CN117078023A - Kiln fault risk assessment method based on big data analysis - Google Patents
Kiln fault risk assessment method based on big data analysis Download PDFInfo
- Publication number
- CN117078023A CN117078023A CN202311337906.8A CN202311337906A CN117078023A CN 117078023 A CN117078023 A CN 117078023A CN 202311337906 A CN202311337906 A CN 202311337906A CN 117078023 A CN117078023 A CN 117078023A
- Authority
- CN
- China
- Prior art keywords
- sintering
- time window
- stage
- sintering stage
- kiln
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000012502 risk assessment Methods 0.000 title claims abstract description 32
- 238000007405 data analysis Methods 0.000 title claims abstract description 23
- 238000005245 sintering Methods 0.000 claims abstract description 197
- 238000012544 monitoring process Methods 0.000 claims abstract description 22
- 239000011159 matrix material Substances 0.000 claims abstract description 19
- 230000008569 process Effects 0.000 claims abstract description 13
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 claims description 33
- 239000001301 oxygen Substances 0.000 claims description 33
- 229910052760 oxygen Inorganic materials 0.000 claims description 33
- 230000008859 change Effects 0.000 claims description 18
- 238000010438 heat treatment Methods 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 5
- 238000001816 cooling Methods 0.000 claims description 5
- 230000000087 stabilizing effect Effects 0.000 claims description 4
- 238000000513 principal component analysis Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 4
- 239000000919 ceramic Substances 0.000 description 14
- 230000002159 abnormal effect Effects 0.000 description 8
- 230000000630 rising effect Effects 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 6
- 238000013480 data collection Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000010606 normalization Methods 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 238000004140 cleaning Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 239000007789 gas Substances 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- BASFCYQUMIYNBI-UHFFFAOYSA-N platinum Chemical compound [Pt] BASFCYQUMIYNBI-UHFFFAOYSA-N 0.000 description 2
- 239000002994 raw material Substances 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000004566 building material Substances 0.000 description 1
- 238000001354 calcination Methods 0.000 description 1
- 239000004568 cement Substances 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000002485 combustion reaction Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005272 metallurgy Methods 0.000 description 1
- 229910052697 platinum Inorganic materials 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000012847 principal component analysis method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 239000011819 refractory material Substances 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000000779 smoke Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000008646 thermal stress Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/04—Manufacturing
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Theoretical Computer Science (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Manufacturing & Machinery (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Manufacture And Refinement Of Metals (AREA)
Abstract
The application relates to the field of digital data processing, in particular to a kiln fault risk assessment method based on big data analysis, which is used for collecting real-time monitoring data sequences and reference data sequences of parameters of a rotary kiln; dividing the sintering process of the rotary furnace into sintering stages; for each sintering stage, constructing a feature matrix of the sintering stage, and extracting key components of each parameter of the sintering stage; and analyzing the weight of each parameter in the sintering stage; obtaining sintering state parameters of the sintering stage according to key components and weights of each parameter of the sintering stage; acquiring sintering state parameters of each time window, and acquiring sintering stage membership of the time window according to Euclidean distance between the time window and the sintering state parameters of each sintering stage; obtaining a rotary furnace fault risk index of the time window according to the membership degree of the sintering stage of the adjacent time window; and evaluating the fault risk of the rotary furnace in the time window according to the fault risk index of the rotary furnace. Thereby realizing accurate assessment of the fault risk of the kiln.
Description
Technical Field
The application relates to the field of digital data processing, in particular to a kiln fault risk assessment method based on big data analysis.
Background
The kiln is a device for heating and treating materials, which is widely used in industries of metallurgy, chemical industry, building materials, etc., and meanwhile, the kiln can be classified into various types according to purposes, and the rotary kiln belongs to one of the kilns, which is a thermal device and can be used for calcining, roasting or drying granular or powdery materials, such as cement, ceramics, refractory materials, etc. The working principle of the rotary furnace is to utilize the inclination and rotation of the cylinder body to make the materials and combustion perform chemical reaction at high temperature. The rotary furnace belongs to high-temperature equipment, if faults possibly cause fire, explosion and other safety accidents, potential safety hazards can be found in time through fault risk assessment, corresponding measures are taken for repair and improvement, and therefore production efficiency is improved, maintenance cost is reduced, and the like.
In the failure risk assessment of modern ceramic rotary furnaces, a time sequence prediction algorithm, such as a moving average method, is often used, and the algorithm is used for predicting based on historical data occurring before real-time monitoring data. In this scenario, if the prediction is performed using a moving average method at a normal sintering phase change time point, a difference between the predicted data and the normal data will occur to cause a false prediction, thereby affecting the rotary kiln fault risk assessment result.
In summary, the application provides a kiln fault risk assessment method based on big data analysis, which collects operation data of a ceramic rotary kiln through different sensors, divides different sintering stages of a normal working state of the rotary kiln based on preprocessed data time sequence characteristics, constructs sintering state parameters according to parameter self-change and interrelation among the parameters in the different sintering stages, finally calculates the sintering stage membership of a real-time monitoring data time window, further judges whether the data is abnormal, and completes assessment of the rotary kiln fault risk.
Disclosure of Invention
In order to solve the technical problems, the application provides a kiln fault risk assessment method based on big data analysis, so as to solve the existing problems.
The kiln fault risk assessment method based on big data analysis adopts the following technical scheme:
the embodiment of the application provides a kiln fault risk assessment method based on big data analysis, which comprises the following steps:
collecting real-time monitoring data sequences of parameters of the rotary furnace, wherein the parameters comprise temperature, oxygen content and pressure, and recording the data sequences of the parameters of the normal working state of the rotary furnace as reference data sequences;
dividing the rotary furnace sintering process into sintering stages according to the change of the temperature reference data sequence; for each sintering stage, constructing a feature matrix of the sintering stage according to data of each parameter in a data acquisition period corresponding to the sintering stage, and combining PCA main component analysis and the feature matrix to obtain key components of each parameter of the sintering stage; obtaining the weight of each parameter of the sintering stage according to the relation between the data of each parameter in the corresponding data acquisition period of the sintering stage; obtaining sintering state parameters of the sintering stage according to key components and weights of each parameter of the sintering stage;
acquiring sintering state parameters of each sintering stage, constructing a time window for monitoring a data sequence in real time, acquiring the sintering state parameters of each time window, and acquiring the sintering stage membership degree of the time window according to the Euclidean distance between the time window and the sintering state parameters of each sintering stage; obtaining a rotary furnace fault risk index of the time window according to the membership degree of the sintering stage of the adjacent time window; and evaluating the fault risk of the rotary furnace in the time window according to the fault risk index of the rotary furnace.
Further, the dividing the rotary kiln sintering process into sintering stages according to the change of the temperature reference data sequence comprises the following steps:
taking a sequence formed by the difference values of the adjacent previous temperature reference data and the adjacent next temperature reference data in the temperature reference data sequence as a first-order differential sequence, and acquiring inflection points in the first-order differential sequence; and taking the latter temperature reference data corresponding to the inflection point in the temperature reference data sequence as the corresponding point of the inflection point, and dividing the temperature reference data sequence according to the corresponding points to obtain each sintering stage of the rotary furnace sintering process, wherein each sintering stage comprises a heating stage, a stabilizing stage and a cooling stage.
Further, the constructing the feature matrix of the sintering stage includes:
and calculating the average value, standard deviation, maximum value and inclination of the reference data corresponding to each parameter in the data acquisition period corresponding to the sintering stage, and taking the average value standard deviation, maximum value and inclination of each parameter as each row of the feature matrix.
Further, the key components for obtaining each parameter in the sintering stage by combining PCA main component analysis and feature matrix comprise:
and carrying out PCA principal component analysis on each row vector in the feature matrix to obtain a first principal component vector corresponding to each row vector, and taking the first principal component vector as a key component of a corresponding parameter.
Further, the obtaining the weight of each parameter of the sintering stage according to the relation between the parameter data in the corresponding data acquisition period of the sintering stage includes:
respectively calculating pearson correlation coefficients between a temperature reference data sequence, an oxygen content reference data sequence and a pressure reference data sequence in a data acquisition period corresponding to the sintering stage, respectively marking the pearson correlation coefficients as a first temperature correlation coefficient and a second temperature correlation coefficient, and taking the sum of the first temperature correlation coefficient and the second temperature correlation coefficient as the temperature weight of the sintering stage;
calculating a pearson correlation coefficient between an oxygen content reference data sequence and a pressure reference data sequence in a data acquisition period corresponding to the sintering stage, recording the pearson correlation coefficient as an oxygen pressure correlation coefficient, and taking the sum of the oxygen pressure correlation coefficient and the reciprocal of a first temperature correlation coefficient as the weight of the oxygen content in the sintering stage;
and taking the sum of the second temperature correlation coefficient reciprocal and the oxygen pressure correlation coefficient reciprocal as the weight of the sintering stage pressure.
Further, the obtaining the sintering state parameters of the sintering stage according to the key components and weights of the parameters of the sintering stage includes: taking the sum of the products of the key components and the weights of all parameters of the sintering stage as the sintering state parameters of the sintering stage.
Further, the constructing a time window for monitoring the data sequence in real time includes:
with a fixed length of 1The L window divides the real-time monitoring data sequence of each parameter, and the fixed length is 1 +.>The L window is a time window, wherein L is the length of the time window.
Further, the obtaining the membership degree of the sintering stage of the time window according to the Euclidean distance between the time window and the sintering state parameters of each sintering stage includes:
and taking the minimum value of Euclidean distance between the time window and the sintering state parameters of each sintering stage as the membership degree of the sintering stage of the time window.
