Method for detecting abnormal working condition of rotary mechanical equipment based on sound array

Abstract

The invention provides a rotary mechanical equipment working condition anomaly detection method based on a sound array, and relates to the technical field of equipment anomaly detection. According to the method, a sound signal of the rotating mechanical equipment is acquired, and the sound signal is a frequency spectrum signal acquired through a sound array in a target area of the rotating mechanical equipment; preprocessing the sound signal to eliminate trend information of the sound signal and obtain a processed sound signal; determining a reconstruction error corresponding to the processed sound signal through the trained auto-encoder model according to the processed sound signal; and determining a working condition anomaly detection result of the rotary mechanical equipment according to the reconstruction error, wherein the working condition anomaly detection result comprises normal or abnormal working conditions. According to the method provided by the invention, the abnormal working condition of the rotary mechanical equipment can be detected based on the sound array in a long-distance non-contact manner, and the detection efficiency and the detection accuracy can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment abnormality detection, and in particular to a method for detecting abnormality in operating conditions of rotating mechanical equipment based on an acoustic array. Background Art

[0002] At present, rotating machinery and equipment that perform functions through rotational motion, such as steam turbines, gas turbines, and centrifugal compressors, are widely used. Since rotating machinery and equipment usually have high loads and operate in harsh environments, they are very likely to fail. Faults such as wear and tooth loss inside rotating machinery and equipment may lead to abnormal operating conditions, which will not only greatly reduce productivity, but may also cause safety, economic and environmental problems, and even adverse social impacts. Therefore, it is particularly important to detect abnormal operating conditions of rotating machinery and equipment.

[0003] However, in the early stage of the failure, the related chain reaction phenomenon is small, and the staff cannot detect the rotating machinery failure through senses and on-site parameter fluctuations. In related technologies, the working condition of the equipment is usually detected based on the vibration characteristics on the surface of the rotating machinery. However, due to the high surface temperature of the rotating machinery, the difficulty and high cost of installing multiple vibration sensors, some rotating machinery cannot use vibration characteristics to detect abnormal working conditions.

[0004] Therefore, there is an urgent need for a method for detecting abnormal operating conditions of rotating mechanical equipment to achieve rapid and accurate detection of abnormal operating conditions of rotating mechanical equipment. Summary of the invention

[0005] The embodiment of the present invention provides a method for detecting abnormal operating conditions of rotating mechanical equipment based on an acoustic array, which can detect abnormal operating conditions of rotating mechanical equipment over a long distance and without contact based on the acoustic array, and can improve detection efficiency and detection accuracy.

[0006] To achieve the above object, the embodiments of the present invention adopt the following technical solutions:

[0007] In a first aspect, a method for detecting abnormal working conditions of rotating mechanical equipment based on an acoustic array is provided, the method comprising: obtaining a sound signal of the rotating mechanical equipment, the sound signal being a spectrum signal obtained by an acoustic array in a target area of ​​the rotating mechanical equipment; preprocessing the sound signal to eliminate trend information of the sound signal to obtain a processed sound signal; determining a reconstruction error corresponding to the processed sound signal through a trained autoencoder model according to the processed sound signal; determining an abnormal working condition detection result of the rotating mechanical equipment according to the reconstruction error, the abnormal working condition detection result including whether the working condition is normal or abnormal.

[0008] In a possible implementation manner of the first aspect, obtaining a sound signal of a rotating mechanical device includes:

[0009] Determine the spherical coordinate direction of the acoustic array corresponding to the target area of ​​the rotating mechanical equipment;

[0010] Acquire the sound signal in the spherical coordinate direction of the sound array based on the beamforming algorithm;

[0011] Sound signal DAS The calculation formula of (k) is:

[0012]

[0013] Wherein, M is the number of array elements of the acoustic array; The top is the spherical coordinate direction; is the spherical coordinate direction The array response vector corresponding to the delay of each array element, H represents the conjugate transpose of the vector or matrix; x(k) represents the Fourier transform form of the sound signal x(t) received by the sound array;

[0014] The sound signal x(t) received by the sound array is expressed as:

[0015]

[0016] Among them, x i (t) is the signal received by the i-th array element.

[0017] In a possible implementation manner of the first aspect, preprocessing the sound signal to eliminate trend information of the sound signal to obtain the processed sound signal includes:

[0018] Determine the frequency of the sound signal when the power of the sound signal is at a maximum value;

[0019] The formula for determining frequency k is:

[0020]

[0021] Where N is the number of sampling points in the Fourier transform form;

[0022] Determine the rotation period of the rotating mechanical equipment according to the frequency corresponding to the sound signal;

[0023] The formula for determining the rotation period T is:

[0024]

[0025] According to the rotation cycle of the rotating mechanical equipment, the sound signal is decomposed into trend information, seasonal information and residual information through the time series decomposition algorithm;

[0026] The parameter estimation formula corresponding to the decomposition process of the sound signal is:

[0027]

[0028] Among them, U t is the trend information at time t; S t is the seasonal information at time t, V t is the residual information at time t, and the information X at time t t For trend information t , Season Information t and residual information V t The sum of , α is the first smoothing parameter; β is the second smoothing parameter; γ is the third smoothing parameter;

[0029] The trend information is subtracted from the sound signal to obtain a processed sound signal.

[0030] In a possible implementation manner of the first aspect, the autoencoder model is a fully connected network model, a convolutional neural network model, or a recurrent neural network model.

[0031] In a possible implementation of the first aspect, the autoencoder model is specifically used to perform encoding and decoding operations on the processed sound signal to complete dimensionality reduction reconstruction of the processed sound signal to obtain a dimensionality reduced and reconstructed sound signal, and to determine the reconstruction error between the processed sound signal and the dimensionality reduced and reconstructed sound signal.

[0032] In a possible implementation manner of the first aspect, the encoding function formula of the autoencoder model is:

[0033] h=f(x)=s f (Wx+p);

[0034] Among them, h is the code corresponding to the processed sound signal, x is the processed sound signal, s f is the activation function of the encoder, W is the weight matrix, and p is the bias term:

[0035] Activation function f The formula is:

[0036]

[0037] In a possible implementation manner of the first aspect, before acquiring the sound signal of the rotating mechanical equipment, the method further includes:

[0038] Acquire a training sample set, the training sample set including sound signals of multiple rotating mechanical equipment and an abnormal working condition detection result corresponding to each sound signal;

[0039] The autoencoder model is trained based on the training sample set to obtain a trained autoencoder model.

[0040] In a possible implementation of the first aspect, the abnormal operating condition detection result of the rotating machinery equipment is determined based on the reconstruction error, including: when the reconstruction error is less than or equal to a preset threshold, determining that the abnormal operating condition detection result of the rotating machinery equipment is normal; when the reconstruction error is greater than the preset threshold, determining that the abnormal operating condition detection result of the rotating machinery equipment is abnormal.

[0041] The beneficial effects of the present invention are as follows: compared with the method of detecting abnormal working conditions by setting sensors on rotating mechanical equipment in the related art, the method provided by the present invention can detect abnormal working conditions of rotating mechanical equipment, reduce detection time, and improve detection efficiency. Moreover, the accuracy of detection can be improved based on the acoustic array and autoencoder model.

[0042] In a second aspect, a device for detecting an abnormal working condition of a rotating mechanical equipment based on an acoustic array is provided, the device comprising: an acquisition unit, for acquiring a sound signal of the rotating mechanical equipment, the sound signal being a spectrum signal acquired by the acoustic array in a target area of ​​the rotating mechanical equipment; a processing unit, for preprocessing the sound signal to eliminate trend information of the sound signal to obtain a processed sound signal; a reconstruction unit, for determining a reconstruction error corresponding to the processed sound signal through a trained autoencoder model according to the processed sound signal; and a detection unit, for determining an abnormal working condition detection result of the rotating mechanical equipment according to the reconstruction error, the abnormal working condition detection result including whether the working condition is normal or abnormal.

[0043] According to a third aspect, an electronic device is provided, comprising a memory and one or more processors; the memory is coupled to the processor; wherein computer program code is stored in the memory, and the computer program code comprises computer instructions, and when the computer instructions are executed by the processor, the electronic device executes a rotating mechanical equipment operating condition abnormality detection method based on an acoustic array as in any implementation of the first aspect.

[0044] In a fourth aspect, a computer-readable storage medium is provided, comprising computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes a method for detecting abnormal operating conditions of rotating mechanical equipment based on an acoustic array as in any implementation of the first aspect.

[0045] In a fifth aspect, a computer program product is provided. When the computer program product is run on a computer, the computer is enabled to execute a method for detecting abnormal operating conditions of rotating mechanical equipment based on an acoustic array as in any implementation of the first aspect.

[0046] It can be understood that the beneficial effects that can be achieved by the abnormal operating condition detection device of rotating mechanical equipment based on acoustic array described in the second aspect provided above, the electronic device described in the third aspect, the computer-readable storage medium described in the fourth aspect, and the computer program product described in the fifth aspect can refer to the beneficial effects in the first aspect and any possible design method thereof, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 A schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention;

[0048] Figure 2 A method flow chart of a method for detecting abnormal working conditions of rotating mechanical equipment based on an acoustic array according to an embodiment of the present invention;

[0049] Figure 3 A method flow chart of another method for detecting abnormal working conditions of rotating mechanical equipment based on an acoustic array according to an embodiment of the present invention;

[0050] Figure 4 A method flow chart of another method for detecting abnormal working conditions of rotating mechanical equipment based on an acoustic array according to an embodiment of the present invention;

[0051] Figure 5 A schematic diagram of an autoencoder model processing a sound signal according to an embodiment of the present invention;

[0052] Figure 6 A method flow chart of another method for detecting abnormal working conditions of rotating mechanical equipment based on an acoustic array according to an embodiment of the present invention;

[0053] Figure 7 The figure is a schematic diagram of the hardware structure of another detection device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The technical solution in the embodiment of the present invention will be described below in conjunction with the accompanying drawings in the embodiment of the present invention. Among them, in the description of the present invention, unless otherwise specified, " / " indicates that the objects associated before and after are in an "or" relationship, for example, A / B can represent A or B; "and / or" in the present invention is only a description of the association relationship of associated objects, indicating that there can be three relationships, for example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. And, in the description of the present invention, unless otherwise specified, "multiple" means two or more than two. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single items or plural items.

[0055] In addition, in order to clearly describe the technical solutions of the embodiments of the present invention, in the embodiments of the present invention, the words "first", "second", etc. are used to distinguish the same items or similar items with substantially the same functions and effects. Those skilled in the art can understand that the words "first", "second", etc. do not limit the quantity and execution order, and the words "first", "second", etc. do not necessarily limit the difference.

[0056] Meanwhile, in the embodiments of the present invention, words such as "exemplary" or "for example" are used to indicate examples, illustrations or explanations. Any embodiment or design scheme described as "exemplary" or "for example" in the embodiments of the present invention should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way for easy understanding.

[0057] At present, rotating machinery and equipment that perform functions through rotational motion, such as steam turbines, gas turbines, and centrifugal compressors, are widely used. Since rotating machinery and equipment usually have high loads and operate in harsh environments, they are very likely to fail. Faults such as wear and tooth loss inside rotating machinery and equipment may lead to abnormal operating conditions, which will not only greatly reduce productivity, but may also cause safety, economic and environmental problems, and even adverse social impacts. Therefore, it is particularly important to detect abnormal operating conditions of rotating machinery and equipment.

[0058] However, in the early stage of the failure, the related chain reaction phenomenon is small, and the staff cannot detect the rotating machinery failure through senses and on-site parameter fluctuations. In related technologies, the working condition of the equipment is usually detected based on the vibration characteristics on the surface of the rotating machinery. However, due to the high surface temperature of the rotating machinery, the difficulty and high cost of installing multiple vibration sensors, some rotating machinery cannot use vibration characteristics to detect abnormal working conditions.

[0059] Therefore, there is an urgent need for a method for detecting abnormal operating conditions of rotating mechanical equipment to achieve rapid and accurate detection of abnormal operating conditions of rotating mechanical equipment.

[0060] In view of this, an embodiment of the present invention provides a method for detecting abnormal working conditions of rotating mechanical equipment based on an acoustic array, the method comprising: obtaining a sound signal of the rotating mechanical equipment, the sound signal being a spectrum signal obtained by the acoustic array in a target area of ​​the rotating mechanical equipment; preprocessing the sound signal to eliminate trend information of the sound signal to obtain a processed sound signal; determining a reconstruction error corresponding to the processed sound signal through a trained autoencoder model according to the processed sound signal; determining a detection result of the abnormal working condition of the rotating mechanical equipment according to the reconstruction error, the abnormal working condition detection result including whether the working condition is normal or abnormal.

[0061] The method provided by the embodiment of the present invention can detect abnormal working conditions of rotating mechanical equipment without contact over a long distance based on an acoustic array, and can improve detection efficiency and detection accuracy. Specifically, compared with the method of detecting abnormal working conditions by setting sensors on rotating mechanical equipment in the related art, the method provided by the present invention can detect abnormal working conditions of rotating mechanical equipment, can reduce detection time, and improve detection efficiency. And based on the acoustic array and autoencoder model, the detection accuracy can be improved.

[0062] In some embodiments, the method for detecting abnormal working condition of rotating machinery based on acoustic array provided in the embodiments of the present invention can be performed by an abnormal working condition detection device 100 for rotating machinery based on acoustic array (hereinafter referred to as detection device 100). As an example, the detection device 100 can be any electronic device 200 with data processing capability, such as a general-purpose computer, a personal computer, a laptop, a switch or a tablet computer, etc. The specific implementation of the purchase list detection device 100 is not limited here.

[0063] Figure 1 The hardware structure diagram of the electronic device provided by the embodiment of the present invention is shown. The electronic device 200 includes a processor 210, a memory 220 and a communication interface 230.

[0064] The processor 210 may include one or more processing cores. The processor 210 uses various interfaces and lines to connect various parts in the electronic device 200, and executes various functions and processes data of the electronic device 200 by running or executing instructions, programs, code sets or instruction sets stored in the memory 220, and calling data stored in the memory 220. Optionally, the processor 210 can be implemented in at least one hardware form of a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processing (DSP), a field-programmable gate array (FPGA), and a programmable logic array (PLA).

[0065] The memory 220 may include a random access memory (RAM) or a read-only memory (ROM). Optionally, the memory 220 includes a non-transitory computer-readable storage medium. The memory 220 may be used to store instructions, programs, codes, code sets, or instruction sets. The memory 220 may include a program storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as a signal acquisition function, a signal processing function, etc.), instructions for implementing the above-mentioned various method embodiments, etc.

[0066] The communication interface 230 is used to communicate with other devices, equipment or communication networks, such as data storage devices, image processing equipment or Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0067] In physical implementation, the above-mentioned components (such as processor 210, memory 220 and communication interface 230) can be components in the same device (such as a laptop). Alternatively, at least two of the components can be set in the same device, that is, as different components in one device, such as a deployment method similar to devices or components in a distributed system.

[0068] It is to be understood that the structure illustrated in this embodiment does not constitute a specific limitation on the electronic device 200. In other embodiments of the present invention, the electronic device 200 may include more or fewer components than those illustrated, or combine certain components, or separate certain components, or arrange the components differently. The illustrated components may be implemented in hardware, software, or a combination of software and hardware.

[0069] The abnormal operating condition detection method of rotating mechanical equipment based on acoustic array provided by an embodiment of the present invention is described below in conjunction with the accompanying drawings.

[0070] Figure 2 The present invention provides a flowchart of a method for detecting abnormal working conditions of rotating mechanical equipment based on an acoustic array. Optionally, the method can be performed by Figure 1 The method is executed by the electronic device 200 of the hardware structure shown, that is, by the detection device 100. The method may include the following steps:

[0071] S1. Acquire a sound signal of a rotating mechanical device, where the sound signal is a spectrum signal acquired by an acoustic array in a target area of ​​the rotating mechanical device.

[0072] Specifically, the sound signal is a sound signal generated when the target area of ​​the rotating mechanical equipment is running.

[0073] In one possible implementation, see Figure 3 The above S1 specifically includes the following steps:

[0074] S11. Determine the spherical coordinate direction of the acoustic array corresponding to the target area of ​​the rotating mechanical equipment.

[0075] S12. Acquire the sound signal in the spherical coordinate direction of the sound array based on the beamforming algorithm.

[0076] Specifically, the acoustic array includes a plurality of array elements, each of which is used to obtain an acoustic signal in a spherical coordinate direction.

[0077] Sound signal DAS The calculation formula of (k) is:

[0078]

[0079] Wherein, M is the number of array elements of the acoustic array; The top is the spherical coordinate direction; is the spherical coordinate direction The array response vector corresponding to the delay of each array element, H represents the conjugate transpose of the vector or matrix; x(k) represents the Fourier transform form of the sound signal x(t) received by the sound array;

[0080] The sound signal x(t) received by the sound array is expressed as:

[0081]

[0082] Among them, x i (t) is the signal received by the i-th array element.

[0083] It should be understood that the above method of acquiring sound signals through a beamforming algorithm is only an example description, and the signals acquired by the sound array can also be processed by other algorithms to obtain the sound signal of the target area of ​​the rotating mechanical equipment. The embodiment of the present invention does not impose any special restrictions on this.

[0084] S2. Preprocess the sound signal to eliminate trend information of the sound signal and obtain a processed sound signal.

[0085] Specifically, the trend information is the trend item in the sound signal, that is, other low-frequency signals superimposed on the original signal emitted by the rotating mechanical equipment during operation, which causes the original signal to have a tendency to fluctuate up and down. If the trend information of the sound signal is not eliminated, the subsequent processing of the sound signal will lead to inaccurate results in the final abnormal working condition detection, which cannot meet the user's needs.

[0086] In some embodiments, see Figure 4 The above S2 specifically includes the following steps:

[0087] S21. Determine the frequency corresponding to the sound signal when the power of the sound signal is at a maximum value.

[0088] Specifically, the formula for determining the frequency k is:

[0089]

[0090] Where N is the number of sampling points in the Fourier transform form;

[0091] S22, determining the rotation period of the rotating mechanical equipment according to the frequency corresponding to the sound signal;

[0092] The formula for determining the rotation period T is:

[0093]

[0094] S23, decomposing the sound signal into trend information, season information and residual information by using a time series decomposition algorithm according to the rotation cycle of the rotating mechanical equipment;

[0095] The parameter estimation formula corresponding to the decomposition process of the sound signal is:

[0096]

[0097] Among them, U t is the trend information at time t; S t is the seasonal information at time t, V t is the residual information at time t, and the information X at time t t For trend information t , Season Information t and residual information V t The sum of , α is the first smoothing parameter; β is the second smoothing parameter; γ is the third smoothing parameter;

[0098] S24. Subtract the trend information from the sound signal to obtain a processed sound signal.

[0099] It should be understood that the method for removing trend information provided in the embodiment of the present invention is only for illustrative purposes and is not particularly limited in the embodiment of the present invention.

[0100] From the above, it can be seen that the method provided by the embodiment of the present invention can remove the trend information in the sound signal, so that the subsequent autoencoder model can quickly complete the dimensionality reduction reconstruction according to the input sound signal, obtain the reconstruction error corresponding to the sound signal, and then realize the abnormal operating condition detection of rotating mechanical equipment.

[0101] S3. Determine a reconstruction error corresponding to the processed sound signal through the trained autoencoder model according to the processed sound signal.

[0102] Specifically, the encoder of the trained autoencoder model performs dimensionality reduction processing on the processed sound signal to obtain the encoding corresponding to the processed sound signal; then the decoder of the trained autoencoder model reconstructs the encoding to obtain a dimensionality reduced and reconstructed sound signal, and then the reconstruction error is determined based on the processed sound signal and the dimensionality reduced and reconstructed sound signal.

[0103] For example, see Figure 5 , Figure 5 The present invention is a schematic diagram of an autoencoder model processing a sound signal according to an embodiment of the present invention, wherein the autoencoder model includes an encoder f and a decoder g. The encoder f performs dimensionality reduction processing on the input sound signal A1 to obtain a code h corresponding to the sound signal; then the decoder g performs reconstruction processing on the code h to obtain a dimensionality-reduced and reconstructed sound signal A2, and then determines the reconstruction error based on the processed sound signal A1 and the dimensionality-reduced and reconstructed sound signal A2.

[0104] In one possible implementation, the autoencoder model is a fully connected network model, a convolutional neural network model, or a recurrent neural network model.

[0105] It should be noted that the autoencoder model may also be other types of neural network models, and the embodiments of the present invention do not impose any particular limitation on this.

[0106] In some embodiments, the autoencoder model is specifically used to perform encoding and decoding operations on the processed sound signal to complete the dimensionality reduction reconstruction of the processed sound signal to obtain a dimensionality reduced and reconstructed sound signal, and to determine the reconstruction error between the processed sound signal and the dimensionality reduced and reconstructed sound signal.

[0107] Optionally, the encoding function formula of the autoencoder model is:

[0108] h=f(x)=s f (Wx+p);

[0109] Among them, h is the code corresponding to the processed sound signal, x is the processed sound signal, s f is the activation function of the encoder, W is the weight matrix, and p is the bias term:

[0110] Activation function f The formula is:

[0111]

[0112] The decoding function formula of the autoencoder model is:

[0113] r=g(h)=S g (W T h+q).

[0114] S4. Determine an abnormal working condition detection result of the rotating mechanical equipment according to the reconstruction error, where the abnormal working condition detection result includes whether the working condition is normal or abnormal.

[0115] In some embodiments, see Figure 6 The above S4 specifically includes the following steps:

[0116] S41, when the reconstruction error is less than or equal to the preset threshold, determining that the abnormality detection result of the operating condition of the rotating mechanical equipment is normal.

[0117] S42: When the reconstruction error is greater than a preset threshold, determine that the abnormal operating condition detection result of the rotating mechanical equipment is abnormal.

[0118] In some embodiments, before the above S1, the method provided by the embodiment of the present invention also includes the following steps: obtaining a training sample set, the training sample set including sound signals of multiple rotating mechanical equipment and abnormal operating condition detection results corresponding to each sound signal; training the autoencoder model based on the training sample set to obtain a trained autoencoder model.

[0119] In order to facilitate the understanding of this solution, the technical solution of the embodiment of the present invention is exemplarily described below. The method provided by the embodiment of the present invention includes the following three steps, which are divided into obtaining sound signals, preprocessing sound signals and detecting abnormal working conditions. First, a beamforming algorithm (such as the delayed sum method and the linear constrained minimum variance method) is used to directionally collect the sound signals generated during the operation of the target area of ​​the rotating mechanical equipment; then a periodic detection method (such as the periodogram method and the autocorrelation method) is used to calculate the period T of the sound signal generated by the current rotating mechanical equipment, and then the trend information in the sound signal is removed according to the period T with the help of the triple exponential sliding average algorithm (Holt-Winters), that is, data centralization is performed; finally, the preprocessed sound signal is input into the autoencoder network to obtain the abnormal working condition detection result of the rotating mechanical equipment.

[0120] It can be seen from the above S1-S4 that the method provided by the embodiment of the present invention can realize the detection of abnormal working conditions of rotating mechanical equipment based on the acoustic array without contact over a long distance, and can improve the detection efficiency and detection accuracy. Specifically, compared with the method of detecting abnormal working conditions by setting sensors on rotating mechanical equipment in the related art, the method provided by the present invention can realize the detection of abnormal working conditions of rotating mechanical equipment, can reduce the detection time, and improve the detection efficiency. And based on the acoustic array and the autoencoder model, the accuracy of detection can be improved. In other words, the method provided by the embodiment of the present invention has low requirements for the installation of sensors, can realize non-contact monitoring at a relatively long distance, and effectively improve the accuracy of the diagnosis of abnormal working conditions of rotating mechanical equipment. The invention provides a method for using an acoustic array to directionally collect acoustic signals of a target area of ​​a rotating mechanical equipment and perform abnormal working condition detection, and uses an acoustic array and a beamforming algorithm to directionally collect sound signals generated by the operation of the target area, and uses a periodic detection method and an autoencoder network to realize the diagnosis of abnormal working conditions of rotating machinery.

[0121] The above mainly introduces the scheme of the embodiment of the present invention from the perspective of the method. It is understandable that, in order to realize the above functions, the detection device 100 includes at least one of the hardware structure and software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the embodiment of the present invention can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the embodiment of the present invention.

[0122] The embodiment of the present invention can divide the detection device 100 into functional units according to the above method example. For example, the detection device 100 can be divided into functional units corresponding to various functions, or two or more functions can be integrated into one processing unit. The above integrated unit can be implemented in the form of hardware or in the form of software functional units. It should be noted that the division of units in the embodiment of the present invention is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0123] For example, Figure 7The hardware structure diagram of a detection device provided by an embodiment of the present invention is shown. The detection device 100 includes: an acquisition unit 710, which is used to acquire a sound signal of a rotating mechanical device, and the sound signal is a spectrum signal acquired by an acoustic array in a target area of ​​the rotating mechanical device; a processing unit 720, which is used to pre-process the sound signal to eliminate the trend information of the sound signal and obtain a processed sound signal; a reconstruction unit 730, which is used to determine the reconstruction error corresponding to the processed sound signal through a trained autoencoder model according to the processed sound signal; a detection unit 740, which is used to determine the abnormal working condition detection result of the rotating mechanical device according to the reconstruction error, and the abnormal working condition detection result includes whether the working condition is normal or abnormal.

[0124] It should be understood that the specific description of the above optional methods can refer to the above method embodiments, which will not be repeated here. In addition, the explanation of any detection device 100 provided above and the description of the beneficial effects can refer to the above corresponding method embodiments, which will not be repeated here.

[0125] The embodiment of the present invention further provides a computer-readable storage medium, in which at least one computer instruction is stored, and the at least one computer instruction is loaded and executed by a processor to implement the methods of the above embodiments. For the explanation of the relevant contents and the description of the beneficial effects in any of the above-mentioned computer-readable storage media, reference can be made to the above-mentioned corresponding embodiments, which will not be repeated here.

[0126] The embodiment of the present invention further provides a chip. The chip integrates a control circuit and one or more ports for implementing the functions of the above-mentioned purchase list detection device 100. Optionally, the functions supported by the chip can be referred to above and will not be described in detail here.

[0127] Those skilled in the art will appreciate that all or part of the steps of the above embodiments can be implemented by instructing the relevant hardware through a program, and the program can be stored in a computer-readable storage medium. The above-mentioned storage medium can be a read-only memory, a random access memory, etc. The above-mentioned processing unit or processor can be a central processing unit, a general-purpose processor, a specific circuit structure (application specific integrated circuit, ASIC), a microprocessor (digital signal processor, DSP), a field programmable gate array (field programmable gate array, FPGA) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof.

[0128] The embodiment of the present invention also provides a computer program product including instructions, when the instructions are run on a computer, the computer executes any one of the methods in the above embodiments. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on the computer, the process or function according to the embodiment of the present invention is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media integrated therein. The available medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., an SSD), etc.

[0129] It should be noted that the above-mentioned devices for storing computer instructions or computer programs provided in the embodiments of the present invention, such as but not limited to the above-mentioned memory, computer-readable storage medium and communication chip, etc., all have non-transitory. Those skilled in the art should be aware that in one or more of the above-mentioned examples, the functions described in the embodiments of the present invention can be implemented with hardware, software, firmware or any combination thereof. When implemented using software, these functions can be stored in a computer-readable storage medium or transmitted as one or more instructions or codes on a computer-readable storage medium. Computer-readable storage media include computer storage media and communication media, wherein the communication medium includes any medium that is convenient for transmitting a computer program from one place to another. The storage medium can be any available medium that a general or special-purpose computer can access.

[0130] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A method for detecting abnormal working conditions of rotating mechanical equipment based on acoustic array, characterized in that: The method comprises: Acquire a sound signal of a rotating mechanical device, wherein the sound signal is a spectrum signal acquired by an acoustic array in a target area of ​​the rotating mechanical device; Preprocessing the sound signal to eliminate trend information of the sound signal to obtain a processed sound signal; Determining a reconstruction error corresponding to the processed sound signal through a trained autoencoder model according to the processed sound signal; An abnormal operating condition detection result of the rotating mechanical equipment is determined according to the reconstruction error, and the abnormal operating condition detection result includes whether the operating condition is normal or abnormal.

2. The method according to claim 1, characterized in that The step of obtaining the sound signal of the rotating mechanical equipment comprises: Determining the spherical coordinate direction of the acoustic array corresponding to the target area of ​​the rotating mechanical equipment; Acquiring a sound signal in a spherical coordinate direction of the sound array based on a beamforming algorithm; The sound signal y DAS The calculation formula of (k) is: Wherein, M is the number of array elements of the acoustic array; The top is the spherical coordinate direction; is the spherical coordinate direction The array response vector corresponding to the delay of each array element, H represents the conjugate transpose of the vector or matrix; x(k) represents the Fourier transform form of the sound signal x(t) received by the sound array: The sound signal x(t) received by the sound array is expressed as: Among them, x i (t) is the signal received by the i-th array element.

3. The method according to claim 2, characterized in that The preprocessing of the sound signal to eliminate the trend information of the sound signal to obtain the processed sound signal includes: Determine the frequency corresponding to the sound signal when the power of the sound signal is at a maximum value; The formula for determining the frequency k is: Where N is the number of sampling points in the Fourier transform form; Determining the rotation period of the rotating mechanical equipment according to the frequency corresponding to the sound signal; The formula for determining the rotation period T is: Decomposing the sound signal into trend information, season information and residual information by using a time series decomposition algorithm according to the rotation period of the rotating mechanical equipment; The parameter estimation formula corresponding to the decomposition process of the sound signal is: Among them, U t is the trend information at time t; S t is the seasonal information at time t, V t is the residual information at time t, and the information X at time t t For trend information t , Season Information t and residual information V t The sum of , α is the first smoothing parameter; β is the second smoothing parameter; γ is the third smoothing parameter; The trend information is subtracted from the sound signal to obtain the processed sound signal.

4. The method according to claim 3, characterized in that The autoencoder model is a fully connected network model, a convolutional neural network model or a recurrent neural network model.

5. The method according to claim 4, characterized in that The autoencoder model is specifically used to perform encoding and decoding operations on the processed sound signal to complete dimensionality reduction reconstruction of the processed sound signal to obtain the dimensionality reduced and reconstructed sound signal, and to determine the reconstruction error between the processed sound signal and the dimensionality reduced and reconstructed sound signal.

6. The method according to claim 5, characterized in that The encoding function formula of the autoencoder model is: h=f(x)=s f (Wx+p); Wherein, h is the code corresponding to the processed sound signal, x is the processed sound signal, s f is the activation function of the encoder, W is the weight matrix, and p is the bias term: Activation function f The formula is:

7. The method according to claim 6, characterized in that Before obtaining the sound signal of the rotating mechanical equipment, the method further includes: Acquire a training sample set, wherein the training sample set includes sound signals of a plurality of rotating mechanical devices and an abnormal working condition detection result corresponding to each sound signal; The autoencoder model is trained based on the training sample set to obtain the trained autoencoder model.

8. The method according to claim 7, characterized in that The step of determining the abnormal operating condition detection result of the rotating mechanical equipment according to the reconstruction error includes: When the reconstruction error is less than or equal to a preset threshold, determining that the abnormality detection result of the operating condition of the rotating mechanical equipment is normal; When the reconstruction error is greater than a preset threshold, it is determined that the abnormal operating condition detection result of the rotating mechanical equipment is abnormal.

9. A device for detecting abnormal working conditions of rotating mechanical equipment based on acoustic array, characterized in that: The device comprises: An acquisition unit, configured to acquire a sound signal of a rotating mechanical device, wherein the sound signal is a spectrum signal acquired by an acoustic array in a target area of ​​the rotating mechanical device; A processing unit, configured to pre-process the sound signal to eliminate trend information of the sound signal and obtain a processed sound signal; A reconstruction unit, configured to determine a reconstruction error corresponding to the processed sound signal through a trained autoencoder model according to the processed sound signal; A detection unit is used to determine an abnormal working condition detection result of the rotating mechanical equipment according to the reconstruction error, and the abnormal working condition detection result includes whether the working condition is normal or abnormal.

10. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method for detecting abnormal operating conditions of rotating mechanical equipment based on an acoustic array as described in any one of claims 1-8.

Images