Reciprocating compressor oil product online monitoring method based on Internet of Things

Abstract

The invention discloses a reciprocating compressor oil product on-line monitoring method based on the Internet of Things, which comprises the following steps: S1, arranging an oil product detection sensor on a lubricating oil way of a compressor crankcase, the oil product detection sensor comprises a viscosity sensor, a moisture sensor, a pollution degree sensor, a wear particle sensor, a density sensor and a temperature sensor; s2, a data acquisition module acquires data detected by the oil product detection sensor and transmits the data to an upper computer system, and the upper computer system comprises a data analysis module, a monitoring alarm module, a fault diagnosis module and a service life prediction module; wherein the data analysis module is used for calculating and analyzing the online monitoring data of the oil product of the crankcase of the compressor. According to the invention, real-time monitoring of lubricating oil can be realized, parameters are uploaded to the upper computer through the Internet of Things to complete functions of parameter display, fault diagnosis and the like, and accidents are prevented.

Description

Technical Field

[0001] The present invention relates to the technical field of oil monitoring, and more specifically, to an online oil product monitoring method for a reciprocating compressor based on the Internet of Things. Background Art

[0002] Reciprocating compressors are widely used in petrochemical processes, gas transportation and storage due to their advantages of high exhaust pressure, high thermal efficiency and strong adaptability. They are generally an important link in the industry. The failure of reciprocating compressors will cause the shutdown of the entire equipment or process flow, resulting in immeasurable losses. The lubrication system is the core system of the compressor. With the operation of the compressor and the passage of time, the lubricating oil will age and acidify, and be contaminated by impurities such as water, metal particles, corrosive substances, carbon deposits, sludge, paint film, dust, etc. These factors will seriously reduce the quality of the lubricating oil, thereby affecting the normal operation of the reciprocating compressor.

[0003] Traditional lubricating oil monitoring uses an offline sampling method to regularly monitor the quality of the compressor's lubricating oil. However, the offline detection periodicity is low and the data repeatability is poor, resulting in a lag in the actual status information of the lubricating oil quality monitoring. In addition, contamination may occur during the process. Summary of the invention

[0004] The purpose of the present invention is to provide an online monitoring system for reciprocating compressor oil quality based on the Internet of Things, which can realize real-time monitoring of lubricating oil, upload data to a host computer through the Internet of Things to complete parameter display and fault diagnosis functions, and prevent accidents.

[0005] The technical solution adopted by the present invention to solve this technical problem is: an online monitoring method for reciprocating compressor oil based on the Internet of Things, comprising the following steps: S1. Installing an oil detection sensor on the lubricating oil circuit of the compressor crankcase, wherein the oil detection sensor includes a viscosity sensor, a moisture sensor, a contamination sensor, a wear particle sensor, a density sensor and a temperature sensor; S2, the data acquisition module collects the data detected by the oil detection sensor and transmits it to the host computer system, which includes a data analysis module, a monitoring and alarm module, a fault diagnosis module and a life prediction module; The data analysis module is used to calculate and analyze the online monitoring data of the compressor crankcase oil, and to display the lubricating oil viscosity, temperature, moisture content and wear particle parameters of the monitored oil in real time; The monitoring and alarm module sets the thresholds of various oil parameters. The monitoring and alarm module receives the oil parameters calculated by the data analysis module and compares them with the corresponding thresholds. If the oil parameters exceed the thresholds, the monitoring and alarm module issues an alarm message and displays it on the host computer interface of the host computer system to notify the operator. The fault diagnosis module generates preliminary diagnosis results for abnormal monitoring data using fault algorithms; The life prediction module predicts the remaining life of the oil currently in use based on the current physical, chemical, pollution and wear indicators of the oil, evaluates various indicators, and gives specific treatment suggestions based on the oil status.

[0006] As a further solution of the present invention, the data acquisition module is connected to the Internet of Things module, and the Internet of Things module sends the collected parameters to the cloud server via 4G / 5G signals.

[0007] As a further solution of the present invention, the host computer system is connected to the cloud server via wired or wireless connection; the cloud server stores the parameters calculated and analyzed by the data analysis module and supports query and export of historical data and alarm records, and automatically generates reports.

[0008] As a further solution of the present invention, the alarm information includes the over-limit index, over-limit value, over-limit time and related processing results.

[0009] As a further solution of the present invention, the specific diagnosis method of the fault diagnosis module is: when the compressor is shut down or running, the online / offline data (viscosity, density, wear particles, water content, contamination, temperature) of the oil monitoring system sensor is trained with a hidden semi-Markov model HSMM to obtain a compressor lubricating oil fault model library, and the online collected data is input into the fault model library for diagnosis and analysis to obtain the health status of the lubricating oil; The monitoring and alarm module sets the lubricant product health status alarm limit. When the detected lubricant product health status exceeds the lubricant product health status alarm limit, the monitoring and alarm module sends out an alarm message.

[0010] As a further solution of the present invention, the specific prediction method of the life prediction module is: Step 1: Parameter training; construct a hidden semi-Markov model HSMM, use the expectation maximization algorithm EM algorithm to train the model (parameter estimation), and estimate model parameters such as state transition probability; Step 2: Calculation of state duration: Through model parameter estimation, the probability density function of each state duration can be obtained, from which the mean and variance of the state duration can be calculated; Step 3: Life prediction: The remaining effective life of the compressor lubricant is determined by the Viterbi algorithm based on the model parameters and the online or offline oil monitoring system sensor data. The calculation is as follows: For state i at time t, the remaining duration Dt(i) of the state is: Indicates that in the observation sequence Under the condition of , the probability of the state being i at time t+1 and the remaining duration being d, but not the probability of the remaining life being d at time i; therefore: The remaining life in state i at time t is: .

[0011] As a further solution of the present invention, an oil detection sensor, a data acquisition module and an Internet of Things module are arranged in an explosion-proof electric control box, and the explosion-proof electric control box is installed and fixed on a skid around the crankcase through a floor bracket.

[0012] The present invention includes at least the following beneficial effects: the compressor oil online monitoring system can perform real-time online monitoring of the viscosity, density, contamination, wear particles, and temperature parameters of the oil in use through sensors when the unit is operating normally, and can predict the operating conditions and status of the compressor and diagnose abnormal components based on changes in the monitored oil parameters.

[0013] Ensure the healthy operation of reciprocating compressors, avoid expensive unexpected shutdowns in petrochemical enterprises, optimize the manual inspection process, assist in equipment maintenance, greatly reduce maintenance costs and time cycles, and reduce the risk of unexpected shutdowns, thereby improving the level of intelligence.

[0014] Other advantages, objectives and features of the present invention will be embodied in part through the following description, and in part will be understood by those skilled in the art through study and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the arrangement of the oil product detection sensor of the present invention; Figure 2 It is a diagnostic flow chart of the fault diagnosis module of the present invention; Figure 3 It is a prediction flow chart of the life prediction module of the present invention. DETAILED DESCRIPTION

[0016] The present invention is described in detail and completely below in conjunction with the accompanying drawings. A person of ordinary skill in the art will be able to implement the present invention based on these descriptions. Before describing the present invention in conjunction with the accompanying drawings, it should be particularly pointed out that the technical solutions and technical features provided in each part of the present invention, including the following description, can be combined with each other without conflict.

[0017] In addition, the embodiments of the present invention involved in the following description are generally only a part of the embodiments of the present invention, rather than all the embodiments. Therefore, based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0018] The present invention is further described in detail below in conjunction with the accompanying drawings and implementations, and its specific implementation process is as follows: The present invention provides an online monitoring method for oil products of a reciprocating compressor based on the Internet of Things, comprising the following steps: S1. Install an oil quality detection sensor on the compressor crankcase lubricating oil circuit. The oil quality detection sensor includes a viscosity sensor, a moisture sensor, a contamination sensor, a wear particle sensor, a density sensor and a temperature sensor. Figure 1 As shown, the main oil circuit of the compressor crankcase lubricating oil is: bottom of the crankcase → VL1 manual ball valve → compressor lubricating oil station → built-in oil channel lubrication point of the machine body → compressor crankcase, where the main oil circuit is a 2-inch stainless steel oil pipe, with flange connections at both ends of VL1.

[0019] The rear end of VL1 adds a branch of the oil inlet of the compressor oil online monitoring system, which is a 1 / 4-inch stainless steel oil pipe. VL2 is a manual ball valve for the branch of the oil online monitoring system, which is connected to the branch oil pipe with a stainless steel ferrule. Because the oil inlet is close to normal pressure, a 24VDC oil pump is installed in the explosion-proof electric control box to generate pressure in the lubricating oil sampling branch. The lubricating oil is detected by the viscosity sensor, moisture sensor, contamination sensor, wear particle sensor, density sensor and temperature sensor and then returns to the crankcase of the engine body. The sensor and the electric control box meet the requirements of the explosion-proof area level, not less than EXdIIBT4, and the protection level is not less than IP65.

[0020] An NPT 1 / 2 explosion-proof gland is set at the bottom of the electric control cabinet for the 220V AC power supply line, which is then converted to 24VDC through a switch power supply.

[0021] The sensor is connected to the data acquisition module via the terminal block. The data acquisition module transmits the data of the oil detection sensor to the IoT module via the RS485 or RJ45 interface. The IoT module sends the collected parameters to the cloud server via 4G / 5G signals. The cloud server receives the data and stores it in the database. The electrical control cabinet is equipped with an external antenna to enhance the transmission signal.

[0022] S2, the data acquisition module collects the data detected by the oil detection sensor and transmits it to the host computer system, which includes a data analysis module, a monitoring and alarm module, a fault diagnosis module and a life prediction module; The data analysis module is used to calculate and analyze the online monitoring data of the compressor crankcase oil, and to display the lubricating oil viscosity, temperature, moisture content and wear particle parameters of the monitored oil in real time; The monitoring and alarm module sets the thresholds of various oil parameters. The monitoring and alarm module receives the oil parameters calculated by the data analysis module and compares them with the corresponding thresholds. If the oil parameters exceed the thresholds, the monitoring and alarm module issues an alarm message and displays it on the host computer interface of the host computer system to notify the operator. The fault diagnosis module generates preliminary diagnosis results for abnormal monitoring data using fault algorithms.

[0023] The life prediction module predicts the remaining life of the oil currently in use based on the current physical, chemical, pollution and wear indicators of the oil, evaluates various indicators, and gives specific treatment suggestions based on the oil status.

[0024] This technical solution may also include the following technical details to better achieve the technical effect: the data acquisition module is connected to the Internet of Things module, and the Internet of Things module sends the collected parameters to the cloud server through 4G / 5G signals.

[0025] This technical solution can also include the following technical details to better achieve the technical effect: the host computer system is connected to the cloud server via wired or wireless connection; the cloud server stores the parameters calculated and analyzed by the data analysis module and supports the query and export of historical data and alarm records, and automatically generates reports.

[0026] The technical solution may also include the following technical details to better achieve the technical effect: the alarm information includes the exceeded index, exceeded value, exceeded time and related processing results.

[0027] This technical solution may also include the following technical details to better achieve the technical effect: The specific diagnostic method of the fault diagnosis module is: Figure 2As shown, when the compressor is shut down or running, the online / offline data (viscosity, density, wear particles, water content, contamination, temperature) of the oil monitoring system sensor are trained with the hidden semi-Markov model HSMM to obtain the compressor lubricating oil fault model library, and the online collected data is input into the fault model library for diagnosis and analysis to obtain the health status of the lubricating oil; The monitoring and alarm module sets the lubricant product health status alarm limit. When the detected lubricant product health status exceeds the lubricant product health status alarm limit, the monitoring and alarm module sends out an alarm message.

[0028] This technical solution may also include the following technical details to better achieve the technical effect: The specific prediction method of the life prediction module is as follows: Figure 3 : Step 1: Parameter training; construct a hidden semi-Markov model HSMM, use the expectation maximization algorithm EM algorithm to train the model (parameter estimation), and estimate model parameters such as state transition probability; Step 2: Calculation of state duration: Through model parameter estimation, the probability density function of each state duration can be obtained, from which the mean and variance of the state duration can be calculated; Step 3: Life prediction: The remaining effective life of the compressor lubricant is determined by the Viterbi algorithm based on the model parameters and the online or offline oil monitoring system sensor data. The calculation is as follows: For state i at time t, the remaining duration Dt(i) of the state is: Indicates that in the observation sequence Under the condition of , the probability of the state being i at time t+1 and the remaining duration being d, but not the probability of the remaining life being d at time i; therefore: The remaining life in state i at time t is: .

[0029] This technical solution may also include the following technical details to better achieve the technical effect: the oil detection sensor, data acquisition module and Internet of Things module are arranged in an explosion-proof electric control box, and the explosion-proof electric control box is installed and fixed on the skid around the crankcase through a floor bracket.

[0030] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes. They can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the embodiments shown and described herein.

Claims

1. A reciprocating compressor oil online monitoring method based on the Internet of Things, characterized in that: The following steps are involved: S1. Installing an oil detection sensor on the lubricating oil circuit of the compressor crankcase, wherein the oil detection sensor includes a viscosity sensor, a moisture sensor, a contamination sensor, a wear particle sensor, a density sensor and a temperature sensor; S2, the data acquisition module collects the data detected by the oil detection sensor and transmits it to the host computer system, which includes a data analysis module, a monitoring and alarm module, a fault diagnosis module and a life prediction module; The data analysis module is used to calculate and analyze the online monitoring data of the compressor crankcase oil, and to display the lubricating oil viscosity, temperature, moisture content and wear particle parameters of the monitored oil in real time; The monitoring and alarm module sets the thresholds of various oil parameters. The monitoring and alarm module receives the oil parameters calculated by the data analysis module and compares them with the corresponding thresholds. If the oil parameters exceed the thresholds, the monitoring and alarm module issues an alarm message and displays it on the host computer interface of the host computer system. The fault diagnosis module generates preliminary diagnosis results for abnormal monitoring data using fault algorithms; The life prediction module predicts the remaining life of the oil currently in use based on the current physical, chemical, pollution and wear indicators of the oil, evaluates various indicators, and gives specific treatment suggestions based on the oil status.

2. The online monitoring method for reciprocating compressor oil based on the Internet of Things according to claim 1, characterized in that: The data acquisition module is connected to the Internet of Things module, and the Internet of Things module sends the collected parameters to the cloud server via 4G / 5G signals.

3. The online monitoring method for reciprocating compressor oil based on the Internet of Things according to claim 2, characterized in that: The host computer system is connected to the cloud server via wired or wireless connection; The cloud server stores the parameters calculated and analyzed by the data analysis module and supports the query and export of historical data and alarm records, and automatically generates reports.

4. The online monitoring method for reciprocating compressor oil based on the Internet of Things according to claim 1, characterized in that: The alarm information includes the exceeded index, exceeded value, exceeded time and related processing results.

5. The online monitoring method for reciprocating compressor oil based on the Internet of Things according to claim 1, characterized in that: The specific diagnostic method of the fault diagnosis module is as follows: when the compressor is shut down or running, the online / offline data of the oil monitoring system sensor is trained with the hidden semi-Markov model HSMM to obtain the compressor lubricating oil fault model library, and the online collected data is input into the fault model library for diagnostic analysis to obtain the health status of the lubricating oil; The monitoring and alarm module sets the lubricant product health status alarm limit. When the detected lubricant product health status exceeds the lubricant product health status alarm limit, the monitoring and alarm module sends out an alarm message.

6. The online monitoring method for reciprocating compressor oil based on the Internet of Things according to claim 1, characterized in that: The specific prediction method of the life prediction module is: Step 1: Parameter training: construct a hidden semi-Markov model HSMM, use the expectation maximization algorithm EM algorithm to train the model, and estimate model parameters such as state transition probability; Step 2: Calculation of state duration: Through model parameter estimation, the probability density function of each state duration can be obtained, from which the mean and variance of the state duration can be calculated; Step 3: Lifespan prediction; The remaining useful life of the compressor lubricant is determined by the Viterbi algorithm based on the model parameters and the online or offline oil monitoring system sensor data. The calculation is as follows: For state i at time t, the remaining duration Dt(i) of the state is: Indicates that in the observation sequence Under the condition of , the probability of the state being i at time t+1 and the remaining duration being d, but not the probability of the remaining life being d at time i; therefore: The remaining life in state i at time t is: 。 7. The online monitoring method for reciprocating compressor oil based on the Internet of Things according to claim 1, characterized in that: The oil detection sensor, data acquisition module and Internet of Things module are arranged in an explosion-proof electric control box, and the explosion-proof electric control box is installed and fixed on the skid around the crankcase through a floor bracket.

Images