Monitoring method and system for workshop equipment

Abstract

The present invention relates to the field of workshop equipment fault monitoring, and in particular to a monitoring method and system for workshop equipment. The method comprises: collecting vibration information of workshop equipment; obtaining frequency domain signals according to the vibration information, and extracting high-frequency signals and low-frequency signals in the frequency domain signals according to preset rules; calculating the amplitude spectrum index and power spectrum index of the high-frequency signal and the low-frequency signal; and determining the health status of the workshop equipment according to the amplitude spectrum index and the power spectrum index of the high-frequency signal and the low-frequency signal. The present invention effectively solves the problem that the monitoring method in the prior art is not comprehensive and prone to errors.

Description

Technical Field

[0001] The present invention relates to the field of workshop equipment fault monitoring, and more specifically, to a workshop equipment monitoring method and system. Background Art

[0002] During the operation of mechanical parts, due to wear, imbalance, looseness or other defects, specific vibration patterns will be generated. These vibration signals carry rich information and can reflect the health of workshop equipment. Early vibration monitoring mainly relied on experienced engineers to collect data at predetermined monitoring points through handheld vibration analyzers and then conduct offline analysis. However, this method is limited by manpower, efficiency and timeliness, and cannot meet the high requirements of modern industry for accuracy and efficiency. Current workshop equipment monitoring methods mostly use processing and calculation of high-frequency signals or low-frequency signals, or process the frequency of signals, and cannot integrate data from multiple dimensions to monitor workshop equipment.

[0003] At present, the application document with the publication number CN118081479A discloses an online monitoring method for machine tool operation faults. The method predicts and monitors the machine tool operation fault status based on the effective fluctuation sequence of the vibration sequence. Specifically, it discloses: obtaining the target machine tool vibration sequence and the reference machine tool vibration sequence; the target machine tool vibration sequence contains several vibration frequencies; obtaining several vibration subsequences from the vibration sequence and performing effective fluctuation evaluation on them, and obtaining the machine tool operation fault monitoring result by performing comprehensive processing on the effective fluctuation evaluation. The above fault monitoring method essentially only considers the vibration frequency, and monitors the workshop equipment by evaluating the frequency. Therefore, the monitoring method is relatively one-sided and prone to errors in the monitoring results. Summary of the invention

[0004] In order to solve the problem that the monitoring methods in the prior art are incomplete and prone to errors, the present invention provides solutions in the following aspects.

[0005] In a first aspect, the present invention provides a monitoring method for workshop equipment, comprising: collecting vibration information of workshop equipment; obtaining frequency domain signals according to the vibration information, and extracting high-frequency signals and low-frequency signals in the frequency domain signals according to preset rules; calculating amplitude spectrum indicators and power spectrum indicators of the high-frequency signals and low-frequency signals, wherein the amplitude spectrum indicator of the high-frequency signal is a weighted sum of the centroid frequency, root mean square frequency, and frequency standard deviation of the amplitude spectrum of the high-frequency signal, and the power spectrum indicator of the high-frequency signal is a weighted sum of the centroid frequency, root mean square frequency, and frequency standard deviation of the power spectrum density of the high-frequency signal, and the weight coefficients of the centroid frequency, root mean square frequency, and frequency standard deviation of the amplitude spectrum of the high-frequency signal are the same as the weight coefficients of the centroid frequency, root mean square frequency, and frequency standard deviation of the power spectrum density of the high-frequency signal, which are the first coefficients. , the second coefficient and the third coefficient The amplitude spectrum index of the low-frequency signal is the weighted sum of the centroid frequency, root mean square frequency, and frequency standard deviation of the low-frequency signal amplitude spectrum. The power spectrum index of the low-frequency signal is the weighted sum of the centroid frequency, root mean square frequency, and frequency standard deviation of the power spectrum density of the low-frequency signal. The weight coefficients of the centroid frequency, root mean square frequency, and frequency standard deviation of the low-frequency signal amplitude spectrum are the same as the weight coefficients of the centroid frequency, root mean square frequency, and frequency standard deviation of the power spectrum density of the low-frequency signal, which is the fourth coefficient. , the fifth coefficient and the sixth coefficient ; Determine the health status of the workshop equipment based on the amplitude spectrum index and power spectrum index of the high-frequency signal and the low-frequency signal.

[0006] The above scheme determines the health status of workshop equipment by integrating high-frequency signals and low-frequency signals, amplitude spectrum and power spectrum density in the vibration information, and uses the center of gravity frequency, root mean square frequency and frequency standard deviation. It can effectively solve the problem of incomplete and error-prone monitoring methods in existing technologies at multiple levels.

[0007] Preferably, the first coefficient , the second coefficient , the third coefficient and the fourth coefficient , the fifth coefficient , the sixth coefficient , specifically including:

[0008] ,

[0009] in, Represents the highest frequency in the high-frequency signal. Represents the lowest frequency in the high-frequency signal. Represents the average frequency of multiple frequencies contained in the high-frequency signal. Represents the highest frequency in the low-frequency signal. Represents the lowest frequency in the low-frequency signal. Indicates the average frequency of multiple frequencies contained in the low-frequency signal.

[0010] Preferably, the collecting of vibration information of workshop equipment then includes: performing noise reduction and completion processing on the vibration information.

[0011] The above scheme reduces noise and completes the data to obtain more accurate vibration information and avoid the influence of noise and individual data errors on the results.

[0012] Preferably, the denoising and completing the vibration information comprises: denoising the vibration information using a wavelet threshold denoising method.

[0013] Preferably, the determining the health status of the workshop equipment according to the amplitude spectrum index and the power spectrum index of the high-frequency signal and the low-frequency signal includes: the health status includes normal, weak fault, medium fault and damage.

[0014] The above scheme grades the health status of workshop equipment, and can shut down the equipment in time when the fault is serious, and temporarily not shut down the equipment when the fault is not serious, waiting for the appropriate time to shut down the equipment for processing, thus avoiding the loss caused by shutting down when the fault is not serious.

[0015] Preferably, the determining the health status of the workshop equipment according to the amplitude spectrum index and the power spectrum index of the high-frequency signal and the low-frequency signal then includes: issuing different warning signals according to different health statuses of the workshop equipment.

[0016] The above scheme can warn the health status of the workshop equipment through early warning signals, which can promptly and clearly remind the person in charge of the equipment and avoid more serious damage to the workshop equipment.

[0017] Preferably, determining the health status of workshop equipment based on the amplitude spectrum index and power spectrum index of the high-frequency signal and the low-frequency signal includes: calculating the comprehensive deviation of the high-frequency signal based on the amplitude spectrum index and the power spectrum index of the high-frequency signal to determine the high-frequency health status of the workshop equipment; calculating the comprehensive deviation of the low-frequency signal based on the amplitude spectrum index and the power spectrum index of the low-frequency signal to determine the low-frequency health status of the workshop equipment; determining the health status of the workshop equipment based on the high-frequency health status and the low-frequency health status of the workshop equipment.

[0018] The above scheme determines the health status of the device by combining the high-frequency health status and the low-frequency health status, thereby avoiding the error caused by considering only a single frequency.

[0019] In a second aspect, the present invention further provides a monitoring system for workshop equipment, comprising: a memory and a processor, wherein a computer program is stored in the memory, and the processor executes the computer program to implement the above-mentioned monitoring method for workshop equipment.

[0020] The beneficial effects of the present invention are as follows: by integrating the high-frequency signals and low-frequency signals, amplitude spectrum and power spectrum density in the vibration information, and using the center of gravity frequency, root mean square frequency and frequency standard deviation to determine the health status of the workshop equipment, the problem that the workshop equipment fault monitoring method in the prior art is incomplete and prone to errors can be effectively solved at multiple levels. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0022] Figure 1 is a flow chart of a monitoring method for workshop equipment provided by an embodiment of the present invention;

[0023] Figure 2 The present invention provides a monitoring system for workshop equipment. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical invention in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0025] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0026] Figure 1 is a flow chart of a method for monitoring workshop equipment according to an embodiment of the present invention, comprising the following steps:

[0027] S101, collecting vibration information of workshop equipment;

[0028] In modern industrial production, the stable operation of workshop equipment is crucial to the production efficiency and product quality of enterprises. However, various faults are inevitable in the long-term operation of workshop equipment, such as bearing wear, loose gears, mechanical friction, etc. These faults will cause abnormal vibration of workshop equipment. In order to detect and solve these problems in time, workshop equipment vibration monitoring technology came into being and became a key means to ensure the stability of industrial operation.

[0029] Therefore, by collecting the vibration information of the workshop equipment and monitoring the vibration of the workshop equipment in real time, it is possible to promptly discover and solve potential faults and problems of the workshop equipment, thereby improving the reliability and service life of the workshop equipment.

[0030] The collected vibration information often contains some noise or lacks some information. Therefore, in some embodiments, after collecting the vibration information of the workshop equipment, the vibration information needs to be denoised and completed. The present invention uses the wavelet threshold denoising method to denoise the vibration information. The wavelet threshold denoising method has obvious advantages in processing vibration signals. It can better process the complex changes in the vibration signal caused by workshop equipment failure, effectively separate noise and signal, and retain the main features of the signal while removing noise.

[0031] S102, acquiring a frequency domain signal according to the vibration information, and extracting a high-frequency signal and a low-frequency signal from the frequency domain signal according to a preset rule;

[0032] In general, the vibration information directly obtained is a time domain signal, which can be converted into a frequency domain signal using Fourier transform. The frequency domain signal contains signals of multiple frequencies. In the present invention, it is necessary to extract high-frequency signals and low-frequency signals from the signals of multiple frequencies according to preset rules. The high-frequency signal and the low-frequency signal are not signals with a fixed frequency range, but are related to the entire frequency domain signal. For example, if the entire frequency domain signal includes a signal with a frequency of 20-100Hz, 20-30Hz can be divided into low-frequency signals, and 90-100Hz can be divided into high-frequency signals. If the entire frequency domain signal includes a signal with a frequency of 500-3000Hz, 500-800Hz can be divided into low-frequency signals, and 2600-3000Hz can be divided into high-frequency signals.

[0033] In workshop equipment, high-frequency vibration signals and low-frequency vibration signals can reflect different health states. High-frequency vibration signals are usually related to local failures of mechanical components, such as bearing damage or gear problems. These problems will produce higher-frequency vibration signals because they are usually caused by fast-moving parts. Low-frequency vibration signals may be related to problems with the overall structure, such as foundation instability or imbalance in the overall operation of the workshop equipment. These problems will produce lower-frequency but larger-amplitude signals. In addition, in some embodiments, different degrees of damage to the bearings of workshop equipment will be reflected differently in the high and low frequencies of the frequency domain signals of the vibration information. Early damage to the bearings (weak faults) will first be reflected in the high-frequency signal, and as the degree of damage increases (strong faults), the low-frequency signal will also change.

[0034] In some embodiments, different workshop equipment needs to pay attention to different high and low frequency signals. For example, when the equipment in workshop A is working normally, the vibration frequency is 100-1000Hz, then the low frequency signal threshold can be set at 0-100Hz, and the high frequency signal threshold can be set at 1000-1200Hz. When the equipment in workshop B is working normally, the vibration frequency is 30-800Hz, then the low frequency signal threshold can be set at 0-30Hz, and the high frequency signal threshold can be set at 800-950Hz. Therefore, the preset rules described in the present invention can set the threshold according to the characteristics of the workshop equipment, and divide the frequency domain signal into high frequency signal and low frequency signal according to the threshold.

[0035] S103, calculating the amplitude spectrum index and the power spectrum index of the high-frequency signal and the low-frequency signal;

[0036] The amplitude spectrum index of the high-frequency signal is the weighted sum of the centroid frequency, root mean square frequency, and frequency standard deviation of the high-frequency signal amplitude spectrum. The power spectrum index of the high-frequency signal is the weighted sum of the centroid frequency, root mean square frequency, and frequency standard deviation of the high-frequency signal power spectrum density. The weight coefficients of the centroid frequency, root mean square frequency, and frequency standard deviation of the high-frequency signal amplitude spectrum are the same as the weight coefficients of the centroid frequency, root mean square frequency, and frequency standard deviation of the high-frequency signal power spectrum density, which are the first coefficients. , the second coefficient and the third coefficient The amplitude spectrum index of the low-frequency signal is the weighted sum of the centroid frequency, root mean square frequency, and frequency standard deviation of the low-frequency signal amplitude spectrum. The power spectrum index of the low-frequency signal is the weighted sum of the centroid frequency, root mean square frequency, and frequency standard deviation of the power spectrum density of the low-frequency signal. The weight coefficients of the centroid frequency, root mean square frequency, and frequency standard deviation of the low-frequency signal amplitude spectrum are the same as the weight coefficients of the centroid frequency, root mean square frequency, and frequency standard deviation of the power spectrum density of the low-frequency signal, which is the fourth coefficient. , the fifth coefficient and the sixth coefficient .

[0037] When different faults occur in workshop equipment, they are generally reflected in the high or low frequency of the signal, and may also be reflected in the different aspects of the center frequency, root mean square frequency and frequency standard deviation of the signal amplitude spectrum and power spectrum density. For example, the amplitude spectrum mainly reflects the amplitude information of each frequency component of the signal, and can directly show the amplitude characteristics of the vibration of the workshop equipment. Mechanical wear or looseness of workshop equipment may cause the center frequency of the amplitude spectrum to shift, thereby reflecting the existence and development of workshop equipment faults; bearing faults may introduce new high-frequency components, resulting in an increase in the root mean square frequency of the amplitude spectrum; mechanical looseness or imbalance may cause an increase in low-frequency components, affecting the root mean square frequency of the amplitude spectrum; looseness or falling off of workshop equipment parts may introduce a variety of new frequency components, increasing the standard deviation of the amplitude spectrum frequency; and certain specific types of faults may be concentrated in a specific frequency range, reducing the standard deviation of the amplitude spectrum frequency. The power spectrum density reflects the power distribution of the signal at each frequency, and pays more attention to the frequency characteristics of the signal energy. A bearing failure may push the power spectrum density distribution to the high-frequency region, and a gear failure may cause the root mean square frequency of the power spectrum density to increase. An increase in the standard deviation of the power spectrum density frequency may indicate that a workshop equipment failure causes the energy to be dispersed at more frequencies (such as a complex mechanical failure). Therefore, after dividing the high-frequency signal and the low-frequency signal, attention should also be paid to the center frequency, root mean square frequency, and frequency standard deviation of the signal amplitude spectrum and the power spectrum density. By paying attention to the center frequency, root mean square frequency, and frequency standard deviation of the high-frequency signal and the low-frequency signal, the present invention can timely discover hidden faults to the greatest extent possible, while also avoiding monitoring errors caused by focusing only on a single frequency signal or a single factor of the signal.

[0038] The present invention uses the amplitude spectrum index of high-frequency signal and low-frequency signal , and power spectrum index , At the same time, the centroid frequency, root mean square frequency, and frequency standard deviation of the amplitude spectrum and power spectrum density are described. The specific formula is: ,

[0039] ,

[0040] ,

[0041] ,

[0042] Among them, "high" represents high-frequency signals, and "low" represents low-frequency signals. Both high-frequency signals and low-frequency signals contain signals of multiple frequencies. In the above formula, represents the signal frequency in the high-frequency signal, It represents the amplitude spectrum corresponding to a certain frequency signal in the high-frequency signal. The calculation of the signal amplitude spectrum belongs to the well-known technology and will not be described in detail here. Indicates the average frequency of multiple frequency signals contained in the high-frequency signal. It represents the power spectrum density corresponding to a certain frequency signal in the high-frequency signal. Calculating the power spectrum density of the signal is a well-known technology and will not be described in detail here. It represents the centroid frequency of the high-frequency signal amplitude spectrum. represents the RMS frequency of the high-frequency signal amplitude spectrum, represents the frequency standard deviation of the high-frequency signal amplitude spectrum, It represents the centroid frequency of the power spectrum density of the high-frequency signal, represents the RMS frequency of the power spectral density of the high-frequency signal, Represents the frequency standard deviation of the power spectral density of the high-frequency signal, , , Indicates the weight coefficients corresponding to the center frequency, root mean square frequency, and frequency standard deviation in the high-frequency signal, namely, the first coefficient, the second coefficient, and the third coefficient. , , , , , , , , , , , The meaning of is not elaborated here.

[0043] In some embodiments, the , , and , , ,include:

[0044] ,

[0045] in, Represents the highest frequency in the high-frequency signal. Represents the lowest frequency in the high-frequency signal. Represents the average frequency of multiple frequencies contained in the high-frequency signal. Similarly, , , The meaning of is not elaborated here.

[0046] S104: Determine the health status of the workshop equipment according to the amplitude spectrum index and the power spectrum index of the high-frequency signal and the low-frequency signal.

[0047] Traditional fault identification only outputs two states: normal and fault. In one embodiment of the present invention, multiple states including normal, weak fault, medium fault and damage can be identified. By performing more detailed classification of the health status of workshop equipment, the equipment can be shut down in time for processing when the fault is serious, and the equipment can be temporarily stopped when the fault is not serious, waiting for the appropriate time to shut down for processing, thus avoiding losses caused by shutdown when the fault is not serious.

[0048] In some embodiments, determining the health status of workshop equipment based on the amplitude spectrum indicators and power spectrum indicators of the high-frequency signal and the low-frequency signal includes: calculating the comprehensive deviation of the high-frequency signal based on the amplitude spectrum indicators and the power spectrum indicators of the high-frequency signal to determine the high-frequency health status of the workshop equipment; calculating the comprehensive deviation of the low-frequency signal based on the amplitude spectrum indicators and the power spectrum indicators of the low-frequency signal to determine the low-frequency health status of the workshop equipment; determining the health status of the workshop equipment based on the high-frequency health status and the low-frequency health status of the workshop equipment.

[0049] For example, the comprehensive deviation of the high-frequency signal is calculated according to the amplitude spectrum index and the power spectrum index of the high-frequency signal, which can be calculated by the following formula:

[0050] , , ,in, , are the amplitude spectrum index and power spectrum index of the above-mentioned high-frequency signal, It is the minimum value of the amplitude spectrum index and power spectrum index range corresponding to the high-frequency signal of the workshop equipment when it is normal. , It is the maximum value of the amplitude spectrum index and power spectrum index range that normally corresponds to the high-frequency signal of the workshop equipment. and are the index deviations of the amplitude spectrum and power spectrum in the high-frequency signal, It is the comprehensive deviation in high-frequency signal.

[0051] Preset Threshold , according to the comprehensive deviation of high-frequency signal and threshold The relationship between the high-frequency health status of the workshop equipment is determined by: .

[0052] Similarly, the low-frequency health status of workshop equipment can be calculated, which will not be elaborated here.

[0053] After obtaining the high-frequency health status and low-frequency health status of the workshop equipment, the health status of the workshop equipment can be finally determined by combining the two. In one embodiment, if the high frequency is normal and the low frequency is normal, the health status of the workshop equipment is normal; if the high frequency is normal and the low frequency is weak fault, the high frequency is weak fault and the low frequency is normal, or the high frequency is normal and the low frequency is medium fault, the health status of the workshop equipment is weak fault; if the high frequency is damaged and the low frequency is damaged, the high frequency is damaged and the low frequency is medium fault, the high frequency is damaged and the low frequency is weak fault, the high frequency is medium fault and the low frequency is damaged, or the high frequency is weak fault and the low frequency is damaged, the health status of the workshop equipment is damaged; if the other combinations are combined, the health status of the workshop equipment is medium fault.

[0054] After determining the health status of the workshop equipment, the present invention can also issue different warning signals according to the different health status of the workshop equipment. For example, if the workshop equipment is damaged, a red light will be on and a rapid alarm will sound, if a medium fault occurs, a yellow light will be on and a slow alarm will sound, if a weak fault occurs, a yellow light will be on without an alarm sound, and if the equipment is normal, a green light will be on without an alarm sound. Maintenance personnel can formulate different maintenance plans based on different warning signals.

[0055] In workshop equipment, high-frequency vibration signals and low-frequency vibration signals can reflect different health states of workshop equipment, and the center frequency, root mean square frequency, and frequency standard deviation of the amplitude spectrum and power spectrum density can also reflect different aspects of workshop equipment failure. Therefore, the present invention determines the health state of workshop equipment by integrating the high-frequency signal and low-frequency signal, amplitude spectrum and power spectrum density in the vibration information, and using the center frequency, root mean square frequency and frequency standard deviation, which can effectively solve the problem that the workshop equipment failure monitoring method in the prior art is not comprehensive and prone to errors from multiple levels.

[0056] The present invention also provides a monitoring system for workshop equipment. Figure 2 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a workshop equipment monitoring method described in the present invention is implemented.

[0057] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0058] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a workshop device or accessible or connectable to a workshop device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0059] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0060] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternative inventions to the embodiments of the present invention described herein may be employed.

Claims

1. A method for monitoring workshop equipment, characterized in that: include: Collect vibration information of workshop equipment; According to the vibration information, a frequency domain signal is acquired, and a high-frequency signal and a low-frequency signal in the frequency domain signal are extracted according to a preset rule, wherein the preset rule is to set a threshold value according to the characteristics of the workshop equipment; Calculate the amplitude spectrum index and power spectrum index of the high-frequency signal and the low-frequency signal, the amplitude spectrum index of the high-frequency signal is the weighted sum of the centroid frequency, root mean square frequency, and frequency standard deviation of the high-frequency signal amplitude spectrum, the power spectrum index of the high-frequency signal is the weighted sum of the centroid frequency, root mean square frequency, and frequency standard deviation of the high-frequency signal power spectrum density, the weight coefficients of the centroid frequency, root mean square frequency, and frequency standard deviation of the high-frequency signal amplitude spectrum and the centroid frequency, root mean square frequency, and frequency standard deviation of the high-frequency signal power spectrum density are the same as the weight coefficients of the centroid frequency, root mean square frequency, and frequency standard deviation of the high-frequency signal power spectrum density, which are the first coefficients , the second coefficient and the third coefficient The amplitude spectrum index of the low-frequency signal is the weighted sum of the centroid frequency, root mean square frequency, and frequency standard deviation of the low-frequency signal amplitude spectrum. The power spectrum index of the low-frequency signal is the weighted sum of the centroid frequency, root mean square frequency, and frequency standard deviation of the power spectrum density of the low-frequency signal. The weight coefficients of the centroid frequency, root mean square frequency, and frequency standard deviation of the low-frequency signal amplitude spectrum are the same as the weight coefficients of the centroid frequency, root mean square frequency, and frequency standard deviation of the power spectrum density of the low-frequency signal, which is the fourth coefficient. , the fifth coefficient and the sixth coefficient ; Determining the health status of the workshop equipment according to the amplitude spectrum index and power spectrum index of the high-frequency signal and the low-frequency signal, including: calculating the comprehensive deviation of the high-frequency signal according to the amplitude spectrum index and the power spectrum index of the high-frequency signal to determine the high-frequency health status of the workshop equipment; calculating the comprehensive deviation of the low-frequency signal according to the amplitude spectrum index and the power spectrum index of the low-frequency signal to determine the low-frequency health status of the workshop equipment; determining the health status of the workshop equipment according to the high-frequency health status and the low-frequency health status of the workshop equipment; The comprehensive deviation of the high-frequency signal is calculated based on the amplitude spectrum index and the power spectrum index of the high-frequency signal, and satisfies the following relationship: ， ， ， in, , It is the amplitude spectrum index and power spectrum index of high-frequency signal. It is the minimum value of the amplitude spectrum index and power spectrum index range corresponding to the high-frequency signal of the workshop equipment when it is normal. , It is the maximum value of the amplitude spectrum index and power spectrum index range that normally corresponds to the high-frequency signal of the workshop equipment. and are the index deviations of the amplitude spectrum and power spectrum in the high-frequency signal, It is the comprehensive deviation in high-frequency signal; preset threshold , according to the comprehensive deviation of high-frequency signal and threshold The high-frequency health status of the workshop equipment is determined by the relationship; the low-frequency health status of the workshop equipment is calculated similarly.

2. The workshop equipment monitoring method according to claim 1, characterized in that: The first coefficient , the second coefficient , the third coefficient and the fourth coefficient , the fifth coefficient , the sixth coefficient , specifically including: ， in, Represents the highest frequency in the high-frequency signal. Represents the lowest frequency in the high-frequency signal. Indicates the average frequency of multiple frequencies contained in the high-frequency signal. Represents the highest frequency in the low-frequency signal. Represents the lowest frequency in the low-frequency signal. Indicates the average frequency of multiple frequencies contained in the low-frequency signal.

3. The workshop equipment monitoring method according to claim 1, characterized in that: The collecting of vibration information of workshop equipment then includes: The vibration information is subjected to noise reduction and completion processing.

4. The workshop equipment monitoring method according to claim 3, characterized in that: The noise reduction and completion processing of the vibration information includes: The vibration information is denoised using a wavelet threshold denoising method.

5. The method for monitoring workshop equipment according to claim 1, characterized in that: The determining the health status of the workshop equipment according to the amplitude spectrum index and the power spectrum index of the high-frequency signal and the low-frequency signal includes: The health status includes normal, weak fault, moderate fault, and damaged.

6. The method for monitoring workshop equipment according to claim 5, characterized in that: The step of determining the health status of the workshop equipment according to the amplitude spectrum index and the power spectrum index of the high-frequency signal and the low-frequency signal comprises: Different early warning signals are issued according to different health conditions of the workshop equipment.

7. A monitoring system for workshop equipment, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the workshop equipment monitoring method according to any one of claims 1 to 6.

Images