Power transformation equipment monitoring method and device based on vibration signals and structural noise
By collecting and processing the vibration signals and structural noise data of the substation equipment, obtaining noise and vibration characteristics, and calculating monitoring weighted values, the problem of insufficient subjectivity and real-time human inspection in the prior art is solved, and the substation equipment is realized Efficient and accurate monitoring and maintenance.
Patent Information
- Application Number
- CN202411047041.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-01
- Publication Date
- 2024-11-15
AI Technical Summary
The existing technology relies on manual experience in substation equipment inspection, which leads to strong subjectivity, consumes a lot of human resources and is unable to feedback abnormal conditions in real time, resulting in large-scale abnormalities and huge losses in the power grid.
Using a monitoring method based on vibration signals and structural noise, the vibration signals and structural noise data of the substation equipment are collected and processed, and the noise and vibration characteristic data are obtained, and the monitoring weight value is calculated to evaluate the equipment. Running status.
Real-time, comprehensive and accurate monitoring of substation equipment is realized, the subjectivity of manual inspection is reduced, monitoring efficiency and maintenance accuracy are improved, and a stronger maintenance reference basis is provided.
Smart Images

Figure CN118965224A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of substation equipment monitoring, and in particular to a substation equipment monitoring method and device based on vibration signals and structural noise. Background Art
[0002] At present, users are paying more and more attention to the quality and safety of power supply, so it is very important to ensure the safe and stable operation of the power grid. Substation equipment is an important part of the power grid operation. Inspection and related maintenance of substations are the key to ensure the stable operation of substation equipment. At present, the management of substation equipment is mainly achieved by intelligent centralized monitoring and regular inspections with operators. However, in the actual inspection process, some abnormal operation conditions of substation equipment require on-site inspection and monitoring by experienced operation and maintenance personnel to be discovered. This inspection method consumes a lot of human resources, is highly subjective, and requires operation and maintenance personnel to have more professional experience reserves. In addition, due to the periodicity of the inspection of operation and maintenance personnel, the abnormal conditions of transformer equipment often cannot be fed back and resolved in real time, which causes the abnormality of substation equipment to further deteriorate and develop into a chain failure, resulting in large-scale abnormalities in the power grid, and ultimately causing huge losses to the entire power system. Summary of the invention
[0003] The present invention provides a method and a device for monitoring substation equipment based on vibration signals and structural noise, which can monitor and evaluate substation equipment efficiently and accurately.
[0004] In order to solve the above technical problems, an embodiment of the present invention provides a substation equipment monitoring method based on vibration signals and structural noise, comprising:
[0005] Collect vibration signals of substation equipment and structural noise data in substations at preset time intervals;
[0006] De-noising and separating the structural noise data in the substation to obtain a solid noise component, and obtaining noise characteristic data according to the solid noise component;
[0007] Performing time domain processing and frequency domain processing on the vibration signal of the substation equipment in sequence to obtain time domain characteristics and frequency domain characteristics of the vibration signal, and obtaining vibration characteristic data according to the time domain characteristics and frequency domain characteristics;
[0008] A monitoring weighted value is obtained according to the noise characteristic data and the vibration characteristic data, and the operating state of the substation equipment is evaluated according to the monitoring weighted value.
[0009] The beneficial effects of the embodiments of the present invention are:
[0010] The embodiment of the present invention performs denoising and separation on structural noise data to obtain noise characteristic data, performs time-frequency domain processing on the collected vibration signal to obtain vibration characteristic data, and then obtains a monitoring weighted value based on the obtained noise characteristic data and vibration characteristic data to evaluate the operating status of the substation equipment; the substation equipment will generate vibration and make sound during operation, and the vibration and sound information reflects the operating status of the substation equipment, and the vibration and sound are closely related and can represent different detailed information. With the help of this information, the abnormality of the equipment can be better monitored and analyzed. The embodiment of the present invention can monitor and evaluate the operating status of the substation equipment in combination with the acquired noise characteristics and vibration characteristics, avoid the subjectivity of manual inspections and the one-sided results brought about by monitoring the substation equipment based on only a single indicator, and can monitor the substation equipment more comprehensively, accurately, in real time and efficiently, providing a strong reference basis for the subsequent maintenance and management of the substation equipment.
[0011] As a preferred solution, the denoising and separation of the structural noise data in the substation to obtain the solid noise component includes:
[0012] De-noising the structural noise data in the substation to obtain a discrete sequence of structural noise;
[0013] Based on the structural noise discrete sequence, the component subset, characteristic frequency subset and variation coefficient are initialized, and a time-frequency constraint model is constructed with the characteristic bandwidth and minimum of each component in the component subset as the goal; wherein the time-frequency constraint model is specifically:
[0014]
[0015] In the above formula, J is the number of components; BW is the characteristic bandwidth of the component; is the single-sided spectrum of the component; f ct is the preset characteristic frequency;
[0016] Iteratively updating the component subset, the frequency subset and the variation coefficient based on the first component in the component subset until the iteration constraint condition is satisfied, and obtaining the first component corresponding to the first component; repeating this step until obtaining a plurality of components corresponding to each component in the component subset, and completing the solution of the time-frequency constraint model;
[0017] Based on a preset spectrum sequence, several components are compared in sequence, and a solid noise component is separated from the several components.
[0018] This preferred solution performs data denoising before signal separation to remove interference data caused by harsh operating environment or unstable load, improve the signal-to-noise ratio of the required noise components in the structural noise, provide strong support for subsequent structural noise feature extraction, strengthen the vibration characteristics of the substation equipment, more fully explore the required noise information, and further establish the accuracy and reliability of substation equipment monitoring and evaluation; in the substation, the solid noise, vibration source excitation induced noise and other environmental interference noise of the substation equipment are often coupled with each other and difficult to distinguish. After completing data denoising, this preferred solution realizes the frequency domain division and effective separation of each component in the structural noise by constructing and solving the time-frequency constraint model, and further obtains the solid noise component based on the preset spectrum sequence. The obtained solid noise component can well characterize the operating status of the substation equipment itself.
[0019] As a preferred solution, the denoising process is performed on the structural noise data in the substation to obtain a discrete sequence of structural noise, including:
[0020] converting the structure-borne noise data in the substation into an initial discrete sequence;
[0021] Based on a preset transformation function, the initial discrete sequence is decomposed to obtain a plurality of transformation coefficients, transformation coefficients whose absolute values are greater than a preset transformation threshold are retained from the plurality of transformation coefficients, and a discrete sequence to be processed is obtained according to the retained transformation coefficients using a preset inverse transformation function;
[0022] After compensating the preset components of the discrete sequence to be processed based on the preset filter, a structured noise discrete sequence is obtained.
[0023] This preferred solution converts the structural noise data into an initial discrete sequence for subsequent denoising; then, based on a preset transformation function and a preset transformation threshold, the required transformation coefficient is obtained to complete preliminary rapid denoising, and the threshold method can better suppress unnecessary data; the frequencies of effective characteristic noise signals and interference signals such as environmental noise emitted by substation equipment under various operating conditions are different, so this preferred solution then uses a preset filter to compensate the denoised signal for a preset component, increases the required noise signal component, and makes the spectral parameters of the noise data tend to be stable, which helps to improve the signal-to-noise ratio of the noise signal for noise signal spectrum analysis, and further better obtains the acoustic characteristics related to the transformer noise signal.
[0024] As a preferred solution, the step of obtaining noise characteristic data according to the solid noise component includes:
[0025] Obtain a noise data set according to the solid noise component;
[0026] Dividing the noise data set according to a preset ratio to obtain two noise sub-data sets;
[0027] Inputting the two noise sub-data sets into two neural networks of a preset feature extraction model correspondingly, and outputting first feature data and second feature data;
[0028] Feature fusion is performed on the first feature data and the second feature data to obtain noise feature data.
[0029] This preferred solution divides the noise data set and uses different types of neural networks to extract features of solid noise components respectively, and then fuses the different feature data extracted by the two networks to ensure the comprehensiveness of the extracted noise features and reduce the data dimension, thereby improving the data utilization rate of the noise data set.
[0030] As a preferred solution, the vibration signal of the substation equipment is processed in time domain and frequency domain in sequence to obtain time domain characteristics and frequency domain characteristics of the vibration signal, and vibration characteristic data is obtained according to the time domain characteristics and frequency domain characteristics, including:
[0031] Performing a convolution operation on the vibration signal of the substation equipment and a preset characteristic wavelet based on a preset characteristic frequency and characteristic scale, and extracting a time domain feature of the vibration signal from the convolution operation result;
[0032] Rearranging the vibration signal of the power conversion equipment in reverse order to obtain a plurality of subsequences and a plurality of recursive levels; performing butterfly operations on the plurality of subsequences in turn at each recursive level until a second preset condition is met to obtain a vibration spectrum;
[0033] Obtaining frequency domain characteristics of the vibration signal based on the vibration spectrum;
[0034] Vibration characteristic data is obtained according to the time domain characteristics and the frequency domain characteristics.
[0035] This preferred solution performs convolution operations on the vibration signal and the preset characteristic wavelet according to the preset characteristic frequency and characteristic scale, so as to quickly and effectively obtain the time domain characteristics of the vibration signal; then, this preferred solution performs bit-reversal rearrangement on the vibration signal and performs butterfly operations on several subsequences, which is simple to calculate and can conveniently and efficiently obtain the vibration spectrum. The vibration spectrum can intuitively convey rich signal frequency domain information, and the frequency domain characteristics of the vibration signal can be conveniently and quickly obtained based on the vibration spectrum; finally, this preferred solution obtains the vibration characteristic data according to the time domain characteristics and the frequency domain characteristics, which can convey the relationship between the signal frequency and time, and can better and comprehensively characterize the characteristics of the vibration signal of the substation equipment.
[0036] As a preferred solution, obtaining a monitoring weighted value according to the noise characteristic data and the vibration characteristic data, and evaluating the operating state of the substation equipment according to the monitoring weighted value includes:
[0037] After the noise characteristic data and the vibration characteristic data are dimensionally processed respectively by a preset dimension processing formula, a number of corresponding dimension averages are obtained; the preset dimension processing formula is specifically:
[0038]
[0039] In the above formula, k is the corresponding feature data size; σ is the preset processing coefficient; x i is a characteristic data component in the noise characteristic data or the vibration characteristic data; is the average number of steel after dimension processing;
[0040] Assigning a number of preset weight values corresponding to the number of steel quantity averages, and obtaining a monitoring weighted value according to the number of steel quantity averages and the corresponding number of preset weight values;
[0041] Comparing the monitoring weighted value with a preset threshold, and when the monitoring weighted value is greater than the preset threshold, determining that the operating state of the substation equipment is abnormal;
[0042] Compare a plurality of steel measurement averages with a plurality of steel measurement thresholds or preset steel measurement ranges respectively, and retain the steel measurement averages that are greater than the corresponding steel measurement thresholds or exceed the corresponding preset steel measurement ranges;
[0043] According to the retained average steel quantity, a first fault cause is searched and obtained in a preset fault cause set, and warning information is output according to the first fault cause.
[0044] This preferred scheme proposes a quantitative evaluation method for the operating status of substation equipment, which performs dimensional processing on the noise characteristic data and the vibration characteristic data based on a preset dimensional processing formula, so that the noise characteristic data and the vibration characteristic data are converted into the same scale, and a number of dimensional averages that can characterize multiple information of vibration signals and structural noise are obtained, so as to eliminate the dimensional influence between different data or characteristics. After that, this preferred scheme evaluates a number of dimensional averages through a number of dimensional thresholds, further evaluates whether there are features that need attention in the noise characteristic data and the vibration characteristic data, and finally searches and obtains the first fault cause in the pre-constructed fault cause set according to the retained dimensional averages, and outputs warning information according to the first fault cause. When the substation equipment is abnormal, this preferred scheme can help operation and maintenance personnel quickly determine the abnormal area and possible causes, narrow the search range, and enable emergency repair personnel to efficiently and accurately perform substation equipment maintenance.
[0045] Accordingly, in order to solve the above technical problems, an embodiment of the present invention further provides a substation equipment monitoring device based on vibration signals and structural noise, comprising: a data acquisition module, a noise feature acquisition module, a vibration feature acquisition module and a monitoring and evaluation module;
[0046] Wherein, the data acquisition module is used to collect vibration signals of substation equipment and structural noise data in the substation at preset time intervals;
[0047] The noise characteristic acquisition module is used to perform denoising and separation on the structural noise data in the substation to obtain a solid noise component, and obtain noise characteristic data according to the solid noise component;
[0048] The vibration feature acquisition module is used to perform time domain processing and frequency domain processing on the vibration signal of the substation equipment in sequence to obtain the time domain features and frequency domain features of the vibration signal, and obtain vibration feature data according to the time domain features and frequency domain features;
[0049] The monitoring and evaluation module is used to obtain a monitoring weighted value according to the noise characteristic data and the vibration characteristic data, and evaluate the operating status of the substation equipment according to the monitoring weighted value.
[0050] As a preferred solution, the noise feature acquisition module includes: a denoising unit, an iteration unit and a separation unit;
[0051] The denoising unit is used to perform denoising on the structural noise data in the substation to obtain a discrete sequence of structural noise;
[0052] The iteration unit is used to initialize the component subset, characteristic frequency subset and variation coefficient based on the discrete sequence of the structural noise, and to construct a time-frequency constraint model with the characteristic bandwidth and minimum of each component in the component subset as the goal; iteratively update the component subset, frequency subset and variation coefficient based on the first component in the component subset until the iteration constraint condition is satisfied, and obtain the first component corresponding to the first component; repeat this step until a number of components corresponding to each component in the component subset are obtained, and the solution of the time-frequency constraint model is completed; wherein the time-frequency constraint model is specifically:
[0053]
[0054] In the above formula, J is the number of components; BW is the characteristic bandwidth of the component; is the single-sided spectrum of the component; f ct is the preset characteristic frequency;
[0055] The separation unit is used to sequentially compare a plurality of components based on a preset frequency spectrum sequence, and separate a solid noise component from the plurality of components.
[0056] As a preferred solution, the vibration feature acquisition module includes: a time domain analysis unit, a frequency domain analysis unit and a vibration feature acquisition unit;
[0057] The time domain analysis unit is used to perform a convolution operation on the vibration signal of the substation equipment and a preset characteristic wavelet based on a preset characteristic frequency and characteristic scale, and extract the time domain characteristics of the vibration signal from the convolution operation result;
[0058] The frequency domain analysis unit is used to perform bit-reversal rearrangement on the vibration signal of the substation equipment to obtain a plurality of subsequences and a plurality of recursive levels; at each recursive level, butterfly operations are performed on the plurality of subsequences in turn until a second preset condition is met to obtain a vibration spectrum; and frequency domain features of the vibration signal are obtained based on the vibration spectrum;
[0059] The vibration feature acquisition unit is used to obtain vibration feature data according to the time domain feature and the frequency domain feature.
[0060] As a preferred solution, the monitoring and evaluation module includes: a dimensional processing unit, a weighted acquisition unit and an evaluation and early warning unit;
[0061] The dimension processing unit is used to perform dimension processing on the noise characteristic data and the vibration characteristic data respectively through a preset dimension processing formula to obtain a number of corresponding dimension averages; the preset dimension processing formula is specifically:
[0062]
[0063] In the above formula, k is the corresponding feature data size; σ is the preset processing coefficient; x i is a characteristic data component in the noise characteristic data or the vibration characteristic data; is the average number of steel after dimension processing;
[0064] The weighted acquisition unit is used to assign a number of preset weight values corresponding to the number of steel measurement averages, and obtain a monitoring weight value according to the number of steel measurement averages and the corresponding number of preset weight values;
[0065] The evaluation and early warning unit is used to compare the monitoring weighted value with a preset threshold value, and when the monitoring weighted value is greater than the preset threshold value, determine that the operating state of the substation equipment is abnormal;
[0066] The evaluation and early warning unit is further used to compare a plurality of steel measurement averages with a plurality of steel measurement thresholds or preset steel measurement ranges, and retain the steel measurement averages that are greater than the corresponding steel measurement thresholds or exceed the corresponding preset steel measurement ranges;
[0067] The evaluation and early warning unit is further used to search and obtain a first fault cause in a preset fault cause set according to the retained average steel quantity, and output early warning information according to the first fault cause. BRIEF DESCRIPTION OF THE DRAWINGS
[0068] Figure 1 : A flow chart of an embodiment of a method for monitoring substation equipment based on vibration signals and structural noise provided by the present invention;
[0069] Figure 2 : A schematic structural diagram of an embodiment of a substation equipment monitoring device based on vibration signals and structural noise provided by the present invention;
[0070] Figure 3 : A structural diagram of an embodiment of a noise feature acquisition module provided by the present invention;
[0071] Figure 4 : A structural schematic diagram of an embodiment of a vibration feature acquisition module provided by the present invention;
[0072] Figure 5 : A schematic diagram of the structure of an embodiment of the monitoring and evaluation module provided by the present invention. DETAILED DESCRIPTION
[0073] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0074] At present, in the actual inspection and management process of substation equipment, some abnormal operating conditions of substation equipment need to be discovered by experienced operation and maintenance personnel through on-site inspection and monitoring. This inspection method consumes a lot of human resources, is highly subjective, and requires operation and maintenance personnel to have more professional experience reserves. In addition, due to the periodicity of the inspection by operation and maintenance personnel, the abnormal conditions of transformer equipment often cannot be fed back and solved in real time, which causes the abnormality of substation equipment to further deteriorate and develop into a chain failure, resulting in large-scale abnormalities in the power grid, and ultimately causing huge losses to the entire power system.
[0075] Embodiment 1
[0076] In order to solve the above technical problems, the present invention provides a substation equipment monitoring method and device based on vibration signals and structural noise, which can monitor and evaluate substation equipment efficiently and accurately.
[0077] Please refer to Figure 1, is a flow chart of an embodiment of a method for monitoring substation equipment based on vibration signals and structural noise provided by an embodiment of the present invention. Figure 1 As shown, the substation equipment monitoring method based on vibration signals and structural noise includes steps 101 to 104, specifically:
[0078] Step 101: collecting vibration signals of substation equipment and structural noise data in the substation at preset time intervals;
[0079] Step 102: De-noising and separating the structural noise data in the substation to obtain solid noise components, and obtaining noise characteristic data according to the solid noise components;
[0080] Step 103: performing time domain processing and frequency domain processing on the vibration signal of the substation equipment in sequence to obtain time domain characteristics and frequency domain characteristics of the vibration signal, and obtaining vibration characteristic data according to the time domain characteristics and frequency domain characteristics;
[0081] Step 104: Obtain a monitoring weighted value according to the noise characteristic data and the vibration characteristic data, and evaluate the operating status of the substation equipment according to the monitoring weighted value.
[0082] During the operation of the substation equipment, due to mechanical vibration, uniform sound will always be generated. This sound under normal operation has certain regularity. When a certain fault occurs in the substation equipment, the sound it emits will also change due to the change in the operating state. By changing the audio characteristics such as the amplitude and frequency of the sound signal and analyzing the specific characteristics of the vibration signal, it can be determined whether the equipment is in an abnormal operating state, and even the type and severity of the fault can be determined. For example, after the winding of the substation equipment undergoes mechanical faults such as deformation and falling off, the clamping force of the winding is insufficient, which aggravates the unbalance of the winding ampere-turns, resulting in stronger vibration of the winding, which is reflected in the signal as: the fundamental frequency intensity of the vibration signal changes; the multi-point grounding fault of the iron core will increase the vibration. After the iron core fails to loosen, the insufficient clamping force will cause the vibration of the iron core to intensify, which is reflected in the vibration signal as follows: the signal frequency component is more complex and the vibration signal intensity becomes larger. Based on this, this application considers the vibration signal and structural noise data of the substation equipment to monitor the substation equipment.
[0083] In step 101, the preset time interval is empirically set according to the historical operating conditions of the substation equipment; and, in this embodiment, a sensor group is used to collect vibration signals of the substation equipment and structural noise data in the substation; the sensor group includes a vibration sensor and a sound sensor, the vibration sensor can perform vibration wave sampling, and specifically, an acceleration sensor can be used to collect vibration signals on the surface of the transformer box, and the acceleration sensor can convert the vibration signals on the surface of the box into voltage signals by being adsorbed on the surface of the traction transformer; the sound sensor can adopt a capacitive sound sensor, a piezoelectric sound sensor or other sound sensors such as resistive and thermal noise types, and the selection of which one is most suitable depends on the characteristics of the sound signals to be detected in the substation equipment and the substation; wherein, the capacitive sound sensor detects sound by measuring the capacitance change caused by sound waves, has a good response to both low-frequency and high-frequency sounds, and is suitable for applications requiring wide-band response; the piezoelectric sound sensor uses the vibration of piezoelectric materials to generate electrical signals to detect sound, and is particularly sensitive to high-frequency sounds, so it is very useful in detecting sharp or harsh sounds.
[0084] By comprehensively considering the characteristics of the sound signal to be detected, the sensitivity, dynamic range, frequency response and other parameters of the sensor, the impact of environmental factors such as temperature and humidity on sensor performance, and taking into account the relatively harsh environment of substation equipment and factory boundaries, the high noise and the requirements for accuracy and frequency range, the corresponding sensor model and function need to be set according to the historical operation data of the substation equipment or other substation data.
[0085] Furthermore, in step 102, denoising and separating the structural noise data in the substation to obtain a solid noise component includes:
[0086] De-noising the structural noise data in the substation to obtain a discrete sequence of structural noise;
[0087] Based on the structural noise discrete sequence, the component subset, characteristic frequency subset and variation coefficient are initialized, and a time-frequency constraint model is constructed with the characteristic bandwidth and minimum of each component in the component subset as the goal; wherein the time-frequency constraint model is specifically:
[0088]
[0089] In the above formula, J is the number of components; BW is the characteristic bandwidth of the component; is the single-sided spectrum of the component; f ct is the preset characteristic frequency;
[0090] Iteratively updating the component subset, the frequency subset and the variation coefficient based on the first component in the component subset until the iteration constraint condition is satisfied, and obtaining the first component corresponding to the first component; repeating this step until obtaining a plurality of components corresponding to each component in the component subset, and completing the solution of the time-frequency constraint model;
[0091] Based on a preset spectrum sequence, several components are compared in sequence, and a solid noise component is separated from the several components.
[0092] In this embodiment, the preset characteristic frequency is specifically shown in the following formula:
[0093]
[0094] In the above formula, ω j is the characteristic frequency corresponding to each component;
[0095] The single-sided spectrum of the component is specifically shown as follows:
[0096]
[0097] In the above formula, m j (t) is the component function of the component; δ(t) is the unit pulse function.
[0098] In this embodiment, the components of the current iteration and the components of the previous iteration are obtained, and the square norm of the difference between the two components is calculated, which is recorded as the first norm value; the square norm of the components of the previous iteration is obtained, which is recorded as the second norm value; when performing each iteration, the ratio of the first norm value to the second norm value is obtained, and the ratio is accumulated to obtain the first criterion; therefore, the iteration constraint condition is specifically that the first criterion is less than a preset precision, wherein the preset precision is a value greater than zero.
[0099] This embodiment performs data denoising before signal separation to remove interference data caused by harsh operating environment or unstable load, improve the signal-to-noise ratio of required noise components in structural noise, provide strong support for subsequent structural noise feature extraction, strengthen the vibration characteristics of substation equipment, more fully explore the required noise information, and further establish the accuracy and reliability of substation equipment monitoring and evaluation; in the substation, the solid noise, vibration source excitation induced noise and other environmental interference noise of the substation equipment are often coupled with each other and difficult to distinguish. After completing data denoising, this embodiment realizes frequency domain division and effective separation of various components in structural noise by constructing and solving a time-frequency constraint model, and further obtains the solid noise component based on a preset spectrum sequence. The obtained solid noise component can well characterize the operating status of the substation equipment itself.
[0100] In this embodiment, the obtained solid noise component is the noise emitted by the substation during operation. In the substation, in addition to the noise emitted by the substation during operation, there is also noise such as environmental noise. The preset spectrum sequence includes various noise components emitted by the substation during operation. Based on the preset spectrum sequence, the solid noise component can be separated and extracted.
[0101] Furthermore, the denoising process is performed on the structural noise data in the substation to obtain a discrete sequence of structural noise, including:
[0102] converting the structure-borne noise data in the substation into an initial discrete sequence;
[0103] Based on a preset transformation function, the initial discrete sequence is decomposed to obtain a plurality of transformation coefficients, transformation coefficients whose absolute values are greater than a preset transformation threshold are retained from the plurality of transformation coefficients, and a discrete sequence to be processed is obtained according to the retained transformation coefficients using a preset inverse transformation function;
[0104] After compensating the preset components of the discrete sequence to be processed based on the preset filter, a structured noise discrete sequence is obtained.
[0105] In this embodiment, the transformation coefficients can be acquired using preset transformation functions such as fast wavelet transform (FWT) or multi-resolution analysis (MRA); the discrete sequence to be processed can be acquired using inverse fast wavelet transform (IFWT) or inverse multi-resolution analysis (IMRA).
[0106] In this embodiment, different settings of the preset transformation threshold value will produce different results, such as retaining different transformation coefficients. In practical applications, it is necessary to make reasonable settings based on actual conditions and needs.
[0107] In this embodiment, it is possible but not limited to selecting a first-order high-pass digital filter or other types of filters to perform preset component compensation on the discrete sequence to be processed; performing preset component compensation can compensate for the high-frequency components that account for a relatively small proportion of the noise signal. Since most of the high-frequency components in the structural noise data have been removed when denoising the structural noise data to achieve environmental noise removal, the high-frequency components that do not belong to the environmental noise contain many detailed components about the substation equipment. Therefore, this implementation increases the required noise signal components through preset component compensation.
[0108] This embodiment converts the structural noise data into an initial discrete sequence for subsequent denoising processing; then, based on a preset transformation function and a preset transformation threshold, the required transformation coefficient is obtained to complete the preliminary rapid denoising processing, and the threshold method can better suppress unnecessary data; the effective characteristic noise signal and the interference signal such as environmental noise emitted by the substation equipment under various operating conditions have different frequencies, so this embodiment then uses a preset filter to compensate the preset component of the denoised signal, increases the required noise signal component, and makes the spectral parameters of the noise data tend to be stable, which helps to improve the signal-to-noise ratio of the noise signal for noise signal spectrum analysis, and further better obtain the acoustic characteristics related to the transformer noise signal.
[0109] Further, in step 102, obtaining noise characteristic data according to the solid noise component includes:
[0110] Obtain a noise data set according to the solid noise component;
[0111] Dividing the noise data set according to a preset ratio to obtain two noise sub-data sets;
[0112] Inputting the two noise sub-data sets into two neural networks of a preset feature extraction model correspondingly, and outputting first feature data and second feature data;
[0113] Feature fusion is performed on the first feature data and the second feature data to obtain noise feature data.
[0114] This embodiment divides the noise data set and uses different types of neural networks to extract features of solid noise components respectively, and then performs feature fusion on the different feature data extracted by the two networks, so as to ensure the comprehensiveness of the extracted noise features and reduce the data dimension, thereby improving the data utilization rate of the noise data set.
[0115] In this embodiment, when the noise data set is divided according to a preset ratio, it is necessary to ensure that the data in the two noise sub-data sets obtained are relatively balanced; the preset ratio can be reasonably set according to the data scale and size that can be processed by different neural networks.
[0116] In this embodiment, the preset feature extraction model includes two neural networks for feature extraction and a feature fusion network; wherein, the two neural networks for feature extraction may specifically be convolutional neural networks, recurrent neural networks, Transfomer networks, feature pyramid structures or other networks or structures that can perform feature extraction, which are not specifically limited here; the feature fusion network may specifically be a multi-scale feature fusion network or other networks or structures that can perform feature fusion, which are not specifically limited here.
[0117] Further, in step 103, the vibration signal of the substation equipment is processed in time domain and frequency domain in sequence to obtain time domain characteristics and frequency domain characteristics of the vibration signal, and vibration characteristic data is obtained according to the time domain characteristics and frequency domain characteristics, including:
[0118] Performing a convolution operation on the vibration signal of the substation equipment and a preset characteristic wavelet based on a preset characteristic frequency and characteristic scale, and extracting a time domain feature of the vibration signal from the convolution operation result;
[0119] Rearranging the vibration signal of the power conversion equipment in reverse order to obtain a plurality of subsequences and a plurality of recursive levels; performing butterfly operations on the plurality of subsequences in turn at each recursive level until a second preset condition is met to obtain a vibration spectrum;
[0120] Obtaining frequency domain characteristics of the vibration signal based on the vibration spectrum;
[0121] Vibration characteristic data is obtained according to the time domain characteristics and the frequency domain characteristics.
[0122] In this embodiment, in performing a convolution operation on the vibration signal of the substation and a preset characteristic wavelet based on a preset characteristic frequency and characteristic scale, and extracting the time domain characteristics of the vibration signal from the convolution operation result, the preset characteristic frequency and characteristic scale are selected as needed to analyze the signal at different scales, thereby extracting features at different scales, so that the time domain feature extraction method has good time-frequency localization characteristics and can well describe the time-frequency characteristics of the signal.
[0123] In this embodiment, the characteristic wavelet is in complex form, the real part of which represents the amplitude information of the signal, and the imaginary part of which represents the phase information of the signal.
[0124] In this embodiment, the convolution operation result contains rich time domain features, such as amplitude and phase information of the signal; the frequency domain features include average frequency, centroid frequency, root mean square frequency, and frequency standard deviation.
[0125] In this embodiment, the second preset condition is specifically a preset number of points, and the preset number of points is related to the number of sampling points of the vibration signal in the time domain.
[0126] This embodiment performs convolution operation on the vibration signal and the preset characteristic wavelet according to the preset characteristic frequency and characteristic scale, so as to quickly and effectively obtain the time domain characteristics of the vibration signal; then this embodiment performs bit-reversal rearrangement on the vibration signal and performs butterfly operation on several subsequences, which is simple to calculate and can conveniently and efficiently obtain the vibration spectrum. The vibration spectrum can intuitively convey rich signal frequency domain information, and the frequency domain characteristics of the vibration signal can be conveniently and quickly obtained based on the vibration spectrum; finally, this embodiment obtains the vibration characteristic data according to the time domain characteristics and the frequency domain characteristics, which can convey the relationship between the signal frequency and time, and can better and comprehensively characterize the characteristics of the vibration signal of the substation equipment.
[0127] Further, in step 104, a monitoring weighted value is obtained according to the noise characteristic data and the vibration characteristic data, and the operating state of the substation equipment is evaluated according to the monitoring weighted value, including:
[0128] After the noise characteristic data and the vibration characteristic data are dimensionally processed respectively by a preset dimension processing formula, a number of corresponding dimension averages are obtained; the preset dimension processing formula is specifically:
[0129]
[0130] In the above formula, k is the corresponding feature data size; σ is the preset processing coefficient; x i is a characteristic data component in the noise characteristic data or the vibration characteristic data; is the average number of steel after dimension processing;
[0131] Assigning a number of preset weight values corresponding to the number of steel quantity averages, and obtaining a monitoring weighted value according to the number of steel quantity averages and the corresponding number of preset weight values;
[0132] Comparing the monitoring weighted value with a preset threshold, and when the monitoring weighted value is greater than the preset threshold, determining that the operating state of the substation equipment is abnormal;
[0133] Compare a plurality of steel measurement averages with a plurality of steel measurement thresholds or preset steel measurement ranges respectively, and retain the steel measurement averages that are greater than the corresponding steel measurement thresholds or exceed the corresponding preset steel measurement ranges;
[0134] According to the retained average steel quantity, a first fault cause is searched and obtained in a preset fault cause set, and warning information is output according to the first fault cause.
[0135] In this embodiment, the several quantity averages all correspond to different characteristics of noise or vibration. When the substation equipment is in different operating states such as normal operation, abnormal operation, fault stop, etc., the several quantity averages will have corresponding different numerical expressions. By comparing the several quantity averages with the corresponding several quantity thresholds or preset quantity ranges, the quantity averages with abnormal values can be obtained. By using these "abnormal" quantity averages and comparing with the preset fault cause set, the current operating state of the substation equipment can be judged.
[0136] In this embodiment, the preset fault cause set is obtained based on the historical operating data of the substation equipment, specifically, the measurement thresholds or measurement ranges corresponding to each noise feature and vibration feature of the substation equipment under different operating conditions are statistically analyzed, and a one-to-one or one-to-many correspondence is made with the abnormal areas or abnormal components corresponding to the substation equipment, and the corresponding abnormal causes; for example, if an abnormality occurs in a component in the substation equipment, there may be multiple "abnormal" measurement averages, or there may be only one "abnormal" measurement average; therefore, in this embodiment, when an "abnormal" measurement average occurs, the corresponding abnormal area and abnormal cause can be found in the preset fault cause set.
[0137] The present embodiment proposes a quantitative evaluation method for the operating status of a substation equipment. The noise characteristic data and the vibration characteristic data are dimensionally processed based on a preset dimensional processing formula, so that the noise characteristic data and the vibration characteristic data are converted into the same scale, and a number of dimensional averages that can characterize multiple information of vibration signals and structural noise are obtained, so as to eliminate the dimensional influence between different data or features. After that, the present embodiment evaluates a number of dimensional averages through a number of dimensional thresholds, further evaluates whether there are features that need attention in the noise characteristic data and the vibration characteristic data, and finally searches and obtains the first fault cause in a pre-constructed set of fault causes based on the retained dimensional averages, and outputs warning information based on the first fault cause. When an abnormality occurs in the substation equipment, the present embodiment can help operation and maintenance personnel quickly determine the abnormal area and possible causes, narrow the search range, and enable emergency repair personnel to efficiently and accurately perform substation equipment maintenance.
[0138] Accordingly, in order to solve the above technical problems, the embodiment of the present invention also provides a substation equipment monitoring device based on vibration signals and structural noise. Figures 2 to 5 ,in, Figure 2 A schematic diagram of the structure of an embodiment of a substation equipment monitoring device based on vibration signals and structural noise provided by the present invention; Figure 3 A schematic diagram of the structure of an embodiment of a noise feature acquisition module provided by the present invention; Figure 4 A schematic diagram of the structure of an embodiment of a vibration feature acquisition module provided by the present invention; Figure 5A schematic diagram of the structure of an embodiment of the monitoring and evaluation module provided by the present invention.
[0139] like Figure 2 As shown, the substation equipment monitoring device 20 based on vibration signals and structural noise includes: a data acquisition module 201, a noise feature acquisition module 202, a vibration feature acquisition module 203 and a monitoring and evaluation module 204;
[0140] The data acquisition module 201 is used to collect vibration signals of substation equipment and structural noise data in the substation at preset time intervals;
[0141] The noise characteristic acquisition module 202 is used to perform denoising and separation on the structural noise data in the substation to obtain a solid noise component, and obtain noise characteristic data according to the solid noise component;
[0142] The vibration feature acquisition module 203 is used to perform time domain processing and frequency domain processing on the vibration signal of the substation equipment in sequence to obtain the time domain features and frequency domain features of the vibration signal, and obtain vibration feature data according to the time domain features and frequency domain features;
[0143] The monitoring and evaluation module 204 is used to obtain a monitoring weighted value according to the noise characteristic data and the vibration characteristic data, and evaluate the operating status of the substation equipment according to the monitoring weighted value.
[0144] Furthermore, if Figure 3 As shown, the noise feature acquisition module 202 includes: a denoising unit 2021, an iteration unit 2022 and a separation unit 2023;
[0145] The denoising unit 2021 is used to perform denoising on the structural noise data in the substation to obtain a discrete sequence of structural noise;
[0146] The iteration unit is used to initialize the component subset, characteristic frequency subset and variation coefficient based on the discrete sequence of structural noise in 2022, and construct a time-frequency constraint model with the characteristic bandwidth and minimum of each component in the component subset as the goal; iteratively update the component subset, frequency subset and variation coefficient based on the first component in the component subset until the iteration constraint condition is satisfied, and obtain the first component corresponding to the first component; repeat this step until a number of components corresponding to each component in the component subset are obtained, and the time-frequency constraint model is solved; wherein the time-frequency constraint model is specifically:
[0147]
[0148] In the above formula, J is the number of components; BW is the characteristic bandwidth of the component; is the single-sided spectrum of the component; fct is the preset characteristic frequency;
[0149] The separation unit 2023 is used to sequentially compare the multiple components based on a preset frequency spectrum sequence, and separate the solid noise component from the multiple components.
[0150] Furthermore, if Figure 4 As shown, the vibration feature acquisition module 203 includes: a time domain analysis unit 2031, a frequency domain analysis unit 2032 and a vibration feature acquisition unit 2033;
[0151] The time domain analysis unit 2031 is used to perform a convolution operation on the vibration signal of the substation equipment and a preset characteristic wavelet based on a preset characteristic frequency and characteristic scale, and extract the time domain characteristics of the vibration signal from the convolution operation result;
[0152] The frequency domain analysis unit 2032 is used to perform bit-reversal rearrangement on the vibration signal of the substation equipment to obtain a plurality of subsequences and a plurality of recursive levels; at each recursive level, perform butterfly operations on the plurality of subsequences in turn until a second preset condition is met to obtain a vibration spectrum; and obtain frequency domain features of the vibration signal based on the vibration spectrum;
[0153] The vibration feature acquisition unit 2033 is used to obtain vibration feature data according to the time domain features and the frequency domain features.
[0154] Furthermore, if Figure 5 As shown, the monitoring and evaluation module 204 includes: a dimension processing unit 2041, a weighted acquisition unit 2042 and an evaluation and early warning unit 2043;
[0155] The dimension processing unit 2041 is used to perform dimension processing on the noise characteristic data and the vibration characteristic data respectively through a preset dimension processing formula to obtain a number of corresponding dimension averages; the preset dimension processing formula is specifically:
[0156]
[0157] In the above formula, k is the corresponding feature data size; σ is the preset processing coefficient; x i is a characteristic data component in the noise characteristic data or the vibration characteristic data; is the average number of steel after dimension processing;
[0158] The weighted acquisition unit 2042 is used to assign a number of preset weight values corresponding to the number of steel measurement averages, and obtain a monitoring weight value according to the number of steel measurement averages and the corresponding number of preset weight values;
[0159] The evaluation and early warning unit 2043 is used to compare the monitoring weighted value with a preset threshold value, and when the monitoring weighted value is greater than the preset threshold value, determine that the operating state of the substation equipment is abnormal;
[0160] The evaluation and early warning unit 2043 is further used to compare the plurality of steel measurement averages with a plurality of steel measurement thresholds or preset steel measurement ranges, and retain the steel measurement averages that are greater than the corresponding steel measurement thresholds or exceed the corresponding preset steel measurement ranges;
[0161] The evaluation and early warning unit 2043 is further used to search and obtain a first fault cause in a preset fault cause set according to the retained average steel quantity, and output early warning information according to the first fault cause.
[0162] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:
[0163] The embodiment of the present invention performs denoising and separation on structural noise data to obtain noise characteristic data, performs time-frequency domain processing on the collected vibration signal to obtain vibration characteristic data, and then obtains a monitoring weighted value based on the obtained noise characteristic data and vibration characteristic data to evaluate the operating status of the substation equipment; the substation equipment will generate vibration and make sound during operation, and the vibration and sound information reflect the operating status of the substation equipment, and the vibration and sound are closely related and can represent different detailed information. With the help of this information, the abnormality of the equipment can be better monitored and analyzed. The embodiment of the present invention can monitor and evaluate the operating status of the substation equipment in combination with the acquired noise characteristics and vibration characteristics, and can avoid the one-sided results caused by the subjectivity of manual inspection and monitoring of substation equipment based on only a single indicator, and can monitor the substation equipment more comprehensively, accurately, in real time and efficiently, providing a strong reference basis for the subsequent maintenance and management of the substation equipment.
[0164] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.
Claims
1. A substation equipment monitoring method based on vibration signals and structural noise, characterized in that: include: Collect vibration signals of substation equipment and structural noise data in substations at preset time intervals; De-noising and separating the structural noise data in the substation to obtain a solid noise component, and obtaining noise characteristic data according to the solid noise component; Performing time domain processing and frequency domain processing on the vibration signal of the substation equipment in sequence to obtain time domain characteristics and frequency domain characteristics of the vibration signal, and obtaining vibration characteristic data according to the time domain characteristics and frequency domain characteristics; A monitoring weighted value is obtained according to the noise characteristic data and the vibration characteristic data, and the operating state of the substation equipment is evaluated according to the monitoring weighted value.
2. The method for monitoring substation equipment based on vibration signals and structural noise according to claim 1, characterized in that: The denoising and separation of the structural noise data in the substation to obtain a solid noise component includes: De-noising the structural noise data in the substation to obtain a discrete sequence of structural noise; Based on the structural noise discrete sequence, the component subset, characteristic frequency subset and variation coefficient are initialized, and a time-frequency constraint model is constructed with the characteristic bandwidth and minimum of each component in the component subset as the goal; wherein the time-frequency constraint model is specifically: In the above formula, J is the number of components; BW is the characteristic bandwidth of the component; is the single-sided spectrum of the component; f ct is the preset characteristic frequency; Iteratively updating the component subset, the frequency subset and the variation coefficient based on the first component in the component subset until the iteration constraint condition is satisfied, and obtaining the first component corresponding to the first component; repeating this step until obtaining a plurality of components corresponding to each component in the component subset, and completing the solution of the time-frequency constraint model; Based on a preset spectrum sequence, several components are compared in sequence, and a solid noise component is separated from the several components.
3. The substation equipment monitoring method based on vibration signals and structural noise according to claim 2, characterized in that: The denoising process is performed on the structural noise data in the substation to obtain a structural noise discrete sequence, including: converting the structure-borne noise data in the substation into an initial discrete sequence; Based on a preset transformation function, the initial discrete sequence is decomposed to obtain a plurality of transformation coefficients, transformation coefficients whose absolute values are greater than a preset transformation threshold are retained from the plurality of transformation coefficients, and a discrete sequence to be processed is obtained according to the retained transformation coefficients using a preset inverse transformation function; After compensating the preset components of the discrete sequence to be processed based on the preset filter, a structured noise discrete sequence is obtained.
4. The method for monitoring substation equipment based on vibration signals and structural noise according to claim 1, characterized in that: The obtaining of noise characteristic data according to the solid noise component comprises: Obtain a noise data set according to the solid noise component; Dividing the noise data set according to a preset ratio to obtain two noise sub-data sets; Inputting the two noise sub-data sets into two neural networks of a preset feature extraction model correspondingly, and outputting first feature data and second feature data; Feature fusion is performed on the first feature data and the second feature data to obtain noise feature data.
5. The method for monitoring substation equipment based on vibration signals and structural noise according to claim 1, characterized in that: The step of sequentially performing time domain processing and frequency domain processing on the vibration signal of the power transformation equipment to obtain time domain characteristics and frequency domain characteristics of the vibration signal, and obtaining vibration characteristic data according to the time domain characteristics and frequency domain characteristics includes: Performing a convolution operation on the vibration signal of the substation equipment and a preset characteristic wavelet based on a preset characteristic frequency and characteristic scale, and extracting a time domain feature of the vibration signal from the convolution operation result; Rearranging the vibration signal of the power conversion equipment in reverse order to obtain a plurality of subsequences and a plurality of recursive levels; performing butterfly operations on the plurality of subsequences in turn at each recursive level until a second preset condition is met to obtain a vibration spectrum; Obtaining frequency domain characteristics of the vibration signal based on the vibration spectrum; Vibration characteristic data is obtained according to the time domain characteristics and the frequency domain characteristics.
6. The method for monitoring substation equipment based on vibration signals and structural noise according to claim 1, characterized in that: Acquiring a monitoring weighted value according to the noise characteristic data and the vibration characteristic data, and evaluating the operating state of the substation equipment according to the monitoring weighted value, including: After the noise characteristic data and the vibration characteristic data are dimensionally processed respectively by a preset dimension processing formula, a number of corresponding dimension averages are obtained; the preset dimension processing formula is specifically: In the above formula, k is the corresponding feature data size; σ is the preset processing coefficient; x i is a characteristic data component in the noise characteristic data or the vibration characteristic data; is the average number of steel after dimension processing; Assigning a number of preset weight values corresponding to the number of steel quantity averages, and obtaining a monitoring weighted value according to the number of steel quantity averages and the corresponding number of preset weight values; Comparing the monitoring weighted value with a preset threshold, and when the monitoring weighted value is greater than the preset threshold, determining that the operating state of the substation equipment is abnormal; Compare a plurality of steel measurement averages with a plurality of steel measurement thresholds or preset steel measurement ranges respectively, and retain the steel measurement averages that are greater than the corresponding steel measurement thresholds or exceed the corresponding preset steel measurement ranges; According to the retained average steel quantity, a first fault cause is searched and obtained in a preset fault cause set, and warning information is output according to the first fault cause.
7. A substation equipment monitoring device based on vibration signals and structural noise, characterized in that: include: Data acquisition module, noise feature acquisition module, vibration feature acquisition module and monitoring and evaluation module; Wherein, the data acquisition module is used to collect vibration signals of substation equipment and structural noise data in the substation at preset time intervals; The noise characteristic acquisition module is used to perform denoising and separation on the structural noise data in the substation to obtain a solid noise component, and obtain noise characteristic data according to the solid noise component; The vibration feature acquisition module is used to perform time domain processing and frequency domain processing on the vibration signal of the substation equipment in sequence to obtain the time domain features and frequency domain features of the vibration signal, and obtain vibration feature data according to the time domain features and frequency domain features; The monitoring and evaluation module is used to obtain a monitoring weighted value according to the noise characteristic data and the vibration characteristic data, and evaluate the operating status of the substation equipment according to the monitoring weighted value.
8. The substation equipment monitoring device based on vibration signals and structural noise according to claim 7, characterized in that: The noise feature acquisition module includes: a denoising unit, an iteration unit and a separation unit; The denoising unit is used to perform denoising on the structural noise data in the substation to obtain a discrete sequence of structural noise; The iteration unit is used to initialize the component subset, characteristic frequency subset and variation coefficient based on the discrete sequence of the structural noise, and to construct a time-frequency constraint model with the characteristic bandwidth and minimum of each component in the component subset as the goal; iteratively update the component subset, frequency subset and variation coefficient based on the first component in the component subset until the iteration constraint condition is satisfied, and obtain the first component corresponding to the first component; repeat this step until a number of components corresponding to each component in the component subset are obtained, and the solution of the time-frequency constraint model is completed; wherein the time-frequency constraint model is specifically: In the above formula, J is the number of components; BW is the characteristic bandwidth of the component; is the single-sided spectrum of the component; f ct is the preset characteristic frequency; The separation unit is used to sequentially compare a plurality of components based on a preset frequency spectrum sequence, and separate a solid noise component from the plurality of components.
9. The substation equipment monitoring device based on vibration signals and structural noise according to claim 7, characterized in that: The vibration feature acquisition module includes: a time domain analysis unit, a frequency domain analysis unit and a vibration feature acquisition unit; The time domain analysis unit is used to perform a convolution operation on the vibration signal of the substation equipment and a preset characteristic wavelet based on a preset characteristic frequency and characteristic scale, and extract the time domain characteristics of the vibration signal from the convolution operation result; The frequency domain analysis unit is used to perform bit-reversal rearrangement on the vibration signal of the substation equipment to obtain a plurality of subsequences and a plurality of recursive levels; at each recursive level, butterfly operations are performed on the plurality of subsequences in turn until a second preset condition is met to obtain a vibration spectrum; and frequency domain features of the vibration signal are obtained based on the vibration spectrum; The vibration feature acquisition unit is used to obtain vibration feature data according to the time domain feature and the frequency domain feature.
10. The substation equipment monitoring device based on vibration signals and structural noise according to claim 7, characterized in that: The monitoring and evaluation module includes: a dimensional processing unit, a weighted acquisition unit and an evaluation and early warning unit; The dimension processing unit is used to perform dimension processing on the noise characteristic data and the vibration characteristic data respectively through a preset dimension processing formula to obtain a number of corresponding dimension averages; the preset dimension processing formula is specifically: In the above formula, k is the corresponding feature data size; σ is the preset processing coefficient; x i is a characteristic data component in the noise characteristic data or the vibration characteristic data; is the average number of steel after dimension processing; The weighted acquisition unit is used to assign a number of preset weight values corresponding to the number of steel measurement averages, and obtain a monitoring weight value according to the number of steel measurement averages and the corresponding number of preset weight values; The evaluation and early warning unit is used to compare the monitoring weighted value with a preset threshold value, and when the monitoring weighted value is greater than the preset threshold value, determine that the operating state of the substation equipment is abnormal; The evaluation and early warning unit is further used to compare a plurality of steel measurement averages with a plurality of steel measurement thresholds or preset steel measurement ranges, and retain the steel measurement averages that are greater than the corresponding steel measurement thresholds or exceed the corresponding preset steel measurement ranges; The evaluation and early warning unit is further used to search and obtain a first fault cause in a preset fault cause set according to the retained average steel quantity, and output early warning information according to the first fault cause.
Citation Information
Cited By
Virtual instrument data acquisition and processing method and system
CN119179888A
Laser vibration measurement signal optimization method, equipment and medium
CN120063469A
Operation and maintenance management method and system for hydropower station
CN120124996A
Voice-controlled intelligent lifting control method and system
CN122177100A
