A method for intelligent remote monitoring of power equipment

Abstract

The present invention relates to the field of power equipment monitoring technology, and in particular to an intelligent remote monitoring method for power equipment. The present invention continuously obtains audio information and power generation of each wind turbine in a preset area, calculates wind turbine operation characterization parameters based on the audio information and power generation at predetermined intervals, divides each wind turbine operation category, and selects a processing method for monitoring data of each wind turbine according to the operation category of each wind turbine, including determining whether each wind turbine fails according to the power generation fluctuation amount of each wind turbine, or identifying a characteristic time domain segment, constructing an audio time domain fluctuation curve and fitting it with samples in a sample library to determine whether the wind turbine has an abnormality. The present invention obtains significant analysis information by identifying the characteristic time domain segment, and the analysis of the operating status of the wind turbine is more accurate and reliable.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment monitoring, and in particular to an intelligent remote monitoring method for power equipment. Background Art

[0002] Power equipment refers to equipment and facilities used for power generation, transmission, distribution and power conversion, and is an important part of the power system. Intelligent remote monitoring methods utilize a variety of technical means such as sensor technology, network communication technology, data processing technology and artificial intelligence algorithms to achieve comprehensive, real-time and intelligent monitoring and management of power equipment.

[0003] For example, Chinese patent publication number: CN105006887A discloses a system and method for realizing intelligent power distribution remote monitoring. The power equipment configuration information of various power equipment is stored in the cloud server, and the purpose of remote monitoring, remote control and intelligent setting is achieved through interactive synchronization with the monitoring client and the power equipment control unit. In addition, by automatically learning the user's power consumption, intelligent decision-making suggestions are provided to discover and prevent the risk of failure caused by overvoltage, overcurrent, abnormal load status, etc. The use of this system can realize the power distribution system with few people or no one on duty, reduce the operating costs of various power equipment, and improve the efficiency and automation level of power supply and distribution management.

[0004] However, there are still the following problems in the prior art:

[0005] In the prior art, when monitoring a wind turbine, whether there may be abnormalities in the operation of the wind turbine is not classified according to the operating status of the wind turbine, and a corresponding analysis strategy is not adopted for different operating statuses of the wind turbine, resulting in low reliability of monitoring the wind turbine. Summary of the invention

[0006] To this end, the present invention provides an intelligent remote monitoring method for power equipment to overcome the problem in the prior art that when monitoring wind turbines, whether there may be abnormalities in the operation of the wind turbines is not classified according to the operating status of the wind turbines, and corresponding analysis strategies are not adopted for different operating statuses of wind turbines, resulting in low monitoring reliability for wind turbines.

[0007] To achieve the above object, the present invention provides an intelligent remote monitoring method for electric power equipment, which comprises:

[0008] Step S1, continuously acquiring audio information and power generation of each wind turbine in a preset area, synchronously acquiring wind parameters of the wind turbine, and calculating wind turbine operation characteristic parameters according to the audio information and power generation at predetermined intervals, wherein the wind parameters include wind direction and wind speed;

[0009] Step S2, classifying each wind turbine operation category based on the wind turbine operation characterization parameters;

[0010] Step S3, selecting a processing method for monitoring data of each wind turbine according to the operation category of each wind turbine, including:

[0011] Monitor wind turbines in real time, determine whether each wind turbine has a fault based on the power fluctuation of each wind turbine, divide the wind turbine group into several wind turbine groups, and determine whether there is an abnormality in the wind turbine group;

[0012] Alternatively, an audio time domain fluctuation curve is constructed, and a characteristic time domain segment is identified based on the changes in wind speed and wind direction in the time domain segment. An audio time domain fluctuation curve is constructed for the audio information in the characteristic time domain segment and is fitted with samples in the sample library to determine whether there is an abnormality in the wind turbine.

[0013] Furthermore, in step S1, the wind turbine operation characteristic parameter is calculated according to formula (1):

[0014]

[0015] In formula (1), E represents the generator operation characteristic parameter, f represents the average audio frequency of the wind turbine generator within the predetermined time, fd represents the preset frequency threshold, P represents the average power generation of the wind turbine generator within the predetermined time, and Pd represents the preset power generation threshold.

