CN117110741A - Equipment fault diagnosis method, device, equipment and storage medium - Google Patents
Equipment fault diagnosis method, device, equipment and storage medium Download PDFInfo
- Publication number
- CN117110741A CN117110741A CN202310995660.7A CN202310995660A CN117110741A CN 117110741 A CN117110741 A CN 117110741A CN 202310995660 A CN202310995660 A CN 202310995660A CN 117110741 A CN117110741 A CN 117110741A
- Authority
- CN
- China
- Prior art keywords
- parameters
- equipment
- health
- related variable
- fault diagnosis
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 95
- 238000000034 method Methods 0.000 title claims abstract description 51
- 230000036541 health Effects 0.000 claims abstract description 141
- 239000012530 fluid Substances 0.000 claims abstract description 110
- 238000012423 maintenance Methods 0.000 claims abstract description 49
- 238000011156 evaluation Methods 0.000 claims abstract description 37
- 238000012384 transportation and delivery Methods 0.000 claims description 24
- 238000004458 analytical method Methods 0.000 claims description 18
- 238000012545 processing Methods 0.000 claims description 16
- 238000005070 sampling Methods 0.000 claims description 16
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 16
- 238000001914 filtration Methods 0.000 claims description 6
- 230000001052 transient effect Effects 0.000 claims description 6
- 208000037408 Device failure Diseases 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 229910000831 Steel Inorganic materials 0.000 claims description 4
- 239000010959 steel Substances 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 238000007726 management method Methods 0.000 description 10
- 238000007689 inspection Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000012549 training Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 230000007774 longterm Effects 0.000 description 4
- 230000008901 benefit Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 3
- 230000018109 developmental process Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000013439 planning Methods 0.000 description 3
- 230000008439 repair process Effects 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000002411 adverse Effects 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000004134 energy conservation Methods 0.000 description 2
- 230000007257 malfunction Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000013499 data model Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000004886 process control Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M99/00—Subject matter not provided for in other groups of this subclass
- G01M99/005—Testing of complete machines, e.g. washing-machines or mobile phones
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application belongs to the technical field of equipment diagnosis and discloses an equipment fault diagnosis method, an equipment fault diagnosis device, equipment and a storage medium; the application comprises the following steps: collecting related variable parameters of the fluid conveyor electrical equipment in real time, wherein the related variable parameters comprise physical parameters and operation related parameters; when the related variable parameter is not smaller than the parameter threshold, carrying out health evaluation on the fluid conveyor electrical equipment according to the related variable parameter to obtain a health value; when the health value of the fluid conveyor mechanical equipment is smaller than or equal to a health threshold value, performing fault diagnosis on the fluid conveyor mechanical equipment according to related variable parameters; according to the application, the real-time health assessment is carried out on the equipment by collecting the relevant variable parameters of the equipment in real time, the fault diagnosis is carried out on the equipment according to the assessment result, the sudden fault can be found in time, the tracking prediction is carried out on the state of the equipment, the traditional passive operation and maintenance mode based on events or time is changed, and the overall management level of the fluid conveying electromechanical equipment is effectively improved.
Description
Technical Field
The present application relates to the field of device diagnosis technologies, and in particular, to a device fault diagnosis method, apparatus, device, and storage medium.
Background
With the development of informatization, device health management has become the development direction of intelligent operation and maintenance of electromechanical devices nowadays. By integrating the equipment management regulation system and the business flow, the whole process control is carried out on the factors related to the equipment health by tightly combining the information such as equipment state monitoring, maintenance, use, environment and the like, and the operation and maintenance work is planned and optimized, so that the intelligent operation and maintenance is realized. The equipment keeps a better working state in actual working, reduces maintenance cost and improves working efficiency.
Fluid delivery type electromechanical devices are one of the most common electromechanical devices, and mainly comprise various types of water pump and fan type electromechanical devices. At present, aiming at the daily operation and maintenance of the fluid conveying electromechanical equipment, a maintenance plan is mainly made by experience or the maintenance is carried out after the fault occurs, so that the real-time performance and the scientificity are poor.
Disclosure of Invention
The application mainly aims to provide a device fault diagnosis method, device, equipment and storage medium, and aims to solve the technical problem that the prior art cannot prevent and diagnose possible faults of equipment.
To achieve the above object, the present application provides an apparatus failure diagnosis method comprising the steps of:
collecting related variable parameters of the fluid conveyor electrical equipment in real time, wherein the related variable parameters comprise physical parameters and operation related parameters;
when the related variable parameter is not smaller than a parameter threshold, carrying out health evaluation on the fluid conveyor electromechanical equipment according to the related variable parameter to obtain a health value of the fluid conveyor electromechanical equipment;
judging whether the health value of the fluid conveyor electrical equipment is smaller than or equal to a health threshold value;
and when the health value of the fluid conveyor electric equipment is smaller than or equal to a health threshold value, performing fault diagnosis on the fluid conveyor electric equipment according to the related variable parameters.
Optionally, the real-time collection of related variable parameters of the fluid transporter electro-mechanical device, including physical parameters and operation related parameters, further includes:
collecting original variable parameters of the fluid conveyor electrical equipment;
sampling the original variable parameters to obtain sampling data, filtering the sampling data to obtain filtered data, and removing error data in the filtered data to obtain reference variable parameters;
determining an initial related variable parameter of the reference variable parameters according to steady state data and fault transient state data of the fluid conveyor electrical equipment;
and removing the parameter with repeated characteristics in the initial related variable parameters to obtain the related variable parameters.
Optionally, the removing the characteristic repeated parameter in the initial related variable parameter, after obtaining the related variable parameter, further includes:
performing association degree analysis on each characteristic index in the related variable parameters to obtain an analysis result;
obtaining slow variable characteristic indexes and important variable characteristic indexes in the related variable parameters according to the analysis result;
performing quantitative steel transformation on slow variable characteristic indexes in the related variable parameters, and performing characteristic extraction on important variable characteristic indexes in the related variable parameters to obtain optimized related variable parameters;
and determining the weight of each characteristic index in the optimized related variable parameters according to a preset condition.
Optionally, before the health evaluation is performed on the fluid delivery electromechanical device according to the related variable parameter when the related variable parameter is not less than the parameter threshold value, the method further includes:
acquiring historical energy efficiency characteristic index parameters of the fluid conveyor electrical equipment;
determining an energy efficiency dynamic relation between the characteristic parameters and the energy efficiency according to the historical energy efficiency characteristic index parameters;
and determining an energy efficiency grade table of the fluid conveyor electric equipment according to the energy efficiency dynamic relation.
Optionally, the related variable parameters further include historical operating data and historical maintenance data;
and when the related variable parameter is not smaller than a parameter threshold, performing health evaluation on the fluid conveyor electrical equipment according to the related variable parameter to obtain a health value of the fluid conveyor electrical equipment, wherein the health value comprises the following steps:
obtaining a historical health value of the equipment according to the historical operation data and the historical maintenance data;
determining an energy efficiency value of the fluid delivery machine according to the energy efficiency level table;
determining a real-time health value of the fluid conveyor electrical equipment according to the energy efficiency value, the related variable parameter and the index weight of each characteristic index in the related variable parameter;
and obtaining the total health value of the equipment according to the historical health value of the equipment and the real-time health value of the equipment.
Optionally, before the diagnosing the fault of the fluid transporter electromechanical device according to the related variable parameter when the health value of the fluid transporter electromechanical device is less than or equal to a health threshold value, the method further includes:
acquiring historical related parameters of the fluid conveyor electrical equipment and fault parameters corresponding to historical faults, wherein the historical related parameters comprise fan parameters and water pump parameters;
constructing a fault diagnosis model according to the history related parameters and fault parameters corresponding to the history faults;
and constructing a fault diagnosis database according to the fault parameters and the reference processing strategy.
Optionally, the diagnosing the fault of the fluid transporter electromechanical device according to the related variable parameter includes:
inputting the related variable parameters into the fault diagnosis model to obtain a predicted fault type;
matching the predicted fault type with fault parameters in the fault diagnosis database to obtain a predicted fault cause, and determining a corresponding reference processing strategy according to the fault cause;
fault diagnosis of the fluid delivery electro-mechanical device is accomplished based on the reference processing strategy. .
In addition, in order to achieve the above object, the present application also proposes an equipment failure diagnosis apparatus including:
the health evaluation module is used for collecting related variable parameters of the fluid conveyor electrical equipment in real time, wherein the related variable parameters comprise physical parameters and operation related parameters;
the health evaluation module is further used for performing health evaluation on the fluid conveyor electrical equipment according to the related variable parameters when the related variable parameters are not smaller than a parameter threshold value, so as to obtain a health value of the fluid conveyor electrical equipment;
the fault diagnosis module is used for judging whether the health value of the fluid conveyor electrical equipment is smaller than or equal to a health threshold value;
the fault diagnosis module is further configured to perform fault diagnosis on the fluid transporter electrical equipment according to the related variable parameter when the health value of the fluid transporter electrical equipment is less than or equal to a health threshold value.
In addition, in order to achieve the above object, the present application also proposes an apparatus failure diagnosis apparatus including: a memory, a processor, and a device fault diagnosis program stored on the memory and executable on the processor, the device fault diagnosis program being configured to implement the steps of the device fault diagnosis method as described above.
In addition, in order to achieve the above object, the present application also proposes a storage medium having stored thereon an equipment failure diagnosis program which, when executed by a processor, implements the steps of the equipment failure diagnosis method as described above.
According to the application, the real-time health assessment is carried out on the equipment by collecting the relevant variable parameters of the equipment in real time, the fault diagnosis is carried out on the equipment according to the assessment result, the sudden fault and the trend tracking can be timely found out, the traditional passive operation and maintenance mode based on events or time is changed, the intelligent operation and maintenance based on the state is realized, the overall management level of the fluid conveying electromechanical equipment is effectively improved, the working quality is ensured, and the demonstration effect is played for popularization of the leading edge intelligent and informatization technology in operation and maintenance work.
Drawings
FIG. 1 is a schematic diagram of a device fault diagnosis device of a hardware operating environment according to an embodiment of the present application;
FIG. 2 is a schematic flow chart of a first embodiment of the apparatus fault diagnosis method of the present application;
FIG. 3 is a flow chart of a second embodiment of the device fault diagnosis method of the present application;
FIG. 4 is a schematic diagram showing steps related to fault prediction according to an embodiment of the apparatus fault diagnosis method of the present application;
fig. 5 is a block diagram showing the construction of a first embodiment of the apparatus for diagnosing a malfunction of a device according to the present application.
The achievement of the objects, functional features and advantages of the present application will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.
Referring to fig. 1, fig. 1 is a schematic structural diagram of an equipment fault diagnosis device of a hardware running environment according to an embodiment of the present application.
As shown in fig. 1, the device failure diagnosis device may include: a processor 1001, such as a central processing unit (Central Processing Unit, CPU), a communication bus 1002, a user interface 1003, a network interface 1004, a memory 1005. Wherein the communication bus 1002 is used to enable connected communication between these components. The user interface 1003 may include a Display, an input unit such as a Keyboard (Keyboard), and the optional user interface 1003 may further include a standard wired interface, a wireless interface. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a high-speed random access Memory (Random Access Memory, RAM) Memory or a stable nonvolatile Memory (NVM), such as a disk Memory. The memory 1005 may also optionally be a storage device separate from the processor 1001 described above.
It will be appreciated by those skilled in the art that the structure shown in fig. 1 does not constitute a limitation of the device fault diagnosis device, and may include more or fewer components than shown, or may combine certain components, or a different arrangement of components.
As shown in fig. 1, an operating system, a network communication module, a user interface module, and a device failure diagnosis program may be included in the memory 1005 as one type of storage medium.
In the device failure diagnosis device shown in fig. 1, the network interface 1004 is mainly used for data communication with a network server; the user interface 1003 is mainly used for data interaction with a user; the processor 1001 and the memory 1005 in the device fault diagnosis apparatus of the present application may be provided in the device fault diagnosis apparatus, which invokes the device fault diagnosis program stored in the memory 1005 through the processor 1001 and executes the device fault diagnosis method provided by the embodiment of the present application.
An embodiment of the present application provides a method for diagnosing a device fault, and referring to fig. 2, fig. 2 is a schematic flow chart of a first embodiment of a method for diagnosing a device fault according to the present application.
In this embodiment, the device fault diagnosis method includes the following steps:
step S10: related variable parameters of the fluid delivery electro-mechanical device are collected in real time, including physical parameters and operational related parameters.
It is understood that various sensors, meters, sensor networks and the like can be installed on the fluid conveyor mechanical equipment, and related variable parameters of the fluid conveyor mechanical equipment can be acquired through the series of equipment.
It should be appreciated that the related variable parameters may include physical parameters and operation related parameters, where the related variable parameters may include current, voltage, power, frequency, etc. power parameters during power-on operation of the power meter monitoring device; monitoring physical parameters such as working rotation speed, vibration, shaft temperature, noise and the like in the starting operation process of equipment through built-in professional sensing elements; parameters such as medium temperature, pressure, flow and the like related to normal operation of the equipment are monitored through an external sensing device.
It should be noted that, by long-term tracking of the equipment operation data and research, it is found that the health condition of the equipment has relevance with the data such as current, voltage, power, rotation speed, shaft temperature, vibration, noise and the like during the operation of the equipment, and along with the accumulation of the service life of the equipment, adverse factors such as aging and the like of the equipment can cause adverse changes of the data quantity, such as rise of the shaft temperature, increase of the noise, increase of the vibration, rise of the current, fluctuation of the voltage, unstable rotation speed, increase of the power and the like. Further analysis and screening find that the rotating speed and the voltage have overlapping property, and the current, the voltage, the power, the shaft temperature, the diagnosis and the noise are selected as characteristic data after the rotating speed is removed. By long-term tracking of equipment operation data and research, the health condition of the equipment is found to have a certain correlation with the equipment operation energy efficiency. As the device ages accumulate, the device energy efficiency value may decrease. And selecting data related to the energy efficiency of the equipment, such as wind pressure, wind quantity, power of a fan, flow rate, lift (pressure), power of a water pump and the like.
Step S20: and when the related variable parameter is not smaller than a parameter threshold, carrying out health evaluation on the fluid conveyor electromechanical equipment according to the related variable parameter to obtain a health value of the fluid conveyor electromechanical equipment.
It will be appreciated that the initial relevant variable parameter of the fluid delivery electro-mechanical device may be detected at the very beginning of operation of the fluid delivery electro-mechanical device, and may be used as a relevant variable parameter representative of the health of the fluid delivery electro-mechanical device.
It should be understood that, when the long-term usage of the fluid conveying electromechanical device is summarized and the collected relevant variable parameter values corresponding to the fluid conveying electromechanical device when different faults occur, the parameter threshold value is comprehensively set according to the relevant variable parameter values when different faults occur, and the parameter threshold value can be defined according to practical situations, which is not limited in this embodiment.
It should be noted that, the health evaluation may be understood as a process of comprehensively scoring the device according to various real-time related parameters of the fluid delivery machine, and the health of the device may be evaluated according to the real-time related parameters to obtain the health value of the device.
It should be noted that, when the related variable parameter is not less than the parameter threshold, the health evaluation is performed on the fluid conveyor electrical equipment according to the related variable parameter, and before the health value of the fluid conveyor electrical equipment is obtained, the method further includes:
the historical energy efficiency characteristic index parameters of the fluid conveyor electrical equipment are obtained, and it is understood that the characteristic index parameters (wind pressure, wind volume, power, rotating speed, water pressure, water flow and the like) capable of representing the energy efficiency of the equipment are selected to carry out acquisition tracking in a statistical period.
And determining the energy efficiency dynamic relation between the characteristic parameters and the energy efficiency according to the historical energy efficiency characteristic index parameters, and analyzing the dynamic relation between the characteristic parameters and the energy efficiency.
Determining an energy efficiency level table of the fluid conveyor electromechanical equipment according to the energy efficiency dynamic relation, wherein fan efficiency is calculated according to the current wind pressure, the wind quantity, the fan impeller power and the like of a fan according to a related efficiency calculation method and an energy efficiency level system in a fan energy efficiency limiting value and energy efficiency level, and a fan performance curve is drawn; and combining the calculated pressure coefficient value and the specific rotation speed value to refer to the energy efficiency grade table to obtain the energy efficiency grade. The energy efficiency class of the wind turbine is divided into 3 stages, wherein the energy efficiency of the stage 1 is highest, and the energy efficiency of the stage 3 is lowest. According to a related efficiency calculation method and an energy efficiency and energy conservation evaluation system in the energy efficiency limit value and energy conservation evaluation value of the centrifugal pump of clear water, water pump efficiency is calculated according to the current flow, the lift (pressure), the pump shaft power and the like of the water pump, and a water pump performance curve is drawn; and the indexes such as an energy efficiency limiting value, an energy efficiency energy saving evaluation value and the like are obtained by combining the calculated specific rotation speed with the reference energy efficiency reference value and the energy efficiency correction value related standard chart, and the energy efficiency evaluation is carried out by comparing and analyzing with the actual efficiency.
It is emphasized that the related variable parameters also include historical operating data and historical maintenance data;
and when the related variable parameter is not smaller than a parameter threshold, performing health evaluation on the fluid conveyor electrical equipment according to the related variable parameter to obtain a health value of the fluid conveyor electrical equipment, wherein the health value comprises the following steps:
and obtaining a device historical health value according to the historical operation data and the historical maintenance data, wherein it can be understood that a device health evaluation system is constructed based on the operation historical data, the maintenance historical data, the device operation real-time energy efficiency data and the characteristic index real-time monitoring data capable of representing the device health of the fluid conveying electromechanical device. Wherein the operation history data includes: the equipment is started up for times, time length, fault-free time length and the like; the maintenance history data includes: maintenance times, failure rate, etc.; the equipment operation real-time energy efficiency data is an equipment energy efficiency value obtained according to the equipment real-time state data; the real-time monitoring data of the characteristic index capable of representing the health of the equipment comprises the following steps: current, voltage, power, shaft temperature, vibration, noise, etc.
Determining an energy efficiency value of the fluid delivery machine according to the energy efficiency level table; determining a real-time health value of the fluid conveyor electrical equipment according to the energy efficiency value, the related variable parameter and the index weight of each characteristic index in the related variable parameter; and obtaining the total health value of the equipment according to the historical health value of the equipment and the real-time health value of the equipment.
In the specific implementation, according to the historical running state and maintenance condition of the equipment, the scores of the historical data elements in the health evaluation system are manually determined and are divided into 100 points. And analyzing the relation among the data elements in the health evaluation system by using an analytic hierarchy process, artificially determining and distributing the weights of the data elements by combining experience, continuously optimizing and correcting the data elements according to the subsequent evaluation result of the system, and quantifying the qualitative problem to achieve the purpose of normalization processing.
The values of the energy efficiency data elements monitored by the equipment in real time and the equipment health characteristic indexes, the scores of the operation history data elements and the scores of the maintenance history data elements are comprehensively imported into an equipment health value evaluation system for quantitative analysis, as shown in the following formula,
where Ha is the total health evaluation value of each type of operation and maintenance history data element, ai is the score of the ith operation and maintenance history data element, and Wi is the weight of the ith operation and maintenance history data element.
Wherein Hb is the total health evaluation value of all energy efficiency and health characteristic index real-time data elements, xi is the monitoring value of the ith energy efficiency and health characteristic index real-time data elements, ki is the threshold average value of the ith energy efficiency and health characteristic index real-time data elements, timax is the threshold maximum value of the ith energy efficiency and health characteristic index real-time data elements, timin is the threshold minimum value of the ith energy efficiency and health characteristic index real-time data elements, and Wi is the weight of the ith energy efficiency and health characteristic index real-time data elements.
H＝H a +H b
Wherein H is the total index value of the equipment health evaluation, ha is the total health evaluation value of various operation and maintenance history data elements, and Hb is the total health evaluation value of various energy efficiency and health characteristic index real-time data elements.
Step S30: and judging whether the health value of the fluid conveyor electric equipment is smaller than or equal to a health threshold value.
It should be noted that, the health value scores are divided into different grades in advance, and the different grades correspond to different scores, for example, the health value is 85-100, and the health grade is good; health value is 75-84, and health grade is good; health value is 60-74, and health grade is medium; health values less than 60, health grades poor; the health status of the current device can be obtained according to the health value.
Further, whether the health value is larger than a preset threshold value or not is judged, if the health value is smaller than the preset threshold value, equipment maintenance is needed or equipment failure is needed to be prevented in advance.
It is understood that the health threshold may be set according to practical situations, which is not limited in this embodiment.
Step S40: and when the health value of the fluid conveyor electric equipment is smaller than or equal to a health threshold value, performing fault diagnosis on the fluid conveyor electric equipment according to the related variable parameters.
It will be appreciated that the fault diagnosis may be to confirm a problem present in the device, while a corresponding solution is derived based on the confirmed problem.
It should be noted that, inputting the related variable parameters into the fault diagnosis model to obtain a predicted fault type;
matching the predicted fault type with fault parameters in the fault diagnosis database to obtain a predicted fault cause, and determining a corresponding reference processing strategy according to the fault cause;
fault diagnosis of the fluid delivery electro-mechanical device is accomplished based on the reference processing strategy.
It should be noted that, when the health value of the fluid transporter electromechanical device is less than or equal to the health threshold value, before performing fault diagnosis on the fluid transporter electromechanical device according to the related variable parameter, the method further includes:
acquiring historical related parameters of the fluid conveyor mechanical equipment and fault parameters corresponding to the historical faults, wherein the historical related parameters comprise fan parameters and water pump parameters, and it is understood that the characteristic parameters related to the faults of the fan equipment comprise wind pressure, wind quantity, vibration, noise, shaft temperature, current and power, and the characteristic parameters related to the faults of the water pump equipment comprise water pressure, water flow, vibration, noise, shaft temperature, current and power;
and constructing a fault diagnosis model according to the historical related parameters and fault parameters corresponding to the historical faults, wherein the fault characteristic parameters and the equipment states (whether faults exist) are respectively acquired according to the types of fault diagnosis objects (fans and water pumps), and training is carried out by adopting an artificial neural network algorithm model based on the acquired historical data so as to construct the fault diagnosis model. The initial weight and bias of the algorithm model are set manually according to experience and are continuously trained and learned and corrected by the later algorithm model so as to optimize the algorithm model and improve the prediction precision. And according to the fault prediction model, based on the characteristic parameters related to the equipment faults acquired in real time, inputting the characteristic parameters into the equipment fault prediction model to perform fault probability prediction.
Further, the data features are further extracted from the feature data, so that the pointing sensitivity of the feature data is improved. The data feature extraction can be referred to in the following table:
and constructing a fault diagnosis database according to the fault parameters and the reference processing strategy.
It should be further noted that the fault diagnosis database may be a mapping table of solutions corresponding to various faults, which is pre-established, and the following table may be referred to in detail:
further:
for influencing factors of fans, reference may be made to the following table:
it should be noted that, determining relevant feature variables of equipment faults, determining the type of the equipment faults in time by combining an equipment fault diagnosis model with a fault diagnosis knowledge base, locating possible causes of the faults, and providing a fault processing method and maintenance suggestions to form an automatic intelligent diagnosis flow.
According to the method, the device is subjected to real-time health assessment through the real-time collection of the related variable parameters of the device, the device is subjected to fault diagnosis according to the assessment result, sudden faults can be found in time, the device state is tracked and predicted, the traditional passive operation and maintenance mode based on events or time is changed, and the overall management level of the fluid conveying electromechanical device is effectively improved.
Referring to fig. 3, fig. 3 is a schematic flow chart of a second embodiment of an apparatus fault diagnosis method according to the present application.
Based on the first embodiment, the device fault diagnosis method of the present embodiment further includes, before the step S10:
step S101: the original variable parameters of the fluid conveyor electrical equipment are collected.
It is understood that the raw variable parameter may be a parameter collected by the fluid delivery electro-mechanical device over historical use.
It should be understood that the original variable parameters after being collected can be used for training a fault diagnosis model, wherein when the model is trained, data needs to be preprocessed, the processed data trains the model, and features can be processed and classified more accurately.
Step S102: sampling the original variable parameters to obtain sampling data, filtering the sampling data to obtain filtered data, and removing error data in the filtered data to obtain reference variable parameters.
It can be understood that the sampling of the original variable parameters to obtain the sampled data can be performed by researching the optimal sampling frequency and the balanced sampling method of the data so as to solve the problem that the data are not equal in length due to different sampling rates.
In a specific implementation, multi-source data collected on site are analyzed into original data in a system data model; adopting a recursive average filtering algorithm with small calculated amount to realize data filtering on the data signal; and detecting and eliminating errors, inconsistencies, incomplete and repeated data and the like from a data source by using data cleaning technologies such as mathematical statistics, data mining, predefined cleaning rules and the like, and providing high-quality data for subsequent health evaluation, fault diagnosis and prediction.
Step S103: an initial correlation variable parameter of the reference variable parameters is determined from steady state data and fault transient data of the fluid delivery electromechanical device.
It can be understood that the steady state data can be related data of the equipment in the daily use process of the fluid conveyor electric equipment, and the change of the steady state data can intuitively see the use loss and the service life of the equipment; the fault transient data may be understood as data of the device when a fault occurs, for example, parameters such as current, voltage, etc. collected when the device fails.
It should be understood that, in the event of a fault, a plurality of parameters may be changed at the same time, and the corresponding plurality of parameters may be used as relevant parameters of the fault, which further illustrates that there may be a plurality of relevant parameters that are changed correspondingly, for example, a current is changed, a corresponding voltage is changed, and when relevant parameters are acquired for the fault, the current and the voltage are repeated parameters, and a number of repeated variable parameters increase the data volume of the model when the model is trained, so that the model training speed is slow, the prediction speed is slower, and even the model is over-converged.
It should be noted that, through the steady state data under each state of the equipment obtained by long-term operation tracking of the fluid-delivery electromechanical equipment and the transient state data when the abnormal phenomenon occurs, the data parameters of the equipment state abnormal or the change generated when the fault occurs are researched, the relevant characteristic parameters which can point to the equipment health and fault state are judged, the characteristic parameters with repeated judging performance are screened and de-duplicated, the running state of the equipment is completely and accurately described by the characteristic quantity less than the number of the original parameters, and the calculation quantity of subsequent health assessment, fault diagnosis and prediction is greatly reduced.
Step S104: and removing the parameter with repeated characteristics in the initial related variable parameters to obtain the related variable parameters.
It can be understood that the relevant variable parameters are obtained after the repeated parameters in the relevant parameters of the equipment are removed, so that model training can be completed more quickly, and meanwhile, the model data processing amount is reduced, and an accurate fault diagnosis result is obtained.
It should be noted that, after removing the parameter with repeated features in the initial related variable parameter to obtain the related variable parameter, the method further includes:
performing association degree analysis on each characteristic index in the related variable parameters to obtain an analysis result, wherein the association degree analysis can be set according to the association degree between each related variable parameter and equipment faults, and the association degree between 0 and 1 represents the association degree between the two parameters;
obtaining and determining a slow variable characteristic index and an important variable characteristic index in the related variable parameters according to the analysis result, wherein the analysis result represents the association degree between the two parameters, the association degree is large and represents the important variable characteristic index, the analysis result is compared with a preset index characteristic threshold value, the important variable characteristic index is the analysis result when the analysis result is larger than the threshold value, and the slow variable characteristic index is the slow variable characteristic index when the analysis result is smaller than the threshold value;
the slow variable characteristic indexes in the related variable parameters are subjected to quantitative steel transformation, namely, the characteristic indexes can be simply normalized, the normalized data can be more rapidly trained when model characteristic training is carried out, and important variable characteristic indexes in the related variable parameters are subjected to characteristic extraction to obtain optimized related variable parameters;
and determining each characteristic index weight in the optimized related variable parameters according to a preset condition, wherein the preset condition can be that the association degree between each parameter and the equipment fault is set between 0 and 1 based on the association degree between the parameters and the equipment fault under different equipment faults.
In specific implementation, reference may be made to fig. 4, where fig. 4 is a relevant step of fault prediction, and in the drawing, based on a health evaluation result, comprehensive operation and maintenance management of daily inspection, maintenance and repair of the object device and query of relevant information are completed, including equipment ledger management, operation and maintenance personnel management, spare part warehouse management, maintenance manual management, operation and maintenance knowledge base, etc., to provide recommended measures for operation and maintenance work, and reasonably formulate an equipment operation and maintenance plan.
Furthermore, the development of daily inspection, maintenance and repair operation and maintenance work can be guided based on the health evaluation result, and equipment inspection, maintenance and repair plans can be reasonably formulated. By reasonably planning the inspection time interval and reasonably configuring inspection personnel, the inspection efficiency is improved, and the labor cost is saved. And (3) performing high-frequency inspection on equipment with low health and easy failure, tracking the state of the equipment, and timely finding the state change condition of the equipment. By reasonably planning the maintenance time interval, the health state of the equipment is maintained, the service life of the equipment is prolonged, and the use benefit of the equipment is improved. Through carrying out fault pre-judgment and early warning on equipment which is about to fail, a manager is reminded to carry out key inspection on the equipment, and important parameter records are adjusted and watched, so that maintenance personnel can make equipment maintenance or replacement preparation in advance, and the loss caused by sudden equipment failure to normal operation of an equipment system is reduced. And (3) reasonably planning human resources of operation and maintenance and spare parts stock, and continuously perfecting a maintenance manual and an operation and maintenance knowledge base according to operation and maintenance events.
According to the method, the device and the system, the device relevant parameters are collected in advance, repeated characteristics and error data in the relevant parameters are removed, system faults and device relevant parameters are further analyzed from two aspects of steady-state data and transient-state data, relevant variable parameters are finally obtained, model training is conducted based on the relevant variable parameters, model training is rapidly completed through fewer characteristic data, and therefore a prediction result can be obtained more rapidly and accurately when fault prediction is conducted through the device real-time relevant parameters.
In addition, the embodiment of the application also provides a storage medium, wherein the storage medium stores an equipment fault diagnosis program, and the equipment fault diagnosis program realizes the steps of the equipment fault diagnosis method when being executed by a processor.
Referring to fig. 5, fig. 5 is a block diagram showing the construction of a first embodiment of the apparatus for diagnosing a malfunction of a device according to the present application.
As shown in fig. 5, the device fault diagnosis apparatus according to the embodiment of the present application includes:
a health assessment module 10 for collecting in real time relevant variable parameters of the fluid delivery machine electrical equipment, including physical parameters and operational related parameters;
the health evaluation module 10 is further configured to perform health evaluation on the fluid transporter electrical equipment according to the related variable parameter when the related variable parameter is not less than a parameter threshold value, so as to obtain a health value of the fluid transporter electrical equipment;
a fault diagnosis module 20 for determining whether a health value of the fluid delivery electro-mechanical device is less than or equal to a health threshold;
the fault diagnosis module 20 is further configured to perform fault diagnosis on the fluid transporter electric device according to the related variable parameter when the health value of the fluid transporter electric device is less than or equal to a health threshold value.
According to the method, the device is subjected to real-time health assessment through the real-time collection of the related variable parameters of the device, the device is subjected to fault diagnosis according to the assessment result, sudden faults can be found in time, the device state is tracked and predicted, the traditional passive operation and maintenance mode based on events or time is changed, and the overall management level of the fluid conveying electromechanical device is effectively improved.
In one embodiment, the health assessment module 10 is further configured to collect raw variable parameters of the fluid delivery electro-mechanical device;
sampling the original variable parameters to obtain sampling data, filtering the sampling data to obtain filtered data, and removing error data in the filtered data to obtain reference variable parameters;
determining an initial related variable parameter of the reference variable parameters according to steady state data and fault transient state data of the fluid conveyor electrical equipment;
and removing the parameter with repeated characteristics in the initial related variable parameters to obtain the related variable parameters.
In an embodiment, the health evaluation module 10 is further configured to perform association analysis on each feature index in the related variable parameter to obtain an analysis result;
obtaining slow variable characteristic indexes and important variable characteristic indexes in the related variable parameters according to the analysis result;
performing quantitative steel transformation on slow variable characteristic indexes in the related variable parameters, and performing characteristic extraction on important variable characteristic indexes in the related variable parameters to obtain optimized related variable parameters;
and determining the weight of each characteristic index in the optimized related variable parameters according to a preset condition.
In one embodiment, the health assessment module 10 is further configured to obtain historical energy efficiency characteristic index parameters of the fluid delivery electro-mechanical device;
determining an energy efficiency dynamic relation between the characteristic parameters and the energy efficiency according to the historical energy efficiency characteristic index parameters;
and determining an energy efficiency grade table of the fluid conveyor electric equipment according to the energy efficiency dynamic relation.
In one embodiment, the health evaluation module 10 is further configured to obtain a device historical health value according to the historical operation data and the historical maintenance data;
determining an energy efficiency value of the fluid delivery machine according to the energy efficiency level table;
determining a real-time health value of the fluid conveyor electrical equipment according to the energy efficiency value, the related variable parameter and the index weight of each characteristic index in the related variable parameter;
and obtaining the total health value of the equipment according to the historical health value of the equipment and the real-time health value of the equipment.
In an embodiment, the fault diagnosis module 20 is further configured to obtain a history related parameter of the fluid delivery machine and a fault parameter corresponding to a history fault, where the history related parameter includes a fan parameter and a water pump parameter;
constructing a fault diagnosis model according to the history related parameters and fault parameters corresponding to the history faults;
and constructing a fault diagnosis database according to the fault parameters and the reference processing strategy.
In an embodiment, the fault diagnosis module 20 is further configured to input the related variable parameter into the fault diagnosis model to obtain a predicted fault type;
matching the predicted fault type with fault parameters in the fault diagnosis database to obtain a predicted fault cause, and determining a corresponding reference processing strategy according to the fault cause;
fault diagnosis of the fluid delivery electro-mechanical device is accomplished based on the reference processing strategy.
It should be understood that the foregoing is illustrative only and is not limiting, and that in specific applications, those skilled in the art may set the application as desired, and the application is not limited thereto.
It should be noted that the above-described working procedure is merely illustrative, and does not limit the scope of the present application, and in practical application, a person skilled in the art may select part or all of them according to actual needs to achieve the purpose of the embodiment, which is not limited herein.
Furthermore, it should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The foregoing embodiment numbers of the present application are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments.
From the above description of the embodiments, it will be clear to those skilled in the art that the above-described embodiment method may be implemented by means of software plus a necessary general hardware platform, but of course may also be implemented by means of hardware, but in many cases the former is a preferred embodiment. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art in the form of a software product stored in a storage medium (e.g. Read Only Memory)/RAM, magnetic disk, optical disk) and including several instructions for causing a terminal device (which may be a mobile phone, a computer, a server, or a network device, etc.) to perform the method according to the embodiments of the present application.
It should be understood that, although the steps in the flowcharts in the embodiments of the present application are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited in order and may be performed in other orders, unless explicitly stated herein. Moreover, at least some of the steps in the figures may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, the order of their execution not necessarily occurring in sequence, but may be performed alternately or alternately with other steps or at least a portion of the other steps or stages.
The foregoing description is only of the preferred embodiments of the present application, and is not intended to limit the scope of the application, but rather is intended to cover any equivalents of the structures or equivalent processes disclosed herein or in the alternative, which may be employed directly or indirectly in other related arts.
Claims (10)
1. An apparatus failure diagnosis method, characterized in that the apparatus failure diagnosis method comprises:
collecting related variable parameters of the fluid conveyor electrical equipment in real time, wherein the related variable parameters comprise physical parameters and operation related parameters;
when the related variable parameter is not smaller than a parameter threshold, carrying out health evaluation on the fluid conveyor electromechanical equipment according to the related variable parameter to obtain a health value of the fluid conveyor electromechanical equipment;
judging whether the health value of the fluid conveyor electrical equipment is smaller than or equal to a health threshold value;
and when the health value of the fluid conveyor electric equipment is smaller than or equal to a health threshold value, performing fault diagnosis on the fluid conveyor electric equipment according to the related variable parameters.
2. The device fault diagnosis method of claim 1, wherein the real-time acquisition of related variable parameters of the fluid delivery electro-mechanical device, the related variable parameters including physical parameters and operational correlation parameters, further comprising, prior to:
collecting original variable parameters of the fluid conveyor electrical equipment;
sampling the original variable parameters to obtain sampling data, filtering the sampling data to obtain filtered data, and removing error data in the filtered data to obtain reference variable parameters;
determining an initial related variable parameter of the reference variable parameters according to steady state data and fault transient state data of the fluid conveyor electrical equipment;
and removing the parameter with repeated characteristics in the initial related variable parameters to obtain the related variable parameters.
3. The apparatus fault diagnosis method according to claim 2, wherein the removing the parameter of the feature repetition in the initial related variable parameter, after obtaining the related variable parameter, further comprises:
performing association degree analysis on each characteristic index in the related variable parameters to obtain an analysis result;
obtaining slow variable characteristic indexes and important variable characteristic indexes in the related variable parameters according to the analysis result;
performing quantitative steel transformation on slow variable characteristic indexes in the related variable parameters, and performing characteristic extraction on important variable characteristic indexes in the related variable parameters to obtain optimized related variable parameters;
and determining the weight of each characteristic index in the optimized related variable parameters according to a preset condition.
4. The apparatus fault diagnosis method according to claim 1, wherein when the relevant variable parameter is not less than a parameter threshold, before performing health assessment on the fluid conveyor electric apparatus according to the relevant variable parameter to obtain a health value of the fluid conveyor electric apparatus, further comprising:
acquiring historical energy efficiency characteristic index parameters of the fluid conveyor electrical equipment;
determining an energy efficiency dynamic relation between the characteristic parameters and the energy efficiency according to the historical energy efficiency characteristic index parameters;
and determining an energy efficiency grade table of the fluid conveyor electric equipment according to the energy efficiency dynamic relation.
5. The device fault diagnosis method as claimed in claim 4, wherein the related variable parameters further comprise historical operating data and historical maintenance data;
and when the related variable parameter is not smaller than a parameter threshold, performing health evaluation on the fluid conveyor electrical equipment according to the related variable parameter to obtain a health value of the fluid conveyor electrical equipment, wherein the health value comprises the following steps:
obtaining a historical health value of the equipment according to the historical operation data and the historical maintenance data;
determining an energy efficiency value of the fluid delivery machine according to the energy efficiency level table;
determining a real-time health value of the fluid conveyor electrical equipment according to the energy efficiency value, the related variable parameter and the index weight of each characteristic index in the related variable parameter;
and obtaining the total health value of the equipment according to the historical health value of the equipment and the real-time health value of the equipment.
6. The apparatus fault diagnosis method as claimed in any one of claims 1 to 5, wherein when the health value of the fluid conveyor apparatus is equal to or less than a health threshold value, before performing fault diagnosis on the fluid conveyor apparatus according to the related variable parameter, further comprising:
acquiring historical related parameters of the fluid conveyor electrical equipment and fault parameters corresponding to historical faults, wherein the historical related parameters comprise fan parameters and water pump parameters;
constructing a fault diagnosis model according to the history related parameters and fault parameters corresponding to the history faults;
and constructing a fault diagnosis database according to the fault parameters and the reference processing strategy.
7. The apparatus fault diagnosis method according to claim 6, wherein said fault diagnosing said fluid conveyor electrical apparatus based on said related variable parameter comprises:
inputting the related variable parameters into the fault diagnosis model to obtain a predicted fault type;
matching the predicted fault type with fault parameters in the fault diagnosis database to obtain a predicted fault cause, and determining a corresponding reference processing strategy according to the fault cause;
fault diagnosis of the fluid delivery electro-mechanical device is accomplished based on the reference processing strategy.
8. An apparatus failure diagnosis device, characterized in that the apparatus failure diagnosis device comprises:
the health evaluation module is used for collecting related variable parameters of the fluid conveyor electrical equipment in real time, wherein the related variable parameters comprise physical parameters and operation related parameters;
the health evaluation module is further used for performing health evaluation on the fluid conveyor electrical equipment according to the related variable parameters when the related variable parameters are not smaller than a parameter threshold value, so as to obtain a health value of the fluid conveyor electrical equipment;
the fault diagnosis module is used for judging whether the health value of the fluid conveyor electrical equipment is smaller than or equal to a health threshold value;
the fault diagnosis module is further configured to perform fault diagnosis on the fluid transporter electrical equipment according to the related variable parameter when the health value of the fluid transporter electrical equipment is less than or equal to a health threshold value.
9. An apparatus failure diagnosis apparatus, characterized in that the apparatus comprises: a memory, a processor, and a device fault diagnosis program stored on the memory and executable on the processor, the device fault diagnosis program configured to implement the device fault diagnosis method according to any one of claims 1 to 7.
10. A storage medium having stored thereon a device failure diagnosis program which, when executed by a processor, implements the device failure diagnosis method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310995660.7A CN117110741A (en) | 2023-08-08 | 2023-08-08 | Equipment fault diagnosis method, device, equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310995660.7A CN117110741A (en) | 2023-08-08 | 2023-08-08 | Equipment fault diagnosis method, device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117110741A true CN117110741A (en) | 2023-11-24 |
Family
ID=88811981
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310995660.7A Pending CN117110741A (en) | 2023-08-08 | 2023-08-08 | Equipment fault diagnosis method, device, equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117110741A (en) |
-
2023
- 2023-08-08 CN CN202310995660.7A patent/CN117110741A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7627454B2 (en) | Method and system for predicting turbomachinery failure events employing genetic algorithm | |
| CN111459700B (en) | Equipment fault diagnosis method, diagnosis device, diagnosis equipment and storage medium | |
| CN112052979A (en) | Equipment spare part demand prediction system based on fault prediction and health management | |
| US20120283988A1 (en) | Automated system and method for implementing unit and collective level benchmarking of power plant operations | |
| CN114861827B (en) | Coal mining machine predictive diagnosis and health management method based on multi-source data fusion | |
| JP5868331B2 (en) | Method and system for diagnosing a compressor | |
| CN115638875B (en) | Power plant equipment fault diagnosis method and system based on map analysis | |
| CN115617606A (en) | Equipment monitoring method and system, electronic equipment and storage medium | |
| CN114215705B (en) | Wind turbine generator system fault early warning method and system | |
| CN116381542B (en) | Health diagnosis method and device of power supply equipment based on artificial intelligence | |
| US11339763B2 (en) | Method for windmill farm monitoring | |
| CN117410961A (en) | Wind power prediction method, device, equipment and storage medium | |
| CN117110741A (en) | Equipment fault diagnosis method, device, equipment and storage medium | |
| CN115795999B (en) | Early warning method for abnormal performance of long-term service pumped storage unit | |
| CN114837902B (en) | Health degree evaluation method, system, equipment and medium for wind turbine generator | |
| CN112526558B (en) | System operation condition identification and cutting method under partial data loss condition | |
| Beduschi et al. | Optimizing rotating equipment maintenance through machine learning algorithm | |
| Zhang | Comparison of data-driven and model-based methodologies of wind turbine fault detection with SCADA data | |
| JP2022191680A (en) | Data selection support device, and data selection support method | |
| Trstenjak et al. | A Decision Support System for the Prediction of Wastewater Pumping Station Failures Based on CBR Continuous Learning Model. | |
| CN116118010B (en) | Energy management system for asymmetric steel-profile steel concrete column | |
| CN117649209B (en) | Enterprise revenue auditing method, system, equipment and storage medium | |
| CN117150032B (en) | Intelligent maintenance system and method for hydropower station generator set | |
| US20240035445A1 (en) | Systems and methods for estimating future risk of failure of a wind turbine component using machine learning | |
| US20240201680A1 (en) | Systems and methods for displaying renewable energy asset health risk information |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |