CN114278397A - Rotating machine health monitoring system and method based on Internet of things - Google Patents
Rotating machine health monitoring system and method based on Internet of things Download PDFInfo
- Publication number
- CN114278397A CN114278397A CN202111601202.8A CN202111601202A CN114278397A CN 114278397 A CN114278397 A CN 114278397A CN 202111601202 A CN202111601202 A CN 202111601202A CN 114278397 A CN114278397 A CN 114278397A
- Authority
- CN
- China
- Prior art keywords
- lubricating grease
- rotary machine
- module
- data
- initial prediction
- 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.)
- Granted
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/20—Hydro energy
Abstract
The invention discloses a rotary machine health monitoring system and method based on the Internet of things, and belongs to the technical field of rotary machine health monitoring. The system comprises a working environment information monitoring module, a lubricating grease adding management module, an initial prediction module, an engineering project analysis module, a scheduling module and a rotary machine health monitoring module; the output end of the working environment information monitoring module is connected with the input end of the lubricating grease adding management module; the output end of the lubricating grease adding management module is connected with the input end of the initial prediction module; the output end of the initial prediction module is connected with the input end of the engineering project analysis module; the engineering project analysis module, the scheduling module and the rotary machine health monitoring module are connected in sequence. Meanwhile, the invention also provides a method for intelligently adjusting the adding interval duration of the lubricating grease in the rotating machinery in a machine learning mode.
Description
Technical Field
The invention relates to the technical field of health monitoring of rotating machinery, in particular to a rotating machinery health monitoring system and method based on the Internet of things.
Background
The rotating machine is a machine which mainly depends on rotation to complete specific functions, and typical rotating machines comprise a steam turbine, a gas turbine, a centrifugal and axial flow compressor, a fan, a pump, a water turbine, a generator, an aircraft engine and the like, and are widely applied to departments of electric power, petrifaction, metallurgy, aerospace and the like.
In rotating machines, the most basic and common is the bearing, which is essential in mechanical equipment and the function of which is very important. In order to ensure the correct lubrication of mechanical parts, the lubrication is usually maintained by injecting lubricating grease, however, the lubricating grease needs to be replaced at regular time due to the oil distribution amount, the evaporation degree, the oxidation resistance and the like of the lubricating grease, in the current technical means, the judgment is usually carried out through the behavior habits or long-term experience of workers, a machine learning scheme is not provided, the manual judgment brings too much uncertainty, if the judgment is early, the raw materials are wasted by adding for many times, and huge workload is brought to the later-period cleaning; if the judgment is late, the bearing is easy to be damaged, and serious fire is easy to be caused due to overhigh temperature. In addition, unlike lubricating oil, lubricating oil often requires a machine to be stopped for operation when lubricating oil is injected, generally requires parts to be removed for addition, and there is no technique that can cope with a delay in the work period due to the addition of lubricating oil.
Disclosure of Invention
The invention aims to provide a rotary machine health monitoring system and method based on the Internet of things, and aims to solve the problems in the background technology.
In order to solve the technical problems, the invention provides the following technical scheme:
a rotary machine health monitoring system based on the Internet of things comprises a working environment information monitoring module, a lubricating grease adding management module, an initial prediction module, an engineering project analysis module, a scheduling module and a rotary machine health monitoring module;
the working environment information monitoring module is used for acquiring working environment information data of the rotary machine and constructing a basic database, wherein the working environment information data of the rotary machine comprises working environment temperature, working environment pollution level, rotary machine noise data and rotary machine vibration data; the lubricating grease adding management module is used for acquiring historical working data of the rotary machine and lubricating grease adding interval duration; the initial prediction module is used for constructing a lubricating grease adding interval duration initial prediction model according to historical data and information data of a working environment of the rotary machine; the engineering project analysis module is used for acquiring engineering projects where the rotary machinery is located and the construction period duration of each engineering project; the scheduling module is used for acquiring a newly added engineering project, constructing a dynamic scheduling method and adjusting an initial prediction model of the lubricating grease adding interval duration; the rotating machine health monitoring module is used for monitoring the health state of the rotating machine in real time;
the output end of the working environment information monitoring module is connected with the input end of the lubricating grease adding management module; the output end of the lubricating grease adding management module is connected with the input end of the initial prediction module; the output end of the initial prediction module is connected with the input end of the engineering project analysis module; the output end of the engineering project analysis module is connected with the input end of the scheduling module; the output end of the dispatching module is connected with the input end of the rotating machinery health monitoring module.
According to the technical scheme, the working environment information monitoring module comprises a working environment temperature monitoring unit, a working environment pollution level judging unit, a rotary mechanical noise data acquisition unit and a rotary mechanical vibration data acquisition unit;
the working environment temperature monitoring unit is used for monitoring the working environment temperature condition of the rotary machine; the working environment pollution level judging unit is used for judging the pollution level of the working environment according to national standards; the rotary machine noise data acquisition unit monitors noise data of the rotary machine by using an instrument; the rotary machine vibration data acquisition unit acquires vibration data of the rotary machine by using an instrument;
the output ends of the working environment temperature monitoring unit, the working environment pollution level judging unit, the rotating mechanical noise data acquisition unit and the rotating mechanical vibration data acquisition unit are connected with the input end of the lubricating grease adding management module.
According to the technical scheme, the lubricating grease adding management module comprises a historical data unit and a lubricating grease adding unit;
the historical data unit is used for acquiring historical working data of the rotary machine; the lubricating grease adding unit is used for acquiring the interval duration of adding lubricating grease to the rotary machine;
the output end of the historical data unit is connected with the input end of the initial prediction module; and the output end of the lubricating grease adding unit is connected with the input end of the initial prediction module.
According to the technical scheme, the initial prediction module comprises a model construction unit and a prediction output unit;
the model construction unit is used for constructing an initial prediction model of the lubricating grease adding interval duration according to historical data and the information data of the working environment of the rotary machine; the prediction output unit is used for outputting the predicted interval time for adding the lubricating grease to the rotating machinery according to the initial prediction model for the interval time for adding the lubricating grease;
the output end of the model building unit is connected with the input end of the prediction output unit; and the output end of the prediction output unit is connected with the input end of the engineering project analysis module.
According to the technical scheme, the scheduling module comprises a newly-added item acquisition unit and a dynamic scheduling unit;
the newly-added project acquisition unit is used for acquiring newly-added project; the dynamic scheduling unit is used for constructing a dynamic scheduling method and adjusting an initial prediction model of the lubricating grease adding interval duration;
the output end of the newly-added item acquisition unit is connected with the input end of the dynamic scheduling unit; and the output end of the dynamic scheduling unit is connected with the input end of the rotating machinery health monitoring module.
A rotating machinery health monitoring method based on the Internet of things comprises the following steps:
s1, acquiring the information data of the working environment of the rotary machine, and constructing a basic database;
s2, obtaining historical working data of the rotary machine and interval duration of adding lubricating grease, and constructing an initial prediction model of the interval duration of adding the lubricating grease according to a basic database;
s3, acquiring engineering projects where the rotary machinery is located, acquiring the construction period duration of each engineering project, and calculating the adding mode of the lubricating grease;
s4, acquiring a newly added engineering project, constructing a dynamic scheduling method, adjusting a lubricating grease adding interval duration initial prediction model, constructing a rotary machine health monitoring module based on the adjusted lubricating grease adding interval duration initial prediction model, and monitoring the running state of the rotary machine.
According to the above technical solution, in step S1, the data of the information of the working environment of the rotary machine includes a temperature of the working environment, a pollution level of the working environment, noise data of the rotary machine, and vibration data of the rotary machine.
The rotary mechanical noise data and the rotary mechanical vibration data mainly realize the internet of things through an industrial instrument and continuously acquire real-time data
According to the above technical solution, in step S2, the constructing an initial prediction model of the grease adding interval duration includes:
s8-1, acquiring historical working data of the rotary machine, selecting data with characteristics in a basic database as training data of a model, wherein the characteristics refer to information data of working environment of the rotary machine;
the characteristics represent the situation of the data of the working environment information of the rotary machine, for example, in a certain data, the working environment is A1 degrees, the pollution level of the working environment is A2 level, the noise data of the rotary machine is A3, and the vibration data of the rotary machine is A4, which shows that the characteristics in the data are as follows: temperature a1, pollution a2, noise A3, vibration a 4;
s8-2, taking the characteristic of certain data in the training data of the model as training input data, adding the interval duration of the lubricating grease as an execution result, and constructing an initial prediction model of the interval duration of the lubricating grease addition:
obtaining training input data and constructing a training input data set { (x)1，y1)、(x2，y2)、…、(xm，ym) In which x1、x2、…、xmRepresenting the characteristic data as an input vector; y is1、y2、…、ymRepresenting an execution result, indicating the interval duration of adding lubricating grease twice, and being an output variable; m is the number of samples, representing the number of training input data for training;
constructing a loss function L (y)i(x), a least squares loss function as a loss function;
wherein f (x) represents an approximation function, the approximation function f (x) being such that the loss function L (y)iF (x)) is minimal;
initializing a make-loss function L (y)iF (x)) minimum weak learner f0(x)；
Wherein c is a constant value estimated to minimize the loss function, and is a tree with only one root node; y isi∈y1、y2、…、ym；
Iteratively training a weak learner, wherein the maximum iteration number is T;
obtaining a strong learner obtained by the t-th round of training:
wherein T represents the run, T ═ 1, 2, …, T;
for each training input data sample, calculating its negative gradient rti：
Wherein, f (x)i) The function represented is the function of the previous iteration, i.e. in the training round t, the function used is the function of round t-1, xi∈x1、x2、…、xm，
Represents a differential;
using negative gradient rtiFitting the regression tree to obtain the t regression tree with the corresponding leaf node region as Rtj，j＝1，2，…，m；
Obtaining the best fitting value ctj：
Adding the weak learner into the trained model to obtain a new strong learner:
wherein f ist-1(x) Strong learner for the t-1 st round of training, ft(x) A strong learner obtained for the t-th round of training; i for reaction with ctjPartial combination, which represents the decision tree fitting function of the current round;
in the iteration of GBDT, assume that the strong learner we obtained from the previous iteration is ft-1(x) The loss function is (, f)t-1(x) The objective of our iteration round is to find a weak learner of the CART regression tree model, let the loss function (f, f) of the roundt(x))＝(,ft-1(x) + thisWeak learners) is minimal. That is, the iteration of this round finds the decision tree, so as to make the loss as small as possible and the prediction result is better, because the gradient is obtained on the basis of the previous round, so the function f (x) used in the calculation is f (x) ft-1(x) That is, the calculation of the present round is performed on the basis of the previous round;
after the circulation is finished, the final strong learner f is obtainedt(x) And the initial prediction model is used as the initial prediction model of the time interval of the grease addition.
According to the above technical solution, in step S3, the method further includes:
construction date K1，K1The date of adding the lubricating grease to the rotary machine is obtained according to the initial prediction model of the lubricating grease adding interval duration;
obtaining K1The idle construction period duration a of the project where the rotating machinery is located on the date1；
Obtaining the disassembly and assembly time length a of the rotary machine in the process of adding the lubricating grease2；
If a1Greater than a2Normally adding lubricating grease according to an initial prediction model of the lubricating grease adding interval duration; if a1Is less than a2Constructing an error value B1Outputting an adjusted lubricating grease adding interval duration initial prediction model as ft(x)-B1。
According to the above technical solution, in step S4, the method further includes:
acquiring a newly added engineering project;
acquiring the time length a required by the newly added engineering project3；
If a1-a3Greater than a2Normally adding lubricating grease according to an initial prediction model of the lubricating grease adding interval duration; if a1Greater than a2And a is1-a3Is less than a2Constructing an error value B2Outputting an adjusted lubricating grease adding interval duration initial prediction model as ft(x)-B2。
In the above technical scheme, if a1Is less than a2Constructing an error value B1Generally, the error value B1Set between 0 and 24 hours, mainly by estimating it to the end of the work item of the previous day, and if a1Greater than a2And a is1-a3Is less than a2Constructing an error value B2In the method, because the added item causes the delay of the original action of adding the lubricating grease, the relation between the added item and the original work item is obtained, the position of the added item is judged to be before or after the action of adding the lubricating grease is predicted, and if the position of the added item is before the action of adding the lubricating grease is predicted, an error value B is set2And ensuring that lubricating grease is added firstly and newly adding items.
Compared with the prior art, the invention has the following beneficial effects:
the invention can utilize the working environment information monitoring module to obtain the working environment information data of the rotary machine, and utilize the lubricating grease adding management module to obtain the historical working data of the rotary machine and the interval duration of adding lubricating grease; the method comprises the steps that an initial prediction module is used for analyzing comprehensive data, a lubricating grease adding interval duration initial prediction model is built, the interval duration of lubricating grease adding of the rotary machine is obtained through prediction, machine learning replaces manual judgment, the probability of misoperation is reduced, an intelligent monitoring mode is provided, and the development requirements of the times are met; meanwhile, the invention also utilizes the project analysis module to obtain the project of the rotary machine and the construction period duration of each project; acquiring a newly added engineering project by using a scheduling module, constructing a dynamic scheduling method, and adjusting an initial prediction model of the lubricating grease adding interval duration; the problem of delay influence caused by adding lubricating grease when the construction period is urgent or an engineering project is newly added can be solved, and the working efficiency is improved.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a schematic flow diagram of a rotary machine health monitoring system and method based on the Internet of things according to the present invention;
fig. 2 is a schematic step diagram of a rotating machine health monitoring method based on the internet of things.
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.
Referring to fig. 1-2, the present invention provides a technical solution:
a rotary machine health monitoring system based on the Internet of things comprises a working environment information monitoring module, a lubricating grease adding management module, an initial prediction module, an engineering project analysis module, a scheduling module and a rotary machine health monitoring module;
the working environment information monitoring module is used for acquiring working environment information data of the rotary machine and constructing a basic database, wherein the working environment information data of the rotary machine comprises working environment temperature, working environment pollution level, rotary machine noise data and rotary machine vibration data; the lubricating grease adding management module is used for acquiring historical working data of the rotary machine and lubricating grease adding interval duration; the initial prediction module is used for constructing a lubricating grease adding interval duration initial prediction model according to historical data and information data of a working environment of the rotary machine; the engineering project analysis module is used for acquiring engineering projects where the rotary machinery is located and the construction period duration of each engineering project; the scheduling module is used for acquiring a newly added engineering project, constructing a dynamic scheduling method and adjusting an initial prediction model of the lubricating grease adding interval duration; the rotating machine health monitoring module is used for monitoring the health state of the rotating machine in real time;
the output end of the working environment information monitoring module is connected with the input end of the lubricating grease adding management module; the output end of the lubricating grease adding management module is connected with the input end of the initial prediction module; the output end of the initial prediction module is connected with the input end of the engineering project analysis module; the output end of the engineering project analysis module is connected with the input end of the scheduling module; the output end of the dispatching module is connected with the input end of the rotating machinery health monitoring module.
The working environment information monitoring module comprises a working environment temperature monitoring unit, a working environment pollution level judging unit, a rotating mechanical noise data acquisition unit and a rotating mechanical vibration data acquisition unit;
the working environment temperature monitoring unit is used for monitoring the working environment temperature condition of the rotary machine; the working environment pollution level judging unit is used for judging the pollution level of the working environment according to national standards; the rotary machine noise data acquisition unit monitors noise data of the rotary machine by using an instrument; the rotary machine vibration data acquisition unit acquires vibration data of the rotary machine by using an instrument;
the output ends of the working environment temperature monitoring unit, the working environment pollution level judging unit, the rotating mechanical noise data acquisition unit and the rotating mechanical vibration data acquisition unit are connected with the input end of the lubricating grease adding management module.
The lubricating grease adding management module comprises a historical data unit and a lubricating grease adding unit;
the historical data unit is used for acquiring historical working data of the rotary machine; the lubricating grease adding unit is used for acquiring the interval duration of adding lubricating grease to the rotary machine;
the output end of the historical data unit is connected with the input end of the initial prediction module; and the output end of the lubricating grease adding unit is connected with the input end of the initial prediction module.
The initial prediction module comprises a model construction unit and a prediction output unit;
the model construction unit is used for constructing an initial prediction model of the lubricating grease adding interval duration according to historical data and the information data of the working environment of the rotary machine; the prediction output unit is used for outputting the predicted interval time for adding the lubricating grease to the rotating machinery according to the initial prediction model for the interval time for adding the lubricating grease;
the output end of the model building unit is connected with the input end of the prediction output unit; and the output end of the prediction output unit is connected with the input end of the engineering project analysis module.
The scheduling module comprises a newly-added item acquisition unit and a dynamic scheduling unit;
the newly-added project acquisition unit is used for acquiring newly-added project; the dynamic scheduling unit is used for constructing a dynamic scheduling method and adjusting an initial prediction model of the lubricating grease adding interval duration;
the output end of the newly-added item acquisition unit is connected with the input end of the dynamic scheduling unit; and the output end of the dynamic scheduling unit is connected with the input end of the rotating machinery health monitoring module.
A rotating machinery health monitoring method based on the Internet of things comprises the following steps:
s1, acquiring the information data of the working environment of the rotary machine, and constructing a basic database;
s2, obtaining historical working data of the rotary machine and interval duration of adding lubricating grease, and constructing an initial prediction model of the interval duration of adding the lubricating grease according to a basic database;
s3, acquiring engineering projects where the rotary machinery is located, acquiring the construction period duration of each engineering project, and calculating the adding mode of the lubricating grease;
s4, acquiring a newly added engineering project, constructing a dynamic scheduling method, adjusting a lubricating grease adding interval duration initial prediction model, constructing a rotary machine health monitoring module based on the adjusted lubricating grease adding interval duration initial prediction model, and monitoring the running state of the rotary machine.
In step S1, the rotating machine work environment information data includes a work environment temperature, a work environment pollution level, rotating machine noise data, and rotating machine vibration data.
In step S2, the constructing the grease addition interval duration initial prediction model includes:
s8-1, acquiring historical working data of the rotary machine, selecting data with characteristics in a basic database as training data of a model, wherein the characteristics refer to information data of working environment of the rotary machine;
s8-2, taking the characteristic of certain data in the training data of the model as training input data, adding the interval duration of the lubricating grease as an execution result, and constructing an initial prediction model of the interval duration of the lubricating grease addition:
obtaining training input data and constructing a training input data set { (x)1，y1)、(x2，y2)、…、(xm，ym) In which x1、x2、…、xmRepresenting the characteristic data as an input vector; y is1、y2、…、ymRepresenting an execution result, indicating the interval duration of adding lubricating grease twice, and being an output variable; m is the number of samples, representing the number of training input data for training;
constructing a loss function L (y)i(x), a least squares loss function as a loss function;
wherein f (x) represents an approximation function, the approximation function f (x) being such that the loss function L (y)iF (x)) is minimal;
initializing a make-loss function L (y)iF (x)) minimum weak learner f0(x)；
Wherein c is a constant value estimated to minimize the loss function, and is a tree with only one root node; y isi∈y1、y2、…、ym；
Iteratively training a weak learner, wherein the maximum iteration number is T;
obtaining a strong learner obtained by the t-th round of training:
wherein T represents the run, T ═ 1, 2, …, T;
for each training inputData samples, respectively calculating their negative gradients rti：
Wherein, f (x)i) The function represented is the function of the previous iteration, i.e. in the training round t, the function used is the function of round t-1, xi∈x1、x2、…、xm，
Represents a differential;
using negative gradient rtiFitting the regression tree to obtain the t regression tree with the corresponding leaf node region as Rtj，j＝1，2，…，m；
Obtaining the best fitting value ctj：
Adding the weak learner into the trained model to obtain a new strong learner:
wherein f ist-1(x) Strong learner for the t-1 st round of training, ft(x) A strong learner obtained for the t-th round of training; i for reaction with ctjPartial combination, which represents the decision tree fitting function of the current round;
after the circulation is finished, the final strong learner f is obtainedt(x) And the initial prediction model is used as the initial prediction model of the time interval of the grease addition.
In step S3, the method further includes:
construction date K1，K1The date of adding the lubricating grease to the rotary machine is obtained according to the initial prediction model of the lubricating grease adding interval duration;
obtaining K1The idle construction period duration a of the project where the rotating machinery is located on the date1；
Obtaining the disassembly and assembly time length a of the rotary machine in the process of adding the lubricating grease2；
If a1Greater than a2Normally adding lubricating grease according to an initial prediction model of the lubricating grease adding interval duration; if a1Is less than a2Constructing an error value B1Outputting an adjusted lubricating grease adding interval duration initial prediction model as ft(x)-B1。
In step S4, the method further includes:
acquiring a newly added engineering project;
acquiring the time length a required by the newly added engineering project3；
If a1-a3Greater than a2Normally adding lubricating grease according to an initial prediction model of the lubricating grease adding interval duration; if a1Greater than a2And a is1-a3Is less than a2Constructing an error value B2Outputting an adjusted lubricating grease adding interval duration initial prediction model as ft(x)-B2。
In this embodiment:
the rotating machinery is marked as a bearing;
acquiring information data of a working environment of the rotary machine, and constructing a basic database;
the rotary machine working environment information data comprises working environment temperature, working environment pollution level, rotary machine noise data and rotary machine vibration data;
acquiring historical working data of the rotary machine and interval duration of adding lubricating grease;
constructing model training data according to historical working data of the rotary machine and interval duration of adding lubricating grease;
taking the characteristic of certain data in training data as training input data, taking the interval duration of adding lubricating grease as an execution result, and constructing an initial prediction model of the interval duration of adding lubricating grease:
obtaining training input data and constructing a training input data set { (x)1，y1)、(x2，y2)、…、(xm，ym) In which x1、x2、…、xmRepresenting the characteristic data as an input vector; y is1、y2、…、ymRepresenting an execution result, indicating the interval duration of adding lubricating grease twice, and being an output variable; m is the number of samples, representing the number of training input data for training;
constructing a loss function L (y)i(x), a least squares loss function as a loss function;
then there are:
wherein f (x) represents an approximation function, the approximation function f (x) being such that the loss function L (y)iF (x)) is minimal;
initializing a make-loss function L (y)iF (x)) minimum weak learner f0(x)；
Wherein c is a constant value estimated to minimize the loss function, and is a tree with only one root node; y isi∈y1、y2、…、ym；
Iteratively training a weak learner, wherein the maximum iteration time is T, and T is 7;
obtaining a strong learner obtained by the t-th round of training:
wherein T represents the run, T ═ 1, 2, …, T;
for each training input data sample, programming by means of matlab software, and calculating the negative gradient r of the input code respectivelyti：
When t is 7, the negative gradient rti：
Wherein, f (x)i) The function represented is the function of the previous iteration, i.e. in the 7 th training, the function used is the function of the 6 th round, xi∈x1、x2、…、xm，
Represents a differential;
using negative gradient rtiFitting the regression tree to obtain the t regression tree with the corresponding leaf node region as Rtj，j＝1，2，…，m；
Obtaining the best fitting value ctj：
Adding the weak learner into the trained model to obtain a new strong learner:
wherein f is6(x) Strong learner for run 6, f7(x) A strong learner for the 7 th round of training; i for reaction with ctjPartial combination, which represents the decision tree fitting function of the current round;
after the circulation is finished, the final strong learner f is obtained7(x) It has reached the set maximum number of iterations and is therefore used as the initial prediction model for the duration of the grease addition interval.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus 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 apparatus.
Finally, it should be noted that: although the present invention has been described in detail with reference to the foregoing embodiments, it will be apparent to those skilled in the art that changes may be made in the embodiments and/or equivalents thereof without departing from the spirit and scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The utility model provides a rotating machinery health monitoring system based on thing networking which characterized in that: the system comprises a working environment information monitoring module, a lubricating grease adding management module, an initial prediction module, an engineering project analysis module, a scheduling module and a rotary machine health monitoring module;
the working environment information monitoring module is used for acquiring working environment information data of the rotary machine and constructing a basic database, wherein the working environment information data of the rotary machine comprises working environment temperature, working environment pollution level, rotary machine noise data and rotary machine vibration data; the lubricating grease adding management module is used for acquiring historical working data of the rotary machine and lubricating grease adding interval duration; the initial prediction module is used for constructing a lubricating grease adding interval duration initial prediction model according to historical data and information data of a working environment of the rotary machine; the engineering project analysis module is used for acquiring engineering projects where the rotary machinery is located and the construction period duration of each engineering project; the scheduling module is used for acquiring a newly added engineering project, constructing a dynamic scheduling method and adjusting an initial prediction model of the lubricating grease adding interval duration; the rotating machine health monitoring module is used for monitoring the health state of the rotating machine in real time;
the output end of the working environment information monitoring module is connected with the input end of the lubricating grease adding management module; the output end of the lubricating grease adding management module is connected with the input end of the initial prediction module; the output end of the initial prediction module is connected with the input end of the engineering project analysis module; the output end of the engineering project analysis module is connected with the input end of the scheduling module; the output end of the dispatching module is connected with the input end of the rotating machinery health monitoring module.
2. The rotary machine health monitoring system based on the internet of things of claim 1, wherein: the working environment information monitoring module comprises a working environment temperature monitoring unit, a working environment pollution level judging unit, a rotating mechanical noise data acquisition unit and a rotating mechanical vibration data acquisition unit;
the working environment temperature monitoring unit is used for monitoring the working environment temperature condition of the rotary machine; the working environment pollution level judging unit is used for judging the pollution level of the working environment according to national standards; the rotary machine noise data acquisition unit monitors noise data of the rotary machine by using an instrument; the rotary machine vibration data acquisition unit acquires vibration data of the rotary machine by using an instrument;
the output ends of the working environment temperature monitoring unit, the working environment pollution level judging unit, the rotating mechanical noise data acquisition unit and the rotating mechanical vibration data acquisition unit are connected with the input end of the lubricating grease adding management module.
3. The rotary machine health monitoring system based on the internet of things of claim 1, wherein: the lubricating grease adding management module comprises a historical data unit and a lubricating grease adding unit;
the historical data unit is used for acquiring historical working data of the rotary machine; the lubricating grease adding unit is used for acquiring the interval duration of adding lubricating grease to the rotary machine;
the output end of the historical data unit is connected with the input end of the initial prediction module; and the output end of the lubricating grease adding unit is connected with the input end of the initial prediction module.
4. The rotary machine health monitoring system based on the internet of things of claim 1, wherein: the initial prediction module comprises a model construction unit and a prediction output unit;
the model construction unit is used for constructing an initial prediction model of the lubricating grease adding interval duration according to historical data and the information data of the working environment of the rotary machine; the prediction output unit is used for outputting the predicted interval time for adding the lubricating grease to the rotating machinery according to the initial prediction model for the interval time for adding the lubricating grease;
the output end of the model building unit is connected with the input end of the prediction output unit; and the output end of the prediction output unit is connected with the input end of the engineering project analysis module.
5. The rotary machine health monitoring system based on the internet of things of claim 1, wherein: the scheduling module comprises a newly-added item acquisition unit and a dynamic scheduling unit;
the newly-added project acquisition unit is used for acquiring newly-added project; the dynamic scheduling unit is used for constructing a dynamic scheduling method and adjusting an initial prediction model of the lubricating grease adding interval duration;
the output end of the newly-added item acquisition unit is connected with the input end of the dynamic scheduling unit; and the output end of the dynamic scheduling unit is connected with the input end of the rotating machinery health monitoring module.
6. A rotating machinery health monitoring method based on the Internet of things is characterized in that: the method comprises the following steps:
s1, acquiring the information data of the working environment of the rotary machine, and constructing a basic database;
s2, obtaining historical working data of the rotary machine and interval duration of adding lubricating grease, and constructing an initial prediction model of the interval duration of adding the lubricating grease according to a basic database;
s3, acquiring engineering projects where the rotary machinery is located, acquiring the construction period duration of each engineering project, and calculating the adding mode of the lubricating grease;
s4, acquiring a newly added engineering project, constructing a dynamic scheduling method, adjusting a lubricating grease adding interval duration initial prediction model, constructing a rotary machine health monitoring module based on the adjusted lubricating grease adding interval duration initial prediction model, and monitoring the running state of the rotary machine.
7. The rotating machinery health monitoring method based on the internet of things as claimed in claim 6, wherein: in step S1, the rotating machine work environment information data includes a work environment temperature, a work environment pollution level, rotating machine noise data, and rotating machine vibration data.
8. The rotating machinery health monitoring method based on the internet of things as claimed in claim 7, wherein: in step S2, the constructing the grease addition interval duration initial prediction model includes:
s8-1, acquiring historical working data of the rotary machine, selecting data with characteristics in a basic database as training data of a model, wherein the characteristics refer to information data of working environment of the rotary machine;
s8-2, taking the characteristic of certain data in the training data of the model as training input data, adding the interval duration of the lubricating grease as an execution result, and constructing an initial prediction model of the interval duration of the lubricating grease addition:
obtaining training input data and constructing a training input data set { (x)1，y1)、(x2，y2)、…、(xm，ym) In which x1、x2、…、xmRepresenting the characteristic data as an input vector; y is1、y2、…、ymRepresenting an execution result, indicating the interval duration of adding lubricating grease twice, and being an output variable; m is the number of samples, representing the number of training input data for training;
constructing a loss function L (y)i(x), a least squares loss function as a loss function;
wherein f (x) represents an approximation function, the approximation function f (x) being such that the loss function L (y)iF (x)) is minimal;
initializing a make-loss function L (y)iF (x)) minimum weak learner f0(x)；
Where c is a constant value estimated to minimize the loss function, a tree with only one root node: y isi∈y1、y2、…、ym；
Iteratively training a weak learner, wherein the maximum iteration number is T;
obtaining a strong learner obtained by the t-th round of training:
wherein T represents the run, T ═ 1, 2, …, T;
for each training input data sample, calculating its negative gradient rti：
Wherein, f (x)i) The function represented is the function of the previous iteration, i.e. in the training round t, the function used is the function of round t-1, xi∈x1、x2、…、xm，
Represents a differential;
using negative gradient rtiFitting the regression tree to obtain the t regression tree with the corresponding leaf node region as Rtj，j＝1，2，…，m；
Obtaining the best fitting value ctj：
Adding the weak learner into the trained model to obtain a new strong learner:
wherein f ist-1(x) Strong learner for the t-1 st round of training, ft(x) A strong learner obtained for the t-th round of training; i for reaction with ctjPartial combination, which represents the decision tree fitting function of the current round;
after the circulation is finished, the final strong learner f is obtainedt(x) And the initial prediction model is used as the initial prediction model of the time interval of the grease addition.
9. The rotating machinery health monitoring method based on the internet of things as claimed in claim 8, wherein: in step S3, the method further includes:
construction date K1，K1The date of adding the lubricating grease to the rotary machine is obtained according to the initial prediction model of the lubricating grease adding interval duration;
obtaining K1The idle construction period duration a of the project where the rotating machinery is located on the date1；
Obtaining the disassembly and assembly time length a of the rotary machine in the process of adding the lubricating grease2；
If a1Greater than a2Normally adding lubricating grease according to an initial prediction model of the lubricating grease adding interval duration; if a1Is less than a2Constructing an error value B1Outputting the adjusted lubricating greaseAdding an initial prediction model of interval duration of ft(x)-B1。
10. The rotating machinery health monitoring method based on the internet of things as claimed in claim 9, wherein: in step S4, the method further includes:
acquiring a newly added engineering project;
acquiring the time length a required by the newly added engineering project3；
If a1-a3Greater than a2Normally adding lubricating grease according to an initial prediction model of the lubricating grease adding interval duration; if a1Greater than a2And a is1-a3Is less than a2Constructing an error value B2Outputting an adjusted lubricating grease adding interval duration initial prediction model as ft(x)-B2。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111601202.8A CN114278397B (en) | 2021-12-24 | 2021-12-24 | Rotating machine health monitoring system and method based on Internet of things |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111601202.8A CN114278397B (en) | 2021-12-24 | 2021-12-24 | Rotating machine health monitoring system and method based on Internet of things |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114278397A true CN114278397A (en) | 2022-04-05 |
| CN114278397B CN114278397B (en) | 2022-08-19 |
Family
ID=80875149
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111601202.8A Active CN114278397B (en) | 2021-12-24 | 2021-12-24 | Rotating machine health monitoring system and method based on Internet of things |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114278397B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116661543A (en) * | 2023-07-28 | 2023-08-29 | 常州满旺半导体科技有限公司 | Intelligent regulation system and method based on low-power consumption voltage source |
| CN116822323A (en) * | 2023-03-06 | 2023-09-29 | 江苏金鹏航天智能装备有限公司 | Laser spot monitoring system and method based on Internet of things |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7134323B1 (en) * | 1998-04-02 | 2006-11-14 | Rockwell Automation Technologies, Inc. | System and method for dynamic lubrication adjustment for a lubrication analysis system |
| JP2010182287A (en) * | 2008-07-17 | 2010-08-19 | Steven C Kays | Intelligent adaptive design |
| WO2014043623A1 (en) * | 2012-09-17 | 2014-03-20 | Siemens Corporation | Log-based predictive maintenance |
| CN107862108A (en) * | 2017-10-12 | 2018-03-30 | 成都阜特科技股份有限公司 | A kind of industrial machinery health status analysis and Forecasting Methodology and its system |
| CN111274737A (en) * | 2020-02-25 | 2020-06-12 | 山东大学 | Method and system for predicting remaining service life of mechanical equipment |
| US20200272139A1 (en) * | 2019-02-21 | 2020-08-27 | Abb Schweiz Ag | Method and System for Data Driven Machine Diagnostics |
| CN112129928A (en) * | 2020-11-18 | 2020-12-25 | 震坤行网络技术(南京)有限公司 | Method, computing device and computer storage medium for detecting state of lubricating oil |
| CN112580153A (en) * | 2020-12-29 | 2021-03-30 | 成都运达科技股份有限公司 | Health state management system and method for vehicle running gear monitoring component |
| CN113221280A (en) * | 2021-05-14 | 2021-08-06 | 西安交通大学 | Rolling bearing modeling and model updating method and system based on digital twinning |
| CN113449473A (en) * | 2021-06-29 | 2021-09-28 | 南京工业大学 | Wind power bearing degradation trend prediction method, system and device based on DFCAE-BilSTM |
-
2021
- 2021-12-24 CN CN202111601202.8A patent/CN114278397B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7134323B1 (en) * | 1998-04-02 | 2006-11-14 | Rockwell Automation Technologies, Inc. | System and method for dynamic lubrication adjustment for a lubrication analysis system |
| JP2010182287A (en) * | 2008-07-17 | 2010-08-19 | Steven C Kays | Intelligent adaptive design |
| WO2014043623A1 (en) * | 2012-09-17 | 2014-03-20 | Siemens Corporation | Log-based predictive maintenance |
| CN107862108A (en) * | 2017-10-12 | 2018-03-30 | 成都阜特科技股份有限公司 | A kind of industrial machinery health status analysis and Forecasting Methodology and its system |
| US20200272139A1 (en) * | 2019-02-21 | 2020-08-27 | Abb Schweiz Ag | Method and System for Data Driven Machine Diagnostics |
| CN111274737A (en) * | 2020-02-25 | 2020-06-12 | 山东大学 | Method and system for predicting remaining service life of mechanical equipment |
| CN112129928A (en) * | 2020-11-18 | 2020-12-25 | 震坤行网络技术(南京)有限公司 | Method, computing device and computer storage medium for detecting state of lubricating oil |
| CN112580153A (en) * | 2020-12-29 | 2021-03-30 | 成都运达科技股份有限公司 | Health state management system and method for vehicle running gear monitoring component |
| CN113221280A (en) * | 2021-05-14 | 2021-08-06 | 西安交通大学 | Rolling bearing modeling and model updating method and system based on digital twinning |
| CN113449473A (en) * | 2021-06-29 | 2021-09-28 | 南京工业大学 | Wind power bearing degradation trend prediction method, system and device based on DFCAE-BilSTM |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116822323A (en) * | 2023-03-06 | 2023-09-29 | 江苏金鹏航天智能装备有限公司 | Laser spot monitoring system and method based on Internet of things |
| CN116822323B (en) * | 2023-03-06 | 2023-11-14 | 江苏金鹏航天智能装备有限公司 | Laser spot monitoring system and method based on Internet of things |
| CN116661543A (en) * | 2023-07-28 | 2023-08-29 | 常州满旺半导体科技有限公司 | Intelligent regulation system and method based on low-power consumption voltage source |
| CN116661543B (en) * | 2023-07-28 | 2023-10-20 | 常州满旺半导体科技有限公司 | Intelligent regulation system and method based on low-power consumption voltage source |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114278397B (en) | 2022-08-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114278397B (en) | Rotating machine health monitoring system and method based on Internet of things | |
| Zhou et al. | A novel grey prognostic model based on Markov process and grey incidence analysis for energy conversion equipment degradation | |
| CN108920863B (en) | Method for establishing energy consumption estimation model of robot servo system | |
| CN107391542B (en) | Open source software community expert recommendation method based on file knowledge graph | |
| Welte et al. | Models for lifetime estimation: an overview with focus on applications to wind turbines | |
| Xie | Explanations about grey information and framework of grey system modeling | |
| CN103310051A (en) | Method for predicting failure rate of vehicle-mounted information terminal in entire life cycle | |
| Ji et al. | Solving high-order uncertain differential equations via Runge–Kutta method | |
| CN113627032B (en) | Intelligent decision-making method for equipment design/maintenance scheme based on digital twinning | |
| CN111860899A (en) | Motor operation and maintenance method, device, electronic equipment and system | |
| CN113793227A (en) | Human-like intelligent perception and prediction method for social network events | |
| CN111460275B (en) | Social network-oriented dynamic network representation learning method and system | |
| CN107609669A (en) | Forecasting Methodology and device, the Wind turbines bearing stuffing system of bearing stuffing amount | |
| Bergs et al. | Novel method for online wear estimation of centrifugal pumps using multi-fidelity modeling | |
| CN113807027A (en) | Health state evaluation model, method and system for wind turbine generator | |
| Kolodenkova et al. | Technical diagnostics of industrial equipment based on soft computing technologies | |
| Akbar Ghafouri Rokn Abadi | Constrained model predictive control of low-power industrial gas turbine | |
| Sivadas et al. | Fermatean Fuzzy Interactive Aggregation Operators and their Application to Decision-making. | |
| CN117117858B (en) | Wind turbine generator power prediction method, device and storage medium | |
| CN114791357B (en) | Transmission fault monitoring method and system for wind power gear box | |
| Biard et al. | Reliability Assessment of an Electrical Network with Digital Twins | |
| Jin et al. | Overview of Research on Health Assessment and Fault Prediction of Complex Equipment Driven by Big Data | |
| CN113240162B (en) | Hospital energy consumption prediction method based on EEMD-Prophet algorithm | |
| Zhang et al. | Joint probability inference algorithms of a Bayesian network and reliability analysis of electronic products | |
| Li et al. | A novel fuzzy time series model based on fuzzy logical relationships tree |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |