temperature fluctuation analysis on the first temperature health area and generating a temperature fluctuation coefficient;

the second temperature abnormal region generation module is used for generating a second temperature abnormal region when the temperature fluctuation coefficient is greater than or equal to a temperature fluctuation coefficient threshold value;

the fault identification module is used for carrying out fault identification on the temperature control elements in the first temperature abnormal region and the second temperature abnormal region and sending the fault identification to the air pressure sintering furnace control terminal.