Intelligent power plant fault diagnosis method, device and equipment and storage medium

Abstract

The invention relates to the technical field of fault diagnosis, in particular to an intelligent power plant fault diagnosis method and device, equipment and a storage medium, and the method comprises the steps: obtaining message information reported by power plant equipment in response to a fault diagnosis instruction; determining candidate fault equipment according to the message information; driving a fault information acquisition device to acquire original electrical data, original image data and original sound wave data of the candidate fault equipment; respectively inputting the original electrical data, the original image data and the original sound wave data into a fault diagnosis model corresponding to each data category for fault analysis; and generating a fault diagnosis text according to the fault analysis process so as to provide fault diagnosis auxiliary information, determining equipment suspected to have a fault based on message information reported by the equipment, performing fault diagnosis analysis on the equipment from three dimensions of electricity, images and sound waves, and providing the fault diagnosis analysis process for a user. And the information serves as auxiliary information of subsequent maintenance.

Description

Technical Field

[0001] The present invention relates to the field of fault diagnosis technology, and in particular to a smart power plant fault diagnosis method, device, equipment and storage medium. Background Art

[0002] Equipment status detection and fault maintenance are important foundations for ensuring the normal operation of power systems. However, due to the diversity of the environments and defect types of power plant equipment, it is impossible to fully and accurately detect the operating status of equipment or diagnose faults when detecting the operating status of power plant equipment. Current power equipment fault diagnosis technology generally diagnoses power equipment from a certain dimension. When faced with some unrecorded fault types, it can only report errors, affecting equipment maintenance efficiency. Summary of the Invention

[0003] The main purpose of the present invention is to provide a smart power plant fault diagnosis method, device, equipment and storage medium, aiming to solve the technical problems of low fault detection accuracy and insufficient comprehensiveness of power equipment in the existing technology.

[0004] To achieve the above objectives, the present invention provides a smart power plant fault diagnosis method, which includes the following steps:

[0005] In response to the fault diagnosis instruction, obtain message information reported by each power plant device, wherein the message information represents a character string corresponding to the power plant device information, the current time, and the current operating status of the device;

[0006] Determine a candidate fault device according to the message information;

[0007] Driving the fault information collection device to collect original electrical data, original image data, and original sound wave data of the candidate fault device;

[0008] Inputting the raw electrical data, raw image data, and raw acoustic wave data into the fault diagnosis model corresponding to each data category to perform fault analysis, and outputting a fault analysis process;

[0009] A fault diagnosis text is generated according to the fault analysis process to provide auxiliary information for fault diagnosis.

[0010] Optionally, inputting the original electrical data, original image data, and original acoustic wave data into fault diagnosis models corresponding to respective data categories for fault analysis includes:

[0011] performing data preprocessing on the original electrical data, image data, and acoustic wave data respectively;

[0012] Compare the pre-processed raw electrical data with the electrical data in the historical operation cycle, and determine the abnormal power data and the source of the abnormal power data based on the comparison results;

[0013] and / or

[0014] The pre-processed image data is subjected to long-term and short-term neural network to identify abnormal image areas and obtain abnormal image areas;

[0015] and / or

[0016] The time domain features and frequency domain features of the preprocessed sound wave data are extracted, and the time domain features and frequency domain features are used to perform equipment fault analysis through a trained 1D CNN model to obtain abnormal sound wave data.

[0017] Optionally, the performing data preprocessing on the original electrical data, original image data, and original acoustic wave data respectively includes:

[0018] Performing time alignment on the raw electrical data, and performing time series normalization processing on the aligned raw electrical data;

[0019] Performing visual enhancement on the image data, and performing grayscale balancing processing on the visually enhanced image data;

[0020] Acquire historical environmental noise, and denoise the sound wave data based on the historical environmental noise.

[0021] Optionally, determining a candidate faulty device according to the message information includes:

[0022] Decoding the message information to obtain a message data stream;

[0023] Extracting a fault code from the message data stream, wherein the fault code is a label that matches a fault label in a fault label database;

[0024] Extracting a header identifier in the message data stream based on the fault code, where the header identifier is used to represent a unique identification code of the device;

[0025] A candidate faulty device is determined according to the header identifier.

