CN117409815A - PCS fault detection method and related device for energy storage converter - Google Patents
PCS fault detection method and related device for energy storage converter Download PDFInfo
- Publication number
- CN117409815A CN117409815A CN202311707951.8A CN202311707951A CN117409815A CN 117409815 A CN117409815 A CN 117409815A CN 202311707951 A CN202311707951 A CN 202311707951A CN 117409815 A CN117409815 A CN 117409815A
- Authority
- CN
- China
- Prior art keywords
- audio
- data set
- pcs
- audio data
- audio segment
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004146 energy storage Methods 0.000 title claims abstract description 88
- 238000001514 detection method Methods 0.000 title claims abstract description 80
- 238000012545 processing Methods 0.000 claims abstract description 121
- 238000000034 method Methods 0.000 claims abstract description 54
- 230000009467 reduction Effects 0.000 claims abstract description 46
- 238000007781 pre-processing Methods 0.000 claims abstract description 38
- 238000012423 maintenance Methods 0.000 claims abstract description 26
- 238000000605 extraction Methods 0.000 claims abstract description 19
- 230000007613 environmental effect Effects 0.000 claims description 61
- 238000004590 computer program Methods 0.000 claims description 13
- 238000004891 communication Methods 0.000 claims description 12
- 238000001228 spectrum Methods 0.000 claims description 11
- 230000005672 electromagnetic field Effects 0.000 claims description 8
- 238000003860 storage Methods 0.000 claims description 8
- 230000003321 amplification Effects 0.000 claims description 3
- 238000003199 nucleic acid amplification method Methods 0.000 claims description 3
- 238000010183 spectrum analysis Methods 0.000 claims description 3
- 230000005540 biological transmission Effects 0.000 claims description 2
- 238000007405 data analysis Methods 0.000 abstract description 5
- 230000006870 function Effects 0.000 description 13
- 230000002159 abnormal effect Effects 0.000 description 10
- 230000008569 process Effects 0.000 description 7
- 238000010586 diagram Methods 0.000 description 5
- 230000005236 sound signal Effects 0.000 description 5
- 230000003595 spectral effect Effects 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000000284 extract Substances 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000002457 bidirectional effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004140 cleaning Methods 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000000926 separation method Methods 0.000 description 2
- 238000004378 air conditioning Methods 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 239000003990 capacitor Substances 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009432 framing Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000001681 protective effect Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 230000026676 system process Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
- G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
-
- G—PHYSICS
- G10—MUSICAL INSTRUMENTS; ACOUSTICS
- G10L—SPEECH ANALYSIS OR SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING; SPEECH OR AUDIO CODING OR DECODING
- G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
- G10L25/27—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique
- G10L25/30—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 characterised by the analysis technique using neural networks
Abstract
The application discloses an energy storage converter PCS fault detection method and a related device, wherein the method comprises the following steps: acquiring an audio data set of PCS in real time; performing data preprocessing on the audio data set to obtain a first audio segment data set corresponding to the operation audio data and a second audio segment data set corresponding to the environment audio data; obtaining first characteristic information through characteristic extraction; carrying out noise reduction treatment on the first audio segment data set according to the first characteristic information to obtain an audio segment data set to be detected; judging whether the PCS has faults or not according to the audio segment data set to be detected and the standard audio segment data set; if the fault occurs, determining the fault type and generating a fault detection report; and sending a fault detection report. Therefore, whether the PCS is in fault or not is judged through noise reduction processing and data analysis of the audio data, and a fault detection report is correspondingly generated, so that the normal operation and the maintenance timeliness of the PCS are facilitated.
Description
Technical Field
The application relates to the technical field of data processing, in particular to an energy storage converter PCS fault detection method and a related device.
Background
The energy storage converter (Power Conversion System, PCS) is one of the key components in the overall energy storage system, and its operating state has a significant impact on the performance and safety of the energy storage system. In a practical application scenario, the failure of the PCS is often discovered after a certain period of time, and in the middle period of time, some accidents are easy to be caused because the failure is not discovered in time. In practical application, a more common mode of PCS fault detection is to periodically check equipment state and alarm information by a maintainer, and if abnormal conditions or alarm prompts are found, the personnel are contacted for fault detection and maintenance, and the mode requires a user to detect frequently and manually confirm whether faults occur or not, so that the whole flow is not intelligent and has insufficient efficiency.
Therefore, a method for detecting PCS faults of an energy storage converter is needed to solve the above problems.
Disclosure of Invention
The embodiment of the application provides a PCS fault detection method and a related device of an energy storage converter, which are used for determining whether a PCS is faulty or not by carrying out data analysis and processing on audio data generated during the working of the PCS, and correspondingly generating a fault detection report, so that the normal operation and maintenance of the PCS are facilitated.
In a first aspect, an embodiment of the present application provides a method for detecting a PCS fault of an energy storage converter, which is applied to an energy storage system, where the energy storage system includes a PCS, and the PCS includes an audio data acquisition device;
the method comprises the following steps:
acquiring an audio data set of the PCS in real-time operation, wherein the audio data set comprises operation audio data generated by the PCS in operation and environment audio data of an environment where the PCS is located;
performing data preprocessing on the audio data set to obtain a first audio segment data set corresponding to the running audio data and a second audio segment data set corresponding to the environment audio data, wherein the data preprocessing comprises at least one of the following steps: performing mute section audio deleting processing on the operation audio data and/or the environment audio data, and performing cutting-off processing or filling processing on the operation audio data and/or the environment audio data to obtain audio section data with the same length;
extracting features of the second audio segment data set to obtain first feature information corresponding to the environmental audio data;
acquiring a historical audio data set of at least one unit time period from the audio data acquisition device, wherein the unit time period is a time period in a normal running state after the PCS finishes one-time maintenance;
Classifying the historical audio data set to respectively obtain operation audio data and environment audio data corresponding to each unit period;
performing data preprocessing on the operation audio data and the environment audio data corresponding to each unit time period to respectively obtain a third audio segment data set and a fourth audio segment data set;
performing feature extraction according to the fourth audio segment data set to obtain second feature information corresponding to the environmental audio data corresponding to each unit time period;
carrying out noise reduction processing on the third audio segment data set according to the second characteristic information to obtain a standard audio segment data set corresponding to each unit time period;
the noise reduction processing is carried out on the first audio segment data set according to the first characteristic information, so that an audio segment data set to be detected is obtained;
judging whether the PCS has faults or not according to the audio segment data set to be detected and the standard audio segment data set corresponding to each unit time period;
if the PCS fails, determining the failure type of the PCS and generating a failure detection report;
and sending the fault detection report to terminal equipment.
In a second aspect, an embodiment of the present application provides an energy storage converter PCS fault detection device, which is applied to an energy storage system, where the energy storage system includes a PCS, and the PCS includes an audio data acquisition device;
the device comprises: an acquisition unit, a processing unit, a judgment unit, a determination unit and a transmission unit, wherein,
the acquiring unit is configured to acquire an audio data set during real-time running of the PCS, where the audio data set includes running audio data generated during running of the PCS and environmental audio data where the PCS is located;
the processing unit is configured to perform data preprocessing on the audio data set to obtain a first audio segment data set corresponding to the running audio data and a second audio segment data set corresponding to the environmental audio data, where the data preprocessing includes at least one of: performing mute section audio deleting processing on the operation audio data and/or the environment audio data, and performing cutting-off processing or filling processing on the operation audio data and/or the environment audio data to obtain audio section data with the same length;
the processing unit is further used for extracting the characteristics of the second audio segment data set to obtain first characteristic information corresponding to the environmental audio data;
The processing unit is further configured to obtain a historical audio data set of at least one unit period from the audio data acquisition device, where the unit period is a period of time in a normal running state after the PCS completes one-time overhaul;
the processing unit is further used for classifying the historical audio data set to respectively obtain operation audio data and environment audio data corresponding to each unit time period;
the processing unit is further used for carrying out data preprocessing on the operation audio data and the environment audio data corresponding to each unit time period to respectively obtain a third audio segment data set and a fourth audio segment data set;
the processing unit is further used for carrying out feature extraction according to the fourth audio segment data set to obtain second feature information corresponding to the environmental audio data corresponding to each unit time period;
the processing unit is further configured to perform noise reduction processing on the third audio segment data set according to the second feature information, so as to obtain a standard audio segment data set corresponding to each unit time period;
the processing unit is further configured to perform the noise reduction processing on the first audio segment data set according to the first feature information to obtain an audio segment data set to be detected;
The judging unit is configured to judge whether the PCS has a fault according to the audio segment data set to be detected and the standard audio segment data set corresponding to each unit period;
the determining unit is used for determining the fault type of the PCS and generating a fault detection report if the PCS fails;
the sending unit is configured to send the fault detection report to a terminal device.
In a third aspect, an embodiment of the present application provides an electronic device, including a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and configured to be executed by the processor, the programs including instructions for performing steps in any of the methods of the first aspect of the embodiments of the present application.
In a fourth aspect, embodiments of the present application provide a computer-readable storage medium, where the computer-readable storage medium stores a computer program for electronic data exchange, where the computer program causes a computer to perform some or all of the steps as described in any of the methods of the first aspect of the embodiments of the present application.
In a fifth aspect, embodiments of the present application provide a computer program product, wherein the computer program product comprises a non-transitory computer readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in any of the methods of the first aspect of embodiments of the present application. The computer program product may be a software installation package.
It can be seen that, in the embodiment of the present application, by acquiring an audio data set during real-time running of the PCS, where the audio data set includes running audio data generated during running of the PCS and environmental audio data where the PCS is located; performing data preprocessing on the audio data set to obtain a first audio segment data set corresponding to the operation audio data and a second audio segment data set corresponding to the environment audio data; extracting features of the second audio segment data set to obtain first feature information corresponding to the environmental audio data; carrying out noise reduction treatment on the first audio segment data set according to the first characteristic information to obtain an audio segment data set to be detected; judging whether the PCS has faults or not according to the audio segment data set to be detected and the standard audio segment data set; if the PCS fails, determining the failure type of the PCS and generating a failure detection report; and sending a fault detection report to the terminal equipment. Therefore, the method can be realized, and by means of similarity calculation between the audio data and the standard reference data when the PCS works, whether the PCS fails or not is determined, and a failure detection report is correspondingly generated, so that the timeliness of normal operation and maintenance of the PCS is facilitated.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, it is obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a system architecture of an energy storage system according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a method for detecting PCS faults of an energy storage converter according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a functional unit of a PCS fault detection device for an energy storage converter provided in an embodiment of the present application.
Detailed Description
In order to make the present application solution better understood by those skilled in the art, the following description will clearly and completely describe the technical solution in the embodiments of the present application with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art based on the embodiments herein without making any inventive effort, are intended to be within the scope of the present application.
The terms first, second and the like in the description and in the claims of the present application and in the above-described figures, are used for distinguishing between different objects and not for describing a particular sequential order. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion. For example, a process, method, system, article, or apparatus that comprises a list of steps or elements is not limited to only those listed steps or elements but may include other steps or elements not listed or inherent to such process, method, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearances of such phrases in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. Those of skill in the art will explicitly and implicitly appreciate that the embodiments described herein may be combined with other embodiments.
For a better understanding of aspects of embodiments of the present application, reference is made to electronic devices, related terms, concepts and related contexts to which embodiments of the present application may relate.
The electronic device may be a portable electronic device that also contains other functions such as personal digital assistant and/or music player functions, such as a cell phone, tablet computer, wearable electronic device with wireless communication capabilities (e.g., a smart watch), etc. Exemplary embodiments of portable electronic devices include, but are not limited to, portable electronic devices that are equipped with IOS systems, android systems, microsoft systems, or other operating systems. The portable electronic device may also be other portable electronic devices such as a Laptop computer (Laptop) or the like. It should also be understood that in other embodiments, the electronic device may also be an electronic device for controlling the fault detection system of the energy storage converter in the present application.
The energy storage converter (Power Conversion System, PCS) is also called a bidirectional energy storage converter, and is a biphase current controllable conversion device for connecting an energy storage battery system and a power grid (or a load). The charging and discharging processes of the energy storage battery can be controlled, the conversion of alternating current and direct current is realized between the power grid and the energy storage system, and the power can be directly supplied to an alternating current load under the condition of no power grid. The device consists of a direct current/alternating current bidirectional converter, a control unit, protection, monitoring and other software and hardware, and can realize the adjustment of active power and reactive power of a power grid, the protective charge and discharge of a battery, the adjustment of output voltage and frequency and the like.
Specifically, as shown in fig. 1, fig. 1 is a schematic system architecture of an energy storage system according to an embodiment of the present application. As shown in fig. 1, the energy storage system establishes a communication connection with a terminal device, which may be one or more of the electronic devices described above.
Illustratively, the energy storage system as shown in FIG. 1 includes, but is not limited to, the following: an energy storage battery pack, an energy storage converter, an external power grid and the like. The energy storage converter provides an interface between the public power grid and the energy storage battery pack, and realizes the charge and discharge of the energy storage system. In the scheme, the energy storage converter is additionally provided with an audio data acquisition device for acquiring audio data generated in the operation process of the energy storage converter and environmental audio data of the PCS. The energy storage system processes audio data based on the audio data set acquired by the data acquisition device, so that PCS fault detection and analysis are performed according to the processed data, a fault detection report is generated and then sent to the terminal equipment, and the terminal equipment uses personnel to timely monitor and troubleshoot the PCS fault to ensure the normal operation of the energy storage system.
The present application will be described in detail with reference to specific examples.
Referring to fig. 2, fig. 2 is a schematic flow chart of a method for detecting a PCS fault of an energy storage converter, which is applied to an energy storage system, wherein the energy storage system includes a PCS, and the PCS includes an audio data acquisition device; as shown in fig. 2, the method for detecting the PCS fault of the energy storage converter specifically includes the following steps:
s201, acquiring an audio data set of the PCS in real-time operation.
The audio data set comprises operation audio data generated when the PCS operates and environment audio data where the PCS is located.
For example, in actual operation, the PCS may generate a corresponding sound during normal operation or abnormal operation of each electronic component, for example: electromagnetic sounds generated by internal capacitors, reactors, etc., sounds generated by corona discharge of incoming and outgoing lines and hardware, etc. Meanwhile, in the environment where the PCS is located, there is also an environmental sound, that is, a sound existing around the device by the life of a person or in the environment itself, for example: human speech, air conditioning wind, etc. (where the ambient sound may be viewed as a noise), and the PCS may also differ in its ambient sound when operating at different times. The audio data acquisition device of the PCS acquires the operation audio data generated during the operation of the PCS in real time, and simultaneously acquires the environment audio data.
Illustratively, during operation, a PCS may behave as if it were to fail: the noise decibel value generated during the operation is obviously increased, and meanwhile, the noise is possibly accompanied by discharging sound or vibration sound different from the normal operation state. For example: if the direct current absolute value of the neutral point of the PCS has obvious mutation, compared with the direct current absolute value of the PCS in a normal running state, vibration and noise signals of internal parts of the PCS can be caused to be obviously increased, and abnormal audio data caused by vibration or noise signals can occur in data acquired in real time by the audio data acquisition device.
Illustratively, if the internal components of the PCS are, for example: the problem of insufficient fastening of bolts and the like also causes abnormal vibration caused by frictional collision between internal parts, and generates audio data different from the normal operation state.
In an exemplary embodiment, the energy storage system is in a normal running state of the PCS in a unit period after each maintenance of the PCS, and at this time, the running audio data and the environmental audio data of the PCS are collected as reference data. And judging whether and what kind of faults occur in the current PCS according to the comparison between the operation audio data in the normal operation state and the operation audio data acquired in real time. For example: the abrupt abnormal discharge of current may cause abnormal audio data to occur.
Further, the energy storage system obtains the operation audio data and the environment audio data from the audio data acquisition device.
Illustratively, the environmental audio data is external environmental audio during PCS operation, and the operational audio data includes relevant audio generated during operation of the internal devices.
In a possible example, an audio data acquisition device of a PCS related in the present application includes a first acquisition device and a second acquisition device, where the first acquisition device is disposed inside the PCS, and the second acquisition device is disposed outside the PCS.
The first acquisition device and the second acquisition device acquire the operation audio data of the PCS in the operation process and also acquire the environment audio data. However, due to the location setting, the audio signal strength of the environmental audio data collected by the first collection device is lower than the audio signal strength of the environmental audio data collected by the second collection device.
Further, after the energy storage system amplifies the audio data of the environmental audio data of the first acquisition device, the energy storage system performs audio data separation based on the environmental audio data acquired by the second acquisition device to obtain the operation audio data acquired by the first acquisition device.
The energy storage system takes the audio data acquired by the second acquisition device as environment sample data, extracts at least one voiceprint feature class from the environment sample data, and carries out class labeling on each voiceprint feature data to obtain a plurality of voiceprint labels.
Further, the audio data collected by the first collection device and a plurality of voiceprint labels are used as input information of the neural network, and noise data separation is carried out on the audio data collected by the first collection device, so that operation audio data are obtained.
S202, data preprocessing is carried out on the audio data set to obtain a first audio segment data set corresponding to the operation audio data and a second audio segment data set corresponding to the environment audio data.
Wherein the data preprocessing includes at least one of: and performing cutting-off processing or filling processing on the operation audio data and/or the environment audio data to obtain audio segment data with the same length.
Illustratively, the energy storage system performs data preprocessing on the collected operational audio data and environmental audio data, specifically, the data preprocessing includes, but is not limited to: and deleting mute audio segments or blank audio segments in the running audio data and the environment audio data, segmenting the deleted two audio data with the same length, and if audio segments with insufficient length exist, filling the audio to ensure that the audio segments after the data preprocessing are equal-length audio segments. And respectively obtaining a first audio segment data set corresponding to the operation audio data and a second audio segment data set corresponding to the environment audio data after data preprocessing.
The data pre-processing further comprises, illustratively, implementing pre-emphasis of audio in the first set of audio segment data and the second set of audio segment data by means of a filter, wherein the pre-emphasis is used for amplifying high frequency components of the sound signal. In fact, the power spectrum of speech, music, etc. decreases with increasing frequency, most of its energy being concentrated in the low frequency range. Thus, the resulting signal amplitude is caused by the low frequency component of the signal. Pre-emphasis is a processing method for compensating high frequency components of an original signal. Through pre-emphasis filtering, random noise can be effectively suppressed.
Further, the above-mentioned sound signal is subjected to framing processing. In the scheme, in order to reduce signal interruption at the beginning and the end of each frame, a part of overlapped area is reserved between frames, and each frame is multiplied by a Hamming window function to increase continuity at the left end and the right end of the frame, wherein the window function is mainly used for reducing frequency spectrum leakage, so that the signal better meets the periodic requirement of feature extraction.
And S203, carrying out feature extraction on the second audio segment data set to obtain first feature information corresponding to the environmental audio data.
The energy storage system, for example, extracts first characteristic information from the second audio segment data set that characterizes the current environmental audio data.
S204, acquiring a historical audio data set of at least one unit time period from the audio data acquisition device.
The unit time period is a time period in a normal running state after the PCS finishes one-time maintenance.
Illustratively, the energy storage system obtains a historical audio data set acquired by the audio data acquisition device of the PCS during a unit period after each PCS overhaul period from the data acquisition device of the PCS. The length of the unit time period can be set according to actual scene requirements, and can be 6 hours, 12 hours or other unit time periods after the overhaul period is completed.
S205, classifying the historical audio data set to respectively obtain operation audio data and environment audio data corresponding to each unit period.
S206, performing data preprocessing on the operation audio data and the environment audio data corresponding to each unit time period to respectively obtain a third audio segment data set and a fourth audio segment data set.
The historical audio data set collected by the audio data collecting device still includes operation audio data and environment audio data when the PCS operates, and the operation audio data can be used for representing characteristic information when the PCS operates normally, but still includes environment noise. In addition, in the historical audio data collection acquired after different overhaul periods, the running audio data and the environment audio data also have differences. For example, the influence of the ambient temperature on the operating state of the electronic component, and the ambient audio frequency also varies from moment to moment. Therefore, the running audio data and the environment audio data corresponding to different time periods need to be continuously classified to obtain a third audio segment data set and a fourth audio segment data set corresponding to the two data corresponding to different unit time periods.
And S207, performing feature extraction according to the fourth audio segment data set to obtain second feature information corresponding to the environmental audio data corresponding to each unit time period.
S208, carrying out noise reduction processing on the third audio segment data set according to the second characteristic information to obtain the standard audio segment data set corresponding to each unit time period.
Further, the third audio segment data set is subjected to noise reduction processing according to the second characteristic information of the fourth audio segment data set, so that a standard audio segment data set corresponding to each unit time period is obtained.
S209, carrying out noise reduction processing on the first audio segment data set according to the first characteristic information to obtain an audio segment data set to be detected.
Illustratively, the energy storage system performs noise reduction processing on the first audio segment data set according to first characteristic information corresponding to the environmental audio data. That is, according to the first feature information, feature removal is performed on the environmental noise in the first audio segment data set, and features of operation audio data generated by the internal electronic component during PCS operation are more reserved, so that the audio segment data set to be detected is obtained.
S210, judging whether the PCS has faults or not according to the audio segment data set to be detected and the standard audio segment data set corresponding to each unit time period.
The energy storage system performs audio data similarity analysis according to the audio segment data set to be detected and the standard audio segment data set to obtain an analysis result. The standard audio segment data set is an audio segment data set which is acquired by the audio data acquisition device in a unit time period and subjected to data cleaning after the PCS finishes one-time maintenance. It should be noted that, with the overhaul period in the overhaul plan as a time window, the PCS just overhauled is usually normal in a certain time, so in each overhaul period, the audio data acquisition device acquires the operation audio data and the environmental audio data of the PCS in this period, and after data preprocessing and data cleaning, a standard audio segment data set with the normal working state of the PCS is obtained, and the standard audio segment data set is used as a reference data set.
Further, the energy storage system takes the data of the audio segment to be detected and the data set of the standard audio segment as input data of a neural network, extracts characteristic information of the data set of the audio segment to be detected and the data set of the standard audio segment respectively through a neural network model, calculates the similarity of the distribution of the audio characteristics in the two data sets, and outputs a similarity result.
Further, the energy storage system judges whether the PCS has faults according to the similarity result.
S211, if the PCS fails, determining the failure type of the PCS and generating a failure detection report.
S212, sending the fault detection report to the terminal equipment.
The energy storage system is in communication connection with a terminal device of a user, and maintenance personnel can timely acquire the overall operation state of the energy storage system through the terminal device.
The energy storage system generates a corresponding maintenance proposal according to the fault type, generates a fault detection report, and sends the fault detection report to the terminal equipment, so that the terminal equipment can timely acquire the fault information of the PCS and timely perform fault maintenance or further detection on the PCS according to the fault detection report.
It can be seen that, in the method for detecting the PCS fault of the energy storage converter described in the embodiment of the present application, an audio data set during the real-time operation of the PCS is obtained; performing data preprocessing on the audio data set to obtain a first audio segment data set corresponding to the operation audio data and a second audio segment data set corresponding to the environment audio data; obtaining first characteristic information through characteristic extraction; carrying out noise reduction treatment on the first audio segment data set according to the first characteristic information to obtain an audio segment data set to be detected; judging whether the PCS has faults or not according to the audio segment data set to be detected and the standard audio segment data set; if the PCS fails, determining the failure type of the PCS and generating a failure detection report; and sending a fault detection report to the terminal equipment. Therefore, whether the PCS is in fault or not is judged through noise reduction processing and data analysis of the audio data, and a fault detection report is correspondingly generated, so that the normal operation and the maintenance timeliness of the PCS are facilitated. In addition, the standard audio segment data set used as a reference is obtained by carrying out the processes of data preprocessing, noise reduction processing and the like on the data set acquired by the PCS in the running state after each maintenance, so that the subsequent energy storage system can judge whether the PCS at the current moment has faults or not more rapidly and accurately through the feature comparison and similarity analysis of the audio data acquired in real time and the standard audio segment data set, thereby being more beneficial to the use and maintenance of the PCS.
In one possible example, before the feature extraction is performed on the second audio segment data set to obtain the first feature information corresponding to the environmental audio data, the method may include the following steps: determining a target unit period corresponding to the time of acquiring the audio data set; acquiring the second characteristic information corresponding to the target unit time period; and carrying out sound gain processing on the second audio segment data set according to the second characteristic information and a preset gain coefficient, wherein the sound gain processing is used for carrying out sound amplification processing on each segment of the audio segment in the second audio segment data set.
For example, in order to obtain better feature information corresponding to the environmental audio data, the effect of noise reduction processing on the running audio data is improved. The energy storage system determines a corresponding target unit time period through the time of data acquisition of the audio data acquisition device, wherein the target unit time period refers to the same unit time period in the same day corresponding to the audio data set acquired in real time.
Further, the environmental audio data corresponding to the target unit time period is obtained from the historical audio data set, and the second characteristic information corresponding to the environmental audio data of the environment where the PCS of the target unit time period is located is obtained through data preprocessing and characteristic extraction of the environmental audio data corresponding to the target unit time period. The second characteristic information may be energy information, spectral characteristic information, or other characteristic information of the audio, which may be used to evaluate the volume of the audio, and so on.
Further, the energy storage system can select a preset gain coefficient, and amplify the environmental audio data acquired in real time based on the proper preset gain coefficient and the second characteristic information. The audio frequency amplifying treatment is used for amplifying the weak sound cell number into a signal which has enough power or amplitude and is consistent with the change rule of the original signal, namely, the signal is amplified without distortion.
In this example, the current environmental audio data is amplified by amplifying the environmental audio data acquired in real time. Therefore, the extraction of the first characteristic information is more accurate, the accuracy of noise reduction processing of the running audio data is further improved, and finally the efficiency and accuracy of PCS fault detection are improved.
In one possible example, the noise reduction processing is performed on the first audio segment data set according to the first feature information, and the method may include the steps of: performing spectrum analysis on each section of the audio frequency section in the first audio frequency section data set, and determining noise information and frequency characteristic information in the first audio frequency section data set; and according to the first characteristic information, the noise information and the frequency characteristic information, carrying out noise reduction processing on each audio segment in the first audio segment data set, and extracting each detection audio to obtain the audio data set to be detected, wherein the noise reduction processing is used for removing the environmental noise frequency band in the first audio segment data set.
The energy storage system performs noise reduction processing on the first audio segment data set by acquiring frequency characteristic information and possible noise information capable of characterizing audio characteristics in the first audio segment data set, and then based on the first characteristic information of the second audio segment data corresponding to the environmental audio data set.
Illustratively, the noise reduction process may employ spectral subtraction (Spectral Subtraction): spectral subtraction is a common noise reduction method that is based on the assumption that at different frequencies, the noise component differs from the energy of the original signal component. By calculating a noise estimate and subtracting the noise estimate from the spectrum of the original signal, a noise reduction effect can be achieved. Spectral subtraction can be achieved by Short-time fourier transform (Short-Time Fourier Transform, STFT).
For example, the noise reduction processing may be performed based on a filter, updated according to a difference between the input signal and the reference signal, and the noise reduced signal may be output as the audio signal of the audio data set to be detected.
The first audio segment data set may also be noise-reduced based on a pre-trained neural network model, for example, by a deep learning approach.
It should be noted that, the above noise reduction method is one or more noise reduction processing methods that may be selected in the scheme of the present application, and in practical application, an appropriate method may be selected according to a specific situation, or a combination of a plurality of methods may be used to achieve a better noise reduction effect. The present invention is not particularly limited herein.
It can be seen that, in this example, the noise reduction processing of the running audio data is implemented by the feature information of the environmental audio data to obtain more accurate audio segment data when the PCS runs. The more accurate operation audio frequency segment data can better extract the audio frequency characteristic information during operation, thereby improving the accuracy of PCS fault detection.
In one possible example, the determining whether the PCS is faulty according to the audio segment data set to be detected and the standard audio segment data set may include the following steps: acquiring target standard audio segment data corresponding to the target unit time period from the standard audio segment data set; taking the target standard audio segment data and the audio segment data set to be detected as input data of a judgment model to obtain an output result, wherein the judgment model is used for detecting similarity between audio data, and the output result is used for representing the similarity between the input data; and judging whether the PCS has faults or not according to the relation between the output result and a preset threshold value.
The energy storage system acquires target standard audio segment data of a target unit period corresponding to time from the standard audio segment data set according to the time of acquiring the audio segment data set to be detected in real time. This process is to reduce as much as possible the error caused by the environmental noise in the target standard audio segment data.
Further, the energy storage system takes the data set of the audio segment to be detected and the data of the target standard audio segment as input data of the judgment model, and obtains an output result. The output result is used for representing the similarity between the current input data.
In one possible example, the determining whether the PCS is faulty according to the relationship between the output result and a preset threshold may include the following steps: if the output result is greater than or equal to the preset threshold value, determining that the PCS fails; and if the output result is smaller than the preset threshold value, determining that the PCS has no fault.
Illustratively, the energy storage system determines whether the PCS is malfunctioning according to a magnitude relationship between the similarity value and a preset threshold. Specifically, if the similarity value is smaller than or equal to a preset threshold value, the fact that the similarity between the data in the audio segment data set to be detected and the target standard audio segment data is smaller is indicated, and the PCS at the current moment is determined to be faulty; if the similarity value is larger than a preset threshold value, the similarity between the two data is higher, and the PCS is determined to normally operate at the current moment.
In one possible example, after obtaining the standard audio segment data set, the energy storage system may obtain audio energy corresponding to the data set corresponding to different time instants. And obtaining a fault judgment threshold value corresponding to the current moment according to the audio energy distribution corresponding to the different moments. And then, carrying out operations such as audio feature extraction, audio feature distribution calculation and the like on the data in the audio segment data set to be detected, and judging whether the audio energy distribution corresponding to the audio segment data set to be detected meets the criterion of a fault judgment threshold value. If yes, determining that the current PCS fails.
For example, because the environmental conditions will also change during different overhaul time periods, and the change of the environmental conditions will also have a certain influence on the running state of the PCS, in this application, by acquiring the historical audio data sets corresponding to the overhaul periods, multiple different fault determination thresholds can be set according to the historical audio data sets of different time nodes, so as to ensure the accuracy and flexibility of fault determination.
In this example, the energy storage system determines whether the current PCS has a fault by comparing the similarity between the audio segment data set to be detected and the standard audio segment data set by using the standard audio segment data set as standard reference data. When a large difference exists between sound data and standard data generated during PCS operation, the abnormal occurrence of the PCS at the current moment can be judged rapidly and accurately, and therefore the efficiency and the accuracy of fault detection are improved.
In one possible example, the fault type includes an electromagnetic interference fault type; the determining the fault type of the PCS and generating a fault detection report may include the steps of: if the PCS is determined to be faulty, acquiring magnetic field information and electromagnetic field information of electronic elements in the PCS; judging whether electromagnetic interference occurs according to the magnetic field information and the electromagnetic field information of the electronic element; if the electromagnetic interference is determined to occur, determining the electromagnetic spectrum at the current moment; if the electromagnetic spectrum is larger than a preset range, determining that the fault type of the PCS is the electromagnetic interference fault type; and generating the fault detection report according to the electromagnetic interference fault type.
Illustratively, the fault types for the PCS include, but are not limited to: electromagnetic interference fault type, internal device fault type of the converter, etc.
For example, if it is determined that the current PCS has a fault according to the audio data set, magnetic field information and electromagnetic field information of electronic components inside the PCS are obtained, and whether electromagnetic interference occurs is determined. Wherein the electronic components inside the energy storage converter and the electromagnetic field may interact, thereby generating electromagnetic interference. These disturbances may lead to acoustic anomalies, especially in the high frequency range.
Further, if it is determined that electromagnetic interference occurs, determining an electromagnetic spectrum of the internal device at the current moment when the internal device works, and if the current electromagnetic spectrum is greater than a preset range, namely in a high frequency range, determining that the fault type of the current PCS is the electromagnetic interference fault type.
Further, a fault detection report is generated based on the determined fault type.
Further, a fault detection report is sent to the terminal device. After determining that the PCS has a fault, the energy storage system determines a fault type and a generated fault detection report according to the working condition of the internal device of the present PCS, so as to facilitate a inspector to quickly locate a cause of the fault in a short time or quickly remove the fault according to the fault detection report. For the problem of abnormal sound of the energy storage converter, the method is suggested to timely contact related professional technicians for overhauling and maintaining, so that the safety and the normal operation of equipment are ensured.
It can be seen that, in this example, when the energy storage system determines that the PCS has a fault and the fault type is an electromagnetic interference fault type, then a fault detection report is generated according to a relevant fault removal method that is feasible for the electromagnetic interference fault type, and the fault detection report is sent to the terminal device. Therefore, the accuracy of fault detection can be facilitated, the efficiency of PCS fault removal can be improved, and the user can maintain the fault detection report more conveniently, so that the energy storage system can operate normally.
In one possible example, the fault type includes a converter internal device fault type; the determining the fault type of the PCS and generating a fault detection report may include the steps of: if the PCS is determined to be faulty, acquiring operation information of electronic elements in the PCS, wherein the electronic elements comprise at least one; judging whether a target electronic element operation fault occurs according to the operation information, wherein the target electronic element is one or more of the electronic elements; if the operation fault of the target electronic element is determined to exist, determining that the fault type of the PCS is the fault type of an internal device of the converter; determining the position information of the target electronic element, and generating maintenance suggestions according to the position information; and combining the fault type and the maintenance suggestion to obtain the fault detection report.
For example, if it is currently determined that the PCS is malfunctioning, the energy storage system obtains operation information of electronic components of the PCS, where the operation information includes operation state information of each electronic component currently, connection information between each electronic component, and so on. During actual operation of the PCS, internal electronic components may be present, such as: switches, relays, connectors, etc., may fail or fail during operation, resulting in an abnormal sound.
Further, whether the components normally operate and the connection relation is normal is judged according to the operation information of the electronic components. And if the abnormal electronic component is determined to exist, determining that the target electronic component has operation faults, and determining that the fault type of the PCS is the fault type of the internal device of the converter.
Further, location information of the target electronic component is determined, and a repair suggestion is generated.
Further, the energy storage system transmits the fault type of the PCS and the repair advice to the terminal equipment in the form of a fault detection report.
It should be noted that, during the actual operation of the energy storage system, the possible fault types of the PCS and the reasons for the fault types are various, and only two fault types and fault cause investigation modes are taken as examples in the scheme of the application.
In this example, when determining that the PCS has a fault and determining that the fault type is the fault type of the internal device of the converter according to the operation information of the electronic component in the PCS, the operation information of the electronic component is used to further determine the failed target electronic component, and after locating the position of the target electronic component, a maintenance suggestion is generated, and then the maintenance suggestion and the fault type are sent to the terminal device in the form of a fault detection report. Therefore, the accuracy of fault detection can be facilitated, the efficiency of PCS fault removal can be improved, and the user can maintain the fault detection report more conveniently, so that the energy storage system can operate normally.
Referring to fig. 3, fig. 3 is a schematic structural diagram of an electronic device provided in an embodiment of the present application, where, as shown in fig. 3, the electronic device includes a processor, a memory, a communication interface, and one or more programs, where the one or more programs are stored in the memory and are configured to be executed by the processor, and the electronic device is applied to an energy storage system, where the energy storage system includes a PCS, and the PCS includes an audio data acquisition device; the program includes instructions for performing the steps of:
acquiring an audio data set of the PCS in real-time operation, wherein the audio data set comprises operation audio data generated by the PCS in operation and environment audio data of an environment where the PCS is located;
performing data preprocessing on the audio data set to obtain a first audio segment data set corresponding to the running audio data and a second audio segment data set corresponding to the environment audio data, wherein the data preprocessing comprises at least one of the following steps: performing mute section audio deleting processing on the operation audio data and/or the environment audio data, and performing cutting-off processing or filling processing on the operation audio data and/or the environment audio data to obtain audio section data with the same length;
Extracting features of the second audio segment data set to obtain first feature information corresponding to the environmental audio data;
acquiring a historical audio data set of at least one unit time period from the audio data acquisition device, wherein the unit time period is a time period in a normal running state after the PCS finishes one-time maintenance;
classifying the historical audio data set to respectively obtain operation audio data and environment audio data corresponding to each unit period;
performing data preprocessing on the operation audio data and the environment audio data corresponding to each unit time period to respectively obtain a third audio segment data set and a fourth audio segment data set;
performing feature extraction according to the fourth audio segment data set to obtain second feature information corresponding to the environmental audio data corresponding to each unit time period;
carrying out noise reduction processing on the third audio segment data set according to the second characteristic information to obtain a standard audio segment data set corresponding to each unit time period;
the noise reduction processing is carried out on the first audio segment data set according to the first characteristic information, so that an audio segment data set to be detected is obtained;
Judging whether the PCS has faults or not according to the audio segment data set to be detected and the standard audio segment data set corresponding to each unit time period;
if the PCS fails, determining the failure type of the PCS and generating a failure detection report;
and sending the fault detection report to terminal equipment.
It can be seen that, in the method for detecting the PCS fault of the energy storage converter described in the embodiment of the present application, an audio data set during the real-time operation of the PCS is obtained; performing data preprocessing on the audio data set to obtain a first audio segment data set corresponding to the operation audio data and a second audio segment data set corresponding to the environment audio data; obtaining first characteristic information through characteristic extraction; carrying out noise reduction treatment on the first audio segment data set according to the first characteristic information to obtain an audio segment data set to be detected; judging whether the PCS has faults or not according to the audio segment data set to be detected and the standard audio segment data set; if the PCS fails, determining the failure type of the PCS and generating a failure detection report; and sending a fault detection report to the terminal equipment. Therefore, whether the PCS is in fault or not is judged through noise reduction processing and data analysis of the audio data, and a fault detection report is correspondingly generated, so that the normal operation and the maintenance timeliness of the PCS are facilitated.
In one possible example, before the feature extraction is performed on the second audio segment data set to obtain the first feature information corresponding to the environmental audio data, the program includes instructions for performing the following steps:
determining a target unit period corresponding to the time of acquiring the audio data set;
acquiring the second characteristic information corresponding to the target unit time period;
and carrying out sound gain processing on the second audio segment data set according to the second characteristic information and a preset gain coefficient, wherein the sound gain processing is used for carrying out sound amplification processing on each segment of the audio segment in the second audio segment data set.
In one possible example, the performing the noise reduction processing on the first audio segment data set according to the first feature information includes:
performing spectrum analysis on each section of the audio frequency section in the first audio frequency section data set, and determining noise information and frequency characteristic information in the first audio frequency section data set;
and according to the first characteristic information, the noise information and the frequency characteristic information, carrying out noise reduction processing on each audio segment in the first audio segment data set, and extracting each detection audio to obtain the audio data set to be detected, wherein the noise reduction processing is used for removing the environmental noise frequency band in the first audio segment data set.
In one possible example, the determining whether the PCS is faulty according to the audio segment data set to be detected and the standard audio segment data set includes instructions for performing the following steps:
acquiring target standard audio segment data corresponding to the target unit time period from the standard audio segment data set;
taking the target standard audio segment data and the audio segment data set to be detected as input data of a judgment model to obtain an output result, wherein the judgment model is used for detecting similarity between audio data, and the output result is used for representing the similarity between the input data;
and judging whether the PCS has faults or not according to the relation between the output result and a preset threshold value.
In one possible example, the determining whether the PCS is faulty according to the relationship between the output result and a preset threshold value includes instructions for performing the following steps:
if the output result is greater than or equal to the preset threshold value, determining that the PCS fails;
and if the output result is smaller than the preset threshold value, determining that the PCS has no fault.
In one possible example, the fault type includes an electromagnetic interference fault type;
the above procedure includes instructions for performing the steps of:
if the PCS is determined to be faulty, acquiring magnetic field information and electromagnetic field information of electronic elements in the PCS;
judging whether electromagnetic interference occurs according to the magnetic field information and the electromagnetic field information of the electronic element;
if the electromagnetic interference is determined to occur, determining the electromagnetic spectrum at the current moment;
if the electromagnetic spectrum is larger than a preset range, determining that the fault type of the PCS is the electromagnetic interference fault type;
and generating the fault detection report according to the electromagnetic interference fault type.
In one possible example, the fault type includes a converter internal device fault type;
the above procedure includes instructions for performing the steps of:
if the PCS is determined to be faulty, acquiring operation information of electronic elements in the PCS, wherein the electronic elements comprise at least one;
Judging whether a target electronic element operation fault occurs according to the operation information, wherein the target electronic element is one or more of the electronic elements;
if the operation fault of the target electronic element is determined to exist, determining that the fault type of the PCS is the fault type of an internal device of the converter;
determining the position information of the target electronic element, and generating maintenance suggestions according to the position information;
and combining the fault type and the maintenance suggestion to obtain the fault detection report.
The foregoing description of the embodiments of the present application has been presented primarily in terms of a method-side implementation. It will be appreciated that the electronic device, in order to achieve the above-described functions, includes corresponding hardware structures and/or software modules that perform the respective functions. Those of skill in the art will readily appreciate that the elements and algorithm steps described in connection with the embodiments disclosed herein may be embodied as hardware or a combination of hardware and computer software. Whether a function is implemented as hardware or computer software driven hardware depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
The embodiment of the application may divide the functional units of the electronic device according to the above method example, for example, each functional unit may be divided corresponding to each function, or two or more functions may be integrated in one processing unit. The integrated units may be implemented in hardware or in software functional units. It should be noted that, in the embodiment of the present application, the division of the units is schematic, which is merely a logic function division, and other division manners may be implemented in actual practice.
In the case of dividing each functional module by adopting corresponding each function, fig. 4 shows a schematic structural diagram of a functional unit of an energy storage converter PCS fault detection device provided in an embodiment of the present application, as shown in fig. 4, the energy storage converter PCS fault detection device 400 is applied to an electronic device, where the energy storage converter PCS fault detection device 400 may include an obtaining unit 401, a processing unit 402, a judging unit 403, a determining unit 404 and a sending unit 405,
the acquiring unit 401 is configured to acquire an audio data set during real-time running of the PCS, where the audio data set includes running audio data generated during running of the PCS and environmental audio data of an environment where the PCS is located;
The processing unit 402 is configured to perform data preprocessing on the audio data set to obtain a first audio segment data set corresponding to the running audio data and a second audio segment data set corresponding to the environmental audio data, where the data preprocessing includes at least one of: performing mute section audio deleting processing on the operation audio data and/or the environment audio data, and performing cutting-off processing or filling processing on the operation audio data and/or the environment audio data to obtain audio section data with the same length;
the processing unit 402 is further configured to perform feature extraction on the second audio segment data set to obtain first feature information corresponding to the environmental audio data;
the processing unit 402 is further configured to perform the noise reduction processing on the first audio segment data set according to the first feature information to obtain an audio segment data set to be detected;
the processing unit 402 is further configured to obtain an audio data set during real-time running of the PCS, where the audio data set includes running audio data generated during running of the PCS and environmental audio data of an environment where the PCS is located;
The processing unit 402 is further configured to perform data preprocessing on the audio data set to obtain a first audio segment data set corresponding to the running audio data and a second audio segment data set corresponding to the environmental audio data, where the data preprocessing includes at least one of: performing mute section audio deleting processing on the operation audio data and/or the environment audio data, and performing cutting-off processing or filling processing on the operation audio data and/or the environment audio data to obtain audio section data with the same length;
the processing unit is further used for extracting the characteristics of the second audio segment data set to obtain first characteristic information corresponding to the environmental audio data;
the processing unit 402 is further configured to obtain a historical audio data set of at least one unit period from the audio data acquisition device, where the unit period is a period of time in a normal running state after the PCS completes one-time overhaul;
the processing unit is further used for classifying the historical audio data set to respectively obtain operation audio data and environment audio data corresponding to each unit time period;
The processing unit 402 is further configured to perform the data preprocessing on the operation audio data and the environmental audio data corresponding to each unit period, so as to obtain a third audio segment data set and a fourth audio segment data set respectively;
the processing unit 402 is further configured to perform feature extraction according to the fourth audio segment data set, so as to obtain second feature information corresponding to the environmental audio data corresponding to each unit period;
the processing unit 402 is further configured to perform noise reduction processing on the third audio segment data set according to the second feature information, to obtain a standard audio segment data set corresponding to each unit period;
the processing unit 402 is further configured to perform the noise reduction processing on the first audio segment data set according to the first feature information to obtain an audio segment data set to be detected;
the judging unit 403 is configured to judge whether the PCS has a fault according to the audio segment data set to be detected and the standard audio segment data set corresponding to each unit period;
the determining unit 404 is configured to determine a fault type of the PCS and generate a fault detection report if the PCS fails;
The sending unit 405 is configured to send the fault detection report to a terminal device.
As can be seen, in the energy storage converter PCS fault detection device provided in the embodiment of the present application, an audio data set during real-time operation of the PCS is obtained by using an obtaining unit; the processing unit performs data preprocessing on the audio data set to obtain a first audio segment data set corresponding to the operation audio data and a second audio segment data set corresponding to the environment audio data; extracting the characteristics of the processing unit to obtain first characteristic information; the processing unit performs noise reduction processing on the first audio segment data set according to the first characteristic information to obtain an audio segment data set to be detected; the judging unit judges whether the PCS has faults according to the audio segment data set to be detected and the standard audio segment data set; if the PCS fails, determining the failure type of the PCS and generating a failure detection report by the determining unit; the transmitting unit transmits a failure detection report to the terminal device. Therefore, whether the PCS is in fault or not is judged through noise reduction processing and data analysis of the audio data, and a fault detection report is correspondingly generated, so that the normal operation and the maintenance timeliness of the PCS are facilitated.
It should be noted that, all relevant contents of each step related to the above method embodiment may be cited to the functional description of the corresponding functional module, which is not described herein.
The electronic device provided in this embodiment is configured to execute the above method for detecting PCS fault of an energy storage converter, so that the same effect as that of the implementation method can be achieved.
In case an integrated unit is employed, the electronic device may comprise a processing module, a storage module and a communication module. The processing module may be configured to control and manage an action of the electronic device, and may be configured to support the electronic device to perform the steps performed by the acquiring unit 401, the processing unit 402, the judging unit 403, the determining unit 404, and the transmitting unit 405. The memory module may be used to support the electronic device to execute stored program code, data, etc. And the communication module can be used for supporting the communication between the electronic device and other devices.
Wherein the processing module may be a processor or a controller. Which may implement or perform the various exemplary logic blocks, modules, and circuits described in connection with this disclosure. A processor may also be a combination that performs computing functions, e.g., including one or more microprocessors, digital signal processing (digital signal processing, DSP) and microprocessor combinations, and the like. The memory module may be a memory. The communication module can be a radio frequency circuit, a Bluetooth chip, a Wi-Fi chip and other equipment which interact with other electronic equipment.
The embodiment of the application also provides a computer storage medium, where the computer storage medium stores a computer program for electronic data exchange, where the computer program causes a computer to execute part or all of the steps of any one of the methods described in the embodiments of the method, where the computer includes an electronic device.
Embodiments of the present application also provide a computer program product comprising a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any one of the methods described in the method embodiments above. The computer program product may be a software installation package, said computer comprising an electronic device.
It should be noted that, for simplicity of description, the foregoing method embodiments are all expressed as a series of action combinations, but it should be understood by those skilled in the art that the present application is not limited by the order of actions described, as some steps may be performed in other order or simultaneously in accordance with the present application. Further, those skilled in the art will also appreciate that the embodiments described in the specification are all preferred embodiments, and that the acts and modules referred to are not necessarily required in the present application.
In the foregoing embodiments, the descriptions of the embodiments are emphasized, and for parts of one embodiment that are not described in detail, reference may be made to related descriptions of other embodiments.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, such as the above-described division of units, merely a division of logic functions, and there may be additional manners of dividing in actual implementation, such as multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, or may be in electrical or other forms.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units, may be located in one place, or may be distributed over a plurality of 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.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit. The integrated units may be implemented in hardware or in software functional units.
The integrated units described above, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable memory. Based on such understanding, the technical solution of the present application may be embodied in essence or a part contributing to the prior art or all or part of the technical solution in the form of a software product stored in a memory, including several instructions for causing a computer device (which may be a personal computer, a server or a network device, etc.) to perform all or part of the steps of the above-mentioned method of the various embodiments of the present application. And the aforementioned memory includes: a U-disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a removable hard disk, a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Those of ordinary skill in the art will appreciate that all or a portion of the steps in the various methods of the above embodiments may be implemented by a program that instructs associated hardware, and the program may be stored in a computer readable memory, which may include: flash disk, read-Only Memory (ROM), random access Memory (Random Access Memory, RAM), magnetic disk or optical disk.
The foregoing has outlined rather broadly the more detailed description of embodiments of the present application, wherein specific examples are provided herein to illustrate the principles and embodiments of the present application, the above examples being provided solely to assist in the understanding of the methods of the present application and the core ideas thereof; meanwhile, as those skilled in the art will have modifications in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Claims (10)
1. The PCS fault detection method for the energy storage converter is characterized by being applied to an energy storage system, wherein the energy storage system comprises a PCS, and the PCS comprises an audio data acquisition device;
the method comprises the following steps:
acquiring an audio data set of the PCS in real-time operation, wherein the audio data set comprises operation audio data generated by the PCS in operation and environment audio data of an environment where the PCS is located;
Performing data preprocessing on the audio data set to obtain a first audio segment data set corresponding to the running audio data and a second audio segment data set corresponding to the environment audio data, wherein the data preprocessing comprises at least one of the following steps: performing mute section audio deleting processing on the operation audio data and/or the environment audio data, and performing cutting-off processing or filling processing on the operation audio data and/or the environment audio data to obtain audio section data with the same length;
extracting features of the second audio segment data set to obtain first feature information corresponding to the environmental audio data;
acquiring a historical audio data set of at least one unit time period from the audio data acquisition device, wherein the unit time period is a time period in a normal running state after the PCS finishes one-time maintenance;
classifying the historical audio data set to respectively obtain operation audio data and environment audio data corresponding to each unit period;
performing data preprocessing on the operation audio data and the environment audio data corresponding to each unit time period to respectively obtain a third audio segment data set and a fourth audio segment data set;
Performing feature extraction according to the fourth audio segment data set to obtain second feature information corresponding to the environmental audio data corresponding to each unit time period;
carrying out noise reduction processing on the third audio segment data set according to the second characteristic information to obtain a standard audio segment data set corresponding to each unit time period;
the noise reduction processing is carried out on the first audio segment data set according to the first characteristic information, so that an audio segment data set to be detected is obtained;
judging whether the PCS has faults or not according to the audio segment data set to be detected and the standard audio segment data set corresponding to each unit time period;
if the PCS fails, determining the failure type of the PCS and generating a failure detection report;
and sending the fault detection report to terminal equipment.
2. The method of claim 1, wherein before the feature extraction is performed on the second audio segment data set to obtain the first feature information corresponding to the environmental audio data, the method further comprises:
determining a target unit period corresponding to the time of acquiring the audio data set;
acquiring the second characteristic information corresponding to the target unit time period;
And carrying out sound gain processing on the second audio segment data set according to the second characteristic information and a preset gain coefficient, wherein the sound gain processing is used for carrying out sound amplification processing on each segment of the audio segment in the second audio segment data set.
3. The method of claim 2, wherein said denoising said first set of audio segment data according to said first characteristic information comprises:
performing spectrum analysis on at least one audio segment in the first audio segment data set, and determining noise information and frequency characteristic information in the first audio segment data set;
and according to the first characteristic information, the noise information and the frequency characteristic information, carrying out noise reduction processing on each audio segment in the first audio segment data set, and extracting each detection audio to obtain the audio data set to be detected, wherein the noise reduction processing is used for removing the environmental noise frequency band in the first audio segment data set.
4. The method of claim 3, wherein the determining whether the PCS is faulty based on the set of audio segment data to be detected and the set of standard audio segment data corresponding to each of the unit periods comprises:
Acquiring target standard audio segment data corresponding to the target unit time period from the standard audio segment data set;
taking the target standard audio segment data and the audio segment data set to be detected as input data of a judgment model to obtain an output result, wherein the judgment model is used for detecting similarity between audio data, and the output result is used for representing the similarity between the input data;
and judging whether the PCS has faults or not according to the relation between the output result and a preset threshold value.
5. The method of claim 4, wherein the determining whether the PCS is faulty based on the relationship between the output result and a preset threshold value comprises:
if the output result is greater than or equal to the preset threshold value, determining that the PCS fails;
and if the output result is smaller than the preset threshold value, determining that the PCS has no fault.
6. The method of claim 1, wherein the fault type comprises an electromagnetic interference fault type;
the determining the fault type of the PCS and generating a fault detection report comprises the following steps:
if the PCS is determined to be faulty, acquiring magnetic field information and electromagnetic field information of electronic elements inside the PCS;
Judging whether electromagnetic interference occurs according to the magnetic field information and the electromagnetic field information of the electronic element;
if the electromagnetic interference is determined to occur, determining the electromagnetic spectrum at the current moment;
if the electromagnetic spectrum is larger than a preset range, determining that the fault type of the PCS is the electromagnetic interference fault type;
and generating the fault detection report according to the electromagnetic interference fault type.
7. The method of claim 1, wherein the fault type comprises a converter internal device fault type;
the determining the fault type of the PCS and generating a fault detection report comprises the following steps:
if the PCS is determined to be faulty, acquiring operation information of electronic elements inside the PCS, wherein the electronic elements comprise at least one;
judging whether a target electronic element operation fault occurs according to the operation information, wherein the target electronic element is one or more of the electronic elements;
if the operation fault of the target electronic element is determined to exist, determining that the fault type of the PCS is the fault type of an internal device of the converter;
determining the position information of the target electronic element, and generating maintenance suggestions according to the position information;
And combining the fault type and the maintenance suggestion to obtain the fault detection report.
8. The PCS fault detection device of the energy storage converter is characterized by being applied to an energy storage system, wherein the energy storage system comprises a PCS, and the PCS comprises an audio data acquisition device;
the device comprises: an acquisition unit, a processing unit, a judgment unit, a determination unit and a transmission unit, wherein,
the acquiring unit is configured to acquire an audio data set during real-time running of the PCS, where the audio data set includes running audio data generated during running of the PCS and environmental audio data of an environment where the PCS is located;
the processing unit is configured to perform data preprocessing on the audio data set to obtain a first audio segment data set corresponding to the running audio data and a second audio segment data set corresponding to the environmental audio data, where the data preprocessing includes at least one of: performing mute section audio deleting processing on the operation audio data and/or the environment audio data, and performing cutting-off processing or filling processing on the operation audio data and/or the environment audio data to obtain audio section data with the same length;
The processing unit is further used for extracting the characteristics of the second audio segment data set to obtain first characteristic information corresponding to the environmental audio data;
the processing unit is further configured to perform the noise reduction processing on the first audio segment data set according to the first feature information to obtain an audio segment data set to be detected;
the processing unit is further configured to obtain an audio data set during real-time running of the PCS, where the audio data set includes running audio data generated during running of the PCS and environmental audio data of an environment where the PCS is located;
the processing unit is further configured to perform data preprocessing on the audio data set to obtain a first audio segment data set corresponding to the running audio data and a second audio segment data set corresponding to the environmental audio data, where the data preprocessing includes at least one of: performing mute section audio deleting processing on the operation audio data and/or the environment audio data, and performing cutting-off processing or filling processing on the operation audio data and/or the environment audio data to obtain audio section data with the same length;
The processing unit is further used for extracting the characteristics of the second audio segment data set to obtain first characteristic information corresponding to the environmental audio data;
the processing unit is further configured to obtain a historical audio data set of at least one unit period from the audio data acquisition device, where the unit period is a period of time in a normal running state after the PCS completes one-time overhaul;
the processing unit is further used for classifying the historical audio data set to respectively obtain operation audio data and environment audio data corresponding to each unit time period;
the processing unit is further used for carrying out data preprocessing on the operation audio data and the environment audio data corresponding to each unit time period to respectively obtain a third audio segment data set and a fourth audio segment data set;
the processing unit is further used for carrying out feature extraction according to the fourth audio segment data set to obtain second feature information corresponding to the environmental audio data corresponding to each unit time period;
the processing unit is further configured to perform noise reduction processing on the third audio segment data set according to the second feature information, so as to obtain a standard audio segment data set corresponding to each unit time period;
The processing unit is further configured to perform the noise reduction processing on the first audio segment data set according to the first feature information to obtain an audio segment data set to be detected;
the judging unit is configured to judge whether the PCS has a fault according to the audio segment data set to be detected and the standard audio segment data set corresponding to each unit period;
the determining unit is used for determining the fault type of the PCS and generating a fault detection report if the PCS fails;
the sending unit is configured to send the fault detection report to a terminal device.
9. An electronic device comprising a processor, a memory, a communication interface, and one or more programs stored in the memory and configured to be executed by the processor, the programs comprising instructions for performing the steps in the method of any of claims 1-7.
10. A computer-readable storage medium, characterized in that a computer program for electronic data exchange is stored, wherein the computer program causes a computer to perform the method according to any one of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311707951.8A CN117409815A (en) | 2023-12-13 | 2023-12-13 | PCS fault detection method and related device for energy storage converter |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311707951.8A CN117409815A (en) | 2023-12-13 | 2023-12-13 | PCS fault detection method and related device for energy storage converter |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117409815A true CN117409815A (en) | 2024-01-16 |
Family
ID=89500276
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311707951.8A Pending CN117409815A (en) | 2023-12-13 | 2023-12-13 | PCS fault detection method and related device for energy storage converter |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117409815A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108469109A (en) * | 2018-03-01 | 2018-08-31 | 广东美的制冷设备有限公司 | Detection method, device, system, air conditioner and the storage medium of unit exception |
| CN113670434A (en) * | 2021-06-21 | 2021-11-19 | 深圳供电局有限公司 | Transformer substation equipment sound abnormality identification method and device and computer equipment |
| CN115313820A (en) * | 2022-08-19 | 2022-11-08 | 江苏天合储能有限公司 | Carrier synchronization control method and device for parallel energy storage converter |
| CN115420977A (en) * | 2022-08-26 | 2022-12-02 | 正泰集团研发中心(上海)有限公司 | Electric appliance fault detection method, training method, computer equipment and storage medium |
| CN115875797A (en) * | 2021-09-26 | 2023-03-31 | 佛山市顺德区美的电子科技有限公司 | Fault detection method of air supply equipment and related equipment |
| CN116345682A (en) * | 2023-03-06 | 2023-06-27 | 远东电池江苏有限公司 | Energy storage system and CAN bus abnormal fault detection and diagnosis method thereof |
-
2023
- 2023-12-13 CN CN202311707951.8A patent/CN117409815A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108469109A (en) * | 2018-03-01 | 2018-08-31 | 广东美的制冷设备有限公司 | Detection method, device, system, air conditioner and the storage medium of unit exception |
| CN113670434A (en) * | 2021-06-21 | 2021-11-19 | 深圳供电局有限公司 | Transformer substation equipment sound abnormality identification method and device and computer equipment |
| CN115875797A (en) * | 2021-09-26 | 2023-03-31 | 佛山市顺德区美的电子科技有限公司 | Fault detection method of air supply equipment and related equipment |
| CN115313820A (en) * | 2022-08-19 | 2022-11-08 | 江苏天合储能有限公司 | Carrier synchronization control method and device for parallel energy storage converter |
| CN115420977A (en) * | 2022-08-26 | 2022-12-02 | 正泰集团研发中心(上海)有限公司 | Electric appliance fault detection method, training method, computer equipment and storage medium |
| CN116345682A (en) * | 2023-03-06 | 2023-06-27 | 远东电池江苏有限公司 | Energy storage system and CAN bus abnormal fault detection and diagnosis method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101150788B (en) | Self modulation radio broadcast terminal system and its monitoring processor | |
| CN109616140B (en) | Abnormal sound analysis system | |
| WO2016027996A1 (en) | Power equipment sound diagnosis system | |
| CN111918196B (en) | Method, device and equipment for diagnosing recording abnormity of audio collector and storage medium | |
| WO2015101426A1 (en) | Devices and methods for arc fault detection | |
| EP4085376A1 (en) | Method and apparatus for inspecting wind turbine blade, and device and storage medium thereof | |
| CN102547526B (en) | Real-time monitoring method and system of microphone working state | |
| WO2019103251A1 (en) | System and method for automatically detecting ultrasonic waves from power distribution facility | |
| CN113595251B (en) | Automatic monitoring and early warning system and method for substation power equipment | |
| CN112067323B (en) | Automatic inspection system | |
| CN115687969A (en) | Low-voltage transformer fault diagnosis method based on sound characteristic analysis | |
| CN110794032A (en) | Bridge expansion joint monitoring devices | |
| KR102009993B1 (en) | Intelligent fire prevention diagnosis system and method | |
| CN106956985A (en) | A kind of elevator early warning voice pacifies system and its control method | |
| KR20220056782A (en) | System and method for monitoring a machine | |
| CN117409815A (en) | PCS fault detection method and related device for energy storage converter | |
| CN114252906A (en) | Sound event detection method and device, computer equipment and storage medium | |
| CN112666430A (en) | Intelligent transformer voiceprint fault detection method and system | |
| CN110017894B (en) | Method and device for filtering random noise in vibration and sound detection of transformer in running state | |
| KR101641269B1 (en) | Partial discharge diagnostic system using emf sensor and acoustic sensor | |
| CN107548007B (en) | Detection method and device of audio signal acquisition equipment | |
| US20230162755A1 (en) | Object left-behind detection method, object left-behind detection apparatus, and program | |
| KR101612025B1 (en) | smart diagnose system using car noise | |
| CN113777434A (en) | Fault monitoring method and device and power supply and distribution system | |
| CN112866877A (en) | Speaker control method, speaker control device, electronic apparatus, and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |