A self-checking system for a submersible reciprocating pump drive mechanism

Abstract

The present invention discloses a self-inspection system for a submersible reciprocating pump drive mechanism, which specifically relates to the field of pump body detection technology. It collects multi-dimensional operating parameters such as vibration, temperature, current and pressure, and optimizes the data transmission bandwidth through compression technology, thereby improving transmission efficiency and stability. The data processing module processes the collected data in real time based on a threshold adjustment mechanism, accurately identifies equipment abnormalities and promptly issues alarm signals, thereby avoiding the occurrence of potential faults. In addition, the system is combined with an aging status monitoring and prediction module, which analyzes the historical and real-time operating data of the equipment through a machine learning algorithm, identifies the aging trend of the equipment in advance, optimizes the maintenance and replacement cycle, and reduces equipment downtime and maintenance costs.

Description

Technical Field

[0001] The present invention relates to the technical field of pump body detection, and more specifically, to a self-detection system for a submersible reciprocating pump driving mechanism. Background Art

[0002] With the continuous improvement of the automation level of industrial equipment, submersible reciprocating pumps are widely used in deep well water collection, oil extraction and other liquid transportation fields. However, this type of equipment operates in a complex environment for a long time, and is prone to performance degradation or even failure due to factors such as abnormal vibration of mechanical parts, excessive temperature rise of heat-sensitive parts, or current pressure overload. Traditional equipment monitoring methods usually rely on single parameter monitoring or regular manual inspections, and are unable to capture equipment aging trends or potential fault signals in a timely manner. Especially when the amount of operating data is huge, the lack of data transmission efficiency and processing timeliness significantly limits the comprehensive evaluation of the equipment's operating status and maintenance efficiency.

[0003] Traditional submersible reciprocating pump monitoring methods have the disadvantages of single operating status monitoring dimension, low data processing efficiency, and lack of aging trend prediction capabilities. Especially when faced with multi-dimensional parameter monitoring needs and huge operating data, traditional systems are limited by transmission efficiency and processing capabilities and cannot achieve real-time and efficient status assessment, resulting in delayed equipment maintenance and reduced operating reliability. Summary of the invention

[0004] In order to overcome the above-mentioned defects of the prior art, an embodiment of the present invention provides a self-inspection system for a submersible reciprocating pump drive mechanism, which collects the operating parameters of the submersible reciprocating pump, such as vibration, temperature, current and pressure, in real time through a multi-sensor module, and combines compression, threshold adjustment and machine learning algorithms to monitor the equipment status in real time, predict aging trends, and issue abnormal alarms, thereby optimizing the equipment's operation management and maintenance strategies to solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above-mentioned purpose, the present invention provides the following technical solutions: a self-checking system for a submersible reciprocating pump drive mechanism, comprising a sensor module, a data acquisition and transmission module, a data processing module, an aging state monitoring and prediction module, an alarm module and a data storage module:

[0006] The sensor module is used to collect the operating parameters of the submersible reciprocating pump drive mechanism in real time. The operating parameters include vibration parameters, temperature parameters, current parameters and pressure parameters. The operating parameters are collected by the vibration sensor, temperature sensor, current sensor and pressure sensor included in the sensor module respectively;

[0007] The data acquisition and transmission module is used to compress the operating parameters collected by the sensor module and transmit the compressed data to the data processing module through wired or wireless transmission to optimize bandwidth utilization;

[0008] The data processing module processes the compressed data in real time based on the threshold adjustment mechanism and generates a threshold that matches the equipment operation status. By comparing the operation parameters with the threshold, the deviation of the values ​​is identified and the equipment operation status is determined.

[0009] The aging status monitoring and prediction module builds an aging status monitoring and prediction model based on the historical operating parameters of the equipment and the operating parameters collected in real time, and combines machine learning algorithms to analyze the operating trends of the equipment and identify abnormal conditions;

[0010] The alarm module is used to detect when the equipment operating parameters exceed the set threshold range and send out an alarm signal to indicate abnormal equipment operation;

[0011] The data storage module is used to record the historical operating data, threshold range and alarm information of the equipment, and perform trend analysis on the operating status of the equipment.

[0012] In a preferred embodiment, the vibration sensor includes an acceleration sensor and a displacement sensor. The acceleration sensor is used to monitor the vibration intensity and frequency of the driving mechanism, and the displacement sensor is used to monitor the displacement changes of the internal components of the equipment, which is used to further analyze the mechanical health of the equipment. Vibration analysis is performed through the vibration deviation index, and the vibration deviation index expression formula is:

[0013]

[0014] Where VDI(t) is the vibration deviation index, which indicates the vibration health status of the equipment calculated at time t; n is the number of sensors collecting data; a i (t) is the vibration data collected by the i-th acceleration sensor at time t; a baseline is the reference value of the acceleration sensor; d i (t) is the displacement data collected by the i-th displacement sensor at time t; d baseline is the reference value of the displacement sensor; β1 is the exponential adjustment coefficient of the acceleration data; β2 is the exponential adjustment coefficient of the displacement data; β3 is the comprehensive adjustment coefficient.

[0015] In a preferred embodiment, the temperature sensor is an infrared temperature sensor, which is used to monitor the temperature change of the device in real time and detect temperature anomalies. The temperature change value is analyzed by the temperature deviation index, and the temperature deviation index expression formula is:

[0016]

[0017] Where, TDI(t) is the temperature deviation index; m is the number of temperature sensors; T i(t) is the temperature data collected by the i-th temperature sensor at time t; T ref,i is the reference temperature value of the i-th sensor; T avg,i (t) is the weighted average temperature value of the i-th sensor at time t; α1 is the influence of controlling the deviation between the i-th sensor temperature and the reference value; α2 is the influence of controlling the deviation between the i-th sensor weighted average temperature and the reference value; α3 is used to scale and adjust the comprehensive result.

[0018] In a preferred embodiment, the data acquisition and transmission module optimizes bandwidth utilization by compressing data and analyzes the continuous transmission time of the data stream. The compression coefficient calculation formula is:

[0019]

[0020] Among them, k c is the data compression coefficient, used to quantify the compression effect; v i,t is the data collected by the i-th sensor at time t; v i,ref is the reference value of the i-th sensor; α i , β, γ are adjustment coefficients; n is the number of sensors.

[0021] In a preferred embodiment, the data processing module processes the compressed data in real time based on a threshold adjustment mechanism, and the calculation formula of the state deviation is:

[0022]

[0023] Among them, D offset is the state deviation, which indicates the degree of deviation between the equipment operating parameters and the threshold; v i,t is the operating parameter of the ith sensor at time t; v i,th is the threshold of the i-th sensor; n represents the number of sensors.

[0024] In a preferred embodiment, the aging status monitoring and prediction module uses a long short-term memory network to analyze the long-term operation trend of the equipment, identify the aging mode of the equipment, and adjust the maintenance and replacement cycle of the equipment according to the prediction results. The long short-term memory network expression formula is:

[0025]

[0026] Among them, h t is the output at time t; x t is the input data at time t; is the predicted aging state output; W f is the weight matrix; b f is the bias; h t-1is the hidden state at the previous time t-1.

[0027] In a preferred embodiment, the alarm module not only includes a sound alarm device, but also includes a function of sending push notifications through a mobile application. The trigger judgment condition of the push notification is notified through time detection, and the event detection expression formula is:

[0028]

[0029] Among them, P alert (t) represents the probability of triggering an alarm notification at time t; n represents the number of operating parameters; x i (t) represents the value measured by the ith sensor or parameter at time t. If the ith sensor is used to measure vibration, its value is the vibration value measured at time t; θ i represents the set threshold corresponding to the i-th sensor; δ1 is the adjustment coefficient; m is the number of device state changes; x j (t) represents the state parameter measured by the jth sensor at time t; θ j represents the threshold value set by the jth sensor; x j (t-1) is the state parameter measured by the j-th sensor at time t-1; δ2 is the influence of adjusting the deviation between the measured value of the j-th sensor and the set threshold on the alarm probability; δ3 is the influence of the change between the current value and the value of the previous moment between two measurements of the j-th sensor on the alarm probability; δ4 is the comprehensive adjustment coefficient.

[0030] In a preferred embodiment, the data storage module is used to store the historical operation data, threshold range and alarm information of the equipment, and perform trend analysis on the operation status of the equipment. The trend analysis expression formula is:

[0031]

[0032] Among them, T trend is the changing trend of the operating status; v t is the equipment operating parameter at time t; is the mean of historical data; m is the total number of moments of historical data.

[0033] Technical effects and advantages of the present invention:

[0034] 1. By integrating multiple sensor modules and data acquisition modules, it can collect multi-dimensional operating parameters of the equipment such as vibration, temperature, current and pressure in real time, and use compression technology to effectively optimize the data transmission bandwidth. At the same time, the data processing module combined with the threshold adjustment mechanism can accurately identify the degree of deviation of the equipment status, ensuring that equipment anomalies can be detected and processed in time;

[0035] 2. The aging status monitoring and prediction module of the present invention is based on a long short-term memory network. By analyzing historical operating data and multi-parameter information collected in real time, a prediction model is constructed, which can accurately identify the aging mode of the equipment and its operating trend. Combined with the real-time adjustment mechanism of the threshold, the module can predict potential equipment failures while optimizing the maintenance and replacement cycle. In addition, the alarm module supports multi-level alarm functions, including sound prompts and push notifications through mobile terminals, to achieve efficient feedback and rapid response to abnormal conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a schematic diagram of the process of the present invention. DETAILED DESCRIPTION

[0037] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0038] Refer to the instruction manual Figure 1 A self-checking system for a submersible reciprocating pump drive mechanism according to an embodiment of the present invention includes a sensor module, a data acquisition and transmission module, a data processing module, an aging state monitoring and prediction module, an alarm module and a data storage module:

[0039] The sensor module is used to collect the operating parameters of the submersible reciprocating pump drive mechanism in real time. The operating parameters include vibration parameters, temperature parameters, current parameters and pressure parameters. The operating parameters are collected by the vibration sensor, temperature sensor, current sensor and pressure sensor included in the sensor module respectively;

[0040] The data acquisition and transmission module is used to compress the operating parameters collected by the sensor module and transmit the compressed data to the data processing module through wired or wireless transmission to optimize bandwidth utilization;

[0041] The data processing module processes the compressed data in real time based on the threshold adjustment mechanism and generates a threshold that matches the equipment operation status. By comparing the operation parameters with the threshold, the deviation of the values ​​is identified and the equipment operation status is determined.

[0042] The aging status monitoring and prediction module builds an aging status monitoring and prediction model based on the historical operating parameters of the equipment and the operating parameters collected in real time, and combines machine learning algorithms to analyze the operating trends of the equipment and identify abnormal conditions;

[0043] The alarm module is used to detect when the equipment operating parameters exceed the set threshold range and send out an alarm signal to indicate abnormal equipment operation;

[0044] The data storage module is used to record the historical operation data, threshold range and alarm information of the equipment, and to perform trend analysis on the operation status of the equipment;

[0045] The sensors of the sensor module are installed at the key parts of the submersible reciprocating pump drive mechanism according to the characteristics of the equipment operating environment and monitoring requirements. The vibration sensor is installed at the key load-bearing part of the drive mechanism to monitor the vibration intensity and frequency. The temperature sensor adopts an infrared temperature sensor, which is installed on the motor and other heat-sensitive components to monitor temperature changes in real time. The current sensor and pressure sensor are installed in the circuit and pipeline system respectively to monitor the current and pressure status of the equipment. Through reasonable sensor arrangement, it is ensured that various parameters of the equipment operating status can be fully and accurately collected.

[0046] Vibration sensors include acceleration sensors and displacement sensors. Acceleration sensors are used to monitor the vibration intensity and frequency of the drive mechanism, and displacement sensors are used to monitor the displacement changes of internal components of the equipment. They are used to further analyze the mechanical health of the equipment and perform vibration analysis through the vibration deviation index. The vibration deviation index expression formula is:

[0047]

[0048] Where VDI(t) is the vibration deviation index, which indicates the vibration health status of the equipment calculated at time t. The larger the value, the more abnormal the vibration of the equipment is, and the more likely it is to fail. n is the number of sensors collecting data; a i (t) is the vibration data collected by the ith acceleration sensor at time t. The acceleration sensor monitors the vibration intensity of the equipment; a baseline The reference value of the acceleration sensor, usually the vibration value during normal equipment operation, is used for comparison with real-time data; d i (t) is the displacement data collected by the ith displacement sensor at time t. The displacement sensor monitors the displacement degree of the equipment component; d baseline is the reference value of the displacement sensor, usually the displacement value during normal operation; α i, β, γ are adjustment parameters used to control the contribution of acceleration and displacement to the vibration deviation index. By adjusting these parameters, the influence of vibration and displacement on the index can be made more accurate; β1 is the exponential adjustment coefficient of acceleration data; β2 is the exponential adjustment coefficient of displacement data; β3 is the comprehensive adjustment coefficient used to adjust the scale of the calculation result; by calculating the vibration deviation index of the equipment, the abnormality of the vibration and mechanical state of the equipment is measured by the data of the acceleration and displacement sensors. The value of each sensor will be compared with the benchmark value, and the deviation will be calculated and weighted and summed. Finally, a comprehensive health assessment index is obtained through index adjustment. The larger the vibration deviation index value, the more abnormal the equipment state is, and maintenance is required;

[0049] The temperature sensor uses an infrared temperature sensor, which is used to monitor the temperature change of the equipment in real time and detect temperature anomalies. The temperature deviation index is used to analyze the temperature change value. The temperature deviation index expression formula is:

[0050]

[0051] Where, TDI(t) is the temperature deviation index; m is the number of temperature sensors; T i (t) is the temperature data collected by the i-th temperature sensor at time t; T ref,i is the reference temperature value of the i-th sensor; T avg,i (t) is the weighted average temperature value of the i-th sensor at time t; α1 is the influence of controlling the deviation between the i-th sensor temperature and the reference value; α2 is the influence of controlling the deviation between the i-th sensor weighted average temperature and the reference value; α3 is used to scale and adjust the comprehensive result; by analyzing the deviation between the temperature data and the weighted average temperature data, the temperature deviation index is calculated. If the temperature of the device exceeds the set threshold, the index becomes larger, and the device has a temperature abnormality. The temperature deviation is weighted and processed, and the index coefficient is used to control the influence of different data on the final result;

[0052] The data acquisition and transmission module optimizes bandwidth utilization by compressing data and analyzes the continuous transmission time of the data stream, thereby improving the efficiency and stability of remote transmission. The compression coefficient calculation formula is:

[0053]

[0054] Among them, k c is the data compression coefficient, used to quantify the compression effect; v i,t is the data collected by the i-th sensor at time t; v i,ref is the reference value of the i-th sensor; α i, β, γ are adjustment coefficients; n is the number of sensors; through data compression to optimize bandwidth utilization and improve remote transmission efficiency and stability, the data acquisition and transmission module adopts efficient data compression algorithms such as Huffman coding and LZ77 to compress the parameter data collected in real time to optimize bandwidth utilization; the specific compression rate is automatically adjusted according to the amount of data collected by the sensor and the transmission conditions; the compressed data is transmitted to the data processing module via wired or wireless means, effectively reducing data transmission delay and improving network bandwidth utilization efficiency, which is particularly suitable for remote monitoring and large data transmission environments;

[0055] The data processing module processes the compressed data in real time based on the threshold adjustment mechanism, and the calculation formula of its state deviation is:

[0056]

[0057] Among them, D offset is the state deviation, which indicates the degree of deviation between the equipment operating parameters and the threshold; v i,t is the operating parameter of the ith sensor at time t; v i,th is the threshold of the i-th sensor; n represents the number of sensors; when the state deviation D offset When the preset range is exceeded, the equipment operation status is judged to be abnormal; the data processing module compares the thresholds based on historical data and real-time operation parameters; the thresholds are adjusted by monitoring the normal operation range of the equipment and combining the changes in the equipment's working conditions; for example, when the equipment load increases, the threshold range will automatically widen to adapt to the new working conditions; when the equipment is running stably, the threshold will be tightened to improve the sensitivity of fault detection; by comparing the deviation between the operating parameters and the thresholds in real time, the system can promptly identify abnormal equipment status;

[0058] The aging status monitoring and prediction module uses a long short-term memory network to analyze the long-term operation trend of the equipment, identify the aging mode of the equipment, and adjust the maintenance and replacement cycle of the equipment according to the prediction results. The long short-term memory network expression formula is:

[0059]

[0060] Among them, h t is the output at time t, indicating the state prediction of the device at this time; x t is the input data at time t, usually data from sensors; is the predicted aging state output; W f is the weight matrix; b f is the bias; h t-1 is the hidden state at the previous moment t-1, which carries the previous information and is used to predict the output at the current moment; C t-1The LSTM network is the unit state at the last moment, which controls the long-term transmission of information. The LSTM network can remember long-term time series data and predict the future. In equipment status monitoring, this formula is used to predict the future status of the equipment, thereby warning of potential failures in advance. The aging status monitoring and prediction module uses the LSTM network model to analyze the historical operation data and real-time monitoring data of the equipment. The training data includes various parameter data (such as vibration, temperature, current, etc.) during the operation of the equipment, and is trained in combination with the equipment's fault records. The model predicts future operating trends by identifying the aging mode of the equipment. To ensure high-precision predictions, the model will be retrained regularly and the parameters of the prediction model will be adjusted according to the actual operating conditions of the equipment.

[0061] The alarm module not only includes a sound alarm device, but also includes the function of sending push notifications through mobile applications. The trigger judgment condition of the push notification is notified through time detection. The event detection expression formula is:

[0062]

[0063] Among them, P alert (t) represents the probability of triggering an alarm notification at time t. The larger the value, the higher the possibility of abnormal equipment status and the greater the probability of triggering an alarm notification. n represents the number of operating parameters, which represents the number of different parameters used to monitor the equipment operating status in the system, such as temperature, vibration, current, etc.; x i (t) represents the value measured by the ith sensor or parameter at time t. If the ith sensor is used to measure vibration, its value is the vibration value measured at time t; θ i It represents the set threshold value corresponding to the i-th sensor, that is, the reference value of the sensor during normal operation. The threshold value of the temperature sensor is set to a specific temperature value. If the temperature exceeds this threshold value, the device is considered abnormal. δ1 is the adjustment coefficient, which is used to control the sensor deviation in the calculation |x i (t)-θ i |The impact degree, this value can be used to amplify or reduce the contribution of sensor deviation to the alarm probability; m is the number of device state changes, m represents the total number of sensors or the number of related states that need to be compared; x j (t) represents the state parameter measured by the jth sensor at time t; θ j represents the threshold value set for the jth sensor. Each sensor has its own normal range, and an alarm may be triggered if it exceeds the range; x j(t-1) is the state parameter measured by the j-th sensor at time t-1, indicating the device state at the previous moment t-1, and is used to compare with the state at the current moment to detect state changes; δ2 is the degree of influence of adjusting the deviation between the j-th sensor measurement value and the set threshold on the alarm probability; δ3 is the influence of adjusting the change between the current value and the value at the previous moment of the j-th sensor between two measurements on the alarm probability, and this value is used to detect whether the device state changes rapidly; δ4 is the comprehensive adjustment coefficient, which is used to control the scale and influence of the entire formula, and it affects the weight of each sensor state change in the calculation; The current measurement value x of all sensors i (t) and its set threshold θ i By using the δ1 index for weighting, the system can amplify or reduce the contribution of the deviation to the alarm. If the deviation of a sensor is very large and the equipment is operating abnormally, its impact will be greater; In order to take into account the impact of the device's state change between time t and time t-1, and the impact of deviation from the set threshold, the alarm module not only supports static threshold alarms based on device operating parameters, but also includes a threshold alarm mechanism; when the device operating parameters exceed the set threshold range, the alarm module will promptly trigger a sound alarm and send a push notification through the mobile application; the alarm response time can be adjusted in the system settings to optimize the sensitivity and reaction speed of the alarm trigger according to different device operating scenarios, ensuring real-time and effective fault warning;

[0064] The data storage module is used to store the historical operation data, threshold range and alarm information of the equipment, and to perform trend analysis on the operation status of the equipment. The trend analysis expression formula is:

[0065]

[0066] Among them, T trend is the changing trend of the operating status; v t is the equipment operating parameter at time t; is the mean of historical data; m is the total number of moments of historical data; through trend analysis, the fluctuation of equipment operation status is judged to provide a basis for equipment maintenance strategy. The data storage module adopts a distributed storage architecture to support efficient storage and management of large amounts of data; historical operation data, threshold ranges and alarm information are recorded in real time and backed up regularly to ensure data integrity and security; the data storage module uses efficient data compression and deduplication algorithms to optimize the use of storage space; through the trend analysis function, the system can provide equipment operation trend forecasts based on historical data fluctuations to help maintenance personnel formulate reasonable maintenance and replacement strategies.

[0067] Finally: 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 principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A self-checking system for a submersible reciprocating pump drive mechanism, comprising a sensor module, a data acquisition and transmission module, a data processing module, an aging state monitoring and prediction module, an alarm module and a data storage module, characterized in that: The sensor module is used to collect the operating parameters of the submersible reciprocating pump drive mechanism in real time. The operating parameters include vibration parameters, temperature parameters, current parameters and pressure parameters. The operating parameters are collected by the vibration sensor, temperature sensor, current sensor and pressure sensor included in the sensor module respectively; The data acquisition and transmission module is used to compress the operating parameters collected by the sensor module and transmit the compressed data to the data processing module through wired or wireless transmission to optimize bandwidth utilization; The data processing module processes the compressed data in real time based on the threshold adjustment mechanism and generates a threshold that matches the equipment operation status. By comparing the operation parameters with the threshold, the deviation of the values ​​is identified and the equipment operation status is determined. The aging status monitoring and prediction module builds an aging status monitoring and prediction model based on the historical operating parameters of the equipment and the operating parameters collected in real time, and combines machine learning algorithms to analyze the operating trends of the equipment and identify abnormal conditions; The alarm module is used to detect when the equipment operating parameters exceed the set threshold range and send out an alarm signal to indicate abnormal equipment operation; The data storage module is used to record the historical operating data, threshold range and alarm information of the equipment, and perform trend analysis on the operating status of the equipment.

2. A self-checking system for a submersible reciprocating pump drive mechanism according to claim 1, characterized in that: Vibration sensors include acceleration sensors and displacement sensors. Acceleration sensors monitor the vibration intensity and frequency of the drive mechanism, and displacement sensors monitor the displacement changes of internal components of the equipment. Vibration analysis is performed through the vibration deviation index, and the vibration deviation index expression formula is: Where VDI(t) is the vibration deviation index, which indicates the vibration health status of the equipment calculated at time t; n is the number of sensors collecting data; a i (t) is the vibration data collected by the i-th acceleration sensor at time t; a baseline is the reference value of the acceleration sensor; d i (t) is the displacement data collected by the i-th displacement sensor at time t; d baseline is the reference value of the displacement sensor; β1 is the exponential adjustment coefficient of the acceleration data; β2 is the exponential adjustment coefficient of the displacement data; β3 is the comprehensive adjustment coefficient.

3. A self-checking system for a submersible reciprocating pump drive mechanism according to claim 2, characterized in that: The temperature sensor uses an infrared temperature sensor, which is used to monitor the temperature change of the equipment in real time and detect temperature anomalies. The temperature deviation index is used to analyze the temperature change value. The temperature deviation index expression formula is: Where, TDI(t) is the temperature deviation index; m is the number of temperature sensors; T i (t) is the temperature data collected by the i-th temperature sensor at time t; T ref,i is the reference temperature value of the i-th sensor; T avg,i (t) is the weighted average temperature value of the i-th sensor at time t; α1 is the influence of controlling the deviation between the i-th sensor temperature and the reference value; α2 is the influence of controlling the deviation between the i-th sensor weighted average temperature and the reference value; α3 is used to scale and adjust the comprehensive result.

4. A self-checking system for a submersible reciprocating pump drive mechanism according to claim 3, characterized in that: The data acquisition and transmission module optimizes bandwidth utilization by compressing data and analyzing the continuous transmission time of the data stream. The compression coefficient calculation formula is: Among them, k c is the data compression coefficient, used to quantify the compression effect; v i,t is the data collected by the i-th sensor at time t; v i,ref is the reference value of the i-th sensor; α i , β, γ are adjustment coefficients; n is the number of sensors.

5. A self-checking system for a submersible reciprocating pump drive mechanism according to claim 4, characterized in that: The data processing module processes the compressed data in real time through the threshold adjustment mechanism, and the calculation formula of its state deviation is: Among them, D offset is the state deviation, which indicates the degree of deviation between the equipment operating parameters and the threshold; v i,t is the operating parameter of the ith sensor at time t; v i,th is the threshold of the i-th sensor; n represents the number of sensors.

6. A self-checking system for a submersible reciprocating pump drive mechanism according to claim 5, characterized in that: The aging status monitoring and prediction module uses a long short-term memory network to analyze the long-term operation trend of the equipment, identify the aging mode of the equipment, and adjust the maintenance and replacement cycle of the equipment according to the prediction results. The long short-term memory network expression formula is: Among them, h t is the output at time t; x t is the input data at time t; is the predicted aging state output; W f is the weight matrix; b f is the bias; h t-1 is the hidden state at the previous moment t-1; C t-1 is the unit status at the previous moment.

7. A self-checking system for a submersible reciprocating pump drive mechanism according to claim 6, characterized in that: The alarm module not only includes a sound alarm device, but also includes the function of sending push notifications through mobile applications. The trigger judgment condition of the push notification is notified through time detection. The event detection expression formula is: Among them, P alert (t) represents the probability of triggering an alarm notification at time t; n represents the number of operating parameters; x i (t) represents the value measured by the ith sensor or parameter at time t. If the ith sensor is used to measure vibration, its value is the vibration value measured at time t; θ i represents the set threshold corresponding to the i-th sensor; δ1 is the adjustment coefficient; m is the number of device state changes; x j (t) represents the state parameter measured by the jth sensor at time t; θ j represents the threshold value set by the jth sensor; x j (t-1) is the state parameter measured by the j-th sensor at time t-1; δ2 is the influence of adjusting the deviation between the measured value of the j-th sensor and the set threshold on the alarm probability; δ3 is the influence of the change between the current value and the value of the previous moment between two measurements of the j-th sensor on the alarm probability; δ4 is the comprehensive adjustment coefficient.

8. A self-checking system for a submersible reciprocating pump drive mechanism according to claim 7, characterized in that: The data storage module is used to store the historical operation data, threshold range and alarm information of the equipment, and to perform trend analysis on the operation status of the equipment. The trend analysis expression formula is: Among them, T trend is the changing trend of the operating status; v t is the equipment operating parameter at time t; is the mean of historical data; m is the total number of moments of historical data; through trend analysis, the fluctuation of equipment operation status can be judged to provide a basis for equipment maintenance strategy.

Images