Power transmission tower bolt looseness online monitoring method and system based on DSP voiceprint information

Abstract

The invention relates to a power transmission tower bolt looseness online monitoring method and system based on DSP voiceprint information. The method comprises the following steps: intercepting a first sound sample from a received sound sample according to the emission time of an excitation signal; second sound samples are intercepted from the sound samples with the starting time of the first sound samples as the reference, and the second sound samples are all located in front of the first sound samples in the time sequence; generating a screening sample by using the second sound sample; and removing parts which are the same as or similar to the screening sample in the first sound sample to obtain an excitation sample, and comparing the excitation sample with the excitation model sample to obtain a loosening result. According to the online monitoring method and system for bolt looseness of the power transmission tower based on the DSP voiceprint information, analysis is carried out by means of an actively generated excitation signal and a mode of comparing voiceprint characteristics of front and back sections, so that a feedback signal of the excitation signal is accurately picked up; and then the loosening condition of the bolt on the transmission tower is determined according to the feedback signal.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to an online monitoring method and system for loosening of transmission tower bolts based on DSP voiceprint information. Background Art

[0002] Transmission line towers are widely used in transmission lines as supports for overhead conductors. The safety of the towers is directly related to the safe and stable operation of the transmission lines. Transmission lines swing in strong winds, and even conductors may dance when certain meteorological conditions such as icing are met. In this case, the stress on the tower increases, causing the bolts of the tower to loosen. If not handled in time, defects such as bolts falling off may occur, and even tower collapse and line break accidents may occur.

[0003] At present, there are some difficulties in voiceprint recognition, such as: In practical applications, acoustic signals are easily interfered by noise signals, especially in noisy environments. The recognition rate of voiceprint recognition is greatly reduced, affecting the practical effect of the voiceprint recognition system.

[0004] The sound characteristics of each tower are not static and fixed, but have time-varying characteristics; and the sound of the tower will change with the changes in the environment. Therefore, how to extract stable and reliable feature parameters is also a difficulty in voiceprint recognition. Summary of the invention

[0005] The present invention provides a method and system for online monitoring of bolt loosening of a transmission tower based on DSP voiceprint information, which uses an actively generated excitation signal and a front-end and back-end voiceprint feature comparison method to perform analysis to accurately pick up a feedback signal of the excitation signal, and then determines the looseness of the bolts on the transmission tower based on the feedback signal.

[0006] The above object of the present invention is achieved through the following technical solutions: In a first aspect, the present invention provides a method for online monitoring of loose bolts of transmission towers based on DSP voiceprint information, comprising: intercepting a first sound sample from the received sound sample according to the sending time of the excitation signal; Taking the start time of the first sound sample as a reference, intercepting a second sound sample from the sound sample, the number of the second sound samples is multiple, and in the time sequence, the second sound samples are all located in front of the first sound sample; generating a screening sample using the second sound sample; Eliminate the parts of the first sound sample that are identical or similar to the screening sample to obtain a stimulus sample; Compare the incentive sample with the incentive model sample to obtain the loosening result.

[0007] In a possible implementation manner of the first aspect, using the second sound sample to generate a screening sample includes: Transfer the screening samples into the time domain and frequency domain for decomposition to obtain decomposed screening samples; Dividing the decomposition screening sample into a first continuous decomposition screening sample and a first non-continuous decomposition screening sample according to the length of the waveform included in the decomposition screening sample; Compare all first continuous decomposition and screening samples, retain waveforms that appear more than or equal to a set number of times or a set proportion, and obtain second continuous decomposition and screening samples; Compare all first non-continuous decomposition and screening samples, retain waveforms that appear more than or equal to a set number of times or a set proportion, and obtain second non-continuous decomposition and screening samples; The second continuous decomposition screening sample and the second non-continuous decomposition screening sample are combined to obtain a screening sample.

[0008] In a possible implementation manner of the first aspect, merging the second continuous decomposition screening sample and the second non-continuous decomposition screening sample includes: Obtaining a profiling line of a second continuous decomposition and screening sample and a profiling line of a second non-continuous decomposition and screening sample respectively, wherein the profiling line comprises an upper profiling line and a lower profiling line; All upper profiling lines are combined to obtain an upper profiling composite line, and all lower profiling lines are combined to obtain a lower profiling composite line; The upper profile synthesis line and the lower profile synthesis line are combined to obtain a screening sample.

[0009] In a possible implementation of the first aspect, when obtaining the upper profiling synthetic line, at least one upper profiling line is moved in the horizontal direction, so that the peaks and troughs on the upper profiling synthetic line that are greater than or equal to a set ratio are enhanced; After determining the upper contour line to be moved, the upper contour line to be moved needs to be regenerated; When the lower profile synthesis line is obtained, at least one lower profile synthesis line is moved in the horizontal direction, so that the peaks and valleys on the lower profile synthesis line that are greater than or equal to a set ratio are enhanced; After the lower contour line to be moved is determined, the lower contour line to be moved needs to be regenerated.

[0010] In a possible implementation of the first aspect, after determining the upper profiling line that needs to be moved and the lower profiling line that needs to be moved, performing relationship merging processing on the upper profiling line that needs to be moved and the lower profiling line that needs to be moved; Relationship merging means that the upper contour line that needs to be moved and the lower contour line that needs to be moved belong to the same decomposition screening sample.

[0011] In a possible implementation of the first aspect, removing a portion of the first sound sample that is identical to or similar to the screening sample to obtain the excitation sample includes: Processing the first sound sample by wavelet decomposition to obtain a first sound sample waveform, wherein the number of the first sound sample waveforms is multiple, and the first sound sample waveform has a starting position point and an end position point; The first sound sample waveform is superimposed on the screening sample, and the superposition result is recorded, and the positions of the superposition use the starting position point and the ending position point of the first sound sample waveform; The waveform of the first sound sample that does not appear in the screening sample is counted as the excitation sample.

[0012] In a possible implementation manner of the first aspect, the method further includes: determining an attenuation coefficient according to the excitation signal and the first sound sample and repairing the first sound sample waveform using the attenuation coefficient; Putting the restored first sound sample waveform belonging to the excitation signal into the excitation sample; The harmonics and subharmonics corresponding to the restored first sound sample waveform belonging to the excitation signal are placed into the excitation sample.

[0013] In a second aspect, the present invention provides an online monitoring device for loosening of transmission tower bolts based on DSP voiceprint information, comprising: A first sample interception unit, used for intercepting a first sound sample from a received sound sample according to the sending time of the excitation signal; A second sample interception unit is used to intercept a second sound sample from the sound sample based on the start time of the first sound sample, the number of the second sound samples is multiple, and in the time sequence, the second sound samples are all located in front of the first sound sample; a sample generating unit for generating a screening sample using the second sound sample; A sample elimination unit, used to eliminate the parts of the first sound sample that are identical or similar to the screening sample, to obtain an excitation sample; The sample comparison unit is used to compare the excitation sample with the excitation model sample to obtain a loosening result.

[0014] In a third aspect, the present invention provides an online monitoring system for loosening of transmission tower bolts based on DSP voiceprint information, the system comprising: one or more memories for storing instructions; and One or more processors, used to call and run the instructions from the memory to execute the method as described in the first aspect and any possible implementation of the first aspect.

[0015] In a fourth aspect, the present invention provides a computer-readable storage medium, the computer-readable storage medium comprising: Program, when the program is executed by a processor, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0016] In a fifth aspect, the present invention provides a computer program product, comprising program instructions, and when the program instructions are executed by a computing device, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0017] In a sixth aspect, the present invention provides a chip system comprising a processor for implementing the functions involved in the above aspects, for example, generating, receiving, sending, or processing the data and / or information involved in the above methods.

[0018] The chip system may be composed of chips, or may include chips and other discrete devices.

[0019] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wired or wireless means, or the processor and the memory can also be coupled on the same device. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 The present invention provides a schematic flowchart of the steps of an online monitoring method for loosening of transmission tower bolts.

[0021] Figure 2 It is a schematic diagram of obtaining a first sound sample and a second sound sample provided by the present invention.

[0022] Figure 3 It is a schematic diagram of the relative positions of a second sound sample and a first sound sample in time provided by the present invention.

[0023] Figure 4 It is a schematic diagram of a process for obtaining a screening sample provided by the present invention.

[0024] Figure 5 It is a schematic diagram of an audio signal provided by the present invention.

[0025] Figure 6 It is a schematic diagram of synthesizing a contour line using the peaks or troughs of an audio signal provided by the present invention. DETAILED DESCRIPTION

[0026] In order to more conveniently understand the technical solution of the present invention, the relevant technology is first introduced.

[0027] One way of voiceprint recognition is to directly collect voiceprint information and then analyze the collected sound samples. This analysis method requires relatively complex preliminary signal processing to obtain the target voiceprint. The difficulty in obtaining the target voiceprint lies in that when the environment in which the target voiceprint is generated changes, the difficulty of picking up will suddenly increase, and even the situation of being unable to pick up may occur.

[0028] This problem also exists when using neural networks for picking processing, because the generalization ability and stability of the model are limited by the training environment and parameter settings.

[0029] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings.

[0030] The present invention discloses an online monitoring method for loosening of transmission tower bolts based on DSP voiceprint information. Figure 1 In some examples, the online monitoring method for loosening of transmission tower bolts based on DSP voiceprint information disclosed in the present invention includes the following steps: S101, intercepting a first sound sample from a received sound sample according to the sending time of the excitation signal; S102, taking the start time of the first sound sample as a reference, intercepting a second sound sample from the sound sample, the number of the second sound samples being multiple, and the second sound samples being all located ahead of the first sound sample in time sequence; S103, using the second sound sample to generate a screening sample; S104, removing the parts of the first sound sample that are identical or similar to the screening sample to obtain a stimulus sample; S105, comparing the excitation sample with the excitation model sample to obtain a loosening result.

[0031] In step S101, firstly, a first sound sample is intercepted from the received sound sample according to the sending time of the excitation signal, such as Figure 2 As shown, the excitation signal here is emitted by an excitation device installed on a transmission tower, and the working time of the excitation device is a known quantity, so the starting time of the first sound sample can be conveniently determined, and the starting time is the same as the generation time of the excitation signal or slightly earlier than the generation time of the excitation signal.

[0032] Regarding the cutoff time of the first sound sample, it is generally determined according to the height of the transmission tower and the installation location of the excitation device, and the duration of the first sound sample is generally controlled at 3-5 seconds.

[0033] In step S102, a second sound sample is intercepted from the sound sample based on the start time of the first sound sample. The number of the second sound samples is multiple, and in the time sequence, all the second sound samples are located in front of the first sound sample, as shown in 3.

[0034] The second sound sample is generally obtained in an interval acquisition manner.

[0035] In step S103, a second sound sample is used to generate a screening sample. It should be understood that the second sound sample can be understood as the first sound sample that does not include the excitation signal feedback. That is, using the second sound sample, the part of the first sound sample except the excitation signal and the excitation signal feedback signal can be eliminated.

[0036] In step S104, the parts of the first sound sample that are identical or similar to the screening sample are removed to obtain an excitation sample. Finally, in step S105, the excitation sample is compared with the excitation model sample to obtain a loosening result.

[0037] In the comparison method here, the content included in the excitation model sample is obtained when the bolts are not loose. When the similarity between the excitation sample and the excitation model sample is high, it is considered that the bolts on the transmission tower are not loose. Otherwise, it means that the bolts on the transmission tower are loose.

[0038] The advantage of the above method is that it does not require additional model training, but uses the second sound sample to screen the first sound sample. When selecting the detection time period, it is necessary to select a time when the surrounding environment is relatively stable. Here, the surrounding environment stability refers to the stability of temperature, wind speed, light and other conditions. At the same time, in terms of obtaining sound samples, choose to obtain them by direct contact with the transmission tower instead of obtaining them through the air medium.

[0039] The purpose of using multiple second sound samples is to improve the accuracy of screening samples by averaging.

[0040] For some examples, see Figure 4 , the specific way to generate the screening sample using the second sound sample is: S201, transferring the screened samples into the time domain and the frequency domain for decomposition to obtain decomposed screened samples; S202, dividing the decomposition and screening samples into a first continuous decomposition and screening sample and a first non-continuous decomposition and screening sample according to the length of the waveform included in the decomposition and screening sample; S203, comparing all first continuous decomposition and screening samples, retaining waveforms that appear more than or equal to a set number of times or a set proportion, to obtain second continuous decomposition and screening samples; S204, comparing all first non-continuous decomposition and screening samples, retaining waveforms that appear more than or equal to a set number of times or a set ratio, to obtain second non-continuous decomposition and screening samples; S205, merging the second continuous decomposition screening sample and the second non-continuous decomposition screening sample to obtain a screening sample.

[0041] In step S201, the screened samples are first transferred to the time domain and frequency domain for decomposition (wavelet decomposition) to obtain decomposed screened samples. At this time, the decomposed screened samples are composed of multiple waveforms, each of which has an amplitude, a frequency, a starting position and an end position.

[0042] Then in step S202, the decomposition and screening samples are divided into a first continuous decomposition and screening sample and a first discontinuous decomposition and screening sample according to the length of the waveform included in the decomposition and screening samples. The length of the waveform corresponds to the appearance time of the waveform. The specific processing method is to put the waveform whose appearance time length is equal to the appearance time length of the decomposition and screening sample into the first continuous decomposition and screening sample, and put the waveform whose appearance time length is less than the appearance time length of the decomposition and screening sample into the first discontinuous decomposition and screening sample.

[0043] Next, in step S203, all first continuous decomposition and screening samples are compared, and waveforms with a number of occurrences greater than or equal to a set number of times or a set ratio are retained to obtain second continuous decomposition and screening samples. The purpose of this step is to remove interference noise in the first continuous decomposition and screening samples.

[0044] In step S204, all first non-continuous decomposition and screening samples are compared, and waveforms that appear more than or equal to a set number of times or a set proportion are retained to obtain second non-continuous decomposition and screening samples. The purpose of this step is also to remove interference noise in the first non-continuous decomposition and screening samples.

[0045] The interference noise here is generated by factors such as acquisition error, calculation error and surrounding environment. In the present invention, the role of the second sound sample is to feedback the background environment before the excitation signal is generated, so these interference noises need to be removed.

[0046] Finally, in step S205, the second continuous decomposition screening sample and the second non-continuous decomposition screening sample are combined to obtain a screening sample.

[0047] The specific method of merging the second continuous decomposition screening sample and the second non-continuous decomposition screening sample is: S301, respectively obtaining a profiling line of a second continuous decomposition and screening sample and a profiling line of a second non-continuous decomposition and screening sample, wherein the profiling line includes an upper profiling line and a lower profiling line; S302, merging all the upper profiling lines to obtain an upper profiling composite line, and merging all the lower profiling lines to obtain a lower profiling composite line; S303, merging the upper profile synthesis line and the lower profile synthesis line to obtain a screening sample.

[0048] The specific method of obtaining the profiling line of the second continuous decomposition and screening samples is to generate an audio signal using the second continuous decomposition and screening samples after the interference noise removal process, and then use the peaks and troughs of the audio signal to synthesize the profiling lines respectively. The profiling line synthesized using the peaks is called the upper profiling line, and the profiling line synthesized using the troughs is called the lower profiling line, such as Figure 5 and Figure 6 shown.

[0049] Then, all the upper profiling lines are merged to obtain an upper profiling synthetic line, all the lower profiling lines are merged to obtain a lower profiling synthetic line, and finally, the upper profiling synthetic line and the lower profiling synthetic line are merged to obtain a screening sample.

[0050] When obtaining the upper profile synthesis line, the following contents are also added: In a possible implementation of the first aspect, when obtaining the upper profiling synthetic line, at least one upper profiling line is moved in the horizontal direction so that the peaks and troughs on the upper profiling synthetic line that are greater than or equal to a set ratio are enhanced, and after determining the upper profiling line to be moved, the upper profiling line to be moved needs to be regenerated.

[0051] The purpose of moving at least one upper contour line in the horizontal direction is to take into account that when intercepting the second sound sample, the starting time point and the ending time point of intercepting the second sound sample may not be appropriate, which will result in the peaks and troughs that appear according to a certain rule not being aligned when all the upper contour lines are merged.

[0052] At this time, the peaks and troughs cannot be enhanced, and may even be weakened, resulting in the loss or weakening of the characteristics carried by the upper contoured synthetic line.

[0053] In order to solve this problem, the present invention uses a method of moving at least one upper profiling line in the horizontal direction to carry out processing, and the purpose of the movement is to make the peaks and troughs on the upper profiling synthetic line be aligned as much as possible.

[0054] Of course, it may happen that the peaks and troughs cannot be completely aligned. In this case, an alignment ratio needs to be calculated, and the ratio is generally controlled to be greater than or equal to 98%.

[0055] Similarly, when obtaining the lower profiling composite line, at least one lower profiling line is moved in the horizontal direction so that the peaks and troughs on the lower profiling composite line that are greater than or equal to the set ratio are enhanced, and after determining the moved lower profiling line, the lower profiling line that needs to be moved needs to be regenerated.

[0056] Further, after determining the upper profiling line and the lower profiling line that need to be moved, the upper profiling line and the lower profiling line that need to be moved are subjected to relationship merging processing, and the purpose of the merging processing is to reduce the number of regenerated upper profiling synthetic lines and the number of lower profiling lines.

[0057] Relationship merging means that the upper contour line that needs to be moved and the lower contour line that needs to be moved belong to the same decomposition screening sample.

[0058] For example, if an upper profiling synthesis line and a lower profiling line need to be moved at the same time, if the upper profiling synthesis line and the lower profiling line belong to the same decomposition and screening sample, then only one decomposition and screening sample needs to be moved to simultaneously generate a new upper profiling synthesis line and a new lower profiling line.

[0059] In some examples, the specific method of removing the same or similar parts of the first sound sample as the screening sample to obtain the excitation sample is as follows: S401, processing a first sound sample by using a wavelet decomposition method to obtain a first sound sample waveform, wherein the number of the first sound sample waveforms is multiple, and the first sound sample waveform has a starting position point and an end position point; S402, superimposing the first sound sample waveform onto the screening sample, and recording the superimposition result, wherein the superimposition position uses the starting position point and the ending position point of the first sound sample waveform; S403, counting the waveforms of the first sound samples that do not appear in the screening samples as excitation samples.

[0060] In step S401 to step S403, after the first sound sample is processed by wavelet decomposition, the obtained first sound sample waveform is superimposed on the screening sample, and the superposition result is recorded synchronously. The superposition result means that the screening sample is compared with the screening sample superimposed with the first sound sample waveform, and the increase in area is greater than or equal to a set value. At this time, the superposition result is 1, otherwise the superposition result is 0.

[0061] A superposition result of 1 indicates that the first sound sample waveform appears on the screening sample, whereas a superposition result of 1 indicates that the first sound sample waveform does not appear on the screening sample.

[0062] Finally, the first sound sample waveform that does not appear in the screening sample is used as the excitation sample.

[0063] Furthermore, it also includes: S501, determining an attenuation coefficient according to an excitation signal and a first sound sample and repairing the first sound sample waveform using the attenuation coefficient; S502, putting the first sound sample waveform that has been repaired and belongs to the excitation signal into the excitation sample; S503: Put the harmonics and subharmonics corresponding to the first sound sample waveform that has been repaired and belongs to the excitation signal into the excitation sample.

[0064] In the contents of step S501 to step S503, some first sound sample waveforms are extracted using the attenuation coefficient, and these extracted first sound sample waveforms are put into the excitation sample as a supplement.

[0065] It should be understood that if the bolts on the transmission tower become loose, harmonic signals and subharmonic signals will appear in the feedback signal generated based on the excitation signal. These signals may be eliminated when obtaining the excitation sample. The content of steps S501 to S503 is to retrieve the first sound sample waveforms that were mistakenly eliminated.

[0066] The specific method is to first determine the attenuation coefficient based on the excitation signal and the first sound sample and use the attenuation coefficient to repair the first sound sample waveform. Here, the excitation signal is a known quantity, and the feedback signal of the excitation signal can be directly obtained from the first sound sample. Then, the attenuation coefficient can be calculated by the peak ratio. The number of attenuation coefficients may be one or more.

[0067] Then, the repaired first sound sample waveform belonging to the excitation signal is put into the excitation sample. The repair is to increase the peak value of the first sound sample waveform by using the attenuation coefficient, and then determine whether the first sound sample waveform at this time is generated based on the excitation signal.

[0068] At the same time, the harmonics and subharmonics corresponding to the repaired first sound sample waveform belonging to the excitation signal need to be put into the excitation sample, because when the bolts are loose, harmonics and subharmonics are easily generated, and the frequency calculation and amplitude calculation of the harmonics and subharmonics are based on the excitation signal.

[0069] The present invention also provides an online monitoring device for loosening of transmission tower bolts based on DSP voiceprint information, comprising: A first sample interception unit, used for intercepting a first sound sample from a received sound sample according to the sending time of the excitation signal; A second sample interception unit is used to intercept a second sound sample from the sound sample based on the start time of the first sound sample, the number of the second sound samples is multiple, and in the time sequence, the second sound samples are all located in front of the first sound sample; a sample generating unit for generating a screening sample using the second sound sample; A sample elimination unit, used to eliminate the parts of the first sound sample that are identical or similar to the screening sample, to obtain an excitation sample; The sample comparison unit is used to compare the excitation sample with the excitation model sample to obtain a loosening result.

[0070] Furthermore, it also includes: A first decomposition processing unit is used to transfer the screening samples into the time domain and the frequency domain for decomposition to obtain decomposed screening samples; A grouping processing unit, used for dividing the decomposition and screening samples into first continuous decomposition and screening samples and first non-continuous decomposition and screening samples according to the length of the waveform included in the decomposition and screening samples; A first comparison processing unit is used to compare all first continuous decomposition and screening samples, retain waveforms with a number of occurrences greater than or equal to a set number of times or a set ratio, and obtain second continuous decomposition and screening samples; A second comparison processing unit is used to compare all the first non-continuous decomposition and screening samples, retain the waveforms whose occurrence times are greater than or equal to the set times or the set proportion, and obtain the second non-continuous decomposition and screening samples; The merging processing unit is used to merge the second continuous decomposition and screening sample with the second non-continuous decomposition and screening sample to obtain a screening sample.

[0071] Furthermore, it also includes: A first processing unit is used to obtain a profiling line of a second continuous decomposition and screening sample and a profiling line of a second non-continuous decomposition and screening sample, respectively, wherein the profiling line includes an upper profiling line and a lower profiling line; The second processing unit is used for merging all the upper profiling lines to obtain an upper profiling composite line, and merging all the lower profiling lines to obtain a lower profiling composite line; The third processing unit is used for merging the upper profiling synthesis line and the lower profiling synthesis line to obtain a screening sample.

[0072] Further, when obtaining the upper profiling synthetic line, at least one upper profiling line is moved in the horizontal direction, so that the peaks and valleys on the upper profiling synthetic line that are greater than or equal to a set ratio are enhanced; After determining the upper contour line to be moved, the upper contour line to be moved needs to be regenerated; When the lower profile synthesis line is obtained, at least one lower profile synthesis line is moved in the horizontal direction, so that the peaks and valleys on the lower profile synthesis line that are greater than or equal to a set ratio are enhanced; After the lower contour line to be moved is determined, the lower contour line to be moved needs to be regenerated.

[0073] Further, after determining the upper profiling line that needs to be moved and the lower profiling line that needs to be moved, a relationship merging process is performed on the upper profiling line that needs to be moved and the lower profiling line that needs to be moved; Relationship merging means that the upper contour line that needs to be moved and the lower contour line that needs to be moved belong to the same decomposition screening sample.

[0074] Furthermore, it also includes: A second decomposition processing unit is used to process the first sound sample by using a wavelet decomposition method to obtain a first sound sample waveform, wherein the number of the first sound sample waveforms is multiple, and the first sound sample waveform has a starting position point and an end position point; A superposition processing unit, used to superimpose the first sound sample waveform onto the screening sample, and record the superposition result, wherein the superposition position uses the starting position point and the ending position point of the first sound sample waveform; The statistical processing unit is used to count the waveforms of the first sound samples that do not appear in the screening samples as excitation samples.

[0075] Furthermore, it also includes: A fourth processing unit, configured to determine an attenuation coefficient according to the excitation signal and the first sound sample and to repair the first sound sample waveform using the attenuation coefficient; A first restoration unit, used for putting the restored first sound sample waveform belonging to the excitation signal into the excitation sample; The second restoration unit is used to put the harmonics and subharmonics corresponding to the restored first sound sample waveform belonging to the excitation signal into the excitation sample.

[0076] In one example, the unit in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0077] For another example, when the units in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0078] Various objects such as various messages / information / equipment / network elements / systems / devices / actions / operations / processes / concepts that may appear in the present invention are named. It can be understood that these specific names do not constitute a limitation on the relevant objects. The names assigned may change with factors such as scenarios, contexts or usage habits. The understanding of the technical meaning of the technical terms in the present invention should be mainly determined from the functions and technical effects embodied / executed in the technical scheme.

[0079] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0080] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0081] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0082] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0083] It should also be understood that in various embodiments of the present invention, the first, second, etc. are only used to indicate that multiple objects are different. For example, the first time window and the second time window are only used to indicate different time windows. They should not have any impact on the time window itself, and the first, second, etc. mentioned above should not impose any limitations on the embodiments of the present invention.

[0084] It should also be understood that in the various embodiments of the present invention, unless otherwise specified or there is any logical conflict, the terms and / or descriptions between the different embodiments are consistent and can be referenced to each other, and the technical features in the different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0085] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a computer-readable storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0086] The present invention also provides an online monitoring system for loosening of transmission tower bolts based on DSP voiceprint information, the system comprising: one or more memories for storing instructions; and One or more processors are used to call and run the instructions from the memory to execute the method as described above.

[0087] The present invention also provides a computer program product, which includes instructions. When the instructions are executed, the terminal device and the network device perform operations of the terminal device and the network device corresponding to the above method.

[0088] The present invention also provides a chip system, which includes a processor for implementing the functions involved in the above content, such as generating, receiving, sending, or processing the data and / or information involved in the above method.

[0089] The chip system may be composed of chips, or may include chips and other discrete devices.

[0090] The processor mentioned in any of the above places can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for executing programs for controlling the above-mentioned feedback information transmission method.

[0091] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wire or wireless means to support the chip system to implement various functions in the above embodiments. Alternatively, the processor and the memory can also be coupled on the same device.

[0092] Optionally, the computer instructions are stored in a memory.

[0093] Optionally, the memory is a storage unit within the chip, such as a register, a cache, etc. The memory can also be a storage unit within the terminal located outside the chip, such as a ROM or other types of static storage devices that can store static information and instructions, RAM, etc.

[0094] It can be understood that the memory in the present invention can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0095] The non-volatile memory may be a ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory.

[0096] The volatile memory may be a RAM, which is used as an external cache. There are many different types of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct memory bus RAM.

[0097] The embodiments of this specific implementation method are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for online monitoring of loose bolts of transmission towers based on DSP voiceprint information, characterized in that: include: intercepting a first sound sample from the received sound sample according to the sending time of the excitation signal; Taking the start time of the first sound sample as a reference, intercepting a second sound sample from the sound sample, the number of the second sound samples is multiple, and in the time sequence, the second sound samples are all located in front of the first sound sample; generating a screening sample using the second sound sample; Eliminate the parts of the first sound sample that are identical or similar to the screening sample to obtain a stimulus sample; Compare the incentive sample with the incentive model sample to obtain the loosening result.

2. The method for online monitoring of loose bolts of transmission towers based on DSP voiceprint information according to claim 1 is characterized in that: Generating a filtered sample using the second sound sample includes: Transfer the screening samples into the time domain and frequency domain for decomposition to obtain decomposed screening samples; Dividing the decomposition screening sample into a first continuous decomposition screening sample and a first non-continuous decomposition screening sample according to the length of the waveform included in the decomposition screening sample; Compare all first continuous decomposition and screening samples, retain waveforms that appear more than or equal to a set number of times or a set proportion, and obtain second continuous decomposition and screening samples; Compare all first non-continuous decomposition and screening samples, retain waveforms that appear more than or equal to a set number of times or a set proportion, and obtain second non-continuous decomposition and screening samples; The second continuous decomposition screening sample and the second non-continuous decomposition screening sample are combined to obtain a screening sample.

3. The method for online monitoring of loose bolts of transmission towers based on DSP voiceprint information according to claim 2 is characterized in that: The merging of the second continuous decomposition screening sample and the second non-continuous decomposition screening sample comprises: Obtaining a profiling line of a second continuous decomposition and screening sample and a profiling line of a second non-continuous decomposition and screening sample respectively, wherein the profiling line comprises an upper profiling line and a lower profiling line; All upper profiling lines are combined to obtain an upper profiling composite line, and all lower profiling lines are combined to obtain a lower profiling composite line; The upper profile synthesis line and the lower profile synthesis line are combined to obtain a screening sample.

4. The method for online monitoring of loose bolts of transmission towers based on DSP voiceprint information according to claim 3 is characterized in that: When the upper profiling synthetic line is obtained, at least one upper profiling line is moved in the horizontal direction, so that the peaks and valleys on the upper profiling synthetic line that are greater than or equal to a set ratio are enhanced; After determining the upper contour line to be moved, the upper contour line to be moved needs to be regenerated; When the lower profile synthesis line is obtained, at least one lower profile synthesis line is moved in the horizontal direction, so that the peaks and valleys on the lower profile synthesis line that are greater than or equal to a set ratio are enhanced; After the lower contour line to be moved is determined, the lower contour line to be moved needs to be regenerated.

5. The method for online monitoring of loose bolts of transmission towers based on DSP voiceprint information according to claim 4 is characterized in that: After determining the upper profiling line and the lower profiling line that need to be moved, performing relationship merging processing on the upper profiling line and the lower profiling line that need to be moved; Relationship merging means that the upper contour line that needs to be moved and the lower contour line that needs to be moved belong to the same decomposition screening sample.

6. The method for online monitoring of loose bolts of transmission towers based on DSP voiceprint information according to claim 1 is characterized in that: Eliminate the parts of the first sound sample that are identical or similar to the screening sample, and obtain the excitation samples including: Processing the first sound sample by wavelet decomposition to obtain a first sound sample waveform, wherein the number of the first sound sample waveforms is multiple, and the first sound sample waveform has a starting position point and an end position point; The first sound sample waveform is superimposed on the screening sample, and the superposition result is recorded, and the positions of the superposition use the starting position point and the ending position point of the first sound sample waveform; The waveform of the first sound sample that does not appear in the screening sample is counted as the excitation sample.

7. The method for online monitoring of loose bolts of transmission towers based on DSP voiceprint information according to claim 6 is characterized in that: Also includes: determining an attenuation coefficient according to the excitation signal and the first sound sample and repairing the first sound sample waveform using the attenuation coefficient; Putting the restored first sound sample waveform belonging to the excitation signal into the excitation sample; The harmonics and subharmonics corresponding to the restored first sound sample waveform belonging to the excitation signal are placed into the excitation sample.

8. An online monitoring device for loose bolts on transmission towers based on DSP voiceprint information, characterized in that: include: A first sample interception unit, used for intercepting a first sound sample from a received sound sample according to the sending time of the excitation signal; A second sample interception unit is used to intercept a second sound sample from the sound sample based on the start time of the first sound sample, the number of the second sound samples is multiple, and in the time sequence, the second sound samples are all located in front of the first sound sample; a sample generating unit for generating a screening sample using the second sound sample; A sample elimination unit, used to eliminate the parts of the first sound sample that are identical or similar to the screening sample, to obtain an excitation sample; The sample comparison unit is used to compare the excitation sample with the excitation model sample to obtain a loosening result.

9. An online monitoring system for loose bolts on transmission towers based on DSP voiceprint information, characterized in that: The system comprises: one or more memories for storing instructions; and One or more processors, configured to call and execute the instructions from the memory to perform the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer readable storage medium comprises: The program, when the program is executed by a processor, the method according to any one of claims 1 to 7 is executed.

Images