[0016] Furthermore, in step S2, the wind turbine operation characteristic parameter is compared with a preset wind turbine operation characteristic parameter comparison threshold value.

[0017] If the wind turbine operation characterization parameter is greater than the preset wind turbine operation characterization parameter comparison threshold, classifying the wind turbine operation category as a hidden danger operation category;

[0018] If the wind turbine operation characterization parameter is less than or equal to the preset wind turbine operation characterization parameter comparison threshold, the wind turbine operation category is classified as a good operation category.

[0019] Furthermore, in step S3, a processing method for monitoring data of each wind turbine is selected according to the operation category of each wind turbine, wherein:

[0020] If the wind turbine operation category is a hidden danger operation category, the wind turbine is monitored in real time, and whether each wind turbine has a fault is determined based on the power fluctuation of each wind turbine. The wind turbine group is divided into several wind turbine groups to determine whether there is an abnormality in the wind turbine group;

[0021] If the wind turbine operation category is a good operation category, an audio time domain fluctuation curve is constructed, and the characteristic time domain segment is identified based on the wind speed and wind direction changes in the time domain segment. An audio time domain fluctuation curve is constructed for the audio information in the characteristic time domain segment and fit with the samples in the sample library to determine whether there is any abnormality in the wind turbine.

[0022] Furthermore, in step S3, the power generation fluctuation is calculated according to formula (2):

[0023]

[0024] In formula (2), Y represents the fluctuation of generated power, Pe represents the average value of the generated power obtained n times within the predetermined time, Pi represents the generated power obtained for the ith time, n is the number of times the generated power is obtained within the predetermined time, and n is a positive integer greater than 1.

[0025] Furthermore, in step S3, the power generation fluctuation amount is compared with a preset power generation fluctuation amount comparison threshold value.

[0026] If the power generation fluctuation amount is greater than a preset power generation fluctuation amount comparison threshold, it is determined that the generator fails.

[0027] Furthermore, in step S3, the proportion of faulty wind turbines in each wind turbine group to all wind turbines is obtained. If the proportion of faulty wind turbines in the wind turbine group to all wind turbines is greater than a preset proportion comparison threshold, it is determined that the wind turbine group has an abnormality.

[0028] Furthermore, in step S3, several time domain segments are divided, and the wind speed change value and wind direction change angle in each time domain segment are obtained. If the wind speed change value in the time domain segment is greater than a preset wind speed change value comparison threshold or the wind direction change angle is greater than a preset wind direction change angle comparison threshold, then the time domain segment is identified as a characteristic time domain segment.

[0029] Furthermore, in step S3, an audio amplitude time-domain fluctuation curve and an audio frequency time-domain fluctuation curve are respectively constructed for the audio amplitude and the audio frequency in the characteristic time-domain segment.

[0030] Furthermore, in step S3, the audio amplitude time domain fluctuation curve and the audio frequency time domain fluctuation curve are respectively fitted with the audio amplitude time domain fluctuation sample curve and the audio frequency time domain fluctuation sample curve in the sample library,

[0031] If the fitting value of the audio amplitude time-domain fluctuation curve or the audio frequency time-domain fluctuation curve is less than a preset fitting comparison threshold, it is determined that the wind turbine generator is abnormal.

[0032] Compared with the prior art, the present invention continuously obtains audio information and power generation of each wind turbine in a preset area, calculates wind turbine operation characterization parameters based on the audio information and power generation at predetermined intervals, divides each wind turbine operation category, and selects a processing method for monitoring data of each wind turbine according to the operation category of each wind turbine, including determining whether each wind turbine has a fault based on the power generation fluctuation of each wind turbine, or identifying characteristic time domain segments, constructing an audio time domain fluctuation curve to fit the samples in the sample library, and determining whether the wind turbine has an abnormality. The present invention obtains significant analysis information by identifying characteristic time domain segments, and the analysis of the operating status of wind turbines is more accurate and reliable.

[0033] In particular, the present invention calculates the wind turbine operation characterization parameters based on the audio information and the power generation. During the operation of the wind turbine, the audio frequency and power generation of the wind turbine are important parameters for determining whether the wind turbine is operating normally. When the audio frequency and power generation of the wind turbine differ from the data of the wind turbine in the sample library when the wind turbine is operating normally, it can be determined to a certain extent that the wind turbine may be abnormal at this time. By calculating the wind turbine operation characterization parameters, it helps to provide data support for subsequent analysis.

[0034] In particular, the present invention determines whether each wind turbine has a fault based on the power generation fluctuation of each wind turbine. The power generation fluctuation during the operation of the wind turbine is an important parameter for determining whether the wind turbine is operating stably. When the wind turbine is operating normally, its power generation fluctuation should be relatively low. When the power generation fluctuation is large, it can be determined to a certain extent that the operation of the wind turbine is abnormal. The power generation fluctuation can reliably determine whether the wind turbine is abnormal.

[0035] In particular, the present invention divides the wind turbine generator set into several wind turbine generator groups to determine whether there is any abnormality in the wind turbine generator group. Since the operating status of the wind turbine generator is affected by the environment, when a large number of wind turbine generators in the wind turbine generator group fail, it may happen that the environment in which the wind turbine generator group is located has an impact on the normal operation of the wind turbine generators. Determining whether there is any abnormality in the wind turbine generator group is helpful to conduct preventive evaluation of the operating status of the wind turbine generator.

[0036] In particular, the present invention identifies characteristic time domain segments based on the changes in wind speed and wind direction within the time domain segment. When the wind speed and wind direction change greatly, the audio changes of the wind turbine are more significant than when the wind speed and wind direction are stable, and the data is highly representative. An audio time domain fluctuation curve is constructed for the audio information in the characteristic time domain segment and fits the curve with the samples in the sample library. This can more reliably and accurately determine whether there are abnormalities in the operation of the wind turbine, and make the judgment on the operating status of the wind turbine more accurate and reliable. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 A step diagram of a method for intelligent remote monitoring of electric power equipment according to an embodiment of the invention;

[0038] Figure 2 A diagram showing a method for processing monitoring data of each wind turbine according to an embodiment of the invention;

[0039] Figure 3 A logical determination diagram of whether a wind turbine generator failure occurs according to an embodiment of the invention;

[0040] Figure 4 This is a logic decision diagram of the recognition feature time domain segment of an embodiment of the invention. DETAILED DESCRIPTION

[0041] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0042] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0043] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the term "connection" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0044] See also Figure 1-Figure 4 As shown, Figure 1 This is a step diagram of the intelligent remote monitoring method for power equipment according to an embodiment of the invention. Figure 2 The processing method for monitoring data of each wind turbine generator is selected in the embodiment of the invention. Figure 3 This is a logic diagram for determining whether a wind turbine fails according to an embodiment of the invention. Figure 4 The identification characteristic time domain segment logic decision diagram of the embodiment of the invention, the intelligent remote monitoring method of the power equipment of the present invention includes:

[0045] Step S1, continuously acquiring audio information and power generation of each wind turbine in a preset area, synchronously acquiring wind parameters of the wind turbine, and calculating wind turbine operation characterization parameters according to the audio information and power generation at predetermined intervals, wherein the wind parameters include wind direction and wind speed;

[0046] Step S2, classifying each wind turbine operation category based on the wind turbine operation characterization parameters;

[0047] Step S3, selecting a processing method for monitoring data of each wind turbine according to the operation category of each wind turbine, including:

[0048] Monitor wind turbines in real time, determine whether each wind turbine has a fault based on the power fluctuation of each wind turbine, divide the wind turbine group into several wind turbine groups, and determine whether there is an abnormality in the wind turbine group;

[0049] Alternatively, an audio time domain fluctuation curve is constructed, and a characteristic time domain segment is identified based on the changes in wind speed and wind direction in the time domain segment. An audio time domain fluctuation curve is constructed for the audio information in the characteristic time domain segment and is fitted with samples in the sample library to determine whether there is an abnormality in the wind turbine.

[0050] Specifically, the present invention does not limit the specific method of obtaining the audio information of each wind turbine. The audio information of each wind turbine may be obtained through a microphone. This is a prior art and will not be described in detail.

[0051] Specifically, the present invention does not limit the specific method of obtaining the power generation of each wind turbine. The power value can be calculated by measuring the current and voltage through a current sensor and a voltage sensor. This is a prior art and will not be described in detail.

[0052] Specifically, the present invention obtains the wind speed through a wind speed sensor and obtains the wind direction through a wind direction sensor. This is the prior art and will not be described in detail.

[0053] Specifically, the present invention divides the wind turbines in a preset area into a plurality of wind turbine groups according to the area, and each area is equal in size.

[0054] Specifically, the environmental parameters of the wind turbines in the preset area selected by the present invention are relatively similar, for example, wind speed, temperature, humidity, etc.

[0055] In this embodiment, the predetermined time is selected within the range of [20s, 30s].

[0056] Specifically, in step S1, the wind turbine operation characteristic parameters are calculated according to formula (1):

[0057]

[0058] In formula (1), E represents the generator operation characteristic parameter, f represents the average audio frequency of the wind turbine generator within the predetermined time, fd represents the preset frequency threshold, P represents the average power generation of the wind turbine generator within the predetermined time, and Pd represents the preset power generation threshold.

[0059] In this embodiment, fd and Pd can be obtained through a sample library, which stores the operating parameters of wind turbines under various environmental conditions. In this embodiment, the average audio frequency and average power generation power of several wind turbines with the same wind parameters in normal operation within a predetermined time are selected from the sample library, and their average values ​​fde and Pde are calculated. It is assumed that fd=a×fde, a is the audio coefficient, 0.9<a<1.1, Pd=b×Pde, b is the power generation power coefficient, 0.9<b<1.1.

[0060] Specifically, the present invention calculates the wind turbine operation characterization parameters based on the audio information and the power generation. During the operation of the wind turbine, the audio frequency and power generation of the wind turbine are important parameters for determining whether the wind turbine is operating normally. When the audio frequency and power generation of the wind turbine differ from the data of the wind turbine in the sample library when the wind turbine is operating normally, it can be determined to a certain extent that the wind turbine may be abnormal at this time. By calculating the wind turbine operation characterization parameters, it helps to provide data support for subsequent analysis.

[0061] Specifically, in step S2, the wind turbine operation characteristic parameter is compared with a preset wind turbine operation characteristic parameter comparison threshold value.

[0062] If the wind turbine operation characterization parameter is greater than the preset wind turbine operation characterization parameter comparison threshold, classifying the wind turbine operation category as a hidden danger operation category;

[0063] If the wind turbine operation characterization parameter is less than or equal to the preset wind turbine operation characterization parameter comparison threshold, the wind turbine operation category is classified as a good operation category.

[0064] In this embodiment, the preset generator operation characterization parameter comparison threshold is selected within the range of [1, 1.2].

[0065] Specifically, in step S3, a processing method for monitoring data of each wind turbine is selected according to the operation category of each wind turbine, wherein:

[0066] If the wind turbine operation category is a hidden danger operation category, the wind turbine is monitored in real time, and whether each wind turbine has a fault is determined based on the power fluctuation of each wind turbine. The wind turbine group is divided into several wind turbine groups to determine whether there is an abnormality in the wind turbine group;

[0067] If the wind turbine operation category is a good operation category, an audio time domain fluctuation curve is constructed, and the characteristic time domain segment is identified based on the wind speed and wind direction changes in the time domain segment. An audio time domain fluctuation curve is constructed for the audio information in the characteristic time domain segment and fit with the samples in the sample library to determine whether there is any abnormality in the wind turbine.

[0068] Specifically, the power generation fluctuation is calculated according to formula (2):

[0069]

[0070] In formula (2), Y represents the fluctuation of generated power, Pe represents the average value of the generated power obtained n times within the predetermined time, Pi represents the generated power obtained for the ith time, n is the number of times the generated power is obtained within the predetermined time, and n is a positive integer greater than 1.

[0071] Specifically, in step S3, the power generation fluctuation amount is compared with a preset power generation fluctuation amount comparison threshold value.

[0072] If the power generation fluctuation amount is greater than a preset power generation fluctuation amount comparison threshold, it is determined that the generator fails.

[0073] Specifically, the present invention determines whether each wind turbine has a fault based on the power generation fluctuation of each wind turbine. The power generation fluctuation during the operation of the wind turbine is an important parameter for determining whether the wind turbine is operating stably. When the wind turbine is operating normally, its power generation fluctuation should be relatively low. When the power generation fluctuation is large, it can be determined to a certain extent that the operation of the wind turbine is abnormal. The power generation fluctuation can reliably determine whether the wind turbine is abnormal.

[0074] Specifically, in step S3, the proportion of faulty wind turbines in each wind turbine group to all wind turbines is obtained. If the proportion of faulty wind turbines in the wind turbine group to all wind turbines is greater than a preset proportion comparison threshold, it is determined that the wind turbine group has an abnormality.

[0075] In this embodiment, the preset ratio contrast threshold is selected within the range of [0.6, 0.9].

[0076] Specifically, the present invention divides the wind turbine generator set into several wind turbine generator groups and determines whether there is any abnormality in the wind turbine generator group. Since the operating status of the wind turbine generator is affected by the environment, when a large number of wind turbine generators in the wind turbine generator group fail, it may happen that the environment in which the wind turbine generator group is located has an impact on the normal operation of the wind turbine generators. Determining whether there is an abnormality in the wind turbine generator group is helpful to preventively evaluate the operating status of the wind turbine generator.

[0077] In this embodiment, the preset abnormal reference value comparison threshold is selected within the range of [1, 1.2].

[0078] Specifically, in step S3, several time domain segments are divided, and the wind speed change value and wind direction change angle in each time domain segment are obtained. If the wind speed change value in the time domain segment is greater than a preset wind speed change value comparison threshold or the wind direction change angle is greater than a preset wind direction change angle comparison threshold, then the time domain segment is identified as a characteristic time domain segment.

[0079] In this embodiment, the preset wind speed change value comparison threshold is selected within the range of [2m / s, 4m / s], and the preset wind direction change angle comparison threshold is selected within the range of [10°, 20°].

[0080] Specifically, in step S3, an audio amplitude time domain fluctuation curve and an audio frequency time domain fluctuation curve are constructed respectively for the audio amplitude and the audio frequency in the characteristic time domain segment.

[0081] Specifically, in step S3, the audio amplitude time domain fluctuation curve and the audio frequency time domain fluctuation curve are respectively fitted with the audio amplitude time domain fluctuation sample curve and the audio frequency time domain fluctuation sample curve in the sample library.

[0082] If the fitting value of the audio amplitude time-domain fluctuation curve or the audio frequency time-domain fluctuation curve is less than a preset fitting comparison threshold, it is determined that the wind turbine generator is abnormal.

[0083] In this embodiment, the preset fitting comparison threshold is selected within the range of [0.85, 0.95].

[0084] Specifically, the present invention identifies characteristic time domain segments based on the changes in wind speed and wind direction within the time domain segment. When the wind speed and wind direction change greatly, the audio changes of the wind turbine are more significant than when the wind speed and wind direction are stable, and the data is highly representative. An audio time domain fluctuation curve is constructed for the audio information in the characteristic time domain segment and fits with the samples in the sample library. This can more reliably and accurately determine whether there are abnormalities in the operation of the wind turbine, and make the judgment on the operating status of the wind turbine more accurate and reliable.

[0085] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

Claims

1. An intelligent remote monitoring method for power equipment, characterized in that: include: Step S1, continuously obtaining audio information and power generation of each wind turbine in a preset area, synchronously obtaining wind parameters of the wind turbine, and calculating wind turbine operation characterization parameters according to the audio information and power generation at predetermined intervals; In step S1, the wind turbine operation characteristic parameters are calculated according to formula (1): In formula (1), E represents the generator operation characteristic parameter, f represents the average audio frequency of the wind turbine generator within the predetermined time, fd represents the preset frequency threshold, P represents the average power generation of the wind turbine generator within the predetermined time, and Pd represents the preset power generation threshold; Step S2, classifying each wind turbine operation category based on the wind turbine operation characterization parameters; In the step S2, the wind turbine operation characteristic parameter is compared with a preset wind turbine operation characteristic parameter comparison threshold value. If the wind turbine operation characterization parameter is greater than the preset wind turbine operation characterization parameter comparison threshold, classifying the wind turbine operation category as a hidden danger operation category; If the wind turbine operation characterization parameter is less than or equal to the preset wind turbine operation characterization parameter comparison threshold, classifying the wind turbine operation category as a good operation category; Step S3, selecting a processing method for monitoring data of each wind turbine according to the operation category of each wind turbine, including: If the wind turbine operation category is a hidden danger operation category, the wind turbine is monitored in real time, and whether each wind turbine has a fault is determined based on the power fluctuation of each wind turbine. The wind turbine group is divided into several wind turbine groups to determine whether there is an abnormality in the wind turbine group; If the wind turbine operation category is a good operation category, an audio time domain fluctuation curve is constructed, and a characteristic time domain segment is identified based on the wind speed and wind direction changes in the time domain segment. An audio time domain fluctuation curve is constructed for the audio information in the characteristic time domain segment and fitted with the samples in the sample library to determine whether the wind turbine has an abnormality; In step S3, the power generation fluctuation is calculated according to formula (2): In formula (2), Y represents the fluctuation of generated power, Pe represents the average value of the generated power obtained n times within the predetermined time, Pi represents the generated power obtained for the ith time, n is the number of times the generated power is obtained within the predetermined time, and n is a positive integer greater than 1.

2. The intelligent remote monitoring method for electric power equipment according to claim 1, characterized in that: In step S3, the power generation fluctuation amount is compared with a preset power generation fluctuation amount comparison threshold value. If the power generation fluctuation amount is greater than a preset power generation fluctuation amount comparison threshold, it is determined that the generator fails.

3. The intelligent remote monitoring method for electric power equipment according to claim 1, characterized in that: In step S3, the proportion of faulty wind turbines in each wind turbine group to all wind turbines is obtained. If the proportion of faulty wind turbines in the wind turbine group to all wind turbines is greater than a preset proportion comparison threshold, it is determined that the wind turbine group has an abnormality.

4. The intelligent remote monitoring method for electric power equipment according to claim 1, characterized in that: In step S3, the time domain segment is divided into several sub-time domain segments, and the wind speed change value and wind direction change angle in each sub-time domain segment are obtained. If the wind speed change value in the sub-time domain segment is greater than a preset wind speed change value comparison threshold or the wind direction change angle is greater than a preset wind direction change angle comparison threshold, the sub-time domain segment is identified as a characteristic time domain segment.

5. The intelligent remote monitoring method for electric power equipment according to claim 4, characterized in that: In the step S3, an audio amplitude time domain fluctuation curve and an audio frequency time domain fluctuation curve are respectively constructed for the audio amplitude and the audio frequency in the characteristic time domain segment.

6. The intelligent remote monitoring method for electric power equipment according to claim 1, characterized in that: In step S3, the audio amplitude time domain fluctuation curve and the audio frequency time domain fluctuation curve are respectively fitted with the audio amplitude time domain fluctuation sample curve and the audio frequency time domain fluctuation sample curve in the sample library. If the fitting value of the audio amplitude time-domain fluctuation curve or the audio frequency time-domain fluctuation curve is less than a preset fitting comparison threshold, it is determined that the wind turbine generator is abnormal.

Images