Air compressor monitoring method and monitoring system

Abstract

The invention provides an air compressor monitoring method and system, and the method comprises the following steps: S1, installing a sensor at a designated position; s2, collecting sensor data at different positions; s3, analyzing and judging the data acquired in the step S2; s4, analyzing the data measured in the step S3; s5, the system gives an alarm and reminds fault information; s6, the air compressor is shut down to be overhauled; and S7, ending monitoring. The first data unit and the second data unit are arranged, the first data unit and the second data unit which are used for collecting the positions of main components of the air compressor are monitored, and when temperature and pressure data of the first data unit are abnormal, analysis and judgment are carried out by combining voice data of the second data unit; and the accuracy of judging the fault part is improved. Besides, under the condition that the voice data are normal, the fault part is adjusted and then judged, and therefore the situation that the air compressor is damaged due to the fact that the part breaks down and is not processed is avoided.

Description

Technical Field

[0001] The present invention relates to the field of air compressor monitoring technology, and in particular to an air compressor monitoring method. In addition, the present invention also relates to a monitoring system using the air compressor monitoring method. Background Art

[0002] With the continuous development of industrial production, the development of air compressor technology has received more and more attention. Under the traditional management model, the operating status of the air compressor mainly relies on manual inspection to find abnormalities. Due to the lack of effective data analysis methods, the energy efficiency of the air compressor is low and energy waste is serious.

[0003] The main functions of the air compressor monitoring system include real-time data acquisition, status monitoring and alarm, remote monitoring, fault diagnosis and prediction, energy efficiency management, maintenance reminders and management, data reporting and analysis, and authority management and auditing. In the prior art, there is an air compressor data acquisition system that integrates data acquisition, transmission, processing, and analysis. It accesses the air compressor PLC through an industrial intelligent gateway for data acquisition, and uploads it to the cloud platform or host computer in real time through 5G / 4G / WIFI / Ethernet and other methods. These functions work together to achieve comprehensive monitoring and management of the operating status of the air compressor.

[0004] First of all, air compressor monitoring can avoid safety accidents. By real-time monitoring of the operating status of the air compressor, equipment abnormalities such as abnormal pressure and excessive temperature can be discovered in time, thereby avoiding sudden equipment shutdown or other conditions and ensuring the safe production of the enterprise.

[0005] Secondly, air compressor monitoring helps reduce maintenance costs. Through real-time monitoring and data analysis, the maintenance needs of the equipment can be predicted, and maintenance or parts can be replaced in advance to avoid equipment damage due to untimely maintenance, thereby reducing maintenance costs.

[0006] In addition, air compressor monitoring can also improve manpower utilization. Through the automated monitoring system, the frequency of manual inspections can be reduced, labor costs can be reduced, and the response speed to equipment failures can be improved to ensure the continuous operation of the production line.

[0007] In practical applications, a major problem faced by air compressor monitoring systems is the lack of timely and accurate data support, which makes energy consumption analysis and regulation slow. Although the monitoring system in the existing technology collects and monitors the equipment status, working parameters and energy consumption data, and compares and analyzes the monitored data with the preset threshold, it can then make response measures such as remote adjustment, fault warning, and manual maintenance.

[0008] Among them, the data collection of working parameters is mostly the host temperature, exhaust pressure, instantaneous flow, cumulative flow, operating status, operating time, etc. The main collection method is to use sensors to collect data, convert the collected information into digital signals, and quickly locate and diagnose and take measures by sorting and analyzing the collected data in the data center or host computer.

[0009] In reality, when the monitoring system identifies abnormal data collected, it will automatically alarm and take measures to shut down the machine and wait for maintenance. However, since the motion data of the air compressor is a variable, the temperature data abnormality caused by poor terminal contact, sensor failure, etc., rather than problems with the air compressor components, will cause misjudgment, resulting in the air compressor shutting down and unnecessary production suspension. Summary of the invention

[0010] In view of this, the present invention aims to propose an air compressor monitoring method to obtain accurate collection data while avoiding air compressor shutdown due to system misjudgment.

[0011] To achieve the above object, the technical solution of the present invention is achieved as follows:

[0012] A method for monitoring an air compressor comprises the following steps:

[0013] S1, install the sensor at the specified location;

[0014] S2, collecting sensor data at different locations, the sensor data including a first data unit and a second data unit, the first data unit including a first temperature value and a first pressure value, and the second data unit including voice data;

[0015] S3, analyzing and judging the data collected in S2;

[0016] S31, analyzing the first data unit in S2 to determine whether the measured first temperature value or first pressure value is abnormal;

[0017] S32, processing and analyzing the second data unit in S2, and determining whether the voice data is abnormal;

[0018] S4, analyzing the first temperature value, the first pressure value, and the voice data measured in S3;

[0019] The analysis steps are as follows:

[0020] S41, when one of the first temperature value and the first pressure value measured in S31 and S32 is abnormal, and the voice data is abnormal, execute S5;

[0021] S42, when the first temperature value or the first pressure value obtained in S31 is abnormal, and the voice data is normal, adjust the fault location and make a re-judgment, and execute S5 when it is determined that the data is abnormal;

[0022] S5, the system alarms and reminds the fault information, and manually checks whether the sensor of the first data unit is invalid. If it is not invalid, execute S6;

[0023] S6, the air compressor is shut down for maintenance;

[0024] S7, end monitoring.

[0025] Further, S42 includes the following steps:

[0026] S421, identifying abnormal data of the first temperature value and the first pressure value, locking the abnormal parts, and making corresponding adjustments;

[0027] S422, collecting again the second pressure value and the second temperature value of the location of the abnormal data in S421;

[0028] S423, determining whether the measured second pressure value and second temperature value are abnormal. When the measured data are normal, no processing is performed. When the measured data are abnormal, executing S5.

[0029] Furthermore, the installation positions of the sensors in S1 include an intake pipe, an exhaust pipe, a power system, a cylinder block, and a cooling system.

[0030] Further, S32 includes the following steps:

[0031] S321, collecting voice data at the sensor installation location in step 3;

[0032] S322, filtering the voice data collected in S321 using a filtering algorithm;

[0033] S323, performing equipment failure predictive analysis based on the filtered voice data to obtain a prediction result

[0034] S324, setting a prediction result threshold, and judging the prediction structure obtained in S323 The value is compared with the threshold value, and if it exceeds the numerical range of the threshold value, it is determined to be abnormal.

[0035] Furthermore, in S322, the filtering method adopts a nanofiltration algorithm, and the calculation formula is as follows:

[0036]

[0037] in, n(t) and y(t) are the original speech signal, noise and speech data contaminated by noise in the i-th frame respectively;

[0038] s(t)=y(t)*H(n);

[0039] Among them, H(n) is a linear filter and s(t) is the pure original speech signal.

[0040] Further, in S323, the equipment failure predictive analysis includes the following steps:

[0041] S3231, calculate the air compression ratio of the air compressor,

[0042] That is (v1 / v2) (γ-1) ;

[0043] Where v1 is the inlet air volume, V2 is the outlet air volume, and γ is the adiabatic index of the air;

[0044] S3232, by measuring the inlet and outlet pressures of the tested component and combining the air compression ratio, determine whether there is a large difference in pressure conversion by the following formula;

[0045] (v1 / v2) (γ-1) p2-p1;

[0046] Where p1 is the inlet pressure and p2 is the outlet pressure;

[0047] S3233, the soundprint decibel d2 collected by the acquisition sensor at time T and the standard soundprint decibel d1 are compared and analyzed, and the estimated value after linear filtering is combined for comprehensive analysis to obtain the fault prediction model:

[0048]

[0049] represents the actual value of the prediction result at time t, and s(t) is the pure original speech signal calculated in step S322.

[0050] Further, in S324, when the actual value of the prediction result When the threshold value is not exceeded, a prediction analysis curve chart is drawn and maintenance conditions are set;

[0051] When the actual value of the predicted result If the threshold is exceeded three times, it is determined to be abnormal.

[0052] Compared with the prior art, the present invention has the following advantages:

[0053] The air compressor monitoring method of the present invention monitors the first data unit and the second data unit collected from the positions of the main components of the air compressor by setting the first data unit and the second data unit. When the temperature and pressure data of the first data unit are abnormal, the voice data of the second data unit are combined for analysis and judgment to increase the accuracy of the fault location judgment. In addition, the fault location is adjusted and then judged when the voice data is normal, thereby avoiding the situation where the air compressor is damaged due to the failure of the component and not being handled.

[0054] In addition, the air compressor monitoring method of the present invention combines the superposition judgment of abnormal data in the traditional monitoring system with the sound collection in actual applications to improve the judgment accuracy. And when there is no abnormality in the voice data and there are abnormalities in the temperature and pressure, the location where the abnormal data occurs is adjusted. If the data is abnormal after adjustment, it means that there is a hidden danger of failure in this location, which can be checked on weekends. If the data is still abnormal after adjustment, the system alarm is used to eliminate the false stop by manually checking the sensor. This method effectively avoids production stoppages caused by misjudgment of the monitoring system and ensures the operational stability of the air compressor.

[0055] Another object of the present invention is to provide an air compressor monitoring system, which uses the air compressor monitoring method as described above to monitor the air compressor, and the system includes:

[0056] Controller, data receiver, sensor, display module and alarm;

[0057] The output end, display module and alarm of the data receiving end are respectively connected to the controller; the controller is used to control the operation or stop of the air compressor, and adjust various working modes and parameters of the air compressor.

[0058] Furthermore, the sensor includes a pressure sensor, a temperature sensor, a sound collector, a flow sensor, a vibration sensor, etc.

[0059] Furthermore, the sound collector includes a mounting frame, a sound collection mainboard arranged on the mounting frame, and a noise-proof component.

[0060] The air compressor monitoring system described in the present invention adopts the air compressor monitoring method as described above. Before the air compressor needs to be shut down due to data abnormalities, a judgment step of voiceprint collection is added. When the temperature and pressure data are abnormal, the voiceprint is judged again, thereby further improving the accuracy of discovering the fault location and avoiding the phenomenon of the air compressor being forced to stop accidentally due to data abnormalities caused by faults such as temperature and pressure sensors. BRIEF DESCRIPTION OF THE DRAWINGS

[0061] The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the accompanying drawings:

[0062] Figure 1 This is a flow chart of the air compressor monitoring method according to an embodiment of the present invention;

[0063] Figure 2 As described in the embodiments of the present invention;

[0064] Figure 3 The figure is a cross-sectional schematic diagram of the sound collector according to the embodiment of the present invention.

[0065] Description of reference numerals:

[0066] 1. Mounting frame; 2. Collection mainboard; 3. Windproof cotton; 4. PEEK film; 5. Connecting plate; 6. Sealing ring;

[0067] 101. Upper cover; 102. Lower cover. DETAILED DESCRIPTION

[0068] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features in the embodiments may be combined with each other.

[0069] In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper", "lower", "inner", "back", etc. are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first" and "second" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0070] In addition, in the description of the present invention, unless otherwise clearly defined, the terms "installed", "connected", "connected", and "connector" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood in combination with specific circumstances.

[0071] The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments.

[0072] This embodiment relates to an air compressor monitoring method, which includes the following steps.

[0073] S1, install sensors at designated locations; the sensor installation locations of this embodiment include the air intake pipeline, exhaust pipeline, power system, cylinder body, and cooling system. Common faults of air compressors, such as excessively high exhaust temperature of the air compressor, air compressor stop during operation, low exhaust pressure, abnormal sound of the air compressor, etc., can all be monitored by temperature, pressure, and sound. Therefore, temperature sensors, pressure sensors, and sound collectors are set at the above-mentioned installation locations.

[0074] The pressure value described in this embodiment is the air pressure value. Of course, the voltage, current and other data also need to be monitored in the monitoring system. The monitoring of the electrical part is the same as that in the prior art and is not limited here.

[0075] In step S2, it is necessary to collect sensor data at different locations, the sensor data includes a first data unit and a second data unit, the first data unit includes a first temperature value and a first pressure value, and the second data unit includes voice data.

[0076] In step S3, the data collected in S2 is analyzed and judged;

[0077] S31, analyzing the first data unit in S2 to determine whether the measured first temperature value or the first pressure value is abnormal. Specifically, temperature thresholds and pressure thresholds of different components are set in the system, and when the measured first temperature value and the first pressure value exceed the corresponding thresholds, it is a data abnormal state.

[0078] S32, processing and analyzing the second data unit in S2, and determining whether the voice data is abnormal.

[0079] S32 includes the following steps:

[0080] S321, collecting voice data at the sensor installation location in step 3;

[0081] S322, filtering the voice data collected in S321 using a filtering algorithm;

[0082] In S322, the filtering method is a nanofiltration algorithm, and the calculation formula is as follows:

[0083]

[0084] in, n(t) and y(t) are the original speech signal, noise and speech data contaminated by noise in the i-th frame respectively;

[0085] s(t)=y(t)*H(n);

[0086] Among them, H(n) is a linear filter and s(t) is the pure original speech signal.

[0087] Specifically, the acquisition sensor includes a sound collector, a temperature sensor, a pressure sensor, etc. The speech data collected by the acquisition sensor is a noisy speech signal y(t), which is obtained from the noise n(t) and the original speech signal of the i-th frame. The estimated value s(t) is filtered by a linear filter, which is the pure original speech signal separated after filtering. This can ensure that the speech data is more accurate and reduce the probability of misjudgment.

[0088] As shown in the following table, in this embodiment, given speech data collection at five different detection positions, H(n) is about 0.6, and after estimation, the following table is obtained to obtain pure original speech signals at different time points:

[0089] Time step y(t) s(t) 1 0.6 0.36 2 0.5 0.3 3 0.4 0.24 4 0.3 0.18 5 0.2 0.12

[0090] S323, performing equipment failure predictive analysis based on the filtered voice data to obtain a prediction result

[0091] In S323, the equipment failure predictive analysis includes the following steps:

[0092] S3231, calculate the air compression ratio of the air compressor,

[0093] That is (v1 / v2) (γ-1) ;

[0094] Where v1 is the inlet air volume, V2 is the outlet air volume, and γ is the adiabatic index of the air;

[0095] S3232, by measuring the inlet and outlet pressures of the tested component and combining the air compression ratio, determine whether there is a large difference in pressure conversion by the following formula;

[0096] (v1 / v2) (γ-1) p2-p1;

[0097] Where p1 is the inlet pressure and p2 is the outlet pressure;

[0098] It should be pointed out that the above-mentioned p1 and p2 are the inlet and outlet pressures of the above-mentioned intake pipe, exhaust pipe, power system, cylinder block, and cooling system.

[0099] S3233, compare and analyze the soundprint decibel d2 collected by the acquisition sensor at time T and the standard soundprint decibel d1, and perform comprehensive analysis based on the estimated value obtained after linear filtering to obtain a fault prediction model:

[0100]

[0101] represents the actual value of the prediction result at time t, and s(t) is the pure original speech signal calculated in step S322.

[0102] S324, setting a prediction result threshold, and judging the prediction structure obtained in S323 The value is compared with the threshold and is considered abnormal if it exceeds the threshold value range.

[0103] In S324, when the actual value of the prediction result When the threshold value is not exceeded, a prediction analysis curve is drawn and maintenance conditions are set;

[0104] When the predicted result is actually If the value exceeds the threshold three times, it is considered abnormal.

[0105] In the specific process, Figure 2 As shown in the figure, the data of a certain air compressor power system is measured, v1=1, v2=1.8, p2=3.2, p1=1.0, d1=20, d2=21.6, and the equipment operation stability threshold is set to ±1.5 according to the characteristics of the air compressor equipment. The soundprints of the suction pipeline, exhaust pipeline, power system, cylinder block, and cooling system in five locations are collected and analyzed over a period of time, and the prediction formula is used to obtain the following Figure 2 The analytical curve is shown.

[0106] from Figure 2 From the analysis curve, we can see The operation is in a stable and steady state. At around 28:00 The value suddenly increases. If it exceeds 1.5, it means that there is a problem with the power system.

[0107] In addition, it is also possible to Further analysis is done to obtain the maintenance conditions, which are set based on the daily failure experience of air compressor equipment, such as ±1, ±0.9, ±0.8, ±0.7, ±0.6, ±0.5, etc.

[0108] Furthermore, the equipment optimization strategy can be carried out according to the prediction analysis curve. When it is within the threshold range, the actual value of the prediction result obtained in the device step S3 is The equipment maintenance methods are formulated according to the changes in the equipment. The equipment maintenance methods are set according to the use field, number of times used, use environment and common faults of the air compressor, which will not be repeated here.

[0109] In step S4, the first temperature value, the first pressure value, and the voice data measured in S3 are analyzed.

[0110] The analysis steps are as follows:

[0111] S41, when one of the first temperature value and the first pressure value measured by S31 and S32 is abnormal, and the voice data is abnormal, execute S5;

[0112] S42, when the first temperature value or the first pressure value obtained in S31 is abnormal, and the voice data is normal, the fault location is adjusted and then judged, and S5 is executed when the data is judged to be abnormal;

[0113] Wherein, S42 includes the following steps:

[0114] S421, identify the abnormal data of the first temperature value and the first pressure value, lock the abnormal part, and make corresponding adjustments. Specifically, the adjustment includes pressure adjustment and temperature adjustment. Among them, pressure adjustment is to find that the pressure of the air compressor is too high or too low, and the corresponding adjustment can be made by adjusting the pressure switch or the pressure reducing valve. When adjusting, pay attention to gradually increase or decrease the pressure to avoid excessive pressure fluctuations causing damage to the equipment.

[0115] If the temperature of the above components is found to be too high during temperature adjustment, consider adding cooling equipment or improving ventilation conditions, and at the same time reasonably distribute the workload of the equipment.

[0116] S422, collecting again the second pressure value and the second temperature value of the location of the abnormal data in S421;

[0117] S423, determining whether the measured second pressure value and second temperature value are abnormal. When the measured data are normal, no processing is performed. When the measured data are abnormal, executing S5.

[0118] S5, the system alarms and reminds the fault information, and manually checks whether the sensor of the first data unit is invalid. If it is not invalid, execute S6;

[0119] S6, the air compressor is shut down for maintenance;

[0120] S7, end monitoring.

[0121] The air compressor monitoring method of the present invention monitors the first data unit and the second data unit collected from the positions of the main components of the air compressor by setting the first data unit and the second data unit. When the temperature and pressure data of the first data unit are abnormal, the voice data of the second data unit are combined for analysis and judgment to increase the accuracy of the fault location judgment. In addition, the fault location is adjusted and then judged when the voice data is normal, thereby avoiding the situation where the air compressor is damaged due to the failure of the component and not being handled.

[0122] In addition, the air compressor monitoring method of the present invention combines the superposition judgment of abnormal data in the traditional monitoring system with the sound collection in actual applications to improve the judgment accuracy. And when there is no abnormality in the voice data and there are abnormalities in the temperature and pressure, the location where the abnormal data occurs is adjusted. If the data is abnormal after adjustment, it means that there is a hidden danger of failure in this location, which can be checked on weekends. If the data is still abnormal after adjustment, the system alarm is used to eliminate the false stop by manually checking the sensor. This method effectively avoids production stoppages caused by misjudgment of the monitoring system and ensures the operational stability of the air compressor.

[0123] The present embodiment also relates to an air compressor monitoring system, which uses the above-mentioned air compressor monitoring method to monitor the air compressor, and the system includes:

[0124] Controller, data receiver, sensor, display module and alarm;

[0125] The output end of the data receiving end, the display module and the alarm are respectively connected to the controller; the controller is used to control the operation or stop of the air compressor, and adjust various working modes and parameters of the air compressor.

[0126] The controller adopts a PLC controller, such as a Mitsubishi programmable controller, an AB programmable controller or a Siemens programmable controller. In addition, a wireless transmitter is wirelessly connected to a wireless receiver, and the wireless receiver is connected to a monitoring terminal to notify the personnel or management personnel responsible for maintenance of the monitoring results, thereby realizing a closed loop of monitoring.

[0127] In addition, sensors include pressure sensors, temperature sensors, sound collectors, flow sensors, vibration sensors, etc.

[0128] Specifically, the temperature sensor of this embodiment adopts a thermocouple or a thermistor. The pressure sensor adopts a pressure sensor and a differential pressure sensor. In addition, a liquid level sensor is also provided: used to measure the liquid level of the lubricating oil or cooling water of the air compressor, and common ones include a float liquid level sensor and a capacitive liquid level sensor. Flow sensor: used to measure the gas flow of the air compressor, and common ones include a turbine flow sensor and a differential pressure flow sensor. Gas concentration sensor: used to measure the gas concentration in the exhaust gas of the air compressor, and common ones include an oxygen sensor and a carbon dioxide sensor.

[0129] In addition, a vibration sensor is also provided: used to monitor the vibration of the air compressor so as to detect faults in time. Lubricating oil sensor: used to monitor the quality and use of the lubricating oil of the air compressor so as to replace or maintain it in time. Moisture sensor: used to monitor the moisture content in the exhaust gas of the air compressor so as to remove the moisture in time.

[0130] Furthermore, if Figure 3As shown, the sound collector includes a mounting frame 1, a collection mainboard 2 arranged on the mounting frame 1, and a noise-proof component. The collection mainboard 2 is a MIC mainboard. Among them, a storage space is provided in the mounting frame 1, and the collection mainboard 2 is arranged in the storage space. A windproof cotton 3 is provided on the outside of the collection mainboard 2, and a PEEK film 4 is provided on the outside of the windproof cotton 3. The PEEK film 4 can be used to filter external dust and oil to ensure the collection effect of the sound collector. The windproof cotton 3 is used to reduce noise and further improve the accuracy of sound collection.

[0131] In addition, if Figure 3 As shown, in order to avoid damaging the peek film, a metal mesh is provided outside the peek film. To facilitate assembly, the mounting frame 1 includes an upper cover 101 and a lower cover 102. In order to reduce the impact of noise on the MIC mainboard, a sealing ring 6 is provided between the upper cover 101 and the lower cover 102 to prevent external wind noise from entering the vicinity of the MIC mainboard.

[0132] In addition, if Figure 3 As shown, the mounting frame 1 fixes the sound collector to the corresponding mounting position through bolts and connecting plates 5. For example, the sound collector is fixed to the mounting bolts of the power system engine through the mounting frame 1 and the connecting plate 5. The soundprint collector can also be installed on the intake and exhaust pipes by using a strap, and the temperature sensor and the pressure sensor can be arranged in the pipes.

[0133] The air compressor monitoring system described in the present invention adopts the air compressor monitoring method as described above. Before the air compressor needs to be shut down due to data abnormalities, a judgment step of voiceprint collection is added. When the temperature and pressure data are abnormal, the voiceprint is judged again, thereby further improving the accuracy of discovering the fault location and avoiding the phenomenon of the air compressor being forced to stop accidentally due to data abnormalities caused by faults such as temperature and pressure sensors.

[0134] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring an air compressor, characterized in that: The following steps are included: S1, install the sensor at the specified location; S2, collecting sensor data at different locations, the sensor data including a first data unit and a second data unit, the first data unit including a first temperature value and a first pressure value, and the second data unit including voice data; S3, analyzing and judging the data collected in S2; S31, analyzing the first data unit in S2 to determine whether the measured first temperature value or first pressure value is abnormal; S32, processing and analyzing the second data unit in S2, and determining whether the voice data is abnormal; S4, analyzing the first temperature value, the first pressure value, and the voice data measured in S3; The analysis steps are as follows: S41, when one of the first temperature value and the first pressure value measured in S31 and S32 is abnormal, and the voice data is abnormal, execute S5; S42, when the first temperature value or the first pressure value obtained in S31 is abnormal, and the voice data is normal, adjust the fault location and make a re-judgment, and execute S5 when it is determined that the data is abnormal; S5, the system alarms and reminds the fault information, and manually checks whether the sensor of the first data unit is invalid. If it is not invalid, execute S6; S6, the air compressor is shut down for maintenance; S7, end monitoring.

2. The air compressor monitoring method according to claim 1, characterized in that: S42 includes the following steps: S421, identifying abnormal data of the first temperature value and the first pressure value, locking the abnormal parts, and making corresponding adjustments; S422, collecting again the second pressure value and the second temperature value of the location of the abnormal data in S421; S423, determining whether the measured second pressure value and second temperature value are abnormal. When the measured data are normal, no processing is performed. When the measured data are abnormal, executing S5.

3. The air compressor monitoring method according to claim 1, characterized in that: The installation positions of the sensors in S1 include an intake pipe, an exhaust pipe, a power system, a cylinder block, and a cooling system.

4. The air compressor monitoring method according to claim 3, characterized in that: S32 includes the following steps: S321, collecting voice data at the sensor installation location in step 3; S322, filtering the voice data collected in S321 using a filtering algorithm; S323, performing equipment failure predictive analysis based on the filtered voice data to obtain a prediction result; S324, setting a prediction result threshold, comparing the prediction structure obtained in S323 with the threshold, and determining it as abnormal if it exceeds the numerical range of the threshold.

5. The air compressor monitoring method according to claim 4, characterized in that: In S322, the filtering method adopts a nanofiltration algorithm, and the calculation formula is as follows: ； in, n(t) and y(t) are the original speech signal, noise and speech data contaminated by noise in the i-th frame respectively; s(t)=y(t)*H(n); Among them, H(n) is a linear filter and s(t) is the pure original speech signal.

6. The air compressor monitoring method according to claim 5, characterized in that: In S323, the equipment failure predictive analysis includes the following steps: S3231, calculate the air compression ratio of the air compressor, That is (v1 / v2) (γ-1) ; Where v1 is the inlet air volume, V2 is the outlet air volume, and γ is the adiabatic index of the air; S3232, by measuring the inlet and outlet pressures of the tested component and combining the air compression ratio, determine whether there is a large difference in pressure conversion by the following formula; <h2 style=";text-align:left;direction:ltr">(v1 / v2)<h2 style=";text-align:left;direction:ltr"> (γ-1) <h2 style=";text-align:left;direction:ltr"> p2-p1; Where p1 is the inlet pressure and p2 is the outlet pressure S3233, the soundprint decibel d2 collected by the acquisition sensor at time T and the standard soundprint decibel d1 are compared and analyzed, and the estimated value after linear filtering is combined for comprehensive analysis to obtain the fault prediction model: represents the actual value of the prediction result at time t, and s(t) is the pure original speech signal calculated in step S322.

7. The air compressor monitoring method according to claim 6, characterized in that: In S324, when the actual value of the prediction result When the threshold value is not exceeded, a prediction analysis curve chart is drawn and maintenance conditions are set; When the predicted result is actually If the threshold is exceeded three times, it is determined to be abnormal.

8. An air compressor monitoring system, characterized in that: The air compressor is monitored by using the air compressor monitoring method according to any one of claims 1 to 7, the system comprising: Controller, data receiver, sensor, display module and alarm; The output end, display module and alarm of the data receiving end are respectively connected to the controller; the controller is used to control the operation or stop of the air compressor, and adjust various working modes and parameters of the air compressor.

9. The air compressor monitoring system according to claim 8, characterized in that: The sensors include pressure sensors, temperature sensors, sound collectors, flow sensors, vibration sensors, etc.

10. The air compressor monitoring system according to claim 9, characterized in that: The sound collector comprises a mounting frame (1), a sound collection mainboard (2) arranged on the mounting frame (1), and a noise-proof component.

Images