Abnormality monitoring system of reciprocating diaphragm pump and monitoring method thereof
By using a reciprocating diaphragm pump anomaly monitoring system, sound pressure data analysis is used to identify pneumatic pump anomalies, solving the problems of low monitoring accuracy and efficiency in existing technologies, and achieving rapid and accurate anomaly identification and repair.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2026-03-10
AI Technical Summary
Existing pneumatic pump monitoring methods are not accurate and efficient, and cannot accurately identify the cause of abnormalities during operation. The pump body needs to be disassembled to determine the location of the abnormality.
An anomaly monitoring system employing a reciprocating diaphragm pump includes an audio acquisition module, a feature extraction module, a feature analysis module, and an anomaly analysis module. It identifies abnormal factors and issues warnings through sound pressure data analysis, and performs precise monitoring by combining signal optimization and a standard database.
It enables rapid and accurate identification of the cause of pump malfunctions, improving monitoring accuracy and maintenance efficiency, and reducing manual intervention and disassembly frequency.
Smart Images
Figure CN121630698A_ABST
Abstract
Description
Technical Field
[0001] This application relates to a monitoring system and a monitoring method, and more particularly to an abnormal monitoring system and a monitoring method for a reciprocating diaphragm pump. Background Technology
[0002] In existing industries (such as the chemical industry, petroleum industry, etc.), when it is necessary to transport hazardous or volatile liquids, a pneumatic pump is usually used to transport the liquid safely.
[0003] However, existing pneumatic pump monitoring typically relies on manual inspection to check for leaks or flow rate detection for abnormalities. Neither method can accurately pinpoint the location of the malfunction while the pump is running. The exact cause usually requires disassembling the pump, resulting in low accuracy and efficiency in current pneumatic pump monitoring methods. Summary of the Invention
[0004] The main purpose of this application is to solve the problems of low accuracy and low efficiency of existing pneumatic pump monitoring methods.
[0005] To achieve the above objectives, according to some embodiments of this application, an anomaly monitoring system for a reciprocating diaphragm pump is provided for monitoring the pump's operating status. The anomaly monitoring system for the reciprocating diaphragm pump includes an audio acquisition module, a feature extraction module, a feature analysis module, and an anomaly analysis module. An audio acquisition module is located outside the pump body and is used to acquire the pump's operating sound pressure data. A feature extraction module is coupled to the audio acquisition module and is used to extract features from the operating sound pressure data to obtain multiple operating feature data corresponding to the operating sound pressure data. A feature analysis module is coupled to the feature extraction module and includes a factor analysis unit and a sound pressure analysis unit. The factor analysis unit is used to perform factor analysis on the operating feature data to obtain multiple factor feature data corresponding to multiple abnormal factors. The sound pressure analysis unit performs sound pressure analysis on the factor feature data through a sound pressure analysis model to obtain factor sound pressure feature data corresponding to each of the multiple abnormal factors. An anomaly analysis module is coupled to the feature analysis module and performs anomaly analysis on the factor sound pressure feature data. If the factor sound pressure feature data corresponding to one of the multiple abnormal factors exceeds the range of standard sound pressure data, the anomaly analysis module issues an anomaly warning.
[0006] In other embodiments, the abnormal monitoring system of the reciprocating diaphragm pump according to some embodiments of this application further includes a signal optimization module coupled to the audio acquisition module. The signal optimization module optimizes the signal-to-noise ratio of the operating sound pressure data to acquire and output the optimized operating sound pressure data to the feature extraction module. The feature extraction module extracts features from the optimized operating sound pressure data.
[0007] In other embodiments, the sound pressure analysis model of the sound pressure analysis unit is established using operational sound pressure data, operational characteristic data, factor characteristic data, and factor sound pressure characteristic data as training data, and through machine learning methods.
[0008] In other embodiments, the anomaly monitoring system for a reciprocating diaphragm pump according to some embodiments of this application further includes a standard database storing standard sound pressure data.
[0009] In other embodiments, the operational characteristic data includes frequency characteristic data, damping characteristic data, time characteristic data, and angle characteristic data; abnormal factors include air valve failure factors, ball valve failure factors, ball wear factors, diaphragm rupture factors, and ball seat breakage factors.
[0010] According to some embodiments of this application, an abnormal monitoring method for a reciprocating diaphragm pump is also provided, which includes an audio signal acquisition step, a feature extraction step, a feature analysis step, and an abnormal analysis step. The audio signal acquisition step involves placing an audio acquisition module outside the pump body and obtaining the pump's operating sound pressure data through the audio acquisition module. The feature extraction step involves extracting features from the operating sound pressure data using a feature extraction module to obtain multiple operating feature data corresponding to the operating sound pressure data. The feature analysis step involves performing factor analysis on the operating feature data using the factor analysis unit of the feature analysis module to obtain multiple factor feature data corresponding to multiple abnormal factors, and using the sound pressure analysis model of the feature analysis module to perform sound pressure analysis on the factor feature data to obtain factor sound pressure feature data corresponding to each of the multiple abnormal factors. The abnormal analysis step involves performing anomaly analysis on the factor sound pressure feature data using an anomaly analysis module. If the factor sound pressure feature data corresponding to one of the multiple abnormal factors exceeds the range of standard sound pressure data, the anomaly analysis module issues an abnormality warning.
[0011] In other embodiments, the abnormal monitoring method for a reciprocating diaphragm pump according to some embodiments of this application further includes a signal optimization step: optimizing the signal-to-noise ratio of the operating sound pressure data through a signal optimization module to obtain optimized operating sound pressure data; and in the feature extraction step, extracting features from the optimized operating sound pressure data.
[0012] In other embodiments, during the anomaly analysis step, the anomaly analysis module obtains standard sound pressure data for each of the multiple anomaly factors from a standard database.
[0013] In other embodiments, the method for establishing a standard database includes: a normal audio signal acquisition step: setting an audio acquisition module outside the normal pump body and obtaining normal operating sound pressure data of the normal pump body through the audio acquisition module; a normal feature extraction step: performing feature extraction on the normal operating sound pressure data through a feature extraction module to obtain multiple normal operating feature data corresponding to the normal operating sound pressure data; a normal feature analysis step: performing factor analysis on the normal operating feature data through a factor analysis unit to obtain multiple factor normal feature data corresponding to multiple abnormal factors, and performing sound pressure analysis on the factor normal feature data using a sound pressure analysis model to obtain standard sound pressure data for each abnormal factor among the multiple abnormal factors; and a database establishment step: establishing a standard database storing standard sound pressure data for each abnormal factor among the multiple abnormal factors.
[0014] Therefore, this application monitors the operation of the pump body through sound pressure monitoring, which can quickly detect when the pump body is in an abnormal operating state and accurately determine the cause of the abnormality. This allows personnel to quickly and accurately perform real-time repair and inspection of abnormal parts of the pump body, thereby improving the monitoring accuracy and maintenance efficiency of the pump body. Attached Figure Description
[0015] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0016] Figure 1 A block connection diagram of an anomaly monitoring system for a reciprocating diaphragm pump according to some embodiments of the present disclosure is shown.
[0017] Figure 2 A block connection diagram of an anomaly monitoring system for a reciprocating diaphragm pump according to other embodiments of the present disclosure is shown.
[0018] Figure 3 A block flow diagram of an anomaly monitoring method for a reciprocating diaphragm pump according to some embodiments of the present disclosure is shown.
[0019] Figure 4 A block flow diagram of an anomaly monitoring method for a reciprocating diaphragm pump according to other embodiments of the present disclosure is shown.
[0020] Figure 5 This is a block flowchart illustrating the method for establishing a standard database according to an embodiment of this application.
[0021] Figure label: 1. Pump body; 100. Abnormal monitoring system for reciprocating diaphragm pumps; 200. Methods for abnormal monitoring of reciprocating diaphragm pumps; 300. Methods for establishing a standard database; 10. Audio acquisition module; 20. Feature extraction module; 30. Feature Analysis Module; 31. Factor Analysis Unit; 32. Sound pressure analysis unit; 321. Sound pressure analysis model; 40. Anomaly Analysis Module; 50. Signal Optimization Module; 60. Standard database; S1. Audio acquisition steps; S2, Feature extraction step; S3, Feature analysis step; S4, Anomaly Analysis Step; S5, Signal Optimization Step; P1. Normal audio acquisition steps; P2. Normal feature extraction steps; P3, Normal Feature Analysis Steps; P4, Database Establishment Steps. Detailed Implementation
[0022] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of the embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application.
[0023] It should be noted that all directional indications in the embodiments of this application are only used to explain the relative positional relationship and movement of each component in a specific posture. If the specific posture changes, the directional indications will also change accordingly.
[0024] In this application, unless otherwise expressly specified and limited, the terms "connection," "fixed," etc., should be interpreted broadly. For example, "fixed" can mean a fixed connection, a detachable connection, or an integral part; it can mean a mechanical connection or an electrical connection; it can mean a direct connection or an indirect connection through an intermediate medium; it can mean the internal communication of two components or the interaction between two components, unless otherwise expressly limited. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.
[0025] Furthermore, the use of terms such as "first" and "second" in this application is for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of those features. Additionally, the technical solutions of the various embodiments can be combined with each other, but only on the basis of being achievable by those skilled in the art. If the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed in this application.
[0026] The technical solution of this application is described below with reference to the accompanying drawings and specific embodiments.
[0027] Please see Figures 1 to 5 An anomaly monitoring system 100 for a reciprocating diaphragm pump, according to some embodiments of the present disclosure, is used to monitor the operating status of the pump body 1. The anomaly monitoring system 100 for the reciprocating diaphragm pump includes an audio acquisition module 10, a feature extraction module 20, a feature analysis module 30, and an anomaly analysis module 40. The pump body 1 is a pneumatic diaphragm reciprocating diaphragm pump.
[0028] An audio acquisition module 10 is disposed outside the pump body 1; the audio acquisition module 10 is used to acquire the sound pressure data of the pump body 1 during operation. The audio acquisition module 10 is a microphone, and the audio acquisition module 10 collects the sound generated by the operation of the pump body 1 in a non-contact manner.
[0029] The feature extraction module 20 is coupled to the audio acquisition module 10. The feature extraction module 20 is used to extract features from the operating sound pressure data to obtain multiple operating feature data corresponding to the operating sound pressure data. The feature extraction module 20 extracts features from the operating sound pressure data using the Laplace wavelet transform method. The multiple operating feature data include frequency feature data, damping feature data, time feature data, and angle feature data, where the angle feature data is the periodic angle corresponding to the time feature data.
[0030] The feature analysis module 30 is coupled to the feature extraction module 20. The feature analysis module 30 includes a factor analysis unit 31 and a sound pressure analysis unit 32. The factor analysis unit 31 performs factor analysis on the multiple operational feature data to obtain multiple factor feature data corresponding to multiple abnormal factors. The sound pressure analysis unit 32 performs sound pressure analysis on the multiple factor feature data through a sound pressure analysis model 321 to obtain factor sound pressure feature data corresponding to each of the abnormal factors. The multiple abnormal factors include air valve failure factors, ball valve failure factors, ball wear factors, diaphragm rupture factors, and ball seat fracture factors. The factor feature data includes frequency feature data, damping feature data, time feature data, and angle feature data corresponding to the air valve failure factors; frequency feature data, damping feature data, time feature data, and angle feature data corresponding to the ball valve failure factors; and so on.
[0031] It should be noted that the factor analysis unit 31 performs factor analysis on the angle feature data to obtain the multiple factor feature data corresponding to the multiple abnormal factors. For example, the angle feature data corresponding to the air valve failure factor is an angle between 0 degrees and 30 degrees. Therefore, the factor analysis unit 31 will classify the angle feature data between 0 degrees and 30 degrees as the angle feature data of the air valve failure factor, and at the same time classify the frequency feature data, damping feature data, and time feature data corresponding to the angle feature data of the air valve failure factor as frequency feature data of the air valve failure factor, damping feature data of the air valve failure factor, and time feature data of the air valve failure factor.
[0032] For example, the sound pressure analysis unit 32 performs sound pressure analysis on the frequency characteristic data, damping characteristic data, and time characteristic data of the air valve failure factors through the sound pressure analysis model 321 to obtain the sound pressure characteristic data of the air valve failure factors corresponding to the abnormal air valve failure factors. This allows the anomaly analysis module 40 to analyze whether the air valve of the pump body 1 is in normal operating condition based on the sound pressure characteristic data of the air valve failure factors.
[0033] In some embodiments, the sound pressure analysis model 321 of the sound pressure analysis unit 32 is established using the operational sound pressure data, the operational characteristic data, the factor characteristic data, and the factor sound pressure characteristic data as training data, and through machine learning methods. Therefore, the sound pressure analysis model 321 can improve its overall analysis accuracy by continuously acquiring more training data and performing machine learning.
[0034] An anomaly analysis module 40 is coupled to the feature analysis module 30. The anomaly analysis module 40 performs anomaly analysis on the sound pressure characteristic data of the factors. If the sound pressure characteristic data corresponding to one of the multiple anomaly factors exceeds the range of standard sound pressure data, the anomaly analysis module 40 issues an anomaly warning. The standard sound pressure data corresponding to the air valve malfunction factor is 0.005 Pa to 0.025 Pa, the standard sound pressure data corresponding to the ball valve malfunction factor is 0.12 Pa to 0.32 Pa, and the standard sound pressure data corresponding to the ball seat fracture factor is 0.79 Pa to 0.99 Pa.
[0035] In some embodiments, this application performs periodic calculations on the sound pressure characteristic data of the ball wear factor corresponding to the ball wear factor and the sound pressure characteristic data of the diaphragm rupture factor corresponding to the diaphragm rupture factor to obtain the corresponding periodic data of the ball wear factor and the diaphragm rupture factor, and performs anomaly analysis of the ball wear factor and the diaphragm rupture factor with the aid of the corresponding standard periodic data (between 140s and 160s).
[0036] For example, if the sound pressure characteristic data of the air valve failure factor obtained by the sound pressure analysis model 321 is 0.03 Pa, then after the anomaly analysis by the anomaly analysis module 40, it will be found that the sound pressure characteristic data of the air valve failure factor (0.03 Pa) exceeds the range of the corresponding standard sound pressure data (0.005 Pa to 0.025 Pa). Therefore, the anomaly analysis module 40 will issue an anomaly warning of air valve failure to inform personnel that the air valve needs to be adjusted and repaired.
[0037] Please see Figure 2 As shown, the anomaly monitoring system for a reciprocating diaphragm pump according to some embodiments of this application further includes a signal optimization module 50 coupled to the audio acquisition module 10. The signal optimization module 50 optimizes the signal-to-noise ratio of the operating sound pressure data to acquire and output optimized operating sound pressure data to the feature extraction module 20. The feature extraction module 20 extracts features from the optimized operating sound pressure data, thereby improving the analysis accuracy of the subsequent feature analysis module 30 and anomaly analysis module 40. Since the audio acquisition module 10 is located outside the pump body 1, the outer shell of the pump body 1 causes the operating sound pressure data to include some noise. Therefore, the signal optimization module 50 can remove some noise from the operating sound pressure data to generate the optimized operating sound pressure data, making subsequent analysis more accurate. The signal optimization module 50 uses a multi-resolution blind deconvolution algorithm to optimize the signal-to-noise ratio of the operating sound pressure data.
[0038] Please see Figure 2As shown, the abnormal monitoring system for a reciprocating diaphragm pump according to some embodiments of this application further includes a standard database 60, which stores the standard sound pressure data. The abnormality analysis module 40 extracts the corresponding standard sound pressure data from the standard database 60 according to each of the abnormal factors and performs abnormality analysis.
[0039] Please see Figures 3 to 5 As shown, this application also provides an anomaly monitoring method 200 for a reciprocating diaphragm pump, which includes an audio signal acquisition step S1, a feature extraction step S2, a feature analysis step S3, and an anomaly analysis step S4.
[0040] Audio acquisition step S1: The audio acquisition module 10 is placed outside the pump body 1, and the sound pressure data of the pump body 1 during operation is obtained through the audio acquisition module 10. The audio acquisition module 10 is a microphone, and the audio acquisition module 10 collects the sound generated by the operation of the pump body 1 in a non-contact manner.
[0041] Feature extraction step S2: The feature extraction module 20 extracts features from the operational sound pressure data to obtain the multiple operational feature data corresponding to the operational sound pressure data. Specifically, the feature extraction module 20 uses the Laplace wavelet transform method to extract features from the operational sound pressure data.
[0042] Feature analysis step S3: The factor analysis unit 31 of the feature analysis module 30 performs factor analysis on the operational feature data to obtain the multiple factor feature data corresponding to the multiple abnormal factors, and the sound pressure analysis model 321 of the feature analysis module 30 performs sound pressure analysis on the factor feature data to obtain the factor sound pressure feature data corresponding to each of the abnormal factors.
[0043] The multiple abnormal factors include the air valve failure factor, the ball valve failure factor, the ball wear factor, the diaphragm rupture factor, and the ball seat fracture factor; the factor characteristic data includes the frequency characteristic data, damping characteristic data, time characteristic data, and angle characteristic data of the air valve failure factor corresponding to the air valve failure factor, and the frequency characteristic data, damping characteristic data, time characteristic data, and angle characteristic data of the ball valve failure factor corresponding to the ball valve failure factor, and so on.
[0044] Anomaly analysis step S4: The anomaly analysis module 40 performs anomaly analysis on the sound pressure characteristic data of the factors. If the sound pressure characteristic data of the factor corresponding to one of the multiple abnormal factors exceeds the range of the standard sound pressure data, the anomaly analysis module 40 issues an anomaly warning to inform personnel to adjust and repair the pump body parts accordingly.
[0045] Please see Figure 4 As shown, in some embodiments, the anomaly monitoring method 200 for a reciprocating diaphragm pump according to some embodiments of this application further includes a signal optimization step S5: the signal optimization module 50 optimizes the signal-to-noise ratio of the operating sound pressure data to obtain optimized operating sound pressure data. In the feature extraction step S2, features are extracted from the optimized operating sound pressure data. This improves the accuracy of subsequent feature analysis module 30 and anomaly analysis module 40. In the signal optimization step S5, the signal optimization module 50 uses a multi-resolution blind deconvolution algorithm to optimize the signal-to-noise ratio of the operating sound pressure data.
[0046] Please see Figure 4 As shown, in some embodiments, in the anomaly analysis step S4, the anomaly analysis module 40 obtains the standard sound pressure data corresponding to each of the anomaly factors from the standard database 60 to perform anomaly analysis on the sound pressure characteristic data of the factors.
[0047] Please see Figure 5 As shown, in some embodiments, this application also provides a standard database establishment method 300, which includes a normal audio information acquisition step P1, a normal feature extraction step P2, a normal feature analysis step P3, and a database establishment step P4.
[0048] Normal audio acquisition step P1: The audio acquisition module 10 is placed outside the normal pump body, and the normal operating sound pressure data of the normal pump body is obtained through the audio acquisition module 10. The audio acquisition module 10 is a microphone, and the audio acquisition module 10 collects the sound generated by the normal pump body during operation in a non-contact manner.
[0049] Normal feature extraction step P2: The feature extraction module 20 extracts features from the normal operating sound pressure data to obtain multiple normal operating feature data corresponding to the normal operating sound pressure data. Specifically, the feature extraction module 20 uses the Laplace wavelet transform method to extract features from the normal operating sound pressure data.
[0050] Normal feature analysis step P3: The factor analysis unit 31 performs factor analysis on the normal operation feature data to obtain multiple factor normal feature data corresponding to the multiple abnormal factors, and uses the sound pressure analysis model 321 to perform sound pressure analysis on the factor normal feature data to obtain the standard sound pressure data corresponding to each of the abnormal factors.
[0051] Database establishment step P4: Establish a standard database 60 storing the standard sound pressure data corresponding to each of the aforementioned abnormal factors. Therefore, the anomaly analysis module 40 extracts the corresponding standard sound pressure data from the standard database 60 based on each of the aforementioned abnormal factors to perform anomaly analysis. Users can store the standard database 60 on a terminal device or a cloud server, allowing for convenient storage and maintenance of the standard database 60.
[0052] Therefore, this application monitors the operation of pump body 1 by means of sound pressure monitoring. When pump body 1 is abnormal, it can quickly detect that pump body 1 is in an abnormal operating state and accurately determine the cause of the abnormality. This allows personnel to quickly and accurately carry out real-time repair and inspection of abnormal parts of pump body 1, thereby improving the monitoring accuracy and maintenance efficiency of pump body 1.
[0053] Furthermore, the signal optimization module 50 of this application can remove some noise from the operating sound pressure data to generate optimized operating sound pressure data, allowing the subsequent feature analysis module 30 and anomaly analysis module 40 to perform more accurate analysis.
[0054] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. In addition, those skilled in the art can combine and integrate the different embodiments or examples described in this specification.
[0055] Furthermore, the technical solutions of the various embodiments can be combined with each other, but only if they are based on the ability of a person skilled in the art to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be considered that such combination of technical solutions does not exist and is not within the scope of protection claimed in this disclosure.
[0056] Although embodiments of the present disclosure have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the present disclosure, the scope of which is defined by the claims and their equivalents.
Claims
1. An abnormality monitoring system for a reciprocating diaphragm pump, characterized by, The reciprocating diaphragm pump abnormality monitoring system is used for monitoring the operation condition of a pump body, and the reciprocating diaphragm pump abnormality monitoring system comprises: An audio acquisition module is arranged outside the pump body and is used for acquiring the running sound pressure data of the pump body; A feature extraction module is coupled to the audio acquisition module and is used for performing feature extraction on the running sound pressure data to obtain a plurality of running feature data corresponding to the running sound pressure data; A feature analysis module is coupled to the feature extraction module; the feature analysis module comprises a factor analysis unit and a sound pressure analysis unit, the factor analysis unit is used for performing factor analysis on the plurality of running feature data to obtain a plurality of factor feature data corresponding to a plurality of abnormal factors, and the sound pressure analysis unit performs sound pressure analysis on the plurality of factor feature data through a sound pressure analysis model to obtain factor sound pressure feature data corresponding to each abnormal factor in the plurality of abnormal factors; and An abnormality analysis module is coupled to the feature analysis module; the abnormality analysis module performs abnormality analysis on the plurality of factor sound pressure feature data, and if the factor sound pressure feature data corresponding to one abnormal factor in the plurality of abnormal factors is out of the range of standard sound pressure data, the abnormality analysis module issues an abnormality warning.
2. The abnormality monitoring system of a reciprocating diaphragm pump according to claim 1, characterized by, A signal optimization module coupled to the audio acquisition module is further included; the signal optimization module performs signal-to-noise ratio optimization on the running sound pressure data to obtain and output optimized running sound pressure data to the feature extraction module, and the feature extraction module performs feature extraction on the optimized running sound pressure data.
3. The abnormality monitoring system of a reciprocating diaphragm pump according to claim 1, characterized by, The sound pressure analysis model of the sound pressure analysis unit is established through a machine learning method by taking the running sound pressure data, the plurality of running feature data, the plurality of factor feature data, and the plurality of factor sound pressure feature data as training data.
4. The abnormality monitoring system of a reciprocating diaphragm pump according to claim 1, characterized by, A standard database is further included, and the standard database stores the standard sound pressure data.
5. The abnormality monitoring system of a reciprocating diaphragm pump according to claim 1, characterized by, The plurality of running feature data comprises frequency feature data, damping feature data, time feature data, and angle feature data; and the plurality of abnormal factors comprises a guide valve failure factor, a ball valve failure factor, a ball sub-wear factor, a diaphragm rupture factor, and a ball seat rupture factor.
6. An abnormality monitoring method of a reciprocating diaphragm pump, characterized by, The reciprocating diaphragm pump abnormality monitoring method comprises: An audio acquisition step: an audio acquisition module is arranged outside a pump body, and the running sound pressure data of the pump body is obtained through the audio acquisition module; A feature extraction step: a feature extraction module is used for performing feature extraction on the running sound pressure data to obtain a plurality of running feature data corresponding to the running sound pressure data; A feature analysis step: a factor analysis unit of a feature analysis module is used for performing factor analysis on the plurality of running feature data to obtain a plurality of factor feature data corresponding to a plurality of abnormal factors, and a sound pressure analysis model of the feature analysis module is used for performing sound pressure analysis on the plurality of factor feature data to obtain factor sound pressure feature data corresponding to each abnormal factor in the plurality of abnormal factors; and An abnormality analysis module is coupled to the feature analysis module; the feature analysis module performs abnormality analysis on the plurality of factor sound pressure feature data, and if the factor sound pressure feature data corresponding to one abnormal factor in the plurality of abnormal factors is out of the range of standard sound pressure data, the abnormality analysis module issues an abnormality warning. The abnormality analysis module analyzes the factor sound pressure characteristic data, and if the factor sound pressure characteristic data corresponding to one of the abnormal factors exceeds the range of the standard sound pressure data, the abnormality analysis module issues an abnormality warning.
7. The abnormality monitoring method of a reciprocating diaphragm pump according to claim 6, characterized by, The signal optimization module optimizes the operation sound pressure data in terms of signal-to-noise ratio to obtain optimized operation sound pressure data.
8. The abnormality monitoring method of a reciprocating diaphragm pump according to claim 6, characterized by, The sound pressure analysis model of the characteristic analysis module is established by using the operation sound pressure data, the operation characteristic data, the factor characteristic data, and the factor sound pressure characteristic data as training data and by using a machine learning method.
9. The abnormality monitoring method of a reciprocating diaphragm pump according to claim 6, characterized by, In the abnormality analysis step, the abnormality analysis module obtains the standard sound pressure data corresponding to each of the abnormal factors from a standard database.
10. The abnormality monitoring method of a reciprocating diaphragm pump according to claim 9, characterized by, The standard database is established by: The audio acquisition module is arranged outside the normal pump body, and the normal operation sound pressure data of the normal pump body is obtained by using the audio acquisition module. The characteristic extraction module extracts the normal operation characteristic data corresponding to the normal operation sound pressure data. The factor analysis unit analyzes the normal operation characteristic data to obtain factor normal characteristic data corresponding to the abnormal factors, and the sound pressure analysis model is used to analyze the factor normal characteristic data to obtain the standard sound pressure data corresponding to each of the abnormal factors. The standard database is established by:
11. The abnormality monitoring method of a reciprocating diaphragm pump according to claim 6, characterized by, The operation characteristic data includes frequency characteristic data, damping characteristic data, time characteristic data, and angle characteristic data, and the abnormal factors include air guide valve failure factors, ball valve failure factors, ball wear factors, diaphragm rupture factors, and ball seat rupture factors.