Method and system for monitoring abnormality of similar components of large reciprocating pump

Abstract

This invention relates to the field of industrial equipment condition monitoring and fault diagnosis technology, and discloses a method for monitoring anomalies in similar components of a large reciprocating pump. The method includes a baseline data establishment stage and a real-time monitoring stage: In the baseline data establishment stage, temperature data under fault-free operating conditions is collected, the median temperature is calculated as the group temperature benchmark, and the median deviation value of each measuring point is calculated as the operating condition deviation baseline; in the real-time monitoring stage, temperature data is collected in real time, high-temperature anomalies are identified and alarms are triggered, and the current median temperature, current deviation value, relative deviation value, median absolute value of the current deviation value, and anomaly score are calculated. Anomaly scores are identified as abnormal and warnings are issued. This invention also discloses a system for monitoring anomalies in similar components of a large reciprocating pump. This invention's method and system for monitoring anomalies in similar components of a large reciprocating pump eliminates inherent temperature deviations between similar components, suppresses abnormal interference, and sensitively identifies early slow temperature rises, achieving accurate early warnings and ensuring safe equipment operation.

Description

Technical Field

[0001] This invention relates to the field of industrial equipment condition monitoring and fault diagnosis technology, specifically to a method and system for abnormal monitoring of similar components in a large reciprocating pump. Background Technology

[0002] Reciprocating pumps are core equipment in the oil production process. Their similar components (such as multi-cylinder, multi-valve group, crankshaft bearing, motor bearing, crosshead, large-end bearing, packing, etc.) are highly similar in structure and operating conditions. Abnormal temperature is an important precursor to component failure.

[0003] Existing temperature monitoring technologies mostly employ fixed threshold methods (such as alarms when temperatures exceed 80°C) or simple mean deviation methods, which have the following core drawbacks: 1. Inherent deviations in component operating conditions cannot be eliminated: Due to differences in installation location, machining accuracy, and flow field distribution, similar components have inherent temperature differences. Traditional methods do not compensate for this deviation, which can easily lead to false alarms under normal operating conditions. 2. Insensitive to early slow temperature rise: Early faults often manifest as a slow, small temperature rise. Traditional fixed threshold methods cannot detect such weak anomalies, resulting in delayed warnings and missing the best maintenance opportunity. 3. Susceptible to abnormal interference: Sensor noise and instantaneous operating condition fluctuations in industrial settings can easily generate abnormal data, which can contaminate traditional mean calculations, leading to benchmark distortion and increased misjudgments.

[0004] Therefore, there is an urgent need for a temperature monitoring method that can eliminate inherent operating condition deviations, sensitively identify early slow temperature rises, and resist abnormal interference, so as to improve the operational safety and reliability of large reciprocating pump equipment. Summary of the Invention

[0005] The purpose of this invention is to address the shortcomings of the above-mentioned technologies by providing a method and system for abnormal monitoring of similar components in large reciprocating pumps. This method eliminates inherent temperature deviations between similar components, suppresses abnormal interference, sensitively identifies early slow temperature rises, achieves accurate early warning, and ensures safe operation of the equipment.

[0006] To achieve the above objectives, the present invention provides a method for monitoring anomalies in similar components of a large reciprocating pump, comprising a baseline data establishment stage and a real-time monitoring stage. The baseline data establishment stage includes the following steps: A1) In One measuring point is set at the same location on each of the same type of component, totaling... Data was collected from one measurement point. Temperature data of each measuring point during a period of time under fault-free operating conditions. , For a point in time; A2) Calculate based on the temperature data Each measuring point at each time point median temperature To avoid contamination of the baseline by anomalies and address the vulnerability to anomaly interference, The measurement point number; A3) Calculate the first The deviation of each measuring point relative to the group temperature reference This reflects its deviation from the group temperature baseline; A4) Calculate the first The median of the deviation values ​​at each measuring point during the fault-free time. As the baseline of the working condition deviation of the measuring point, it is used to subtract the inherent deviation in subsequent real-time monitoring, thereby eliminating false alarms caused by the inherent temperature difference between components from the root cause. The real-time monitoring phase includes the following steps: B1) Real-time data acquisition Current temperature data at measuring points on similar components ; B2) Determine the first Current temperature data at each measuring point Is it higher than the preset high temperature threshold? If yes, an alarm message will be issued and the process will end to handle the emergency fault. If no, the median temperature at all measuring points will be calculated. ; B3) Calculate the first Each measuring point relative to the current median temperature Current deviation value ; B4) Combine the baseline of operating condition deviation obtained in step A4) Calculate the first Relative deviation of each measuring point Eliminate the inherent operating condition deviations of the measuring points and retain only the true abnormal signals; B5) Calculate the median of the absolute values ​​of the current deviations at all measuring points. This reflects the degree of dispersion of temperature distribution under the current operating conditions, and realizes the dynamic standardization of anomaly scores; B6) Calculate the first Current anomaly score at each measuring point In the formula, For conversion factors, This is the resolution compensation coefficient. Based on the resolution of the on-site temperature data, to avoid distortion at low resolution, this formula amplifies the weak signal of early slow temperature rise through MAD-based standardization processing, overcoming the deficiency of insensitivity to early slow temperature rise and achieving sensitive identification of early slow temperature rise. If an abnormal score is detected... , If the temperature reaches the abnormal threshold, an early warning message will be issued to indicate an early temperature anomaly, and the process will end.

[0007] Preferably, in step A1), the fault-free operating conditions cover the equipment under loaded, unloaded, and variable load operating conditions to ensure the integrity and representativeness of the baseline data.

[0008] Preferably, in step A1), the running time is not less than 24 hours to ensure the integrity and representativeness of the baseline data.

[0009] Preferably, in step B6), The value is 1.4826. The median absolute value of the current deviation is converted to an equivalent standard deviation to ensure the robustness of the statistic, combined with the resolution compensation coefficient. This enables the standardized amplification of early, subtle anomalies, addressing the issue of insensitivity to slow temperature rises.

[0010] Preferred, .

[0011] Preferred, .

[0012] Preferably, it also includes a baseline update mechanism, which periodically re-collects temperature data under fault-free operating conditions during long-term equipment operation, updates the operating condition deviation baseline, and adapts to equipment aging or changes in operating conditions.

[0013] A large reciprocating pump component anomaly monitoring system includes a temperature sensor group, a data processing module, and an alarm output module. The temperature sensor group is installed on the component to collect temperature data. The data processing module is connected to the temperature sensor group to acquire the temperature data. The temperature data is processed and analyzed using the large reciprocating pump component anomaly monitoring method. The alarm output module is connected to the data processing module to output alarm information or early warning information.

[0014] Preferably, the data processing module includes a baseline establishment unit and a real-time monitoring unit. The baseline establishment unit is used to calculate the median temperature, the deviation value, and the operating condition deviation baseline. The real-time monitoring unit is used to monitor in real time and calculate the current median temperature, the current deviation value, the relative deviation value, the median absolute value of the current deviation value, and the current anomaly score.

[0015] Preferably, the alarm output module includes two-level alarm units: a high temperature alarm unit and an abnormality warning unit. The high temperature alarm unit triggers an emergency alarm and outputs alarm information when it detects an abnormal high temperature. The abnormality warning unit triggers an early warning and outputs warning information when it detects an abnormality score.

[0016] Compared with the prior art, the present invention has the following advantages: 1. By establishing a baseline for operating condition deviation at the measurement point level, the inherent temperature deviation between similar components is eliminated, thereby reducing the false alarm rate from the root cause. The false alarm rate is reduced by more than 60% compared to traditional methods. 2. A robust median statistic is used instead of the mean to suppress the interference of outliers on the benchmark calculation and improve the robustness of the algorithm; 3. The design is based on the relative deviation anomaly score of the median absolute value of the deviation, which standardizes and amplifies the early slow temperature rise signal. This can amplify the slow temperature rise of 0.5℃ / h to a recognizable range, achieving accurate early warning of anomalies. The warning is 30 to 60 minutes earlier than the fixed threshold method. 4. Construct a two-level alarm mechanism of "high temperature emergency alarm + abnormal score early warning". The high temperature emergency alarm ensures the handling of extreme faults, while the abnormal score early warning enables early detection of potential hazards, balancing safety and operation and maintenance efficiency, and ensuring the timeliness and foresight of fault handling. 5. It has strong versatility and is applicable to all large reciprocating pump equipment with similar symmetrical components. The algorithm logic is clear and easy to embed into existing monitoring systems. Attached Figure Description

[0017] Figure 1 This is a flowchart of the abnormal monitoring method for similar components of a large reciprocating pump according to the present invention. Detailed Implementation

[0018] The technical solution of the present invention will now be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0019] like Figure 1 As shown, a method for monitoring anomalies in similar components of a large reciprocating pump includes a baseline data establishment stage and a real-time monitoring stage. The baseline data establishment stage includes the following steps: A1) In One measuring point is set at the same location on each of the same type of component, totaling... Data was collected from one measurement point. Temperature data of each measuring point during a period of time under fault-free operating conditions. , The time point is defined as the fault-free operating condition covering the equipment under loaded, no-load, and variable load operating conditions, and the operating time is not less than 24 hours. A2) Calculation based on temperature data Each measuring point at each time point median temperature As a group temperature benchmark, The measurement point number; A3) Calculate the first Deviation of each measuring point relative to the group temperature reference This reflects its deviation from the group temperature baseline; A4) Calculate the first The median of the deviation values ​​at each measuring point during the fault-free time. This serves as the baseline for the operating condition deviation of the measuring point. The real-time monitoring phase includes the following steps: B1) Real-time data acquisition Current temperature data at measuring points on similar components ; B2) Determine the first Current temperature data at each measuring point Is it higher than the preset high temperature threshold? , If yes, then issue an alarm and end the process directly; otherwise, calculate the median current temperature of all measuring points. ; B3) Calculate the first Each measuring point relative to the current median temperature Current deviation value ; B4) Combine the baseline of operating condition deviation obtained in step A4) Calculate the first Relative deviation of each measuring point ; B5) Calculate the median of the absolute values ​​of the current deviations at all measuring points. ; B6) Calculate the first Current anomaly score at each measuring point In the formula, For conversion factors, The median absolute value of the current deviation is 1.4826. Convert this median to the equivalent standard deviation. This is the resolution compensation coefficient. The resolution is determined based on the on-site temperature data; if the score is abnormal... , This is the abnormal threshold. If the temperature is abnormal in the early stages, an early warning message will be issued, indicating an early temperature anomaly, and the process will end.

[0020] In addition, a baseline update mechanism is included, which periodically re-collects temperature data under fault-free operating conditions during long-term equipment operation and updates the operating condition deviation baseline.

[0021] A large reciprocating pump component anomaly monitoring system includes a temperature sensor group, a data processing module, and an alarm output module. The temperature sensor group is installed on the component to collect temperature data. The data processing module is connected to the temperature sensor group to acquire the temperature data. The temperature data is processed and analyzed using the large reciprocating pump component anomaly monitoring method of this invention. The alarm output module is connected to the data processing module to output alarm information or early warning information.

[0022] The data processing module includes a baseline establishment unit and a real-time monitoring unit. The baseline establishment unit is used to calculate the median temperature, deviation value, and operating condition deviation baseline. The real-time monitoring unit is used for real-time monitoring and to calculate the current median temperature, current deviation value, relative deviation value, median absolute value of the current deviation value, and current anomaly score.

[0023] The alarm output module includes two levels of alarm units: a high temperature alarm unit and an abnormality warning unit. The high temperature alarm unit triggers an emergency alarm and outputs alarm information when it detects an abnormal high temperature. The abnormality warning unit triggers an early warning and outputs warning information when it detects an abnormality score.

[0024] Taking a large reciprocating pump (the seven crossheads of a 7-cylinder pump are of the same type, with one measuring point set on each crosshead) as an example, the implementation steps include the baseline data establishment stage and the real-time monitoring stage, as follows: The baseline data establishment phase includes the following steps: A1) Continuously collect temperature data from 7 crossheads during 24 hours of trouble-free operation. The sampling interval is 1 second, covering full load, 70% load, and no-load conditions; A2) Based on the temperature data, calculate the values ​​of the 7 measuring points at each time point. median temperature , as a group temperature benchmark; A3) Calculate the first Deviation of each measuring point relative to the group temperature reference ; A4) Calculate the first The median of the deviation values ​​at each measuring point during the fault-free time. The baseline of the working condition deviation of the seven crossheads is obtained, and the inherent temperature difference of each crosshead is eliminated.

[0025] The real-time monitoring phase includes the following steps: B1) Real-time acquisition of current temperature data at the current 7 crosshair measuring points. ; B2) Determine the first Current temperature data at each measuring point Is it higher than the preset high temperature threshold? In this embodiment, If yes, then issue an alarm and end the process directly; otherwise, calculate the median current temperature of all measuring points. ; B3) Calculate the first Each measuring point relative to the current median temperature Current deviation value ; B4) Combine the baseline of operating condition deviation obtained in step A4) Calculate the first Relative deviation of each measuring point The relative deviation value after eliminating inherent bias is obtained; B5) Calculate the median of the absolute values ​​of the current deviations at all measuring points. ; B6) Calculate the first Current anomaly score at each measuring point In the formula, For conversion factors, It is 1.4826. For the resolution compensation coefficient, take... K =0.15 (matching sensor 0.1℃ resolution), if abnormal score , As an abnormal threshold, in this embodiment, If the temperature is abnormal in the early stages, an early warning message will be issued, indicating an early temperature anomaly, and the process will end.

[0026] This invention relates to a method and system for monitoring anomalies in similar components of large reciprocating pumps. By establishing a baseline for operational deviation at the measurement point level, it eliminates inherent temperature deviations between similar components, reducing the false alarm rate by more than 60% compared to traditional methods. It uses a robust median statistic instead of the mean to suppress interference from anomalies in baseline calculations, improving algorithm robustness. A relative deviation anomaly score based on the median absolute value of the deviation is designed to standardize and amplify early slow temperature rise signals, amplifying slow temperature rises of 0.5℃ / h to an identifiable range, achieving accurate early warning of anomalies 30-60 minutes earlier than the fixed threshold method. A two-level alarm mechanism is constructed: a high-temperature emergency alarm and an anomaly score early warning. The high-temperature emergency alarm ensures handling of extreme faults, while the anomaly score early warning enables early hazard identification, balancing safety and operational efficiency, and ensuring timely and proactive fault handling. It is highly versatile, applicable to all large reciprocating pump equipment with similar symmetrical components, and its algorithm logic is clear and easily embedded into existing monitoring systems.

[0027] It should be noted that the above description of the technical solutions is exemplary, and this specification may be embodied in different forms and should not be construed as limiting it to the technical solutions set forth herein. Rather, providing these descriptions will ensure that the disclosure of this invention is thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art. Furthermore, the technical solutions of this invention are defined only by the scope of the claims.

[0028] The shapes, dimensions, ratios, angles, and figures disclosed in the description of various aspects of this specification and claims are merely examples, and therefore, this specification and claims are not limited to the details shown. In the following description, detailed descriptions of relevant known functions or configurations will be omitted where it would be determined that they unnecessarily obscure the focus of this specification and claims.

[0029] Finally, it should be noted that the above embodiments are merely representative examples of the present invention. Obviously, the present invention is not limited to the above embodiments and many variations are possible. Any simple modifications, equivalent changes, and alterations made to the above embodiments based on the technical essence of the present invention should be considered within the protection scope of the present invention.

Claims

1. A method for monitoring anomalies in similar components of a large reciprocating pump, characterized in that: It includes a baseline data establishment phase and a real-time monitoring phase. The baseline data establishment phase includes the following steps: A1) In One measuring point is set at the same location on each of the same type of component, totaling... Data was collected from one measurement point. Temperature data of each measuring point during a period of time under fault-free operating conditions. , For a point in time; A2) Calculate based on the temperature data Each measuring point at each time point median temperature As a group temperature benchmark, The measurement point number; A3) Calculate the first The deviation of each measuring point relative to the group temperature reference This reflects its deviation from the group temperature baseline; A4) Calculate the first The median of the deviation values ​​at each measuring point during the fault-free time. This serves as the baseline for the operating condition deviation of the measuring point. The real-time monitoring phase includes the following steps: B1) Real-time data acquisition Current temperature data at measuring points on similar components ; B2) Determine the first Current temperature data at each measuring point Is it higher than the preset high temperature threshold? If yes, then issue an alarm and end the process directly; otherwise, calculate the median current temperature of all measuring points. ; B3) Calculate the first Each measuring point relative to the current median temperature Current deviation value ; B4) Combine the baseline of operating condition deviation obtained in step A4) Calculate the first Relative deviation of each measuring point ; B5) Calculate the median of the absolute values ​​of the current deviations at all measuring points. ; B6) Calculate the first Current anomaly score at each measurement point In the formula, For conversion factors, This is the resolution compensation coefficient. The resolution is determined based on the on-site temperature data; if the score is abnormal... , If the temperature reaches the abnormal threshold, an early warning message will be issued to indicate an early temperature anomaly, and the process will end.

2. The method for monitoring abnormalities in similar components of a large reciprocating pump as described in claim 1, characterized in that: In step A1), the fault-free operating conditions cover the equipment under loaded, unloaded, and variable load operating conditions.

3. The method for monitoring abnormalities in similar components of a large reciprocating pump as described in claim 1, characterized in that: In step A1), the duration of the operation period shall not be less than 24 hours.

4. The method for monitoring abnormalities in similar components of a large reciprocating pump as described in claim 1, characterized in that: In step B6), The value is 1.4826, which converts the median absolute value of the current deviation to the equivalent standard deviation.

5. The method for monitoring abnormalities in similar components of a large reciprocating pump as described in claim 1, characterized in that: 。 6. The method for monitoring abnormalities in similar components of a large reciprocating pump as described in claim 1, characterized in that: 。 7. The method for monitoring abnormalities in similar components of a large reciprocating pump as described in claim 1, characterized in that: It also includes a baseline update mechanism, which periodically re-collects temperature data under fault-free operating conditions during long-term equipment operation and updates the operating condition deviation baseline.

8. A fault monitoring system for similar components of a large reciprocating pump, characterized in that: The device includes a temperature sensor group, a data processing module, and an alarm output module. The temperature sensor group is installed on a similar component to collect temperature data. The data processing module is connected to the temperature sensor group to acquire the temperature data. The temperature data is processed and analyzed using the abnormal monitoring method for similar components of a large reciprocating pump as described in any one of claims 1 to 7. The alarm output module is connected to the data processing module to output alarm information or early warning information.

9. The abnormal monitoring system for similar components of a large reciprocating pump as described in claim 8, characterized in that: The data processing module includes a baseline establishment unit and a real-time monitoring unit. The baseline establishment unit is used to calculate the median temperature, deviation value, and operating condition deviation baseline. The real-time monitoring unit is used to monitor in real time and calculate the current median temperature, current deviation value, relative deviation value, median absolute value of the current deviation value, and current anomaly score.

10. The abnormal monitoring system for similar components of a large reciprocating pump as described in claim 8, characterized in that: The alarm output module includes two levels of alarm units: a high temperature alarm unit and an abnormality warning unit. The high temperature alarm unit triggers an emergency alarm and outputs alarm information when it detects an abnormal high temperature. The abnormality warning unit triggers an early warning and outputs warning information when it detects an abnormality score.

Images