CN111337237B

CN111337237B - Equipment fault diagnosis method and system

Info

Publication number: CN111337237B
Application number: CN202010215929.1A
Authority: CN
Inventors: 成国良; 黄俊飞; 占鹏
Original assignee: Beijing Bicotest Tech Co ltd
Current assignee: Beijing Bicotest Tech Co ltd
Priority date: 2020-03-17
Filing date: 2020-03-17
Publication date: 2021-10-15
Anticipated expiration: 2040-03-17
Also published as: CN111337237A

Abstract

The invention relates to a method and a system for diagnosing equipment faults. The diagnostic method comprises the following steps: obtaining a diagnostic model of the device; acquiring component parameters of each component in the equipment to be detected according to the diagnosis model; acquiring a fault model matrix corresponding to equipment to be detected; obtaining vibration data of the equipment to be detected, wherein the vibration data of each part at a plurality of detection points is included; for the ith component, screening the vibration data of the component according to the fault code information of the component to obtain a data screening table corresponding to the component; extracting the data screening table of the component by using the characteristic parameter extraction rule of the component to generate a characteristic parameter extraction table of the component; performing logic operation and arithmetic operation on data of a characteristic parameter extraction table of the component by using a fault diagnosis rule of the component, and determining a fault mode and a fault level corresponding to the component; and obtaining a fault detection result of the equipment to be detected. The invention can realize fault diagnosis of the general equipment and improve the accuracy of fault detection.

Description

Equipment fault diagnosis method and system

Technical Field

The invention relates to the field of equipment maintenance, in particular to a method and a system for diagnosing equipment faults.

Background

With the continuous improvement of the technological development level and the upgrading of the production and manufacturing requirements, various production equipment is continuously developed towards large scale, automation and intellectualization, and especially in the industrial field of continuous production, the requirement on the reliability of the equipment is higher and higher. Once equipment fails, the production line is shut down if the equipment fails, so that great economic loss is caused, and equipment accidents occur if the equipment fails, so that the equipment and personal safety are endangered. Therefore, more and more industries and enterprises pay more and more attention to the running state of the equipment, and various state monitoring systems are gradually introduced to realize state monitoring and fault prediction of important equipment, scientifically arrange shutdown, prevent equipment accidents and improve the reliability of the equipment.

In the past, the operating state of the rotating equipment is judged mainly by traditional simple means such as listening, touching, seeing and the like in the process of operating and maintaining the equipment. The perceptual judgment is far from the actual running state of the equipment, and the waveform and frequency spectrum change of the equipment vibration cannot be checked by hearing, touching and watching of a person, so that some sudden faults, such as the most common faults of a bearing, a gear, blade falling, dynamic balance and the like, often occur, people are in a passive maintenance state, and minor problems are caused to be major accidents. Particularly, in some process industries with continuous production, a chain reaction of damaging other equipment is often caused due to untimely damage treatment of one equipment, and heavy burden is brought to safe production and maintenance work.

Therefore, both mechanical experts and equipment management personnel at home and abroad seek a better solution to accurately judge the cause of the accident in the initial state of the fault, so that the equipment can be maintained in advance and becomes passive to active. After extensive exploration and continuous practice, the vibration analysis system is widely applied to the field of fault detection and diagnosis of rotary mechanical equipment. The state monitoring and fault diagnosis of the equipment is to quantitatively measure the mechanical technical state in the condition that the machine is in operation or the mechanical structure is not basically disassembled, quantitatively identify the real-time technical state of the mechanical equipment, parts and components thereof by processing and analyzing the measured signals and combining the historical condition of a diagnosis object, predict the abnormal and future technical state of the machine, analyze and judge fault positions and reasons, and timely determine necessary countermeasures and the most suitable repair time.

The equipment state monitoring and fault diagnosis technology is beneficial to enterprises to implement modern equipment management and overcomes the phenomena of 'excessive maintenance' and 'insufficient maintenance' in maintenance work, thereby achieving the aims of most economical cost and highest comprehensive efficiency of equipment in the service life cycle of the equipment.

At present, vibration analysis technology is well developed in the diagnosis of faults of rotating machinery equipment, and the vibration analysis technology is a method for converting vibration signals into electric signals by using a piezoelectric acceleration sensor by using a professional instrument, processing and analyzing the vibration signals to obtain accurate values of various vibration quantities of the equipment, and further judging whether the running states of the equipment are good, and the positions and reasons of the faults and the maintenance of the equipment. In order to better apply the fault diagnosis technology of the vibration analysis equipment, a certain understanding needs to be provided for the vibration theory, the mechanical principle, the signal processing, the computer application and the like, various professional maps such as a time domain oscillogram, a frequency spectrogram and the like are skillfully read, the significance and the use of special parameters such as a pulse index, a peak factor, a kurtosis index and the like are familiar, the professional knowledge is high, the requirement on the professional knowledge is high, training of a special system and a large amount of practice accumulation are needed, and the general personnel are difficult to master. In addition, in the state monitoring work, the data volume acquired at one time is large, time and labor are consumed when manual analysis is adopted, timeliness is insufficient, only emphasis can be placed on an alarm value, machines with state parameters reaching alarm threshold values pay attention to and analyze emphasis, devices which are not obviously represented due to the hidden trouble are ignored, focus points of state monitoring are insufficient, and the hidden trouble of early failure of the machines is difficult to find.

In order to overcome the defects of the manual analysis, a plurality of vibration analysis technology manufacturers develop a series of automatic diagnosis systems, and perform automatic diagnosis by applying pure theoretical knowledge such as vibration analysis theory, failure mechanism and performance, failure map performance characteristics and the like after performing some necessary processing on data acquired by an instrument, so as to provide possible failure types of the current machine, and some manufacturers can further provide necessary processing measures for diagnosis conclusions on the basis. In the traditional automatic diagnosis system, the diagnosis of the fault is often inferred from the angle of pure theoretical analysis, the full consideration of actual working conditions and machine characteristics is lacked, the diagnosis result lists possible faults one by one in a credibility mode, the conclusion is fuzzy, the uncertainty is large, and then a user accepts or rejects the fault according to the conclusion and the actual test data, so that higher professional requirements are provided for the user or the direct user; given conclusions can rarely quantify the severity of the fault, and a user needs to manually evaluate the fault according to the acquired data through experience; the further treatment measures are often lack of pertinence, are mostly universal solutions, are less combined with diagnosis conclusions and actual machine states, and lack of guidance. However, in the conventional automatic diagnosis system, an "absolute standard" is mostly adopted to determine whether a fault exists, the consideration on the difference of state parameters of the machine under different backgrounds such as actual working conditions, operating conditions, arrangement modes, installation and maintenance is lacked, and the diagnosis conclusion is "static" and "dead" and cannot be actually adapted to the equipment. Such as: a certain machine runs under high vibration for a long time, but all parts of the machine are possibly in a normal state, and the high vibration is the special working condition of the machine; and if the vibration of a certain machine is low, high impact can exist in the machine, and faults such as bearing abrasion and the like frequently occur. The traditional diagnosis system adopts the 'absolute standard' to cause poor accuracy of diagnosis of the two machines, and even cause wrong guidance to a user, thereby causing unnecessary loss.

In the development of the traditional automatic diagnosis system, an automatic diagnosis system aiming at a certain type of equipment or a certain special equipment is also developed, and the accuracy and the practicability of the automatic diagnosis system are also practically verified. The system is often an expert diagnosis system, is an intelligent computer program capable of carrying out fault at a human expert level, and has high diagnosis efficiency and high diagnosis level because the targeted objects and application scenes are often large and complex special equipment and are reasoned by a computer under the knowledge of human experts, thereby representing certain advancement. However, such systems are mainly applied to special and special equipment, such as turbo generator sets, automobile or railway locomotives, large engineering machinery and the like, and are mostly used for comprehensive diagnosis. The reproducibility and the portability of the logic and the rules are poor, the method is only suitable for the machine, other types of machines cannot be diagnosed, the general applicability is poor, and the use cost is high for users. In the industrial field, various general-purpose machines such as various pumps, fans, compressors, motors, gear boxes and other devices are widely applied, and the diagnosis system is obviously not suitable for automatic diagnosis of the general-purpose machines. On the other hand, the diagnostic logic of such systems is often built into the software through program codes, and has no or a small amount of logic maintenance functions, and only hopes to upgrade the whole software program. Related rules are closed, the formation of the rules often needs to have certain computer programming capability, some codes need to be written, and the establishment of the rules is difficult to realize only by business personnel or diagnostic experts.

Disclosure of Invention

The invention aims to provide a method and a system for diagnosing equipment faults, so as to realize automatic fault diagnosis of general equipment through open diagnosis rules and improve the accuracy of fault detection.

In order to achieve the purpose, the invention provides the following scheme:

a method of diagnosing equipment failure, comprising:

obtaining a diagnostic model of the device; the diagnostic model comprises component parameters corresponding to each component, and the component parameters comprise component codes, characteristic codes, data source codes and fault code information; the part code characterizes a type of part; the property code characterizes a local property of the component; the data source code represents the index position of data required by diagnosis of the component; the fault code information is frequency component information corresponding to each fault code, and each component comprises a plurality of fault codes;

acquiring component parameters of each component in the equipment to be detected according to the diagnosis model;

acquiring a fault model matrix corresponding to the equipment to be detected according to the component parameters of each component in the equipment to be detected; the fault model matrix comprises a characteristic parameter extraction rule and a fault diagnosis rule; the characteristic parameter extraction rule is a parameter calculation and data screening rule required for diagnosing component faults and corresponds to the component code; the fault diagnosis rule comprises a logic operation rule and an arithmetic operation rule, is a rule for generating a fault mode and a fault grade by utilizing characteristic parameters through logic and arithmetic operations, and corresponds to a code formed by combining the component code and the characteristic code;

acquiring vibration data of equipment to be detected; the vibration data of the equipment to be detected comprises vibration data of each part at a plurality of detection point positions, and comprises frequency spectrum data, time domain data, passband value data, common evaluation index data and the like;

for the ith component, screening the vibration data of the component according to the fault code information of the component to obtain a data screening table corresponding to the component;

extracting the data screening table of the component by using the characteristic parameter extraction rule of the component to generate a characteristic parameter extraction table of the component;

performing logical operation and arithmetic operation on data of a characteristic parameter extraction table of the component by using a fault diagnosis rule of the component, and determining a fault mode and a fault level corresponding to the component; the failure mode of the component is a result of the logical operation, and the failure level of the component is a result of the arithmetic operation;

and acquiring the fault mode and the fault grade corresponding to each part to obtain the fault detection result of the equipment to be detected.

Optionally, the obtaining a fault model matrix corresponding to the device to be detected according to the component parameter of each component in the device to be detected further includes:

determining the feature parameter extraction rule according to the component code of the component;

and determining the fault diagnosis rule according to the component code and the characteristic code of the component.

Optionally, for the ith component, screening the vibration data of the component according to the fault code information of the component to obtain a data screening table corresponding to the component, specifically including:

extracting peak data of each fault code frequency component information from each vibration data according to the frequency component information corresponding to each fault code of the ith component to obtain a plurality of fault code peak data corresponding to each vibration data; the fault code frequency component information is frequency component information corresponding to the fault code;

extracting peak data of a plurality of non-fault code frequency component information from each piece of vibration data to obtain a plurality of non-fault code peak data corresponding to each piece of vibration data; the non-fault code frequency component information is a plurality of frequency component information with higher amplitude except the frequency component information corresponding to the fault code, and is arranged in descending order according to the amplitude;

acquiring baseline data of each fault code frequency component information and baseline data of each non-fault code frequency component information;

calculating the difference value of each fault code frequency component information and the difference value of each non-fault code frequency component information in each vibration data; the difference value of the fault code frequency component information is the difference value of peak data and baseline data of the fault code frequency component information, and the difference value of the non-fault code frequency component information is the difference value of peak data and baseline data of the non-fault code frequency component information;

obtaining a mark value corresponding to each vibration data; when the difference value of the fault code frequency component information is larger than zero, the mark value corresponding to the fault code frequency component information is not null, and when the difference value of the fault code frequency component information is not larger than zero, the mark value corresponding to the fault code frequency component information is null; when the difference value of the non-fault code frequency component information is larger than zero, the corresponding mark value of the non-fault code frequency component information is not null, and when the difference value of the non-fault code frequency component information is not larger than zero, the corresponding mark value of the non-fault code frequency component information is null;

and generating a data screening table corresponding to the ith component according to fault code peak data, non-fault code peak data, a difference value of fault code frequency component information, a difference value of non-fault code frequency component information and a marking value corresponding to each vibration data of the ith component.

Optionally, the fault model matrix further includes an action suggestion rule, where the action suggestion rule is a rule for generating an action suggestion and a priority through a logic operation and an arithmetic operation by using a fault mode and a fault level, and corresponds to the component code;

the method comprises the following steps of obtaining a fault mode and a fault grade corresponding to each component to obtain a fault detection result of the equipment to be detected, and then:

and adopting the logic operation and the arithmetic operation of the action suggestion rule to the fault modes and the fault grades corresponding to all the parts to obtain the action suggestions and the priority of the equipment to be detected.

Optionally, the obtaining of the action recommendation of the device to be detected by using the logical operation of the action recommendation rule for the fault mode and the fault level corresponding to all the components further includes:

acquiring a structured code of a new action suggestion rule input by a user;

and updating the action suggestion rules in the fault model matrix by adopting the new action suggestion rules.

Optionally, the determining the fault mode and the fault level corresponding to the component by performing logical operation and arithmetic operation on the data in the feature parameter extraction table of the component according to the fault diagnosis rule of the component specifically includes:

according to an operational rule of an operator in the fault diagnosis rule of the component, data of a characteristic parameter extraction table of the component are operated, and a fault mode and a fault level corresponding to the component are determined; the operators comprise comparison operators, arithmetic logic operators, logic operators and arithmetic operators; the arithmetic logic operator is used for simultaneously carrying out logic operation and arithmetic operation; the logical operator is used for carrying out logical operation; the arithmetic operator is used for performing arithmetic operations.

Optionally, the obtaining a fault mode and a fault level corresponding to each component to obtain a fault detection result of the device to be detected, and then further includes:

acquiring an imaging operator dragged and selected by a user; the imaging operator includes: a comparison operator, an arithmetic logic operator, a logic operator and an arithmetic operator; the arithmetic logic operator is used for simultaneously carrying out logic operation and arithmetic operation; the logical operator is used for carrying out logical operation; the arithmetic operator is used for carrying out arithmetic operation;

generating a new fault diagnosis rule according to the imaging operator dragged and selected by the user;

and updating the fault diagnosis rule in the fault model matrix by adopting the new fault diagnosis rule.

acquiring an extraction parameter corresponding to each fault code selected by a user; different extraction parameters correspond to different parameter extraction algorithms;

generating a new characteristic parameter extraction rule according to the extraction parameters corresponding to each fault code selected by the user;

and updating the characteristic parameter extraction rule in the fault model matrix by adopting the new characteristic parameter extraction rule.

The invention also provides a system for diagnosing equipment faults, which comprises:

the diagnostic model acquisition module is used for acquiring a diagnostic model of the equipment; the diagnostic model comprises component parameters corresponding to each component, and the component parameters comprise component codes, characteristic codes, data source codes and fault code information; the part code characterizes a type of part; the property code characterizes a local property of the component; the data source code represents the index position of data required by diagnosis of the component; the fault code information is frequency component information corresponding to each fault code, and each component comprises a plurality of fault codes;

the component parameter acquisition module is used for acquiring component parameters of each component in the equipment to be detected according to the diagnosis model;

the fault model matrix acquisition module is used for acquiring a fault model matrix corresponding to the equipment to be detected according to the component parameters of each component in the equipment to be detected; the fault model matrix comprises a characteristic parameter extraction rule and a fault diagnosis rule; the characteristic parameter extraction rule is a parameter calculation and data screening rule required for diagnosing component faults and corresponds to the component code; the fault diagnosis rule comprises a logic operation rule and an arithmetic operation rule, is a rule for generating a fault mode and a fault grade by utilizing characteristic parameters through logic and arithmetic operations, and corresponds to a code formed by combining the component code and the characteristic code;

the vibration data acquisition module is used for acquiring vibration data of the equipment to be detected; the vibration data of the equipment to be detected comprises vibration data of each part at a plurality of detection point positions;

the data screening module is used for screening the vibration data of the ith component according to the fault code information of the component to obtain a data screening table corresponding to the component;

the parameter extraction module is used for extracting the data screening table of the component by using the characteristic parameter extraction rule of the component to generate a characteristic parameter extraction table of the component;

the fault diagnosis module is used for performing logic operation and arithmetic operation on data of the characteristic parameter extraction table of the component by using a fault diagnosis rule of the component to determine a fault mode and a fault level corresponding to the component; the failure mode of the component is a result of the logical operation, and the failure level of the component is a result of the arithmetic operation;

and the fault detection result acquisition module is used for acquiring the fault mode and the fault grade corresponding to each component to obtain the fault detection result of the equipment to be detected.

Optionally, the method further includes:

the characteristic parameter extraction rule determining module is used for determining the characteristic parameter extraction rule according to the component code of each component before the fault model matrix corresponding to the equipment to be detected is obtained according to the component parameter of each component in the equipment to be detected;

and the fault diagnosis rule determining module is used for determining the fault diagnosis rule according to the component code and the characteristic code of the component.

Optionally, the data screening module specifically includes:

a fault code peak data extraction unit, configured to extract peak data of each fault code frequency component information from each piece of vibration data according to frequency component information corresponding to each fault code of the ith component, so as to obtain multiple fault code peak data corresponding to each piece of vibration data; the fault code frequency component information is frequency component information corresponding to the fault code;

the non-fault code peak data extraction unit is used for extracting peak data of a plurality of pieces of non-fault code frequency component information from each piece of vibration data to obtain a plurality of pieces of non-fault code peak data corresponding to each piece of vibration data; the non-fault code frequency component information is a plurality of frequency component information except the frequency component information corresponding to the fault code;

a baseline data acquisition unit for acquiring baseline data of each fault code frequency component information and baseline data of each non-fault code frequency component information;

a difference value calculating unit for calculating a difference value of each fault code frequency component information and a difference value of each non-fault code frequency component information in each piece of vibration data; the difference value of the fault code frequency component information is the difference value of peak data and baseline data of the fault code frequency component information, and the difference value of the non-fault code frequency component information is the difference value of peak data and baseline data of the non-fault code frequency component information;

the marking value acquisition unit is used for acquiring a marking value corresponding to each piece of vibration data; when the difference value of the fault code frequency component information is larger than zero, the mark value corresponding to the fault code frequency component information is not null, and when the difference value of the fault code frequency component information is not larger than zero, the mark value corresponding to the fault code frequency component information is null; when the difference value of the non-fault code frequency component information is larger than zero, the corresponding mark value of the non-fault code frequency component information is not null, and when the difference value of the non-fault code frequency component information is not larger than zero, the corresponding mark value of the non-fault code frequency component information is null;

and the data screening table generating unit is used for generating a data screening table corresponding to the ith component according to fault code peak data, non-fault code peak data, the difference value of fault code frequency component information, the difference value of non-fault code frequency component information and the marking value corresponding to each vibration data of the ith component.

the system for diagnosing the equipment fault further comprises:

and the action suggestion acquisition module is used for acquiring the fault mode and the fault grade corresponding to each component to obtain the fault detection result of the equipment to be detected, and then adopting the logic operation and the arithmetic operation of the action suggestion rule to the fault mode and the fault grade corresponding to all the components to obtain the action suggestion and the priority of the equipment to be detected.

Optionally, the method further includes:

the user dragging selection information acquisition module is used for acquiring a fault mode and a fault grade corresponding to each part and acquiring a fault detection result of the equipment to be detected and then acquiring an imaging operator selected by user dragging;

the new fault diagnosis rule acquisition module is used for generating a new fault diagnosis rule according to the imaging operator dragged and selected by the user;

and the fault diagnosis rule base updating module is used for updating the fault diagnosis rules in the fault model matrix by adopting the new fault diagnosis rules.

According to the specific embodiment provided by the invention, the invention discloses the following technical effects:

by applying the invention, not only can the fault be diagnosed, but also the severity of the fault and the corresponding maintenance suggestion can be further calculated, and the five problems concerned by the user are really solved? "," where there is a fault? "," what failure is? "," how serious a fault is? What is "and"? ". Compared with the traditional automatic diagnosis system which can only diagnose the fault type, the automatic diagnosis system has the advantages that all faults on the machine are pushed out, the faults are graded and quantified, solutions are provided for the faults with different severities, the problem which is most concerned by users in practical application is really solved, and the health state of the machine is mastered.

The invention can replace or assist the practitioner to complete the work which can be completed by depending on special technology or experts before, help the practitioner to get rid of the dependence on technical experts, strengthen the equipment state management capability and the equipment health management capability, liberate from the fussy and repeated work, put more energy into professional management and equipment management activities, and generate positive and significant social benefits in the aspects of improving the equipment reliability and safety, reducing the maintenance cost and production cost, prolonging the equipment service life and the like.

In addition, the invention adopts an open rule editing system, realizes diagnosis logic compiling by using a logic configuration diagram mode, is visual and open, can ensure that a user designs the rule at any time, does not need to modify program codes for editing and modifying the rule, does not need programming professional knowledge, and is more convenient for the maintenance of the rule by diagnosis technicians; the human expert can conveniently maintain the content of the knowledge base, and the product performance and the user experience are continued through continuous updating and continuous upgrading of the knowledge base.

Drawings

In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings needed to be used in the embodiments will be briefly described 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 without inventive exercise.

FIG. 1 is a schematic flow chart of a method for diagnosing equipment failure according to the present invention;

FIG. 2 is a schematic view of a part of the structure of the device to be tested according to the present invention;

FIG. 3 is a diagram of the relationship between data source codes and position codes;

FIG. 4 is a logical block diagram of one of the failure modes in the failure diagnosis rules;

FIG. 5 is a diagram of the logic structure of an action suggestion rule;

fig. 6 is a schematic structural diagram of the apparatus failure diagnosis system of the present invention.

Detailed Description

The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.

Fig. 1 is a schematic flow chart of the method for diagnosing the equipment fault according to the present invention. As shown in fig. 1, the method for diagnosing the equipment fault of the present invention includes the following steps:

step 100: a diagnostic model of the device is obtained. Most machines or devices are broken down into multiple components according to structural characteristics, and the components are generally common. For example, according to the structural characteristics of a certain water pump, the water pump is divided into three parts, namely a Motor (MTR), a Coupling (CPL) and a centrifugal Pump (PUM). The diagnostic model of the present invention includes component parameters corresponding to each generic component, including component code, property code, data source code, and fault code information. Wherein the part code characterizes a type of part; the property code characterizes a local property of the component; the data source code represents the index position of data required by diagnosis of the component; the fault code information is frequency component information corresponding to each fault code, and each component comprises a plurality of fault codes.

In the actual operation of the machine, specific frequency components are necessarily existed, wherein the specific frequency components are higher or lower, the frequency components are from the excitation frequency in the operation process of the internal structural parts of the machine/component, and the existence of the frequency components is often one of the bases for diagnosing faults. The invention defines the components by adopting fault codes, identifies specific frequency components by using different codes, such as 1 frequency multiplication and/or harmonic waves, gear meshing frequency, blade passing frequency and the like, and classifies and defines the special frequency components of each type of components to form a uniform fault code table. Each fault code has a unique frequency component corresponding to it in a particular machine test datum. These specific fault codes are used uniformly to identify specific frequency components in the development of diagnostic rules and the execution of diagnostic procedures. Therefore, the fault code information of the present invention is frequency component information corresponding to each fault code, and each component includes a plurality of fault codes.

Step 200: and acquiring the component parameters of each component in the equipment to be detected according to the diagnosis model. The diagnostic model comprises the component parameters of each component, so that the component parameters corresponding to each component of the equipment to be detected can be extracted from the diagnostic model according to the components of the equipment to be detected.

Step 300: and acquiring a fault model matrix corresponding to the equipment to be detected according to the component parameters of each component in the equipment to be detected. The fault model matrix comprises characteristic parameter extraction rules and fault diagnosis rules. The feature parameter extraction rule is a parameter calculation and data screening rule required for diagnosing component faults and corresponds to the component code. Therefore, the feature parameter extraction rule can be determined from the component code of the component at the time of diagnosis. The fault diagnosis rule includes a logic operation rule and an arithmetic operation rule, is a rule for generating a fault mode and a fault level by a logic and arithmetic operation using a characteristic parameter, and corresponds to a code in which the component code and the characteristic code are combined. At the time of diagnosis, the failure diagnosis rule can be directly determined based on the component code and the characteristic code of the component.

Step 400: and acquiring vibration data of the equipment to be detected. The vibration data of the device under test includes vibration data for each component at a plurality of inspection site locations. The vibration data of the component are all located on the determined measuring points, and can be unidirectional data, namely data with one measuring point only in one direction, or multidirectional data, namely data with two or more directions on one measuring point.

The vibration data of the device to be detected is a set of data of each measuring point of each part, and the distribution of each measuring point of each part is closely related to the part. By taking fig. 2 as an example, fig. 2 is a schematic view of a part of the structure of the device to be tested according to the present invention. As shown in fig. 2, the test data of the device to be tested comes from the motor 1 and the centrifugal pump 2, and the vibration data of the device to be tested is the vibration data decomposed on the components. In practice, the definition of the machine point code is completely random, and is randomly determined by a tester according to some agreed customs and the actual situation of the field device, and the data must be correctly decomposed on the component to carry out correct diagnosis. Therefore, there is a need for a fixed rule to distribute data to meet diagnostic needs. The invention adopts the data source code to convert the test data. The data source codes are attached to the existence of the components, each component of the machine is allocated to one data source code according to corresponding logic, the data source codes are sequences formed by corresponding machine measuring point codes on the components, the data source codes comprise measuring point codes of the components and measuring point codes of adjacent components, and the measuring point codes are arranged according to a specific sequence. As shown in fig. 2, the data source Code (DS Code) of the motor 1 is: 1, 4; the data source Code (DS Code) of the coupler is: 1, 4; the data source Code (DS Code) of the centrifugal pump is 4, 1.

The length and the arrangement order of the data source codes are not fixed, and the data source codes of each type of components are uniformly regulated according to the number of the measuring points on the components, data required for diagnosis and the like. Although the data source code uses the measuring point code of the machine, the invention uses the position code in the diagnosis process. Taking fig. 3 as an example, fig. 3 is a relationship diagram of data source codes and position codes. In the figure, A, B, C, D of the data source code is the station code of the machine, and the position code is the position of the machine station code in the data source code. If motor MTRAC in fig. 2 has DS codes of 1 and 4, its position codes are 1 and 2, respectively. The measuring point codes of the machine/component are unified through the data source codes, so that the randomness of the definition of the measuring point codes cannot influence the chaos of diagnostic data. In the diagnosis process, data on a corresponding measuring point of the machine is obtained through the corresponding relation between the position code and the measuring point code A, B, C, D, if a certain rule is pump rotor unbalance, 1R and 1A data diagnosis is used in the diagnosis rule, and data corresponding to measuring point codes of 4R and 4A are used, as can be seen from figure 2, the data of the centrifugal pump is used for diagnosing the fault of the equipment to be detected.

Step 500: and for the ith component, screening the vibration data of the component according to the fault code information of the component to obtain a data screening table corresponding to the component. The data screening table of the component is obtained by extracting corresponding peak data and other peak data under corresponding fault codes according to vibration data of the component, the peak data comprises peaks of fixed algorithms and higher peaks except the fault codes, and the data are respectively extracted according to measuring point distribution.

Different components correspond to different fault code information, and for the ith component, the specific process of screening is as follows:

extracting peak data of each fault code frequency component information from each vibration data according to the frequency component information corresponding to each fault code of the ith component to obtain a plurality of fault code peak data corresponding to each vibration data; and the fault code frequency component information is frequency component information corresponding to the fault code.

Extracting peak data of a plurality of non-fault code frequency component information from each piece of vibration data to obtain a plurality of non-fault code peak data corresponding to each piece of vibration data; the non-fault code frequency component information is a plurality of frequency component information with high peak values except the frequency component information corresponding to the fault code.

Baseline data for each fault code frequency component information and baseline data for each non-fault code frequency component information are obtained. The baseline data refers to a normal peak value corresponding to each measuring point position under the frequency component information.

And calculating the difference value of each fault code frequency component information and the difference value of each non-fault code frequency component information in each piece of vibration data. The difference value of the fault code frequency component information is the difference value of peak data and baseline data of the fault code frequency component information, and the difference value of the non-fault code frequency component information is the difference value of peak data and baseline data of the non-fault code frequency component information.

Obtaining a mark value corresponding to each vibration data; when the difference value of the fault code frequency component information is larger than zero, the mark value corresponding to the fault code frequency component information is not null, and when the difference value of the fault code frequency component information is not larger than zero, the mark value corresponding to the fault code frequency component information is null; when the difference value of the non-fault code frequency component information is larger than zero, the corresponding mark value of the non-fault code frequency component information is not null, and when the difference value of the non-fault code frequency component information is not larger than zero, the corresponding mark value of the non-fault code frequency component information is null.

And generating a data screening table corresponding to the ith component according to fault code peak data, non-fault code peak data, a difference value of fault code frequency component information, a difference value of non-fault code frequency component information and a marking value corresponding to each vibration data of the ith component. The data screening table is shown in table 1.

Table 1 data screening table example

Loc	1X	2X	100	3X	4X	5X	PV	7X	8X	9X	Peak1	Peak 2	Peak 3	Peak 4
															2A Real	112	99	93	85	77	80	87	78	70	59	-2(0.79)	-5(0.89)	-5(0.88)	-7(1.46)
2A Byd	2	-1	-2	0	-8	-5	-12	-6	-10	-21	88(0.79)	85(0.89)	85(0.88)	83(1.46)
															2R Rea1	116	103	93	89	83	81	83	80	73	62	1(1.01)	-4(1.56)	-4(0.83)	-6(1.59)
2R Byd	6	3	-2	4	-2	-4	-16	-4	-7	-18	91(1.01)	86(1.56)	86(0.83)	84(1.59)
															2T Real	115	92	94	92	74	77	80	65	63	59	1(1.01)	-7(0.99)	2(3.01)	-8(1.56)
2T Byd	5	-8	-1	7	-11	-8	-19	-19	-17	-21	91(1.01)	83(0.99)	82(3.01)	82(1.56)
															4A Real	96	98	92	91	73	79	89	82	63	71	2(1.24)	2(1.3)	1(1.31)	0(1.32)
4A Byd	-12	4	3	1	-17	-11	-16	-8	-22	-14	87(1.24)	87(1.3)	86(1.31)	85(1.32)
															4R Real	117	98	91	91	76	58	93	87	80	77	2(0.89)	1(0.96)	0(0.94)	0(1.24)
4R Byd	9	4	2	1	-14	-32	-12	-3	-5	-8	87(0.89)	86(0.96)	85(0.94)	85(1.24)
															4T Real	116	89	88	94	84	79	83	89	77	74	5(1.49)	4(2.99)	3(1.5)	3(1.53)
4T Byd	8	-5	-1	4	-6	-11	-22	-1	-8	-11	90(1.49)	89(2.99)	88 (1.5)	88(1.53)

In table 1, Loc columns are test point codes and data directions corresponding to test data; 1X to 9X are different fault codes, Peak1 to Peak4 are 4 large Peak values excluding the Peak value corresponding to the fault code, and the number within (is) is the frequency (expressed by order) corresponding to Peak. As shown in table 1, the number of rows in the data screening table is determined according to the test data points and the direction, and in general, the vibration data of the machine test has data in at most three directions, namely, the axial direction a, the horizontal direction T and the vertical direction R, so that each test point occupies 3 groups, each group occupies 3 rows (the marked row is omitted in table 1, and each group occupies 2 rows), and the data structures of the groups are consistent. The first behavior is measured data, i.e., vibration data Real, the difference Byd between the measured data and the baseline data of the second behavior, and the third behavior is a marking line, and a specific mark is made when the measured value is greater than the baseline value. Taking the measurement point 2 as an example, the measurement point 2 includes three sets of data 2A, 2R and 2T, for the 2A set of data, 2area represents the vibration data, 2AByd represents the difference between the vibration data and the baseline data, and the marked line is omitted. Baseline data is an important indicator of "relative standard" evaluation, with each type of equipment corresponding to a set of artificial baselines. The artificial baseline is a reference value set for a fault code of a component by integrating a large amount of data according to different components.

In the step, the calculation of the difference value of the fault code frequency component information and the calculation of the difference value of the non-fault code frequency component information are both carried out in a unified logarithmic coordinate, and in the process of acquiring the vibration data, the unification of a data unit and a coordinate is firstly completed.

Step 600: the data screening table of the component is extracted by using the characteristic parameter extraction rule of the component, and a characteristic parameter extraction table (CFET) of the component is generated. The characteristic parameter extraction table is a two-dimensional matrix classified according to components, and all parameters used for subsequent fault diagnosis are directly from the characteristic parameter extraction table. The rows and columns of the feature parameter extraction table are not fixed. The rows are determined by the length of the data source code and the columns are determined by the parameters required for diagnosis. An example of the feature parameter extraction table is shown in table 2.

TABLE 2 characteristic parameter extraction

Each column number in table 2 corresponds to a diagnostic parameter, and the calculation of the corresponding value under the diagnostic parameter is determined by the feature parameter extraction rule. The line number and the column number of the characteristic parameter extraction table can respectively correspond to different names (line marks) so as to be convenient for quick reading in the process of editing the fault diagnosis rule subsequently. But only the row and column numbers are sufficient for diagnostic use of the data.

Before the diagnosis is started or after the diagnosis is finished, the user can update the characteristic parameter extraction rule, the user can add new characteristic parameters (columns) or modify the existing characteristic parameters, set new or modify the existing corresponding extraction parameters to generate a new characteristic parameter extraction rule, and the new characteristic parameter extraction rule is adopted to replace the characteristic parameter extraction rule in the fault model matrix, so that the diagnosis result is more accurate.

The method for generating the characteristic parameter extraction table comprises the following steps: the diagnostic feature parameters are extracted by setting extraction identification codes (fault codes), designating the types of the identification codes and components of fixed frequency and setting corresponding extraction parameters for each identification code. The columns of the characteristic parameter extraction table can be conveniently identified and read through a text naming mode. Each column of the characteristic parameter extraction table represents different extraction parameters, each extraction parameter corresponds to a different parameter extraction algorithm, and the rules corresponding to the algorithms, namely the characteristic parameter extraction rules, mainly comprise:

1. specifying an identification code: including specifying the type of identification code and the identification code. The type of identification code refers to whether the identification code is a fundamental frequency or a harmonic, a center frequency or a sideband, an order calculation or a frequency calculation. When the harmonic wave or the center frequency is designated, the identification code is extracted after being combined with the following rule as the fundamental frequency of the harmonic wave or the fundamental frequency of the center frequency; when the identification code is designated as a sideband, the identification code performs sum and difference operation with the fundamental frequency of the sideband which is centered on the identification code designated by the harmonic or the center frequency and the identification code component designated by the harmonic or the center frequency. The identification code refers to a fault code to be quoted when the characteristic value is extracted, and the frequency corresponding to the identification code/identification codes is the fundamental frequency. When the type of the identification code is the order, the identification code is a fault code; when the identification code type is frequency, the identification code is a specific frequency Hz.

2. Given multiplying power: the multiplying power range of the fundamental frequency harmonic represents a series of harmonic frequencies, and when the characteristic value is extracted, the frequency component which accords with the set multiplying power relation with the corresponding fundamental frequency is extracted.

3. Setting conditions: extracting qualified data, including:

(1) whether it is a special mark: only the values with special marks in the third row of each group in the data screening table are extracted.

(2) Whether accurate frequency multiplication is performed: whether the frequency component of the extracted data has a given multiplying factor with the fundamental frequency or not is judged.

4. Range or source of data: where to take eligible data, including:

corresponding data under fault codes: when data is extracted, only the data with the fault code identification is extracted.

Data under N large peaks outside the fault code: data is extracted from N large peaks, usually the largest two, other than the peak corresponding to the fault code in the DSS.

5. Whether there is a special calculation: extracting whether the data is subjected to some special calculation includes:

calculating the axial ratio separately: if axial data exists, calculating the ratio of the sum of the data of the axial values in three directions (or all directions).

And (3) eliminating scrambling: when extracting a feature value from a range of frequencies, this peak value will not be considered if there is a particular fault frequency (identified by a specific fault code) within this range. Considering that this is a machine/component specific component.

6. Priority at extraction: when data is extracted, the data is extracted according to defined priority. The smaller the priority value, the more priority is in extraction. Once a component has been extracted by a low priority parameter, the component is not extracted again by a higher priority parameter.

The above 1, 2, 3, 4, 5, and 6 are extraction parameters, and each extraction parameter represents a corresponding parameter extraction algorithm. Through the rules or algorithms, relevant data are extracted from the data screening table, necessary calculation is carried out on the data, and then the data are filled into the upper table, so that a characteristic parameter extraction table of the component is generated.

Step 700: and performing logical operation and arithmetic operation on the data of the characteristic parameter extraction table of the component by using the fault diagnosis rule of the component, and determining the fault mode and the fault level corresponding to the component. The failure mode of a component is the result of a logical operation and the failure level of a component is the result of an arithmetic operation. Stored in the fault diagnosis rule base is a fault model matrix, in which each fault mode corresponds to the diagnosis logic of the fault. As shown in fig. 4, fig. 4 is a logical structure diagram of one of the failure modes in the failure diagnosis rule. The corresponding failure mode of fig. 4 is motor imbalance.

The fault diagnosis rule is a group of logic formulas, corresponding values are directly matched from the characteristic parameter extraction table by analyzing parameters in the formulas, the result of each node is calculated, and a final diagnosis conclusion is obtained according to corresponding logic processing. The operators in the fault diagnosis rule include comparison operators, arithmetic logic operators, logical operators, and arithmetic operators. A plurality of diagnosis modes may be configured in the fault diagnosis rule as a combined diagnosis basis, and then the result of each diagnosis mode is calculated respectively, and finally the result of the combination is calculated to obtain a conclusion.

In the fault diagnosis rule, one fault mode may include N component subclasses, or conversely, one component subclass may also belong to a plurality of fault modes, that is, the relation between the fault mode and the component subclass is N to N. Through the subclass of the components of the equipment, N fault modes can be obtained, and finally, N diagnosis conclusions obtained according to each fault mode are the final diagnosis conclusion of the equipment. The differences in the component subclasses are distinguished according to the property code.

Each diagnostic logic performs two operations simultaneously, a logical operation and an arithmetic operation. The logic operation is used for judging whether the current logic is established or not, and if the current logic is established, the fault mode is correct and can be used as a diagnosis result; and calculating the corresponding severity of the fault mode by arithmetic operation for fault quantitative grading. When a logical operation is established, the result of the arithmetic operation is meaningful, otherwise the result of the arithmetic operation is meaningless. Threshold values for evaluating the severity of the fault are set under each fault mode or diagnosis logic, the arithmetic operation result of the logic is compared with the set threshold values, and when the evaluation threshold values of the severity of the corresponding level are met, the severity of the fault mode is determined.

The invention adopts some special arithmetic logic operators to complete the above functions in order to solve the problem of fault quantization grading, and the arithmetic logic operators are used for simultaneously carrying out logic operation and arithmetic operation. The arithmetic logic operators may be graphical, symbolic, or otherwise. The arithmetic logic operation functions of the present invention include:

and (SAND) operation, which performs AND operation on N logic values of the inputs, outputs true when all inputs are true, and sums the arithmetic values of all input branches at the same time.

And Or (SOR) operations, which perform an or operation on the N logical values of the inputs, the output being true when any one of the inputs is true, while summing the arithmetic values of the branches for which the input logical value is true.

And exclusive OR (SXOR) operations, which exclusive OR's the 2 logical values of the inputs, outputs true if and only if one input is true, while summing the arithmetic values of the branches whose input logical value is true.

And Not (SNOT) operation, which performs a not operation on N logical values of the inputs, outputs true when all inputs are false, and sums the arithmetic values of all input branches at the same time.

The comparison operation function includes:

the forward parameter comparison determines whether the parameter or parameter expression is greater than a set value (logical value) and the difference (arithmetic value) between the parameter or parameter expression and the set value.

The reverse parameter comparison determines whether the parameter or parameter expression is less than a set value (logical value) and the difference (arithmetic value) between the set value and the parameter or parameter expression.

The comparison operation function simultaneously completes two operations and outputs two results: the first is logic operation: judging whether the left side is larger than the right side, and outputting a logic value; secondly, arithmetic operation: and outputting an arithmetic value according to the difference between the parameter or the parameter expression result and the set value. The parameters of the comparison operation function are directly taken from the CFET, and the determined elements in the matrix are obtained by specifying the row number (or row mark) and the column number (column mark) of the CFET. The comparison operation function supports simple formula operation, and complex comparison operation can be completed through addition and subtraction operation of a plurality of matrix elements.

In addition, the traditional logical operation function and simple arithmetic operation function are adopted, including: logical AND (AND), logical OR (OR), logical NOT (NOT), logical exclusive OR (XOR), arithmetic SUM (SUM), AND arithmetic inverse (OPP), which function with logical operations can achieve almost all rule editing.

In the logical operation, the input is only a logical value, and the output is a logical value. When the input is a mixture of a logic value and an arithmetic value, only the logic value is taken as the input, and the output is still the logic value.

In arithmetic logic operations, the inputs are arithmetic and logical values and the outputs are arithmetic and logical values. When each input is a mixture of logical and arithmetic values, the output then outputs the logical and arithmetic values and values, respectively. When m of the N inputs are only arithmetic values, k are only logical values, and N-m-k are arithmetic logical values, the output is the sum of the m arithmetic values and the arithmetic values in the N-m-k arithmetic logics and the operation result of the k logical values and the logical values in the N-m-k arithmetic logical values. Special cases are as follows: (1) when all the inputs are only arithmetic values, the output is an arithmetic value SUM value, which is equivalent to SUM arithmetic operation; (2) when all inputs are only logical values, the output is a logical value result, which is equivalent to a logical operation.

In the arithmetic operation, the input is only an arithmetic value, and the output is an arithmetic value. When the input is a mixture of logic value and arithmetic value, only the arithmetic value is taken as input, and the output is still the arithmetic value.

Through the logic combination, corresponding logic rules are set for the fault mode, the computer analyzes the rules to complete operation, the result of the logic operation is the fault mode, and the result of the arithmetic operation is the severity level.

Step 800: and acquiring the corresponding fault mode and fault grade of each component to obtain the fault detection result of the equipment to be detected.

After the fault detection result of the equipment to be detected is obtained, the action suggestion of the equipment to be detected can be obtained by further adopting the logic operation of the action suggestion rule for the fault modes and the fault grades corresponding to all the parts. As shown in fig. 5, fig. 5 is a logical structure diagram of an action suggestion rule. The action suggestion rule is a set of logic formulas, and the result of each node is calculated through the input failure mode and the severity level to obtain the final action suggestion. The resulting action recommendation in fig. 5 is: checking the coupler centering. The action suggestion rule is open, a user can construct a new action suggestion according to requirements, the user can generate the new action suggestion rule by inputting the structured code of the new action suggestion, applying a fault diagnosis conclusion and the severity level thereof and editing logic operation, and further update the original action suggestion rule base in the fault model matrix.

As a specific embodiment, the present invention may also provide a function of user-defined rules autonomously. The user selects an imaging operator by dragging, and then a new fault diagnosis rule can be generated according to the imaging operator selected by the user by dragging, and then the original fault diagnosis rule in the fault model matrix is updated by adopting the new fault diagnosis rule.

The present invention also provides a system for diagnosing a device fault, as shown in fig. 6, where fig. 6 is a schematic structural diagram of the system for diagnosing a device fault according to the present invention, and the system for diagnosing a device fault according to the present invention includes:

a diagnostic model obtaining module 601, configured to obtain a diagnostic model of the device; the diagnostic model comprises component parameters corresponding to each component, and the component parameters comprise component codes, characteristic codes, data source codes and fault code information; the part code characterizes a type of part; the property code characterizes a local property of the component; the data source code represents the index position of data required by diagnosis of the component; the fault code information is frequency component information corresponding to each fault code, and each component comprises a plurality of fault codes.

A component parameter obtaining module 602, configured to obtain component parameters of each component in the device to be tested according to the diagnostic model.

A fault model matrix obtaining module 603, configured to obtain a fault model matrix corresponding to the device to be detected according to the component parameter of each component in the device to be detected; the fault model matrix comprises a characteristic parameter extraction rule and a fault diagnosis rule; the characteristic parameter extraction rule is a parameter calculation and data screening rule required for diagnosing component faults and corresponds to the component code; the fault diagnosis rule includes a logic operation rule and an arithmetic operation rule, is a rule for generating a fault mode and a fault level through logic and arithmetic operations by using characteristic parameters, and corresponds to a code obtained by combining the component code and the characteristic code.

A vibration data obtaining module 604, configured to obtain vibration data of the device to be tested; the vibration data of the device to be tested comprises vibration data of each component at a plurality of detection point positions.

And the data screening module 605 is configured to, for the ith component, screen the vibration data of the component according to the fault code information of the component to obtain a data screening table corresponding to the component.

A parameter extraction module 606, configured to extract the data screening table of the component according to the feature parameter extraction rule of the component, and generate a feature parameter extraction table of the component.

A fault diagnosis module 607, configured to perform logical operation and arithmetic operation on the data in the feature parameter extraction table of the component by using the fault diagnosis rule of the component, and determine a fault mode and a fault level corresponding to the component; the failure mode of the component is a result of the logical operation, and the failure level of the component is a result of the arithmetic operation.

A fault detection result obtaining module 608, configured to obtain a fault mode and a fault level corresponding to each component, so as to obtain a fault detection result of the device to be detected.

As another embodiment, the system for diagnosing a device failure of the present invention further includes:

and the characteristic parameter extraction rule determining module is used for determining the characteristic parameter extraction rule according to the component code of the component before acquiring the fault model matrix corresponding to the equipment to be detected according to the component parameter of each component in the equipment to be detected.

And the fault diagnosis rule determining module is used for determining the fault diagnosis rule according to the component code and the characteristic code of the component. .

As another embodiment, the data screening module 604 of the system for diagnosing a device fault of the present invention specifically includes:

a fault code peak data extraction unit, configured to extract peak data of each fault code frequency component information from each piece of vibration data according to frequency component information corresponding to each fault code of the ith component, so as to obtain multiple fault code peak data corresponding to each piece of vibration data; and the fault code frequency component information is frequency component information corresponding to the fault code.

The non-fault code peak data extraction unit is used for extracting peak data of a plurality of pieces of non-fault code frequency component information from each piece of vibration data to obtain a plurality of pieces of non-fault code peak data corresponding to each piece of vibration data; the non-fault code frequency component information is a plurality of frequency component information except the frequency component information corresponding to the fault code.

And a baseline data acquisition unit for acquiring baseline data of each fault code frequency component information and baseline data of each non-fault code frequency component information.

A difference value calculating unit for calculating a difference value of each fault code frequency component information and a difference value of each non-fault code frequency component information in each piece of vibration data; the difference value of the fault code frequency component information is the difference value of peak data and baseline data of the fault code frequency component information, and the difference value of the non-fault code frequency component information is the difference value of peak data and baseline data of the non-fault code frequency component information.

The marking value acquisition unit is used for acquiring a marking value corresponding to each piece of vibration data; when the difference value of the fault code frequency component information is larger than zero, the mark value corresponding to the fault code frequency component information is not null, and when the difference value of the fault code frequency component information is not larger than zero, the mark value corresponding to the fault code frequency component information is null; when the difference value of the non-fault code frequency component information is larger than zero, the corresponding mark value of the non-fault code frequency component information is not null, and when the difference value of the non-fault code frequency component information is not larger than zero, the corresponding mark value of the non-fault code frequency component information is null.

As another embodiment, the fault model matrix in the system for diagnosing a fault in an apparatus according to the present invention further includes an action suggestion rule, which is a rule for generating an action suggestion and a priority through a logical operation and an arithmetic operation using a fault pattern and a fault level, and corresponds to a component code.

The system for diagnosing the equipment fault further comprises:

and the user dragging selection information acquisition module is used for acquiring the corresponding fault mode and fault grade of each part and acquiring the fault detection result of the equipment to be detected and then acquiring the imaging operator selected by the user dragging.

And the new fault diagnosis rule acquisition module is used for generating a new fault diagnosis rule according to the imaging operator dragged and selected by the user.

And the fault diagnosis rule updating module is used for updating the fault diagnosis rule in the fault model matrix by adopting the new fault diagnosis rule.

The system of the invention adopts a diagnosis modeling tool DMA to construct a diagnosis model. The DMA is a graphical equipment model modeling tool, and the diagnostic model modeling is completed by the components of the component classification storage rule in a configuration mode of component graphic elements. Each part graphic element corresponds to a corresponding attribute, the setting of a part Code (Component Code), a characteristic Code (Speciality Code), a Fault Code (Fault Code) and a data source Code (DS Code) is completed by editing and setting the attributes of the selected part, model information is formed and stored in a related database, and corresponding model information in the database is read by input parameters during automatic diagnosis to match with a diagnosis rule.

The embodiments in the present description are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other. For the system disclosed by the embodiment, the description is relatively simple because the system corresponds to the method disclosed by the embodiment, and the relevant points can be referred to the method part for description.

The principles and embodiments of the present invention have been described herein using specific examples, which are provided only to help understand the method and the core concept of the present invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed. In view of the above, the present disclosure should not be construed as limiting the invention.

Claims

1. A method of diagnosing equipment failure, comprising:

acquiring a fault model matrix corresponding to the equipment to be detected according to the component parameters of each component in the equipment to be detected; the fault model matrix comprises a characteristic parameter extraction rule and a fault diagnosis rule; the characteristic parameter extraction rule is a parameter calculation and data screening rule required for diagnosing component faults and corresponds to the component code; the fault diagnosis rule comprises a logic operation rule and an arithmetic operation rule, is a rule for generating a fault mode and a fault grade by utilizing characteristic parameters through logic and arithmetic operations, and corresponds to a code formed by combining the component code and the characteristic code; the fault model matrix further comprises action suggestion rules, wherein the action suggestion rules are rules for generating action suggestions and priorities through logical operation and arithmetic operation by utilizing fault modes and fault levels and correspond to component codes;

acquiring vibration data of equipment to be detected; the vibration data of the equipment to be detected comprises vibration data of each part at a plurality of detection point positions;

for the ith component, screening the vibration data of the component according to the fault code information of the component to obtain a data screening table corresponding to the component; the specific process is as follows: extracting peak data of each fault code frequency component information from each vibration data according to the frequency component information corresponding to each fault code of the ith component to obtain a plurality of fault code peak data corresponding to each vibration data; the fault code frequency component information is frequency component information corresponding to the fault code; extracting peak data of a plurality of non-fault code frequency component information from each piece of vibration data to obtain a plurality of non-fault code peak data corresponding to each piece of vibration data; the non-fault code frequency component information is a plurality of frequency component information except the frequency component information corresponding to the fault code; acquiring baseline data of each fault code frequency component information and baseline data of each non-fault code frequency component information; calculating the difference value of each fault code frequency component information and the difference value of each non-fault code frequency component information in each vibration data; the difference value of the fault code frequency component information is the difference value of peak data and baseline data of the fault code frequency component information, and the difference value of the non-fault code frequency component information is the difference value of peak data and baseline data of the non-fault code frequency component information; obtaining a mark value corresponding to each vibration data; when the difference value of the fault code frequency component information is larger than zero, the mark value corresponding to the fault code frequency component information is not null, and when the difference value of the fault code frequency component information is not larger than zero, the mark value corresponding to the fault code frequency component information is null; when the difference value of the non-fault code frequency component information is larger than zero, the corresponding mark value of the non-fault code frequency component information is not null, and when the difference value of the non-fault code frequency component information is not larger than zero, the corresponding mark value of the non-fault code frequency component information is null; generating a data screening table corresponding to the ith component according to fault code peak data, non-fault code peak data, a difference value of fault code frequency component information, a difference value of non-fault code frequency component information and a marking value corresponding to each vibration data of the ith component;

2. The method for diagnosing equipment failure according to claim 1, wherein the obtaining a failure model matrix corresponding to the equipment to be detected according to component parameters of each component in the equipment to be detected further comprises:

3. The method for diagnosing equipment failure according to claim 1, wherein the obtaining of the failure mode and the failure grade corresponding to each component obtains a failure detection result of the equipment to be detected, and then further comprises:

4. The method for diagnosing equipment failure according to claim 3, wherein the logic operation of the action suggestion rule is adopted for the failure mode and the failure grade corresponding to all the components to obtain the action suggestion of the equipment to be detected, and then the method further comprises:

acquiring a structured code of a new action suggestion rule input by a user;

5. The method according to claim 1, wherein the determining a failure mode and a failure level corresponding to the component by performing logical operation and arithmetic operation on data in the feature parameter extraction table of the component using the failure diagnosis rule of the component specifically includes:

6. The method for diagnosing equipment failure according to claim 1, wherein the obtaining of the failure mode and the failure grade corresponding to each component obtains a failure detection result of the equipment to be detected, and then further comprises:

7. The method for diagnosing equipment failure according to claim 1, wherein the obtaining of the failure mode and the failure grade corresponding to each component obtains a failure detection result of the equipment to be detected, and then further comprises:

8. A system for diagnosing equipment failure, comprising:

the fault model matrix acquisition module is used for acquiring a fault model matrix corresponding to the equipment to be detected according to the component parameters of each component in the equipment to be detected; the fault model matrix comprises a characteristic parameter extraction rule and a fault diagnosis rule; the characteristic parameter extraction rule is a parameter calculation and data screening rule required for diagnosing component faults and corresponds to the component code; the fault diagnosis rule comprises a logic operation rule and an arithmetic operation rule, is a rule for generating a fault mode and a fault grade by utilizing characteristic parameters through logic and arithmetic operations, and corresponds to a code formed by combining the component code and the characteristic code; the fault model matrix further comprises action suggestion rules, wherein the action suggestion rules are rules for generating action suggestions and priorities through logical operation and arithmetic operation by utilizing fault modes and fault levels and correspond to component codes;

the data screening module is used for screening the vibration data of the ith component according to the fault code information of the component to obtain a data screening table corresponding to the component; the data screening module specifically comprises: a fault code peak data extraction unit, configured to extract peak data of each fault code frequency component information from each piece of vibration data according to frequency component information corresponding to each fault code of the ith component, so as to obtain multiple fault code peak data corresponding to each piece of vibration data; the fault code frequency component information is frequency component information corresponding to the fault code; the non-fault code peak data extraction unit is used for extracting peak data of a plurality of pieces of non-fault code frequency component information from each piece of vibration data to obtain a plurality of pieces of non-fault code peak data corresponding to each piece of vibration data; the non-fault code frequency component information is a plurality of frequency component information except the frequency component information corresponding to the fault code; a baseline data acquisition unit for acquiring baseline data of each fault code frequency component information and baseline data of each non-fault code frequency component information; a difference value calculating unit for calculating a difference value of each fault code frequency component information and a difference value of each non-fault code frequency component information in each piece of vibration data; the difference value of the fault code frequency component information is the difference value of peak data and baseline data of the fault code frequency component information, and the difference value of the non-fault code frequency component information is the difference value of peak data and baseline data of the non-fault code frequency component information; the marking value acquisition unit is used for acquiring a marking value corresponding to each piece of vibration data; when the difference value of the fault code frequency component information is larger than zero, the mark value corresponding to the fault code frequency component information is not null, and when the difference value of the fault code frequency component information is not larger than zero, the mark value corresponding to the fault code frequency component information is null; when the difference value of the non-fault code frequency component information is larger than zero, the corresponding mark value of the non-fault code frequency component information is not null, and when the difference value of the non-fault code frequency component information is not larger than zero, the corresponding mark value of the non-fault code frequency component information is null; a data screening table generating unit, configured to generate a data screening table corresponding to the ith component according to fault code peak data, non-fault code peak data, a difference value of fault code frequency component information, a difference value of non-fault code frequency component information, and a flag value corresponding to each vibration data of the ith component;

9. The system for diagnosing equipment failure of claim 8, further comprising:

10. The system for diagnosing device failure according to claim 8,

the system for diagnosing the equipment fault further comprises:

11. The system for diagnosing equipment failure of claim 8, further comprising: