Chemical equipment fault diagnosis and maintenance system

Abstract

The embodiment of the invention discloses a chemical equipment fault diagnosis and maintenance system, and belongs to the technical field of equipment monitoring, and the system comprises an equipment monitoring module which is installed on equipment and is used for monitoring and reading various data during the operation of the equipment; the data acquisition module is used for acquiring the equipment operation data monitored and read by the equipment monitoring module, and compressing, filtering and uploading the acquired data; and the monitoring diagnosis module is used for receiving the equipment operation data uploaded by the data acquisition module, performing fault diagnosis on the data, and performing fault maintenance on target equipment according to a fault diagnosis result. According to the embodiment of the invention, the cost can be reduced, the equipment reliability can be improved, and online monitoring, real-time fault alarm and hidden danger prediction reminding of the equipment are realized; and the influence of sensor errors on fault diagnosis is reduced.

Description

Technical Field

[0001] This application belongs to the field of equipment monitoring technology, specifically, it relates to a fault diagnosis and maintenance system for chemical equipment. Background Technology

[0002] Currently, with the increasing modernization of chemical production and the continuous improvement of safety awareness, the safe operation of mechanical equipment is not only a necessary condition for the normal operation of enterprise production, but also a prerequisite for avoiding production accidents. Especially in large-scale process production enterprises, continuous and uninterrupted chemical production is a necessary condition, which puts forward higher requirements for ensuring the reliability of equipment safety.

[0003] Existing equipment monitoring methods are mainly divided into wireless and wired acquisition methods. However, wireless acquisition methods may result in waveform loss and cannot guarantee the acquisition of a complete cycle. Wired acquisition methods are not limited by space but have higher initial construction costs, making it difficult to select a suitable acquisition method according to needs. At the same time, both wired and wired sensors have movement errors. During the monitoring process, the accumulation of error values ​​may lead to deviations in monitoring results, ultimately affecting fault analysis results, hindering timely equipment maintenance, and failing to meet industrial needs. Summary of the Invention

[0004] To address the aforementioned problems and technical deficiencies, this application provides the following technical solution: a chemical equipment fault diagnosis and repair system, comprising:

[0005] The equipment monitoring module is installed on the equipment to monitor and read various data during equipment operation.

[0006] The data acquisition module is used to collect equipment operation data read by the equipment monitoring module, and to compress, filter and upload the collected data.

[0007] The monitoring and diagnostic module is used to receive equipment operation data uploaded by the data acquisition module, perform fault diagnosis on the data, and carry out fault repair on the target equipment based on the fault diagnosis results.

[0008] Preferably, the equipment monitoring module reads the operating data of the target equipment by installing wired or wireless sensors on the target equipment and reads the parameter data of the target equipment by connecting to an electrical cabinet connected to the target equipment.

[0009] The operational data read by the sensor includes: temperature data, noise data, vibration data, and pressure data;

[0010] The electrical cabinet reads the following parameter data: voltage data, current data, power data, and electrical quantity data.

[0011] Furthermore, the wired sensor is a wired temperature and vibration integrated sensor, and the wireless sensor is a wireless split-type Zigbee sensor. The wireless sensor uses a low-power local area network protocol based on the IEEE 802.15.4 standard for data transmission.

[0012] Preferably, the wired or wireless sensor needs to undergo an accuracy verification test before installation, and the test process is as follows:

[0013] Place the standard sensor and the target sensor to be tested onto the standard vibration table, and start the standard vibration table;

[0014] The standard vibration signal from the standard sensor and the target diagnostic signal from the target sensor are sent to the conditioning amplifier, which amplifies the collected signals and transmits them to the calibration controller.

[0015] The calibration controller compares the error between the amplified standard vibration signal from the standard sensor and the target diagnostic signal from the target sensor, and sends the error comparison result to the computer.

[0016] The computer controls the power amplifier through the calibration controller based on the error comparison results and the number of tests. The power amplifier controls the vibration frequency of the standard vibration table.

[0017] By conducting multiple tests at different vibration frequencies, the error values ​​of the target sensor compared to the standard sensor in different frequency ranges are obtained, and it is determined whether the data of the target sensor is within the error range.

[0018] Furthermore, the formula for calculating the error comparison between the standard vibration signal and the target diagnostic signal is as follows:

[0019]

[0020] Where RRMSEP is the root square error of prediction, N is the total number of trials, i is the current trial number, and x i y represents the standard value of the standard vibration signal in the current test. i This represents the measured value of the target diagnostic signal in the current experiment.

[0021] Preferably, the data acquisition module includes an edge computing module, which can perform time-domain feature, frequency-domain feature, signal compression, filtering and integration calculations on the acquired data to achieve real-time online analysis.

[0022] Preferably, the monitoring and diagnosis module uses an absolute value alarm strategy to diagnose faults in the target device. By pre-setting multiple alarm thresholds, the alarm thresholds are then sent to the data acquisition module. The alarm level is obtained based on the set multiple alarm thresholds. The alarm levels are divided into normal, early warning, alarm, and warning.

[0023] Furthermore, if the data acquisition module detects that the device's operating data exceeds the normal range, it will trigger an alarm and send an alarm signal. The judgment process after sending the alarm signal is as follows:

[0024] Determine if there is an alarm signal. If so, determine if it is a low alarm. If so, determine if the parameter data is greater than the low limit minus the hysteresis value. If so, cancel the alarm signal.

[0025] Determine if there is an alarm signal. If so, determine if it is a low alarm. If so, determine if the parameter data is greater than the low limit minus the hysteresis value. If not, send the abnormal parameter data to the monitoring and diagnosis module.

[0026] Determine if there is an alarm signal. If there is, determine if it is a low alarm. If not, determine if the parameter data is less than the upper limit plus the hysteresis value. If so, cancel the alarm signal.

[0027] Determine if there is an alarm signal. If so, determine if it is a low alarm. If not, determine if the parameter data is less than the upper limit plus the hysteresis value. If not, send the abnormal parameter data to the monitoring and diagnosis module.

[0028] Determine if there is an alarm signal. If not, determine if it is a low alarm. If so, determine if the parameter data is less than the lower limit. If so, reset the alarm signal.

[0029] Determine if there is an alarm signal. If not, determine if it is a low alarm. If so, determine if the parameter data is less than the lower limit. If not, send the abnormal parameter data to the monitoring and diagnosis module.

[0030] Determine if there is an alarm signal. If not, determine if it is a low alarm. If not, determine if the parameter data is greater than the high limit. If so, reset the alarm signal.

[0031] Determine if there is an alarm signal. If not, determine if it is a low alarm. If not, determine if the parameter data is greater than the upper limit. If not, send the abnormal parameter data to the monitoring and diagnostic module.

[0032] Furthermore, determining whether it is a low alarm refers to determining whether it is below the normal range of operating data; the low limit refers to the minimum alarm threshold; the high limit refers to the maximum alarm threshold; and the hysteresis value is a preset fixed value.

[0033] Furthermore, the monitoring and diagnostic module needs to perform anomaly identification processing on the received abnormal parameter data, remove data anomalies through data cleaning, identify erroneous data in the abnormal parameter data, compare the correlation of the signal spectrum at both ends of the abnormal parameter data, identify non-periodic signals, filter out change signals caused by non-device faults, and reduce false alarm interference.

[0034] Compared with the prior art, the beneficial effects of the embodiments of this application are as follows:

[0035] (1) This application conducts experiments on hardware, software platforms, algorithms, etc., analyzes their actual performance, promotes the transition of equipment from preventive maintenance to condition maintenance, provides technical support for the establishment of full life cycle condition monitoring for subsequent equipment, and ensures the accuracy of data collection, the stability of platform operation, and the accuracy of algorithm analysis;

[0036] (2) This application compares the standard signal generated by the standard vibration table with the sensor acquisition signal, and finally judges whether the consistency and accuracy of the data acquired by the online equipment meet the requirements. By verifying the alarm information of abnormal measuring points, the alarm strategy is optimized, the alarm accuracy is improved, the accuracy of equipment status data acquisition and the accuracy of abnormal measuring point alarm are verified, and the accuracy of the data acquired on site is guaranteed.

[0037] (3) This application evaluates the overall application effect of online monitoring, diagnosis and health management of equipment through the trial operation of the system. It adopts two data acquisition methods: wireless sensor and wired sensor. According to environmental factors such as mutual interference between air equipment and site limitations, the appropriate data acquisition method is selected to meet different environmental factors and equipment requirements. It can ensure that the operating status of the equipment is collected and improve the feasibility of equipment deployment and the accuracy of data acquisition. Attached Figure Description

[0038] In the attached diagram:

[0039] Figure 1 This is a schematic diagram of the system structure according to an embodiment of this application;

[0040] Figure 2 This is an overall monitoring structure diagram of an embodiment of this application;

[0041] Figure 3 This is a flowchart illustrating the alarm judgment process in an embodiment of this application. Detailed Implementation

[0042] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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 some embodiments of this application, but not all embodiments. Generally, the components of the embodiments of this application described and shown in the accompanying drawings can be arranged and designed in various different configurations.

[0043] Example

[0044] like Figure 1 As shown, a chemical equipment fault diagnosis and maintenance system includes:

[0045] The equipment monitoring module is installed on the equipment to monitor and read various data during equipment operation.

[0046] The data acquisition module is used to collect equipment operation data read by the equipment monitoring module, and to compress, filter and upload the collected data.

[0047] The monitoring and diagnostic module is used to receive equipment operation data uploaded by the data acquisition module, perform fault diagnosis on the data, and carry out fault repair on the target equipment based on the fault diagnosis results.

[0048] The equipment monitoring module reads the operating data of the target equipment by installing wired or wireless sensors on the target equipment and reads the parameter data of the target equipment by connecting to the electrical cabinet.

[0049] The operational data read by the sensor includes: temperature data, noise data, vibration data, and pressure data;

[0050] The electrical cabinet reads the following parameter data: voltage data, current data, power data, and electrical quantity data.

[0051] The wired sensor is a wired temperature and vibration integrated sensor, while the wireless sensor is a wireless split-type Zigbee sensor. The wireless sensor uses a low-power local area network protocol based on the IEEE 802.15.4 standard for data transmission.

[0052] The wired or wireless sensor needs to undergo an accuracy verification test before installation. The test process is as follows:

[0053] Place the standard sensor and the target sensor to be tested onto the standard vibration table, and start the standard vibration table;

[0054] The standard vibration signal from the standard sensor and the target diagnostic signal from the target sensor are sent to the conditioning amplifier, which amplifies the collected signals and transmits them to the calibration controller.

[0055] The calibration controller compares the error between the amplified standard vibration signal from the standard sensor and the target diagnostic signal from the target sensor, and sends the error comparison result to the computer.

[0056] The computer controls the power amplifier through the calibration controller based on the error comparison results and the number of tests. The power amplifier controls the vibration frequency of the standard vibration table.

[0057] By conducting multiple tests at different vibration frequencies, the error values ​​of the target sensor compared to the standard sensor in different frequency ranges are obtained, and it is determined whether the data of the target sensor is within the error range.

[0058] The formula for calculating the error between the standard vibration signal and the target diagnostic signal is as follows:

[0059]

[0060] Where RRMSEP is the root square error of prediction, N is the total number of trials, i is the current trial number, and x i y represents the standard value of the standard vibration signal in the current test. i This represents the measured value of the target diagnostic signal in the current experiment.

[0061] The data acquisition module includes an edge computing module, which can perform time-domain feature and frequency-domain feature calculations, signal compression, filtering, and integration calculations on the acquired data to achieve real-time online analysis.

[0062] The monitoring and diagnostic module uses an absolute value alarm strategy to diagnose faults in the target equipment. Multiple alarm thresholds are preset and then sent to the data acquisition module. The alarm level is obtained based on the multiple alarm thresholds. The alarm levels are divided into normal, early warning, alarm and warning.

[0063] The data acquisition module will trigger an alarm if it detects that the equipment's operating data exceeds the normal range. The alarm signal will be sent, and the subsequent judgment process is as follows:

[0064] Determine if there is an alarm signal. If so, determine if it is a low alarm. If so, determine if the parameter data is greater than the low limit minus the hysteresis value. If so, cancel the alarm signal.

[0065] Determine if there is an alarm signal. If so, determine if it is a low alarm. If so, determine if the parameter data is greater than the low limit minus the hysteresis value. If not, send the abnormal parameter data to the monitoring and diagnosis module.

[0066] Determine if there is an alarm signal. If there is, determine if it is a low alarm. If not, determine if the parameter data is less than the upper limit plus the hysteresis value. If so, cancel the alarm signal.

[0067] Determine if there is an alarm signal. If so, determine if it is a low alarm. If not, determine if the parameter data is less than the upper limit plus the hysteresis value. If not, send the abnormal parameter data to the monitoring and diagnosis module.

[0068] Determine if there is an alarm signal. If not, determine if it is a low alarm. If so, determine if the parameter data is less than the lower limit. If so, reset the alarm signal.

[0069] Determine if there is an alarm signal. If not, determine if it is a low alarm. If so, determine if the parameter data is less than the lower limit. If not, send the abnormal parameter data to the monitoring and diagnosis module.

[0070] Determine if there is an alarm signal. If not, determine if it is a low alarm. If not, determine if the parameter data is greater than the high limit. If so, reset the alarm signal.

[0071] Determine if there is an alarm signal. If not, determine if it is a low alarm. If not, determine if the parameter data is greater than the upper limit. If not, send the abnormal parameter data to the monitoring and diagnostic module.

[0072] The determination of whether it is a low alarm refers to determining whether it is below the normal range of operating data; the low limit refers to the minimum alarm threshold; the high limit refers to the maximum alarm threshold; and the hysteresis value is a preset fixed value.

[0073] The monitoring and diagnostic module needs to identify and process the received abnormal parameter data, remove abnormal data through data cleaning, identify erroneous data in the abnormal parameter data, compare the correlation of the signal spectrum before and after the abnormal parameter data, identify non-periodic signals, filter out change signals caused by non-equipment faults, and reduce false alarm interference.

[0074] The embodiments described above are merely preferred embodiments of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this application. It should be noted that those skilled in the art can make various modifications, improvements, and substitutions without departing from the concept of this application, and these all fall within the protection scope of this application.

Claims

1. A chemical equipment fault diagnosis and maintenance system, characterized in that: include: Equipment monitoring module, used to be installed on the equipment to monitor and read various data during the operation of the equipment; The data acquisition module is used to collect the equipment operation data monitored and read by the equipment monitoring module, and compress, filter and upload the collected data; The monitoring and diagnosis module is used to receive the equipment operation data uploaded by the data acquisition module, perform fault diagnosis on the data, and perform fault repair on the target equipment according to the fault diagnosis results.

2. A chemical equipment fault diagnosis and maintenance system according to claim 1, characterized in that: The equipment monitoring module is to install a wired sensor or a wireless sensor on the target equipment, read the operation data of the target equipment through the wired sensor or the wireless sensor, and read the parameter data of the target equipment by connecting the electrical cabinet with the target equipment; The operating data read by the sensor include: temperature data, noise data, vibration data and pressure data; The parameter data read by the electrical cabinet include: voltage data, current data, power data and power data.

3. A chemical equipment fault diagnosis and maintenance system according to claim 2, characterized in that: The wired sensor is a wired temperature-vibration integrated sensor, the wireless sensor is a wireless split Zigbee sensor, and the wireless sensor uses a low-power LAN protocol based on the IEEE802.15.4 standard for data transmission.

4. A chemical equipment fault diagnosis and maintenance system according to claim 1, characterized in that: The wired sensor or wireless sensor needs to undergo an accuracy verification test before installation. The test process is as follows: Place the standard sensor and the target sensor with test on the standard vibration table, and start the standard vibration table; The standard vibration signal of the standard sensor and the target diagnostic signal of the target sensor are sent to the conditioning amplifier, which amplifies the collected signals and transmits them to the calibration controller; The calibration controller performs error comparison between the amplified standard vibration signal of the standard sensor and the target diagnosis signal of the target sensor, and sends the error comparison result to the computer; The computer controls the power generator through the calibration controller according to the error comparison result and the number of tests, and the power generator controls the vibration frequency of the standard vibration table; Through multiple tests at different vibration frequencies, the error value between the target sensor and the standard sensor in different frequency ranges is obtained to determine whether the data of the target sensor is within the error range.

5. A chemical equipment fault diagnosis and maintenance system according to claim 4, characterized in that: The calculation formula for comparing the error between the standard vibration signal and the target diagnostic signal is as follows: Among them, RRMSEP is the root square error of prediction, N is the total number of trials, i is the current number of trials, and x is i is the standard value of the standard vibration signal in the current test, y i is the measured value of the target diagnostic signal in the current trial.

6. A chemical equipment fault diagnosis and maintenance system according to claim 1, characterized in that: The data acquisition module includes an edge computing module, which can perform time domain characteristics, frequency domain characteristics, signal compression, filtering and integration calculations on the collected data to achieve real-time online analysis.

7. A chemical equipment fault diagnosis and maintenance system according to claim 1, characterized in that: The monitoring and diagnosis module adopts an absolute value alarm strategy to perform fault diagnosis on the target device. By pre-setting multiple alarm thresholds, the alarm thresholds are then sent to the data acquisition module, and the alarm level is obtained according to the set multiple alarm thresholds. The alarm level is divided into normal, early warning, alarm and warning.

8. A chemical equipment fault diagnosis and maintenance system according to claim 7, characterized in that: When the data acquisition module detects that the equipment operation data exceeds the normal range, it will perform alarm processing and send an alarm signal. The judgment process after sending the alarm signal is as follows: Determine whether there is an alarm signal. If yes, determine whether it is a low alarm. If yes, determine whether the parameter data is greater than the lower limit minus the hysteresis value. If yes, cancel the alarm signal. Determine whether there is an alarm signal, if yes, determine whether it is a low alarm, if yes, determine whether the parameter data is greater than the lower limit minus the hysteresis value, if not, send the abnormal parameter data to the monitoring and diagnosis module; Determine whether there is an alarm signal. If yes, determine whether it is a low alarm. If not, determine whether the parameter data is less than the high limit plus the hysteresis value. If so, cancel the alarm signal. Determine whether there is an alarm signal. If yes, determine whether it is a low alarm. If not, determine whether the parameter data is less than the upper limit plus the hysteresis value. If not, send the abnormal parameter data to the monitoring and diagnosis module; Determine whether there is an alarm signal, if not, determine whether it is a low alarm, if so, determine whether the parameter data is less than the lower limit, if so, reset the alarm signal; Determine whether there is an alarm signal. If not, determine whether it is a low alarm. If so, determine whether the parameter data is less than the lower limit. If not, send the abnormal parameter data to the monitoring and diagnosis module; Determine whether there is an alarm signal, if not, determine whether it is a low alarm, if not, determine whether the parameter data is greater than the high limit, if so, reset the alarm signal; Determine whether there is an alarm signal. If not, determine whether it is a low alarm. If not, determine whether the parameter data is greater than the upper limit. If not, send the abnormal parameter data to the monitoring and diagnosis module.

9. A chemical equipment fault diagnosis and maintenance system according to claim 8, characterized in that: The determination of whether it is an underreport refers to determining whether it is lower than the normal range of the operating data; the lower limit refers to the minimum alarm threshold; the upper limit refers to the maximum alarm threshold; and the hysteresis value is a preset fixed value.

10. A chemical equipment fault diagnosis and maintenance system according to claim 8, characterized in that: The monitoring and diagnosis module needs to perform abnormal point identification processing on the received abnormal parameter data, remove data abnormal points through data cleaning, determine the erroneous data in the abnormal parameter data, and compare the correlation of the signal spectrum before and after the abnormal parameter data, identify non-periodic signals, filter out change signals caused by reasons other than equipment failure, and reduce false alarm interference.

Images