[0026] Optionally, generating a fault diagnosis text according to the fault analysis process to provide auxiliary information for fault diagnosis includes:

[0027] Based on abnormal power data, abnormal power data sources, abnormal image areas and abnormal sound wave data, data fusion is performed through a data fusion model to obtain fused abnormal data features;

[0028] Performing a preliminary fault analysis on the fused abnormal data features through historical fault cases to determine a preliminary fault analysis result;

[0029] Querying the diagnostic plan and verification plan corresponding to the preliminary fault analysis result;

[0030] The diagnosis scheme, the verification scheme, and the preliminary fault analysis result are filled into a preset diagnosis text template to obtain a fault diagnosis text to provide auxiliary information for fault diagnosis.

[0031] Optionally, the data fusion is performed based on the abnormal power data, the abnormal power data source, the abnormal image area and the abnormal sound wave data through a data fusion model to obtain fused abnormal data features, including:

[0032] Extract abnormal power data, abnormal power data sources, abnormal image areas, and abnormal acoustic wave data modal feature representations;

[0033] Determine the support between each data, and calculate the support mean and support variance based on the support;

[0034] Based on the support matrix and the support variance, weighting is performed on the target operation data to be fused through a support weighting model to obtain the weight of each data;

[0035] Data fusion is performed according to the weights of the data through a data fusion model to obtain fused data.

[0036] In addition, to achieve the above-mentioned purpose, the present invention further proposes a smart power plant fault diagnosis device, which includes:

[0037] An acquisition module, configured to obtain, in response to a fault diagnosis instruction, message information reported by each power plant device, wherein the message information represents a character string corresponding to power plant device information, current time, and current operating status of the device;

[0038] A determination module, configured to determine a candidate faulty device based on the message information;

[0039] An acquisition module is used to drive a fault information acquisition device to acquire original electrical data, original image data, and original acoustic wave data of the candidate fault device;

[0040] An analysis module, configured to input the raw electrical data, raw image data, and raw acoustic wave data into a fault diagnosis model corresponding to each data category to perform fault analysis, and output a fault analysis process;

[0041] The diagnosis module is used to generate a fault diagnosis text according to the fault analysis process to provide auxiliary information for fault diagnosis.

[0042] In addition, to achieve the above-mentioned purpose, the present invention also proposes a smart power plant fault diagnosis device, which includes: a memory, a processor, and a smart power plant fault diagnosis program stored on the memory and runnable on the processor, and the smart power plant fault diagnosis program is configured to implement the steps of the smart power plant fault diagnosis method described above.

[0043] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a smart power plant fault diagnosis program is stored. When the smart power plant fault diagnosis program is executed by a processor, the steps of the smart power plant fault diagnosis method described above are implemented.

[0044] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the smart power plant fault diagnosis method as described above.

[0045] The present invention obtains the message information reported by each power plant equipment in response to the fault diagnosis instruction; determines the candidate fault equipment according to the message information; drives the fault information acquisition device to collect the original electrical data, original image data and original sound wave data of the candidate fault equipment; inputs the original electrical data, original image data and original sound wave data into the fault diagnosis model corresponding to each data category for fault analysis; generates a fault diagnosis text according to the fault analysis process to provide auxiliary information for fault diagnosis, determines the equipment suspected of having a fault based on the message information reported by the equipment, and performs fault diagnosis and analysis on the equipment from three dimensions of electrical, image and sound wave, and provides the fault diagnosis and analysis process to the user as auxiliary information for subsequent maintenance. The fault diagnosis analysis in multiple dimensions improves the fault detection accuracy and comprehensiveness, and avoids the technical problems of low fault detection accuracy and lack of comprehensiveness of power equipment in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0048] Figure 1 This is a flow chart of the first embodiment of the smart power plant fault diagnosis method of the present invention;

[0049] Figure 2 This is a flow chart of a second embodiment of the smart power plant fault diagnosis method of the present invention;

[0050] Figure 3 This is a structural block diagram of the first embodiment of the smart power plant fault diagnosis device of the present invention;

[0051] Figure 4 It is a structural diagram of a smart power plant fault diagnosis device in the hardware operating environment involved in the embodiment of the present invention.

[0052] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0054] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0055] Based on this, the embodiment of the present invention provides a smart power plant fault diagnosis method, referring to Figure 1 , Figure 1 This is a flow chart of a first embodiment of a smart power plant fault diagnosis method according to the present invention.

[0056] In this embodiment, the smart power plant fault diagnosis method includes:

[0057] Step S10: In response to the fault diagnosis instruction, the message information reported by each power plant device is obtained, where the message information represents the power plant device information, the current time, and a character string corresponding to the current operating status of the device.

[0058] Step S20: Determine candidate faulty devices according to the message information.

[0059] Step S30: driving the fault information collection device to collect original electrical data, original image data, and original sound wave data of the candidate fault device.

[0060] Step S40: inputting the original electrical data, original image data, and original acoustic wave data into the fault diagnosis model corresponding to each data category to perform fault analysis, and outputting a fault analysis process.

[0061] Step S50: Generate a fault diagnosis text according to the fault analysis process to provide fault diagnosis auxiliary information.

[0062] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of implementing the above functions, a control computer, etc. The following describes this embodiment and the following embodiments using a control computer as an example.

[0063] It should be understood that the fault diagnosis instruction refers to a periodically generated control instruction used to drive each power plant device to upload message information, wherein the message information represents the information of the power plant equipment, the current time and the character string corresponding to the current operating status of the equipment.

[0064] Furthermore, determining a candidate faulty device according to the message information includes:

[0065] Decoding the message information to obtain a message data stream;

[0066] Extracting a fault code from the message data stream, wherein the fault code is a label that matches a fault label in a fault label database;

[0067] Extracting a header identifier in the message data stream based on the fault code, where the header identifier is used to represent a unique identification code of the device;

[0068] A candidate faulty device is determined according to the header identifier.

[0069] In specific implementations, with the development of various equipment monitoring technologies, there are many technologies that can monitor equipment failures, such as CAN or easyCVR platforms, etc. However, these platforms or devices can only determine that a fault has occurred, but cannot determine the cause of the fault. In addition, these platforms or devices may be affected by a certain sensor or circuit, resulting in misjudgment of the fault and affecting the normal operation of the equipment. In this embodiment, these defective fault identification platforms can be used to locate equipment suspected of having faults, and through further fault diagnosis and analysis, the accuracy of fault diagnosis and identification within the smart power plant can be improved.

[0070] It can be understood that the original electrical data includes at least: voltage, current, power and discharge signal, etc., the original image data includes: at least one of infrared image, ultrasonic image and point cloud image, and the original sound wave data is the sound wave feedback signal emitted and received by the sound wave generator located at the connection of pipelines and equipment.

[0071] In specific implementations, a power plant may experience various faults during operation, such as pipeline leakage, pipeline blockage, poor boiler combustion performance, low electricity conversion rate, low energy storage rate, leakage, and other fault problems. Single-modal data is difficult to identify the above problems well, and the integrated fault analysis model is difficult to train, and the efficiency of processing multi-modal data is low. Therefore, this embodiment performs fault analysis by inputting the original electrical data, original image data, and original sound wave data into the fault diagnosis model corresponding to each data category, and generates the fault analysis process into a fault diagnosis text. From the fault analysis process of multi-modal data, comprehensive equipment fault diagnosis is achieved, but the training workload is relatively small.

[0072] Furthermore, the inputting of the original electrical data, original image data, and original acoustic wave data into the fault diagnosis model corresponding to each data category for fault analysis includes:

[0073] performing data preprocessing on the original electrical data, image data, and acoustic wave data respectively;

[0074] Compare the pre-processed raw electrical data with the electrical data in the historical operation cycle, and determine the abnormal power data and the source of the abnormal power data based on the comparison results;

[0075] and / or

[0076] The pre-processed image data is subjected to long-term and short-term neural network to identify abnormal image areas and obtain abnormal image areas;

[0077] and / or

[0078] The time domain features and frequency domain features of the preprocessed sound wave data are extracted, and the time domain features and frequency domain features are used to perform equipment fault analysis through a trained 1D CNN model to obtain abnormal sound wave data.

[0079] It should be noted that the process of data preprocessing of the original electrical data, image data and acoustic wave data includes but is not limited to time alignment of the original electrical data and time series normalization of the aligned original electrical data; visual enhancement of the image data and grayscale equalization of the visually enhanced image data; obtaining historical environmental noise and denoising the acoustic wave data based on the historical environmental noise, etc.

[0080] Since electrical data is generally in a stable state during normal operation and is easy to quantify, when analyzing electrical data anomalies, the pre-processed raw electrical data can be compared with the electrical data in the historical operation cycle. By calculating the difference between the two, it can be determined whether there is any anomaly in the power data of the equipment in the current cycle.

[0081] For combustion furnaces or other equipment that can be directly observed, long-term and short-term neural networks can be used to identify abnormal image areas, thereby dividing abnormal image areas in the collected image data. For areas such as pipelines and cooling chambers where vibrations exist or where a large range of designs exist, the time domain and frequency domain features of the sound wave data passing through these areas can be extracted, and equipment fault analysis can be performed using a trained 1D CNN model to determine abnormal sound wave data, thereby conducting large-scale fault diagnosis and analysis of areas such as pipelines or cooling chambers.

[0082] It should be understood that, since different devices have different monitorability levels, one or a combination of multiple of the above-mentioned modal data may be used when performing fault analysis, and this embodiment does not impose any specific limitation on this.

[0083] In a specific implementation, generating a fault diagnosis text based on the fault diagnosis process of each modal data means fusing the diagnostic results of each modal data to determine the possible fault cause of the faulty equipment in the form of text, and reducing the possibility of misjudgment of the fault by querying the diagnostic scheme and verification scheme of each possible fault cause. Different from the traditional analysis and combination of multiple single modal data, this embodiment mainly combines the fault analysis processes of each modality into a fault diagnosis text, thereby providing auxiliary information for the intelligent control of the power plant, realizing high-precision fault diagnosis, and also having better solutions for unrecorded faults.

[0084] This embodiment obtains the message information reported by each power plant equipment in response to the fault diagnosis instruction; determines the candidate fault equipment according to the message information; drives the fault information acquisition device to collect the original electrical data, original image data and original sound wave data of the candidate fault equipment; inputs the original electrical data, original image data and original sound wave data into the fault diagnosis model corresponding to each data category for fault analysis; generates a fault diagnosis text according to the fault analysis process to provide auxiliary information for fault diagnosis, determines the equipment suspected of having a fault based on the message information reported by the equipment, and performs fault diagnosis and analysis on the equipment from three dimensions: electrical, image and sound wave, and provides the fault diagnosis analysis process to the user as auxiliary information for subsequent maintenance, thereby avoiding the technical problems of low fault detection accuracy and incompleteness of power equipment in the existing technology.

[0085] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above embodiment 1 can be referred to the above introduction and will not be described in detail later. Figure 2 Step S40 includes:

[0086] Step S401: performing data fusion based on abnormal power data, abnormal power data source, abnormal image area and abnormal sound wave data through a data fusion model to obtain fused abnormal data features.

[0087] Step S402: performing a preliminary fault analysis on the fused abnormal data features through historical fault cases to determine a preliminary fault analysis result.

[0088] Step S403: Query the diagnosis plan and verification plan corresponding to the preliminary fault analysis result.

[0089] Step S404: Fill the diagnosis plan, the verification plan, and the preliminary fault analysis result into a preset diagnosis text template to obtain a fault diagnosis text to provide auxiliary information for fault diagnosis.

[0090] It should be noted that in order to unify the analysis process of each modal data, this embodiment fuses the data lines of each modal data to provide fault location with higher accuracy, and first performs preliminary fault analysis on the fused abnormal data characteristics of the area, and provides at least one possible cause of the fault based on the fault cases in the area in historical fault cases, and gives relevant case introductions.

[0091] After giving at least one possible cause of the fault, a feasible diagnosis plan and verification plan can be issued through the treatment plan stored in the database. Furthermore, after executing a certain diagnosis plan, the maintenance staff can further adjust the operating status of a certain device through the verification plan.

[0092] Furthermore, the abnormal power data, the abnormal power data source, the abnormal image area and the abnormal sound wave data are fused through a data fusion model to obtain fused abnormal data features, including:

[0093] Extract abnormal power data, abnormal power data sources, abnormal image areas, and abnormal acoustic wave data modal feature representations;

[0094] Determine the support between each data, and calculate the support mean and support variance based on the support;

[0095] Based on the support matrix and the support variance, weighting is performed on the target operation data to be fused through a support weighting model to obtain the weight of each data;

[0096] Data fusion is performed according to the weights of the data through a data fusion model to obtain fused data.

[0097] It can be understood that the modal feature representation records the characteristic parameters of the target operating data to be fused, including but not limited to data values, units, etc. Depending on the modality, it may specifically include parameters such as current value, RGB grayscale value, frequency, amplitude, etc.

[0098] Among them, the calculation formula for calculating the support between each modal feature representation is:

[0099]

[0100] Among them, r(t) is the support between modal feature representations, α is the correction coefficient corresponding to the power plant equipment type, and z i (t) and z j (t) is the modal feature representation of participation support, and n is the total number of target operation data to be fused.

[0101] This embodiment performs data fusion through a data fusion model based on abnormal power data, abnormal power data sources, abnormal image areas, and abnormal sound wave data to obtain fused abnormal data features; performs preliminary fault analysis on the abnormal data features through historical fault cases to determine preliminary fault analysis results; queries the diagnostic plan and verification plan corresponding to the preliminary fault analysis results; fills the diagnostic plan, the verification plan, and the preliminary fault analysis results into a preset diagnostic text template to obtain a fault diagnosis text to provide auxiliary information for fault diagnosis, thereby improving the credibility of fault diagnosis by fusing data from various modalities.

[0102] This application also provides a smart power plant fault diagnosis device, please refer to Figure 3 , the smart power plant fault diagnosis device includes:

[0103] The acquisition module 10 is configured to acquire message information reported by each power plant device in response to a fault diagnosis instruction, wherein the message information represents a character string corresponding to power plant device information, current time, and current operating status of the device.

[0104] The determination module 20 is configured to determine a candidate faulty device based on the message information.

[0105] The acquisition module 30 is used to drive the fault information acquisition device to acquire the original electrical data, original image data and original sound wave data of the candidate fault device.

[0106] The analysis module 40 is configured to input the original electrical data, original image data, and original acoustic wave data into the fault diagnosis model corresponding to each data category to perform fault analysis, and output a fault analysis process.

[0107] The diagnosis module 50 is used to generate a fault diagnosis text according to the fault analysis process to provide auxiliary information for fault diagnosis.

[0108] In one embodiment, the analysis module 40 is further used to perform data preprocessing on the original electrical data, image data and acoustic wave data respectively; compare the preprocessed original electrical data with the electrical data in the historical operation cycle, and determine the abnormal power data and the source of the abnormal power data based on the comparison results; and / or identify the abnormal image area of the preprocessed image data through a long-term and short-term neural network to obtain the abnormal image area; and / or extract the time domain features and frequency domain features of the preprocessed acoustic wave data, and perform equipment fault analysis on the time domain features and frequency domain features through a trained 1D CNN model to obtain abnormal acoustic wave data.

[0109] In one embodiment, the analysis module 40 is further used to time-align the original electrical data and perform time series normalization processing on the aligned original electrical data; visually enhance the image data and perform grayscale equalization processing on the visually enhanced image data; obtain historical environmental noise, and denoise the sound wave data based on the historical environmental noise.

[0110] In one embodiment, the determination module 20 is further used to decode the message information to obtain a message data stream; extract a fault code in the message data stream, where the fault code is a label that matches a fault label in a fault label database; extract a header identifier in the message data stream based on the fault code, where the header identifier is used to represent a unique identification code of a device; and determine a candidate fault device based on the header identifier.

[0111] In one embodiment, the diagnostic module 50 is further used to perform data fusion through a data fusion model based on abnormal power data, abnormal power data sources, abnormal image areas, and abnormal sound wave data to obtain fused abnormal data features; perform preliminary fault analysis on the abnormal data features through historical fault cases to determine preliminary fault analysis results; query the diagnostic plan and verification plan corresponding to the preliminary fault analysis results; fill the diagnostic plan, the verification plan, and the preliminary fault analysis results into a preset diagnostic text template to obtain a fault diagnosis text to provide fault diagnosis auxiliary information.

[0112] In one embodiment, the diagnostic module 50 is also used to extract abnormal power data, abnormal power data sources, abnormal image areas, and abnormal sound wave data modal feature representations; determine the support between each data, and calculate the support mean and support variance based on the support; weight the target operating data to be fused based on the support matrix and the support variance through a support weighting model to obtain the weight of each data; perform data fusion through a data fusion model according to the weight of each data to obtain fused data.

[0113] This embodiment obtains the message information reported by each power plant equipment in response to the fault diagnosis instruction; determines the candidate fault equipment according to the message information; drives the fault information acquisition device to collect the original electrical data, original image data and original sound wave data of the candidate fault equipment; inputs the original electrical data, original image data and original sound wave data into the fault diagnosis model corresponding to each data category for fault analysis; generates a fault diagnosis text according to the fault analysis process to provide auxiliary information for fault diagnosis, determines the equipment suspected of having a fault based on the message information reported by the equipment, and performs fault diagnosis and analysis on the equipment from three dimensions: electrical, image and sound wave, and provides the fault diagnosis analysis process to the user as auxiliary information for subsequent maintenance, thereby avoiding the technical problems of low fault detection accuracy and incompleteness of power equipment in the existing technology.

[0114] The present application provides a smart power plant fault diagnosis device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the smart power plant fault diagnosis method in the above-mentioned embodiment one.

[0115] Reference below Figure 4 , which shows a schematic diagram of the structure of a smart power plant fault diagnosis device suitable for implementing an embodiment of the present application. The smart power plant fault diagnosis device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), and in-vehicle terminals (e.g., in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers. Figure 4 The smart power plant fault diagnosis device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0116] like Figure 4As shown, the smart power plant fault diagnosis device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the smart power plant fault diagnosis device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the smart power plant fault diagnosis device to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a smart power plant fault diagnosis device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems may be implemented or have instead.

[0117] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0118] The smart power plant fault diagnosis device provided in this application utilizes the smart power plant fault diagnosis method described in the aforementioned embodiment to address the technical issues surrounding smart power plant fault diagnosis. Compared to the prior art, the beneficial effects of the smart power plant fault diagnosis device provided in this application are the same as those of the smart power plant fault diagnosis method described in the aforementioned embodiment. Other technical features of the smart power plant fault diagnosis device are the same as those disclosed in the aforementioned embodiment and are not further elaborated here.

[0119] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0120] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0121] The present application provides a computer-readable storage medium having computer-readable program instructions (i.e., computer programs) stored thereon, and the computer-readable program instructions are used to execute the smart power plant fault diagnosis method in the above-mentioned embodiment.

[0122] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0123] The above-mentioned computer-readable storage medium may be included in the smart power plant fault diagnosis device; or it may exist independently without being assembled into the smart power plant fault diagnosis device.

[0124] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the smart power plant fault diagnosis device, the smart power plant fault diagnosis device enables: smart power plant fault diagnosis.

[0125] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on the remote computer or server. In cases involving a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0126] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0127] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0128] The computer-readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned smart power plant fault diagnosis method, thereby resolving the technical issues of smart power plant fault diagnosis. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the smart power plant fault diagnosis method provided in the aforementioned embodiments, and are not further elaborated here.

[0129] The present application also provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the above-mentioned smart power plant fault diagnosis method.

[0130] The computer program product provided in this application can solve the technical problem of smart power plant fault diagnosis. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the smart power plant fault diagnosis method provided in the above embodiment, and will not be repeated here.

[0131] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A smart power plant fault diagnosis method, characterized in that: The smart power plant fault diagnosis method includes: In response to the fault diagnosis instruction, obtaining message information of each power plant device, wherein the message information represents a character string corresponding to the power plant device information, the current time, and the current operating status of the device; Determine a candidate fault device according to the message information; Driving the fault information collection device to collect original electrical data, original image data, and original sound wave data of the candidate fault device; Inputting the raw electrical data, raw image data, and raw acoustic wave data into the fault diagnosis model corresponding to each data category to perform fault analysis, and outputting a fault analysis process; A fault diagnosis text is generated according to the fault analysis process to provide auxiliary information for fault diagnosis.

2. The smart power plant fault diagnosis method according to claim 1, characterized in that: The step of inputting the original electrical data, original image data, and original acoustic wave data into the fault diagnosis model corresponding to each data category for fault analysis includes: performing data preprocessing on the original electrical data, image data, and acoustic wave data respectively; Compare the pre-processed raw electrical data with the electrical data in the historical operation cycle, and determine the abnormal power data and the source of the abnormal power data based on the comparison results; and / or The pre-processed image data is subjected to long-term and short-term neural network to identify abnormal image areas and obtain abnormal image areas; and / or The time domain features and frequency domain features of the preprocessed sound wave data are extracted, and the time domain features and frequency domain features are used to perform equipment fault analysis through a trained 1D CNN model to obtain abnormal sound wave data.

3. The smart power plant fault diagnosis method according to claim 2, characterized in that: The data preprocessing of the original electrical data, the original image data and the original acoustic wave data respectively includes: Performing time alignment on the raw electrical data, and performing time series normalization processing on the aligned raw electrical data; Performing visual enhancement on the image data, and performing grayscale balancing processing on the visually enhanced image data; Acquire historical environmental noise, and denoise the sound wave data based on the historical environmental noise.

4. The smart power plant fault diagnosis method according to claim 1, characterized in that: The determining of a candidate faulty device according to the message information includes: Decoding the message information to obtain a message data stream; Extracting a fault code from the message data stream, wherein the fault code is a label that matches a fault label in a fault label database; Extracting a header identifier in the message data stream based on the fault code, where the header identifier is used to represent a unique identification code of the device; A candidate faulty device is determined according to the header identifier.

5. The smart power plant fault diagnosis method according to claim 1, characterized in that: Generating a fault diagnosis text according to the fault analysis process to provide auxiliary information for fault diagnosis includes: Based on abnormal power data, abnormal power data sources, abnormal image areas and abnormal sound wave data, data fusion is performed through a data fusion model to obtain fused abnormal data features; Performing a preliminary fault analysis on the fused abnormal data features through historical fault cases to determine a preliminary fault analysis result; Querying the diagnostic plan and verification plan corresponding to the preliminary fault analysis result; The diagnosis scheme, the verification scheme, and the preliminary fault analysis result are filled into a preset diagnosis text template to obtain a fault diagnosis text to provide auxiliary information for fault diagnosis.

6. The smart power plant fault diagnosis method according to claim 5, characterized in that: The abnormal power data, the abnormal power data source, the abnormal image area and the abnormal sound wave data are fused through a data fusion model to obtain fused abnormal data features, including: Extract abnormal power data, abnormal power data sources, abnormal image areas, and abnormal acoustic wave data modal feature representations; Determine the support between each data, and calculate the support mean and support variance based on the support; Based on the support matrix and the support variance, weighting is performed on the target operation data to be fused through a support weighting model to obtain the weight of each data; Data fusion is performed according to the weights of the data through a data fusion model to obtain fused abnormal data features.

7. A smart power plant fault diagnosis device, characterized in that: The smart power plant fault diagnosis device includes: An acquisition module, configured to obtain, in response to a fault diagnosis instruction, message information reported by each power plant device, wherein the message information represents a character string corresponding to power plant device information, current time, and current operating status of the device; A determination module, configured to determine a candidate faulty device based on the message information; An acquisition module is used to drive a fault information acquisition device to acquire original electrical data, original image data, and original acoustic wave data of the candidate fault device; An analysis module, configured to input the raw electrical data, raw image data, and raw acoustic wave data into a fault diagnosis model corresponding to each data category to perform fault analysis, and output a fault analysis process; The diagnosis module is used to generate a fault diagnosis text according to the fault analysis process to provide auxiliary information for fault diagnosis.

8. A smart power plant fault diagnosis device, characterized in that: The smart power plant fault diagnosis device includes: a memory, a processor, and a smart power plant fault diagnosis program stored in the memory and executable on the processor. The smart power plant fault diagnosis program is configured to implement the smart power plant fault diagnosis method according to any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a smart power plant fault diagnosis program, which, when executed by the processor, implements the smart power plant fault diagnosis method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product includes a computer program, and when the computer program is executed by a processor, the steps of the smart power plant fault diagnosis method according to any one of claims 1 to 6 are implemented.

Images