CN117231441A - Wind driven generator operation fault diagnosis system based on artificial intelligence - Google Patents
Wind driven generator operation fault diagnosis system based on artificial intelligence Download PDFInfo
- Publication number
- CN117231441A CN117231441A CN202311429960.5A CN202311429960A CN117231441A CN 117231441 A CN117231441 A CN 117231441A CN 202311429960 A CN202311429960 A CN 202311429960A CN 117231441 A CN117231441 A CN 117231441A
- Authority
- CN
- China
- Prior art keywords
- value
- preset
- threshold
- signal
- driven generator
- 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.)
- Withdrawn
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 14
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 13
- 238000010248 power generation Methods 0.000 claims abstract description 68
- 230000003068 static effect Effects 0.000 claims abstract description 56
- 238000011156 evaluation Methods 0.000 claims description 76
- 238000012502 risk assessment Methods 0.000 claims description 27
- 238000000034 method Methods 0.000 claims description 21
- 230000002159 abnormal effect Effects 0.000 claims description 17
- 230000000903 blocking effect Effects 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 16
- 230000002452 interceptive effect Effects 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 9
- 238000001816 cooling Methods 0.000 claims description 7
- 230000005764 inhibitory process Effects 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 6
- 239000010687 lubricating oil Substances 0.000 claims description 6
- 238000012423 maintenance Methods 0.000 claims description 4
- 230000001154 acute effect Effects 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 claims description 3
- 230000003647 oxidation Effects 0.000 claims description 3
- 238000007254 oxidation reaction Methods 0.000 claims description 3
- 238000009423 ventilation Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 6
- 230000002829 reductive effect Effects 0.000 abstract description 6
- 230000009286 beneficial effect Effects 0.000 abstract description 5
- 238000012544 monitoring process Methods 0.000 abstract 1
- 238000004891 communication Methods 0.000 description 7
- 230000006872 improvement Effects 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 230000036961 partial effect Effects 0.000 description 1
Landscapes
- Wind Motors (AREA)
Abstract
The invention relates to the technical field of equipment operation supervision, in particular to an artificial intelligence-based wind driven generator operation fault diagnosis system, which comprises a supervision platform, a data acquisition unit, a static supervision unit, an operation supervision unit, a characteristic expression unit, a fault risk unit and an early warning display unit, wherein the monitoring platform is used for acquiring data of the wind driven generator operation fault diagnosis system; according to the invention, analysis is performed from the angles of dynamic inside and outside, static inside and dynamic and static combination so as to timely maintain and manage the wind driven generator, and meanwhile, management and control are reasonably performed on the whole wind driven generator so as to ensure the power generation efficiency and power generation stability of the wind driven generator, and meanwhile, influence of improper standing management of the wind driven generator on subsequent operation is reduced, thus being beneficial to integrally evaluating the operation safety of the wind driven generator, improving data support, analyzing from the angle of dynamic and static combination, being beneficial to improving the accuracy of analysis results, and further improving the management effect and management precision of the wind driven generator so as to reduce the operation fault risk of the wind driven generator.
Description
Technical Field
The invention relates to the technical field of equipment operation supervision, in particular to an artificial intelligence-based wind driven generator operation fault diagnosis system.
Background
The wind driven generator is power equipment for converting wind energy into mechanical work, wherein the mechanical work drives a rotor to rotate, and finally, alternating current is output; the wind driven generator generally comprises wind wheels, a generator (comprising a device), a direction regulator (tail wing), a tower, a speed limiting safety mechanism, an energy storage device and other components; the working principle of the wind driven generator is simple, the wind wheel rotates under the action of wind force, the kinetic energy of wind is converted into mechanical energy of the wind wheel shaft, and the generator rotates to generate electricity under the drive of the wind wheel shaft; in a broad sense, wind energy is also solar energy, so the wind power generator can be said to be a heat energy utilization generator which takes the sun as a heat source and takes the atmosphere as a working medium;
however, when the existing wind driven generator is operated, the operation of the wind driven generator cannot be monitored, and in the prior art, the problem of single analysis data exists, so that the analysis result error is large, the accurate and reasonable management of the wind driven generator is not facilitated, the management rationality of the wind driven generator is reduced, the analysis cannot be performed by combining the cooling condition of a component under the static state of the wind driven generator, the operation condition of the wind driven generator cannot be accurately and integrally analyzed, and the power generation safety and the power generation efficiency of the wind driven generator are reduced;
in view of the above technical drawbacks, a solution is now proposed.
Disclosure of Invention
The invention aims to provide an artificial intelligence-based wind driven generator operation fault diagnosis system to solve the technical defects, and the system analyzes from the angles of dynamic inside and outside, static inside and dynamic and static combination so as to timely maintain and manage a wind driven generator, reasonably manage and regulate the whole wind driven generator, ensure the power generation efficiency and the power generation stability of the wind driven generator, simultaneously reduce the influence of improper standing management of the wind driven generator on the subsequent operation, facilitate the improvement of data support for the integral evaluation of the operation safety of the wind driven generator, analyze from the angle of dynamic and static combination, and facilitate the improvement of the accuracy of analysis results, thereby improving the management effect and the management precision of the wind driven generator and reducing the operation fault risk of the wind driven generator.
The aim of the invention can be achieved by the following technical scheme: the wind driven generator operation fault diagnosis system based on artificial intelligence comprises a supervision platform, a data acquisition unit, a static supervision unit, an operation supervision unit, a characteristic expression unit, a fault risk unit and an early warning display unit;
when the supervision platform generates a management command, the management command is sent to the data acquisition unit and the static supervision unit, the data acquisition unit immediately acquires entity operation data and operation characteristic data of the wind driven generator after receiving the management command, the entity operation data represent rotor eccentric values and line eccentric values, the operation characteristic data comprise internal operation interference values and external salient values, the entity operation data and the operation characteristic data are respectively sent to the operation supervision unit and the characteristic display unit, and the operation supervision unit carries out front rotation deviation supervision evaluation analysis and interactive comparison analysis on the entity operation data after receiving the entity operation data, sends the obtained safety signals to the characteristic display unit and sends the obtained safety signals and early warning signals to the early warning display unit;
the feature expression unit performs side operation supervision feedback operation on the operation feature data after receiving the operation feature data and the safety signal, and sends an obtained risk signal to the early warning display unit;
the static supervision unit immediately collects management data of the wind driven generator after receiving the management command, wherein the management data comprises a damage evaluation value and an environmental impact value, performs operation impact feedback analysis on the management data, sends an obtained management signal to the fault risk unit, and sends the obtained impact signal to the early warning display unit through the supervision platform;
and after receiving the pipe transporting signal, the fault risk unit immediately carries out deep safety evaluation operation on the static operation risk coefficient T corresponding to the pipe transporting signal, and sends the obtained risk integration signal to the early warning display unit.
Preferably, the front rotation deviation supervision and evaluation analysis process of the operation supervision unit is as follows:
collecting the duration from the moment when the wind driven generator starts to generate to the moment when the wind driven generator ends, marking the duration as a time threshold, dividing the time threshold into i sub-time periods, wherein i is a natural number larger than zero, obtaining rotor eccentric values of the wind driven generator in each sub-time period, wherein the rotor eccentric values represent the parts of the rotor rotating track, the areas of which are surrounded by the rotor rotating tracks exceed a preset area, establishing a rectangular coordinate system by taking the number of the sub-time periods as an X axis and taking the rotor eccentric values as a Y axis, drawing a rotor eccentric value curve in a dot drawing manner, further obtaining the area surrounded by the rotor eccentric value curve and the X axis, marking the area as an eccentric risk area, comparing the eccentric risk area with a stored preset eccentric risk area threshold, and marking the parts of which the eccentric risk area is larger than the preset eccentric risk area threshold as a power generation influence value if the eccentric risk area is larger than the preset eccentric risk area threshold;
comparing the power generation influence value with a preset power generation influence value threshold value recorded and stored in the power generation influence value to analyze:
if the power generation influence value is smaller than a preset power generation influence value threshold, generating a normal signal;
and if the power generation influence value is greater than or equal to a preset power generation influence value threshold value, generating an alarm signal.
Preferably, the interactive comparison and analysis process of the operation supervision unit is as follows:
obtaining a line deviation value of a wind driven generator within a time threshold, wherein the line deviation value represents the number of the influence parameters of a line port, the influence parameters comprise an oxidation area, an operating resistance average value and a line loss rate, comparing and analyzing the line deviation value with a stored preset line deviation value threshold, and if the line deviation value is larger than the preset line deviation value threshold, marking the part of the line deviation value larger than the preset line deviation value threshold as a line influence value, and comparing the line influence value with the preset line influence value threshold recorded and stored in the line influence value:
if the ratio between the line influence value and the preset line influence value threshold is smaller than 1, generating an operation signal;
if the ratio between the line influence value and the preset line influence value threshold is greater than or equal to 1, generating an abnormal signal;
the signal interactive analysis is carried out on the normal signal, the alarm signal, the operation signal and the abnormal signal, and the specific signal interactive analysis process is as follows:
if the normal signal and the operation signal are generated, a safety signal is obtained;
and if the normal signal and the abnormal signal are generated, or the alarm signal and the operation signal are generated, or the alarm signal and the abnormal signal are generated, the early warning signal is obtained.
Preferably, the side-running supervision feedback operation procedure of the feature presentation unit is as follows:
s1: acquiring an internal operation interference value in an internal gear box of the wind driven generator in each sub-time period, wherein the internal operation interference value represents an acute angle degree formed by the first intersection of a characteristic change curve of the internal lubricating oil temperature in the gear box and a preset characteristic change curve of the lubricating oil temperature, a rectangular coordinate system is established by taking the number of the sub-time periods as an X axis and the internal operation interference value as a Y axis, an internal operation interference value curve is drawn in a dot drawing mode, and further, the maximum crest value and the minimum trough value in the internal operation interference value curve are acquired, and the difference value between the maximum crest value and the minimum trough value in the internal operation interference value curve is marked as an operation blocking value;
s2: obtaining an apparent salient value of the wind driven generator within a time threshold, wherein the apparent salient value represents the minimum value in a time period corresponding to when a characteristic parameter curve is intersected with a preset normal characteristic parameter curve for the first time, the characteristic parameter curve comprises an abnormal sound mean value characteristic curve and a vibration amplitude mean value characteristic curve, the apparent salient value is compared with a stored preset apparent salient value threshold for analysis, and if the apparent salient value is smaller than the preset apparent salient value threshold, a part of the apparent salient value smaller than the preset apparent salient value threshold is marked as a characteristic evaluation value;
s3: comparing the operation impeding value and the characteristic evaluation value with a preset operation impeding value threshold value and a preset characteristic evaluation value threshold value which are recorded and stored in the operation impeding value and the characteristic evaluation value:
if the operation blocking value is smaller than the preset operation blocking value threshold and the characteristic evaluation value is smaller than the preset characteristic evaluation value threshold, no signal is generated;
and if the operation blocking value is greater than or equal to a preset operation blocking value threshold or the characteristic evaluation value is greater than or equal to a preset characteristic evaluation value threshold, generating a risk signal.
Preferably, the operation influence feedback analysis process of the static supervision unit is as follows:
SS1: collecting the time length of a period of time after the operation of the wind driven generator is finished, marking the time length as analysis time length, dividing the analysis time length into m sub-time nodes, wherein m is a natural number larger than zero, obtaining damage evaluation values of the wind driven generator in each sub-time node, wherein the damage evaluation values represent the number of component parts corresponding to the cooling value in unit time which is smaller than the preset cooling value in unit time, the component parts comprise a rotor, a generator and a gear box, further drawing a sector graph corresponding to the damage evaluation value which is smaller than or equal to the preset damage evaluation value threshold and the damage evaluation value which is larger than the preset damage evaluation value threshold in the time threshold, further obtaining the ratio of the sector area corresponding to the damage evaluation value which is smaller than or equal to the preset damage evaluation value threshold to the sector area corresponding to the damage evaluation value which is larger than the preset damage evaluation value threshold, and marking the ratio as an operation safety value YZ;
SS2: acquiring environment influence values of wind driven generators in each sub-time node, wherein the environment influence values represent the number corresponding to the internal environment parameters which are lower than a preset threshold value, the internal environment parameters comprise ventilation flow and temperature change values in unit time, a set A of the environment influence values is constructed, a maximum subset and a minimum subset in the set A are acquired, and the average value of the difference values between the maximum subset and the minimum subset in the set A is marked as an environment interference value HG;
SS3: according to the formulaObtaining a static running risk coefficient, wherein a1 and a2 are preset scale factor coefficients of a running safety value and an environment interference value respectively, a1 and a2 are positive numbers larger than zero, a3 is a preset correction factor coefficient,the value is 1.928, T is a static running risk coefficient, and the static running risk coefficient T is compared with a preset static running risk coefficient threshold value recorded and stored in the static running risk coefficient T:
if the ratio between the static operation risk coefficient T and the preset static operation risk coefficient threshold value is more than or equal to 1, generating a pipe conveying signal;
and if the ratio between the static running risk coefficient T and the preset static running risk coefficient threshold is smaller than 1, generating an influence signal.
Preferably, the in-depth safety assessment operation procedure of the fault risk unit is as follows:
the method comprises the steps of calling an operation inhibition value and a characteristic evaluation value from a characteristic expression unit, simultaneously obtaining the number of data corresponding to management parameter information of the wind driven generator in a time threshold exceeding a preset threshold, marking the number as a management influence value, wherein the management parameter information comprises a maintenance interval duration mean value and a fault frequency, and marking the operation inhibition value, the characteristic evaluation value and the management influence value as YA, TP and GY respectively;
according to the formulaObtaining a power generation failure risk assessment coefficient, wherein f1, f2 and f3 are respectively preset weight factor coefficients of an operation blocking value, a characteristic assessment value and a management influence value, f1, f2 and f3 are positive numbers larger than zero, f4 is a preset fault tolerance factor coefficient, the value is 1.224, G is the power generation failure risk assessment coefficient, and the power generation failure risk assessment coefficient G is compared with a preset power generation failure risk assessment coefficient threshold value recorded and stored in the power generation failure risk assessment coefficient G:
if the ratio between the power generation fault risk assessment coefficient G and the preset power generation fault risk assessment coefficient threshold is smaller than 1, no signal is generated;
and if the ratio between the power generation fault risk assessment coefficient G and the preset power generation fault risk assessment coefficient threshold is greater than or equal to 1, generating a risk integration signal.
The beneficial effects of the invention are as follows:
according to the invention, analysis is carried out from the angles of dynamic inside and outside, static inside and dynamic and static combination so as to timely maintain and manage the wind driven generator, and meanwhile, management and control are reasonably carried out on the whole wind driven generator so as to ensure the power generation efficiency and power generation stability of the wind driven generator, and meanwhile, the influence of improper standing management of the wind driven generator on the follow-up operation is reduced, thus being beneficial to integrally evaluating the operation safety of the wind driven generator, improving the data support, analyzing from the angle of dynamic and static combination, being beneficial to improving the accuracy of analysis results, and further improving the management effect and management precision of the wind driven generator so as to reduce the operation fault risk of the wind driven generator;
the invention is helpful to improve the supervision and early warning effect and the early warning precision when the wind driven generator operates by analyzing from the dynamic internal and external angles, and maintains and manages the wind driven generator in an information feedback mode, and is helpful to know the operation safety and stability of the wind driven generator from the front and the side by analyzing from the angles of the operation and the operation characteristics of the components.
Drawings
The invention is further described below with reference to the accompanying drawings;
FIG. 1 is a flow chart of the system of the present invention;
fig. 2 is a partial analysis reference diagram of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Embodiment one:
referring to fig. 1 to 2, the invention discloses an artificial intelligence-based wind driven generator operation fault diagnosis system, which comprises a supervision platform, a data acquisition unit, a static supervision unit, an operation supervision unit, a characteristic expression unit, a fault risk unit and an early warning display unit, wherein the supervision platform is in one-way communication connection with the data acquisition unit, the supervision platform is in two-way communication connection with the static supervision unit, the data acquisition unit is in one-way communication connection with the operation supervision unit and the characteristic expression unit, the operation supervision unit is in one-way communication connection with the characteristic expression unit, the operation supervision unit and the characteristic expression unit are in one-way communication connection with the early warning display unit, the static supervision unit and the characteristic expression unit are in one-way communication connection with the fault risk unit, and the fault risk unit is in one-way communication connection with the early warning display unit;
when the supervision platform generates a management command, the management command is sent to the data acquisition unit and the static supervision unit, the data acquisition unit immediately acquires entity operation data and operation characteristic data of the wind driven generator after receiving the management command, the entity operation data represent rotor eccentric values and line eccentric values, the operation characteristic data comprise internal operation interference values and external salient values, the entity operation data and the operation characteristic data are respectively sent to the operation supervision unit and the characteristic expression unit, the operation supervision unit receives the entity operation data and carries out front rotation deviation supervision evaluation analysis on the entity operation data to judge whether internal components of the wind driven generator normally operate or not so as to ensure the power generation efficiency and the power generation stability of the wind driven generator, and the specific front rotation deviation supervision evaluation analysis process is as follows:
collecting the duration from the moment when the wind driven generator starts to generate to the moment when the wind driven generator ends, marking the duration as a time threshold, dividing the time threshold into i sub-time periods, wherein i is a natural number larger than zero, obtaining rotor eccentric values of the wind driven generator in each sub-time period, wherein the rotor eccentric values represent the parts of the areas surrounded by rotor rotating tracks exceeding a preset area, establishing a rectangular coordinate system by taking the number of the sub-time periods as an X axis and taking the rotor eccentric values as a Y axis, drawing a rotor eccentric value curve in a dot drawing manner, further obtaining the area surrounded by the rotor eccentric value curve and the X axis, marking the area as an eccentric risk area, comparing the eccentric risk area with a stored preset eccentric risk area threshold, and marking the parts of the eccentric risk area larger than the preset eccentric risk area threshold as power generation influence values if the eccentric risk area is larger than the preset eccentric risk area threshold, wherein the larger the value of the power generation influence value is required to be described, the abnormal power generation of the wind driven generator is larger;
comparing the power generation influence value with a preset power generation influence value threshold value recorded and stored in the power generation influence value to analyze:
if the power generation influence value is smaller than a preset power generation influence value threshold, generating a normal signal;
if the power generation influence value is greater than or equal to a preset power generation influence value threshold value, generating an alarm signal;
obtaining a line deviation value of a wind driven generator within a time threshold, wherein the line deviation value represents the number of the influence parameters of a line port, the influence parameters comprise an oxidation area, an operating resistance average value, a line loss rate and the like, comparing the line deviation value with a stored preset line deviation value threshold, if the line deviation value is larger than the preset line deviation value threshold, marking a part of the line deviation value larger than the preset line deviation value threshold as a line influence value, and if the line deviation value is larger than the preset line deviation value threshold, the wind driven generator has larger abnormal power generation risk, and comparing the line influence value with the preset line influence value threshold recorded in the line influence value and the line influence value stored in the wind driven generator:
if the ratio between the line influence value and the preset line influence value threshold is smaller than 1, generating an operation signal;
if the ratio between the line influence value and the preset line influence value threshold is greater than or equal to 1, generating an abnormal signal;
the signal interactive analysis is carried out on the normal signal, the alarm signal, the operation signal and the abnormal signal, and the specific signal interactive analysis process is as follows:
if the normal signal and the operation signal are generated, a safety signal is obtained, and the safety signal is sent to the characteristic expression unit;
if a normal signal and an abnormal signal are generated, or an alarm signal and an operation signal are generated, or the alarm signal and the abnormal signal are generated, an early warning signal is obtained, and the safety signal and the early warning signal are sent to an early warning display unit, and after the safety signal and the early warning signal are received, the early warning display unit immediately displays preset early warning characters corresponding to the safety signal and the early warning signal respectively, so that the wind driven generator is maintained and managed in time, and the power generation efficiency and the power generation stability of the wind driven generator are ensured;
after receiving the operation characteristic data and the safety signal, the characteristic expression unit performs side operation supervision feedback operation on the operation characteristic data so as to know the operation safety and stability of the wind driven generator and manage the wind driven generator reasonably, wherein the specific side operation supervision feedback operation process is as follows:
acquiring internal operation interference values in an internal gear box of the wind driven generator in each sub-time period, wherein the internal operation interference values represent acute angle degrees formed by first intersection of a characteristic change curve of the internal lubricating oil temperature in the gear box and a preset characteristic change curve of the lubricating oil temperature, a rectangular coordinate system is established by taking the number of the sub-time periods as an X axis and the internal operation interference values as a Y axis, an internal operation interference value curve is drawn in a dot drawing mode, and further, the maximum crest value and the minimum trough value in the internal operation interference value curve are acquired, and the difference value between the maximum crest value and the minimum trough value in the internal operation interference value curve is marked as an operation interference value;
obtaining an apparent salient value of the wind driven generator within a time threshold, wherein the apparent salient value represents the minimum value in a time period corresponding to when a characteristic parameter curve is intersected with a preset normal characteristic parameter curve for the first time, the characteristic parameter curve comprises an abnormal sound mean value characteristic curve, a vibration amplitude mean value characteristic curve and the like, comparing the apparent salient value with a stored preset apparent salient value threshold for analysis, and if the apparent salient value is smaller than the preset apparent salient value threshold, marking a part of the apparent salient value smaller than the preset apparent salient value threshold as a characteristic evaluation value, wherein the larger the value of the characteristic evaluation value is, the larger the running fault risk of the wind driven generator is;
comparing the operation impeding value and the characteristic evaluation value with a preset operation impeding value threshold value and a preset characteristic evaluation value threshold value which are recorded and stored in the operation impeding value and the characteristic evaluation value:
if the operation blocking value is smaller than the preset operation blocking value threshold and the characteristic evaluation value is smaller than the preset characteristic evaluation value threshold, no signal is generated;
if the operation blocking value is greater than or equal to a preset operation blocking value threshold value or the characteristic evaluation value is greater than or equal to a preset characteristic evaluation value threshold value, generating a risk signal, sending the risk signal to an early warning display unit, and immediately displaying preset early warning characters corresponding to the risk signal after the early warning display unit receives the risk signal, so that the wind driven generator is managed reasonably, and the wind driven generator is analyzed from the angle of the operation characteristics of the wind driven generator, and the operation safety and stability of the wind driven generator are helped to be known from the side.
Embodiment two:
the static supervision unit immediately collects management data of the wind driven generator after receiving the management command, wherein the management data comprises a damage evaluation value and an environmental impact value, and carries out operation impact feedback analysis on the management data to judge whether the running wind driven generator stands normally or not so as to improve the data support for integrally evaluating the operation safety of the wind driven generator, and the specific operation impact feedback analysis process is as follows:
collecting the time length of a period of time after the operation of the wind driven generator is finished, marking the time length as analysis time length, dividing the analysis time length into m sub-time nodes, wherein m is a natural number larger than zero, obtaining damage evaluation values of the wind driven generator in each sub-time node, wherein the damage evaluation values represent the number of component parts corresponding to the cooling values in unit time which are smaller than the preset cooling values in unit time, the component parts comprise a rotor, a generator, a gear box and the like, further drawing a sector graph corresponding to the damage evaluation values which are smaller than or equal to a preset damage evaluation value threshold and the damage evaluation values which are larger than the preset damage evaluation value threshold in the time threshold, further obtaining the ratio of the sector area corresponding to the damage evaluation value which is smaller than or equal to the preset damage evaluation value threshold to the sector area corresponding to the damage evaluation value which is larger than the preset damage evaluation value threshold, and marking the ratio as an operation safety value YZ;
acquiring environment influence values of the wind driven generator in each sub-time node, wherein the environment influence values represent the number of the wind driven generator corresponding to the internal environment parameters which are lower than the preset threshold value, the internal environment parameters comprise ventilation flow per unit time, temperature change values and the like, a set A of the environment influence values is constructed, a maximum subset and a minimum subset in the set A are acquired, the average value of the difference values between the maximum subset and the minimum subset in the set A is marked as an environment interference value HG, and the larger the number of the environment interference value HG is, the larger the influence risk on the subsequent use of the wind driven generator is;
according to the formulaObtaining a static operation risk coefficient, wherein a1 and a2 are preset scale factor coefficients of an operation safety value and an environment interference value respectively, the scale factor coefficients are used for correcting deviation of various parameters in a formula calculation process, so that calculation results are more accurate, a1 and a2 are positive numbers larger than zero, a3 is a preset correction factor coefficient, the value is 1.928, T is the static operation risk coefficient, and the static operation risk coefficient T is compared with a preset static operation risk coefficient threshold value recorded and stored in the static operation risk coefficient T:
if the ratio between the static operation risk coefficient T and the preset static operation risk coefficient threshold value is more than or equal to 1, generating a pipe transporting signal, and sending the pipe transporting signal to a fault risk unit;
if the ratio between the static operation risk coefficient T and the preset static operation risk coefficient threshold value is smaller than 1, generating an influence signal, sending the influence signal to an early warning display unit through a supervision platform, and immediately displaying preset early warning characters corresponding to the influence signal after the early warning display unit receives the influence signal, so that maintenance and management are timely carried out on the wind driven generator, the influence of improper standing management on subsequent operation of the wind driven generator is reduced, and meanwhile, the improvement of data support for the overall evaluation of the operation safety of the wind driven generator is facilitated;
after receiving the pipe transporting signal, the fault risk unit immediately carries out deep-type safety evaluation operation on the static operation risk coefficient T corresponding to the pipe transporting signal so as to judge whether the overall safety of the wind driven generator is qualified or not, so that the wind driven generator is reasonably managed and regulated, and the specific deep-type safety evaluation operation process is as follows:
the method comprises the steps of calling an operation inhibition value and a characteristic evaluation value from a characteristic expression unit, simultaneously obtaining the number of data corresponding to management parameter information of the wind driven generator in a time threshold exceeding a preset threshold, marking the number as a management influence value, wherein the management parameter information comprises a maintenance interval duration mean value, a fault frequency and the like, and respectively marking the operation inhibition value, the characteristic evaluation value and the management influence value as YA, TP and GY;
according to the formulaObtaining a power generation failure risk assessment coefficient, wherein f1, f2 and f3 are respectively preset weight factor coefficients of an operation blocking value, a characteristic assessment value and a management influence value, f1, f2 and f3 are positive numbers larger than zero, f4 is a preset fault tolerance factor coefficient, the value is 1.224, G is the power generation failure risk assessment coefficient, and the power generation failure risk assessment coefficient G is compared with a preset power generation failure risk assessment coefficient threshold value recorded and stored in the power generation failure risk assessment coefficient G:
if the ratio between the power generation fault risk assessment coefficient G and the preset power generation fault risk assessment coefficient threshold is smaller than 1, no signal is generated;
if the ratio between the power generation fault risk assessment coefficient G and the preset power generation fault risk assessment coefficient threshold is greater than or equal to 1, generating a risk integration signal, and sending the risk integration signal to an early warning display unit, wherein the early warning display unit immediately displays preset early warning characters corresponding to the influence signal after receiving the influence signal, so that the whole wind driven generator is reasonably managed and controlled, and the power generation efficiency and the power generation stability of the wind driven generator are ensured;
in summary, the wind driven generator is analyzed from the angles of dynamic interior and exterior, static interior and dynamic and static combination so as to timely maintain and manage the wind driven generator, and meanwhile, the whole wind driven generator is reasonably managed and regulated so as to ensure the generating efficiency and generating stability of the wind driven generator, meanwhile, the influence of improper standing management of the wind driven generator on the subsequent operation is reduced, the data support is improved for integrally evaluating the operation safety of the wind driven generator, the analysis is performed from the angle of static combination so as to improve the accuracy of the analysis result, the management effect and the management precision of the wind driven generator are improved so as to reduce the operation failure risk of the wind driven generator, in addition, the analysis from the angles of dynamic interior and exterior is used for improving the supervision and early warning effect and the early warning precision when the wind driven generator is operated, and the wind driven generator is maintained and managed in an information feedback mode so as to help to know the operation safety and stability of the wind driven generator from the angles of component operation and operation characteristics.
The size of the values is set for ease of comparison, and regarding the size of the threshold, the number of cardinalities is set for each set of sample data depending on how many sample data are and the person skilled in the art; as long as the proportional relation between the parameter and the quantized value is not affected.
The above formulas are all formulas obtained by collecting a large amount of data for software simulation and selecting a formula close to the true value, and coefficients in the formulas are set by a person skilled in the art according to practical situations, and the above is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited thereto, and any person skilled in the art is within the technical scope of the present invention, and the technical scheme and the inventive concept according to the present invention are equivalent to or changed and are all covered in the protection scope of the present invention.
Claims (6)
1. The wind driven generator operation fault diagnosis system based on artificial intelligence is characterized by comprising a supervision platform, a data acquisition unit, a static supervision unit, an operation supervision unit, a characteristic expression unit, a fault risk unit and an early warning display unit;
when the supervision platform generates a management command, the management command is sent to the data acquisition unit and the static supervision unit, the data acquisition unit immediately acquires entity operation data and operation characteristic data of the wind driven generator after receiving the management command, the entity operation data represent rotor eccentric values and line eccentric values, the operation characteristic data comprise internal operation interference values and external salient values, the entity operation data and the operation characteristic data are respectively sent to the operation supervision unit and the characteristic display unit, and the operation supervision unit carries out front rotation deviation supervision evaluation analysis and interactive comparison analysis on the entity operation data after receiving the entity operation data, sends the obtained safety signals to the characteristic display unit and sends the obtained safety signals and early warning signals to the early warning display unit;
the feature expression unit performs side operation supervision feedback operation on the operation feature data after receiving the operation feature data and the safety signal, and sends an obtained risk signal to the early warning display unit;
the static supervision unit immediately collects management data of the wind driven generator after receiving the management command, wherein the management data comprises a damage evaluation value and an environmental impact value, performs operation impact feedback analysis on the management data, sends an obtained management signal to the fault risk unit, and sends the obtained impact signal to the early warning display unit through the supervision platform;
and after receiving the pipe transporting signal, the fault risk unit immediately carries out deep safety evaluation operation on the static operation risk coefficient T corresponding to the pipe transporting signal, and sends the obtained risk integration signal to the early warning display unit.
2. The wind turbine operation fault diagnosis system based on artificial intelligence according to claim 1, wherein the front rotation deviation supervision and evaluation analysis process of the operation supervision unit is as follows:
collecting the duration from the moment when the wind driven generator starts to generate to the moment when the wind driven generator ends, marking the duration as a time threshold, dividing the time threshold into i sub-time periods, wherein i is a natural number larger than zero, obtaining rotor eccentric values of the wind driven generator in each sub-time period, wherein the rotor eccentric values represent the parts of the rotor rotating track, the areas of which are surrounded by the rotor rotating tracks exceed a preset area, establishing a rectangular coordinate system by taking the number of the sub-time periods as an X axis and taking the rotor eccentric values as a Y axis, drawing a rotor eccentric value curve in a dot drawing manner, further obtaining the area surrounded by the rotor eccentric value curve and the X axis, marking the area as an eccentric risk area, comparing the eccentric risk area with a stored preset eccentric risk area threshold, and marking the parts of which the eccentric risk area is larger than the preset eccentric risk area threshold as a power generation influence value if the eccentric risk area is larger than the preset eccentric risk area threshold;
comparing the power generation influence value with a preset power generation influence value threshold value recorded and stored in the power generation influence value to analyze:
if the power generation influence value is smaller than a preset power generation influence value threshold, generating a normal signal;
and if the power generation influence value is greater than or equal to a preset power generation influence value threshold value, generating an alarm signal.
3. The wind turbine operational fault diagnosis system based on artificial intelligence according to claim 2, wherein the interactive comparison and analysis process of the operation supervision unit is as follows:
obtaining a line deviation value of a wind driven generator within a time threshold, wherein the line deviation value represents the number of the influence parameters of a line port, the influence parameters comprise an oxidation area, an operating resistance average value and a line loss rate, comparing and analyzing the line deviation value with a stored preset line deviation value threshold, and if the line deviation value is larger than the preset line deviation value threshold, marking the part of the line deviation value larger than the preset line deviation value threshold as a line influence value, and comparing the line influence value with the preset line influence value threshold recorded and stored in the line influence value:
if the ratio between the line influence value and the preset line influence value threshold is smaller than 1, generating an operation signal;
if the ratio between the line influence value and the preset line influence value threshold is greater than or equal to 1, generating an abnormal signal;
the signal interactive analysis is carried out on the normal signal, the alarm signal, the operation signal and the abnormal signal, and the specific signal interactive analysis process is as follows:
if the normal signal and the operation signal are generated, a safety signal is obtained;
and if the normal signal and the abnormal signal are generated, or the alarm signal and the operation signal are generated, or the alarm signal and the abnormal signal are generated, the early warning signal is obtained.
4. The wind turbine operation fault diagnosis system based on artificial intelligence according to claim 1, wherein the side operation supervision feedback operation process of the characteristic expression unit is as follows:
s1: acquiring an internal operation interference value in an internal gear box of the wind driven generator in each sub-time period, wherein the internal operation interference value represents an acute angle degree formed by the first intersection of a characteristic change curve of the internal lubricating oil temperature in the gear box and a preset characteristic change curve of the lubricating oil temperature, a rectangular coordinate system is established by taking the number of the sub-time periods as an X axis and the internal operation interference value as a Y axis, an internal operation interference value curve is drawn in a dot drawing mode, and further, the maximum crest value and the minimum trough value in the internal operation interference value curve are acquired, and the difference value between the maximum crest value and the minimum trough value in the internal operation interference value curve is marked as an operation blocking value;
s2: obtaining an apparent salient value of the wind driven generator within a time threshold, wherein the apparent salient value represents the minimum value in a time period corresponding to when a characteristic parameter curve is intersected with a preset normal characteristic parameter curve for the first time, the characteristic parameter curve comprises an abnormal sound mean value characteristic curve and a vibration amplitude mean value characteristic curve, the apparent salient value is compared with a stored preset apparent salient value threshold for analysis, and if the apparent salient value is smaller than the preset apparent salient value threshold, a part of the apparent salient value smaller than the preset apparent salient value threshold is marked as a characteristic evaluation value;
s3: comparing the operation impeding value and the characteristic evaluation value with a preset operation impeding value threshold value and a preset characteristic evaluation value threshold value which are recorded and stored in the operation impeding value and the characteristic evaluation value:
if the operation blocking value is smaller than the preset operation blocking value threshold and the characteristic evaluation value is smaller than the preset characteristic evaluation value threshold, no signal is generated;
and if the operation blocking value is greater than or equal to a preset operation blocking value threshold or the characteristic evaluation value is greater than or equal to a preset characteristic evaluation value threshold, generating a risk signal.
5. The wind turbine operational fault diagnosis system based on artificial intelligence according to claim 1, wherein the operational impact feedback analysis process of the static supervision unit is as follows:
SS1: collecting the time length of a period of time after the operation of the wind driven generator is finished, marking the time length as analysis time length, dividing the analysis time length into m sub-time nodes, wherein m is a natural number larger than zero, obtaining damage evaluation values of the wind driven generator in each sub-time node, wherein the damage evaluation values represent the number of component parts corresponding to the cooling value in unit time which is smaller than the preset cooling value in unit time, the component parts comprise a rotor, a generator and a gear box, further drawing a sector graph corresponding to the damage evaluation value which is smaller than or equal to the preset damage evaluation value threshold and the damage evaluation value which is larger than the preset damage evaluation value threshold in the time threshold, further obtaining the ratio of the sector area corresponding to the damage evaluation value which is smaller than or equal to the preset damage evaluation value threshold to the sector area corresponding to the damage evaluation value which is larger than the preset damage evaluation value threshold, and marking the ratio as an operation safety value YZ;
SS2: acquiring environment influence values of wind driven generators in each sub-time node, wherein the environment influence values represent the number corresponding to the internal environment parameters which are lower than a preset threshold value, the internal environment parameters comprise ventilation flow and temperature change values in unit time, a set A of the environment influence values is constructed, a maximum subset and a minimum subset in the set A are acquired, and the average value of the difference values between the maximum subset and the minimum subset in the set A is marked as an environment interference value HG;
SS3: according to the formulaObtaining a static running risk coefficient, wherein a1 and a2 are preset scale factor coefficients of a running safety value and an environment interference value respectively, a1 and a2 are positive numbers larger than zero, a3 is a preset correction factor coefficient, the value is 1.928, and T isThe static operation risk coefficient T is compared with a preset static operation risk coefficient threshold value recorded and stored in the static operation risk coefficient T, and analysis is carried out:
if the ratio between the static operation risk coefficient T and the preset static operation risk coefficient threshold value is more than or equal to 1, generating a pipe conveying signal;
and if the ratio between the static running risk coefficient T and the preset static running risk coefficient threshold is smaller than 1, generating an influence signal.
6. The artificial intelligence based wind turbine operational fault diagnosis system of claim 1, wherein the in-depth safety assessment operation process of the fault risk unit is as follows:
the method comprises the steps of calling an operation inhibition value and a characteristic evaluation value from a characteristic expression unit, simultaneously obtaining the number of data corresponding to management parameter information of the wind driven generator in a time threshold exceeding a preset threshold, marking the number as a management influence value, wherein the management parameter information comprises a maintenance interval duration mean value and a fault frequency, and marking the operation inhibition value, the characteristic evaluation value and the management influence value as YA, TP and GY respectively;
according to the formulaObtaining a power generation failure risk assessment coefficient, wherein f1, f2 and f3 are respectively preset weight factor coefficients of an operation blocking value, a characteristic assessment value and a management influence value, f1, f2 and f3 are positive numbers larger than zero, f4 is a preset fault tolerance factor coefficient, the value is 1.224, G is the power generation failure risk assessment coefficient, and the power generation failure risk assessment coefficient G is compared with a preset power generation failure risk assessment coefficient threshold value recorded and stored in the power generation failure risk assessment coefficient G:
if the ratio between the power generation fault risk assessment coefficient G and the preset power generation fault risk assessment coefficient threshold is smaller than 1, no signal is generated;
and if the ratio between the power generation fault risk assessment coefficient G and the preset power generation fault risk assessment coefficient threshold is greater than or equal to 1, generating a risk integration signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311429960.5A CN117231441A (en) | 2023-10-31 | 2023-10-31 | Wind driven generator operation fault diagnosis system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311429960.5A CN117231441A (en) | 2023-10-31 | 2023-10-31 | Wind driven generator operation fault diagnosis system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117231441A true CN117231441A (en) | 2023-12-15 |
Family
ID=89086203
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311429960.5A Withdrawn CN117231441A (en) | 2023-10-31 | 2023-10-31 | Wind driven generator operation fault diagnosis system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117231441A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117590822A (en) * | 2024-01-19 | 2024-02-23 | 无锡芯感智半导体有限公司 | MEMS gas pressure sensor dispensing processing supervision system based on Internet of things |
| CN117871142A (en) * | 2024-03-12 | 2024-04-12 | 烟台信谊电器有限公司 | Winding machine fault monitoring and judging method and system |
| CN117930733A (en) * | 2024-03-22 | 2024-04-26 | 上海惊叹化学有限公司 | Automatic explosion-proof linkage control system for polyurethane adhesive production process |
-
2023
- 2023-10-31 CN CN202311429960.5A patent/CN117231441A/en not_active Withdrawn
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117590822A (en) * | 2024-01-19 | 2024-02-23 | 无锡芯感智半导体有限公司 | MEMS gas pressure sensor dispensing processing supervision system based on Internet of things |
| CN117590822B (en) * | 2024-01-19 | 2024-03-22 | 无锡芯感智半导体有限公司 | MEMS gas pressure sensor dispensing processing supervision system based on Internet of things |
| CN117871142A (en) * | 2024-03-12 | 2024-04-12 | 烟台信谊电器有限公司 | Winding machine fault monitoring and judging method and system |
| CN117871142B (en) * | 2024-03-12 | 2024-05-28 | 烟台信谊电器有限公司 | Winding machine fault monitoring and judging method and system |
| CN117930733A (en) * | 2024-03-22 | 2024-04-26 | 上海惊叹化学有限公司 | Automatic explosion-proof linkage control system for polyurethane adhesive production process |
| CN117930733B (en) * | 2024-03-22 | 2024-05-28 | 上海惊叹化学有限公司 | Automatic explosion-proof linkage control system for polyurethane adhesive production process |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117231441A (en) | Wind driven generator operation fault diagnosis system based on artificial intelligence | |
| CN102787976B (en) | Method and system for the Dynamic Rule Engine on wind turbine airport | |
| CN104131950B (en) | Partitioning determination method for threshold value of temperature characteristic quantity of wind generating set | |
| CN103758696A (en) | SCADA (supervisory control and data acquisition) temperature parameter based wind turbine set security evaluation method | |
| CN109583075B (en) | Permanent magnet direct-drive wind turbine service quality evaluation method based on temperature parameter prediction | |
| CN112696481A (en) | Intelligent diagnosis method and device for shaft temperature abnormity of wind turbine generator gearbox | |
| Weijie et al. | Investigating instability of the wind turbine simulator with the conventional inertia emulation scheme | |
| CN114114006A (en) | Wind driven generator diagnosis device and diagnosis method thereof | |
| CN202994473U (en) | Wind power generation unit vibration on-line monitoring and fault diagnosis system | |
| CN103557117A (en) | Power curve acquisition device for wind turbine generator system | |
| US8407111B2 (en) | Method, system and computer program product for correlating information and location | |
| EP4060430A1 (en) | Systems and methods for operating power generating assets | |
| CN113761692B (en) | Method for identifying running states of multiple wind turbine generators based on migration component analysis | |
| CN114595989A (en) | Wind turbine generator performance evaluation method and device | |
| CN103217645A (en) | Covert fault monitoring method for fan of wind farm | |
| CN114320773A (en) | Wind turbine generator fault early warning method based on power curve analysis and neural network | |
| CN217384748U (en) | Fault trend diagnosis system for wind power plant group | |
| CN113468765B (en) | Component life determining method, system and readable storage medium | |
| Sriramalakshmi et al. | Time Series Analysis and Forecasting of Wind Turbine Data | |
| EP4040626A1 (en) | Systems and methods for operating a power generating asset | |
| CN114718808A (en) | Fan control method and system | |
| CN114135450A (en) | Full life cycle detection method for wind driven generator | |
| Jia et al. | Research on the method of digital twin operation and maintenance platform for intelligent early warning of wind turbine tower | |
| Wu | Advanced data-driven modelling approaches to alarm-related fault detection and condition monitoring of wind turbines | |
| CN106374527A (en) | Method for calculating electric energy production loss caused by limited power and machine halt of wind power plant cluster |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20231215 |
|
| WW01 | Invention patent application withdrawn after publication |