Fault prediction method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a fault prediction method and device, electronic equipment and a storage medium. Acquiring a vibration signal of the to-be-predicted equipment; sequentially carrying out band-pass filtering and envelope demodulation on the vibration signal to obtain a to-be-predicted envelope spectrum; and according to the similarity distance between the to-be-predicted envelope spectrum and each fault template and the similarity threshold corresponding to each fault template, determining whether the to-be-predicted equipment has a fault of which the fault type is the same as that of the corresponding fault template or not. According to the embodiment of the invention, the fault prediction accuracy of the rotating equipment is improved, and the fault type prediction efficiency is improved.

Description

Technical Field

[0001] This application relates to artificial intelligence technology, and more particularly to a fault prediction method, apparatus, electronic device, and storage medium. Background Technology

[0002] With the continuous improvement of industrialization and intelligence, more and more mechanical equipment is being used to replace humans in performing heavy work, profoundly impacting human production and lifestyles. Among various types of equipment, rotating machinery plays a crucial role due to its ability to transmit force and motion, occupying a large proportion of industrial systems. Ensuring the safety and reliability of mechanical equipment during long-term operation has become a critical issue.

[0003] In existing technologies, equipment failures are typically predicted by analyzing various data related to the equipment's operating status.

[0004] However, during the operation of rotating equipment, there are many interference factors such as changes in operating conditions and fluctuations in rotation speed. These factors may cause the collected vibration signals to contain a large number of interference signals, which will greatly interfere with the identification of fault signals and make it difficult to ensure the accuracy of fault prediction for rotating equipment. Summary of the Invention

[0005] This application provides a fault prediction method, apparatus, electronic device, and storage medium to improve the accuracy of predicting faults in rotating equipment and increase the efficiency of fault type prediction.

[0006] In a first aspect, embodiments of this application provide a fault prediction method, which includes:

[0007] Acquire the vibration signal of the device to be predicted;

[0008] The vibration signal is sequentially subjected to bandpass filtering and envelope demodulation to obtain the envelope spectrum to be predicted.

[0009] Based on the similarity distance between the envelope spectrum to be predicted and each fault template, and the similarity threshold corresponding to each fault template, it is determined whether the device to be predicted has a fault of the same type as the corresponding fault template.

[0010] Secondly, embodiments of this application also provide a fault prediction device, which includes:

[0011] Vibration signal acquisition module, used to acquire vibration signals of the device to be predicted;

[0012] The module for acquiring the envelope spectrum to be predicted is used to sequentially perform bandpass filtering and envelope demodulation on the vibration signal to obtain the envelope spectrum to be predicted.

[0013] The fault prediction module is used to determine whether the device to be predicted has a fault of the same type as the corresponding fault template, based on the similarity distance between the envelope spectrum to be predicted and each fault template, as well as the similarity threshold corresponding to each fault template.

[0014] Thirdly, embodiments of this application also provide an electronic device, which includes:

[0015] One or more processors;

[0016] Storage device for storing one or more programs;

[0017] When one or more programs are executed by one or more processors, the one or more processors implement any of the fault prediction methods provided in the embodiments of this application.

[0018] Fourthly, embodiments of this application also provide a storage medium including computer-executable instructions, which, when executed by a computer processor, are used to perform any of the fault prediction methods provided in embodiments of this application.

[0019] Fifthly, embodiments of this application also provide a computer program product, which includes a computer program that, when executed by a processor, implements any of the fault prediction methods provided in embodiments of this application.

[0020] This application acquires the vibration signal of the equipment to be predicted; performs bandpass filtering and envelope demodulation on the vibration signal sequentially to obtain the envelope spectrum to be predicted. For rotating machinery where fault characteristic frequencies and their harmonics shift due to factors such as speed fluctuations and load changes, envelope demodulation allows for effective feature extraction to reduce noise interference. Based on the similarity distance between the predicted envelope spectrum and each fault template, and the similarity threshold corresponding to each fault template, it is determined whether the equipment to be predicted has a fault of the same type as the corresponding fault template. By combining signal processing technology with a nonlinear alignment mechanism to determine the similarity distance, it can adapt to the judgment of equipment fault types under different speeds, achieving effective prediction of fault types. Furthermore, based on multiple fault templates, it can achieve rapid judgment of multiple fault types, improving the efficiency of fault judgment and overcoming the limitation of traditional methods that can only diagnose single faults. Therefore, the technical solution of this application effectively alleviates the problem of insufficient fault prediction accuracy of traditional methods under varying speeds or operating conditions, achieving the effect of improving the prediction accuracy of rotating equipment faults and the efficiency of fault type prediction. Attached Figure Description

[0021] Figure 1 This is a flowchart of a fault prediction method according to Embodiment 1 of this application;

[0022] Figure 2 This is a flowchart of a fault prediction method according to Embodiment 2 of this application;

[0023] Figure 3 This is a flowchart of a fault prediction method according to Embodiment 3 of this application;

[0024] Figure 4 This is a schematic diagram of the structure of a fault prediction device according to Embodiment 4 of this application;

[0025] Figure 5 This is a schematic diagram of the structure of an electronic device according to Embodiment 5 of this application. Detailed Implementation

[0026] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort should fall within the scope of protection of the present application.

[0027] It should be noted that the terms "first" and "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0028] Example 1

[0029] Figure 1 This is a flowchart of a fault prediction method provided in Embodiment 1 of this application. This embodiment can be applied to the situation of fault prediction for rotating machinery. The method can be executed by a fault prediction device, which can be implemented by software and / or hardware and specifically configured in the fault prediction platform of rotating machinery.

[0030] See Figure 1 The fault prediction method shown includes the following steps:

[0031] S110, Obtain the vibration signal of the device to be predicted.

[0032] The equipment to be predicted can be rotating machinery that requires fault prediction. The vibration signal can be the vibration signal of the equipment to be predicted, used for fault prediction. The vibration signal can be collected in real time by sensors.

[0033] Among various types of equipment, rotating machinery plays a crucial role due to its ability to transmit force and motion, occupying a large proportion of industrial systems. However, the downtime losses and additional maintenance costs caused by rotating equipment failures each year are considerable, and may even lead to serious safety accidents. Therefore, in order to ensure the safe and stable operation of equipment and reduce operating costs, it is of great significance to conduct fault diagnosis research on rotating machinery.

[0034] S120. The vibration signal is sequentially subjected to bandpass filtering and envelope demodulation to obtain the envelope spectrum to be predicted.

[0035] Bandpass filtering can filter vibration signals according to a preset bandwidth to obtain vibration signals within the preset bandwidth range. This can suppress the influence of low-frequency interference and high-frequency noise on fault characteristics. For example, a set of low-frequency cutoff frequencies and high-frequency cutoff frequencies can be set as the preset bandwidth to suppress signals outside the preset bandwidth frequency range and retain signals within the preset bandwidth frequency range, thereby improving the signal-to-noise ratio. In the early stages of fault evolution, fault characteristic frequencies first appear as modulated signals in the resonant frequency band. As the fault worsens, they gradually appear in the low-frequency band. Therefore, a preset bandwidth can be set through the resonant frequency band to obtain the fault signal within the resonant frequency band. Specifically, the preset bandwidth can be determined by professional technicians based on experience or experimentation; this application does not impose specific limitations on this.

[0036] Envelope demodulation can be used to demodulate a bandpass-filtered vibration signal to extract the modulated fault characteristic frequencies and their harmonics in the high-frequency resonant band, thus obtaining the envelope spectrum to be predicted. The envelope spectrum to be predicted can be the envelope spectrum obtained after sequentially performing bandpass filtering and envelope demodulation on the vibration signal, and is used for fault prediction.

[0037] The steps of envelope demodulation include: performing a Hilbert transform on the filtered vibration signal to obtain the envelope signal, and then performing a discrete Fourier transform on the envelope signal to obtain the envelope demodulation spectrum. In order to mitigate the influence of the amplitude difference of the vibration signal under different working conditions, the amplitude of the envelope spectrum can be normalized. After normalization, the amplitude variation range is [0,1].

[0038] The normalization formula is as follows:

[0039]

[0040] in, The normalized envelope spectrum amplitude. The original envelope spectrum amplitude before normalization. The maximum amplitude value in the original envelope spectrum before normalization. This represents the minimum amplitude in the original envelope spectrum before normalization.

[0041] S130. Based on the similarity distance between the envelope spectrum to be predicted and each fault template, and the similarity threshold corresponding to each fault template, determine whether the device to be predicted has a fault of the same type as the corresponding fault template.

[0042] Each fault template can be an envelope spectrum obtained by pre-processing bandpass filtering and envelope demodulation of vibration signals from equipment with various fault types. This envelope spectrum is used to predict whether the equipment to be predicted has the same type of fault. The similarity threshold for each fault template can be the maximum similarity distance between it and the template, used to determine whether the equipment to be predicted has a fault of the same type as the corresponding template. The similarity distance can be the minimum similarity distance between the predicted envelope spectrum and each fault template, determined by a dynamic time warping algorithm. This distance measures the similarity between the predicted envelope spectrum and each fault template, thereby determining whether the equipment to be predicted has a fault of the same type as the corresponding template.

[0043] Dynamic time warping (VT) is used to measure the similarity between two sequences and is widely applied in speech recognition. It effectively addresses differences caused by varying speech rates and pronunciation lengths. Similar to speech data, the vibration signals of rotating equipment change in frequency as the rotation speed changes. VT uses non-linear alignment to find the optimal matching path between two sequences even when they are stretched or compressed to varying degrees along the frequency axis. The general steps of VT are to calculate the distance matrix between the two sequences, and then find the optimal alignment path from the start point to the end point of each sequence, minimizing the cumulative distance along the path.

[0044] For example, when the similarity distance between the envelope spectrum to be predicted and a certain fault template is less than the similarity threshold corresponding to the fault template, it is determined that the device to be predicted has a fault of the same type as the fault template; otherwise, it is determined that the device to be predicted does not have a fault of the same type as the corresponding fault template.

[0045] It should be noted that all information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data used for analysis, etc.) involved in this disclosure are information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of the relevant data comply with the relevant laws, regulations and standards of the relevant regions.

[0046] In practical research on fault prediction in rotating machinery, factors such as changes in operating conditions, speed fluctuations, sensor acquisition errors, and random noise interference can significantly affect the accuracy of fault diagnosis. Currently, there is a lack of a unified solution that can effectively address these issues.

[0047] The technical solution of this embodiment acquires the vibration signal of the equipment to be predicted; performs bandpass filtering and envelope demodulation on the vibration signal sequentially to obtain the envelope spectrum to be predicted. For rotating machinery where fault characteristic frequencies and their harmonics shift due to factors such as speed fluctuations and load changes, envelope demodulation can effectively extract features to reduce noise interference. Based on the similarity distance between the predicted envelope spectrum and each fault template, and the similarity threshold corresponding to each fault template, it is determined whether the equipment to be predicted has a fault of the same type as the corresponding fault template. By combining signal processing technology with a nonlinear alignment mechanism to determine the similarity distance, it can adapt to the judgment of equipment fault types under different speeds, achieving effective prediction of fault types. Furthermore, based on multiple fault templates, it can achieve rapid judgment of multiple fault types, improving the efficiency of fault judgment and overcoming the limitation of traditional methods that can only diagnose single faults. Therefore, the technical solution of this application effectively alleviates the problem of insufficient fault prediction accuracy of traditional methods under varying speeds or operating conditions, achieving the effect of improving the prediction accuracy of rotating equipment faults and improving the efficiency of fault type prediction.

[0048] Example 2

[0049] Figure 2 This is a flowchart of a fault prediction method provided in Embodiment 2 of this application. The technical solution of this embodiment is further refined based on the above technical solution.

[0050] Furthermore, the step of "determining whether the device to be predicted has a fault of the same type as the corresponding fault template based on the similarity distance between the envelope spectrum to be predicted and each fault template, and the similarity threshold corresponding to each fault template" is refined to: "Based on the improved dynamic time warping algorithm, determine the similarity distance between the envelope spectrum to be predicted and each fault template; use the similarity distance as the fault similarity between the vibration signal and each fault template; determine whether there is a fault template whose similarity threshold is not less than the fault similarity; if so, determine that the device to be predicted has a fault of the same type as the corresponding fault template" in order to predict the fault type.

[0051] See Figure 2 A fault prediction method shown includes:

[0052] S210. Obtain the vibration signal of the device to be predicted.

[0053] S220. The vibration signal is sequentially subjected to bandpass filtering and envelope demodulation to obtain the envelope spectrum to be predicted.

[0054] S230. Based on the improved dynamic time warping algorithm, determine the similarity distance between the envelope spectrum to be predicted and each fault template.

[0055] The idea behind the dynamic time warping algorithm is to calculate the similarity distance between the test sequence and the template sequence, thereby determining the similarity between the two sequences. In this application, the frequency and amplitude change when the rotating machinery malfunctions. Therefore, it is necessary to improve the calculation formula in the dynamic time warping algorithm, comprehensively considering both frequency and amplitude deviations in the distance metric, thereby effectively mitigating the matching error caused by small frequency shifts. The improved dynamic time warping algorithm can calculate the similarity distance between the envelope spectrum to be predicted and each fault template.

[0056] In an optional embodiment, the improved dynamic time warping algorithm is: a dynamic time warping algorithm that determines the similarity distance through frequency and amplitude.

[0057] To address the characteristics of rotating equipment, the traditional distance calculation method has been improved by incorporating frequency deviation and amplitude deviation as comprehensive factors. The improved similarity distance calculation formula is shown below:

[0058]

[0059] In the formula, To predict the first in the envelope spectrum Frequency values ​​of each sequence point For the first fault template Frequency values ​​of each sequence point It is the frequency resolution of the envelope spectrum. To predict the first in the envelope spectrum The amplitude of each sequence point after normalization. For the first fault template The amplitude of each sequence point after normalization.

[0060] The process for calculating the cumulative minimum distance is as follows: First, construct the distance matrix, and then find an optimal alignment path between the start point and the end point of the sequence, such that the cumulative distance on this path is minimized.

[0061] The improved dynamic time warping algorithm determines the similarity distance based on frequency and amplitude. Taking into account the characteristics of rotating equipment, the algorithm incorporates frequency deviation and amplitude deviation as comprehensive factors, enabling it to effectively determine similarity for rotating equipment.

[0062] S240. The similarity distance is used as the fault similarity between the vibration signal and each fault template.

[0063] Fault similarity can be the similarity distance between the vibration signal and each fault template. It is used to measure the similarity between the vibration signal and each fault template, and then predict whether the vibration signal has a fault of the type corresponding to each fault template.

[0064] S250. Determine whether there exists a similarity threshold for a fault template that is not less than the fault similarity.

[0065] Each fault template corresponds to a similarity threshold. When the fault similarity is less than the similarity threshold, it can be determined that the device to be predicted has a fault of the same type as the fault template corresponding to the similarity threshold. The fault similarity is compared with the similarity threshold corresponding to each fault template to determine whether there is a fault template whose similarity threshold is not less than the fault similarity.

[0066] S260. If so, then determine that the device to be predicted has a fault of the same type as the corresponding fault template.

[0067] If so, that is, if there is a similarity threshold corresponding to a fault template that is not less than the fault similarity, then it is determined that the device to be predicted has a fault of the same type as the corresponding fault template.

[0068] If not, then it is determined that there is no risk of failure in the equipment to be predicted, and the failure rate of each failure type can be set to 0.

[0069] In an optional embodiment, if so, after determining that the device to be predicted has a fault of the same type as the corresponding fault template, the method further includes: determining the fault probability based on the similarity distance and the similarity threshold corresponding to the corresponding fault template.

[0070] The formula for calculating the failure probability is as follows:

[0071]

[0072] in, Indicates the fault type The corresponding similarity threshold, For the envelope spectrum to be predicted and the fault template Similarity distance, For the equipment in fault type The failure probability value.

[0073] By determining the fault probability based on the similarity distance and the similarity threshold corresponding to the fault template, the fault probability can be determined quickly through the similarity distance, thereby improving the accuracy and efficiency of fault rate determination.

[0074] The technical solution of this embodiment determines the similarity distance between the envelope spectrum to be predicted and each fault template based on an improved dynamic time warping algorithm; the similarity distance is used as the fault similarity between the vibration signal and each fault template; it is determined whether there is a similarity threshold corresponding to a fault template that is not less than the fault similarity; if so, it is determined that the equipment to be predicted has a fault of the same type as the corresponding fault template. Through the nonlinear alignment mechanism of the improved dynamic time warping algorithm, it can adapt to the state judgment of rotating machinery equipment at different speeds, match the envelope spectrum to be predicted with multiple types of fault templates, improve the prediction accuracy of rotating equipment faults, and realize the accurate identification of multiple fault types. This breaks through the limitation of traditional methods that can only diagnose a single fault and improves the efficiency of fault type prediction.

[0075] Example 3

[0076] Figure 3 This is a flowchart of a fault prediction method provided in Embodiment 3 of this application. The technical solution of this embodiment is further refined based on the above technical solution.

[0077] Furthermore, the following steps are added: "Acquire the fault vibration signals of equipment of each fault type; perform bandpass filtering and envelope demodulation on each fault vibration signal to obtain each fault envelope spectrum; determine each fault template based on each fault envelope spectrum and the preset harmonic order," to determine each fault template.

[0078] See Figure 3 A fault prediction method shown includes:

[0079] S310. Obtain the fault vibration signal of the equipment for each fault type.

[0080] Historical data such as maintenance logs or fault repair logs can be used to obtain the vibration signals of various fault types of the equipment, which can then be used to obtain the envelope spectrum of each fault.

[0081] S320. Bandpass filtering and envelope demodulation are performed on each fault vibration signal to obtain the envelope spectrum of each fault.

[0082] Bandpass filtering and envelope demodulation are performed in the same manner as in the aforementioned embodiments. That is, bandpass filtering uses a set of low-frequency and high-frequency cutoff frequencies as a preset bandwidth to suppress signals outside the preset bandwidth frequency range and retain signals within the preset bandwidth frequency range. Envelope demodulation includes performing a Hilbert transform on the filtered vibration signal to obtain the envelope signal, and then performing a discrete Fourier transform on the envelope signal to obtain the envelope demodulation spectrum. The low-frequency and high-frequency cutoff frequencies are the same as in S120. After bandpass filtering and envelope demodulation of each fault vibration signal, normalization can also be performed, or normalization can be performed in S330; this application does not specifically limit this. The envelope spectrum of each fault is the envelope spectrum obtained after bandpass filtering and envelope demodulation of each fault vibration signal, used to determine each fault template.

[0083] S330. Determine each fault template based on the envelope spectrum of each fault and the preset harmonic order.

[0084] A preset harmonic order can be used to determine the range of the selected envelope spectrum. For example, the preset harmonic order can be 10. The preset harmonic order can be determined by professional technicians based on experience or experiments, and this application does not impose specific limitations on it. Based on the fault characteristic frequency and its harmonics, the envelope spectrum range corresponding to the harmonics of the preset harmonic order is selected, normalized, and a fault template is constructed.

[0085] In one optional embodiment, the method for determining the similarity threshold of each fault template includes: determining the health similarity distance between each fault template and the healthy template based on the improved dynamic time warping algorithm; and using the health similarity distance as the similarity threshold of the corresponding fault template.

[0086] The improved dynamic time warping algorithm is a dynamic time warping algorithm that determines the similarity distance through frequency and amplitude. The improved similarity distance calculation formula is the same as in the above embodiment, and will not be repeated here. The health template can be the envelope spectrum obtained by bandpass filtering and envelope demodulation of the vibration signal of a device without any faults, which is used to determine the similarity threshold of the fault template.

[0087] Based on the improved dynamic time warping algorithm, the health similarity distance between each fault template and the healthy template is calculated, and the health similarity distance is used as the similarity threshold of the corresponding fault template.

[0088] By using an improved dynamic time warping algorithm, the health similarity distance between each fault template and a healthy template is determined. This health similarity distance is then used as the similarity threshold for the corresponding fault template, providing an accurate threshold for subsequent prediction of the device to be predicted and improving the prediction accuracy.

[0089] S340: Obtain the vibration signal of the device to be predicted.

[0090] S350. The vibration signal is sequentially subjected to bandpass filtering and envelope demodulation to obtain the envelope spectrum to be predicted.

[0091] S360. Based on the similarity distance between the envelope spectrum to be predicted and each fault template, and the similarity threshold corresponding to each fault template, determine whether the device to be predicted has a fault of the same type as the corresponding fault template.

[0092] The technical solution of this embodiment acquires the fault vibration signals of equipment with various fault types; performs bandpass filtering and envelope demodulation on each fault vibration signal to obtain each fault envelope spectrum; determines each fault template based on each fault envelope spectrum and a preset harmonic order, comprehensively constructing templates for each fault type, which facilitates rapid determination of the fault type by comparing with each fault template. Based on the preset harmonic order, a fault template is determined from the envelope spectrum within a suitable range from each fault envelope spectrum, retaining the main fault features to ensure accurate identification of the corresponding fault in the future. At the same time, it reduces the amount of data for subsequent comparisons, effectively balancing feature retention and data comparison, and ensuring that each fault type can be quickly and accurately identified in the future.

[0093] Example 4

[0094] Figure 4 The diagram shown is a structural schematic of a fault prediction device provided in Embodiment 4 of this application. This embodiment is applicable to the situation of fault prediction for rotating machinery. The specific structure of the fault prediction device is as follows:

[0095] Vibration signal acquisition module 410 is used to acquire the vibration signal of the device to be predicted;

[0096] The envelope spectrum acquisition module 420 is used to sequentially perform bandpass filtering and envelope demodulation on the vibration signal to obtain the envelope spectrum to be predicted.

[0097] The fault prediction module 430 is used to determine whether the device to be predicted has a fault of the same type as the corresponding fault template based on the similarity distance between the envelope spectrum to be predicted and each fault template, and the similarity threshold corresponding to each fault template.

[0098] The technical solution of this embodiment acquires the vibration signal of the equipment to be predicted; performs bandpass filtering and envelope demodulation on the vibration signal sequentially to obtain the envelope spectrum to be predicted. For rotating machinery where fault characteristic frequencies and their harmonics shift due to factors such as speed fluctuations and load changes, envelope demodulation can effectively extract features to reduce noise interference. Based on the similarity distance between the predicted envelope spectrum and each fault template, and the similarity threshold corresponding to each fault template, it is determined whether the equipment to be predicted has a fault of the same type as the corresponding fault template. By combining signal processing technology with a nonlinear alignment mechanism to determine the similarity distance, it can adapt to the judgment of equipment fault types under different speeds, achieving effective prediction of fault types. Furthermore, based on multiple fault templates, it can achieve rapid judgment of multiple fault types, improving the efficiency of fault judgment and overcoming the limitation of traditional methods that can only diagnose single faults. Therefore, the technical solution of this application effectively alleviates the problem of insufficient fault prediction accuracy of traditional methods under varying speeds or operating conditions, achieving the effect of improving the prediction accuracy of rotating equipment faults and improving the efficiency of fault type prediction.

[0099] Optionally, the fault prediction module 430 includes:

[0100] The similarity distance determination unit is used to determine the similarity distance between the envelope spectrum to be predicted and each fault template based on the improved dynamic time warping algorithm.

[0101] The fault similarity determination unit is used to use the similarity distance as the fault similarity between the vibration signal and each fault template.

[0102] The fault similarity judgment unit is used to determine whether there is a fault template whose similarity threshold is not less than the fault similarity.

[0103] The fault type determination unit is used to determine, if yes, that the device to be predicted has a fault of the same type as the corresponding fault template.

[0104] Optionally, the improved dynamic time warping algorithm is: a dynamic time warping algorithm that determines the similarity distance through frequency and amplitude.

[0105] Optionally, the fault prediction module 430 also includes:

[0106] The fault probability determination unit is used to determine the fault probability based on the similarity distance and the similarity threshold corresponding to the fault template.

[0107] Optionally, the fault prediction device also includes:

[0108] The fault vibration signal acquisition module is used to acquire the fault vibration signals of equipment with various fault types.

[0109] The fault envelope spectrum acquisition module is used to perform bandpass filtering and envelope demodulation on each fault vibration signal to obtain the fault envelope spectrum.

[0110] The fault template determination module is used to determine each fault template based on the fault envelope spectrum and the preset harmonic order.

[0111] Optionally, the fault prediction device also includes:

[0112] The health similarity distance determination module is used to determine the health similarity distance between each fault template and the health template based on the improved dynamic time warping algorithm.

[0113] The similarity threshold determination module is used to use the health similarity distance as the similarity threshold for the corresponding fault template.

[0114] The fault prediction device provided in this application embodiment can execute the fault prediction method provided in any embodiment of this application, and has the corresponding functional modules and beneficial effects for executing the fault prediction method.

[0115] According to embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.

[0116] Example 5

[0117] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 5 of this application, as shown below. Figure 5 As shown, the electronic device includes a processor 510, a memory 520, an input device 530, and an output device 540; the number of processors 510 in the electronic device can be one or more. Figure 5 Taking a processor 510 as an example; the processor 510, memory 520, input device 530, and output device 540 in the electronic device can be connected via a bus or other means. Figure 5 Taking the example of a connection between China and Israel via a bus.

[0118] The memory 520, as a computer-readable storage medium, can be used to store software programs, computer-executable programs, and modules, such as the program instructions / modules corresponding to the fault prediction method in the embodiments of this application (e.g., vibration signal acquisition module 410, envelope spectrum acquisition module 420, and fault prediction module 430). The processor 510 executes various functional applications and data processing of the electronic device by running the software programs, instructions, and modules stored in the memory 520, thereby realizing the aforementioned fault prediction method.

[0119] The memory 520 may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function; the data storage area may store data created based on terminal usage. Furthermore, the memory 520 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some instances, the memory 520 may further include memory remotely located relative to the processor 510, which can be connected to the electronic device via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0120] Input device 530 can be used to receive input character information and generate key signal inputs related to user settings and function control of the electronic device. Output device 540 may include display devices such as a display screen.

[0121] Example 6

[0122] Embodiment 6 of this application also provides a storage medium containing computer-executable instructions. When executed by a computer processor, the computer-executable instructions are used to perform a fault prediction method. The method includes: acquiring a vibration signal of a device to be predicted; sequentially performing bandpass filtering and envelope demodulation on the vibration signal to obtain a predicted envelope spectrum; and determining whether the device to be predicted has a fault of the same type as the corresponding fault template based on the similarity distance between the predicted envelope spectrum and each fault template, and the similarity threshold corresponding to each fault template.

[0123] Of course, the computer-executable instructions provided in the embodiments of this application are not limited to the method operations described above, but can also perform related operations in the fault prediction method provided in any embodiment of this application.

[0124] Based on the above description of the implementation methods, those skilled in the art can clearly understand that this application can be implemented using software and necessary general-purpose hardware, and of course, it can also be implemented using hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as a computer floppy disk, read-only memory (ROM), random access memory (RAM), flash memory, hard disk, or optical disk, etc., including several instructions to cause an electronic device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments of this application.

[0125] It is worth noting that in the embodiments of the above-mentioned fault prediction device, the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of each functional unit are only for easy differentiation and are not used to limit the scope of protection of this application.

[0126] Note that the above are merely preferred embodiments and the technical principles employed in this application. Those skilled in the art will understand that this application is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of this application. Therefore, although this application has been described in detail through the above embodiments, this application is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of this application, the scope of which is determined by the scope of the appended claims.

Claims

1. A fault prediction method, characterized in that, include: Acquire the vibration signal of the device to be predicted; The vibration signal is sequentially subjected to bandpass filtering and envelope demodulation to obtain the envelope spectrum to be predicted; Based on the similarity distance between the envelope spectrum to be predicted and each fault template, and the similarity threshold corresponding to each fault template, it is determined whether the device to be predicted has a fault of the same type as the corresponding fault template.

2. The method according to claim 1, characterized in that, The step of determining whether the device to be predicted has a fault of the same type as the corresponding fault template based on the similarity distance between the envelope spectrum to be predicted and each fault template, and the similarity threshold corresponding to each fault template, includes: Based on the improved dynamic time warping algorithm, the similarity distance between the envelope spectrum to be predicted and each fault template is determined; The similarity distance is used as the fault similarity between the vibration signal and each fault template; Determine whether there exists a similarity threshold for a fault template that is not less than the fault similarity. If so, it is determined that the device to be predicted has a fault of the same type as the corresponding fault template.

3. The method according to claim 2, characterized in that, The improved dynamic time warping algorithm is a dynamic time warping algorithm that determines the similarity distance through frequency and amplitude.

4. The method according to claim 2, characterized in that, If so, after determining that the device to be predicted has a fault of the same type as the corresponding fault template, the method further includes: The probability of failure is determined based on the similarity distance and the similarity threshold corresponding to the fault template.

5. The method according to claim 1, characterized in that, Each fault template has been determined, including: Acquire fault vibration signals of equipment for each fault type; Bandpass filtering and envelope demodulation are performed on each of the fault vibration signals to obtain the envelope spectrum of each fault; Each fault template is determined based on its fault envelope spectrum and preset harmonic order.

6. The method according to claim 1, characterized in that, The method for determining the similarity threshold of each fault template includes: Based on the improved dynamic time warping algorithm, the health similarity distance between each fault template and the healthy template is determined. The health similarity distance is used as the similarity threshold for the corresponding fault template.

7. A fault prediction device, characterized in that, include: Vibration signal acquisition module, used to acquire vibration signals of the device to be predicted; The envelope spectrum acquisition module is used to sequentially perform bandpass filtering and envelope demodulation on the vibration signal to obtain the envelope spectrum to be predicted. The fault prediction module is used to determine whether the device to be predicted has a fault of the same type as the corresponding fault template, based on the similarity distance between the envelope spectrum to be predicted and each fault template, and the similarity threshold corresponding to each fault template.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the fault prediction method as described in any one of claims 1-6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the fault prediction method as described in any one of claims 1-6.

10. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the fault prediction method as described in any one of claims 1-6.

Images