Further, the method obtains the rotary furnace fault risk index of the time window according to the membership degree of the sintering stage of the adjacent time window, specifically comprises the following steps:
calculating the membership degree sum value of the sintering stage of the current time window and the sintering stage of the next time window, obtaining the difference value between the sum value and a preset threshold value, and taking the normalized result of the ratio of the difference value to the sum value as a rotary furnace fault risk index of the current time window.
Further, the evaluating the risk of the rotary furnace fault in the time window according to the risk index of the rotary furnace fault comprises: and when the fault risk index of the rotary furnace is higher than the risk threshold, judging that the rotary furnace has fault risk in the time window, and when the fault risk index of the rotary furnace is lower than the risk threshold, judging that the rotary furnace does not have fault risk in the time window.
The application has at least the following beneficial effects:
according to the application, the working state of the normal rotary furnace is divided into different sintering stages based on the temperature time sequence characteristics of the reference data, the characteristic matrix is constructed according to the parameter characteristics of different sintering stages, and then the key components of the parameters of each stage are obtained by dimension reduction, so that the calculated amount can be reduced, and the influence of irrelevant factors is avoided; meanwhile, parameter weight calculation is determined according to the mutual connection among the parameters of different sintering stages, sintering state parameters are obtained, the sintering stage membership degree of a time window is monitored and calculated on real-time data to judge whether the obtained real-time data is abnormal, the error prediction data generated by a conventional prediction algorithm at different sintering stage change time points is avoided, the influence on the rotary furnace fault risk assessment result is prevented, and the rotary furnace fault risk assessment precision is improved.
Drawings
In order to more clearly illustrate the embodiments of the application or the technical solutions and advantages of the prior art, the following description will briefly explain the drawings used in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the application, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flow chart of a kiln fault risk assessment method based on big data analysis.
Detailed Description
In order to further describe the technical means and effects adopted by the application to achieve the preset aim, the following detailed description is given below of the detailed implementation, structure, characteristics and effects of the kiln fault risk assessment method based on big data analysis according to the application in combination with the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
The detailed scheme of the kiln fault risk assessment method based on big data analysis provided by the application is specifically described below with reference to the accompanying drawings.
The application provides a kiln fault risk assessment method based on big data analysis.
Specifically, the following kiln fault risk assessment method based on big data analysis is provided, please refer to fig. 1, and the method comprises the following steps:
and S001, collecting operation data of the ceramsite rotary furnace through different sensors, and performing pretreatment operation on the data.
Different sensors are installed in modern haydite rotary furnace equipment to collect dataThe platinum resistance temperature sensor is fixedly arranged at the middle section position in the rotary furnace to collect temperature data in the rotary furnace; installing an oxygen sensor at a smoke discharge port of the rotary furnace to collect the oxygen content in the rotary furnace; absolute pressure sensors are arranged on the side wall of the rotary furnace to collect pressure data in the rotary furnace, and every +.>The second acquisition of a group of real-time data including temperature, oxygen content and pressure, the acquisition time interval parameter implementation person can select according to the actual situation, the application selects the experience value +.>. Besides the above-mentioned real-time data, the historical data of three parameters of a complete ceramsite sintering period of the rotary kiln in normal working state are collected in advance, and are used as reference data sequences of all the parameters so as to be used for subsequent analysis of sintering stage, and the reference data collection time interval of all the parameters is set as experience value as well>The collection time is determined by the sintering time of the ceramic finished product. Preprocessing the two types of data, including data cleaning and normalization operation, to obtain normalized temperature reference data sequence ++>Oxygen content reference data sequence->Pressure reference data sequence->Real-time monitoring temperature data sequence to be analyzed +.>Oxygen content data sequence->Pressure data sequence->The above data cleaning and normalization are known techniques and will not be described in detail herein.
So far, the method can be used for acquiring the running data of the rotary furnace, and carrying out normalization processing on the data to serve as the basic data for analyzing the running condition of the rotary furnace.
Step S002: dividing different sintering stages of the normal working state of the rotary furnace based on the preprocessed data time sequence characteristics, constructing sintering state parameters according to the parameter self-change and the interrelation among the parameters in the different sintering stages, and calculating the sintering stage membership of the real-time monitoring data time window.
In the embodiment, three parameters of the rotary furnace are collected together, wherein the temperature is used as a key parameter, so that the sintering curve can be reflected, whether the sintering curve is in a normal interval or not can be judged, and the problems of overlarge thermal stress and the like can be early warned when the temperature gradient is abnormal; when the oxygen content is too low, carburization phenomenon is caused; the pressure data show the uniformity of the air flow distribution in the rotary furnace, and the fault risk assessment method of the rotary furnace is completed by analyzing the parameter change trend and the internal relation between the parameters.
In the process of sintering ceramic grains by the rotary furnace, parameters are not constant, and corresponding changes of the parameters can be generated for different ceramic grain sintering stages, and the temperature parameters are taken as an example. In the preheating stage, the temperature of the rotary kiln is slowly increased toLeft and right, so as to evaporate the adsorbed moisture on the raw materials; gradually rise to +.>About, sintering and combining the raw material particles to form solid ceramsite; is kept at +.>Left and right, carrying out comprehensive sintering; finally, the temperature is gradually reduced to +.>The sintering is completed below. That is, if the real-time collected data is changed, it cannot be said that the rotary kiln is necessarily in fault, possibly due to the change of the sintering phase of the ceramic grains, then the change of the data needs to be judged to be the normal change caused by the change of the sintering phase or the abnormal change caused by the fault when the collected data is analyzed.
Firstly, the embodiment determines the data characteristics of each sintering stage of the ceramic grains by analyzing each reference data sequence, wherein the temperature is a parameter which can intuitively reflect the working state of the rotary furnace, and a complete ceramic grain sintering period can be known to comprise a plurality of heating stages, stabilizing stages and final cooling stages by priori knowledge, and the temperature reference data sequence is calculated and obtained firstlyThe first-order differential sequence of the first-order differential sequence is detected by detecting each inflection point (local extreme point) of the first-order differential sequence, wherein the acquisition time corresponding to the inflection point data is the time point representing the change of the sintering stage, and the description is that the corresponding later temperature reference data of the inflection point in the temperature reference data sequence is taken as the corresponding point of the inflection point, namely the corresponding point of the first element of the first-order differential sequence is taken as the second temperature reference data of the temperature reference data sequence, and the first-order differential sequence is characterized in thatThe first element of the temperature reference data sequence is not an inflection point, namely the subsequent analysis content is not influenced, because the temperature is in a heating stage from the beginning when the ceramic grains are sintered. Counting the number of inflection points as M, this +.>The inflection points divide the temperature reference data sequence into +.>Each divided temperature reference data corresponds to one sintering stage, and the sintering stages are respectively marked as heating-up stages +.>Stage of stabilization->And cooling stage->Wherein->And->The reference numerals of the heating stage and the stabilizing stage are respectively given.
After the acquisition time is divided according to the stages, the characteristics of each parameter and the mutual relevance in each sintering stage are analyzed to obtain a first heating stage of the sintering stageFor example, the temperature, oxygen content and pressure data at the acquisition time included in the stage are extracted, and the average value and standard deviation of the temperature, oxygen content and pressure parameters in the data acquisition time period corresponding to the first temperature raising stage are calculated and recorded as->、/>、/>And->、/>、Reflecting the central trend and the discrete degree of the parameter at the stage; then respectively obtaining the maximum value and the gradient of the temperature, the oxygen content and the pressure parameter in the first temperature rising stage, which are respectively marked as +.>、/>、/>And->、、/>Reflecting the extreme value and the distribution shape of the phase parameters, based on which the present embodiment will construct a first temperature rise phaseFeature matrix +.>The following is shown:
each column of data in the feature matrix is identicalThe feature matrix is subjected to dimension reduction by adopting a PCA principal component analysis method, noise and redundant information are removed, the most important features are screened, first principal component vectors are obtained according to the order of the interpretation variance, each first principal component vector is used as a key component of a corresponding parameter, and each first principal component vector obtains a one-dimensional feature matrix：
In the method, in the process of the application,temperature-critical component representing the first temperature rise phase corresponding to the temperature parameter, < >>And (3) withRespectively represents the oxygen content key component and the pressure key component of the first temperature rising stage.
The rate of change of temperature is also different in the different heating stages, e.g. the temperature needs to be increased to the first heating stageAbout, the temperature rise at this stage is relatively slow to fully evaporate the water; in the second heating stage, the temperature needs to be increased toAbout, the temperature rise at this stage is faster; the power of the rotary furnace equipment in the subsequent temperature rising stage is slowly increased, and the temperature is required to be increased for a long time; meanwhile, in the cooling stage after sintering, if the temperature is not uniform, a large temperature difference is generated, so that the ceramic particles are broken, and the like, so that the ceramic particles are naturally cooled, and the temperature change is slower. That is to say the relationship between the temperature and the oxygen content and the pressure during the different temperature variation phases of the normal operation of the rotary kiln plantNor is it exactly the same, so that the interrelationship of the three parameters is likewise determined for each sintering stage.
Taking the first temperature rising stage of the sintering stage as an example, the data acquisition period corresponding to the first temperature rising stage is recorded asThis->The corresponding temperature reference data sequence of the first temperature rising stage in the time period is +.>The reference data sequence of oxygen content is +.>The pressure reference data sequence is->. In the heating stage, the temperature rise accelerates the consumption of oxygen, the change of the oxygen content can influence the sintering atmosphere, and further the sintering effect of the ceramsite, meanwhile, the temperature rise can expand the gas in the rotary furnace, so that the pressure rise is caused, the gas flow in the rotary furnace is uniform under the condition of stable pressure, and the sintering uniformity can be improved. From the above, it can be seen that, although the correlations between the parameters in the different temperature change phases are not exactly the same, the parameters still have a certain linear relationship under the normal condition of the device, and then the pearson correlation coefficients between the parameters are calculated to determine the linear correlation degree, and the pearson correlation coefficient between the temperature reference data sequence and the oxygen content reference data sequence in the data collection period corresponding to the first temperature rise phase, the pearson correlation coefficient between the temperature reference data sequence and the pressure reference data sequence in the data collection period corresponding to the first temperature rise phase, and the pearson correlation coefficient between the oxygen content reference data sequence and the pressure reference data sequence in the data collection period corresponding to the first temperature rise phase are calculated. Then for the first temperature rise phase its sintering state parameter +.>The calculations are as follows:
wherein the method comprises the steps of、/>And +.>The weights of the temperature, the oxygen content and the pressure in the first heating stage are respectively; />A first temperature-related coefficient that is a first temperature-increasing stage; />A second temperature-related coefficient for the first temperature-increasing stage; />The oxygen pressure correlation coefficient is the oxygen pressure correlation coefficient of the first temperature rising stage; />The sintering state parameter is the sintering state parameter of the first heating stage; />The parameter is a parameter adjustment factor, avoiding the situation that the denominator is 0, and taking an empirical value in the embodiment。
When the weight of a certain parameter in the first temperature raising stage is larger, the importance of the key component for the parameter in the stage is larger, the sintering state parameter of the first temperature raising stageThe larger. The sintering state parameters of the first temperature rising stage of the rotary furnace equipment during normal operation can be obtained through the calculation process.
Repeating the method of the embodiment to obtain the sintering state parameters of the rest stages respectively, so as to obtain the sintering state parameters of each stage under the normal working condition of the rotary furnace.
Then, the embodiment analyzes the real-time monitoring data of each parameter of the rotary furnace, calculates the membership degree of the sintering stage of the real-time monitoring data, and judges whether the sintering stage belongs to a certain sintering stage under the normal working condition of the equipment.
For the ceramic grains sintered by the modern industrial rotary furnace, the average sintering time of the large ceramic grains is about one day, and then whether the real-time monitoring data at a single acquisition time belongs to a certain sintering stage cannot be accurately judged, so that the sliding window is used for judging the real-time monitoring data in the embodiment, specifically:
the fixed-length time window is used for collecting real-time monitoring data, key components and weights of all parameters in the time window are calculated in the same mode in the embodiment, so that sintering state parameters of the current monitoring time window are obtained, and compared with sintering state parameters of each stage in reference data to judge whether the monitoring data in the current time window is abnormal or not, and therefore the fault risk of the rotary furnace is evaluated. In this embodiment, 1 is usedL is the length of the time window, which can be set by the implementer by himself,in this embodiment, the empirical value is taken according to the average sintering time period>The practitioner sets the length of the time window in the respective line, here +.>The sintering state parameter of the individual time windows is +.>Then->Sintering stage membership of the individual time windows +.>The calculation method comprises the following steps:
wherein,indicate->Euclidean distance between the sintering state parameter of the time window and the sintering state parameter of the ith stage of the reference data; u is the number of sintering stages; />Is->Membership of sintering stage of each time window;to take a minimum function. According to the membership degree of the sintering stage, the sintering state of the time window is closest to the state of the sintering stage with the minimum Euclidean distance between the sintering state parameters in the normal sintering process.
The method in the embodiment is repeated, the membership degree of the sintering stage in each time window can be calculated, and the method is used for analyzing and evaluating the fault risk condition of the rotary furnace in each time window.
Step S003: and judging whether the data is abnormal or not based on the membership degree of the sintering stage of the time window in the real-time monitoring data sequence, and completing the fault risk assessment of the rotary furnace.
According to the method of the embodiment, the membership degree of the sintering stage of each time window of the real-time monitoring data sequence can be obtained, the detection result of the membership degree of the sintering stage of the time window of the embodiment is analyzed, and if the detection result is the firstSintering stage membership of the individual time windows +.>Less than threshold->It is then stated that the sintering state of the time window belongs to a certain sintering phase of the rotary kiln in normal operation, whereas when it is greater than the threshold +.>When the sintering state parameter of the time window and the data in the reference data sintering state parameter set are larger in difference, the time window is possibly a time window of the rotary furnace fault, but also possibly the real-time data acquired by the fixed-length time window is just at the node of the sintering stage change, so that the subsequent real-time data can be acquired again and the (th) can be calculated according to the situation>Sintering stage membership of the individual time windows +.>If the degree of membership in the sintering stage +.>、/>Are all greater than threshold->Then->The data collected by each time window is abnormal, and a rotary furnace fault risk index is constructed according to the membership degree of the sintering stage>The specific calculation process is as follows:
wherein,is->Rotary furnace fault risk indexes of the time windows; />And->Respectively +.>Time window and->Membership of sintering stage of each time window; />As the threshold value, the parameter can be selected by the practitioner according to the actual situation, in this embodiment, the tested value +.>；/>Is normalized.
When the first isTime window and->Sintering stage membership of the individual time windows +.>、/>Are all greater than threshold->Description of the->Abnormality of data in each time window, i.e. molecules in the above formulaThe larger the time window is, the more likely the rotary furnace is in fault, and the corresponding rotary furnace fault risk index is +.>The larger. Risk indicator for faults of rotary furnace>When the risk threshold value is larger than the risk threshold value, the situation that the rotary furnace is at fault risk is indicated, and related maintenance personnel are timely prompted to overhaul the rotary furnace, so that faults are avoided. It should be noted that, the setting implementation of the risk threshold may be selected by the user, and in this embodiment, the risk threshold is 0.3.
In summary, the embodiment of the application divides the working state of the normal rotary furnace into different sintering stages based on the temperature time sequence characteristics of the reference data, constructs a feature matrix according to the parameter characteristics of different sintering stages, and then reduces the dimension to obtain key components of each parameter of each stage, thereby reducing the overall calculated amount and avoiding the influence of irrelevant data;
meanwhile, according to the embodiment of the application, the parameter weight is determined according to the mutual connection between the parameters of different sintering stages to calculate and acquire the sintering state parameters, the sintering stage membership of the calculation time window is monitored on the real-time data to judge whether the acquired real-time data is abnormal, the generation of misprediction data at the changing time points of different sintering stages by a conventional prediction algorithm is avoided, the influence on the fault risk assessment result of the rotary furnace is prevented, and the fault risk assessment precision of the rotary furnace is improved.
It should be noted that: the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
In this specification, each embodiment is described in a progressive manner, and the same or similar parts of each embodiment are referred to each other, and each embodiment mainly describes differences from other embodiments.
The above embodiments are only for illustrating the technical solution of the present application, and not for limiting the same; the technical solutions described in the foregoing embodiments are modified or some of the technical features are replaced equivalently, so that the essence of the corresponding technical solutions does not deviate from the scope of the technical solutions of the embodiments of the present application, and all the technical solutions are included in the protection scope of the present application.
Claims (10)
1. The kiln fault risk assessment method based on big data analysis is characterized by comprising the following steps of:
collecting real-time monitoring data sequences of parameters of the rotary furnace, wherein the parameters comprise temperature, oxygen content and pressure, and recording the data sequences of the parameters of the normal working state of the rotary furnace as reference data sequences;
dividing the rotary furnace sintering process into sintering stages according to the change of the temperature reference data sequence; for each sintering stage, constructing a feature matrix of the sintering stage according to data of each parameter in a data acquisition period corresponding to the sintering stage, and combining PCA main component analysis and the feature matrix to obtain key components of each parameter of the sintering stage; obtaining the weight of each parameter of the sintering stage according to the relation between the data of each parameter in the corresponding data acquisition period of the sintering stage; obtaining sintering state parameters of the sintering stage according to key components and weights of each parameter of the sintering stage;
acquiring sintering state parameters of each sintering stage, constructing a time window for monitoring a data sequence in real time, acquiring the sintering state parameters of each time window, and acquiring the sintering stage membership degree of the time window according to the Euclidean distance between the time window and the sintering state parameters of each sintering stage; obtaining a rotary furnace fault risk index of the time window according to the membership degree of the sintering stage of the adjacent time window; and evaluating the fault risk of the rotary furnace in the time window according to the fault risk index of the rotary furnace.
2. The kiln failure risk assessment method based on big data analysis according to claim 1, wherein the dividing the rotary kiln sintering process into sintering stages according to the change of the temperature reference data sequence comprises:
taking a sequence formed by the difference values of the adjacent previous temperature reference data and the adjacent next temperature reference data in the temperature reference data sequence as a first-order differential sequence, and acquiring inflection points in the first-order differential sequence; and taking the latter temperature reference data corresponding to the inflection point in the temperature reference data sequence as the corresponding point of the inflection point, and dividing the temperature reference data sequence according to the corresponding points to obtain each sintering stage of the rotary furnace sintering process, wherein each sintering stage comprises a heating stage, a stabilizing stage and a cooling stage.
3. The kiln failure risk assessment method based on big data analysis according to claim 2, wherein the constructing the feature matrix of the sintering stage comprises:
and calculating the average value, standard deviation, maximum value and inclination of the reference data corresponding to each parameter in the data acquisition period corresponding to the sintering stage, and taking the average value standard deviation, maximum value and inclination of each parameter as each row of the feature matrix.
4. The kiln failure risk assessment method based on big data analysis according to claim 3, wherein the key components for obtaining parameters of the sintering stage by combining PCA principal component analysis and feature matrix comprises:
and carrying out PCA principal component analysis on each row vector in the feature matrix to obtain a first principal component vector corresponding to each row vector, and taking the first principal component vector as a key component of a corresponding parameter.
5. The kiln failure risk assessment method based on big data analysis according to claim 1, wherein the obtaining the parameter weights of the sintering phase according to the relation between the parameter data in the corresponding data acquisition period of the sintering phase comprises:
respectively calculating pearson correlation coefficients between a temperature reference data sequence, an oxygen content reference data sequence and a pressure reference data sequence in a data acquisition period corresponding to the sintering stage, respectively marking the pearson correlation coefficients as a first temperature correlation coefficient and a second temperature correlation coefficient, and taking the sum of the first temperature correlation coefficient and the second temperature correlation coefficient as the temperature weight of the sintering stage;
calculating a pearson correlation coefficient between an oxygen content reference data sequence and a pressure reference data sequence in a data acquisition period corresponding to the sintering stage, recording the pearson correlation coefficient as an oxygen pressure correlation coefficient, and taking the sum of the oxygen pressure correlation coefficient and the reciprocal of a first temperature correlation coefficient as the weight of the oxygen content in the sintering stage;
and taking the sum of the second temperature correlation coefficient reciprocal and the oxygen pressure correlation coefficient reciprocal as the weight of the sintering stage pressure.
6. The kiln failure risk assessment method based on big data analysis according to claim 1, wherein the obtaining the sintering state parameters of the sintering stage according to the key components and weights of the parameters of the sintering stage comprises: taking the sum of the products of the key components and the weights of all parameters of the sintering stage as the sintering state parameters of the sintering stage.
7. The kiln failure risk assessment method based on big data analysis according to claim 1, wherein the constructing a time window of a real-time monitoring data sequence comprises:
with a fixed length of 1The L window divides the real-time monitoring data sequence of each parameter, and the fixed length is 1 +.>The L window is a time window, wherein L is the length of the time window.
8. The kiln failure risk assessment method based on big data analysis according to claim 1, wherein the obtaining the sintering stage membership of the time window according to the euclidean distance between the time window and the sintering state parameters of each sintering stage comprises:
and taking the minimum value of Euclidean distance between the time window and the sintering state parameters of each sintering stage as the membership degree of the sintering stage of the time window.
9. The kiln fault risk assessment method based on big data analysis according to claim 1, wherein the rotary kiln fault risk index of the time window is obtained according to the sintering stage membership of the adjacent time window, specifically:
calculating the membership degree sum value of the sintering stage of the current time window and the sintering stage of the next time window, obtaining the difference value between the sum value and a preset threshold value, and taking the normalized result of the ratio of the difference value to the sum value as a rotary furnace fault risk index of the current time window.
10. The kiln failure risk assessment method based on big data analysis according to claim 9, wherein the assessment of the rotary kiln failure risk within the time window according to the rotary kiln failure risk index comprises: and when the fault risk index of the rotary furnace is higher than the risk threshold, judging that the rotary furnace has fault risk in the time window, and when the fault risk index of the rotary furnace is lower than the risk threshold, judging that the rotary furnace does not have fault risk in the time window.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311337906.8A CN117078023B (en) | 2023-10-17 | 2023-10-17 | Kiln fault risk assessment method based on big data analysis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311337906.8A CN117078023B (en) | 2023-10-17 | 2023-10-17 | Kiln fault risk assessment method based on big data analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117078023A true CN117078023A (en) | 2023-11-17 |
| CN117078023B CN117078023B (en) | 2023-12-22 |
Family
ID=88715610
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311337906.8A Active CN117078023B (en) | 2023-10-17 | 2023-10-17 | Kiln fault risk assessment method based on big data analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117078023B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6790034B1 (en) * | 1999-11-04 | 2004-09-14 | Pretoria Portland Cement Company Limited | Kiln plant control system |
| CN108460508A (en) * | 2017-11-06 | 2018-08-28 | 山西大学 | Based on the online energy-saving monitoring method of circulating fluidized bed boiler working characteristics |
| CN110045702A (en) * | 2019-04-23 | 2019-07-23 | 蚌埠中光电科技有限公司 | A kind of simulation of TFT glass furnace production technology and parameter adjust evaluation method |
| CN113110049A (en) * | 2021-04-13 | 2021-07-13 | 苏伟 | Reliable estimation method for monitoring temperature of celadon biscuit firing kiln |
| CN114813635A (en) * | 2022-06-28 | 2022-07-29 | 华谱智能科技(天津)有限公司 | Method for optimizing combustion parameters of coal stove and electronic equipment |
| CN116629607A (en) * | 2023-05-18 | 2023-08-22 | 中钢集团武汉安全环保研究院有限公司 | Dangerous waste environment safety risk identification and assessment method |
| CN116704729A (en) * | 2023-04-28 | 2023-09-05 | 大连重工机电设备成套有限公司 | Industrial kiln early warning system and method based on big data analysis |
-
2023
- 2023-10-17 CN CN202311337906.8A patent/CN117078023B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6790034B1 (en) * | 1999-11-04 | 2004-09-14 | Pretoria Portland Cement Company Limited | Kiln plant control system |
| CN108460508A (en) * | 2017-11-06 | 2018-08-28 | 山西大学 | Based on the online energy-saving monitoring method of circulating fluidized bed boiler working characteristics |
| CN110045702A (en) * | 2019-04-23 | 2019-07-23 | 蚌埠中光电科技有限公司 | A kind of simulation of TFT glass furnace production technology and parameter adjust evaluation method |
| CN113110049A (en) * | 2021-04-13 | 2021-07-13 | 苏伟 | Reliable estimation method for monitoring temperature of celadon biscuit firing kiln |
| CN114813635A (en) * | 2022-06-28 | 2022-07-29 | 华谱智能科技(天津)有限公司 | Method for optimizing combustion parameters of coal stove and electronic equipment |
| CN116704729A (en) * | 2023-04-28 | 2023-09-05 | 大连重工机电设备成套有限公司 | Industrial kiln early warning system and method based on big data analysis |
| CN116629607A (en) * | 2023-05-18 | 2023-08-22 | 中钢集团武汉安全环保研究院有限公司 | Dangerous waste environment safety risk identification and assessment method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117078023B (en) | 2023-12-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112001527B (en) | Industrial production process target data prediction method of multi-feature fusion depth neural network | |
| JP5091604B2 (en) | Distribution evaluation method, product manufacturing method, distribution evaluation program, and distribution evaluation system | |
| CN108897354B (en) | Aluminum smelting process hearth temperature prediction method based on deep belief network | |
| CN116340795B (en) | Operation data processing method for pure oxygen combustion heating furnace | |
| CN114471418B (en) | Method, system and medium for controlling temperature in continuous granulation reaction kettle | |
| JP2002287803A (en) | Property adjusting method in manufacturing process of product | |
| CN116611017B (en) | Nitrogen oxide emission detection method of low-nitrogen combustion heating furnace | |
| CN116772285B (en) | Intelligent building heating load safety real-time monitoring method | |
| CN117056644B (en) | Industrial kiln temperature prediction method and system based on machine learning | |
| CN113757093A (en) | Fault diagnosis method for flash steam compressor unit | |
| CN117078023B (en) | Kiln fault risk assessment method based on big data analysis | |
| CN117725541B (en) | Intelligent monitoring and fault diagnosis system for running state of annealing furnace | |
| CN115358293A (en) | Combination method for reducing interference of system deviation on evaluation result | |
| CN113906216B (en) | Method for detecting damage to a compressor | |
| CN116805065B (en) | Intelligent management method for monitoring data of coal powder heating furnace burner | |
| CN116911621A (en) | Intelligent assessment method and system for resin production safety risk based on data driving | |
| CN115935784A (en) | Method and system for analyzing fuel data in combustion system of architectural ceramic kiln | |
| JP7133154B2 (en) | Driving anomaly detection system | |
| CN114997273A (en) | High-temperature part online service life prediction method based on vision | |
| CN112381235A (en) | Auxiliary method for monitoring state change of preheater in cement plant | |
| WO2024130882A1 (en) | Aging prediction method and system for heating component of power battery material firing system | |
| CN112906101B (en) | Bridge residual deformation abnormity assessment early warning method based on monitoring data | |
| CN117870016B (en) | Real-time monitoring method and system for heating system based on Internet of things | |
| CN117129904B (en) | Industrial power supply rapid switching monitoring method based on data analysis | |
| CN116049922B (en) | Metal structure fatigue reliability prediction method for probability modeling of stress intensity factor threshold value |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: No. 1398 Qinan Road, Yangcheng Science and Technology Industrial Park, Xiangcheng District, Suzhou City, Jiangsu Province, China Patentee after: Suzhou Cohen New Energy Technology Co.,Ltd. Country or region after: China Address before: 215138 buildings 3 and 4, 289 Fengyang Road, Dalou village, Yangchenghu Town, Xiangcheng District, Suzhou City, Jiangsu Province Patentee before: SUZHOU KEER POEN MACHINERY TECHNOLOGY Co.,Ltd. Country or region before: China |