CN113128687A - Fault diagnosis expert system for escalator - Google Patents
Fault diagnosis expert system for escalator Download PDFInfo
- Publication number
- CN113128687A CN113128687A CN202110320264.5A CN202110320264A CN113128687A CN 113128687 A CN113128687 A CN 113128687A CN 202110320264 A CN202110320264 A CN 202110320264A CN 113128687 A CN113128687 A CN 113128687A
- Authority
- CN
- China
- Prior art keywords
- case
- module
- cases
- base
- rule
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 59
- 230000003993 interaction Effects 0.000 claims abstract description 28
- 238000000034 method Methods 0.000 claims description 44
- 230000008569 process Effects 0.000 claims description 26
- 238000012544 monitoring process Methods 0.000 claims description 24
- 230000006870 function Effects 0.000 claims description 16
- 230000009466 transformation Effects 0.000 claims description 9
- 238000012216 screening Methods 0.000 claims description 8
- 230000004913 activation Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 6
- 239000013598 vector Substances 0.000 claims description 6
- 238000012790 confirmation Methods 0.000 claims description 4
- 230000014509 gene expression Effects 0.000 claims description 4
- 230000006698 induction Effects 0.000 claims description 4
- 238000013024 troubleshooting Methods 0.000 claims 3
- 238000013461 design Methods 0.000 abstract description 3
- 238000006243 chemical reaction Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012423 maintenance Methods 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 238000009825 accumulation Methods 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000012217 deletion Methods 0.000 description 1
- 230000037430 deletion Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/046—Forward inferencing; Production systems
- G06N5/047—Pattern matching networks; Rete networks
Abstract
The invention discloses a fault diagnosis expert system for an escalator, which comprises: the system comprises an inference engine module, a knowledge base module, a knowledge interaction module, a case learning module and an interpreter module; the knowledge base module is respectively connected with the inference engine module, the knowledge interaction module and the interpreter module; the knowledge base module comprises cases and diagnosis rules in the field of problems to be solved; the knowledge interaction module is used for acquiring a fact value; the inference engine module calls cases or diagnosis rules in the knowledge base module according to the acquired fact values to infer the fault phenomenon, so that the fault reason is obtained; the fault diagnosis expert system for the escalator, provided by the invention, designs the expert system which has case reasoning and rule reasoning, can flexibly configure and inherit by converting the cases in the case base into rules and storing the rules in the rule base, and meets the actual application requirements.
Description
Technical Field
The invention relates to the field of escalators, in particular to a fault diagnosis expert system for an escalator.
Background
The expert system is a branch of artificial intelligence, which is an emerging application science that was generated and developed in the early 60's of the 20 th century, and is becoming increasingly sophisticated and mature with the continuous development of computer technology. The method is an intelligent program, and solves a complex problem which can be solved only by special knowledge through a knowledge and reasoning process. Has been widely used in the fields of industry, medical treatment, agriculture, education and the like. The application of the fault diagnosis expert system as an expert system in the industry is highly valued by the academic and engineering communities.
There are many models of expert systems, and among them, rule-based expert systems, case-based expert systems, and framework-based expert systems are commonly used.
In the prior art, an expert system for flexibly configuring and inheriting case reasoning and rule reasoning is lacked, and the actual application requirements cannot be met.
Disclosure of Invention
In order to solve the problems of the prior art, the embodiment of the invention provides a fault diagnosis expert system for an escalator. The technical scheme is as follows:
in one aspect, a fault diagnosis expert system for an escalator is provided, comprising: the system comprises an inference engine module, a knowledge base module, a knowledge interaction module, a case learning module and an interpreter module;
the knowledge base module is respectively connected with the inference engine module, the knowledge interaction module and the interpreter module; the knowledge base module comprises cases and diagnosis rules in the field of problems to be solved;
the knowledge interaction module is used for acquiring a fact value;
the inference engine module calls cases or diagnosis rules in the knowledge base module according to the acquired fact values to infer the fault phenomenon, so that the fault reason is obtained;
the interpreter module interprets the reasoning process and the deterministic conclusion obtained by reasoning;
the inference engine module comprises a rule inference engine module and a case inference engine module; the rule reasoning module adopts an expert system based on rules; the case reasoning module adopts an expert system based on frame-type knowledge representation;
the knowledge base module comprises a rule base and a case base; the rule base is connected with the rule reasoning module, and the case base is connected with the case reasoning module;
and the case learning module is used for converting the cases in the case base into rules and storing the rules in the rule base.
Further, the rule reasoning module is a rule reasoning engine technology based on task calling mode and rule activation, and the reasoning engine is enabled to check each rule to guide finding of the fact.
Further, the case reasoning module employs a combined search strategy based on association and knowledge induction.
Further, the case reasoning module quickly finds out the case most similar to the case to be diagnosed from the case base according to the index strategy, the matching method and the similarity calculation method, and the case reasoning module comprises two steps:
the first step is as follows: searching out a similar case set of the equipment from a case library according to the equipment name, the part name and the unit state equipment information of the input case to be diagnosed;
the second step is that: searching out the most similar cases from the equipment similar case set by adopting a nearest matching method;
the nearest neighbor matching method represents the cases from the viewpoint of an n-dimensional space, and the feature vector corresponding to each case is composed of:
let V ═ a (i), …, a (i) } denote the feature vectors of the cases, the similarity of the two cases is expressed as follows:
in the formula:
t represents a case to be diagnosed;
t (i) the ith feature representing case T;
s represents a case in the case base;
(i) represents the ith feature of case S;
ωiweight of the ith feature of the representative case;
(1) t (i) when s (i) is the same, | t (i) -s (i) | 0; when t (i) is different from s (i), | t (i) -s (i) | 1
(2) Characteristic weight ωiIs determined
According to the importance degree of the features, the features are classified into 5 classes which are most important, very important, more important, general and optional, and the grade of the ith feature is assumed to be represented by kiDenotes kiIs a value from 1 to 5, the feature weight calculation method is:
the larger the similarity value is, the more similar the two cases are; the smaller the similarity value is, the larger the difference between the two cases is; when sim (T, S) ═ 1, the two cases are identical; and according to the method, the similarity between the case to be diagnosed and the case in the same type of case set of the equipment is calculated, and the case with the maximum similarity is found.
Further, the knowledge base comprises a rule base and a case base; the rule base and the case base share an attribute table and a fault table;
the attribute table is used for storing the type information of the actual value and the definition of the slot value in the case;
the fault table is used for storing the definition of the equipment fault;
the rule base further comprises:
the fact table is used for storing the characteristic item information of the equipment;
the task table is used for storing task information;
a rule table for storing all rules used in the expert system;
the case base further comprises:
a case table for storing all rules used in the expert system;
case details are used for storing detailed slot value information of the cases;
and the case accessory table is used for storing the accessory information of the case.
Further, the knowledge interaction module has three use modes: full-automatic diagnosis, semi-automatic diagnosis and man-machine conversation;
the method comprises the steps of full-automatic diagnosis, wherein the inference process does not involve interaction with external personnel, real values are automatically obtained, assignment operation is carried out through a state monitoring platform, and default values are adopted if automatic acquisition cannot be carried out;
semi-automatic diagnosis, which is the same as full-automatic reasoning diagnosis, is integrated in a state monitoring platform of a large turbine compressor unit, the fact value which is automatically obtained is assigned through the state monitoring platform, and a dialog box is automatically popped up to carry out selection operation, wherein the fact value which cannot be obtained is assigned through the state monitoring platform;
and man-machine interaction for information interaction between the user and each module of the fault diagnosis system.
Further, the case learning module is also used for converting the private case into the public case;
the private case is directly input from a monitoring platform of the large-scale turbine compressor unit, and the public case is formed after the private case is subjected to case learning and is confirmed by an expert; the use in case reasoning functions is all common cases.
Further, the process of converting the private case into the public case specifically comprises the following steps:
the first step is as follows: standardizing the attribute characteristics of the cases, and standardizing some nonstandard expressions used by case entry personnel;
the second step is that: the expert analyzes the input case and whether the input case has representative significance; after confirmation, a common case is formed.
