CN117662445B - Nitrogen compressor operation control method and system - Google Patents
Nitrogen compressor operation control method and system Download PDFInfo
- Publication number
- CN117662445B CN117662445B CN202410123625.0A CN202410123625A CN117662445B CN 117662445 B CN117662445 B CN 117662445B CN 202410123625 A CN202410123625 A CN 202410123625A CN 117662445 B CN117662445 B CN 117662445B
- Authority
- CN
- China
- Prior art keywords
- pressure
- nitrogen
- inlet
- low
- backlog
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 title claims abstract description 771
- 229910052757 nitrogen Inorganic materials 0.000 title claims abstract description 385
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012544 monitoring process Methods 0.000 claims abstract description 85
- 230000004044 response Effects 0.000 claims abstract description 19
- 230000003993 interaction Effects 0.000 claims abstract description 7
- 238000000926 separation method Methods 0.000 claims description 61
- 230000003213 activating effect Effects 0.000 claims description 20
- 238000013528 artificial neural network Methods 0.000 claims description 15
- 238000007418 data mining Methods 0.000 claims description 15
- 238000005457 optimization Methods 0.000 claims description 14
- 238000004364 calculation method Methods 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 7
- 238000010926 purge Methods 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 4
- 230000007246 mechanism Effects 0.000 abstract description 6
- 238000006243 chemical reaction Methods 0.000 abstract description 4
- 238000004422 calculation algorithm Methods 0.000 description 16
- 230000001276 controlling effect Effects 0.000 description 7
- 238000012549 training Methods 0.000 description 7
- 230000002452 interceptive effect Effects 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000000611 regression analysis Methods 0.000 description 3
- 238000007619 statistical method Methods 0.000 description 3
- 238000012795 verification Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 2
- 238000009412 basement excavation Methods 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000033228 biological regulation Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005265 energy consumption Methods 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000010438 heat treatment Methods 0.000 description 2
- 238000012417 linear regression Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000002922 simulated annealing Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000012300 Sequence Analysis Methods 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 239000000112 cooling gas Substances 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 229910001873 dinitrogen Inorganic materials 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 239000007789 gas Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013450 outlier detection Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000012495 reaction gas Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
- 238000013022 venting Methods 0.000 description 1
Landscapes
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The application provides a nitrogen press operation control method and system, and relates to the technical field of nitrogen press control, wherein the method comprises the following steps: when the shutdown state is switched, the interaction flow sensor receives a nitrogen flow monitoring value, loads the response time of the emptying valve, generates inlet nitrogen backlog quantity, then receives inlet temperature of the low-pressure nitrogen compressor, activates the inlet pressure prediction component to obtain inlet nitrogen pressure of the low-pressure nitrogen compressor, and opens the emptying switching valve to a first preset opening degree when the inlet nitrogen pressure of the low-pressure nitrogen compressor is greater than or equal to the inlet threshold pressure of the low-pressure nitrogen compressor. The method mainly solves the problems that the existing method has limitations, lacks a quick response and automatic control mechanism, cannot timely release redundant nitrogen flow, and causes the aggravation of system pressure fluctuation. By adding the emptying switching valve with larger shunt quantity, the emptying can be responded in time. The risk of chain reaction caused by emergency stop of the medium-pressure nitrogen press is reduced.
Description
Technical Field
The application relates to the technical field of nitrogen compressor control, in particular to a nitrogen compressor operation control method and system.
Background
In many industrial processes, such as chemical industry, steel, electronics, etc., high purity nitrogen is required as a shielding gas, a reaction gas, or a cooling gas. In these applications, the pressure and purity of the nitrogen must be precisely controlled to ensure product quality and production safety. The medium-low pressure nitrogen compressor is used as a core equipment for compressing nitrogen, and the medium-low pressure nitrogen compressor work cooperatively. However, when the medium-pressure nitrogen compressor encounters emergency shutdown, a large amount of nitrogen can rush to the inlet of the low-pressure nitrogen compressor due to the lag of air separation amount adjustment, so that the inlet pressure is instantaneously increased, and the linkage shutdown mechanism of the low-pressure nitrogen compressor is triggered. The existing method mainly aims at solving the problem of overrun of the inlet pressure of the low-pressure nitrogen compressor during emergency shutdown of the medium-pressure nitrogen compressor by adjusting the opening of a valve, controlling the flow of nitrogen and optimizing the layout of a nitrogen pipe network.
However, in the process of implementing the technical scheme of the invention in the embodiment of the application, the above technology is found to have at least the following technical problems:
the existing method has limitations, lacks a quick response and automatic control mechanism, and cannot release excessive nitrogen flow in time, so that the problem of aggravation of system pressure fluctuation is caused.
Disclosure of Invention
The method mainly solves the problems that the existing method has limitations, lacks a quick response and automatic control mechanism, cannot timely release redundant nitrogen flow, and causes the aggravation of system pressure fluctuation.
In view of the foregoing, the present application provides a nitrogen press operation control method and system, and in a first aspect, the present application provides a nitrogen press operation control method, where the method includes: when the medium-pressure nitrogen compressor is switched to a shutdown state, the flow sensor is interacted to receive a nitrogen flow monitoring value; loading the response time of an air separation vent valve, and carrying out nitrogen backlog prediction by combining the nitrogen flow monitoring value to generate the nitrogen backlog quantity of the inlet of the low-pressure nitrogen compressor; an interaction temperature sensor for receiving the inlet temperature of the low-pressure nitrogen compressor; activating a low-pressure nitrogen compressor inlet pressure prediction component, and responding to the nitrogen backlog quantity of the low-pressure nitrogen compressor inlet and the inlet temperature of the low-pressure nitrogen compressor to obtain the nitrogen pressure of the low-pressure nitrogen compressor inlet; and when the nitrogen pressure at the inlet of the low-pressure nitrogen compressor is greater than or equal to the threshold pressure of the inlet of the low-pressure nitrogen compressor, opening the air release switching valve to a first preset opening degree.
In a second aspect, the present application provides a nitrogen press operation control system, the system comprising: the monitoring value acquisition module is used for interacting the flow sensor and receiving the nitrogen flow monitoring value when the medium-pressure nitrogen press is switched to a stop state; the nitrogen backlog generation module is used for loading the response time of the air separation vent valve, and carrying out nitrogen backlog prediction by combining the nitrogen flow monitoring value to generate the nitrogen backlog of the inlet of the low-pressure nitrogen compressor; the inlet temperature receiving module is used for receiving the inlet temperature of the low-pressure nitrogen compressor through the interaction temperature sensor; the inlet nitrogen pressure acquisition module is used for activating a low-pressure nitrogen compressor inlet pressure prediction assembly, responding to the low-pressure nitrogen compressor inlet nitrogen backlog and the low-pressure nitrogen compressor inlet temperature, and acquiring low-pressure nitrogen compressor inlet nitrogen pressure; the emptying switching valve opening module is used for opening the emptying switching valve to a first preset opening degree when the nitrogen pressure of the inlet of the low-pressure nitrogen compressor is larger than or equal to the threshold pressure of the inlet of the low-pressure nitrogen compressor.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
the application provides a nitrogen press operation control method and system, and relates to the technical field of nitrogen press control, wherein the method comprises the following steps: when the shutdown state is switched, the interaction flow sensor receives a nitrogen flow monitoring value, loads the response time of the emptying valve, generates inlet nitrogen backlog quantity, then receives inlet temperature of the low-pressure nitrogen compressor, activates the inlet pressure prediction component to obtain inlet nitrogen pressure of the low-pressure nitrogen compressor, and opens the emptying switching valve to a first preset opening degree when the inlet nitrogen pressure of the low-pressure nitrogen compressor is greater than or equal to the inlet threshold pressure of the low-pressure nitrogen compressor.
The method mainly solves the problems that the existing method has limitations, lacks a quick response and automatic control mechanism, cannot timely release redundant nitrogen flow, and causes the aggravation of system pressure fluctuation. By adding the emptying switching valve with larger shunt quantity, the emptying can be responded in time. The risk of chain reaction caused by emergency stop of the medium-pressure nitrogen press is reduced.
The foregoing description is merely an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
For a clearer description of the technical solutions of the present application or of the prior art, the drawings used in the description of the embodiments or of the prior art will be briefly described below, it being obvious that the drawings in the description below are only exemplary and that other drawings can be obtained, without inventive effort, by a person skilled in the art from the drawings provided.
Fig. 1 is a schematic flow chart of a nitrogen press operation control method according to an embodiment of the present application;
fig. 2 is a schematic flow chart of a method for opening an air release switching valve to a second preset opening in a nitrogen press operation control method according to an embodiment of the present application;
fig. 3 is a schematic flow chart of a method for controlling an air separation vent valve in a nitrogen press operation control method according to an embodiment of the present application;
fig. 4 is a schematic structural diagram of a nitrogen press operation control system according to an embodiment of the present application.
Reference numerals illustrate: the system comprises a monitoring value acquisition module 10, a nitrogen backlog generation module 20, an inlet temperature receiving module 30, an inlet nitrogen pressure acquisition module 40 and a vent switching valve opening module 50.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings of the embodiments of the present application, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The method mainly solves the problems that the existing method has limitations, lacks a quick response and automatic control mechanism, cannot timely release redundant nitrogen flow, and causes the aggravation of system pressure fluctuation. By adding the emptying switching valve with larger shunt quantity, the emptying can be responded in time. The risk of chain reaction caused by emergency stop of the medium-pressure nitrogen press is reduced.
For a better understanding of the foregoing technical solutions, the following detailed description will be given with reference to the accompanying drawings and specific embodiments of the present invention:
examples
The method for controlling the operation of the nitrogen compressor is applied to a medium-low pressure nitrogen compressor, the medium-low pressure nitrogen compressor comprises a medium-pressure nitrogen compressor and a low-pressure nitrogen compressor, the medium-pressure nitrogen compressor is provided with an air release switching valve, and the method comprises the following steps:
when the medium-pressure nitrogen compressor is switched to a shutdown state, the flow sensor is interacted to receive a nitrogen flow monitoring value;
specifically, when the medium-pressure nitrogen press is switched to a shutdown state, the interactive flow sensor can monitor the flow of nitrogen in real time. The interactive flow sensor can detect the flow of nitrogen in real time and provide continuous monitoring data. By comparing the real-time flow data with a preset normal operation value, whether the flow is abnormal or not can be timely found, for example, the flow suddenly drops or rises, which possibly indicates that the equipment has faults or abnormal operation. The monitored values can be used to control the supply and pressure of nitrogen. By receiving the nitrogen flow data, the control system can adjust the running state of the nitrogen press in real time, and ensures stable supply and accurate pressure control of nitrogen. Through the flow of real-time supervision nitrogen gas, provide continuous monitoring data and control feedback, help guaranteeing stability and the security of nitrogen press operation, improve production efficiency and product quality, reduce energy consumption and emission, promote industrial production's sustainable development.
Loading the response time of an air separation vent valve, and carrying out nitrogen backlog prediction by combining the nitrogen flow monitoring value to generate the nitrogen backlog quantity of the inlet of the low-pressure nitrogen compressor;
specifically, response time length data of the air separation vent valve under different conditions is collected and recorded by installing a sensor on the air separation vent valve or using an existing monitoring system. Including the time the valve takes from the receipt of the command to the actual start of the action and the time it takes for the valve to fully open or close. Based on the obtained response time data, the response behavior of the air vent valve is modeled using an appropriate mathematical model (e.g., regression analysis, neural network, etc.). The model will be used to predict the response behavior of the air separation blow-down valve under different flow and pressure conditions. And a prediction algorithm (such as time sequence analysis, kalman filtering and the like) is used for predicting the nitrogen backlog by combining the response model of the air separation vent valve and the nitrogen flow monitoring data. And according to the prediction result, calculating the nitrogen backlog quantity at the inlet of the low-pressure nitrogen compressor. By scaling the predicted backlog with the inlet size and pressure of the low pressure nitrogen compressor.
An interaction temperature sensor for receiving the inlet temperature of the low-pressure nitrogen compressor;
Specifically, the temperature of the inlet of the low-pressure nitrogen compressor can be monitored in real time, and key feedback information is provided for a control system. The temperature is an important indicator of the operating state of the nitrogen compressor. By monitoring the inlet temperature, the temperature change and heat utilization of the nitrogen can be known. The temperature sensor is capable of detecting the inlet temperature in real time and transmitting data to the control system. The control system adjusts the operation parameters of the nitrogen compressor, such as air inflow, heating power and the like, according to the data so as to realize accurate control of temperature. If the inlet temperature increases or decreases abnormally, it may indicate that the nitrogen compressor is malfunctioning or is operating abnormally. After the control system receives the abnormal temperature data, measures such as adjusting air inflow, reducing heating power or giving an alarm can be timely taken so as to prevent equipment damage or accidents. By collecting and analyzing historical temperature data, the heat energy utilization efficiency and the energy consumption of the nitrogen compressor can be evaluated. The method is favorable for finding out potential improvement points, and adopts energy-saving and emission-reducing measures to improve the operation efficiency and energy efficiency of the nitrogen compressor.
Activating a low-pressure nitrogen compressor inlet pressure prediction component, and responding to the nitrogen backlog quantity of the low-pressure nitrogen compressor inlet and the inlet temperature of the low-pressure nitrogen compressor to obtain the nitrogen pressure of the low-pressure nitrogen compressor inlet;
Specifically, the low pressure nitrogen compressor inlet pressure prediction assembly is activated by inputting an activation signal or a start-up program command. The assembly should have the function of monitoring and predicting the nitrogen backlog and temperature at the inlet of the low-pressure nitrogen compressor. After the low-pressure nitrogen compressor inlet pressure prediction component receives the real-time monitoring data of the inlet nitrogen backlog amount and the temperature, the low-pressure nitrogen compressor inlet pressure prediction component predicts the inlet nitrogen pressure by using a prediction algorithm (such as time series analysis, regression analysis and the like). Historical data for training the model is collected by sensor monitoring. Including historical monitoring data of inlet nitrogen backlog, temperature, etc., and corresponding inlet nitrogen pressure. And preprocessing, including data cleaning, format conversion, missing value processing, outlier detection and processing, and the like, selecting features related to inlet nitrogen pressure, calculating a correlation coefficient of each feature and the inlet nitrogen pressure to determine the correlation of the feature and the inlet nitrogen pressure, wherein the correlation coefficient is close to 1 or-1 to indicate high correlation, and can be used as input feature data to divide the collected input feature data into a training set and a verification set. The training set is used to train and optimize the model, and the validation set is used to evaluate the performance of the model. The partitioning of the data set is ensured to be representative and to meet a certain proportion (e.g. 70% for training, 30% for verification). Initializing parameters of the model to be small random numbers close to zero, continuing model training by adopting regression analysis, fitting the model by using a training set, calculating a prediction error of the model, inputting a verification set into the model to obtain a prediction value, comparing the prediction value with actual monitoring data, and obtaining a prediction model if the error is less than 5%, and obtaining a prediction result through the prediction model. According to the prediction result, the inlet pressure prediction component of the low-pressure nitrogen compressor outputs an inlet nitrogen pressure value at the current moment. According to the obtained nitrogen pressure value at the inlet of the low-pressure nitrogen compressor, corresponding measures can be adopted for real-time adjustment and control. For example, if the inlet pressure is predicted to be too high or too low, measures such as adjusting the valve opening or starting up a standby device or the like may be taken in advance to keep the inlet pressure stable. Accurate prediction and real-time control of the inlet nitrogen pressure of the low-pressure nitrogen compressor can be realized, and the reliability and safety of the whole system are improved.
And when the nitrogen pressure at the inlet of the low-pressure nitrogen compressor is greater than or equal to the threshold pressure of the inlet of the low-pressure nitrogen compressor, opening the air release switching valve to a first preset opening degree.
Specifically, when the inlet nitrogen pressure of the low-pressure nitrogen compressor reaches or exceeds a set threshold pressure, in order to protect equipment and ensure safe operation of the system, the control system opens the vent switching valve to a first preset opening degree when the inlet nitrogen pressure is greater than or equal to the inlet threshold pressure. The threshold pressure at the inlet of the low pressure nitrogen compressor is set to ensure safe operation of the system. This pressure value is determined based on the design and operating requirements of the plant, and when the inlet nitrogen pressure exceeds this set point, it means that the system may be at risk of overload or overpressure, which may damage the plant or cause safety accidents. The function of the air release switching valve is to vent part of the nitrogen to atmosphere when necessary to reduce the pressure within the system. And opening the emptying switching valve to a first preset opening degree when the inlet nitrogen pressure reaches or exceeds the threshold pressure. The opening degree of the air discharge switching valve is adjusted, and the flow of discharged nitrogen can be controlled, so that the pressure in the system is regulated. When the inlet nitrogen pressure of the low-pressure nitrogen compressor reaches or exceeds a set threshold pressure, the control system opens the vent switching valve to a first preset opening degree so as to release the pressure in the system. Protecting the equipment and ensuring the safe operation of the system.
Further, as shown in fig. 2, the method of the present application further includes:
when the nitrogen pressure at the inlet of the low-pressure nitrogen compressor is smaller than the threshold pressure at the inlet of the low-pressure nitrogen compressor, obtaining the maximum opening of the air separation vent valve;
performing frequent data mining according to the model of the air separation emptying valve, the maximum opening of the emptying valve, the nitrogen flow monitoring value and a nitrogen pipeline topological graph to generate a first main pipeline high-frequency flow, wherein the monitoring position of the first main pipeline high-frequency flow is positioned at the downstream of the air separation emptying valve;
activating an inlet pressure prediction component of the low-pressure nitrogen compressor, and performing backlog time optimization by combining the inlet threshold pressure of the low-pressure nitrogen compressor and the high-frequency flow of the first main pipeline to generate a first backlog time prediction value;
and when the first backlog duration predicted value is smaller than or equal to the backlog duration threshold value, opening the emptying switching valve to a second preset opening.
Specifically, when the inlet nitrogen pressure is below the threshold pressure, the control system will first obtain the maximum purge valve opening of the air separation purge valve. This opening is determined based on the model and design parameters of the vent valve, and the maximum vent valve opening is obtained to ensure adequate flow and regulation when relief is desired. And carrying out frequent data mining according to the maximum vent valve opening of the air separation vent valve, the nitrogen flow monitoring value and the nitrogen pipeline topological graph. Information related to the current operating conditions and the historical data is extracted to generate a first main line high frequency flow. High frequency flow refers to flow data that is frequently monitored over a specified period of time, which data better reflects real-time changes and fluctuations within the system. By analyzing the data, more accurate flow information can be obtained, and a basis is provided for subsequent pressure prediction and control. And activating an inlet pressure prediction component of the low-pressure nitrogen compressor, and optimizing the backlog time by combining the inlet threshold pressure of the low-pressure nitrogen compressor and the high-frequency flow of the first main pipeline. And adjusting the backlog duration, predicting the inlet pressure by combining the high-frequency flow of the main line pipeline, and when the inlet pressure is equal to the inlet threshold pressure, regarding as a backlog duration predicted value, wherein the backlog duration refers to the accumulated time length of nitrogen in the system, and the parameter has important significance for predicting and controlling the inlet pressure. By combining the inlet threshold pressure and the high frequency flow of the main line pipe, a future backlog trend can be predicted, and a first backlog duration prediction value can be generated according to the trend. And comparing the first backlog duration predicted value with a preset backlog duration threshold value, and determining whether the air switching valve needs to be opened to a second preset opening degree. If the predicted value is less than or equal to the threshold value, the system is indicated as having potential backlog risk, and adjustment is needed. At this time, the control system opens the vent switching valve to a second preset opening. This opening is typically smaller than the first preset opening, aiming at slowly releasing the pressure in the system, avoiding too fast venting of nitrogen. By adjusting the opening of the air release switching valve, the control system can accurately control the discharge amount of nitrogen so as to maintain the stability of inlet pressure.
Further, as shown in fig. 3, the method of the present application further includes:
when the first backlog duration predicted value is larger than the backlog duration threshold value, judging whether the backlog duration deviation of the first backlog duration predicted value and the backlog duration threshold value is larger than or equal to the backlog duration deviation threshold value or not;
if the opening of the air separation emptying valve is larger than or equal to the preset opening, opening optimizing is carried out on the air separation emptying valve, and a third preset opening is generated;
if the opening of the maximum blow valve is smaller than the first preset opening, setting the opening of the maximum blow valve as a third preset opening;
and controlling the air separation emptying valve according to the third preset opening.
Specifically, whether the deviation of the first backlog duration predicted value and the backlog duration threshold value is larger than or equal to the backlog duration deviation threshold value is judged. Confirm whether intervention and control is required. The deviation threshold is a preset value for determining when to take action to adjust the opening of the blow-off valve. If the backlog duration deviation is greater than or equal to the deviation threshold, the backlog trend in the system is obvious, and more accurate control measures are required to be adopted. At this time, the control system may perform opening optimization on the air release valve to generate a third preset opening. The opening optimizing is an optimizing algorithm, and the opening of the emptying valve is automatically adjusted according to the current working condition and historical data so as to realize the optimal control effect. Through continuous iteration and optimization, the control system can find an opening value which can meet control requirements and avoid excessive adjustment. If the backlog duration deviation is smaller than the deviation threshold value, the backlog trend of the system is relatively light, and complex control is not needed. At this time, the maximum relief valve opening is set to the third preset opening, and simple adjustment is performed. By setting the maximum relief valve opening to a preset value, it is possible to quickly respond to pressure changes in the system, ensuring stability of the inlet pressure. According to the third preset opening, the control system can control the air release valve in real time. And according to the set opening value, the control system sends a control instruction to the vent valve, and the opening of the vent valve is adjusted to realize the required pressure regulation. By continuous monitoring and control, stability of the inlet pressure is ensured and backlog is prevented from adversely affecting the system.
Furthermore, according to the method, frequent data mining is performed according to the model of the air separation vent valve, the maximum vent valve opening, the nitrogen flow monitoring value and the nitrogen pipeline topological graph, so as to generate a first main pipeline high-frequency flow, wherein the monitoring position of the first main pipeline high-frequency flow is positioned at the downstream of the air separation vent valve, and the method comprises the following steps:
taking the model of the air separation vent valve, the maximum vent valve opening, the nitrogen flow monitoring value and the nitrogen pipeline topological graph as constraints, and searching a main pipeline record flow set at the downstream of the air separation vent valve on a nitrogen pipeline network data sharing cloud platform;
configuring a neighborhood k value, wherein the neighborhood k value represents the preset quantity of the recorded flow, k is an integer, and k is more than or equal to 5;
traversing the main line pipeline record flow set, and screening neighborhood record flow from near to far by taking the neighborhood k value as a constraint to generate a record flow neighborhood set;
traversing the neighborhood set of the recorded flow, and counting a local sparse coefficient set of the main line pipeline recorded flow set;
calculating the average value of the local sparse coefficient set to generate a local sparse coefficient average value;
calculating the ratio of the local sparse coefficient mean value to the local sparse coefficient set respectively to generate a global set of coefficients;
And deleting the main pipeline record flow which is smaller than or equal to the global concentrated coefficient set and the global concentrated coefficient threshold according to the global concentrated coefficient set, generating a main pipeline concentrated record flow set, carrying out mean value calculation, and generating the first main pipeline high-frequency flow.
Specifically, the model of the air separation emptying valve is used as a screening condition, and related data records are found on a nitrogen pipe network data sharing cloud platform. And adding the maximum opening of the emptying valve, the nitrogen flow monitoring value and the nitrogen pipeline topological graph as constraint conditions, and further reducing the search range. A flow data set of the downstream main line pipe associated with the blow-down valve is finally obtained. Selecting a neighborhood k value, e.g., k=5, indicates that it is desirable to consider the 5 neighborhood traffic data closest to the target traffic data. The main line pipeline records flow concentration, and records adjacent to the target flow data are screened out according to the time sequence (from near to far). Finally, a record flow set in a neighborhood is obtained. And carrying out statistical analysis on each flow data in the main line pipeline record flow set. Calculate their variance or deviation from the target flow. From these differences or deviations, local sparsity coefficients are derived. The local sparse coefficient mean is compared to each local sparse coefficient. A set of global-set coefficients is generated. And screening out key main pipeline record flow data according to the global concentrated coefficient set. Recording traffic whose global-set coefficients are less than or equal to the global-set coefficient threshold may be deleted. And carrying out average value calculation on the screened main line pipeline centralized record flow set. And obtaining the high-frequency flow of the first main line pipe. For example: assuming that the flow data of the main pipeline A, B, C, D downstream of the air separation vent valve in the nitrogen pipe network of a certain chemical plant are F1, F2, F3, and F4, respectively, their time series data are as follows: flow data of the downstream main line A, B, C, D associated with the vent valve is retrieved. And screening out the traffic data of the latest 5 time points of A, B, C, D as neighborhood traffic according to the time sequence data. And analyzing the difference between the flow data of A, B, C, D and the target flow to obtain the local sparse coefficient. The global set coefficients of A, B, C, D are calculated. And screening out key main pipeline data according to the global concentrated coefficients. For example, assuming that only the global set coefficients of a and B are greater than a threshold, only the data of a and B are retained. And (3) carrying out average value calculation on the data of the A and the B to obtain the high-frequency flow of the first main pipeline.
Further, the method of the present application traverses the recording flow neighborhood set, counts a local sparse coefficient set of the main line pipeline recording flow set, and includes:
extracting a first recording flow neighborhood of a first main pipeline recording flow of the main pipeline recording flow set from the recording flow neighborhood set;
counting a neighborhood record flow set of the first record flow neighborhood and a flow deviation set of the first main line pipeline record flow;
and counting the average value of the flow deviation set, setting the average value as a local sparse coefficient of the first main pipeline recorded flow, and adding the local sparse coefficient into the local sparse coefficient set.
In particular, the neighborhood most relevant or closest to the first main line pipe recording traffic is found from the set of recording traffic neighbors. And finding the nearest neighborhood by comparing the similarity or correlation of the flow data of each neighborhood and the recorded flow of the first main line pipeline. And selecting the neighborhood with the highest similarity or correlation as the first recording traffic neighborhood. And calculating the difference between each flow data in the first recorded flow neighborhood and the first main line pipeline recorded flow. This can be obtained by subtracting each flow data. All the difference values are collected into a set, called the flow deviation set. And carrying out statistical analysis on the flow deviation set, and calculating the average value of the flow deviation set. This mean value represents the local sparsity coefficient of the first main line pipe recording flow. The local sparse coefficient is the difference degree or deviation degree of the traffic of the main line and the traffic of other neighborhoods. And adding the calculated local sparse coefficient to the local sparse coefficient set. According to the global concentrated coefficient set, key flow data or main pipeline can be further screened out, and basis is provided for a control strategy. The layout of the nitrogen pipe network can be optimized, the opening of the valve can be adjusted, the future flow change can be predicted and the like according to the data. The key flow data related to the main pipeline can be extracted from the nitrogen pipe network data more accurately, and the local sparse coefficient can be calculated.
Further, in the method, when the nitrogen pressure at the inlet of the low-pressure nitrogen compressor is greater than or equal to the inlet threshold pressure of the low-pressure nitrogen compressor, the emptying switching valve is opened to a first preset opening degree, which comprises the following steps:
obtaining a valve opening interval of the emptying switching valve;
randomly obtaining a first opening assignment result based on the valve opening interval;
performing frequent data mining based on the model of the emptying switching valve, the first opening assignment result, the nitrogen flow monitoring value and a nitrogen pipeline topological graph to generate a second main pipeline high-frequency flow, wherein the monitoring position of the second main pipeline high-frequency flow is positioned at the downstream of the emptying switching valve;
activating an inlet pressure prediction component of the low-pressure nitrogen compressor, and performing backlog time optimization by combining the inlet threshold pressure of the low-pressure nitrogen compressor and the high-frequency flow of the second main pipeline to generate a second backlog time prediction value;
when the second backlog duration predicted value is larger than a backlog duration threshold value, setting the first opening assignment result as the first preset opening;
and updating the first opening assignment result based on the valve opening interval when the second backlog duration predicted value is smaller than or equal to the backlog duration threshold value.
Specifically, a valve opening section of the air release switching valve is obtained: the minimum and maximum opening ranges of the valve under different flow and pressure conditions are determined through experimental or analog calculation. For example, the minimum opening of the valve is 10% and the maximum opening is 80% under the condition that the nitrogen flow rate is 0 to 100 cubic meters per hour. Randomly obtaining a first opening assignment result based on a valve opening interval: if the valve opening interval is 30% to 60%, then one opening value, such as 45%, may be randomly selected. Frequent data mining is carried out based on the model of the air release switching valve, the first opening assignment result, the nitrogen flow monitoring value and the nitrogen pipeline topological graph, and the second main pipeline high-frequency flow is generated: and taking the model of the air release switching valve, the first opening assignment result and the nitrogen flow monitoring value as input data. And excavating the data by using a frequent pattern excavation algorithm (such as an FP-Growth algorithm) to find out the frequent pattern of the nitrogen flow in the second main pipeline. Based on these frequent patterns, a high frequency flow of the second main line pipe is generated. Activating an inlet pressure prediction component of the low-pressure nitrogen compressor, and optimizing the backlog time length by combining the inlet threshold pressure of the low-pressure nitrogen compressor and the high-frequency flow of the second main line pipeline to generate a second backlog time length predicted value: and taking the inlet threshold pressure of the low-pressure nitrogen compressor and the high-frequency flow of the second main line pipeline as input data. The inlet pressure is predicted using a prediction algorithm, such as linear regression or neural networks. And comparing the predicted result with actual pressure data, and calculating the backlog time length. And (5) according to a backlog time length optimization algorithm (such as a genetic algorithm or a simulated annealing algorithm), finding out the optimal backlog time length. Judging and updating a first opening assignment result: if the second backlog duration prediction value is greater than the backlog duration threshold: the first opening degree assignment result is set to a first preset opening degree, for example, 50%. If the second backlog duration prediction value is less than or equal to the backlog duration threshold: and updating the first opening assignment result based on the valve opening interval. For example, if the current valve opening is 45%, and the new calculation suggests a larger opening (e.g., 55%), the first opening assignment is updated to 55%.
Further, in the method, when the predicted value of the first backlog duration is less than or equal to the backlog duration threshold, the emptying switching valve is opened to a second preset opening, including:
obtaining a valve opening interval of the emptying switching valve;
randomly obtaining a second opening assignment result based on the valve opening interval;
carrying out frequent data mining by using the model of the vent switching valve, the second opening assignment result, the model of the air separation vent valve, the maximum vent valve opening, the nitrogen flow monitoring value and a nitrogen pipeline topological graph to generate a third main pipeline high-frequency flow, wherein the monitoring position of the third main pipeline high-frequency flow is positioned at the downstream of the vent switching valve and the air separation vent valve;
activating the inlet pressure prediction component of the low-pressure nitrogen compressor, and performing backlog duration optimization by combining the inlet threshold pressure of the low-pressure nitrogen compressor and the high-frequency flow of the third main pipeline to generate a third backlog duration prediction value;
when the third backlog duration predicted value is larger than a backlog duration threshold value, setting the second opening assignment result as the second preset opening;
and updating the second opening assignment result based on the valve opening interval when the third backlog duration predicted value is smaller than or equal to the backlog duration threshold.
Specifically, a valve opening section of the air release switching valve is obtained: and determining the opening interval of the valve by using a statistical analysis method according to the actual operation data. For example, according to the history data, when the nitrogen flow rate is around 50 cubic meters/hour, the opening degree of the valve ranges from 30% to 60%. And randomly obtaining a second opening assignment result based on the valve opening interval: if the valve opening interval is 30% to 60%, then one opening value, such as 55%, may be randomly selected. Carrying out frequent data mining by using the model of the emptying switching valve, the assignment result of the second opening, the model of the air separation emptying valve, the maximum opening of the emptying valve, the monitoring value of the nitrogen flow and the topological graph of the nitrogen pipeline, and generating the high-frequency flow of the third main pipeline: and taking the model of the air release switching valve, the second opening assignment result, the model of the air separation air release valve, the maximum air release valve opening and the nitrogen flow monitoring value as input data. And excavating the data by using a frequent pattern excavation algorithm (such as an FP-Growth algorithm) to find out the frequent pattern of the nitrogen flow in the third main pipeline. Based on these frequent patterns, a high frequency flow of the third main line pipe is generated. Activating an inlet pressure prediction component of the low-pressure nitrogen compressor, and optimizing the backlog time length by combining the inlet threshold pressure of the low-pressure nitrogen compressor and the high-frequency flow of the third main line pipeline to generate a third backlog time length predicted value: and taking the inlet threshold pressure of the low-pressure nitrogen compressor and the high-frequency flow of the third main line pipeline as input data. The inlet pressure is predicted using a prediction algorithm, such as linear regression or neural networks. And comparing the predicted result with actual pressure data, and calculating the backlog time length. And (5) according to a backlog time length optimization algorithm (such as a genetic algorithm or a simulated annealing algorithm), finding out the optimal backlog time length. Judging and updating a second opening assignment result: if the third backlog duration prediction value is greater than the backlog duration threshold: and setting the second opening degree assignment result as a second preset opening degree, such as 60%. If the third backlog duration prediction value is less than or equal to the backlog duration threshold: and updating the second opening assignment result based on the valve opening interval. For example, if the current valve opening is 55%, and the new calculation suggests a larger opening (e.g., 60%), the second opening assignment is updated to 60%.
Further, the method of the present application activates a low pressure nitrogen compressor inlet pressure prediction component, and obtains a low pressure nitrogen compressor inlet nitrogen pressure in response to the low pressure nitrogen compressor inlet nitrogen backlog and the low pressure nitrogen compressor inlet temperature, including:
setting the air switching valve and the air separation air switching valve in a closed state, and testing the medium-low pressure nitrogen compressor to obtain a nitrogen backlog monitoring value of an inlet of the low pressure nitrogen compressor, a temperature monitoring value of an inlet of the low pressure nitrogen compressor and a nitrogen pressure monitoring value of an inlet of the low pressure nitrogen compressor;
taking the nitrogen pressure monitoring value of the inlet of the low-pressure nitrogen compressor as supervision, and adjusting the nitrogen backlog monitoring value of the inlet of the low-pressure nitrogen compressor and the inlet temperature monitoring value of the low-pressure nitrogen compressor to configure a BP neural network so as to generate the inlet pressure prediction component of the low-pressure nitrogen compressor.
Specifically, the air release switching valve and the air separation air release valve are closed: and placing the air release switching valve and the air separation release valve in a closed state, and testing the medium-low pressure nitrogen press to ensure that the medium-low pressure nitrogen press is in a normal working state. And obtaining a nitrogen backlog monitoring value of the inlet of the low-pressure nitrogen compressor. Obtaining the inlet temperature monitoring value of the low-pressure nitrogen compressor. And obtaining a nitrogen pressure monitoring value of the inlet of the low-pressure nitrogen compressor. Configuring a BP neural network: taking the monitoring value of the inlet nitrogen pressure of the low-pressure nitrogen compressor as supervision, and taking the monitoring value of the inlet nitrogen backlog and the monitoring value of the inlet temperature. A BP neural network (back propagation neural network) is configured, and the low-pressure nitrogen compressor inlet pressure prediction component is generated by taking these monitoring values as inputs. The BP neural network is a neural network structure, and the weight and the threshold value of the neural network are continuously adjusted through a back propagation algorithm, so that the output of the network gradually approaches to an actual pressure value. And training and verifying the BP neural network by using historical data to ensure the prediction accuracy of the BP neural network. And generating a low-pressure nitrogen compressor inlet pressure prediction component based on the trained BP neural network. This assembly can predict changes in inlet pressure in real time based on the current inlet nitrogen backlog and temperature. The pressure change of the inlet of the low-pressure nitrogen compressor can be monitored and predicted in real time by using the prediction component, and a basis is provided for subsequent decisions, such as adjusting the opening degree of a valve, early warning possible pressure fluctuation and the like.
Examples
Based on the same inventive concept as the method of the nitrogen press operation control system of the previous embodiment, as shown in fig. 4, the present application provides a nitrogen press operation control system, which includes:
the monitoring value acquisition module 10 is used for receiving the monitoring value of the nitrogen flow through the interactive flow sensor when the medium-pressure nitrogen press is switched to a stop state;
the nitrogen backlog generation module 20 is used for loading the response time of the air separation vent valve, and carrying out nitrogen backlog prediction by combining the nitrogen flow monitoring value to generate the nitrogen backlog of the inlet of the low-pressure nitrogen compressor;
an inlet temperature receiving module 30, wherein the inlet temperature receiving module 30 is used for receiving the inlet temperature of the low-pressure nitrogen compressor through an interactive temperature sensor;
an inlet nitrogen pressure acquisition module 40, wherein the inlet nitrogen pressure acquisition module 40 is used for activating a low-pressure nitrogen compressor inlet pressure prediction component, responding to the low-pressure nitrogen compressor inlet nitrogen backlog and the low-pressure nitrogen compressor inlet temperature, and obtaining low-pressure nitrogen compressor inlet nitrogen pressure;
the emptying switching valve opening module 50 is used for opening the emptying switching valve to a first preset opening degree when the nitrogen pressure of the inlet of the low-pressure nitrogen compressor is greater than or equal to the threshold pressure of the inlet of the low-pressure nitrogen compressor.
Further, the system further comprises:
the predicted value judging module is used for obtaining the maximum vent valve opening of the air separation vent valve when the nitrogen pressure at the inlet of the low-pressure nitrogen compressor is smaller than the inlet threshold pressure of the low-pressure nitrogen compressor; performing frequent data mining according to the model of the air separation emptying valve, the maximum opening of the emptying valve, the nitrogen flow monitoring value and a nitrogen pipeline topological graph to generate a first main pipeline high-frequency flow, wherein the monitoring position of the first main pipeline high-frequency flow is positioned at the downstream of the air separation emptying valve; activating an inlet pressure prediction component of the low-pressure nitrogen compressor, and performing backlog time optimization by combining the inlet threshold pressure of the low-pressure nitrogen compressor and the high-frequency flow of the first main pipeline to generate a first backlog time prediction value; and when the first backlog duration predicted value is smaller than or equal to the backlog duration threshold value, opening the emptying switching valve to a second preset opening.
Further, the system further comprises:
the air separation emptying valve control module is used for judging whether the backlog duration deviation of the first backlog duration predicted value and the backlog duration threshold is greater than or equal to the backlog duration deviation threshold or not when the first backlog duration predicted value is greater than the backlog duration threshold; if the opening of the air separation emptying valve is larger than or equal to the preset opening, opening optimizing is carried out on the air separation emptying valve, and a third preset opening is generated; if the opening of the maximum blow valve is smaller than the first preset opening, setting the opening of the maximum blow valve as a third preset opening; and controlling the air separation emptying valve according to the third preset opening.
Further, the system further comprises:
the high-frequency flow generation module is used for searching a main line pipeline record flow set at the downstream of the air separation vent valve on the basis of taking the air separation vent valve model, the maximum vent valve opening, the nitrogen flow monitoring value and the nitrogen pipeline topological graph as constraints and sharing a cloud platform on nitrogen pipeline network data; configuring a neighborhood k value, wherein the neighborhood k value represents the preset quantity of the recorded flow, k is an integer, and k is more than or equal to 5; traversing the main line pipeline record flow set, and screening neighborhood record flow from near to far by taking the neighborhood k value as a constraint to generate a record flow neighborhood set; traversing the neighborhood set of the recorded flow, and counting a local sparse coefficient set of the main line pipeline recorded flow set; calculating the average value of the local sparse coefficient set to generate a local sparse coefficient average value; calculating the ratio of the local sparse coefficient mean value to the local sparse coefficient set respectively to generate a global set of coefficients; and deleting the main pipeline record flow which is smaller than or equal to the global concentrated coefficient set and the global concentrated coefficient threshold according to the global concentrated coefficient set, generating a main pipeline concentrated record flow set, carrying out mean value calculation, and generating the first main pipeline high-frequency flow.
Further, the system further comprises:
the local sparse coefficient set adding module is used for extracting a first recording flow neighborhood of the first main pipeline recording flow of the main pipeline recording flow set from the recording flow neighborhood set; counting a neighborhood record flow set of the first record flow neighborhood and a flow deviation set of the first main line pipeline record flow; and counting the average value of the flow deviation set, setting the average value as a local sparse coefficient of the first main pipeline recorded flow, and adding the local sparse coefficient into the local sparse coefficient set.
Further, the system further comprises:
the first result updating module is used for obtaining a valve opening interval of the emptying switching valve; randomly obtaining a first opening assignment result based on the valve opening interval; performing frequent data mining based on the model of the emptying switching valve, the first opening assignment result, the nitrogen flow monitoring value and a nitrogen pipeline topological graph to generate a second main pipeline high-frequency flow, wherein the monitoring position of the second main pipeline high-frequency flow is positioned at the downstream of the emptying switching valve; activating an inlet pressure prediction component of the low-pressure nitrogen compressor, and performing backlog time optimization by combining the inlet threshold pressure of the low-pressure nitrogen compressor and the high-frequency flow of the second main pipeline to generate a second backlog time prediction value; when the second backlog duration predicted value is larger than a backlog duration threshold value, setting the first opening assignment result as the first preset opening; and updating the first opening assignment result based on the valve opening interval when the second backlog duration predicted value is smaller than or equal to the backlog duration threshold value.
Further, the system further comprises:
the second result updating module is used for obtaining a valve opening interval of the emptying switching valve; randomly obtaining a second opening assignment result based on the valve opening interval; carrying out frequent data mining by using the model of the vent switching valve, the second opening assignment result, the model of the air separation vent valve, the maximum vent valve opening, the nitrogen flow monitoring value and a nitrogen pipeline topological graph to generate a third main pipeline high-frequency flow, wherein the monitoring position of the third main pipeline high-frequency flow is positioned at the downstream of the vent switching valve and the air separation vent valve; activating the inlet pressure prediction component of the low-pressure nitrogen compressor, and performing backlog duration optimization by combining the inlet threshold pressure of the low-pressure nitrogen compressor and the high-frequency flow of the third main pipeline to generate a third backlog duration prediction value; when the third backlog duration predicted value is larger than a backlog duration threshold value, setting the second opening assignment result as the second preset opening; and updating the second opening assignment result based on the valve opening interval when the third backlog duration predicted value is smaller than or equal to the backlog duration threshold.
Further, the system further comprises:
the inlet pressure prediction component generation module is used for setting the emptying switching valve and the air separation emptying valve to be in a closed state, and testing the medium-low pressure nitrogen compressor to obtain a low-pressure nitrogen compressor inlet nitrogen backlog monitoring value, a low-pressure nitrogen compressor inlet temperature monitoring value and a low-pressure nitrogen compressor inlet nitrogen pressure monitoring value; taking the nitrogen pressure monitoring value of the inlet of the low-pressure nitrogen compressor as supervision, and adjusting the nitrogen backlog monitoring value of the inlet of the low-pressure nitrogen compressor and the inlet temperature monitoring value of the low-pressure nitrogen compressor to configure a BP neural network so as to generate the inlet pressure prediction component of the low-pressure nitrogen compressor.
The foregoing detailed description of a method for controlling operation of a nitrogen press will be clear to those skilled in the art, and the system disclosed in this embodiment is described more simply because it corresponds to the device disclosed in the embodiment, and the relevant points refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. The utility model provides a nitrogen press operation control method, is characterized in that is applied to low-pressure nitrogen press, low-pressure nitrogen press and middle-pressure nitrogen press including middle-pressure nitrogen press and low-pressure nitrogen press, middle-pressure nitrogen press has the relief switching valve, includes:
when the medium-pressure nitrogen compressor is switched to a shutdown state, the flow sensor is interacted to receive a nitrogen flow monitoring value;
loading the response time of an air separation vent valve, and carrying out nitrogen backlog prediction by combining the nitrogen flow monitoring value to generate the nitrogen backlog quantity of the inlet of the low-pressure nitrogen compressor;
an interaction temperature sensor for receiving the inlet temperature of the low-pressure nitrogen compressor;
activating a low-pressure nitrogen compressor inlet pressure prediction component, and responding to the nitrogen backlog quantity of the low-pressure nitrogen compressor inlet and the inlet temperature of the low-pressure nitrogen compressor to obtain the nitrogen pressure of the low-pressure nitrogen compressor inlet;
when the nitrogen pressure at the inlet of the low-pressure nitrogen compressor is greater than or equal to the threshold pressure of the inlet of the low-pressure nitrogen compressor, opening the air release switching valve to a first preset opening;
wherein, still include:
when the nitrogen pressure at the inlet of the low-pressure nitrogen compressor is smaller than the threshold pressure at the inlet of the low-pressure nitrogen compressor, obtaining the maximum opening of the air separation vent valve;
performing frequent data mining according to the model of the air separation emptying valve, the maximum opening of the emptying valve, the nitrogen flow monitoring value and a nitrogen pipeline topological graph to generate a first main pipeline high-frequency flow, wherein the monitoring position of the first main pipeline high-frequency flow is positioned at the downstream of the air separation emptying valve;
Activating an inlet pressure prediction component of the low-pressure nitrogen compressor, and performing backlog time optimization by combining the inlet threshold pressure of the low-pressure nitrogen compressor and the high-frequency flow of the first main pipeline to generate a first backlog time prediction value;
and when the first backlog duration predicted value is smaller than or equal to the backlog duration threshold value, opening the emptying switching valve to a second preset opening.
2. The method as recited in claim 1, further comprising:
when the first backlog duration predicted value is larger than the backlog duration threshold value, judging whether the backlog duration deviation of the first backlog duration predicted value and the backlog duration threshold value is larger than or equal to the backlog duration deviation threshold value or not;
if the opening of the air separation emptying valve is larger than or equal to the preset opening, opening optimizing is carried out on the air separation emptying valve, and a third preset opening is generated;
if the opening of the maximum blow valve is smaller than the first preset opening, setting the opening of the maximum blow valve as a third preset opening;
and controlling the air separation emptying valve according to the third preset opening.
3. The method of claim 1, wherein frequent data mining is performed according to an air separation purge valve model, the maximum purge valve opening, the nitrogen flow monitor value, and a nitrogen pipeline topology map to generate a first main pipeline high frequency flow, wherein a monitor location of the first main pipeline high frequency flow is located downstream of the air separation purge valve, comprising:
Taking the model of the air separation vent valve, the maximum vent valve opening, the nitrogen flow monitoring value and the nitrogen pipeline topological graph as constraints, and searching a main pipeline record flow set at the downstream of the air separation vent valve on a nitrogen pipeline network data sharing cloud platform;
configuring a neighborhood k value, wherein the neighborhood k value represents the preset quantity of the recorded flow, k is an integer, and k is more than or equal to 5;
traversing the main line pipeline record flow set, and screening neighborhood record flow from near to far by taking the neighborhood k value as a constraint to generate a record flow neighborhood set;
traversing the neighborhood set of the recorded flow, and counting a local sparse coefficient set of the main line pipeline recorded flow set;
calculating the average value of the local sparse coefficient set to generate a local sparse coefficient average value;
calculating the ratio of the local sparse coefficient mean value to the local sparse coefficient set respectively to generate a global set of coefficients;
and deleting the main pipeline record flow which is smaller than or equal to the global concentrated coefficient set and the global concentrated coefficient threshold according to the global concentrated coefficient set, generating a main pipeline concentrated record flow set, carrying out mean value calculation, and generating the first main pipeline high-frequency flow.
4. The method of claim 3, wherein traversing the set of recording traffic neighbors, counting a set of local sparsity coefficients for the set of main line pipe recording traffic, comprises:
Extracting a first recording flow neighborhood of a first main pipeline recording flow of the main pipeline recording flow set from the recording flow neighborhood set;
counting a neighborhood record flow set of the first record flow neighborhood and a flow deviation set of the first main line pipeline record flow;
and counting the average value of the flow deviation set, setting the average value as a local sparse coefficient of the first main pipeline recorded flow, and adding the local sparse coefficient into the local sparse coefficient set.
5. The method of claim 1, wherein opening the vent switching valve to a first preset opening when the low pressure nitrogen press inlet nitrogen pressure is greater than or equal to a low pressure nitrogen press inlet threshold pressure comprises:
obtaining a valve opening interval of the emptying switching valve;
randomly obtaining a first opening assignment result based on the valve opening interval;
performing frequent data mining based on the model of the emptying switching valve, the first opening assignment result, the nitrogen flow monitoring value and a nitrogen pipeline topological graph to generate a second main pipeline high-frequency flow, wherein the monitoring position of the second main pipeline high-frequency flow is positioned at the downstream of the emptying switching valve;
activating an inlet pressure prediction component of the low-pressure nitrogen compressor, and performing backlog time optimization by combining the inlet threshold pressure of the low-pressure nitrogen compressor and the high-frequency flow of the second main pipeline to generate a second backlog time prediction value;
When the second backlog duration predicted value is larger than a backlog duration threshold value, setting the first opening assignment result as the first preset opening;
and updating the first opening assignment result based on the valve opening interval when the second backlog duration predicted value is smaller than or equal to the backlog duration threshold value.
6. The method of claim 1, wherein opening the dump cut valve to a second preset opening when the first backlog duration prediction value is less than or equal to a backlog duration threshold value comprises:
obtaining a valve opening interval of the emptying switching valve;
randomly obtaining a second opening assignment result based on the valve opening interval;
carrying out frequent data mining by using the model of the vent switching valve, the second opening assignment result, the model of the air separation vent valve, the maximum vent valve opening, the nitrogen flow monitoring value and a nitrogen pipeline topological graph to generate a third main pipeline high-frequency flow, wherein the monitoring position of the third main pipeline high-frequency flow is positioned at the downstream of the vent switching valve and the air separation vent valve;
activating the inlet pressure prediction component of the low-pressure nitrogen compressor, and performing backlog duration optimization by combining the inlet threshold pressure of the low-pressure nitrogen compressor and the high-frequency flow of the third main pipeline to generate a third backlog duration prediction value;
When the third backlog duration predicted value is larger than a backlog duration threshold value, setting the second opening assignment result as the second preset opening;
and updating the second opening assignment result based on the valve opening interval when the third backlog duration predicted value is smaller than or equal to the backlog duration threshold.
7. The method of claim 1, wherein activating a low pressure nitrogen press inlet pressure prediction assembly, responsive to the low pressure nitrogen press inlet nitrogen backlog and the low pressure nitrogen press inlet temperature, obtains a low pressure nitrogen press inlet nitrogen pressure, comprising:
setting the air switching valve and the air separation air switching valve in a closed state, and testing the medium-low pressure nitrogen compressor to obtain a nitrogen backlog monitoring value of an inlet of the low pressure nitrogen compressor, a temperature monitoring value of an inlet of the low pressure nitrogen compressor and a nitrogen pressure monitoring value of an inlet of the low pressure nitrogen compressor;
taking the nitrogen pressure monitoring value of the inlet of the low-pressure nitrogen compressor as supervision, and adjusting the nitrogen backlog monitoring value of the inlet of the low-pressure nitrogen compressor and the inlet temperature monitoring value of the low-pressure nitrogen compressor to configure a BP neural network so as to generate the inlet pressure prediction component of the low-pressure nitrogen compressor.
8. A nitrogen compressor operation control system, comprising:
the monitoring value acquisition module is used for interacting the flow sensor and receiving the nitrogen flow monitoring value when the medium-pressure nitrogen press is switched to a stop state;
the nitrogen backlog generation module is used for loading the response time of the air separation vent valve, and carrying out nitrogen backlog prediction by combining the nitrogen flow monitoring value to generate the nitrogen backlog of the inlet of the low-pressure nitrogen compressor;
the inlet temperature receiving module is used for receiving the inlet temperature of the low-pressure nitrogen compressor through the interaction temperature sensor;
the inlet nitrogen pressure acquisition module is used for activating a low-pressure nitrogen compressor inlet pressure prediction assembly, responding to the low-pressure nitrogen compressor inlet nitrogen backlog and the low-pressure nitrogen compressor inlet temperature, and acquiring low-pressure nitrogen compressor inlet nitrogen pressure;
the emptying switching valve opening module is used for opening the emptying switching valve to a first preset opening degree when the nitrogen pressure of the inlet of the low-pressure nitrogen compressor is greater than or equal to the threshold pressure of the inlet of the low-pressure nitrogen compressor;
Further, the system further comprises:
the predicted value judging module is used for obtaining the maximum vent valve opening of the air separation vent valve when the nitrogen pressure at the inlet of the low-pressure nitrogen compressor is smaller than the inlet threshold pressure of the low-pressure nitrogen compressor; performing frequent data mining according to the model of the air separation emptying valve, the maximum opening of the emptying valve, the nitrogen flow monitoring value and a nitrogen pipeline topological graph to generate a first main pipeline high-frequency flow, wherein the monitoring position of the first main pipeline high-frequency flow is positioned at the downstream of the air separation emptying valve; activating an inlet pressure prediction component of the low-pressure nitrogen compressor, and performing backlog time optimization by combining the inlet threshold pressure of the low-pressure nitrogen compressor and the high-frequency flow of the first main pipeline to generate a first backlog time prediction value; and when the first backlog duration predicted value is smaller than or equal to the backlog duration threshold value, opening the emptying switching valve to a second preset opening.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410123625.0A CN117662445B (en) | 2024-01-30 | 2024-01-30 | Nitrogen compressor operation control method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410123625.0A CN117662445B (en) | 2024-01-30 | 2024-01-30 | Nitrogen compressor operation control method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117662445A CN117662445A (en) | 2024-03-08 |
| CN117662445B true CN117662445B (en) | 2024-04-09 |
Family
ID=90064384
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410123625.0A Active CN117662445B (en) | 2024-01-30 | 2024-01-30 | Nitrogen compressor operation control method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117662445B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117927873B (en) * | 2024-03-25 | 2024-06-21 | 玉得气体有限责任公司 | Method and system for controlling amount of nitrogen in balance pipeline |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA586172A (en) * | 1959-11-03 | Wilkinson Walter | Separation of air | |
| CN202031864U (en) * | 2011-05-18 | 2011-11-09 | 河南省煤气(集团)有限责任公司义马气化厂 | Sealed air source automatic switching system for centrifugal oxygen compressor |
| CN204647854U (en) * | 2015-04-28 | 2015-09-16 | 三江乐天化工有限公司 | A kind of mesolow nitrogen air separation facility train |
| CN105318193A (en) * | 2014-07-31 | 2016-02-10 | 宝山钢铁股份有限公司 | Low-pressure nitrogen gas header pipe system and control method |
| CN107965668A (en) * | 2018-01-12 | 2018-04-27 | 新余钢铁集团有限公司 | A kind of energy-saving compressed gas Multilevel partial-pressure regulating system |
| CN210860654U (en) * | 2019-09-17 | 2020-06-26 | 云南玉溪玉昆钢铁集团有限公司 | Nitrogen supply equipment for steel smelting factory |
| CN115419831A (en) * | 2022-08-10 | 2022-12-02 | 中国石油化工股份有限公司 | Device for reducing steam consumption of low-pressure nitrogen press |
| CN115435244A (en) * | 2022-09-23 | 2022-12-06 | 湖南华菱涟源钢铁有限公司 | Control method of middle-low pressure nitrogen gas communication valve of oxygen generation system |
| CN218544016U (en) * | 2021-10-13 | 2023-02-28 | 三江化工有限公司 | Device for nitrogen gas serial-connection circulating nitrogen compressor inlet pipeline of air separation system |
| CN116066739A (en) * | 2022-12-23 | 2023-05-05 | 安阳钢铁股份有限公司 | Grid-connected combined nitrogen supply method for air separation unit |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9476624B2 (en) * | 2013-02-18 | 2016-10-25 | Liebert Corporation | Scroll compressor differential pressure control during compressor shutdown transitions |
| CN112577211B (en) * | 2019-09-30 | 2021-12-14 | 约克（无锡）空调冷冻设备有限公司 | Load balancing method for two compressors |
-
2024
- 2024-01-30 CN CN202410123625.0A patent/CN117662445B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CA586172A (en) * | 1959-11-03 | Wilkinson Walter | Separation of air | |
| CN202031864U (en) * | 2011-05-18 | 2011-11-09 | 河南省煤气(集团)有限责任公司义马气化厂 | Sealed air source automatic switching system for centrifugal oxygen compressor |
| CN105318193A (en) * | 2014-07-31 | 2016-02-10 | 宝山钢铁股份有限公司 | Low-pressure nitrogen gas header pipe system and control method |
| CN204647854U (en) * | 2015-04-28 | 2015-09-16 | 三江乐天化工有限公司 | A kind of mesolow nitrogen air separation facility train |
| CN107965668A (en) * | 2018-01-12 | 2018-04-27 | 新余钢铁集团有限公司 | A kind of energy-saving compressed gas Multilevel partial-pressure regulating system |
| CN210860654U (en) * | 2019-09-17 | 2020-06-26 | 云南玉溪玉昆钢铁集团有限公司 | Nitrogen supply equipment for steel smelting factory |
| CN218544016U (en) * | 2021-10-13 | 2023-02-28 | 三江化工有限公司 | Device for nitrogen gas serial-connection circulating nitrogen compressor inlet pipeline of air separation system |
| CN115419831A (en) * | 2022-08-10 | 2022-12-02 | 中国石油化工股份有限公司 | Device for reducing steam consumption of low-pressure nitrogen press |
| CN115435244A (en) * | 2022-09-23 | 2022-12-06 | 湖南华菱涟源钢铁有限公司 | Control method of middle-low pressure nitrogen gas communication valve of oxygen generation system |
| CN116066739A (en) * | 2022-12-23 | 2023-05-05 | 安阳钢铁股份有限公司 | Grid-connected combined nitrogen supply method for air separation unit |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117662445A (en) | 2024-03-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117662445B (en) | Nitrogen compressor operation control method and system | |
| CN109240244B (en) | Data-driven equipment running state health degree analysis method and system | |
| KR101941854B1 (en) | System and method of estimating load with null data correction | |
| KR101573296B1 (en) | Prediction method of abnormal data, and a computer-readable storege medium having program to perform the same | |
| US9188021B2 (en) | Steam turbine blade vibration monitor backpressure limiting system and method | |
| CN111720296B (en) | Steam feed pump equipment abnormal state early warning method based on self-encoder | |
| RU2739727C1 (en) | Method and system for remote monitoring and prediction of state of process objects | |
| CN102183699A (en) | Method for model mismatching detection and positioning of multivariate predictive control system in chemical process | |
| CN110112442B (en) | Fuel cell system control method and device | |
| CN110764474B (en) | Method and system for monitoring running state of equipment | |
| CN113515049A (en) | Operation regulation and control system and method for gas-steam combined cycle generator set | |
| CN111611751B (en) | Chemical process risk dynamic analysis method based on Bayesian and event tree | |
| CN115496188A (en) | Coal mill fault early warning method based on deep learning convolutional neural network | |
| US20240223661A1 (en) | Methods and smart gas internet of things (iot) systems for smart control of smart gas pipeline network data collection terminals | |
| CN111879522B (en) | Steam turbine operation monitoring and fault distinguishing method and system based on time sequence probability | |
| CN109460403A (en) | The real-time dynamic quantitative scaling method of the stifled ash of air preheater | |
| CN113204867A (en) | Intelligent scheduling method for transient process of pipe network | |
| US10953377B2 (en) | Delta temperature control of catalytic dehydrogenation process reactors | |
| US20230229144A1 (en) | Safety Interlock Recommendation System | |
| CN117196220A (en) | Intelligent gas emergency scheme assessment method, internet of things system and storage medium | |
| CN115186754A (en) | Unit energy efficiency monitoring and diagnosing method based on information entropy and auto-associative regression model | |
| JP6385830B2 (en) | An evaluation method for evaluating the workload of operational operators | |
| JPH04366742A (en) | Plant monitoring device and its method | |
| CN112381235A (en) | Auxiliary method for monitoring state change of preheater in cement plant | |
| CN113778044A (en) | Monitoring method and device for blower system of thermal power plant |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |