CN108520093A - A method and device for fault diagnosis of mechanical equipment based on knowledge base - Google Patents

Abstract

The invention discloses a method and device for fault diagnosis of mechanical equipment based on a knowledge base. The method includes: receiving equipment to be monitored for vibration signal measurement; calculating the characteristic frequency spectrum of the equipment based on the characteristic frequency knowledge base; , performing knowledge reasoning on the characteristic frequency spectrum to obtain the operating state of the device; wherein, the characteristic frequency knowledge base stores the calculation method of the characteristic frequency; the state knowledge base stores the relationship between different operating states of the device and the characteristic frequency . The invention establishes a diagnosis knowledge base, has more diagnosis basis, and has the characteristics of accurate diagnosis result.

Description

A method and device for fault diagnosis of mechanical equipment based on knowledge base

technical field

The invention relates to the technical field of fault diagnosis of rotating mechanical equipment, in particular to a method and device for fault diagnosis of mechanical equipment based on a knowledge base.

Background technique

Fault diagnosis technology refers to judging whether the system is working normally through various monitoring methods under the operating state or working state of the system. Usually, fault diagnosis technology uses various state detection, measurement, analysis and discrimination methods, combined with the historical conditions of the monitored equipment and operating environment factors, to evaluate the equipment operating status, determine whether the equipment is in a normal or abnormal state, and display the status and record. If the equipment is in an abnormal state, an alarm needs to be issued so that the operator can deal with it in time, and provide information and basic data for fault analysis, performance evaluation, rational use and safety work.

With the development of modern technology, people put forward higher requirements for the reliability of rotating mechanical equipment such as generators and blowers under long-term and high-load conditions. It is an effective way to realize the safe operation of mechanical equipment by means of fault diagnosis technology. Knowing the operating status of the system in a timely manner, quickly diagnosing and identifying faults can not only significantly improve maintenance efficiency and reduce maintenance costs, but also prolong the service life of the system. Therefore, the research on fault diagnosis technology has important practical significance.

Due to the urgent need of modern mass production, fault diagnosis technology has developed rapidly, and the content of fault diagnosis technology has become increasingly rich. However, related technologies have more research on a specific component, less research on general-purpose equipment and systems, and more vibration signal collection and analysis functions, and less fault diagnosis functions.

In the fault diagnosis method, based on the vibration signal processing and analysis is the most effective common method proved in practice. In the existing frequency domain characteristic analysis of vibration signals, the main reference is the frequency multiplication of the mechanical equipment speed, such as 1 frequency multiplication, 2 multiplication frequency, 3 multiplication frequency, etc. Although fault diagnosis based on characteristic frequency is a relatively common technical means at present, there is no more comprehensive method to generate characteristic frequency according to the specific composition parameters of the diagnosed mechanical equipment.

Therefore, how to perform accurate fault diagnosis based on the specific parameters of the equipment is an urgent technical problem to be solved by those skilled in the art.

Contents of the invention

In order to overcome the above-mentioned deficiencies in the prior art, the present invention provides a fault diagnosis method, which establishes a related model through equipment parameters, calculates a set of characteristic frequencies, and then generates equipment The status knowledge base is used to analyze the vibration signal to be diagnosed to obtain the equipment status. If the device status is abnormal, give the fault severity and treatment plan.

To achieve the above object, the present invention adopts the following technical solutions:

A method for fault diagnosis of mechanical equipment based on knowledge base, comprising the following steps:

Receive the equipment to be monitored for vibration signal measurement;

Calculate the characteristic frequency spectrum of the device based on the characteristic frequency knowledge base;

Based on the state knowledge base, performing knowledge reasoning on the characteristic spectrum to obtain the operating state of the device;

Wherein, the characteristic frequency knowledge base stores the calculation method of characteristic frequency;

The state knowledge base stores the relationship between different operating states and characteristic frequencies of the device.

Further, the calculation of the characteristic frequency is based on the structural parameters of the device.

Further, the structural parameters include motor parameters, bearing parameters and specific mechanical parameters.

Further, the operation status includes normal and failure; when the operation status is failure, it also includes the failure level.

Further, the method for establishing the state knowledge base is:

Mark the operating status of the historical vibration data on the surface of each device, and generate the relationship between the characteristic spectral lines and the different operating states of each device;

Calculate the amplitude range of the characteristic frequency corresponding to the different operating states of each device to form a state knowledge base.

Further, the status flag includes:

First mark the normal operation or failure type;

According to the historical measurement records, the maximum and minimum values of each characteristic frequency corresponding to each device are obtained, so as to determine the normal value range of each characteristic frequency;

According to the normal range of values, the fault level of each device is further marked.

According to the second object of the present invention, the present invention also provides a mechanical equipment fault diagnosis system based on a knowledge base, including a memory and a processor, the memory stores a device library, a characteristic frequency knowledge base, a state knowledge base, and can be used in A computer program running on a processor, the processor implements the following steps when executing the program, including:

Receive the device name of the device to be monitored, and retrieve the corresponding structural parameters from the device library;

Receive the vibration signal measurement results of the equipment to be monitored;

Calculate the characteristic frequency spectrum of the device based on the characteristic frequency knowledge base;

Based on the state knowledge base, performing knowledge reasoning on the characteristic spectrum to obtain the operating state of the device;

Wherein, the characteristic frequency knowledge base stores the calculation method of characteristic frequency;

The state knowledge base stores the relationship between different operating states and characteristic frequencies of the device.

Beneficial effects of the present invention

1. The present invention focuses on bearing faults and motor faults that are common in general-purpose mechanical equipment, and performs fault diagnosis modeling and algorithm design to realize the identification and fault level analysis of various types of mechanical faults. According to the specific composition parameters of the mechanical equipment, such as the inner diameter and outer diameter of the bearing, 20-30 different characteristic frequencies can be determined, which greatly increases the information content of the diagnosis, so it has the characteristics of accurate diagnosis results.

2. The present invention adopts an automatic diagnosis technology based on a knowledge base, and the knowledge base includes a characteristic frequency knowledge base and an equipment state knowledge base. The characteristic frequency knowledge base records the equipment model and characteristic frequency set, and the equipment status knowledge base records the equipment status, the equipment characteristic spectrum range and so on. For different mechanical equipment, the characteristic frequency can be determined according to its specific composition parameters instead of simply according to the equipment speed, so it also has the characteristics of strong adaptability, strong reliability and maintainability.

Description of drawings

The accompanying drawings constituting a part of the present application are used to provide further understanding of the present application, and the schematic embodiments and descriptions of the present application are used to explain the present application, and do not constitute improper limitations to the present application.

Fig. 1 is a flow chart of equipment fault modeling and fault diagnosis in the present invention.

Detailed ways

It should be pointed out that the following detailed description is exemplary and is intended to provide further explanation to the present application. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.

It should be noted that the terminology used here is only for describing specific implementations, and is not intended to limit the exemplary implementations according to the present application. As used herein, unless the context clearly dictates otherwise, the singular is intended to include the plural, and it should also be understood that when the terms "comprising" and/or "comprising" are used in this specification, they mean There are features, steps, operations, means, components and/or combinations thereof.

In the case of no conflict, the embodiments in the present application and the features in the embodiments can be combined with each other.

Embodiment one

This embodiment discloses a knowledge base-based fault diagnosis modeling method for mechanical equipment, including the following steps:

Step 1: Receive the structural parameters of the rotating device.

The structural parameters include: motor parameters, bearing parameters and specific mechanical parameters. specifically,

1) Motor parameters include: motor main frequency, motor speed, motor stator teeth, motor rotor teeth, and motor pole pairs.

2) Bearing parameters include: bearing inner ring diameter, bearing outer ring diameter, bearing ball diameter, bearing inner circle radius, number of bearing balls, number of bearing rows, number of bearing helixes.

3) Equipment parameters include: equipment speed, number of equipment bearings, number of equipment blades, equipment rotor stages, equipment primary rotor teeth number, equipment secondary rotor teeth number, equipment gear ratio.

Step 2: set up the characteristic frequency knowledge base, include the characteristic frequency calculation formula needed during fault diagnosis in the characteristic frequency knowledge base, and the corresponding characteristic frequency set of each rotating type equipment obtained according to these formulas, generate the characteristic frequency spectrum.

Calculation formula of characteristic frequency T1～T26:

T1=motor speed/60.0;

T2=2.0*T1;

T3＝(T1*bearing inner circle radius*number of bearing rows)/(2.0*(Z1+(bearing ball diameter/2.0)));

T4＝T3*Number of bearing balls*Number of bearing rows;

T5＝T4*Z4*Number of bearing rows;

T6＝(T1*bearing inner circle radius*bearing row number)/bearing ball diameter;

T7＝T6*Number of bearing balls*Number of bearing rows;

T8=(T6–T1)*Number of bearing rows;

T9＝T8*Number of bearing balls*Number of bearing rows;

T10＝(T1–T3)*Number of bearing rows;

T11=T10*Number of bearing balls*Number of bearing rows;

T12=T1*motor stator teeth number;

T13=T1*motor rotor teeth number;

T14＝T1*(motor rotor teeth + motor stator teeth)

T15＝T1*number of equipment rotor blades

T16＝T1*equipment rotor stages

T17＝2.0*Motor main frequency

T18＝4.0*Motor main frequency

T19＝2.0*motor main frequency*Z3

T20＝Engine main frequency*(1–Z3)

T21＝Engine main frequency*(1-2.0*Z3)

T22＝2.0*motor main frequency*(1-2.0*Z3)

T23=2300

T24=3150

T25＝4500

T26 = motor main frequency;

The intermediate parameters involved include:

Z1=(bearing inner ring diameter + bearing outer ring diameter)/4.0-(bearing ball diameter/2.0);

Z2＝(motor main frequency*60.0)/(motor pole pairs);

Z3＝(Z2-motor speed)/Z2

Z4=(Z1+2*bearing ball diameter)/(bearing ball diameter 2.0);

Z5 = bearing ball diameter

Step 3: Establish a state knowledge base, which includes the relationship between the different operating states of each device and the characteristic spectrum. The operation state is normal operation, or fault type and fault level.

The method for establishing the state knowledge base is:

Experts mark the historical vibration data on the surface of each equipment for the operation status, and mark the normal operation or fault type;

According to the historical measurement records, the maximum and minimum values of each characteristic frequency corresponding to each device are obtained, so as to determine the normal value range of each characteristic frequency;

According to the normal range of values, further mark the fault level of each device;

According to the above marks, the relationship between the characteristic spectral lines (the amplitude of the vibration signal at different characteristic frequencies) and the different operating states of each device is generated;

Calculate the amplitude range of the characteristic frequency corresponding to the different operating states of each device to form a state knowledge base.

Step 4: measure the vibration signal of the equipment to be monitored, calculate the characteristic frequency spectrum according to the characteristic frequency set generated in step 2, then carry out knowledge inference to the characteristic frequency spectrum according to the state knowledge base in step 3, and obtain the corresponding operating state.

The present invention focuses on bearing faults and motor faults commonly existing in general mechanical equipment, carries out fault diagnosis modeling and algorithm design, and realizes identification and fault level analysis of various types of mechanical faults.

Preferably, the characteristic frequency knowledge base records equipment models and characteristic frequency sets, and the equipment status knowledge base records equipment models, equipment operating years, equipment status, and equipment characteristic spectrum ranges. The knowledge base can be dynamically updated and supplemented according to factors such as equipment model and age.

Embodiment two

The purpose of this embodiment is to provide a computing device.

A mechanical equipment fault diagnosis device based on a knowledge base, including a memory and a processor, the memory stores a device library, a characteristic frequency knowledge base, a state knowledge base, and a computer program that can run on a processor, and the processor executes The following steps are implemented during the procedure, including:

Receive the device name of the device to be monitored, and retrieve the corresponding structural parameters from the device library;

Receive the vibration signal measurement results of the equipment to be monitored;

Calculate the characteristic frequency spectrum of the device based on the characteristic frequency knowledge base;

Based on the state knowledge base, performing knowledge reasoning on the characteristic spectrum to obtain the operating state of the device;

Wherein, the characteristic frequency knowledge base stores the calculation method of characteristic frequency;

The state knowledge base stores the relationship between different operating states and characteristic frequencies of the device.

Embodiment three

The purpose of this embodiment is to provide a computer storage medium.

A computer storage medium, including a device library, a characteristic frequency knowledge base, a state knowledge base, and a computer program that can run on a processor, and the processor implements the following steps when executing the program, including:

Receive the device name of the device to be monitored, and retrieve the corresponding structural parameters from the device library;

Receive the vibration signal measurement results of the equipment to be monitored;

Calculate the characteristic frequency spectrum of the device based on the characteristic frequency knowledge base;

Based on the state knowledge base, performing knowledge reasoning on the characteristic spectrum to obtain the operating state of the device;

Wherein, the characteristic frequency knowledge base stores the calculation method of characteristic frequency;

The state knowledge base stores the relationship between different operating states and characteristic frequencies of the device.

Beneficial effects of the present invention:

1. The present invention focuses on bearing faults and motor faults that are common in general-purpose mechanical equipment, and performs fault diagnosis modeling and algorithm design to realize the identification and fault level analysis of various types of mechanical faults. According to the specific composition parameters of the mechanical equipment, such as the inner diameter and outer diameter of the bearing, 20-30 different characteristic frequencies can be determined, which greatly increases the information content of the diagnosis, so it has the characteristics of accurate diagnosis results.

2. The present invention adopts an automatic diagnosis technology based on a knowledge base, and the knowledge base includes a characteristic frequency knowledge base and an equipment status knowledge base. The characteristic frequency knowledge base records the equipment model and characteristic frequency set, and the equipment status knowledge base records the equipment status, the equipment characteristic spectrum range and so on. For different mechanical equipment, the characteristic frequency can be determined according to its specific composition parameters instead of simply according to the equipment speed, so it also has the characteristics of strong adaptability, strong reliability and maintainability.

Those skilled in the art should understand that each module or each step of the present invention described above can be realized by a general-purpose computer device, optionally, they can be realized by a program code executable by the computing device, thereby, they can be stored in a memory The device is executed by a computing device, or they are made into individual integrated circuit modules, or multiple modules or steps among them are made into a single integrated circuit module for realization. The invention is not limited to any specific combination of hardware and software.

Although the specific implementation of the present invention has been described above in conjunction with the accompanying drawings, it is not a limitation to the protection scope of the present invention. Those skilled in the art should understand that on the basis of the technical solution of the present invention, those skilled in the art do not need to pay creative work Various modifications or variations that can be made are still within the protection scope of the present invention.

Claims (9)

1. a kind of Trouble Diagnostic Method of Machinery Equipment in knowledge based library, which is characterized in that include the following steps：

It receives equipment to be monitored and carries out vibration measurement；

Feature based frequency knowledge base, calculates the characteristic frequency spectrum of the equipment；

Based on State Knowledge library, knowledge reasoning is carried out to the characteristic frequency spectrum, obtains the operating status of the equipment；

Wherein, the computational methods of the characteristic frequency knowledge library storage characteristic frequency；

Relationship between the State Knowledge storage apparatus difference operating status and characteristic frequency.

2. a kind of Trouble Diagnostic Method of Machinery Equipment in knowledge based library as described in claim 1, which is characterized in that the spy The calculating for levying frequency is structural parameters based on equipment.

3. a kind of Trouble Diagnostic Method of Machinery Equipment in knowledge based library as described in claim 1, which is characterized in that described to set Standby structural parameters acquisition methods are：The device name for receiving equipment to be monitored transfers corresponding construction parameter from equipment library.

4. a kind of Trouble Diagnostic Method of Machinery Equipment in knowledge based library as claimed in claim 2, which is characterized in that the knot Structure parameter includes the parameter of electric machine, bearing parameter and specific mechanical parameter.

5. a kind of Trouble Diagnostic Method of Machinery Equipment in knowledge based library as described in claim 1, which is characterized in that the fortune Row state includes normal and failure；Further include fault level when operating status is failure.

6. a kind of Trouble Diagnostic Method of Machinery Equipment in knowledge based library as described in claim 1, which is characterized in that the shape State Knowledge Base is：

Operating status label is carried out to each equipment surface historical vibration data, generates characteristic spectral line and each equipment difference operating status Between relationship；

Amplitude range at the corresponding characteristic frequency of each equipment difference operating status is calculated, State Knowledge library is formed.

7. a kind of Trouble Diagnostic Method of Machinery Equipment in knowledge based library as claimed in claim 5, which is characterized in that the shape State marks：

Normal operation or fault type are marked first；

Record is measured according to history and obtains the maximum value and minimum value of the corresponding each characteristic frequency of each equipment, so that it is determined that each feature The normal value range of frequency；

According to the normal value range, the fault level of each equipment is further marked.

8. a kind of mechanical fault diagnosis device in knowledge based library, including memory and processor, which is characterized in that described The computer program that memory storage can be run on a processor, the processor realize such as claim when executing described program The Trouble Diagnostic Method of Machinery Equipment in 1-7 any one of them knowledge baseds library.

9. a kind of computer storage media, is stored thereon with computer program, such as right is executed when which is executed by processor It is required that the Trouble Diagnostic Method of Machinery Equipment in 1-7 any one of them knowledge baseds library.