CN111158336A - Industrial intelligent optimization energy-saving system based on cement kiln fault diagnosis - Google Patents
Industrial intelligent optimization energy-saving system based on cement kiln fault diagnosis Download PDFInfo
- Publication number
- CN111158336A CN111158336A CN201911157726.5A CN201911157726A CN111158336A CN 111158336 A CN111158336 A CN 111158336A CN 201911157726 A CN201911157726 A CN 201911157726A CN 111158336 A CN111158336 A CN 111158336A
- Authority
- CN
- China
- Prior art keywords
- fault
- kiln
- knowledge base
- subsystem
- information
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0243—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults model based detection method, e.g. first-principles knowledge model
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
-
- 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
- Y02P80/00—Climate change mitigation technologies for sector-wide applications
- Y02P80/10—Efficient use of energy, e.g. using compressed air or pressurized fluid as energy carrier
Abstract
The invention discloses an industrial intelligent optimization energy-saving system based on cement kiln fault diagnosis. Belongs to the technical field of energy management and energy conservation. The rotary kiln fault detection method mainly solves the problems that the existing rotary kiln fault detection method depends on experience excessively and the fault detection method is low in accuracy. It is mainly characterized in that: the system consists of a parameter acquisition subsystem, a knowledge base management subsystem, a fault diagnosis subsystem and a statistical analysis subsystem; the parameter acquisition subsystem comprises a sensor and a data interface; the knowledge base management subsystem comprises three functions of knowledge base establishment, knowledge base updating and knowledge base query; the fault diagnosis subsystem comprises an inference machine, an interpreter and a man-machine interface; the statistical analysis subsystem is used for summarizing and counting the fault information in a period of time, analyzing fault abnormal points and improving the basis for improving the intelligent degree of equipment inspection. The method has the characteristics of parameter information acquisition, fault diagnosis and statistical analysis, and is mainly used for fault diagnosis of the cement kiln.
Description
Technical Field
The invention belongs to the technical field of energy management and energy conservation, and particularly relates to an industrial intelligent optimization energy-saving system based on cement kiln fault diagnosis.
Background
The rotary kiln calcination is the most important process link in cement production, which comprises complex thermal and chemical processes and directly influences the yield, quality and energy consumption of cement clinker. Due to the complexity of the rotary kiln system, the appearance of the fault has certain ambiguity and diversity; one fault phenomenon may be generated by a plurality of fault reasons, or a plurality of fault phenomena are generated by the same fault reason, etc.; the production process of the clinker in the rotary kiln system is a physicochemical reaction process and has the characteristics of large inertia, pure hysteresis, nonlinearity and the like.
The existing fault diagnosis method for the rotary cement kiln comprises two methods: one is completely carried out manually; and the other method is to apply the fault diagnosis system theory and method to the fault detection of the rotary kiln. The diagnosis mode of the former is completely dependent on the technical level and responsibility of engineering operators, and the fault diagnosis of the rotary kiln cannot be efficiently, quickly and accurately completed; the latter can carry out certain reasoning and diagnosis according to uncertain knowledge, but mainly depends on the detection of a plurality of main parameters, and is not refined to the step of regular representation, and meanwhile, the system knowledge is difficult to update and has transparency.
Disclosure of Invention
Aiming at the defects and shortcomings of the fault diagnosis of the conventional rotary cement kiln, the invention aims to construct a cement kiln fault diagnosis model for enterprises, provide an industrial intelligent optimization energy-saving system integrating parameter information acquisition, fault diagnosis and statistical analysis, and create an intelligent production management platform.
