CN115906437A - Fan state determination method, device, equipment and storage medium - Google Patents

Fan state determination method, device, equipment and storage medium Download PDF

Info

Publication number
CN115906437A
CN115906437A CN202211376367.4A CN202211376367A CN115906437A CN 115906437 A CN115906437 A CN 115906437A CN 202211376367 A CN202211376367 A CN 202211376367A CN 115906437 A CN115906437 A CN 115906437A
Authority
CN
China
Prior art keywords
fan
characteristic data
data
historical
evaluation index
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
Application number
CN202211376367.4A
Other languages
Chinese (zh)
Inventor
李治
邓志成
丁刚
方超
汪勇
王帝
孙猛
陈家颖
谷朋泰
张强
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Shanghai Power Equipment Research Institute Co Ltd
Original Assignee
Shanghai Power Equipment Research Institute Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Shanghai Power Equipment Research Institute Co Ltd filed Critical Shanghai Power Equipment Research Institute Co Ltd
Priority to CN202211376367.4A priority Critical patent/CN115906437A/en
Publication of CN115906437A publication Critical patent/CN115906437A/en
Pending legal-status Critical Current

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
    • Y02E10/70—Wind energy
    • Y02E10/72—Wind turbines with rotation axis in wind direction

Abstract

The invention discloses a method, a device, equipment and a storage medium for determining a fan state. The method comprises the following steps: acquiring a characteristic data set of a fan to be evaluated, wherein the characteristic data set of the fan to be evaluated comprises the following steps: fan data, boiler data, and generator set data; screening the characteristic data set of the fan to be evaluated according to the evaluation index to obtain a target characteristic data set; and determining the state information of the fan to be evaluated according to the target characteristic data set. According to the embodiment of the invention, when the health degree of the fan is evaluated by determining the running state of the fan, the relevance among the fan, the boiler and the generator set is considered, the obtained characteristic data is more comprehensive, and a reasonable evaluation index is determined, so that the state of the fan is more accurately and effectively determined, and the safe and reliable running of the fan is favorably ensured.

Description

Fan state determination method, device, equipment and storage medium
Technical Field
The invention relates to the technical field of power generation equipment, in particular to a method, a device, equipment and a storage medium for determining a fan state.
Background
The three fans of the thermal power plant comprise a blower, a primary fan and an induced draft fan. The primary fan and the air feeder mainly provide primary air quantity containing coal dust, secondary air quantity and air temperature required by combustion for the boiler, and stable combustion of a hearth is ensured; the induced draft fan is used for pumping out the flue gas of the boiler and maintaining the negative pressure of the boiler. The fan is used as an important auxiliary machine of a thermal power plant, the operation state of the fan is closely related to the safety and the economy of the generator set, serious faults can cause the unplanned shutdown of the generator set, and the attention degree of the fan is still low.
At present, most scholars at home and abroad make some state evaluation researches on fan equipment based on analytical models, expert systems and data driving methods, but the researches mainly focus on the vibration state and the fault of the fan, do not evaluate the health state of the fan in real time, and lack the coupling evaluation with the states of a generator set and a boiler. At present, problems are found mainly according to fixed threshold value alarm of partial operation parameters of the fan in the operation process of the fan, and a user carries out analysis and diagnosis according to experience and provides a processing scheme.
However, the actual operation state of the power station fan changes along with the operation scheduling of the generator set, and the traditional health state fixed threshold value monitoring method cannot be used for health state evaluation of the fan under different working conditions. Meanwhile, the traditional threshold method is mostly used for distinguishing the normality and the abnormality of the health state of the fan, quantitative analysis of the internal health degree of the fan is not carried out, misjudgment is easily caused, and quantitative evaluation of the health degree of the running state of the fan cannot be accurately and effectively realized. The evaluation of the health state of the power station fan mainly has the following difficulties: the fan has multiple types, complex structure, bad operation condition and various states; the relation among the running parameters of the fan is complex, and the fan has a strong nonlinear relation; the number of various measuring points of the fan is limited, the operation data is incomplete, and a relatively complete health degree evaluation method is not provided; an analysis and diagnosis model of the fan fault is not established yet, and the analysis and diagnosis model is used for quick positioning and reason analysis of the fault and provides a feasible processing scheme. Therefore, the accurate and effective health degree quantitative evaluation method based on the running state of the power station ventilator is beneficial to guaranteeing safe and reliable running of the ventilator.
Disclosure of Invention
The invention provides a fan state determination method, a fan state determination device, fan state determination equipment and a storage medium, so that the state of a fan can be more accurately and effectively determined, and the safe and reliable operation of the fan is guaranteed.
According to an aspect of the present invention, there is provided a method for determining a state of a wind turbine, the method including:
acquiring a characteristic data set of a fan to be evaluated, wherein the characteristic data set of the fan to be evaluated comprises the following steps: fan data, boiler data, and generator set data;
screening the characteristic data set of the fan to be evaluated according to the evaluation index to obtain a target characteristic data set;
and determining the state information of the fan to be evaluated according to the target characteristic data set.
According to another aspect of the present invention, there is provided a fan status determination apparatus, including:
the first acquisition module is used for acquiring a characteristic data set of the fan to be evaluated, wherein the characteristic data set of the fan to be evaluated comprises: fan data, boiler data, and generator set data;
the screening module is used for screening the characteristic data set of the fan to be evaluated according to the evaluation index to obtain a target characteristic data set;
and the determining module is used for determining the state information of the fan to be evaluated according to the target characteristic data set.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the method of determining a condition of a wind turbine according to any of the embodiments of the present invention.
According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to implement the method for determining a state of a fan according to any of the embodiments of the present invention when the computer instructions are executed.
According to the technical scheme of the embodiment of the invention, the characteristic data set of the fan to be evaluated is obtained, wherein the characteristic data set of the fan to be evaluated comprises the following steps: the method comprises the steps of screening a characteristic data set of a fan to be evaluated according to evaluation indexes to obtain a target characteristic data set, determining state information of the fan to be evaluated according to the target characteristic data set, solving the problem that the state of the fan, the generator set and the boiler is not evaluated in the prior art, considering the relevance of the fan, the boiler and the generator set, obtaining more comprehensive characteristic data, enabling the determination of the state of the fan to be more accurate and effective, and achieving the beneficial effect of being beneficial to guaranteeing safe and reliable operation of the fan.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor delineate the scope of the present invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
Fig. 1 is a flowchart of a method for determining a fan status according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a fan status determining apparatus according to a second embodiment of the present invention;
fig. 3 is a schematic structural diagram of an electronic device implementing the method for determining a fan state according to the embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, 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.
It should be noted that the terms "first," "target," and the like in the description and claims of the present invention and in the above-described drawings are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in other sequences than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Fig. 1 is a flowchart of a fan status determination method according to an embodiment of the present invention, where the present embodiment is applicable to a fan status determination situation, and the method may be executed by a fan status determination device, where the fan status determination device may be implemented in a form of hardware and/or software, and the fan status determination device may be integrated in any electronic device providing a fan status determination function. As shown in fig. 1, the method includes:
s101, acquiring a characteristic data set of the fan to be evaluated.
In this embodiment, the wind turbine to be evaluated may be a generic term of three wind turbines of a thermal power plant. The three fans of the thermal power plant comprise a blower, a primary fan and an induced draft fan, wherein the primary fan and the blower mainly provide primary air quantity containing pulverized coal, secondary air quantity and air temperature required by combustion for a boiler, so that stable combustion of a hearth is ensured; the draught fan takes out the flue gas of boiler, plays the effect of maintaining boiler negative pressure. Specifically, the fan may be composed of a fan component, a motor component, an oil system component, a frequency converter component, and the like.
It should be noted that the characteristic data set of the fan to be evaluated may be a characteristic data set composed of characteristic data of the fan to be evaluated, acquired in real time, characteristic data of a boiler associated with the fan to be evaluated, and characteristic data of a generator set associated with the fan to be evaluated.
Wherein, the characteristic data set of the fan that awaits appraising includes: fan data, boiler data, and generator group data.
In the present embodiment, the blower data may include characteristic data of the blower, the primary blower, and the induced draft fan. Exemplary blower characteristic data may include: secondary air quantity, air pressure, air temperature, opening degree of a damper baffle and the like; the characteristic data of the primary air fan can comprise: primary air quantity, air pressure, air temperature, opening degree of a damper and the like; the characteristic data of the induced draft fan can comprise: flue gas flow, wind pressure, wind temperature, opening degree of a damper and the like. In this embodiment, the fan data further includes online data, point inspection data, and intelligent early warning data characteristic data of the operating state of each component of the single fan. For example, the fan data may include: characteristic data of fan components, characteristic data of motor components, characteristic data of oil system components, characteristic data of frequency converter components and the like. Specifically, the characteristic data of the fan component may include: data such as the angle of the movable blade, inlet pressure, inlet air temperature, outlet pressure, outlet air temperature, bearing temperature, oil temperature and bearing vibration; the characteristic data of the motor component may include: current, stator winding temperature, bearing vibration and other data; the characteristic data of the oil system component may include: oil temperature, lubricating oil pump oil pressure, regulating oil pump oil pressure, oil tank oil level, oil tank oil temperature and other data; the characteristic data of the frequency conversion device components may include: current, voltage, frequency, rotational speed, temperature, etc.
In this embodiment, the boiler data may be characteristic data of a boiler associated with the fan to be evaluated. For example, the boiler data may be the evaporation capacity of the boiler, the total fuel capacity, the main steam flow and the total smoke air flow. The generator set data may be characteristic data of the generator set associated with the wind turbine to be evaluated. For example, the genset data may be real power data of a genset.
Specifically, a characteristic data set of the fan to be evaluated is obtained in a mode of acquiring data of a SIS (Supervisory Information System) System and a PMS (Power production Management System) System in real time through a data interface, wherein the characteristic data set of the fan to be evaluated comprises fan data, boiler data and generator group data.
And S102, screening the characteristic data set of the fan to be evaluated according to the evaluation index to obtain a target characteristic data set.
It should be explained that the evaluation index may be characteristic data selected by a certain rule for characterizing the health degree of the wind turbine. The evaluation index may be, for example, characteristic data of the fan such as vibration, bearing temperature, oil pressure, motor stator winding temperature, fan flow, pressure, and efficiency.
In this embodiment, the screening operation may be to reserve feature data belonging to an evaluation index in a feature data set of the fan to be evaluated, and remove feature data not belonging to the evaluation index. In the actual operation process, some feature data in the feature data set of the fan to be evaluated, which are obtained, may exceed the feature data concerned by the embodiment of the present invention in the feature dimension, and may also exceed the normal operation state of the fan concerned by the embodiment of the present invention in the sample number dimension, so that the feature data need to be subjected to screening operation.
The target characteristic data set can be a characteristic data set of the fan to be evaluated, wherein the characteristic data belonging to the evaluation index in the characteristic data set of the fan to be evaluated are reserved, and the characteristic data not belonging to the evaluation index are removed.
Specifically, the feature data set of the fan to be evaluated is screened according to the evaluation index, for example, feature data belonging to the evaluation index in the feature data set of the fan to be evaluated may be retained, and feature data not belonging to the evaluation index may be removed to obtain a target feature data set.
S103, determining the state information of the fan to be evaluated according to the target characteristic data set.
It should be noted that the state information of the fan to be evaluated may be health state information of the fan to be evaluated, and the state information of the fan to be evaluated may be, for example, that the fan to be evaluated operates normally, or that the fan to be evaluated is abnormal, and if the fan to be evaluated is abnormal, it is specific which component of the fan to be evaluated is abnormal, and the like.
Specifically, the characteristic data in the target characteristic data set is calculated according to a certain rule, and the state information of the fan to be evaluated is determined. In the actual operation process, the health degree of the fan to be evaluated can be evaluated according to the state information of the fan to be evaluated.
According to the technical scheme of the embodiment of the invention, the characteristic data set of the fan to be evaluated is obtained, wherein the characteristic data set of the fan to be evaluated comprises the following steps: the method comprises the steps of screening a characteristic data set of a fan to be evaluated according to evaluation indexes to obtain a target characteristic data set, determining state information of the fan to be evaluated according to the target characteristic data set, solving the problem that the state of the fan, a generator set and a boiler is not evaluated in the prior art, considering the relevance of the fan, the boiler and the generator set, obtaining more comprehensive characteristic data, enabling the state of the fan to be determined more accurately and effectively, and obtaining the beneficial effect of being beneficial to guaranteeing safe and reliable operation of the fan.
Optionally, before the feature data set of the fan to be evaluated is screened according to the evaluation index to obtain the target feature data set, the method further includes:
and performing cluster analysis on the historical fan characteristic data set to obtain a first characteristic data set corresponding to at least one fan operation condition.
In this embodiment, the historical wind turbine characteristic data set may be a characteristic data set composed of collected historical characteristic data of a wind turbine, historical characteristic data of a boiler associated with the wind turbine, and historical characteristic data of a generator set associated with the wind turbine. Wherein, the characteristic data set of the historical wind turbine can comprise: historical fan data, historical boiler data, and historical generator group data.
It should be noted that the clustering analysis may be to cluster the feature data in the historical fan feature data set into at least one feature data set corresponding to different types of fan operating conditions. The fan operation condition may be a condition where the fan is operated, for example, the fan operation condition may be a first fan operation condition, a second fan operation condition, a third fan operation condition or a fourth fan operation condition, and the characteristic parameters or values of the characteristic parameters corresponding to different fan operation conditions may be different.
The first characteristic data set can be a set formed by characteristic data corresponding to different fan operation conditions. For example, the first fan operation condition may correspond to the first characteristic data set a, the second fan operation condition may correspond to the first characteristic data set B, the third fan operation condition may correspond to the first characteristic data set C, and the fourth fan operation condition may correspond to the first characteristic data set D.
In the implementation process, historical operating data and point patrol data of the fans, boilers associated with the fans and generator sets associated with the fans can be screened and collected from a Distributed Control System (DCS) System, a System Information System (SIS) System, a System information System (PMS) System and other monitoring systems to form a historical fan characteristic data set. Some feature data in the historical wind turbine feature data set may exceed feature data concerned by the embodiment of the invention in a feature dimension, and may also exceed normal wind turbine operating conditions concerned by the embodiment of the invention in a sample number dimension, such as fault data, noise data, shutdown data, and the like. Therefore, characteristic data in a historical fan characteristic data set, such as switching value information of fan component states, operation modes, alarm signals and the like, need to be cleaned, the characteristic data are mainly used for judging control logics of the fan and the fan components, and for determining the fan state information, the discrete switching value data not only cause excessive redundancy of the characteristic data, but also reduce the accuracy of calculation, so the first step of data cleaning is to eliminate the switching value data. In addition, for measured value missing or overrun data caused by faults of some measuring points, the data lose value, and for the measuring points, characteristic data can be directly removed.
In the implementation process, the characteristic data in the historical fan characteristic data set after being cleaned is more, the dimensions of the characteristic data are not uniform, in order to reduce the influence of the numerical value and the dimensions of the characteristic data on the determination of the state information of the fan, normalization processing is performed on all the characteristic data, and the specific formula of the normalization processing process is as follows:
Figure BDA0003926727790000081
wherein the content of the first and second substances,
Figure BDA0003926727790000082
representing the numerical value of each feature data after the feature data in the historical fan feature data set is cleaned and subjected to normalization processing, wherein the numerical value is between 0 and 1; x represents an original numerical value of each characteristic data obtained after the characteristic data in the historical fan characteristic data set are cleaned; />
Figure BDA0003926727790000083
Representing the average value of the feature data after cleaning the feature data in the historical fan feature data set; and sigma represents the standard deviation of the characteristic data after the characteristic data in the historical fan characteristic data set are cleaned.
In the implementation process, after the characteristic data in the historical fan characteristic data set is cleaned, the characteristic data is normalized, and then the characteristic data is subjected to clustering analysis by adopting a density clustering algorithm. And according to the closeness degree of the data distribution of the historical generator set and the historical fan data, using the quantity of the characteristic data in the adjacent areas as the working condition communication standard of the association between the generator set and the fan, continuously expanding the association working condition cluster of the generator set and the fan based on the communication, and finally forming a fan operation working condition cluster structure based on the characteristic data of the generator set. And identifying and defining the type of the operating condition of the generator set according to the result of the data clustering analysis, and automatically judging the operating condition of the fan in the subsequent operation to obtain a first characteristic data set corresponding to at least one fan operating condition.
And obtaining the correlation strength values of the historical characteristic data of the fan component and the historical boiler data, the correlation strength values of the historical characteristic data of the fan component and the historical generator set data and the correlation strength values of the historical characteristic data of the fan component and the historical characteristic data of other fan components in the first characteristic data set corresponding to each fan operating condition.
The historical characteristic data of the fan component can be historical characteristic data of the component of the fan, the historical boiler data can be historical characteristic data of a boiler associated with the fan, the historical generator set data can be historical characteristic data of a generator set associated with the fan, and the historical characteristic data of other fan components can be historical characteristic data of other component of the fan.
It should be explained that the correlation intensity value may be a value of the intensity that exhibits a positive correlation or a negative correlation between two characteristic data. For example, when the feature data a is increased, the feature data B is also increased correspondingly, so that the feature data a and the feature data B show positive correlation, and if the increasing amplitudes of the two feature data are also the same, the correlation strength value of the feature data a and the feature data B may be 1.
Specifically, for historical characteristic data of the fan components in the first characteristic data set corresponding to each fan operation condition, a pearson correlation coefficient method is adopted to calculate correlation strength values of the historical characteristic data and historical boiler data, correlation strength values of the historical characteristic data and historical generator set data, and correlation strength values of the historical characteristic data and historical characteristic data of other fan components.
And determining an evaluation index according to the correlation strength values of the historical characteristic data of the fan component and the historical boiler data, the correlation strength values of the historical characteristic data of the fan component and the historical generator set data and the correlation strength values of the historical characteristic data of the fan component and the historical characteristic data of other fan components in the characteristic data set.
Specifically, the evaluation index is determined according to the correlation strength value of the historical characteristic data of the fan component in the characteristic data set with the historical boiler data, the correlation strength value of the historical generator set data and the absolute value of the Pearson correlation coefficient of the historical characteristic data of other fan components, the correlation strength value of the historical characteristic data of the fan component in the characteristic data set relative to the historical boiler data, the correlation strength value relative to the historical generator set data and the weight of the historical characteristic data relative to other fan components.
Optionally, determining an evaluation index according to the correlation strength value between the historical characteristic data of the fan component and the historical boiler data, the correlation strength value between the historical characteristic data of the fan component and the historical generator set data, and the correlation strength value between the historical characteristic data of the fan component and the historical characteristic data of other fan components in the characteristic data set includes:
and determining the weight of the historical characteristic data of the fan component relative to the historical boiler data, the weight of the historical characteristic data of the fan component relative to the historical generator set data and the weight of the historical characteristic data of the fan component relative to the historical characteristic data of other fan components in the characteristic data set according to the correlation strength value of the historical characteristic data of the fan component and the historical boiler data, the correlation strength value of the historical characteristic data of the fan component and the historical generator set data and the correlation strength value of the historical characteristic data of the fan component and the historical characteristic data of other fan components in the characteristic data set.
Specifically, the calculation formula of the weight of the historical characteristic data of the fan component relative to the historical boiler data in the characteristic data set is as follows:
Figure BDA0003926727790000101
wherein r is 1 (x) Representing the weight of historical characteristic data of a fan component in the characteristic data set relative to historical boiler data, x representing the original numerical value of each characteristic data after cleaning the characteristic data in the historical fan characteristic data set, a i1 A value representing the ith 1 st historical boiler data, wherein i1=1,2, …, l, wherein l represents the total number of historical boiler data,
Figure BDA0003926727790000111
and a correlation strength value representing historical characteristic data of the fan component in the characteristic data set and historical boiler data.
The calculation formula of the weight of the historical characteristic data of the fan component relative to the historical generator set data is as follows:
Figure BDA0003926727790000112
wherein r is 2 (x) Representing the weight of historical characteristic data of the fan components in the characteristic data set relative to historical generator set data, x representing the original numerical value of each characteristic data after cleaning the characteristic data in the historical fan characteristic data set, b i2 A value representing the ith 2 historical genset data, where i2=1,2, …, m, where m represents the total number of historical boiler data, r x,bi2 And a correlation strength value representing historical characteristic data of the fan component in the characteristic data set and historical generator set data.
The calculation formula of the weight of the historical characteristic data of the fan component relative to the historical characteristic data of other fan components is as follows:
Figure BDA0003926727790000113
wherein r is 3 (x) Representing the weight of historical characteristic data of the fan component in the characteristic data set relative to historical characteristic data of other fan components, x representing each original numerical value of the characteristic data after cleaning the characteristic data in the historical fan characteristic data set, c i3 A numerical value representing historical characteristic data of an i3 th other fan component, wherein i3=1,2, …, n, wherein n represents the total number of historical characteristic data of the other fan components,
Figure BDA0003926727790000114
the correlation strength values represent historical characteristic data of the fan component in the characteristic data set and historical characteristic data of other fan components.
And determining an evaluation index according to a preset weight threshold, the weight of the historical characteristic data of the fan component relative to the historical boiler data in the characteristic data set, the weight of the historical characteristic data of the fan component relative to the historical generator set data and the weight of the historical characteristic data of the fan component relative to the historical characteristic data of other fan components.
The preset weight threshold may be a weight of historical feature data of the fan component relative to historical boiler data, a weight of historical feature data of the fan component relative to historical power generation group data, and a weight of historical feature data of the fan component relative to historical feature data of other fan components in a feature data set by a user according to an actual situation, which is not limited in this embodiment. Preferably, the preset weight threshold may be, for example, 0.45.
Specifically, the evaluation index representing the health degree of the fan is selected according to a preset weight threshold, the weight of the historical characteristic data of the fan component relative to the historical boiler data in the characteristic data set, the weight of the historical characteristic data of the fan component relative to the historical power generation group data, and the weight of the historical characteristic data of the fan component relative to the historical characteristic data of other fan components. And separating the characteristic data, in which the weight of the historical characteristic data of the fan component relative to the historical boiler data, the weight of the historical characteristic data of the fan component relative to the historical generator set data and the weight of the historical characteristic data of the fan component relative to the historical characteristic data of other fan components are greater than a preset weight threshold (for example, 0.45), and removing redundant characteristic data to form a health degree evaluation index of the fan. Taking a draught fan as an example, the original 35 health degree evaluation indexes are reduced to 18 through weight calculation and redundancy removal, and the calculation amount is reduced.
Optionally, determining the state information of the fan to be evaluated according to the target characteristic data set includes:
and acquiring feature data corresponding to the limit value evaluation index in the target feature data set.
In the embodiment, the limit evaluation indexes may include fan health evaluation indexes such as vibration, bearing temperature, oil pressure, and motor stator winding temperature. Specifically, the limit type evaluation index may be classified into an upper limit alarm type limit type evaluation index and a lower limit alarm type limit type evaluation index. For example, the evaluation indexes such as vibration and temperature belong to the alarm type limit value class exceeding the upper limit, and the evaluation indexes such as oil pressure belong to the alarm type limit value class exceeding the lower limit.
Specifically, if the target feature data set has feature data corresponding to the limit class evaluation index, the feature data corresponding to the limit class evaluation index in the target feature data set is acquired.
And determining a limit value type evaluation index state value of the characteristic data according to the characteristic data, a preset fan state threshold value and a fan state threshold value corresponding to the characteristic data.
The preset fan state threshold value may be a value when the state information of the fan set by the user according to the actual situation is in four states, namely normal, attention, abnormal and severe, and this embodiment does not limit this value. Preferably, the state information of the fan may be set to four states, namely normal, attention, abnormal and severe states, the state information of the fan may be represented by a score of 0 to 100, and the value ranges of the four states may be: normal [100,H A ) Attention to [ H ] A ，H E ) Abnormal [ H ] E ,H S ) And severe [ H E ,0]。
The fan state threshold corresponding to the feature data may be a score value of an evaluation index determined by a user from the perspective of safe operation of the equipment when the state information of the fan is attention, abnormal, or serious according to an industry standard or an operation experience, which is not limited in this embodiment.
In this embodiment, the limit-type evaluation index state value of the feature data may be a state value of the feature data when the feature data in the target feature data set is the limit-type evaluation index.
Specifically, when the feature data corresponding to the limit evaluation index in the target feature data set is an alarm-type limit evaluation index exceeding an upper limit, a specific calculation formula for determining the limit evaluation index state value of the feature data according to the feature data, the preset fan state threshold and the fan state threshold corresponding to the feature data is as follows:
Figure BDA0003926727790000141
wherein H (x) represents a limit class evaluation index state value of the feature data when the feature data corresponding to the limit class evaluation index in the target feature data set is an alarm type limit class evaluation index exceeding the upper limit, x is an actual measurement value of the feature data corresponding to the limit class evaluation index in the target feature data set, H (x) represents a state value of the limit class evaluation index of the feature data corresponding to the alarm type limit class evaluation index exceeding the upper limit in the target feature data set, H (x) represents a state value of the limit class evaluation index exceeding the upper limit A Indicating that the state information of the fan in the preset fan state threshold is the threshold when attention is paid, H E A threshold value H indicating that the state information of the fan is abnormal in the preset fan state threshold value S A threshold value X representing a condition of the fan in a preset fan condition threshold value when the condition information of the fan is serious A Indicating that the state information of the fan in the fan state threshold corresponding to the characteristic data is the threshold when attention is paid, X E A threshold value X representing that the state information of the fan is abnormal in the fan state threshold value corresponding to the characteristic data S And indicating a threshold value when the state information of the fan in the fan state threshold values corresponding to the characteristic data is serious.
When the feature data corresponding to the threshold value type evaluation index in the target feature data set is the lower limit alarm type threshold value type evaluation index, determining a specific calculation formula of the threshold value type evaluation index state value of the feature data according to the feature data, the preset fan state threshold value and the fan state threshold value corresponding to the feature data as follows:
Figure BDA0003926727790000151
wherein H' (x) represents a limit class evaluation index state value of the feature data when the feature data corresponding to the limit class evaluation index in the target feature data set is the lower limit alarm type limit class evaluation index, x is an actual measurement value of the feature data corresponding to the limit class evaluation index in the target feature data set, H A Threshold value for indicating that state information of fan in preset fan state threshold value is attention，H E A threshold value H indicating that the state information of the fan in the preset fan state threshold value is abnormal S Representing a threshold value X 'of the preset fan state threshold value when the state information of the fan is serious' A Indicating that the state information of the fan in the fan state threshold value corresponding to the characteristic data is the threshold value X 'when attention is given' E A threshold value X 'indicating that the state information of the fan in the fan state threshold value corresponding to the characteristic data is abnormal' S And indicating a threshold value when the state information of the fan in the fan state threshold value corresponding to the characteristic data is serious.
And determining the state information of the fan to be evaluated according to the limit value type evaluation index state value of the characteristic data.
Specifically, feature data corresponding to a limit evaluation index in a target feature data set are obtained, a limit evaluation index state value result of the feature data is calculated, and state information of the fan to be evaluated is determined.
Optionally, determining the state information of the fan to be evaluated according to the target feature data set includes:
and acquiring characteristic data corresponding to the performance type evaluation indexes in the target characteristic data set.
In this embodiment, the performance evaluation index may include fan health evaluation indexes such as fan flow, pressure, and efficiency.
Specifically, if the target feature data set has feature data corresponding to the performance type evaluation index, the feature data corresponding to the performance type evaluation index in the target feature data set is obtained.
And determining a first deviation value of the characteristic data according to the characteristic data and the first numerical value corresponding to the characteristic data.
It should be explained that the first numerical value corresponding to the feature data may be a theoretical calculation value of the feature data corresponding to the performance class evaluation index in the target feature data set. And the first numerical value corresponding to the characteristic data is obtained by inputting the characteristic data into the target model. In this embodiment, the target model may be a wind turbine mechanism model.
The first deviation value of the feature data may be a deviation value of the feature data of the performance class evaluation index.
Specifically, the specific calculation formula for determining the first deviation value of the feature data according to the feature data and the first numerical value corresponding to the feature data is as follows:
Figure BDA0003926727790000161
where δ denotes a first deviation value of the feature data, x denotes an actual measurement value of the feature data corresponding to the performance class evaluation index in the target feature data set, and x denotes a second deviation value of the feature data cal And expressing a first numerical value corresponding to the characteristic data, namely, a theoretical calculation value of the characteristic data corresponding to the performance class evaluation index in the target characteristic data set.
And determining the performance type evaluation index state value of the characteristic data according to the first deviation value of the characteristic data, the preset fan state threshold and the fan state first deviation threshold corresponding to the characteristic data.
The first deviation threshold of the fan state corresponding to the characteristic data may be a score value of an evaluation index determined by a user from an operation performance perspective according to the fan mechanism model when the state information of the fan is attention, abnormal, and serious, which is not limited in this embodiment.
In this embodiment, the performance class evaluation index state value of the feature data may be a state value of the feature data when the feature data in the target feature data set is the performance class evaluation index.
Specifically, the specific calculation formula for determining the performance class evaluation index state value of the feature data according to the first deviation value of the feature data, the preset fan state threshold value and the fan state first deviation threshold value corresponding to the feature data is as follows:
Figure BDA0003926727790000171
wherein H δ (x) A performance class evaluation index state value representing the characteristic data, delta representing a first deviation value of the characteristic data, H A A threshold value H indicating that the state information of the fan in the preset fan state threshold value is attention E A threshold value H indicating that the state information of the fan is abnormal in the preset fan state threshold value S A threshold value, δ, representing a condition of the fan in the preset fan condition threshold value when the condition information of the fan is serious A Indicating that the state information of the fan in the first deviation threshold value of the fan state corresponding to the characteristic data is the threshold value delta when attention is paid E A threshold value, delta, indicating that the state information of the fan is abnormal in the first deviation threshold value of the fan state corresponding to the characteristic data S And indicating a threshold value when the state information of the fan is serious in the first deviation threshold value of the fan state corresponding to the characteristic data.
And determining the state information of the fan to be evaluated according to the performance type evaluation index state value of the characteristic data.
Specifically, feature data corresponding to performance evaluation indexes in the target feature data set are obtained, a performance evaluation index state value result of the feature data is calculated, and state information of the fan to be evaluated is determined.
Optionally, determining the state information of the fan to be evaluated according to the target characteristic data set includes:
and acquiring characteristic data corresponding to the early warning evaluation indexes in the target characteristic data set.
In this embodiment, the early warning evaluation indexes may include fan health evaluation indexes such as vibration, bearing temperature, oil pressure, motor stator winding temperature, fan flow, pressure, and efficiency.
Specifically, if the target feature data set has feature data corresponding to the early warning evaluation index, the feature data corresponding to the early warning evaluation index in the target feature data set is obtained.
A second deviation value of the characteristic data is determined based on the characteristic data and the corresponding second value of the characteristic data.
It should be noted that the second numerical value corresponding to the feature data may be a state prediction value of the feature data corresponding to the early warning type evaluation index in the target feature data set.
And obtaining a second numerical value corresponding to the characteristic data by inputting the characteristic data into the target neural network model. The target input neural network model is obtained by iteratively training a neural network model through a target sample set, the target sample set is determined according to a historical fan characteristic data set, and the target sample set comprises characteristic data samples corresponding to early warning evaluation indexes and second numerical values corresponding to the characteristic data samples.
In this embodiment, the target neural network model may be an artificial intelligence neural network model.
The second deviation value of the feature data may be a deviation value of the feature data of the early warning type evaluation index.
Specifically, the specific calculation formula for determining the second deviation value of the feature data according to the feature data and the corresponding second numerical value of the feature data is as follows:
Figure BDA0003926727790000181
wherein, Δ represents a second deviation value of the feature data, x represents an actual measurement value of the feature data corresponding to the early warning evaluation index in the target feature data set, and x represents a second deviation value of the feature data pre And expressing a second numerical value corresponding to the characteristic data, namely, a state prediction value of the characteristic data corresponding to the early warning type evaluation index in the target characteristic data set.
And determining the early warning type evaluation index state value of the characteristic data according to the second deviation value of the characteristic data, the preset fan state threshold and the fan state second deviation threshold corresponding to the characteristic data.
It should be explained that, the second deviation threshold of the fan state corresponding to the feature data is a value of a score of an evaluation index determined by a user according to a data-driven artificial intelligence algorithm from the safety and reliability perspective when the state information of the fan is attention, abnormal, and serious, respectively, which is not limited in this embodiment.
In this embodiment, the early warning type evaluation index state value of the feature data may be a state value of the feature data when the feature data in the target feature data set is an early warning type evaluation index.
Specifically, a specific calculation formula for determining the early warning evaluation index state value of the feature data according to the second deviation value of the feature data, the preset fan state threshold and the fan state second deviation threshold corresponding to the feature data is as follows:
Figure BDA0003926727790000191
wherein H Δ (x) The early warning evaluation index state value of the characteristic data is represented, delta represents a second deviation value of the characteristic data, and H A A threshold value H indicating that the state information of the fan in the preset fan state threshold value is attention E A threshold value H indicating that the state information of the fan is abnormal in the preset fan state threshold value S A threshold value, Δ, indicating a condition of the fan in the preset fan condition threshold value when the condition information of the fan is serious A Indicating that the state information of the fan in the second deviation threshold of the fan state corresponding to the characteristic data is the threshold value delta when attention is paid E A threshold value, delta, representing the abnormal state of the fan in the second deviation threshold value of the fan state corresponding to the characteristic data S And indicating a threshold value when the state information of the fan is serious in the second deviation threshold value of the fan state corresponding to the characteristic data.
And determining the state information of the fan to be evaluated according to the early warning type evaluation index state value of the characteristic data.
Specifically, feature data corresponding to the early warning type evaluation index in the target feature data set is obtained, the early warning type evaluation index state value result of the feature data is calculated, and the state information of the fan to be evaluated is determined.
Optionally, the iteratively training the neural network model through the target sample set includes:
and establishing a neural network model.
And inputting the characteristic data samples corresponding to the early warning evaluation indexes in the target sample set into the neural network model to obtain second numerical values corresponding to the characteristic data samples.
And training parameters of the neural network model according to a target function formed by the second numerical value corresponding to the characteristic data sample and the characteristic data sample corresponding to the early warning evaluation index.
And returning to execute the operation of inputting the characteristic data samples corresponding to the early warning evaluation indexes in the target sample set into the neural network model to obtain second numerical values corresponding to the characteristic data samples until the target neural network model is obtained.
In the implementation process, after the limit type evaluation index state value of the feature data, the performance type evaluation index state value of the feature data, and the early warning type evaluation index state value of the feature data are obtained through calculation, a health degree evaluation model of the fan is constructed according to the weight of the limit type evaluation index, the weight of the performance type evaluation index, and the weight of the early warning type evaluation index (in this embodiment, the weight of the limit type evaluation index, the weight of the performance type evaluation index, and the weight of the early warning type evaluation index may be set by a user according to actual conditions, and this embodiment is not limited thereto), the limit type evaluation index state value of the feature data, the performance type evaluation index state value of the feature data, and the early warning type evaluation index state value of the feature data.
Optionally, the health degree evaluation model may be a health degree calculation method combining a certain limit class and an early warning class evaluation index, or combining a certain performance class and an early warning class evaluation index. Specifically, the calculation formula of the health degree evaluation value may be expressed as follows:
H p (x)＝αH″(x)+(1-α)H Δ (x)；
or:
H p (x)＝βH δ (x)+(1-β)H Δ (x)；
wherein H p (x) The evaluation value of the parameter level health degree is represented, alpha represents the weight of the limit value class evaluation index, H '(x) represents the state value of the limit value class evaluation index of the feature data, wherein H' (x) comprises an over-upper limit alarm type limit value class evaluation index H (x) and an over-lower limit alarm type limit value class evaluation index H '(x), H' (x) Δ (x) The state value of the early warning evaluation index representing the characteristic data, beta represents the weight of the performance evaluation index, H δ (x) And the performance class evaluation index state value of the characteristic data is represented.
Optionally, the health degree evaluation model may be a weight-based health degree calculation method combining all the evaluation indexes of the finite value class, the performance class and the early warning class. Specifically, the calculation formula of the health degree evaluation value may be expressed as follows:
Figure BDA0003926727790000211
wherein H c Indicates a component-level health evaluation value, r 1 (x i ) Weight r representing evaluation index of limit class 1 (x j ) Weight, r, representing performance-type evaluation index 1 (x k ) Representing the weight of the early warning evaluation index; h' (x) i ) And a limit value class evaluation index state value representing characteristic data, wherein H' (x) i ) The method comprises the following steps of (1) including an upper limit alarm type limit value type evaluation index H (x) and a lower limit alarm type limit value type evaluation index H' (x); h δ (x j ) State value of performance class evaluation index H representing characteristic data Δ (x k ) Representing the state value of the early warning evaluation index of the characteristic data; i represents the ith limit value class evaluation index state value, wherein i =1,2, …, l1, and l1 represents the total number of limit value class evaluation index state values in the target feature data set; j represents the j th performance class evaluation index state value, wherein j =1,2, …, l2, and l2 represents the total number of performance class evaluation index state values in the target characteristic data set; k represents the state value of the kth early warning class evaluation index, wherein k =1,2, …, l3, and l3 represents the total number of the state values of the early warning class evaluation indexes in the target feature data set.
In the actual operation process, the health degree evaluation model of the fan is deployed to a power plant, the overall parameters of a generator set and a boiler of an SIS system and a PMS system, various state online parameters of the fan, point inspection data and early warning data are acquired in real time through a data interface, the data are input into the fan health degree evaluation model selected according to actual conditions, the health degree state (normal, attention, abnormal or serious) of the fan is updated in real time, the health degree evaluation value and the trend chart of the fan are output, and meanwhile, the deduction item content of the attention, abnormal or serious health state and the like are output. The output content of the deduction item can include the name of the evaluation index, the deduction rule, the deduction value, the health state, the weight of the evaluation index and the like. Based on fan fault cases and historical experience knowledge collected from a power plant, a fan fault knowledge base is established by combining with the industrial standards, design, installation and operation rules of the fan, all characteristic data related to fan abnormity can be directly extracted through deduction items output by a health degree evaluation model, the characteristic data are coupled with the fan fault knowledge base, fan fault diagnosis is carried out, fault reasons are analyzed, fault parts are located, and an inspection scheme and a treatment measure are given.
According to the technical scheme of the embodiment of the invention, in the determination of the state information of the fan to be evaluated, the characteristic data of the fan, the characteristic data of the boiler and the characteristic data of the generator set are comprehensively considered, so that the comprehensiveness of the acquired data is ensured; the feature data set of the fan to be evaluated is screened according to the evaluation index, more effective and practical feature data are extracted, and the reasonability and the accuracy of determining the state information of the fan to be evaluated are guaranteed. The health degree of the running state of the fan of the power station is determined, the running health state and the development trend of the fan are judged in advance according to the health degree value, early warning of fan faults can be achieved, further expansion of the faults is avoided, and the method and the device have important significance for guaranteeing safe and reliable running of the fan and reducing operation and maintenance cost of the fan. By improving the health management level of the fan, the unplanned shutdown of the thermal power generating unit can be reduced, the operation and maintenance cost of the thermal power plant is reduced, and the stability and the safety of the operation of the power plant or a power grid are ensured.
Example two
Fig. 2 is a schematic structural diagram of a fan status determination apparatus according to a second embodiment of the present invention. As shown in fig. 2, the apparatus includes: a first acquisition module 201, a screening module 202 and a determination module 203.
The first obtaining module 201 is configured to obtain a feature data set of a fan to be evaluated, where the feature data set of the fan to be evaluated includes: fan data, boiler data, and generator set data;
the screening module 202 is configured to screen the feature data set of the fan to be evaluated according to the evaluation index to obtain a target feature data set;
and the determining module 203 is configured to determine the state information of the fan to be evaluated according to the target feature data set.
Optionally, the apparatus further comprises:
the cluster analysis module is used for carrying out cluster analysis on the historical fan characteristic data set before screening the characteristic data set of the fan to be evaluated according to the evaluation index to obtain a target characteristic data set, so as to obtain a first characteristic data set corresponding to at least one fan operation condition;
the second acquisition module is used for acquiring the correlation strength values of the historical characteristic data of the fan part and the historical boiler data, the correlation strength values of the historical characteristic data of the fan part and the historical generator set data and the correlation strength values of the historical characteristic data of the fan part and the historical characteristic data of other fan parts in the first characteristic data set corresponding to the operation condition of each fan before the characteristic data set of the fan to be evaluated is screened according to the evaluation index to obtain a target characteristic data set;
and the second determination module is used for determining the evaluation indexes according to the correlation strength values of the historical characteristic data of the fan part and the historical boiler data, the correlation strength values of the historical characteristic data of the fan part and the historical generator set data and the correlation strength values of the historical characteristic data of the fan part and the historical characteristic data of other fan parts in the characteristic data set before the characteristic data set of the fan to be evaluated is screened according to the evaluation indexes to obtain a target characteristic data set.
Optionally, the second determining module includes:
a first determination unit, configured to determine, according to a correlation strength value of historical feature data of a fan component in the feature data set and historical boiler data, a correlation strength value of the historical feature data of the fan component and historical generator set data, and a correlation strength value of the historical feature data of the fan component and historical feature data of other fan components, a weight of the historical feature data of the fan component relative to the historical boiler data, a weight of the historical feature data of the fan component relative to the historical generator set data, and a weight of the historical feature data of the fan component relative to the historical feature data of other fan components in the feature data set;
the second determination unit is used for determining the evaluation index according to a preset weight threshold value, the weight of historical characteristic data of the fan component relative to historical boiler data in the characteristic data set, the weight of the historical characteristic data of the fan component relative to historical power generation group data and the weight of the historical characteristic data of the fan component relative to historical characteristic data of other fan components.
Optionally, the determining module 203 includes:
the first acquisition unit is used for acquiring feature data corresponding to the limit value evaluation index in the target feature data set;
the third determining unit is used for determining a limit evaluation index state value of the characteristic data according to the characteristic data, a preset fan state threshold value and a fan state threshold value corresponding to the characteristic data;
and the fourth determining unit is used for determining the state information of the fan to be evaluated according to the limit value type evaluation index state value of the characteristic data.
Optionally, the determining module 203 includes:
the second acquisition unit is used for acquiring the characteristic data corresponding to the performance type evaluation indexes in the target characteristic data set;
a fifth determining unit, configured to determine a first deviation value of the feature data according to the feature data and a first numerical value corresponding to the feature data, where the first numerical value corresponding to the feature data is obtained by inputting the feature data into a target model;
a sixth determining unit, configured to determine a performance class evaluation index state value of the feature data according to the first deviation value of the feature data, a preset fan state threshold, and a fan state first deviation threshold corresponding to the feature data;
and the seventh determining unit is used for determining the state information of the fan to be evaluated according to the performance type evaluation index state value of the characteristic data.
Optionally, the determining module 203 includes:
a third obtaining unit, configured to obtain feature data corresponding to an early warning type evaluation index in the target feature data set;
an eighth determining unit, configured to determine a second deviation value of the feature data according to the feature data and a corresponding second numerical value of the feature data, where the second numerical value corresponding to the feature data is obtained by inputting the feature data into a target neural network model, the target input neural network model is obtained by iteratively training a neural network model through a target sample set, the target sample set is determined according to the historical wind turbine feature data set, and the target sample set includes a feature data sample corresponding to an early warning type evaluation index and a second numerical value corresponding to the feature data sample;
a ninth determining unit, configured to determine an early warning type evaluation index state value of the feature data according to the second deviation value of the feature data, a preset fan state threshold, and a fan state second deviation threshold corresponding to the feature data;
and the tenth determining unit is used for determining the state information of the fan to be evaluated according to the early warning type evaluation index state value of the characteristic data.
Optionally, the eighth determining unit is specifically configured to:
establishing a neural network model;
inputting the characteristic data sample corresponding to the early warning evaluation index in the target sample set into the neural network model to obtain a second numerical value corresponding to the characteristic data sample;
training parameters of the neural network model according to a target function formed by a second numerical value corresponding to the characteristic data sample and the characteristic data sample corresponding to the early warning type evaluation index;
and returning to execute the operation of inputting the characteristic data sample corresponding to the early warning evaluation index in the target sample set into the neural network model to obtain a second numerical value corresponding to the characteristic data sample until the target neural network model is obtained.
The fan state determining device provided by the embodiment of the invention can execute the fan state determining method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the executing method.
EXAMPLE III
FIG. 3 shows a schematic block diagram of an electronic device 30 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not intended to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 3, the electronic device 30 includes at least one processor 31, and a memory communicatively connected to the at least one processor 31, such as a Read Only Memory (ROM) 32, a Random Access Memory (RAM) 33, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 31 may perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 32 or the computer program loaded from the storage unit 38 into the Random Access Memory (RAM) 33. In the RAM 33, various programs and data necessary for the operation of the electronic apparatus 30 can also be stored. The processor 31, the ROM 32, and the RAM 33 are connected to each other via a bus 34. An input/output (I/O) interface 35 is also connected to bus 34.
A plurality of components in the electronic device 30 are connected to the I/O interface 35, including: an input unit 36 such as a keyboard, a mouse, etc.; an output unit 37 such as various types of displays, speakers, and the like; a storage unit 38 such as a magnetic disk, an optical disk, or the like; and a communication unit 39 such as a network card, modem, wireless communication transceiver, etc. The communication unit 39 allows the electronic device 30 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The processor 31 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 31 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. The processor 31 performs the various methods and processes described above, such as the fan state determination method:
acquiring a characteristic data set of a fan to be evaluated, wherein the characteristic data set of the fan to be evaluated comprises the following steps: fan data, boiler data, and generator set data;
screening the characteristic data set of the fan to be evaluated according to the evaluation index to obtain a target characteristic data set;
and determining the state information of the fan to be evaluated according to the target characteristic data set.
In some embodiments, the fan condition determination method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 38. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 30 via the ROM 32 and/or the communication unit 39. When the computer program is loaded into the RAM 33 and executed by the processor 31, one or more steps of the above described fan status determination method may be performed. Alternatively, in other embodiments, the processor 31 may be configured to perform the fan status determination method in any other suitable manner (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the Internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and the present invention is not limited to the embodiments described herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and 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. A fan state determination method is characterized by comprising the following steps:
acquiring a characteristic data set of a fan to be evaluated, wherein the characteristic data set of the fan to be evaluated comprises the following steps: fan data, boiler data, and generator set data;
screening the characteristic data set of the fan to be evaluated according to the evaluation index to obtain a target characteristic data set;
and determining the state information of the fan to be evaluated according to the target characteristic data set.
2. The method according to claim 1, wherein before the feature data set of the fan to be evaluated is screened according to the evaluation index to obtain a target feature data set, the method further comprises:
performing cluster analysis on the historical fan characteristic data set to obtain a first characteristic data set corresponding to at least one fan operation condition;
obtaining the correlation strength values of historical characteristic data of a fan component and historical boiler data, the correlation strength values of the historical characteristic data of the fan component and historical generator set data and the correlation strength values of the historical characteristic data of the fan component and historical characteristic data of other fan components in a first characteristic data set corresponding to the operation working condition of each fan;
and determining an evaluation index according to the correlation strength values of the historical characteristic data of the fan component and the historical boiler data, the correlation strength values of the historical characteristic data of the fan component and the historical generator set data and the correlation strength values of the historical characteristic data of the fan component and the historical characteristic data of other fan components in the characteristic data set.
3. The method of claim 2, wherein determining an evaluation index based on the strength values of the historical characterization data of the fan component relative to the historical boiler data, the strength values of the historical characterization data of the fan component relative to the historical genset data, and the strength values of the historical characterization data of the fan component relative to the historical characterization data of other fan components comprises:
determining the weight of the historical characteristic data of the fan component relative to the historical boiler data, the weight of the historical characteristic data of the fan component relative to the historical generator set data and the weight of the historical characteristic data of the fan component relative to the historical characteristic data of other fan components in the characteristic data set according to the correlation strength value of the historical characteristic data of the fan component and the historical boiler data, the correlation strength value of the historical characteristic data of the fan component and the historical generator set data and the correlation strength value of the historical characteristic data of the fan component and the historical characteristic data of other fan components in the characteristic data set;
and determining an evaluation index according to a preset weight threshold, the weight of the historical characteristic data of the fan component relative to the historical boiler data in the characteristic data set, the weight of the historical characteristic data of the fan component relative to the historical power generation group data and the weight of the historical characteristic data of the fan component relative to the historical characteristic data of other fan components.
4. The method according to claim 1, wherein determining the state information of the fan to be evaluated according to the target characteristic data set comprises:
acquiring feature data corresponding to a limit value type evaluation index in the target feature data set;
determining a limit evaluation index state value of the characteristic data according to the characteristic data, a preset fan state threshold value and a fan state threshold value corresponding to the characteristic data;
and determining the state information of the fan to be evaluated according to the limit value type evaluation index state value of the characteristic data.
5. The method according to claim 1, wherein determining the state information of the fan to be evaluated according to the target characteristic data set comprises:
acquiring characteristic data corresponding to performance type evaluation indexes in the target characteristic data set;
determining a first deviation value of the feature data according to the feature data and a first numerical value corresponding to the feature data, wherein the first numerical value corresponding to the feature data is obtained by inputting the feature data into a target model;
determining a performance class evaluation index state value of the characteristic data according to the first deviation value of the characteristic data, a preset fan state threshold value and a fan state first deviation threshold value corresponding to the characteristic data;
and determining the state information of the fan to be evaluated according to the performance type evaluation index state value of the characteristic data.
6. The method according to claim 1, wherein determining the state information of the fan to be evaluated according to the target characteristic data set comprises:
acquiring characteristic data corresponding to early warning type evaluation indexes in the target characteristic data set;
determining a second deviation value of the feature data according to the feature data and a corresponding second numerical value of the feature data, wherein the second numerical value corresponding to the feature data is obtained by inputting the feature data into a target neural network model, the target input neural network model is obtained by iteratively training a neural network model through a target sample set, the target sample set is determined according to the historical fan feature data set, and the target sample set comprises a feature data sample corresponding to an early warning type evaluation index and a second numerical value corresponding to the feature data sample;
determining an early warning type evaluation index state value of the characteristic data according to a second deviation value of the characteristic data, a preset fan state threshold value and a fan state second deviation threshold value corresponding to the characteristic data;
and determining the state information of the fan to be evaluated according to the early warning type evaluation index state value of the characteristic data.
7. The method of claim 6, wherein iteratively training the neural network model through the set of target samples comprises:
establishing a neural network model;
inputting the characteristic data sample corresponding to the early warning evaluation index in the target sample set into the neural network model to obtain a second numerical value corresponding to the characteristic data sample;
training parameters of the neural network model according to a target function formed by a second numerical value corresponding to the characteristic data sample and the characteristic data sample corresponding to the early warning type evaluation index;
and returning to execute the operation of inputting the characteristic data sample corresponding to the early warning evaluation index in the target sample set into the neural network model to obtain a second numerical value corresponding to the characteristic data sample until the target neural network model is obtained.
8. A fan condition determining apparatus, comprising:
the first acquisition module is used for acquiring a characteristic data set of the fan to be evaluated, wherein the characteristic data set of the fan to be evaluated comprises: fan data, boiler data, and generator set data;
the screening module is used for screening the characteristic data set of the fan to be evaluated according to the evaluation index to obtain a target characteristic data set;
and the determining module is used for determining the state information of the fan to be evaluated according to the target characteristic data set.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein the content of the first and second substances,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the fan status determination method of any of claims 1-7.
10. A computer-readable storage medium storing computer instructions for causing a processor to perform the method of determining a condition of a wind turbine according to any of claims 1 to 7 when executed.
CN202211376367.4A 2022-11-04 2022-11-04 Fan state determination method, device, equipment and storage medium Pending CN115906437A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211376367.4A CN115906437A (en) 2022-11-04 2022-11-04 Fan state determination method, device, equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211376367.4A CN115906437A (en) 2022-11-04 2022-11-04 Fan state determination method, device, equipment and storage medium

Publications (1)

Publication Number Publication Date
CN115906437A true CN115906437A (en) 2023-04-04

Family

ID=86495752

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211376367.4A Pending CN115906437A (en) 2022-11-04 2022-11-04 Fan state determination method, device, equipment and storage medium

Country Status (1)

Country Link
CN (1) CN115906437A (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116707326A (en) * 2023-08-07 2023-09-05 湘潭宏光变流电气有限公司 High-power silicon controlled rectifier cabinet and control system

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116707326A (en) * 2023-08-07 2023-09-05 湘潭宏光变流电气有限公司 High-power silicon controlled rectifier cabinet and control system
CN116707326B (en) * 2023-08-07 2023-10-27 湘潭宏光变流电气有限公司 High-power silicon controlled rectifier cabinet and control system

Similar Documents

Publication Publication Date Title
Hsu et al. Wind turbine fault diagnosis and predictive maintenance through statistical process control and machine learning
Wang et al. An overview of industrial alarm systems: Main causes for alarm overloading, research status, and open problems
Zhi-Ling et al. Expert system of fault diagnosis for gear box in wind turbine
CN106404403B (en) Method and system for analysis of a turbomachine
CN113779496B (en) Power equipment state evaluation method and system based on equipment panoramic data
CN112596495A (en) Industrial equipment fault diagnosis method and system based on knowledge graph
CN110674842A (en) Wind turbine generator main shaft bearing fault prediction method
JP6088131B2 (en) Turbine performance diagnostic system and method
JP2013538543A (en) Machine learning for power grids
CN110009208B (en) Method and device for evaluating health state of pole-mounted switch complete equipment based on hybrid intelligent algorithm
Qiu et al. Data mining based framework to identify rule based operation strategies for buildings with power metering system
JP2012007612A (en) Turbomachine airfoil life management system and method
CN111878320B (en) Monitoring method and system of wind generating set and computer readable storage medium
WO2023065580A1 (en) Fault diagnosis method and apparatus for gearbox of wind turbine generator set
CN115906437A (en) Fan state determination method, device, equipment and storage medium
CN112001511A (en) Equipment reliability and dynamic risk evaluation method, system and equipment based on data mining
RU2668852C1 (en) Method and system of accounting residual operation life of turbo-aggregate components
CN114837902B (en) Health degree evaluation method, system, equipment and medium for wind turbine generator
CN114235108B (en) Abnormal state detection method and device for gas flowmeter based on data analysis
WO2023072724A1 (en) System, apparatus and method for monitoring condition of an asset in technical installation
CN115456041A (en) Equipment fault early warning method and device, computing equipment and storage medium
CN114997342A (en) SCR fault diagnosis method, device, equipment and storage medium
CN110738400A (en) System health assessment method and device, electronic equipment and storage medium
CN110874088A (en) Monitoring method of ship key equipment system based on multi-dimensional vector model
US8095588B2 (en) Method and system for data decomposition via graphical multivariate analysis

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