Further, the process of converting the cases in the case base into rules and storing the rules in the rule base specifically comprises the following steps:
the first step is as follows: screening the common cases, and screening out the cases which are similar and can directly distinguish faults;
the second step is that: different feature combinations and use sequences are summarized through optimizing classification;
the third step: the rules for transformation are confirmed by experts and finally saved to a rule base.
The technical scheme provided by the embodiment of the invention has the following beneficial effects:
the fault diagnosis expert system for the escalator, provided by the invention, designs the expert system which has case reasoning and rule reasoning, can flexibly configure and inherit by converting the cases in the case base into rules and storing the rules in the rule base, and meets the actual application requirements.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a flow chart of conventional pattern matching in an embodiment of the present invention;
FIG. 2 is a flow diagram of finding facts and rules in an embodiment of the invention;
FIG. 3 is a flow chart of an expert system mode of operation in an embodiment of the present invention;
FIG. 4 is a flow diagram of an expert schema rules inference schema in an embodiment of the present invention;
FIG. 5 is a flow diagram of case reasoning in an embodiment of the present invention;
FIG. 6 is a schematic representation of knowledge base organization in an embodiment of the invention;
FIG. 7 is a flow chart of a fully automatic mode of operation in an embodiment of the present invention;
FIG. 8 is a flow chart of a semi-automatic mode of operation in an embodiment of the present invention;
FIG. 9 is a flow chart of a human-machine dialog mode of operation in an embodiment of the present invention;
FIG. 10 is a flow chart of case learning in an embodiment of the present invention;
FIG. 11 is a flow diagram of case transformation rules in an embodiment of the invention;
FIG. 12 is a functional diagram of an expert system in an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
The present invention provides a fault diagnosis expert system for an escalator, referring to fig. 1-12, comprising: the system comprises an inference engine module, a knowledge base module, a knowledge interaction module, a case learning module and an interpreter module;
the knowledge base module is respectively connected with the inference engine module, the knowledge interaction module and the interpreter module; the knowledge base module comprises cases and diagnosis rules in the field of problems to be solved;
the knowledge interaction module is used for acquiring a fact value;
the inference engine module calls cases or diagnosis rules in the knowledge base module according to the acquired fact values to infer the fault phenomenon, so that the fault reason is obtained;
the interpreter module interprets the reasoning process and the deterministic conclusion obtained by reasoning;
the inference engine module comprises a rule inference engine module and a case inference engine module; the rule reasoning module adopts an expert system based on rules; the case reasoning module adopts an expert system based on frame-type knowledge representation;
the knowledge base module comprises a rule base and a case base; the rule base is connected with the rule reasoning module, and the case base is connected with the case reasoning module;
and the case learning module is used for converting the cases in the case base into rules and storing the rules in the rule base.
In this embodiment, the rule reasoning part adopts an expert system based on rules, the case reasoning part adopts an expert system based on frame-type knowledge representation, and the case base has a function of extracting cases as rules. The design core of the subway key equipment fault diagnosis expert system comprises 5 key technical points: rule reasoning engine, case reasoning engine, knowledge base (rule base, case base), knowledge interaction and case learning.
Further, the rule reasoning module is a rule reasoning engine technology based on task calling mode and rule activation, and the reasoning engine is enabled to check each rule to guide finding of the fact.
Specifically, a rule reasoning engine of the subway key equipment fault diagnosis expert system is optimized on the basis of a forward chain reasoning technology, and reasoning speed and efficiency are improved. The forward chain refers to a chain which is searched by the problem and solved, and the fact-based conclusion is deduced from the fact.
The rule reasoning process is implemented by pattern matching, as shown in fig. 1.
The facts refer to unit information, characteristic indexes of monitoring data and the like, and the rules are judgment of IF … THEN …. The inference engine determines whether the pattern of rules has been satisfied by examining each rule and looking for a set of facts, and if so, notes the rule in the agenda, as shown in fig. 2. In rule-based languages, the matching process is repeated. Typically, the fact list is modified on each execution, adding new facts to the fact list or deleting old facts. These changes may cause a pattern that previously failed to satisfy the condition to be satisfied, and vice versa. The matching problem is thus an ongoing process. In each loop, the set of rules that have been satisfied must be maintained and updated as facts are added and removed.
In the actual equipment fault diagnosis process, the expert system rule reasoning is not completely in the operation mode, but alarm triggering occurs in the monitoring process or the expert system is triggered manually to operate, only part of relevant rules are operated, and the relevant rules are selected according to the type of the unit and alarm information. As shown in fig. 3.
And (3) providing a rule inference engine technology based on a task calling mode and rule activation by combining the characteristics of a forward chain inference technology and an equipment diagnosis expert system, and enabling an inference engine to check each rule to guide the search of the fact. As shown in fig. 4, the expert system is reasoning about the pattern.
Further, the case reasoning module employs a combined search strategy based on association and knowledge induction.
Specifically, according to the characteristics of the faults of the critical equipment of the subway, a knowledge organization form of the case adopts a frame-based knowledge representation method, and the grooves of the frame are used as the attributes of the case, and the groove values are used as the similarity for judgment. The case reasoning engine employs a combined search strategy based on association and knowledge induction.
Further, the case reasoning module quickly finds out the case most similar to the case to be diagnosed from the case base according to the index strategy, the matching method and the similarity calculation method, as shown in fig. 5, the case reasoning module includes two steps:
the first step is as follows: searching out a similar case set of the equipment from a case library according to the equipment name, the part name and the unit state equipment information of the input case to be diagnosed;
the second step is that: searching out the most similar cases from the equipment similar case set by adopting a nearest matching method;
the nearest neighbor matching method represents the cases from the viewpoint of an n-dimensional space, and the feature vector corresponding to each case is composed of:
let V ═ a (i), …, a (i) } denote the feature vectors of the cases, the similarity of the two cases is expressed as follows:
in the formula:
t represents a case to be diagnosed;
t (i) the ith feature representing case T;
s represents a case in the case base;
(i) represents the ith feature of case S;
ωiweight of the ith feature of the representative case;
(1) t (i) when s (i) is the same, | t (i) -s (i) | 0; when t (i) is different from s (i), | t (i) -s (i) | 1
(2) Characteristic weight ωiIs determined
According to the importance degree of the features, the features are classified into 5 classes which are most important, very important, more important, general and optional, and the grade of the ith feature is assumed to be represented by kiDenotes kiIs a value from 1 to 5, the feature weight calculation method is:
the larger the similarity value is, the more similar the two cases are; the smaller the similarity value is, the larger the difference between the two cases is; when sim (T, S) ═ 1, the two cases are identical; and according to the method, the similarity between the case to be diagnosed and the case in the same type of case set of the equipment is calculated, and the case with the maximum similarity is found.
Further, the knowledge base comprises a rule base and a case base; the rule base and the case base share an attribute table and a fault table;
the attribute table is used for storing the type information of the actual value and the definition of the slot value in the case;
the fault table is used for storing the definition of the equipment fault;
the rule base further comprises:
the fact table is used for storing the characteristic item information of the equipment;
the task table is used for storing task information;
a rule table for storing all rules used in the expert system;
the case base further comprises:
a case table for storing all rules used in the expert system;
case details are used for storing detailed slot value information of the cases;
and the case accessory table is used for storing the accessory information of the case.
In particular, the expert system has both rule-based and case-based diagnostics, such that the knowledge base necessarily contains both parts, wherein fault and feature attributes are a common base. The organization of the knowledge base is shown in FIG. 6.
The area enclosed by the blue dotted line in fig. 6 is a form used for the rule-based diagnosis, and the area enclosed by the black dashed line is a form used for the case-based diagnosis. The following describes the functions of several key forms of the knowledge base table:
(1) attribute table: type information of the fact value and the definition of the slot value in the case are saved. The fields are: attribute ID, attribute name, attribute value set. In an expert system attributes are equal to slots. The attribute definition is carried out on the facts so as to improve the rule reasoning speed and limit the front-piece operation of the rules to integer operation.
(2) A fault table: the definition of the device failure is saved. The fields are: fault ID, fault name.
(3) Fact table: feature entry information for the device is saved. The fields are: fact ID, fact name, attribute ID (associated attribute table).
(4) A task table: and saving the task information. The fields are: task ID, task name, task action set (role: activation rule, activation failure, fact assignment), task type. The task is based on the entry of rules diagnostics, and the user or refinery machinery monitoring platform decides what rules to use by selecting the task.
(5) Rule table: all rules used in the expert system are saved. The fields are: rule ID, rule name, rule condition ID (association condition table), conclusion ID of rule (association conclusion table).
(6) Case table: summary information of the cases is preserved. The fields are: case ID, equipment type, fault ID (association fault table).
(7) Case detail: detailed slot value information for the case is preserved. The fields are: case ID (associated case table), attribute ID (i.e., slot name. associated attribute table), attribute value (i.e., slot value), weight.
(8) Case accessories table: the attachment information of the case is saved. The fields are: case ID (associated case table), attachment type, attachment size, attachment data. The attachments include waveform data, device pictures, and the like.
Further, the knowledge interaction module has three use modes: full-automatic diagnosis, semi-automatic diagnosis and man-machine conversation;
the method comprises the steps of full-automatic diagnosis, wherein the inference process does not involve interaction with external personnel, real values are automatically obtained, assignment operation is carried out through a state monitoring platform, and default values are adopted if automatic acquisition cannot be carried out;
semi-automatic diagnosis, which is the same as full-automatic reasoning diagnosis, is integrated in a state monitoring platform of a large turbine compressor unit, the fact value which is automatically obtained is assigned through the state monitoring platform, and a dialog box is automatically popped up to carry out selection operation, wherein the fact value which cannot be obtained is assigned through the state monitoring platform;
and man-machine interaction for information interaction between the user and each module of the fault diagnosis system.
Specifically, the knowledge interaction module of the expert system mainly aims at completing knowledge acquisition, namely the assignment process of the fact, and has three use modes: full-automatic diagnosis, semi-automatic diagnosis and man-machine conversation.
(1) Fully automatic diagnostics
And in the reasoning process, interaction with external personnel is not involved, the actual value can be automatically acquired, the assignment operation is carried out through the state monitoring platform, and if the actual value cannot be automatically acquired, the default value is adopted. As shown in fig. 7.
(2) Semi-automatic diagnosis
The function is integrated in a state monitoring platform of the large-scale turbine compressor unit, the fact value which can be automatically obtained is assigned through the state monitoring platform, and the fact value which cannot be obtained is automatically popped up to a dialog box for selection operation. Semi-automatic reasoning can improve the diagnostic accuracy compared with full-automatic reasoning, and after all, some data related to gas process parameters and electric appliances can not be obtained in a state monitoring platform sometimes. As shown in fig. 8. The only difference between semi-automatic diagnosis and full-automatic diagnosis is that more knowledge can be acquired through man-machine interaction, and more accurate diagnosis can be achieved.
(3) Human-machine conversation
Different from semi-automatic and full-automatic: human-machine dialog is one way to use the expert system alone. Except for the knowledge acquisition mode, the other steps are the same. Figure 9 shows the operating mode of the human-machine dialog.
Further, the case learning module is also used for converting the private case into the public case;
the private case is directly input from a monitoring platform of the large-scale turbine compressor unit, and the public case is formed after the private case is subjected to case learning and is confirmed by an expert; the use in case reasoning functions is all common cases.
Further, the process of converting the private case into the public case specifically comprises the following steps:
the first step is as follows: standardizing the attribute characteristics of the cases, and standardizing some nonstandard expressions used by case entry personnel;
the second step is that: the expert analyzes the input case and whether the input case has representative significance; after confirmation, a common case is formed.
Specifically, the case learning function mainly completes the function of converting the private case into the public case. The private case refers to a case directly input from a monitoring platform of the large-scale turbine compressor unit, and the public case refers to a case which can be formed after the private case is subjected to case learning and is confirmed by an expert. The use in case reasoning functions is all common cases.
Fig. 10 shows the process of converting a private case into a public case. The method is mainly completed through two steps of operation:
the first step is as follows: standardizing the attribute characteristics (groove values) of the cases, and standardizing some nonstandard expressions used by case entry personnel;
the second step is that: and (4) analyzing the input cases by experts to determine whether the input cases have representative significance. After confirmation, a common case is formed.
Further, the process of converting the cases in the case base into rules and storing the rules in the rule base specifically comprises the following steps:
the first step is as follows: screening the common cases, and screening out the cases which are similar and can directly distinguish faults;
the second step is that: different feature combinations and use sequences are summarized through optimizing classification;
the third step: the rules for transformation are confirmed by experts and finally saved to a rule base.
Specifically, case conversion into rules is an important way for knowledge accumulation, and common cases accumulated by long-term operation of a monitoring and diagnosing platform are an important supplement of an expert system rule base. The current case transformation rules can be put into actual expert diagnosis logic only after being confirmed by experts.
Case transformation into rules is essentially a process of optimizing classification. Case feature values (slot values) having typical features in a common case are judged as the fact of the rule. Fig. 11 is a flow chart of case conversion to rules.
The case conversion rule process is mainly completed in three steps:
the first step is as follows: and screening the common cases, and screening the cases which are similar to and can directly distinguish faults. Similar cases were screened out because two cases were similar and there was no need to handle both cases during transformation. The case which can directly distinguish the fault does not need to pass through a rule flow chart of case conversion, and the combination of all the slot values can be directly used as a front piece of the rule for judgment.
The second step is that: this step is a core step, and the case transformation rules are actually in the process of forming rule antecedents by using individual characteristics of cases. Because of the large number of features, it is necessary to summarize the combination and use order of different features through the process of optimizing classification.
The third step: the rules for transformation are confirmed by experts and finally saved to a rule base.
Meanwhile, the expert system has two modes of plug-in operation and single operation. In the plug-in operation mode, only full-automatic expert diagnosis and semi-automatic expert diagnosis functions can be performed. In the independent operation mode, a man-machine conversation diagnosis function, a rule maintenance function, a case conversion rule function, a report function of a diagnosis process and the like can be performed. Fig. 12 is a function of the expert system.
(1) The rule maintenance functions comprise adding and deleting rules, facts, tasks, attributes and the like.
(2) The case base maintenance is mainly responsible for the addition and deletion of the case base.
The present invention is not limited to the above preferred embodiments, and any modifications, equivalent replacements, improvements, etc. within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A fault diagnosis expert system for an escalator, comprising: the system comprises an inference engine module, a knowledge base module, a knowledge interaction module, a case learning module and an interpreter module;
the knowledge base module is respectively connected with the inference engine module, the knowledge interaction module and the interpreter module; the knowledge base module comprises cases and diagnosis rules in the field of problems to be solved;
the knowledge interaction module is used for acquiring a fact value;
the inference engine module calls cases or diagnosis rules in the knowledge base module according to the acquired fact values to infer the fault phenomenon, so that the fault reason is obtained;
the interpreter module interprets the reasoning process and the deterministic conclusion obtained by reasoning;
the inference engine module comprises a rule inference engine module and a case inference engine module; the rule reasoning module adopts an expert system based on rules; the case reasoning module adopts an expert system based on frame-type knowledge representation;
the knowledge base module comprises a rule base and a case base; the rule base is connected with the rule reasoning module, and the case base is connected with the case reasoning module;
and the case learning module is used for converting the cases in the case base into rules and storing the rules in the rule base.
2. The troubleshooting expert system for an escalator of claim 1, wherein said rule inference module is a rule inference engine technology based on task invocation and rule activation, and having an inference engine examine each rule to guide finding facts.
3. The troubleshooting expert system for an escalator of claim 1, wherein said case reasoning module employs a combined search strategy based on correlation and knowledge induction.
4. The expert system for fault diagnosis of escalator as claimed in claim 3, wherein said case reasoning module quickly finds the case most similar to the case to be diagnosed from the case base according to the indexing strategy, matching method and similarity calculation method, and is divided into two steps:
the first step is as follows: searching out a similar case set of the equipment from a case library according to the equipment name, the part name and the unit state equipment information of the input case to be diagnosed;
the second step is that: searching out the most similar cases from the equipment similar case set by adopting a nearest matching method;
the nearest neighbor matching method represents the cases from the viewpoint of an n-dimensional space, and the feature vector corresponding to each case is composed of:
let V ═ a (i), …, a (i) } denote the feature vectors of the cases, the similarity of the two cases is expressed as follows:
in the formula:
t represents a case to be diagnosed;
t (i) the ith feature representing case T;
s represents a case in the case base;
(i) represents the ith feature of case S;
ωiweight of the ith feature of the representative case;
(1) t (i) when s (i) is the same, | t (i) -s (i) | 0; when t (i) is different from s (i), | t (i) -s (i) | 1
(2) Characteristic weight ωiIs determined
According to the importance degree of the features, the features are classified into the most important, very important, more important, general and optional 5 grades, and the ith feature is assumed to be equalStage by kiDenotes kiIs a value from 1 to 5, the feature weight calculation method is:
the larger the similarity value is, the more similar the two cases are; the smaller the similarity value is, the larger the difference between the two cases is; when sim (T, S) ═ 1, the two cases are identical; and according to the method, the similarity between the case to be diagnosed and the case in the same type of case set of the equipment is calculated, and the case with the maximum similarity is found.
5. The fault diagnosis expert system for an escalator as claimed in claim 1, wherein said knowledge base includes a rule base and a case base; the rule base and the case base share an attribute table and a fault table;
the attribute table is used for storing the type information of the actual value and the definition of the slot value in the case;
the fault table is used for storing the definition of the equipment fault;
the rule base further comprises:
the fact table is used for storing the characteristic item information of the equipment;
the task table is used for storing task information;
a rule table for storing all rules used in the expert system;
the case base further comprises:
a case table for storing all rules used in the expert system;
case details are used for storing detailed slot value information of the cases;
and the case accessory table is used for storing the accessory information of the case.
6. The trouble diagnosis expert system for an escalator as set forth in claim 1,
the knowledge interaction module has three use modes: full-automatic diagnosis, semi-automatic diagnosis and man-machine conversation;
the method comprises the steps of full-automatic diagnosis, wherein the inference process does not involve interaction with external personnel, real values are automatically obtained, assignment operation is carried out through a state monitoring platform, and default values are adopted if automatic acquisition cannot be carried out;
semi-automatic diagnosis, which is the same as full-automatic reasoning diagnosis, is integrated in a state monitoring platform of a large turbine compressor unit, the fact value which is automatically obtained is assigned through the state monitoring platform, and a dialog box is automatically popped up to carry out selection operation, wherein the fact value which cannot be obtained is assigned through the state monitoring platform;
and man-machine interaction for information interaction between the user and each module of the fault diagnosis system.
7. The troubleshooting expert system for an escalator of claim 1, wherein said case learning module is further for converting private cases to public cases;
the private case is directly input from a monitoring platform of the large-scale turbine compressor unit, and the public case is formed after the private case is subjected to case learning and is confirmed by an expert; the use in case reasoning functions is all common cases.
8. The expert system for fault diagnosis of escalator as claimed in claim 1, wherein said process of converting private cases into public cases is specifically:
the first step is as follows: standardizing the attribute characteristics of the cases, and standardizing some nonstandard expressions used by case entry personnel;
the second step is that: the expert analyzes the input case and whether the input case has representative significance; after confirmation, a common case is formed.
9. The expert system for fault diagnosis of escalator as claimed in claim 8, wherein said process of converting cases in case base into rules and storing them in rule base is specifically:
the first step is as follows: screening the common cases, and screening out the cases which are similar and can directly distinguish faults;
the second step is that: different feature combinations and use sequences are summarized through optimizing classification;
the third step: the rules for transformation are confirmed by experts and finally saved to a rule base.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110320264.5A CN113128687A (en) | 2021-03-25 | 2021-03-25 | Fault diagnosis expert system for escalator |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110320264.5A CN113128687A (en) | 2021-03-25 | 2021-03-25 | Fault diagnosis expert system for escalator |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113128687A true CN113128687A (en) | 2021-07-16 |
Family
ID=76774121
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110320264.5A Pending CN113128687A (en) | 2021-03-25 | 2021-03-25 | Fault diagnosis expert system for escalator |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113128687A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522329A (en) * | 2018-09-30 | 2019-03-26 | 蓝库时代(北京)科技有限公司 | A kind of marketing communication analysis method based on artificial intelligence |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105302112A (en) * | 2015-10-23 | 2016-02-03 | 中国电子科技集团公司第十研究所 | Intelligent fault diagnosis system for ICNI system |
| CN107168285A (en) * | 2017-05-26 | 2017-09-15 | 大连理工大学 | A kind of automobile intelligent fault diagnosis of combination subjective and objective information and cloud model and maintenance householder method and system |
| CN110296124A (en) * | 2019-06-03 | 2019-10-01 | 武汉工程大学 | Remote failure diagnosis system and method based on expert system |
| CN110705812A (en) * | 2019-04-15 | 2020-01-17 | 中国石油大学(华东) | Industrial fault analysis system based on fuzzy neural network |
-
2021
- 2021-03-25 CN CN202110320264.5A patent/CN113128687A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105302112A (en) * | 2015-10-23 | 2016-02-03 | 中国电子科技集团公司第十研究所 | Intelligent fault diagnosis system for ICNI system |
| CN107168285A (en) * | 2017-05-26 | 2017-09-15 | 大连理工大学 | A kind of automobile intelligent fault diagnosis of combination subjective and objective information and cloud model and maintenance householder method and system |
| CN110705812A (en) * | 2019-04-15 | 2020-01-17 | 中国石油大学(华东) | Industrial fault analysis system based on fuzzy neural network |
| CN110296124A (en) * | 2019-06-03 | 2019-10-01 | 武汉工程大学 | Remote failure diagnosis system and method based on expert system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109522329A (en) * | 2018-09-30 | 2019-03-26 | 蓝库时代(北京)科技有限公司 | A kind of marketing communication analysis method based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7430548B2 (en) | Rule processing system | |
| US20040181500A1 (en) | Method and system for capturing business rules for automated decision procession | |
| Liu et al. | An efficient expert system for machine fault diagnosis | |
| Xiang et al. | A “microscopic” study of minimum entropy search in learning decomposable Markov networks | |
| Baroni et al. | Diagnosis of a class of distributed discrete-event systems | |
| CN110597235A (en) | Universal intelligent fault diagnosis method | |
| CN113128687A (en) | Fault diagnosis expert system for escalator | |
| CN109766448A (en) | A kind of long-range preventative frequency conversion management system | |
| US5179632A (en) | Fast method for a bidirectional inference | |
| Gu et al. | A knowledge-intensive method for conversational CBR | |
| Alruqi et al. | A structured approach for synchronising the applications of failure mode and effects analysis | |
| Gutierrez et al. | A comparison between expert systems and autonomic computing plus mobile agent approaches for fault management. | |
| Goodman et al. | Real time autonomous expert systems in network management | |
| Kahn | From Application Shell to Knowledge Acquisition System. | |
| Gu et al. | Explanation-boosted question selection in conversational CBR | |
| Rezk et al. | Formalizing production systems with rule-based ontologies | |
| Macleish | Mapping the integration of artificial intelligence into telecommunications | |
| Deutch et al. | Type inference and type checking for queries over execution traces | |
| CN109143189A (en) | A kind of radar transmitter fault diagnosis method and system | |
| Kamp et al. | Falldaten: Case-based reasoning for the diagnosis of technical devices | |
| Padmanabhan | DECIMAL: A requirements engineering tool for product families | |
| Hasan et al. | An object-oriented expert system for power system alarm processing and fault identification | |
| de Silva | A criterion for knowledge base decoupling in fuzzy-logic control systems | |
| Jubo et al. | Application Analysis of Machine Learning in Intelligent Operation and Maintenance System | |
| Shahrestani | Utilization of soft computing to improve cooperative management efficiency |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210716 |
|
| RJ01 | Rejection of invention patent application after publication |