The technical solution of the invention is as follows: the utility model provides an industrial intelligence optimizes economizer system based on cement kiln fault diagnosis which characterized in that: the system comprises a parameter acquisition subsystem, a knowledge base management subsystem, a fault diagnosis subsystem and a statistical analysis subsystem; the parameter acquisition subsystem comprises a sensor, a data interface and a data repository and is used for automatically acquiring the operating parameters of the cement kiln; the knowledge base management subsystem comprises three functions of knowledge base establishment, knowledge base updating and knowledge base query, extracts each type of fault characteristics and fault trigger information through machine learning according to common fault sites and parameter change conditions of the cement kiln, summarizes the fault characteristics and the fault trigger information to form a basic knowledge base, and can be newly added through machine learning and manual intervention; the fault diagnosis subsystem comprises an inference machine, an interpreter and a man-machine interface; the statistical analysis subsystem collects and counts the fault information for a period of time, analyzes fault abnormal points and improves the basis for improving the intelligent degree of equipment inspection.
In the technical scheme of the invention, the parameter acquisition subsystem acquires the parameters of the cement kiln by means of a sensor or a field third-party system, and stores the characteristic parameters into a data repository according to a certain rule, wherein the common rule is storage in a sub-unit mode, a sub-system mode and a sub-area mode; the fault characteristics of the knowledge base management subsystem comprise fault serial numbers, fault names, fault abnormal phenomena and analysis information, the fault trigger information comprises the names of characteristic parameters, extreme values of normal operating ranges of the parameters or other judgment conditions, and in addition, the fault characteristics and the fault trigger information in the knowledge base can be newly added through manual intervention; the fault diagnosis subsystem carries out vector and fuzzification processing on the parameters collected by the parameter collection subsystem, then compares the parameters with fault characteristics and fault trigger information in the knowledge base management subsystem to carry out fault diagnosis, automatically generates a piece of fault information if the fault is judged to be a fault, and checks the fault information through a human-computer interface; if the system can not judge but actually has a fault, the parameter is used as a sample to extract fault characteristics and fault triggering information according to a certain rule, and the fault characteristics and the fault triggering information are automatically added into a knowledge base management subsystem, wherein the certain rule is generally BP neural network training.
The inference engine in the technical scheme of the invention is a tool for comparing the actual parameter information after vectorization and fuzzification with the fault characteristics and fault trigger information in the knowledge base, and adopts three inference modes of forward inference, reverse inference and forward and reverse mixing to ensure rapidity, stability and accuracy of comparison.
The interpreter in the technical solution of the invention is that the interpretation frames of each problem solving mode are organized in the form of natural language and inserted into the corresponding data repository, when the user inquires about the detailed information of the fault, the corresponding interpretation information is added into the interpretation frames and organized into a text to be viewed through a man-machine interface.
The fault characteristics of the knowledge base in the technical scheme of the invention specifically comprise clinker ring formation fault in the kiln, kiln skin collapse, low sintering temperature in the kiln and fly sand material in the kiln; the clinker ring formation faults in the kiln comprise high kiln head temperature, low kiln head temperature, reduced kiln head negative pressure, increased kiln current and increased fluctuation; said crust collapse comprises kiln current rising and then falling; the low in-kiln firing temperature comprises low kiln head temperature, gradually reduced kiln current and high kiln tail temperature; the flying sand in the kiln comprises insufficient liquid phase, overlong transition zone and overhigh silicate of the ingredient.
The technical scheme of the invention is that the fault trigger information consists of operation parameters and monitoring parameters, wherein the operation parameters comprise raw material amount entering a kiln, rotating speed of a cement kiln, decomposition coal feeding amount, kiln head coal feeding amount, kiln tail exhaust fan air volume, a decomposition furnace tertiary air valve and cooler fan air volume; the detection parameters comprise the outlet oxygen concentration of the preheater, the kiln tail oxygen concentration, the kiln tail gas temperature, the kiln tail gas pressure, the outlet gas temperature of the decomposing furnace, the burning zone temperature, the kiln head negative pressure and temperature, the gas temperature pressure of each stage of the preheater, the temperature pressure of the material, the load of a kiln main motor and the temperature of a kiln cylinder.
The forward reasoning in the technical scheme of the invention takes the collected abnormal data as a starting point, and carries out matching in the knowledge base according to a formulated search strategy, the process of rule matching is repeated, when a rule corresponding to the current symptom is searched in the knowledge base, the rule is temporarily stored in a dynamic data repository, and then the rule base is continuously searched until all the rules in the rule base are searched, and an inference result is given; the reverse reasoning is to put forward an assumption, the fact in the dynamic database is the basis for putting forward the assumption, a rule set which is the same as the assumption conclusion is searched in the knowledge base according to a search strategy, after the rule set which meets the conditions is determined, the condition parts of all rules of the rule set are matched in the dynamic database, and if the dynamic database contains the condition information of a certain rule, the rule is proved to be effective; if all rules finally prove to be invalid, the prior assumption is not satisfied, and the assumption needs to be proposed again; the forward and reverse mixed reasoning is a process of finding necessary conditions by combining forward and reverse, wherein the forward reasoning determines hypothesis information on the premise of symptom, and then performs reverse reasoning by taking a hypothesis as a starting point.
The human-computer interface in the technical scheme of the invention transmits the basic information required in the reasoning process to the system through the interface, and the final result of the system reasoning and the explanation of the result can be checked through the human-computer interface.
The invention can diagnose various abnormal states or fault states of the cement kiln equipment timely and correctly, prevent or eliminate faults, guide the operation of the machine, improve the reliability, safety and effectiveness of the operation of the equipment and reduce the fault loss to the lowest level. The invention can ensure that the system can exert the maximum design capability, and a reasonable detection and maintenance system is made, so that the potential of the equipment can be fully excavated under the allowable condition, the service life and the service life are prolonged, and the total life cycle cost of the system is reduced. The invention provides data and information for the structure modification, the optimized design, the reasonable manufacture and the production process of the cement kiln equipment through detection monitoring, fault analysis, performance evaluation and the like.
Compared with the existing fault diagnosis system, the invention has the following innovation: 1. summarizing the fault characteristics and the fault information into a knowledge base; 2. the failure diagnosis accuracy is improved by comparing the inference engine with the failure characteristics and the failure trigger information in the knowledge base; 3. for the fault information which cannot be diagnosed by the system, corresponding characteristic quantity can be extracted through the BP neural network training sample, and a knowledge base is enriched.
Drawings
Fig. 1 is a block diagram of the present invention.
FIG. 2 is an operational logic diagram architecture of the present invention.
Fig. 3 shows the content range of the fault triggering information in the knowledge base of the present invention.
FIG. 4 is a diagram of the matching relationship between the fault signature in the knowledge base of the present invention and the content range and the fault trigger information.
Detailed Description
The invention will be further explained with reference to the drawings.
Referring to fig. 1, the industrial intelligent optimization energy-saving system based on cement kiln fault diagnosis of the present invention is composed of a parameter acquisition subsystem, a knowledge base management subsystem, a fault diagnosis subsystem and a statistical analysis subsystem, and with the fault diagnosis subsystem as a core, under the support of the parameter acquisition subsystem and the knowledge base management subsystem, whether the parameter state is a fault is judged. The parameter acquisition subsystem comprises a sensor, a data interface and a data repository, and the parameter acquisition subsystem has the function process that the parameters of the cement kiln are acquired by the sensor, stored in the database according to a certain rule and then transmitted to the fault diagnosis subsystem through the data interface. The knowledge base management subsystem has three functions of knowledge base establishment, knowledge base updating and knowledge base query, extracts corresponding fault characteristics and fault trigger information through machine learning according to common fault sites and parameter change conditions of the cement kiln to form a basic knowledge base, and adds new fault characteristics and fault trigger information through BP neural network training and manual intervention to enrich the knowledge base. The fault diagnosis subsystem comprises an inference machine, an interpreter and a human-computer interface, and is used for vectorizing and fuzzifying the parameters transmitted by the parameter acquisition subsystem, comparing the vectorized and fuzzified parameters with a knowledge base to diagnose the fault, automatically generating fault information if the fault is judged to be a fault, and checking the fault information through the human-computer interface; if the system can not judge but actually has a fault, the parameter is used as a sample to extract fault characteristics and fault triggering information according to a certain rule, and the fault characteristics and the fault triggering information are automatically added into a knowledge base management subsystem, wherein the certain rule is generally a BP neural network. The statistical analysis subsystem is used for summarizing and counting the fault information in a period of time, checking the fault information and counting the number of the fault information according to specific conditions, analyzing fault abnormal points and providing a basis for improving the intelligent degree of equipment inspection.
The inference method of the inference engine in fig. 1 includes forward inference, backward inference and forward and backward mixed inference.
Forward reasoning: the method is based on the collected abnormal data as the starting point, and the matching is carried out in the knowledge base according to the formulated search strategy. The process of rule matching is repeated, when the rule corresponding to the current symptom is searched in the knowledge base, the rule is temporarily stored in the dynamic data repository, then the rule base is continuously searched until all the rules in the rule base are searched, and an inference result is given.
Reverse reasoning: firstly, proposing hypothesis, wherein the fact in the dynamic data repository is the basis for proposing the hypothesis, searching the knowledge base for the rule set which is the same as the hypothesis conclusion according to the search strategy, matching the condition parts of all rules in the rule set in the dynamic data repository after determining the rule set which meets the condition, and proving that the rule is effective if the dynamic data repository contains the condition information of a certain rule. If all rules eventually prove to be invalid, the previous assumption is not valid and needs to be re-proposed. Both of the above two kinds of reasoning are one-way reasoning. Single forward or reverse reasoning, in the search process for the target.
Forward and reverse mixed reasoning: the method is a process of finding necessary conditions by combining positive and negative conditions by determining hypothesis information through forward reasoning on the premise of symptoms and then performing reverse reasoning by taking the hypothesis as a starting point.
The interpretation method of the interpreter in fig. 1 is to preset texts, organize the interpretation frameworks of each problem solving mode in the form of natural language, and insert the interpretation frameworks into the corresponding data repositories. In the process of executing the target, interpretation information is generated at the same time, and fuzzy variables or language variables in the interpretation information are converted into proper modifiers. When the user inquires about the detailed information, the corresponding explanation information is added into the explanation frame and organized into a text to be submitted to the user.
The man-machine interface in fig. 1 is a window for communication between a user and the system, basic information required in the inference process can be transmitted to the system through the interface, and the final result of the inference of the system and the explanation of the result can be viewed through the man-machine interface.
Referring to fig. 2, the operation logic of the present invention is that the parameters are collected by the sensors in the parameter collection subsystem and stored in the database according to a certain rule, and then transmitted to the fault diagnosis subsystem, vectorization and fuzzification in the fault diagnosis subsystem become information capable of diagnosis and comparison, and the information is compared with the fault trigger information in the knowledge base management subsystem, and the fault characteristics are matched, if the parameter state is judged to be a fault, the fault details are output, otherwise, the fault details are not output, and if the system cannot judge but the parameter is actually in a fault state, the parameter can be input into the system as a sample, and the fault trigger information and the fault characteristics are extracted through the training of the BP neural network, and the parameter is automatically added into the knowledge base. The addition of the fault triggering information and the fault characteristics in the knowledge base can also be realized in a manual addition mode.
Referring to fig. 3, the fault triggering information in the knowledge base is composed of an operation parameter and a detection parameter, the operation parameter refers to a parameter that can be adjusted manually, after the detection parameter is determined by the operation parameter, and determining detection parameters, wherein the operation parameters comprise the raw material amount entering the kiln, the rotating speed of the cement kiln, the decomposition coal feeding amount, the kiln head coal feeding amount, the kiln tail exhaust fan air volume, the tertiary air valve of the decomposition furnace and the fan air volume of a cooling machine, the detection parameters comprise the outlet oxygen concentration of the preheater, the outlet oxygen concentration of the kiln tail, the temperature of kiln tail gas, the pressure of kiln tail gas, the outlet gas temperature of the decomposition furnace, the burning zone temperature, the kiln head negative pressure and temperature, the gas temperature pressure of each stage of the preheater, the temperature pressure of materials, the load of a main motor of the kiln and the temperature of a kiln barrel, and the content of each parameter in the fault trigger information comprises a parameter name, an extreme value of normal operation of the parameter or other.
Referring to fig. 4, the failure contact characteristics in the knowledge base include clinker ring formation failure in the kiln, kiln crust collapse, low sintering temperature in the kiln, fly sand in the kiln and the like, wherein the clinker ring formation failure in the kiln includes high kiln head temperature, low kiln head negative pressure, increased kiln current and large fluctuation; said crust collapse comprises kiln current rising and then falling; the low in-kiln firing temperature comprises low kiln head temperature, gradually reduced kiln current and high kiln tail temperature; the flying sand in the kiln comprises liquid phase quantity reduction, transition zone increase and ingredient silicate overhigh.
Referring to fig. 4, the logic relationship between the fault triggering information is that when the temperature of the kiln head is high, the coal injection pipe needs to be moved outwards; when the temperature of the kiln head is low, the feeding amount needs to be reduced; when the negative pressure of the kiln head is reduced, the secondary air quantity needs to be increased; when the kiln current is increased and the fluctuation is increased, the kiln speed needs to be properly accelerated. Collapse of the crust involves the kiln current rising and then falling. When the kiln current is increased and then decreased, the kiln head coal feeding amount needs to be reduced, the grate speed of the grate cooler needs to be increased or the kiln speed needs to be decreased. The low in-kiln firing temperature comprises low kiln head temperature, gradually reduced kiln current and high kiln tail temperature. When the kiln current is gradually reduced, the air exhaust amount is too large, and the primary air quantity, the coal powder fineness and the coal injection pipe are required to be reduced. The flying sand in the kiln comprises insufficient liquid phase, overlong transition zone and overhigh silicate of the mixture. When the liquid phase quantity is insufficient, the coal injection quantity needs to be increased; when the transition zone is too long, the proportion of primary air and secondary air needs to be optimized; when the silicate is too high, the material is prepared according to the kiln diameter ratio.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (8)
1. The utility model provides an industrial intelligence optimizes economizer system based on cement kiln fault diagnosis which characterized in that: the system comprises a parameter acquisition subsystem, a knowledge base management subsystem, a fault diagnosis subsystem and a statistical analysis subsystem; the parameter acquisition subsystem comprises a sensor, a data interface and a data repository and is used for automatically acquiring the operating parameters of the cement kiln; the knowledge base management subsystem comprises three functions of knowledge base establishment, knowledge base updating and knowledge base query, extracts each type of fault characteristics and fault trigger information through machine learning according to common fault sites and parameter change conditions of the cement kiln, summarizes the fault characteristics and the fault trigger information to form a basic knowledge base, and can be newly added through machine learning and manual intervention; the fault diagnosis subsystem comprises an inference machine, an interpreter and a man-machine interface; the statistical analysis subsystem collects and counts the fault information for a period of time, analyzes fault abnormal points and improves the basis for improving the intelligent degree of equipment inspection.
2. The cement kiln fault diagnosis based industrial intelligent optimization energy-saving system is characterized in that: the parameter acquisition subsystem acquires cement kiln parameters by means of a sensor or a field third-party system, and stores the characteristic parameters into a data repository according to a certain rule, wherein the common rule is storage in a sub-unit mode, a sub-system mode and a sub-area mode; the fault characteristics of the knowledge base management subsystem comprise fault serial numbers, fault names, fault abnormal phenomena and analysis information, the fault trigger information comprises the names of characteristic parameters, extreme values of normal operating ranges of the parameters or other judgment conditions, and in addition, the fault characteristics and the fault trigger information in the knowledge base can be newly added through manual intervention; the fault diagnosis subsystem carries out vector and fuzzification processing on the parameters collected by the parameter collection subsystem, then compares the parameters with fault characteristics and fault trigger information in the knowledge base management subsystem to carry out fault diagnosis, automatically generates a piece of fault information if the fault is judged to be a fault, and checks the fault information through a human-computer interface; if the system can not judge but actually has a fault, the parameter is used as a sample to extract fault characteristics and fault triggering information according to a certain rule, and the fault characteristics and the fault triggering information are automatically added into a knowledge base management subsystem, wherein the certain rule is generally BP neural network training.
3. The cement kiln fault diagnosis based industrial intelligent optimization energy-saving system is characterized in that: the inference machine is a tool for comparing actual parameter information with fault characteristics and fault trigger information in a knowledge base, and three inference modes of forward inference, reverse inference and forward and reverse mixing are adopted to ensure rapidity, stability and accuracy of comparison.
4. The cement kiln fault diagnosis based industrial intelligent optimization energy-saving system is characterized in that: the interpreter is that the interpretation frames of each problem solving mode are organized in a natural language mode and inserted into corresponding data repositories, and when a user inquires about detailed information of a fault, the corresponding interpretation information is added into the interpretation frames and organized into texts to be viewed through a man-machine interface.
5. The cement kiln fault diagnosis based industrial intelligent optimization energy-saving system is characterized in that: the fault characteristics of the knowledge base specifically comprise clinker ring formation fault in the kiln, kiln skin collapse, low sintering temperature in the kiln and fly sand material in the kiln; the clinker ring formation faults in the kiln comprise high kiln head temperature, low kiln head temperature, reduced kiln head negative pressure, increased kiln current and increased fluctuation; said crust collapse comprises kiln current rising and then falling; the low in-kiln firing temperature comprises low kiln head temperature, gradually reduced kiln current and high kiln tail temperature; the flying sand in the kiln comprises insufficient liquid phase, overlong transition zone and overhigh silicate of the ingredient.
6. The cement kiln fault diagnosis based industrial intelligent optimization energy-saving system is characterized in that: the fault trigger information consists of operation parameters and monitoring parameters, wherein the operation parameters comprise the raw material amount entering the kiln, the rotating speed of the cement kiln, the decomposition coal feeding amount, the kiln head coal feeding amount, the kiln tail exhaust fan air volume, the tertiary air valve of the decomposition furnace and the cooler fan air volume; the detection parameters comprise the outlet oxygen concentration of the preheater, the kiln tail oxygen concentration, the kiln tail gas temperature, the kiln tail gas pressure, the outlet gas temperature of the decomposing furnace, the burning zone temperature, the kiln head negative pressure and temperature, the gas temperature pressure of each stage of the preheater, the temperature pressure of the material, the load of a kiln main motor and the temperature of a kiln cylinder.
7. The cement kiln fault diagnosis based industrial intelligent optimization energy-saving system is characterized in that: the forward reasoning is that the acquired abnormal data is taken as a starting point, matching is carried out in a knowledge base according to a formulated search strategy, the rule matching process is repeated, after a rule corresponding to the current symptom is searched in the knowledge base, the rule is temporarily stored in a dynamic data repository, then the rule base is continuously searched until all the rules in the rule base are searched, and an inference result is given; the reverse reasoning is to put forward an assumption, the fact in the dynamic database is the basis for putting forward the assumption, a rule set which is the same as the assumption conclusion is searched in the knowledge base according to a search strategy, after the rule set which meets the conditions is determined, the condition parts of all rules of the rule set are matched in the dynamic database, and if the dynamic database contains the condition information of a certain rule, the rule is proved to be effective; if all rules finally prove to be invalid, the prior assumption is not satisfied, and the assumption needs to be proposed again; the forward and reverse mixed reasoning is a process of finding necessary conditions by combining forward and reverse, wherein the forward reasoning determines hypothesis information on the premise of symptom, and then performs reverse reasoning by taking a hypothesis as a starting point.
8. The cement kiln fault diagnosis based industrial intelligent optimization energy-saving system is characterized in that: the human-computer interface transmits basic information required in the reasoning process to the system through the interface, and the final result of the system reasoning and the explanation of the result can be checked through the human-computer interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911157726.5A CN111158336A (en) | 2019-11-22 | 2019-11-22 | Industrial intelligent optimization energy-saving system based on cement kiln fault diagnosis |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911157726.5A CN111158336A (en) | 2019-11-22 | 2019-11-22 | Industrial intelligent optimization energy-saving system based on cement kiln fault diagnosis |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111158336A true CN111158336A (en) | 2020-05-15 |
Family
ID=70556018
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911157726.5A Pending CN111158336A (en) | 2019-11-22 | 2019-11-22 | Industrial intelligent optimization energy-saving system based on cement kiln fault diagnosis |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111158336A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112149342A (en) * | 2020-08-21 | 2020-12-29 | 杭州玖欣物联科技有限公司 | Model method for optimizing quality of cement raw material |
| CN112365458A (en) * | 2020-11-02 | 2021-02-12 | 中材邦业(杭州)智能技术有限公司 | Grate cooler snowman identification method and system based on ANN neural network |
| CN113218639A (en) * | 2021-03-25 | 2021-08-06 | 浙江中自庆安新能源技术有限公司 | Rotary kiln fault detection method and device, computer equipment and storage medium |
| CN113985814A (en) * | 2021-10-25 | 2022-01-28 | 东华大学 | Digital twinning-based machining process self-adaptive control method |
| CN114760338A (en) * | 2022-04-07 | 2022-07-15 | 济南大学 | System and method for diagnosing process faults in cement clinker preparation process |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020010517A1 (en) * | 1998-12-17 | 2002-01-24 | Siemens Ag. | System of case-based reasoning for sensor prediction in a technical process, especially in a cement kiln, method and apparatus therefore |
| CN101907867A (en) * | 2010-08-25 | 2010-12-08 | 中南大学 | Self-tuning expert control method of burning trough point parameter based on working condition recognition |
| CN102298316A (en) * | 2011-04-27 | 2011-12-28 | 中南大学 | Sintering granulating moisture control parameter tuning method for effectively inhibiting raw material flow fluctuation |
| CN104019661A (en) * | 2014-05-26 | 2014-09-03 | 北方工业大学 | Rotary kiln control system |
| CN105223495A (en) * | 2015-10-20 | 2016-01-06 | 国家电网公司 | A kind of method of testing of the Analog-digital circuit fault diagnosis based on expert system |
| CN105447764A (en) * | 2015-12-31 | 2016-03-30 | 浙江省公众信息产业有限公司 | Meteorological decision support method and meteorological decision support device based on T-S model |
| CN107272646A (en) * | 2017-06-30 | 2017-10-20 | 南京理工大学 | Forcing press fault diagnosis system based on expert system |
-
2019
- 2019-11-22 CN CN201911157726.5A patent/CN111158336A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020010517A1 (en) * | 1998-12-17 | 2002-01-24 | Siemens Ag. | System of case-based reasoning for sensor prediction in a technical process, especially in a cement kiln, method and apparatus therefore |
| CN101907867A (en) * | 2010-08-25 | 2010-12-08 | 中南大学 | Self-tuning expert control method of burning trough point parameter based on working condition recognition |
| CN102298316A (en) * | 2011-04-27 | 2011-12-28 | 中南大学 | Sintering granulating moisture control parameter tuning method for effectively inhibiting raw material flow fluctuation |
| CN104019661A (en) * | 2014-05-26 | 2014-09-03 | 北方工业大学 | Rotary kiln control system |
| CN105223495A (en) * | 2015-10-20 | 2016-01-06 | 国家电网公司 | A kind of method of testing of the Analog-digital circuit fault diagnosis based on expert system |
| CN105447764A (en) * | 2015-12-31 | 2016-03-30 | 浙江省公众信息产业有限公司 | Meteorological decision support method and meteorological decision support device based on T-S model |
| CN107272646A (en) * | 2017-06-30 | 2017-10-20 | 南京理工大学 | Forcing press fault diagnosis system based on expert system |
Non-Patent Citations (1)
| Title |
|---|
| 尹朝庆: "《人工智能与专家系统（第2版》", 30 April 2009, pages: 70 - 72 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112149342A (en) * | 2020-08-21 | 2020-12-29 | 杭州玖欣物联科技有限公司 | Model method for optimizing quality of cement raw material |
| CN112365458A (en) * | 2020-11-02 | 2021-02-12 | 中材邦业(杭州)智能技术有限公司 | Grate cooler snowman identification method and system based on ANN neural network |
| CN113218639A (en) * | 2021-03-25 | 2021-08-06 | 浙江中自庆安新能源技术有限公司 | Rotary kiln fault detection method and device, computer equipment and storage medium |
| CN113218639B (en) * | 2021-03-25 | 2022-05-20 | 浙江中自庆安新能源技术有限公司 | Rotary kiln fault detection method and device, computer equipment and storage medium |
| CN113985814A (en) * | 2021-10-25 | 2022-01-28 | 东华大学 | Digital twinning-based machining process self-adaptive control method |
| CN114760338A (en) * | 2022-04-07 | 2022-07-15 | 济南大学 | System and method for diagnosing process faults in cement clinker preparation process |
| CN114760338B (en) * | 2022-04-07 | 2023-04-18 | 济南大学 | Cement clinker preparation process fault diagnosis system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111158336A (en) | Industrial intelligent optimization energy-saving system based on cement kiln fault diagnosis | |
| CN103838216B (en) | Power boiler burning optimization method based on data-driven case coupling | |
| CN111804146B (en) | Intelligent ammonia injection control method and intelligent ammonia injection control device | |
| CN111651931B (en) | Blast furnace fault diagnosis rule derivation method based on deep neural network | |
| CN111077869A (en) | Optimization control method and system for big data intelligent control bag-type dust collector | |
| CN111581581B (en) | Method and system for detecting NOx concentration at SCR inlet under multi-boundary condition | |
| CN106650944B (en) | Knowledge-based converter gas scheduling method for metallurgical enterprises | |
| CN106327004A (en) | Cement firing process optimizing method based on clinker quality index | |
| JP2021530669A (en) | Boiler coal saving control method | |
| CN111242469B (en) | Method and system for coupling ultralow emission and high-efficiency energy-saving operation of boiler or kiln | |
| CN109064368A (en) | A kind of gas explosion accident ontological construction and inference method based on OWL | |
| CN113177352A (en) | Boiler combustion optimization system and method based on numerical simulation and artificial intelligence | |
| CN114881207A (en) | Steam pressure prediction method and device based on LSTM deep circulation neural network | |
| CN114427688A (en) | Closed-loop combustion optimization control method based on air temperature influence structure on boiler operation | |
| CN115113519A (en) | Coal-gas co-combustion boiler denitration system outlet NO x Concentration early warning method | |
| CN114413249B (en) | Data analysis method for power station boiler efficiency benchmarking optimization | |
| Li et al. | Research on Optimal Setting of Cement Decomposing Furnace Temperature based on Case Reasoning | |
| CN108641733A (en) | A kind of closed loop control method of dry coke quenching recyclegas CO concentration | |
| Liu et al. | Research on knowledge base of dam safety monitoring expert system based on relational database | |
| CN103472729A (en) | Crowd-sourcing system and method for controlling harmful emissions of pesticide waste liquid incinerator to reach standard | |
| CN103488087B (en) | Optimum pesticide waste liquid incinerator hazardous emission controls up to par system and method | |
| CN113722837B (en) | Method for establishing diesel vehicle fuel consumption and emission model according to data clusters of different working conditions | |
| Zhou | Application of data mining in coal mine safety decision system based on rough set | |
| CN115081338B (en) | Hobbing carbon consumption prediction method based on improved generation of countercheck filling network under data loss | |
| Ma et al. | Research on modelling and simulation of cement raw meal predecomposition process |
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 |