CN102928118A - Detection method and system for clinker temperature of cooling zone in rotary kiln - Google Patents
Detection method and system for clinker temperature of cooling zone in rotary kiln Download PDFInfo
- Publication number
- CN102928118A CN102928118A CN2012104624950A CN201210462495A CN102928118A CN 102928118 A CN102928118 A CN 102928118A CN 2012104624950 A CN2012104624950 A CN 2012104624950A CN 201210462495 A CN201210462495 A CN 201210462495A CN 102928118 A CN102928118 A CN 102928118A
- Authority
- CN
- China
- Prior art keywords
- salband
- grog
- rotary kiln
- image
- clinker
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Muffle Furnaces And Rotary Kilns (AREA)
Abstract
The invention provides a detection method and a detection system for clinker temperature of a cooling zone in a rotary kiln. The method comprises the steps of acquiring a clinker image of the cooling zone in the rotary kiln, obtaining a characteristic parameter of the clinker image of the cooling zone according to the clinker image of the cooling zone in the rotary kiln, obtaining a clinker characteristic parameter of the cooling zone according to the characteristic parameter of the clinker image of the cooling zone and thermotechnical data in the rotary kiln, and obtaining a clinker temperature state of the cooling zone by comparing the similarity of the clinker characteristic parameter of the cooling zone with a clinker parameter model of the cooling zone. According to the detection method and the detection system for the clinker temperature of the cooling zone in the rotary kiln, the thermotechnical data in the rotary kiln and the characteristic parameter of the image are fused and compared with the clinker parameter model of the cooling zone, so that the accuracy and reliability of the detection of the temperature state of the cooling zone in the rotary kiln can be improved.
Description
Technical field
The present invention relates to the temperature detection technology, relate in particular to salband clinker temperature detection method and system in a kind of rotary kiln.
Background technology
Process for making alumina mainly is divided into according to the characteristics of processing ore: Bayer process, sintering process and Bayer, sintering combination method.Sintering process is mainly for the treatment of siliceous height, bauxite that alumina silica ratio is low.Clinkersintering is to use sintering process to carry out the critical process of alumina producing, and clinkersintering production is organized centered by rotary kiln.
In the clinkersintering process, the clinker temperature of salband directly affects the quality of sintering quality in the rotary kiln.In the prior art, the temperature detection of salband in the rotary kiln is mainly adopted the method for image recognition, use the grog image of camera acquisition rotary kiln salband, obtain image features according to the image that collects, again by manually according to image features and empirical value, obtain the state of temperature of salband grog.Described state of temperature refers to, for example, set the lower of salband clinker temperature and be limited to 700 ℃, on be limited to 1300 ℃, wherein per 100 ℃ are divided into a state of temperature, then being divided into is 6 state of temperatures.
Prior art is to the temperature checking method of salband in the rotary kiln, on the one hand, because circumstance complication in the industrial rotary kiln kiln, coal dust and smog disturb larger, cause the grog picture quality deficient in stability that collects, inaccurate to the testing result of the state of temperature of grog; On the other hand, rely on the artificial experience value to judge state of temperature, because artificial experience is different, also can cause the testing result of the state of temperature of grog inaccurate, therefore, prior art is also unreliable to the temperature checking method of salband in the rotary kiln, can not satisfy the needs of actual industrial production.
Summary of the invention
The invention provides salband clinker temperature detection method and system in a kind of rotary kiln, to improve accuracy and the reliability that the salband state of temperature detects in the rotary kiln.
The invention provides salband clinker temperature detection method in a kind of rotary kiln, comprising:
Gather salband grog image in the rotary kiln, and according to salband grog image in the described rotary kiln, obtain salband grog image features;
According to Pyrological data in described salband grog image features and the rotary kiln, obtain salband grog characteristic parameter;
Described salband grog characteristic parameter and salband grog parameter model are carried out the similarity contrast, obtain salband clinker temperature state.
The interior salband grog image of the rotary kiln that described basis collects obtains salband grog image features and comprises:
Salband grog image in the described rotary kiln is carried out freeze frame, smog filtering, gradation of image stretching, image segmentation processing successively, obtain described salband grog area image;
In described rotary kiln, extract described salband grog image features the salband grog area image;
Described according to Pyrological data in described salband grog image features and the rotary kiln, obtain salband grog characteristic parameter and comprise:
With salband clinker temperature, temperature of kiln head, kiln end temperature, main frame electric current, kiln hood negative pressure as Pyrological data in the described rotary kiln;
Pyrological data in described salband grog image features and the described rotary kiln is carried out data fusion obtain described salband grog characteristic parameter.
Described described salband grog characteristic parameter and salband grog parameter model are compared obtains also comprising before the salband clinker temperature state:
Salband clinker temperature state according to corresponding with described salband grog characteristic parameter obtains described salband grog parameter model;
Described salband grog parameter model is Hidden Markov Model (HMM).
Described described salband grog characteristic parameter and salband grog parameter model are carried out the similarity contrast, comprising:
With the observation sequence of described salband grog characteristic parameter as described salband grog parameter model;
Adopt Forward-backward algorithm to calculate the probability of corresponding each the described salband grog parameter model of described observation sequence;
The salband clinker temperature state that the salband grog parameter model of the maximum probability that calculates is corresponding is as described salband clinker temperature state.
Described described salband grog characteristic parameter and salband grog parameter model are compared, obtain also comprising after the salband clinker temperature state:
The clinker temperature that detects when stablizing in described salband clinker temperature state and the kiln compares, and upgrades described salband grog parameter model.
The present invention also provides salband clinker temperature detection system in a kind of rotary kiln, comprising: image collecting device and industrial computer;
Described image collecting device is used for gathering salband grog image in the rotary kiln, and sends described salband grog image to industrial computer;
Described industrial computer is used for obtaining salband grog image features according to salband grog image in the rotary kiln that collects; According to Pyrological data in described salband grog image features and the rotary kiln, obtain salband grog characteristic parameter; Described salband grog characteristic parameter and salband grog parameter model are carried out the similarity contrast, obtain salband clinker temperature state.
Described industrial computer comprises:
Graphics processing unit is used for salband grog image in the described rotary kiln is carried out freeze frame, smog filtering, gradation of image stretching, image segmentation processing successively, obtains described salband grog image;
Feature extraction unit is extracted described salband grog image features for salband grog image in described rotary kiln; With salband clinker temperature, temperature of kiln head, kiln end temperature, main frame electric current, kiln hood negative pressure as Pyrological data in the described rotary kiln;
The data fusion unit is used for that Pyrological data in described salband grog image features and the described rotary kiln is carried out data fusion and obtains described salband grog characteristic parameter.
Described industrial computer also comprises:
The characteristic model unit, the salband clinker temperature state according to corresponding with described salband grog characteristic parameter obtains described salband grog parameter model;
Described salband grog parameter model is Hidden Markov Model (HMM).
Described industrial computer also comprises:
State detection unit is used for the observation sequence of described salband grog characteristic parameter as described salband grog parameter model; Adopt Forward-backward algorithm to calculate the probability of corresponding each the described salband grog parameter model of described observation sequence; The salband clinker temperature state that the salband grog parameter model of the maximum probability that calculates is corresponding is as described salband clinker temperature state.
Described industrial computer also comprises:
State updating unit is used for that the clinker temperature of detection compares when stablizing in described salband clinker temperature state and the kiln, upgrades described salband grog parameter model.
Salband clinker temperature detection method and system in the rotary kiln provided by the invention, fusion by Pyrological data in the rotary kiln and salband image features, reduced because the interior circumstance complication of rotary kiln, coal dust and smog disturb the picture quality impact, have improved the accuracy in detection to salband state of temperature in the rotary kiln; By salband grog characteristic parameter and salband grog parameter model being carried out the similarity contrast, avoided the error manually brought, improved the reliability that salband state of temperature in the rotary kiln is detected.
Description of drawings
Fig. 1 is the process flow diagram of salband clinker temperature detection method embodiment one in the rotary kiln provided by the invention;
Fig. 2 is the process flow diagram of salband clinker temperature detection method embodiment two in the rotary kiln provided by the invention;
Fig. 3 is the structural representation of salband clinker temperature detection system embodiment one in the rotary kiln provided by the invention;
Fig. 4 is the structural representation of salband clinker temperature detection system embodiment two in the rotary kiln provided by the invention.
Embodiment
Fig. 1 is the process flow diagram of salband clinker temperature detection method embodiment one in the rotary kiln provided by the invention, and as shown in Figure 1, the method for the present embodiment can comprise:
Step S101 gathers salband grog image in the rotary kiln, and according to salband grog image in the rotary kiln, obtains salband grog image features.
Particularly, the present embodiment at first uses image collecting device to gather salband grog image in the rotary kiln in order to detect salband clinker temperature in the rotary kiln, for example can use the rotary kiln spy to see the image of salband in the fiery video camera shooting rotary kiln.Then with a certain frame in the image that photographs as salband grog image in this moment rotary kiln, adopt image processing techniques that this two field picture is processed, obtain required salband grog image features.Described salband grog image features can comprise: the parameter informations such as grog brightness, particle shape, height of materials, shadow area.
Step S102 according to Pyrological data in salband grog image features and the rotary kiln, obtains salband grog characteristic parameter.
Particularly, the present embodiment is in order to detect salband clinker temperature in the rotary kiln, also need to obtain Pyrological data in the rotary kiln, and the salband grog image features that obtains among Pyrological data and the step S101 in the use rotary kiln, jointly obtain characterizing the salband grog characteristic parameter of salband grog complete characteristic in the rotary kiln.Because circumstance complication in the rotary kiln, the interference of coal dust and smog is larger, therefore only use salband grog image features or rotary kiln may not obtain exactly salband clinker temperature in the rotary kiln by Pyrological data, therefore Pyrological data in the rotary kiln and salband grog image features are come salband clinker temperature state is judged as salband grog characteristic parameter jointly, thereby can judge the salband clinker temperature more exactly.
Need to prove, in the present embodiment the above-mentioned step execution sequence that obtains Pyrological data in salband grog image features and the rotary kiln is not done restriction, above-mentioned two steps can also be to carry out synchronously, but Pyrological data need to be for synchronization in the salband grog image features that obtains and the rotary kiln.
Step S103 carries out the similarity contrast with salband grog characteristic parameter and salband grog parameter model, obtains salband clinker temperature state.
Particularly, after obtaining salband grog characteristic parameter, this characteristic parameter and salband grog parameter model are carried out the similarity contrast, draw the salband grog parameter model the highest with this characteristic parameter similarity, the corresponding salband clinker temperature of this model state is salband clinker temperature state in this moment rotary kiln.In the present embodiment, described salband clinker temperature state can for: establish that the salband clinker temperature is up to 700 ℃ in the rotary kiln, be up to 1300 ℃, per 100 ℃ are divided into a state, such as 700 ℃～800 ℃ first state, 801 ℃～900 ℃ is the second state, the like totally 6 states.After obtaining the interior salband clinker temperature state of rotary kiln among the above-mentioned steps S103, can be with this State-output to rotary kiln automatic control system or operating personnel.In the practical application in industry, owing to the difference of ore state or owing to the difference to the final products demand, may need to make the temperature of salband in the rotary kiln to be in different state of temperatures.Therefore, after obtaining the interior salband clinker temperature state of rotary kiln, if state of temperature is not required state, rotary kiln automatic control system or operating personnel can be according to the actual requirements, the rotary kiln duty is changed, make rotary kiln salband temperature be in temperature required state, finish the control procedure of closed loop, thus the alumina product practical requirement that sintering is gone out.
Salband clinker temperature detection method in the rotary kiln of the present embodiment, fusion by Pyrological data in the rotary kiln and salband image features, reduced because the interior circumstance complication of rotary kiln, coal dust and smog disturb the picture quality impact, have improved the accuracy in detection to salband state of temperature in the rotary kiln; By salband grog characteristic parameter and salband grog parameter model being carried out the similarity contrast, avoided the error manually brought, improved the reliability that salband state of temperature in the rotary kiln is detected.
Further, among the above-mentioned steps S101, according to salband grog image in the rotary kiln, obtaining salband grog image features specifically can comprise: salband grog image in the rotary kiln is carried out freeze frame, smog filtering, gradation of image stretching, image segmentation processing successively, obtain salband grog area image; In rotary kiln, extract salband grog image features the salband grog area image.
Particularly, the processing procedure that salband grog image in the rotary kiln is carried out is: the grog picture signal that image collecting device collects is after signal amplifier amplifies, by pre-service, it is carried out (1) freeze frame, namely utilize the function that driver provides in the image pick-up card, certain two field picture in the continuous acquisition aluminium oxide flame video; (2) smog filtering, adopt median filter that the grog picture signal is carried out pre-service, eliminate on-the-spot smog to the impact of image, can adopt the moving window of 5 points in the concrete operations, the intermediate value of each gray-scale value in the window is replaced the central point gray-scale value of window; (3) gradation of image stretches, and the grog image after smog filtering is processed carries out linear gray scale and stretches, outstanding grog profile, the contrast of raising grog image; (4) image segmentation, adopt FCM(Fuzzy C-means, fuzzy C-mean algorithm) image partition method, in computing machine with RGB(Red Green Blue, the redgreenblue signal) Data Segmentation becomes 4 zones (to deceive subregion pyrosphere zone, grog zone, kiln wall zone), be partitioned into salband grog area image.From salband grog area image, extract salband grog characteristic parameter.Adopt said method that the salband grog image that obtains is processed, obtain salband grog area image, and from salband grog area image, extract salband grog characteristic parameter, can improve the accuracy of the salband grog characteristic parameter of extraction.
Further, among the above-mentioned steps S102, according to Pyrological data in salband grog image features and the rotary kiln, obtaining salband grog characteristic parameter can comprise: with salband clinker temperature, temperature of kiln head, kiln end temperature, main frame electric current, kiln hood negative pressure as Pyrological data in the rotary kiln; Pyrological data in salband grog image features and the rotary kiln is carried out data fusion obtain salband grog characteristic parameter.
Particularly, Pyrological data can comprise in the rotary kiln: the parameters such as temperature of kiln head, kiln end temperature, main frame electric current, kiln hood negative pressure, salband clinker temperature.Wherein temperature of kiln head, kiln end temperature, salband clinker temperature can obtain by the fiber ratio color temperature measurer detection that is installed in the kiln, the main frame electric current can read at the reometer of rotary kiln main frame, and the kiln hood negative pressure can detect by the pressure transducer that is installed in kiln hood and obtain.Because circumstance complication in the kiln, therefore the salband clinker temperature that records by the fiber ratio color temperature measurer is inaccurate, therefore above-mentioned Pyrological data and salband grog image features are carried out data fusion, jointly come the salband clinker temperature is judged as salband grog characteristic parameter, thereby can judge the salband clinker temperature more exactly.
Fig. 2 is the process flow diagram of salband clinker temperature detection method embodiment two in the rotary kiln provided by the invention, and as shown in Figure 2, the method for the present embodiment can comprise:
Step S201 gathers salband grog image in the rotary kiln, and according to salband grog image in the rotary kiln, obtains salband grog image features.
Step S202 according to Pyrological data in salband grog image features and the rotary kiln, obtains salband grog characteristic parameter.
Step S203, the salband clinker temperature state according to corresponding with described salband grog characteristic parameter obtains described salband grog parameter model.
Particularly, before according to salband grog characteristic parameter and salband grog parameter model salband clinker temperature state being judged, at first need to set up salband grog parameter model, the grog parameter model of the present embodiment adopts HMM(Hidden Markov models, Hidden Markov Model (HMM)).
The application of HMM is divided into two stages to be carried out, i.e. learning phase and reasoning stage.Learning phase is to be set out by the one group of sample that comprises identification result that observes, and finds the parameter of HMM to determine the concrete model structure.The reasoning stage is in the situation that given one group of observation sample and HMM, the output probability of calculating observation sample under each HMM, the highest identification result that is.In the present embodiment, the process of setting up salband grog parameter model is the learning phase of HMM, in the situation that the kiln internal state is stable, can obtain comparatively accurately salband clinker temperature data by the fiber ratio color temperature measurer that is installed in the kiln, with its identification result as HMM, and obtain the salband grog parameter in this moment as the observation sample of HMM, carry out the study of HMM; Perhaps can be judged Pyrological data in salband grog image features and the rotary kiln by the veteran firer of seeing people, obtain the state of temperature judged result, with its identification result as HMM, and obtain the salband grog parameter in this moment as the observation sample of HMM, carry out the study of HMM.
In order to utilize HMM to carry out pattern-recognition, at first the lower limit with clinker temperature is set as 700 ℃, higher limit is set as 1300 ℃, and be divided into state 1 with 700 ℃～800 ℃, 801 ℃～900 ℃ are divided into 2,901 ℃～1000 ℃ of states and are divided into 3,1001 ℃～1100 ℃ of states and are divided into state 4,1101 ℃～1200 ℃ are divided into 5,1201 ℃～1300 ℃ of states and are divided into state 6.Amount to 6 states.
HMM can use five-tuple λ=(M, N, π, A, B) to represent, or is abbreviated as λ=(π, A, B).The meaning of parameters is as follows:
N is state number, 6 states that clinker temperature is divided in the present embodiment, i.e. N={1,2,3,4,5,6}.
M is the observed reading number, extracts the observed reading after the feature in the present embodiment, i.e. M={1,2,3,4}.
π is the probability distribution of original state, is distributed in 6 probability on the state when beginning most in the present embodiment.
The state-transition matrix of A and time-independent.It namely is the probability from a state transitions to another state.
B is under the given state, the observed reading concept matrix.Namely be under certain state, the probability of certain observed reading occurs.
The learning phase concrete steps of HMM can for:
(1) obtains accurately state of temperature judged result by fiber ratio color temperature measurer or the veteran firer of seeing people, and salband image in the rotary kiln in this moment is processed.
(2) extract Pyrological data in salband grog image features and the rotary kiln, obtain salband grog parameter model, as the observation sequence of HMM.
(3) utilize the probability P (O| λ) of Forward-backward algorithm calculating observation value sequence.
(4) utilize the assessment formula in Baum-Welch algorithm to come parameter π, A, B are assessed.
(5) re-use forward direction-backward algorithm and calculate the probability of the sequence of observations of this moment
If
Δ is a given smaller value, and study finishes, otherwise forwards for (4) step to.
When carrying out HMM study, can run into arithmetic underflow and zero probability problem.In calculating, adopt Logarithmic calculation that multiplying is become additive operation in order to solve the arithmetic underflow problem.The method that can adopt threshold value to limit in order to solve the zero probability problem.Threshold value limits and to refer to then its pressure is set as this threshold value, and all relevant parameters are carried out the ratio adjusting, to satisfy constraint condition when revaluation certain parameter out during less than the threshold value of prior agreement.At last study obtains 66 HMM that state is corresponding.
Step S204 is with the observation sequence of salband grog characteristic parameter as salband grog parameter model.
Particularly, obtain the salband parameter model after, just can detect the salband clinker temperature, namely carry out the reasoning stage of HMM.Namely with the observation sequence of salband grog characteristic parameter as salband grog parameter model, detect the clinker temperature state of rotary kiln salband.At first extract salband grog characteristic parameter and with its observation sequence as salband grog parameter model, then read 6 HMM that train.
Step S205 adopts Forward-backward algorithm to calculate the probability of corresponding each the salband grog parameter model of described observation sequence.
Particularly, adopt Forward-backward algorithm to calculate the probability of each HMM among corresponding 6 HMM of above-mentioned observation sequence.
Step S206, the salband clinker temperature state that the salband grog parameter model of the maximum probability that calculates is corresponding is as the testing result of this salband clinker temperature state.
Particularly, calculate the probability of 6 HMM corresponding to observation sequence after, the testing result of salband clinker temperature state in the rotary kiln when state of temperature that the HMM of maximum probability is corresponding is this and detects.
Salband clinker temperature detection method in the rotary kiln of the present embodiment, set up rotary kiln salband clinker temperature state model by adopting Hidden Markov Model (HMM), and obtain rotary kiln salband clinker temperature state according to salband grog characteristic parameter, provide a kind of accurately, reliable salband state of temperature detection method in the rotary kiln.
Further, among the said method embodiment two, after step S206 obtains the testing result of salband clinker temperature state, can also compare renewal salband grog parameter model by the clinker temperature of detection when stablize in this salband clinker temperature state and the kiln.Particularly, when the rotary kiln internal state is stablized, can obtain comparatively accurately salband clinker temperature data by the fiber ratio color temperature measurer that is installed in the kiln, therefore, after the testing result that obtains salband clinker temperature state, if when stablizing with the rotary kiln internal state, state corresponding to the salband clinker temperature data that the fiber ratio color temperature measurer detects is different, then according to the Data Update salband grog parameter model of this detection.Thereby can further improve the accuracy of salband clinker temperature state-detection in the rotary kiln.
Fig. 3 is the structural representation of salband clinker temperature detection system embodiment one in the rotary kiln provided by the invention, and as shown in Figure 3, the system of the present embodiment can comprise: image collecting device 31 and industrial computer 32.
Particularly, image collecting device 31 can be seen convex lens video camera etc. for the rotary kiln spy and be used for taking the industrial camera of situation in the rotary kiln, by concentric cable the image that photographs is sent to industrial computer 32.Further, the image collecting device 31 of the present embodiment can also be sent to monitor with another road signal by concentric cable, directly observes image in the rotary kiln for operating personnel.
Particularly, industrial computer 32 is used for carrying out each step of embodiment of the method shown in Figure 1.
Salband clinker temperature detection system is used for carrying out the technical scheme of embodiment of the method shown in Figure 1 in the rotary kiln of the present embodiment, and its realization principle and technique effect are similar, repeat no more herein.
Fig. 4 is the structural representation of salband clinker temperature detection system embodiment two in the rotary kiln provided by the invention, and as shown in Figure 4, the system of the present embodiment is on the basis of system shown in Figure 3, and industrial computer 32 can comprise:
Graphics processing unit 41 is used for salband grog image in the rotary kiln is carried out freeze frame, smog filtering, gradation of image stretching, image segmentation processing successively, obtains salband grog image.
Particularly, graphics processing unit 41 can comprise image pick-up card and be installed in image processing software in the industrial computer, be digital signal by image pick-up card with the image transitions that image collecting device 31 collects, and use by image processing software image is treated to required salband grog image.
Feature extraction unit 42 is extracted salband grog image features for salband grog image in rotary kiln; With salband clinker temperature, temperature of kiln head, kiln end temperature, main frame electric current, kiln hood negative pressure as Pyrological data in the rotary kiln.
State detection unit 45 is used for the observation sequence of salband grog characteristic parameter as salband grog parameter model; Adopt the probability of corresponding each the described salband grog parameter model of Forward-backward algorithm calculating observation sequence; The salband clinker temperature state that the salband grog parameter model of the maximum probability that calculates is corresponding is as described salband clinker temperature state.
Salband clinker temperature detection system in the rotary kiln of the present embodiment, fusion by Pyrological data in the rotary kiln and salband image features, reduced because the interior circumstance complication of rotary kiln, coal dust and smog disturb the picture quality impact, have improved the accuracy in detection to salband state of temperature in the rotary kiln; By salband grog characteristic parameter and salband grog parameter model being carried out the similarity contrast, avoided the error manually brought, improved equally the reliability that salband state of temperature in the rotary kiln is detected.
It should be noted that at last: above each embodiment is not intended to limit only in order to technical scheme of the present invention to be described; Although with reference to aforementioned each embodiment the present invention is had been described in detail, those of ordinary skill in the art is to be understood that: it still can be made amendment to the technical scheme that aforementioned each embodiment puts down in writing, and perhaps some or all of technical characterictic wherein is equal to replacement; And these modifications or replacement do not make the essence of appropriate technical solution break away from the scope of various embodiments of the present invention technical scheme.
Claims (10)
1. the interior salband clinker temperature detection method of rotary kiln is characterized in that, comprising:
Gather salband grog image in the rotary kiln, and according to salband grog image in the described rotary kiln, obtain salband grog image features;
According to Pyrological data in described salband grog image features and the rotary kiln, obtain salband grog characteristic parameter;
Described salband grog characteristic parameter and salband grog parameter model are carried out the similarity contrast, obtain salband clinker temperature state.
2. method according to claim 1 is characterized in that, the interior salband grog image of the rotary kiln that described basis collects obtains salband grog image features and comprises:
Salband grog image in the described rotary kiln is carried out freeze frame, smog filtering, gradation of image stretching, image segmentation processing successively, obtain described salband grog area image;
In described rotary kiln, extract described salband grog image features the salband grog area image;
Described according to Pyrological data in described salband grog image features and the rotary kiln, obtain salband grog characteristic parameter and comprise:
With salband clinker temperature, temperature of kiln head, kiln end temperature, main frame electric current, kiln hood negative pressure as Pyrological data in the described rotary kiln;
Pyrological data in described salband grog image features and the described rotary kiln is carried out data fusion obtain described salband grog characteristic parameter.
3. method according to claim 1 and 2 is characterized in that, described described salband grog characteristic parameter and salband grog parameter model are compared obtains also comprising before the salband clinker temperature state:
Salband clinker temperature state according to corresponding with described salband grog characteristic parameter obtains described salband grog parameter model;
Described salband grog parameter model is Hidden Markov Model (HMM).
4. method according to claim 3 is characterized in that, described described salband grog characteristic parameter and salband grog parameter model is carried out the similarity contrast, comprising:
With the observation sequence of described salband grog characteristic parameter as described salband grog parameter model;
Adopt Forward-backward algorithm to calculate the probability of corresponding each the described salband grog parameter model of described observation sequence;
The salband clinker temperature state that the salband grog parameter model of the maximum probability that calculates is corresponding is as described salband clinker temperature state.
5. method according to claim 4 is characterized in that, described described salband grog characteristic parameter and salband grog parameter model is compared, and obtains also comprising after the salband clinker temperature state:
The clinker temperature that detects when stablizing in described salband clinker temperature state and the kiln compares, and upgrades described salband grog parameter model.
6. the interior salband clinker temperature detection system of rotary kiln is characterized in that, comprising: image collecting device and industrial computer;
Described image collecting device is used for gathering salband grog image in the rotary kiln, and sends described salband grog image to industrial computer;
Described industrial computer is used for obtaining salband grog image features according to salband grog image in the rotary kiln that collects; According to Pyrological data in described salband grog image features and the rotary kiln, obtain salband grog characteristic parameter; Described salband grog characteristic parameter and salband grog parameter model are carried out the similarity contrast, obtain salband clinker temperature state.
7. system according to claim 6 is characterized in that, described industrial computer comprises:
Graphics processing unit is used for salband grog image in the described rotary kiln is carried out freeze frame, smog filtering, gradation of image stretching, image segmentation processing successively, obtains described salband grog image;
Feature extraction unit is extracted described salband grog image features for salband grog image in described rotary kiln; With salband clinker temperature, temperature of kiln head, kiln end temperature, main frame electric current, kiln hood negative pressure as Pyrological data in the described rotary kiln;
The data fusion unit is used for that Pyrological data in described salband grog image features and the described rotary kiln is carried out data fusion and obtains described salband grog characteristic parameter.
8. according to claim 6 or 7 described systems, it is characterized in that, described industrial computer also comprises:
The characteristic model unit, the salband clinker temperature state according to corresponding with described salband grog characteristic parameter obtains described salband grog parameter model;
Described salband grog parameter model is Hidden Markov Model (HMM).
9. system according to claim 8 is characterized in that, described industrial computer also comprises:
State detection unit is used for the observation sequence of described salband grog characteristic parameter as described salband grog parameter model; Adopt Forward-backward algorithm to calculate the probability of corresponding each the described salband grog parameter model of described observation sequence; The salband clinker temperature state that the salband grog parameter model of the maximum probability that calculates is corresponding is as described salband clinker temperature state.
10. system according to claim 9 is characterized in that, described industrial computer also comprises:
State updating unit is used for that the clinker temperature of detection compares when stablizing in described salband clinker temperature state and the kiln, upgrades described salband grog parameter model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210462495.0A CN102928118B (en) | 2012-11-16 | 2012-11-16 | Detection method and system for clinker temperature of cooling zone in rotary kiln |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201210462495.0A CN102928118B (en) | 2012-11-16 | 2012-11-16 | Detection method and system for clinker temperature of cooling zone in rotary kiln |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102928118A true CN102928118A (en) | 2013-02-13 |
| CN102928118B CN102928118B (en) | 2014-12-24 |
Family
ID=47642973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201210462495.0A Active CN102928118B (en) | 2012-11-16 | 2012-11-16 | Detection method and system for clinker temperature of cooling zone in rotary kiln |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102928118B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103557965A (en) * | 2013-11-25 | 2014-02-05 | 北京汉能清源科技有限公司 | Method for measuring temperature of rotary cement kiln and method and device for online detection of temperature field of rotary cement kiln |
| CN104634478A (en) * | 2015-03-06 | 2015-05-20 | 沈阳工业大学 | Soft measurement method for burning zone temperature of rotary kiln |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH01291016A (en) * | 1988-05-19 | 1989-11-22 | Sumitomo Cement Co Ltd | Measurement of secondary air-temperature of furnace |
| CN1821756A (en) * | 2006-03-30 | 2006-08-23 | 湖南大学 | Computer detecting method and device for rotary kiln sintered clinker quality |
-
2012
- 2012-11-16 CN CN201210462495.0A patent/CN102928118B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH01291016A (en) * | 1988-05-19 | 1989-11-22 | Sumitomo Cement Co Ltd | Measurement of secondary air-temperature of furnace |
| CN1821756A (en) * | 2006-03-30 | 2006-08-23 | 湖南大学 | Computer detecting method and device for rotary kiln sintered clinker quality |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103557965A (en) * | 2013-11-25 | 2014-02-05 | 北京汉能清源科技有限公司 | Method for measuring temperature of rotary cement kiln and method and device for online detection of temperature field of rotary cement kiln |
| CN103557965B (en) * | 2013-11-25 | 2015-10-07 | 北京汉能清源科技有限公司 | Cement rotary kiln temperature measuring and temperature field online test method, device |
| CN104634478A (en) * | 2015-03-06 | 2015-05-20 | 沈阳工业大学 | Soft measurement method for burning zone temperature of rotary kiln |
| CN104634478B (en) * | 2015-03-06 | 2018-01-16 | 沈阳工业大学 | A kind of flexible measurement method of calcined by rotary kiln with temperature |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102928118B (en) | 2014-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112883819B (en) | Multi-target tracking method, device, system and computer readable storage medium | |
| CN107507173B (en) | No-reference definition evaluation method and system for full-slice image | |
| JP5603403B2 (en) | Object counting method, object counting apparatus, and object counting program | |
| CN107705288B (en) | Infrared video detection method for dangerous gas leakage under strong interference of pseudo-target motion | |
| CN103279765B (en) | Steel wire rope surface damage detection method based on images match | |
| CN103597514B (en) | Object detection frame display device and object detection frame display packing | |
| CN103279763B (en) | A kind of wheel hub type automatic identifying method of structure based feature | |
| JP6565600B2 (en) | Attention detection device and attention detection method | |
| CN107133969A (en) | A kind of mobile platform moving target detecting method based on background back projection | |
| CN103177456A (en) | Method for detecting moving target of video image | |
| EP2965262A1 (en) | Method for detecting and tracking objects in sequence of images of scene acquired by stationary camera | |
| CN104700430A (en) | Method for detecting movement of airborne displays | |
| EP3733876B1 (en) | System and method for evaluating operational conditions of blast furnace | |
| CN107428261B (en) | Lifting hook detection device based on image processing | |
| CN109724776B (en) | Method and device for determining damage degree of grate bar of sintering machine trolley | |
| CN110263662B (en) | Human body contour key point and key part identification method based on grading | |
| CN103020635B (en) | Sintering belt temperature checking method and system in rotary kiln | |
| CN109636835B (en) | Foreground object detection method based on template optical flow | |
| CN108364306B (en) | Visual real-time detection method for high-speed periodic motion | |
| CN103578121B (en) | Method for testing motion based on shared Gauss model under disturbed motion environment | |
| JP4713261B2 (en) | Cell culture equipment | |
| CN102928118A (en) | Detection method and system for clinker temperature of cooling zone in rotary kiln | |
| JP2001357402A (en) | Method and device for detecting vehicle | |
| CN110827263A (en) | Magnetic shoe surface defect detection system and detection method based on visual identification technology | |
| CN111768390B (en) | Image recognition-based grate cooler red river recognition method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |