A method and apparatus for troubleshooting photovoltaic inverters based on acoustic characteristics

Abstract

This invention relates to the field of fault diagnosis technology and discloses a method and apparatus for handling photovoltaic inverter faults based on acoustic characteristics. The method includes: acquiring acoustic signals during the operation of the photovoltaic inverter; establishing a current acoustic characteristic curve based on the acoustic signals during operation; acquiring the acoustic characteristic curve of a normally operating inverter; comparing the current acoustic characteristic curve with the acoustic characteristic curve of a normally operating inverter; and determining the operating state of the photovoltaic inverter based on the comparison result; and handling the photovoltaic inverter faults using a fault handling strategy based on the operating state of the photovoltaic inverter. This invention improves the efficiency of fault detection and handling for photovoltaic inverters.

Description

Technical Field

[0001] This invention relates to the field of fault diagnosis technology, and specifically to a method and apparatus for handling photovoltaic inverter faults based on acoustic characteristics. Background Technology

[0002] In recent years, the photovoltaic power generation industry has developed rapidly. However, since photovoltaic power generation projects often require large areas of land resources, they are mostly located in remote areas such as mountains or deserts with complex terrain. This special geographical environment brings many challenges to the fault detection of photovoltaic inverters, especially for mountain photovoltaic power generation systems. The complex terrain conditions make the inverter equipment easy to be blocked, and minor inverter faults are also highly concealed, making it difficult to efficiently complete fault detection and handling tasks manually. Summary of the Invention

[0003] In view of this, the present invention provides a photovoltaic inverter fault handling method and apparatus based on acoustic characteristics to solve the problem of low fault detection accuracy of photovoltaic inverters.

[0004] In a first aspect, the present invention provides a photovoltaic inverter fault handling method based on acoustic characteristics, the method comprising:

[0005] Acoustic signals are collected during the operation of the photovoltaic inverter, and the current acoustic characteristic curve is established based on the acoustic signals during the operation of the photovoltaic inverter.

[0006] Acoustic characteristic curves of a normally operating inverter are obtained, the current acoustic characteristic curve is compared with the acoustic characteristic curves of a normally operating inverter, and the operating status of the photovoltaic inverter is determined based on the comparison results.

[0007] Based on the operating status of the photovoltaic inverter, fault handling strategies are used to handle faults in the photovoltaic inverter.

[0008] This embodiment provides a photovoltaic inverter fault handling method based on acoustic characteristics. By collecting acoustic signals during the operation of the photovoltaic inverter, generating acoustic characteristic curves, and comparing them with the acoustic characteristic curves of inverters in normal operation, the operating status of the photovoltaic inverter is intelligently determined, and corresponding processing measures are taken, thereby improving the efficiency of fault detection and handling of photovoltaic inverters.

[0009] In one optional implementation, establishing a current acoustic characteristic curve based on acoustic signals generated during photovoltaic inverter operation includes:

[0010] Endpoint detection is performed on the acoustic signals during the operation of the photovoltaic inverter to obtain valid acoustic signals;

[0011] The effective acoustic signal is framed to obtain the framed acoustic signal;

[0012] Feature extraction is performed on the framed acoustic signal to obtain acoustic features;

[0013] The optimal alignment path is obtained by performing dynamic time warping on the acoustic features.

[0014] The current acoustic feature curve is established by using the time axis corresponding to the optimal alignment path as the horizontal axis and the preset feature dimension corresponding to the acoustic feature as the vertical axis.

[0015] This embodiment provides a photovoltaic inverter fault handling method based on acoustic features. By performing endpoint detection and frame segmentation processing on the acoustic signals during the operation of the photovoltaic inverter, it achieves effective denoising and feature extraction of the acoustic signals. Furthermore, by performing dynamic time warping processing on the acoustic features, it effectively solves the similarity calculation problem caused by "length mismatch" and "rhythm difference" in the acoustic signals. Then, by using the current acoustic feature curve, it transforms the high-dimensional time-series features corresponding to the acoustic signals into a two-dimensional visualization of time-feature values, which can help to intuitively identify abnormal moments and feature change trends, laying the foundation for subsequent determination of the operating status of the photovoltaic inverter.

[0016] In one optional implementation, the current acoustic characteristic curve is compared with the acoustic characteristic curve of a normally operating inverter, and the operating status of the photovoltaic inverter is determined based on the comparison result, including:

[0017] Calculate the similarity between the current acoustic characteristic curve and the acoustic characteristic curve of a normally operating inverter;

[0018] The similarity is compared with a preset threshold. If the similarity is less than the preset threshold and no background alarm information is collected, the photovoltaic inverter is in normal operating status.

[0019] Alternatively, if the similarity is less than a preset threshold and a background alarm is collected, the photovoltaic inverter's operating status is the first abnormal state.

[0020] This embodiment provides a photovoltaic inverter fault handling method based on acoustic features. By combining the acoustic features of the sound of the photovoltaic inverter during operation with background alarm information, the operating status of the photovoltaic inverter is identified, thereby improving the fault detection efficiency of the photovoltaic inverter.

[0021] In one optional implementation, comparing the current acoustic characteristic curve with the acoustic characteristic curve of a normally operating inverter, and determining the operating status of the photovoltaic inverter based on the comparison result, further includes:

[0022] The current acoustic characteristic curve is fitted with a straight line. If the straight line fitting result matches the preset fitting value, the photovoltaic inverter is in a shutdown state.

[0023] In one optional implementation, comparing the current acoustic characteristic curve with the acoustic characteristic curve of a normally operating inverter, and determining the operating status of the photovoltaic inverter based on the comparison result, further includes:

[0024] If there is a sudden change in the current acoustic characteristic curve and no alarm information is collected from the background, the photovoltaic inverter is in the second abnormal state.

[0025] If there is a sudden change in the current acoustic characteristic curve and alarm information is collected from the background, the photovoltaic inverter's operating status is the third abnormal state.

[0026] In one optional implementation, based on the operating status of the photovoltaic inverter, a fault handling strategy is used to handle faults in the photovoltaic inverter, including:

[0027] If the photovoltaic inverter is in normal operation, a sleep command is sent to the photovoltaic inverter, and a work command is sent to the photovoltaic inverter after a preset time period.

[0028] If the photovoltaic inverter is in the first abnormal state, or in the shutdown state, or in the third abnormal state, an audible and visual alarm will be triggered, and a maintenance work order will be sent to the client.

[0029] If the photovoltaic inverter is in the second abnormal state, the acoustic characteristic curves of the photovoltaic inverter in multiple time periods are obtained, the operating status of the photovoltaic inverter is updated based on the acoustic characteristic curves in multiple time periods, and the photovoltaic inverter is fault-handled based on the updated operating status.

[0030] This embodiment provides a photovoltaic inverter fault handling method based on acoustic features. It combines the acoustic features of the sound of the photovoltaic inverter during operation with background alarm information to identify the operating status of the photovoltaic inverter. Then, it classifies the photovoltaic inverter based on the operating status, realizes targeted processing of different operating states of the photovoltaic inverter, and improves the fault handling efficiency of the photovoltaic inverter.

[0031] Secondly, the present invention provides a photovoltaic inverter fault handling device based on acoustic characteristics, the device comprising:

[0032] A module is established to collect acoustic signals during the operation of the photovoltaic inverter and to establish the current acoustic characteristic curve based on the acoustic signals during the operation of the photovoltaic inverter.

[0033] The comparison module is used to obtain the acoustic characteristic curve of the inverter in normal operation, compare the current acoustic characteristic curve with the acoustic characteristic curve of the inverter in normal operation, and determine the operating status of the photovoltaic inverter based on the comparison results.

[0034] The fault handling module is used to handle faults in the photovoltaic inverter based on its operating status and using fault handling strategies.

[0035] Thirdly, the present invention provides a computer device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform a photovoltaic inverter fault handling method based on acoustic characteristics as described in the first aspect or any corresponding embodiment.

[0036] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to execute a photovoltaic inverter fault handling method based on acoustic features as described in the first aspect or any corresponding embodiment.

[0037] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute a photovoltaic inverter fault handling method based on acoustic characteristics as described in the first aspect or any corresponding embodiment. Attached Figure Description

[0038] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0039] Figure 1 This is a schematic flowchart of a photovoltaic inverter fault handling method based on acoustic features according to an embodiment of the present invention.

[0040] Figure 2 This is a flowchart illustrating another photovoltaic inverter fault handling method based on acoustic features according to an embodiment of the present invention.

[0041] Figure 3 This is a flowchart illustrating another photovoltaic inverter fault handling method based on acoustic features according to an embodiment of the present invention.

[0042] Figure 4 This is a flowchart illustrating another photovoltaic inverter fault handling method based on acoustic features according to an embodiment of the present invention.

[0043] Figure 5 This is a structural block diagram of a photovoltaic inverter fault handling device based on acoustic features according to an embodiment of the present invention.

[0044] Figure 6 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. Detailed Implementation

[0045] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] This invention provides a photovoltaic inverter fault handling method based on acoustic features. It should be noted that the execution subject of this method can be a photovoltaic inverter fault handling device based on acoustic features. This device can be implemented as part or all of an electronic device through software, hardware, or a combination of both. The electronic device can be a server or a terminal. In this embodiment, the server can be a single server or a server cluster composed of multiple servers. The terminal can be a smartphone, personal computer, tablet computer, wearable device, or other intelligent hardware device such as a smart robot. The following method embodiments all use an electronic device as the execution subject for illustration.

[0047] According to an embodiment of the present invention, a photovoltaic inverter fault handling method based on acoustic features is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0048] This embodiment provides a photovoltaic inverter fault handling method based on acoustic characteristics, which can be used in the aforementioned electronic equipment. Figure 1 This is a flowchart of a photovoltaic inverter fault handling method based on acoustic features according to an embodiment of the present invention, as shown below. Figure 1 As shown, the process includes the following steps:

[0049] Step S101: Acoustic signals during the operation of the photovoltaic inverter are collected, and the current acoustic characteristic curve is established based on the acoustic signals during the operation of the photovoltaic inverter.

[0050] Specifically, microphones or accelerometers are installed near the photovoltaic inverter to ensure a high signal-to-noise ratio and to perform multi-channel recording. This means using multiple microphones to collect independent sound sources from different components or to record the total operating noise. Additionally, the operating status is recorded simultaneously, i.e., the current operating parameters (load, temperature, etc.) are read.

[0051] Step S102: Obtain the acoustic characteristic curve of the inverter in normal operation, compare the current acoustic characteristic curve with the acoustic characteristic curve of the inverter in normal operation, and determine the operating status of the photovoltaic inverter based on the comparison result.

[0052] Step S103: Based on the operating status of the photovoltaic inverter, fault handling strategies are used to handle the photovoltaic inverter.

[0053] This embodiment provides a photovoltaic inverter fault handling method based on acoustic characteristics. By collecting acoustic signals during the operation of the photovoltaic inverter, generating acoustic characteristic curves, and comparing them with the acoustic characteristic curves of inverters in normal operation, the operating status of the photovoltaic inverter is intelligently determined, and corresponding processing measures are taken, thereby improving the efficiency of fault detection and handling of photovoltaic inverters.

[0054] This embodiment provides a photovoltaic inverter fault handling method based on acoustic characteristics, which can be used in the aforementioned electronic equipment. Figure 2 This is a flowchart of a photovoltaic inverter fault handling method based on acoustic features according to an embodiment of the present invention, as shown below. Figure 2 As shown, the process includes the following steps:

[0055] Step S201: Acoustic signals during the operation of the photovoltaic inverter are collected, and the current acoustic characteristic curve is established based on the acoustic signals during the operation of the photovoltaic inverter.

[0056] Specifically, step S201 includes:

[0057] Step S2011: Endpoint detection is performed on the acoustic signals during the operation of the photovoltaic inverter to obtain valid acoustic signals.

[0058] Specifically, endpoint detection utilizes a dual-threshold algorithm of short-time energy and zero-crossing rate, or WebRTC VAD (Web Real-Time Communications Voice Activity Detection, a technique for detecting speech activity in audio streams, primarily used in real-time communication systems) / Silero-VAD (Silero Voice Activity Detection, a lightweight speech activity detection model based on deep learning technology) to find all possible voice-containing segments and discard short segments <200ms. Parameters in the endpoint detection process include a frame length of 25ms, a frame shift of 10ms, an energy threshold of ambient noise floor + 12dB, and a zero-crossing rate threshold of mean + .

[0059] Furthermore, the specific steps of the short-time energy + zero-crossing rate dual-threshold algorithm include: framing and windowing: the signal is divided into continuous frames with a frame length of 25ms and a frame length of 10ms, and a Hamming window is added to each frame; calculating the short-time energy E(n): the sum of squares of the samples within the nth frame window is calculated to obtain the total energy E(n) of that frame; calculating the short-time zero-crossing rate Z(n): the number of sign changes of adjacent samples within the window is counted and normalized to obtain Z(n); automatic threshold generation: the first 10 frames are taken as the background noise segment, and its average energy is calculated. with standard deviation and the mean zero-crossing rate with standard deviation Setting: High Energy Threshold Low-energy gate Zero-crossing threshold Level 3 State Decision: Silent State: When the energy of a certain frame > When entering the transition zone, mark the possible starting point; Transition zone: if continuous Frame (usually 5 frames) energy > And the zero-crossing rate < Then it is confirmed as the start of the speech; Speech status: if continuous Frame (usually 10 frames) energy < If the start and end positions are not detected, they are confirmed as the end of the speech segment. Post-processing: remove short segments with a total duration of less than 200ms; extend outward by 2 frames (about 25ms) at each detected start and end position to prevent cutting off effective edge information, and finally output the start and end sample indices of the effective speech / machine voice segments.

[0060] Furthermore, in addition to the silent segments and background noise (such as birdsong and wind noise) in the acoustic signals during the operation of the photovoltaic inverter, the specific steps are as follows: First, use a 1kHz high-pass filter to suppress low-frequency wind noise; since birdsong energy is concentrated in the 2–8kHz range, a secondary filtering rule of "spectral centroid > 1500Hz and duration > 300ms" can be added after VAD to retain only the effective speech / machine sound segments, with a 25ms margin before and after to prevent truncation.

[0061] Furthermore, the spectral centroid SC and roll-off point R are calculated for each frame: speech retention: SC falls within 300–3400Hz and R < 4kHz; machine retention: SC falls within 80–1200Hz and R < 2kHz; those outside the range are considered birdsong, wind noise, or knocking and are removed.

[0062] Furthermore, the approximate energy is calculated within a 1-second sliding window. and variance ;like > If the normal steady-state baseline is 3 times higher, it is judged as a transient impact and discarded; energy is checked again: the average energy of the frame must be 6dB higher than the noise floor and lower than the 95th percentile of saturation; only the frame sequence that is continuous for ≥500ms and passes the above check is retained as "valid speech / machine sound segment".

[0063] Step S2012: Perform frame segmentation on the effective acoustic signal to obtain the framed acoustic signal.

[0064] Specifically, the frame length is set to 25ms (sampling rate 16kHz → number of sampling points 400), the frame shift is 10ms (160 points), and the frame overlap is 60% to facilitate smoothing. The effective acoustic signal is processed by framing using the frame length and frame shift, and a window function, such as the Hamming window, is applied to each frame signal to divide the continuous signal into 20~50ms frames.

[0065] Furthermore, the acoustic signals during the operation of the photovoltaic inverter can be processed in frames before step S2011, and then endpoint detection can be performed.

[0066] Step S2013: Extract features from the framed acoustic signal to obtain acoustic features.

[0067] Specifically, for each frame of acoustic signal, FFT (Fast Fourier Transform) → 26-dimensional Mel filter bank (a tool for speech signal processing) → log (logarithmic compression) → DCT (Discrete Cosine Transform) → take the first 13 dimensions of MFCC (Mel frequency cepstral coefficients) (0~12), where the pre-emphasis coefficient is 0.97, and there are 24 Mel filter banks.

[0068] Step S2014: Perform dynamic time warping on the acoustic features to obtain the optimal alignment path.

[0069] Specifically, the audio of "normal operating condition" is acquired, processed to obtain the MFCC template sequence T, the audio segment S corresponding to the acoustic features, and the inter-frame distance is calculated, i.e., the Euclidean distance is calculated. :

[0070]

[0071] in, This represents the i-th frame of the MFCC template sequence. This represents the j-th frame of the audio segment corresponding to the acoustic feature; based on the above Euclidean distance calculation, after aligning the MFCC template sequence and the audio segment corresponding to the acoustic feature through the optimal path, all [elements on the path are...] The cumulative value is the DTW distance (cumulative distance).

[0072] Furthermore, in the process of calculating the DTW distance, the following constraints are set: Sakoe-Chiba bandwidth = |ij| ≤ max(len(T), len(S) / 10 (to prevent ill-conditioned alignment); start point / end point are freely aligned.

[0073] Furthermore, if the system is offline, N normal samples are taken, and the D_normal distribution is calculated. As initial threshold If offline, the knobs operated by on-site personnel will be mapped to a threshold. , , The "multiplier" indicates the sensitivity setting of the field sensitivity knob. Then use the default threshold calculated offline. Impartial and unbiased; when If it becomes smaller (minimum 0.5), then Smaller, more sensitive, it will sound an alarm at the slightest abnormality; when If it increases (maximum 2), then The alarm becomes larger and less sensitive, only sounding when there is a significant abnormality; the physical knob's 0-100% scale is linearly turned to... Then calculate the real-time threshold. The "physical knob" is not a standard accessory of any fixed instrument, but rather any adjustable potentiometer or encoder knob determined by the site deployment method, as long as it can convert the rotation angle into an analog / digital signal of 0–1023 (or 0–100%). A B10K rotary potentiometer is used. Advantages: Most intuitive, "screw-tightening" operation.

[0074] Specifically, the DTW distance between each of the N normal samples and the template T is calculated to obtain N distance values. The overall distribution (or array) of N distance values ​​is abbreviated as D_normal; the D_normal distribution is used to calculate... and Therefore, an initial threshold is set. ,in, This represents the mean. It represents the standard deviation.

[0075] Furthermore, the DTW distance D is compared with the aforementioned threshold. If If it is determined to be "normal", it is "abnormal". If it is determined to be normal, the optimal alignment path and DTW distance are output.

[0076] Step S2015: Use the time axis corresponding to the optimal alignment path as the horizontal axis and the preset feature dimension corresponding to the acoustic feature as the vertical axis to establish the current acoustic feature curve.

[0077] Specifically, the steps for extracting the first dimension of MFCC frame by frame are as follows: calculate once for each frame. , The first number in the 13-dimensional MFCC vector represents the approximate energy. The calculation process is as follows: take a 25ms frame (400 points) and apply a Hamming window; perform a 512-point FFT to obtain the complex spectrum, and then calculate the power. The power spectrum is passed through a group of 24 triangular Mel filters to obtain 24 frequency bands of energy. Taking the natural logarithm of the energy of each band, we get a 24-dimensional band. Summation:

[0078]

[0079] The 0th dimension of DCT is a special case, since cos(0)=1, which is equivalent to accumulating logarithmic energy; then smoothing is performed: 3-point median filtering to eliminate spikes.

[0080] Furthermore, the X-axis (horizontal axis) is: frame number × frame shift → seconds, and the Y-axis (vertical axis) is... (Can be normalized to 0–1); Update: Refresh the acoustic feature curve every 1 second, retaining the scrolling window of the most recent 60 seconds.

[0081] Step S202: Obtain the acoustic characteristic curve of the inverter in normal operation, compare the current acoustic characteristic curve with the acoustic characteristic curve of the inverter in normal operation, and determine the operating status of the photovoltaic inverter based on the comparison result. For details, please refer to [link to relevant documentation]. Figure 1 Step S102 of the illustrated embodiment will not be described again here.

[0082] Step S203: Based on the operating status of the photovoltaic inverter, fault handling strategies are used to handle faults in the photovoltaic inverter. For details, please refer to [link to relevant documentation]. Figure 1 Step S103 of the illustrated embodiment will not be described again here.

[0083] This embodiment provides a photovoltaic inverter fault handling method based on acoustic features. By performing endpoint detection and frame segmentation processing on the acoustic signals during the operation of the photovoltaic inverter, it achieves effective denoising and feature extraction of the acoustic signals. Furthermore, by performing dynamic time warping processing on the acoustic features, it effectively solves the similarity calculation problem caused by "length mismatch" and "rhythm difference" in the acoustic signals. Then, by using the current acoustic feature curve, it transforms the high-dimensional time-series features corresponding to the acoustic signals into a two-dimensional visualization of time-feature values, which can help to intuitively identify abnormal moments and feature change trends, laying the foundation for subsequent determination of the operating status of the photovoltaic inverter.

[0084] This embodiment provides a photovoltaic inverter fault handling method based on acoustic characteristics, which can be used in the aforementioned electronic equipment. Figure 3 This is a flowchart of a photovoltaic inverter fault handling method based on acoustic features according to an embodiment of the present invention, as shown below. Figure 3 As shown, the process includes the following steps:

[0085] Step S301: Acoustic signals are collected during the operation of the photovoltaic inverter, and a current acoustic characteristic curve is established based on the acoustic signals during the operation of the photovoltaic inverter. For details, please refer to [link to relevant documentation]. Figure 2 Step S201 of the illustrated embodiment will not be described again here.

[0086] Step S302: Obtain the acoustic characteristic curve of the inverter in normal operation, compare the current acoustic characteristic curve with the acoustic characteristic curve of the inverter in normal operation, and determine the operating status of the photovoltaic inverter based on the comparison result.

[0087] Specifically, step S302 includes:

[0088] Step S3021: Calculate the similarity between the current acoustic characteristic curve and the acoustic characteristic curve of the normally operating inverter.

[0089] Specifically, the DTW distance between the current acoustic characteristic curve and the acoustic characteristic curve of a normally operating inverter is calculated, and the DTW distance is used as the similarity.

[0090] Step S3022: Compare the similarity with a preset threshold. If the similarity is less than the preset threshold and no background alarm information is collected, the photovoltaic inverter is in normal operating condition.

[0091] Specifically, if the cumulative distance of the DTW path is less than a certain set value (e.g., <200), it is considered similar. If the current acoustic characteristic curve is similar to the acoustic characteristic curve of a normally operating inverter, and the background of the photovoltaic inverter does not issue any alarm information, the photovoltaic inverter is determined to be in a normal state.

[0092] In step S3023, if the similarity is less than the preset threshold and background alarm information is collected, the operating status of the photovoltaic inverter is the first abnormal state.

[0093] Step S3024: Perform linear fitting on the current acoustic characteristic curve. If the linear fitting result matches the preset fitting value, the photovoltaic inverter is in a shutdown state.

[0094] Specifically, if the current acoustic characteristic curve is close to a straight line, the photovoltaic inverter is determined to be in a shutdown state.

[0095] Furthermore, the current step for determining whether an acoustic characteristic curve is close to a straight line is to calculate the linear residual, the formula of which is:

[0096]

[0097] Where Std is the standard deviation of the residual sequence, which gives the average fluctuation of the entire curve from the straight line. The value represents the residual; the smaller the value, the closer the curve is to a straight line. The residual represents the difference between the actual energy value and the "ideal straight line". Its calculation method is as follows: [The text abruptly ends here, so the translation stops.] A polynomial fit of the sequence over time yields a straight line. Subtract frame by frame: The difference sequence is .

[0098] Furthermore, straight lines The calculation method is as follows: given a segment Sequence: Frame Number , Indicates sequence length and energy value ,remember:

[0099]

[0100]

[0101]

[0102]

[0103] but , This yields a straight line: .

[0104] Furthermore, if That is, the current acoustic characteristic curve is regarded as a "straight line". This is the residual threshold.

[0105] Furthermore, the absolute value of the slope can be used to determine whether the current acoustic characteristic curve is close to a straight line. The slope k = the coefficient of the first term of polyfit (a function used for polynomial fitting). (Empirical value: 0.002 / frame, corresponding to a change of >10% within 1 second), is considered a "straight line".

[0106] Step S3025: If there is a sudden change in the current acoustic characteristic curve and no alarm information is collected from the background, the operating status of the photovoltaic inverter is the second abnormal state.

[0107] Specifically, if the change in the characteristic value of the current acoustic characteristic curve suddenly increases or suddenly decreases, then the current acoustic characteristic curve exhibits an abrupt change. The abrupt change indices include first-order difference abrupt change, Z-score abrupt change, and sliding variance abrupt change. The steps for identifying a first-order difference abrupt change are: calculate... :

[0108]

[0109] (After normalization), the instantaneous energy jump occurs.

[0110] The steps for identifying Z-score mutations are: calculate the standard deviation. The calculation formula is as follows:

[0111]

[0112] in, Within the current window The average value, Within the same window standard deviation This indicates a deviation greater than the 99.7% confidence interval, which is considered a sudden change and a significant deviation from the relative window mean.

[0113] The steps for detecting abrupt changes in sliding variance are as follows: Calculate Var1s:

[0114]

[0115] Where t represents the current frame number, This indicates the last 1 second, which contains 100 frames. sequence( Var1s indicates 100 Calculate the sample variance. Violent fluctuations within 1 second This indicates that the equipment was operating within its historical normal steady-state range (e.g., the first 5 minutes of silent or stable operation). The long-term average of the variance represents the normal fluctuations that should exist.

[0116] For example, And the duration is <200 ms, possible causes: impact, metal knocking; And subsequently Possible cause: sudden shutdown; And Z>6, possible reasons: microphone saturation / explosion.

[0117] Step S3026: If there is a sudden change in the current acoustic characteristic curve and alarm information is collected from the background, the operating status of the photovoltaic inverter is the third abnormal state.

[0118] Step S303: Based on the operating status of the photovoltaic inverter, fault handling strategies are used to handle faults in the photovoltaic inverter. For details, please refer to [link to relevant documentation]. Figure 2 Step S203 of the illustrated embodiment will not be described again here.

[0119] This embodiment provides a photovoltaic inverter fault handling method based on acoustic features. By combining the acoustic features of the sound of the photovoltaic inverter during operation with background alarm information, the operating status of the photovoltaic inverter is identified, thereby improving the fault detection efficiency of the photovoltaic inverter.

[0120] This embodiment provides a photovoltaic inverter fault handling method based on acoustic characteristics, which can be used in the aforementioned electronic equipment. Figure 4 This is a flowchart of a photovoltaic inverter fault handling method based on acoustic features according to an embodiment of the present invention, as shown below. Figure 4 As shown, the process includes the following steps:

[0121] Step S401: Acoustic signals are collected during the operation of the photovoltaic inverter, and a current acoustic characteristic curve is established based on the acoustic signals during the operation of the photovoltaic inverter. For details, please refer to [link to relevant documentation]. Figure 3 Step S301 of the illustrated embodiment will not be described again here.

[0122] Step S402: Obtain the acoustic characteristic curve of the inverter in normal operation, compare the current acoustic characteristic curve with the acoustic characteristic curve of the inverter in normal operation, and determine the operating status of the photovoltaic inverter based on the comparison result. For details, please refer to [link to relevant documentation]. Figure 3 Step S302 of the illustrated embodiment will not be described again here.

[0123] Step S403: Based on the operating status of the photovoltaic inverter, fault handling strategies are used to handle the photovoltaic inverter.

[0124] Specifically, step S403 includes:

[0125] Step S4031: If the photovoltaic inverter is in normal operation, a sleep command is sent to the photovoltaic inverter, and a work command is sent to the photovoltaic inverter after a preset time period.

[0126] Specifically, if the photovoltaic inverter is in normal operation, the control system will go into sleep mode and repeat the workflow after a period of time. The preset time period can be set by the on-site personnel, such as three hours.

[0127] Step S4032: If the photovoltaic inverter is in the first abnormal state, or in the shutdown state, or in the third abnormal state, an audible and visual alarm will be triggered, and a maintenance work order will be sent to the client.

[0128] Specifically, if the photovoltaic inverter is in the first abnormal state, or in the shutdown state, or in the third abnormal state, a work order will be issued to the maintenance personnel for manual handling, and an audible and visual alarm will be triggered when the maintenance personnel arrive, so that the maintenance personnel can locate the photovoltaic inverter.

[0129] Step S4033: If the operating state of the photovoltaic inverter is the second abnormal state, then obtain the acoustic characteristic curves of the photovoltaic inverter in multiple time periods, update the operating state of the photovoltaic inverter based on the acoustic characteristic curves in multiple time periods, and perform fault handling on the photovoltaic inverter based on the updated operating state of the photovoltaic inverter.

[0130] Specifically, the process involves three consecutive workflows: collecting acoustic characteristic curves over three time periods and determining the corresponding operating status of the photovoltaic inverter. If the photovoltaic inverter is determined to be in normal operation all three times, the system goes into sleep mode and repeats the workflow after a period of time (e.g., three hours). If the photovoltaic inverter experiences one or more first abnormal states, one or more shutdown states, or one or more third abnormal states, a work order is dispatched to maintenance personnel for manual handling. An audible and visual alarm is triggered when maintenance personnel arrive to help them locate the photovoltaic inverter. If the photovoltaic inverter experiences three second abnormal states, a work order is dispatched to maintenance personnel for manual handling. If the second abnormal state occurs less than three times and the first, shutdown, and third abnormal states do not occur, the above process is repeated. If the above process is repeated three times and the above situation still occurs, the system stops determining the status and dispatches a work order to maintenance personnel for manual handling.

[0131] This embodiment provides a photovoltaic inverter fault handling method based on acoustic features. It combines the acoustic features of the sound of the photovoltaic inverter during operation with background alarm information to identify the operating status of the photovoltaic inverter. Then, it classifies the photovoltaic inverter based on the operating status, realizes targeted processing of different operating states of the photovoltaic inverter, and improves the fault handling efficiency of the photovoltaic inverter.

[0132] This embodiment also provides a photovoltaic inverter fault handling device based on acoustic characteristics. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0133] This embodiment provides a photovoltaic inverter fault handling device based on acoustic characteristics, such as... Figure 5 As shown, it includes:

[0134] Module 501 is established to collect acoustic signals during the operation of the photovoltaic inverter and to establish the current acoustic characteristic curve based on the acoustic signals during the operation of the photovoltaic inverter.

[0135] The comparison module 502 is used to obtain the acoustic characteristic curve of the inverter in normal operation, compare the current acoustic characteristic curve with the acoustic characteristic curve of the inverter in normal operation, and determine the operating status of the photovoltaic inverter based on the comparison result.

[0136] The fault handling module 503 is used to handle faults in the photovoltaic inverter based on its operating status and using fault handling strategies.

[0137] In some alternative implementations, the establishment module 501 includes:

[0138] The endpoint detection unit is used to perform endpoint detection on the acoustic signals during the operation of the photovoltaic inverter to obtain valid acoustic signals;

[0139] The framing processing unit is used to perform framing processing on the effective acoustic signal to obtain the framed acoustic signal.

[0140] The feature extraction unit is used to extract features from the framed acoustic signal to obtain acoustic features;

[0141] Alignment units are used to perform dynamic time warping on acoustic features to obtain the optimal alignment path;

[0142] A unit is established to use the time axis corresponding to the optimal alignment path as the horizontal axis and the preset feature dimension corresponding to the acoustic feature as the vertical axis to establish the current acoustic feature curve.

[0143] In some alternative implementations, the comparison module 502 includes:

[0144] The calculation unit is used to calculate the similarity between the current acoustic characteristic curve and the acoustic characteristic curve of the normally operating inverter;

[0145] The first judgment unit is used to compare the similarity with a preset threshold. If the similarity is less than the preset threshold and no background alarm information is collected, the photovoltaic inverter is in normal operating status.

[0146] The second judgment unit is used to determine the first abnormal state of the photovoltaic inverter if the similarity is less than a preset threshold and background alarm information is collected.

[0147] In some optional implementations, the comparison module 502 further includes:

[0148] The third judgment unit is used to perform linear fitting on the current acoustic characteristic curve. If the linear fitting result meets the preset fitting value, the photovoltaic inverter is in the shutdown state.

[0149] In some optional implementations, the comparison module 502 further includes:

[0150] The fourth judgment unit is used to determine the second abnormal state of the photovoltaic inverter if there is a sudden change in the current acoustic characteristic curve and no alarm information is collected from the background.

[0151] The fifth judgment unit is used to determine the third abnormal state of the photovoltaic inverter if there is a sudden change in the current acoustic characteristic curve and alarm information is collected from the background.

[0152] In some alternative implementations, the fault handling module 503 includes:

[0153] The sending unit is used to send a sleep command to the photovoltaic inverter if the photovoltaic inverter is in normal operation, and to send a work command to the photovoltaic inverter after a preset time period.

[0154] The alarm unit is used to issue an audible and visual alarm and send a maintenance work order to the client if the photovoltaic inverter is in the first abnormal state, the shutdown state, or the third abnormal state.

[0155] The update unit is used to obtain the acoustic characteristic curves of the photovoltaic inverter in multiple time periods if the operating state of the photovoltaic inverter is the second abnormal state, update the operating state of the photovoltaic inverter based on the acoustic characteristic curves in multiple time periods, and perform fault handling on the photovoltaic inverter based on the updated operating state of the photovoltaic inverter.

[0156] Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0157] In this embodiment, a photovoltaic inverter fault handling device based on acoustic characteristics is presented in the form of a functional unit. Here, a unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that execute one or more software or fixed programs, and / or other devices that can provide the above functions.

[0158] This invention also provides a computer device having the above-described features. Figure 5 The diagram shows a photovoltaic inverter fault handling device based on acoustic characteristics.

[0159] Please see Figure 6 , Figure 6 This is a schematic diagram of the structure of a computer device provided in an optional embodiment of the present invention, such as... Figure 6As shown, the computer device includes one or more processors 10, memory 20, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. The components communicate with each other via different buses and can be mounted on a common motherboard or otherwise installed as needed. The processors can process instructions executed within the computer device, including instructions stored in or on memory to display graphical information of a GUI on external input / output devices (such as display devices coupled to the interfaces). In some alternative implementations, multiple processors and / or multiple buses can be used with multiple memories, if desired. Similarly, multiple computer devices can be connected, each providing some of the necessary operations (e.g., as a server array, a group of blade servers, or a multiprocessor system). Figure 6 Take a processor 10 as an example.

[0160] Processor 10 may be a central processing unit, a network processor, or a combination thereof. Processor 10 may further include a hardware chip. The hardware chip may be an application-specific integrated circuit (ASIC), a programmable logic device (PLD), or a combination thereof. The programmable logic device may be a complex programmable logic device (CAMP), a field-programmable gate array (FPGA), a general-purpose array logic (GDA), or any combination thereof.

[0161] The memory 20 stores instructions executable by at least one processor 10 to cause the at least one processor 10 to perform the method shown in the above embodiments.

[0162] The memory 20 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the computer device. Furthermore, the memory 20 may include high-speed random access memory and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some alternative embodiments, the memory 20 may optionally include memory remotely located relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0163] The memory 20 may include volatile memory, such as random access memory; the memory may also include non-volatile memory, such as flash memory, hard disk or solid-state drive; the memory 20 may also include a combination of the above types of memory.

[0164] The computer device also includes an input device 30 and an output device 40. The processor 10, memory 20, input device 30, and output device 40 can be connected via a bus or other means. Figure 6 Taking the example of a connection between China and Israel via a bus.

[0165] Input device 30 can receive input numerical or character information, and generate key signal inputs related to user settings and function control of the computer device, such as a touchscreen, keypad, mouse, trackpad, touchpad, joystick, one or more mouse buttons, trackball, joystick, etc. Output device 40 may include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors). The aforementioned display devices include, but are not limited to, liquid crystal displays, light-emitting diodes, displays, and plasma displays. In some alternative embodiments, the display device may be a touchscreen.

[0166] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code, which, when accessed and executed by the computer, processor, or hardware, implements the methods shown in the above embodiments.

[0167] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0168] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A photovoltaic inverter fault handling method based on acoustic characteristics, characterized in that, The method includes: Acoustic signals are collected during the operation of the photovoltaic inverter, and a current acoustic characteristic curve is established based on the acoustic signals during the operation of the photovoltaic inverter. Acoustic characteristic curves of a normally operating inverter are obtained, the current acoustic characteristic curves are compared with those of a normally operating inverter, and the operating status of the photovoltaic inverter is determined based on the comparison results. Based on the operating status of the photovoltaic inverter, a fault handling strategy is used to handle the faults of the photovoltaic inverter. The step of comparing the current acoustic characteristic curve with the acoustic characteristic curve of a normally operating inverter, and determining the operating status of the photovoltaic inverter based on the comparison result, includes: The current acoustic characteristic curve is fitted with a straight line. If the straight line fitting result meets the preset fitting value, the photovoltaic inverter is in a shutdown state. If the current acoustic characteristic curve is close to a straight line, the photovoltaic inverter is determined to be in a shutdown state. The determination step for the current acoustic characteristic curve being close to a straight line is: calculating the linear residual, the calculation formula of which is: Where Std is the standard deviation of the residual sequence, which gives the average fluctuation of the entire curve from the straight line. The value represents the residual; the smaller the value, the closer the curve is to a straight line. This represents the difference between the actual energy value and the ideal straight line. The calculation method is as follows: [The text abruptly ends here, likely due to an incomplete sentence or a formatting error.] A polynomial fit of the sequence over time yields a straight line. Subtract frame by frame: The difference sequence is ; The step of comparing the current acoustic characteristic curve with the acoustic characteristic curve of a normally operating inverter, and determining the operating status of the photovoltaic inverter based on the comparison result, further includes: If the current acoustic characteristic curve exhibits a sudden change, and no background alarm information is collected, then the photovoltaic inverter's operating state is the second abnormal state. The sudden change indicators include first-order difference sudden change, Z-score sudden change, and moving variance sudden change. The judgment steps for the first-order difference sudden change are: calculating... : (After normalization), the instantaneous energy jump occurs; The steps for identifying Z-score mutations are: calculate the standard deviation. The calculation formula is: in, Within the current window The average value, Within the same window standard deviation A deviation greater than the 99.7% confidence interval is considered a sudden change, indicating a significant deviation from the relative window mean. The steps for detecting abrupt changes in sliding variance are as follows: Calculate Var1s: Where t represents the current frame number, This indicates the last 1 second, which contains 100 frames. sequence( Var1s indicates 100 Calculate the sample variance. Violent fluctuations within 1 second This indicates that the equipment is in its historical normal steady-state range. The long-term mean of the variance; If there is a sudden change in the current acoustic characteristic curve and a background alarm is detected, the photovoltaic inverter will be in the third abnormal state.

2. The method according to claim 1, characterized in that, The process of establishing the current acoustic characteristic curve based on the acoustic signals during the operation of the photovoltaic inverter includes: Endpoint detection is performed on the acoustic signals during the operation of the photovoltaic inverter to obtain valid acoustic signals; The effective acoustic signal is subjected to frame segmentation to obtain the framed acoustic signal; Feature extraction is performed on the framed acoustic signal to obtain acoustic features; The acoustic features are subjected to dynamic time warping to obtain the optimal alignment path; Using the time axis corresponding to the optimal alignment path as the horizontal axis and the preset feature dimension corresponding to the acoustic feature as the vertical axis, the current acoustic feature curve is established.

3. The method according to claim 1, characterized in that, The step of comparing the current acoustic characteristic curve with the acoustic characteristic curve of a normally operating inverter, and determining the operating status of the photovoltaic inverter based on the comparison result, includes: Calculate the similarity between the current acoustic characteristic curve and the acoustic characteristic curve of the normally operating inverter; The similarity is compared with a preset threshold. If the similarity is less than the preset threshold and no background alarm information is collected, the photovoltaic inverter is in normal operating condition. Alternatively, if the similarity is less than the preset threshold and a background alarm is collected, the operating status of the photovoltaic inverter is the first abnormal state.

4. The method according to claim 3, characterized in that, The fault handling strategy for the photovoltaic inverter based on its operating status includes: If the photovoltaic inverter is in normal operation, a sleep command is sent to the photovoltaic inverter, and a work command is sent to the photovoltaic inverter after a preset time period. If the photovoltaic inverter is in the first abnormal state, or in the shutdown state, or in the third abnormal state, an audible and visual alarm will be triggered, and a maintenance work order will be sent to the client. If the photovoltaic inverter is in the second abnormal state, then the acoustic characteristic curves of the photovoltaic inverter in multiple time periods are obtained, the operating state of the photovoltaic inverter is updated based on the acoustic characteristic curves in multiple time periods, and the photovoltaic inverter is fault-handled based on the updated operating state of the photovoltaic inverter.

5. A photovoltaic inverter fault handling device based on acoustic characteristics, characterized in that, The device includes: A module is established to collect acoustic signals during the operation of the photovoltaic inverter and to establish a current acoustic characteristic curve based on the acoustic signals during the operation of the photovoltaic inverter. The comparison module is used to obtain the acoustic characteristic curve of the inverter in normal operation, compare the current acoustic characteristic curve with the acoustic characteristic curve of the inverter in normal operation, and determine the operating status of the photovoltaic inverter based on the comparison result. The fault handling module is used to handle faults in the photovoltaic inverter based on the operating status of the photovoltaic inverter using fault handling strategies. The comparison module includes: The third judgment unit is used to perform linear fitting on the current acoustic characteristic curve. If the linear fitting result matches the preset fitting value, the photovoltaic inverter is in a shutdown state. Specifically, if the current acoustic characteristic curve is close to a straight line, the photovoltaic inverter is determined to be in a shutdown state. The judgment step for the current acoustic characteristic curve being close to a straight line is: calculating the linear residual, the calculation formula of which is: Where Std is the standard deviation of the residual sequence, which gives the average fluctuation of the entire curve from the straight line. The value represents the residual; the smaller the value, the closer the curve is to a straight line. This represents the difference between the actual energy value and the ideal straight line. The calculation method is as follows: [The text abruptly ends here, likely due to an incomplete sentence or a formatting error.] A polynomial fit of the sequence over time yields a straight line. Subtract frame by frame: The difference sequence is ; The comparison module also includes: The fourth judgment unit is used to determine the second abnormal state of the photovoltaic inverter if there is a sudden change in the current acoustic characteristic curve and no alarm information is collected from the background. The sudden change indicators include first-order difference sudden change, Z-score sudden change, and moving variance sudden change. The judgment steps for the first-order difference sudden change are: calculate... : (After normalization), the instantaneous energy jump occurs; The steps for identifying Z-score mutations are: calculate the standard deviation. The calculation formula is: in, Within the current window The average value, Within the same window standard deviation A deviation greater than the 99.7% confidence interval is considered a sudden change, indicating a significant deviation from the relative window mean. The steps for detecting abrupt changes in sliding variance are as follows: Calculate Var1s: Where t represents the current frame number, This indicates the last 1 second, which contains 100 frames. sequence( Var1s indicates 100 Calculate the sample variance. Violent fluctuations within 1 second This indicates that the equipment is in its historical normal steady-state range. The long-term mean of the variance; The fifth judgment unit is used to determine the third abnormal state of the photovoltaic inverter if there is a sudden change in the current acoustic characteristic curve and alarm information is collected from the background.

6. A computer device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform the photovoltaic inverter fault handling method based on acoustic characteristics as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute the photovoltaic inverter fault handling method based on acoustic features as described in any one of claims 1 to 4.

8. A computer program product, characterized in that, Includes computer instructions for causing a computer to execute the photovoltaic inverter fault handling method based on acoustic features as described in any one of claims 1 to 4.

Images