Method and device for controlling temperature of medium outlet of head air cooling system of fractionating tower

Abstract

The invention discloses a fractionating tower head air cooling system medium outlet temperature control method and device. The method comprises the steps that real-time operation data and real-time environment data of a fractionating tower head air cooling system are obtained; judging whether the air cooling system fluctuates or not based on the real-time operation data, the real-time environment data and a preset temperature change range; when the system fluctuates, calculating a motor control quantity based on a preset control rule and a preset control parameter; and performing frequency conversion control on the motor based on the motor control quantity and a gradient optimization algorithm so as to complete temperature control on the medium outlet of the fractionating tower head air cooling system. And frequency conversion control is performed on the motor according to the real-time operation data, so that temperature control on the medium outlet of the fractionating tower head air cooling system is realized, and high efficiency and adaptability of temperature control on the medium outlet of the fractionating tower head air cooling system are improved.

Description

Technical Field

[0001] The invention relates to the technical field of temperature control, and in particular to a method and a device for controlling the outlet temperature of a medium in an air cooling system at the top of a fractionating tower. Background Art

[0002] The air cooling system at the top of the fractionation tower includes inlet and outlet pipes, packing and an axial flow fan. The axial flow fan draws air above the packing and exchanges heat and cools the material flowing down the packing by forced convection heat exchange. The fan is driven by a motor. In order to change the speed of the fan to change its cooling capacity, it is known to use a frequency converter so that the motor speed can be changed in a simple way. The frequency converter is a sensitive electronic component.

[0003] As a power device for cooling materials, the air cooling system uses a fan to exchange heat between the flowing air and the medium entering the tower to reduce the temperature of the medium. However, when the external environment temperature and humidity change, or when the device operating conditions fluctuate, causing the medium flow rate and inlet temperature to change, the cooling capacity provided by the axial flow fan running at the industrial frequency may be higher or lower than the cooling capacity required to cool the medium to the target temperature. At this time, the discharge temperature of the air cooling system will deviate from the design temperature, and the fan speed is not the optimal value.

[0004] The existing air cooling system for the distillation tower controls the temperature of the entire distillation tower by optimizing the parameters of the distillation tower based on the distillation tower data and computer programs. However, the fan frequency conversion of the distillation tower air cooling system requires manual adjustment by the operator and cannot be adjusted in time. In addition, the fan of the distillation tower air cooling system cannot achieve stepless speed change and can only perform fixed-speed frequency conversion. It cannot effectively respond to various changes and accurately control the outlet temperature of the medium of the air cooling system at the top of the distillation tower. Summary of the invention

[0005] The present invention provides a method for controlling the outlet temperature of a medium in an air cooling system at the top of a fractionating tower, so as to control the temperature of the outlet of the medium in the air cooling system at the top of a fractionating tower according to a real-time scenario, thereby improving the efficiency and adaptability of the outlet temperature control of the medium in the air cooling system at the top of a fractionating tower.

[0006] In order to solve the above technical problems, an embodiment of the present invention provides a method for controlling the outlet temperature of a medium in a fractionation tower top air cooling system, comprising:

[0007] Obtain real-time operation data and real-time environmental data of the air cooling system at the top of the fractionator;

[0008] Determining whether there is fluctuation in the air cooling system based on the real-time operation data, the real-time environmental data and a preset temperature variation range;

[0009] When there are fluctuations in the system, the motor control amount is calculated based on preset control rules and preset control parameters; and the motor is frequency-controlled based on the motor control amount and the gradient optimization algorithm to complete the temperature control of the medium outlet of the distillation tower top air cooling system.

[0010] The present invention determines whether the system has abnormal fluctuations by collecting real-time operation data of the fractionation tower top air cooling system and a preset temperature variation range. When the fractionation tower top air cooling system has abnormal fluctuations, the motor control amount is calculated based on preset control rules and preset control parameters, so as to perform variable frequency control on the motor according to the motor control amount and the gradient optimization algorithm, and find the optimal motor control amount through the gradient optimization algorithm to achieve efficient temperature control. The motor is frequency-controlled with real-time operation data, so as to achieve temperature control of the medium outlet of the fractionation tower top air cooling system, and improve the efficiency and adaptability of the medium outlet temperature control of the fractionation tower top air cooling system.

[0011] Further, the real-time operation data includes the medium feed temperature and the medium feed flow rate; the real-time environmental data includes the ambient temperature and the medium outlet temperature; and judging whether there is abnormal fluctuation in the air cooling system at the top of the fractionation tower based on the real-time operation data, the real-time environmental data and the preset temperature variation range includes:

[0012] When the medium outlet temperature is within the temperature variation range, if the sum of the change rates of the medium feed temperature, the medium feed flow rate and the ambient temperature is greater than a preset variation threshold, the air cooling system has abnormal fluctuations.

[0013] When the medium outlet temperature is within the temperature variation range, the present invention determines whether the system fluctuates based on the sum of the medium feed temperature, the medium feed flow rate and the rate of change of the ambient temperature, thereby suppressing the tendency of abnormal fluctuations in the air cooling system.

[0014] Further, judging whether there is abnormal fluctuation in the air cooling system at the top of the fractionation tower based on the real-time operation data, the real-time environmental data and a preset temperature variation range includes:

[0015] When the medium outlet temperature is not within the temperature variation range, the air cooling system has abnormal fluctuations.

[0016] The present invention monitors real-time operation data and environmental data to determine whether the medium outlet temperature of the air cooling system at the top of the distillation tower exceeds a preset temperature variation range, thereby identifying whether there is abnormal fluctuation in the system and adjusting the motor.

[0017] Further, the calculation of the motor control amount based on the real-time operation data, the preset target temperature and the preset fuzzy neural network includes:

[0018] Calculate a control coefficient and a frequency conversion range based on the real-time operation data and the real-time environment data;

[0019] Calculating a temperature error and an error change rate based on the real-time operating data and the target temperature;

[0020] Calculate PID parameters based on the temperature error, the error change rate and the fuzzy neural network;

[0021] The motor control amount is calculated based on the control coefficient, the frequency conversion range and the PID parameter.

[0022] The present invention uses real-time operation data, preset target temperature and fuzzy neural network to calculate accurate motor control quantity to achieve accurate control of the outlet temperature of the medium of the air cooling system at the top of the fractionating tower. This helps to improve the temperature control accuracy and the stability and operation efficiency of the air cooling system, ensuring that the outlet temperature of the medium of the air cooling system can be maintained within the set range under various working conditions.

[0023] Furthermore, the variable frequency control of the motor based on the motor control amount and the gradient optimization algorithm includes:

[0024] Updating the parameters of the fuzzy neural network based on a preset error cost function and the gradient optimization algorithm;

[0025] The motor control quantity is dynamically adjusted based on the updated fuzzy neural network to perform variable frequency control on the motor.

[0026] The present invention uses a gradient optimization algorithm and an error cost function to adaptively adjust the parameters of the fuzzy neural network, optimize the motor control quantity, minimize the control error of the system, thereby achieving more precise control and efficient regulation of the motor variable frequency control.

[0027] In a second aspect, the present invention provides a medium outlet temperature control device for a fractionation tower top air cooling system, comprising: a data acquisition module, a monitoring module and a control module;

[0028] The data acquisition module is used to obtain real-time operation data and real-time environmental data of the air cooling system at the top of the fractionation tower;

[0029] The monitoring module is used to determine whether there is abnormal fluctuation in the air cooling system at the top of the fractionation tower based on the real-time operation data, the real-time environmental data and a preset temperature variation range;

[0030] The control module is used to calculate the motor control quantity based on the real-time operation data, the preset target temperature and the preset fuzzy neural network when there is an abnormal fluctuation in the air cooling system at the top of the distillation tower; and to perform frequency conversion control on the motor based on the motor control quantity and the gradient optimization algorithm to complete the temperature control of the medium outlet of the air cooling system at the top of the distillation tower.

[0031] The present invention determines whether the system has abnormal fluctuations by collecting real-time operation data of the fractionation tower top air cooling system and a preset temperature variation range. When the fractionation tower top air cooling system has abnormal fluctuations, the motor control amount is calculated based on preset control rules and preset control parameters, so as to perform variable frequency control on the motor according to the motor control amount and the gradient optimization algorithm, and find the optimal motor control amount through the gradient optimization algorithm to achieve efficient temperature control. The motor is frequency-controlled with real-time operation data, so as to achieve temperature control of the medium outlet of the fractionation tower top air cooling system, and improve the efficiency and adaptability of the medium outlet temperature control of the fractionation tower top air cooling system.

[0032] Furthermore, the real-time operation data includes the medium feed temperature and the medium feed flow rate; the real-time environmental data includes the ambient temperature and the medium outlet temperature; the monitoring module is used to:

[0033] When the medium outlet temperature is within the temperature variation range, if the sum of the change rates of the medium feed temperature, the medium feed flow rate and the ambient temperature is greater than a preset variation threshold, the air cooling system has abnormal fluctuations.

[0034] Furthermore, the monitoring module is used to:

[0035] When the medium outlet temperature is not within the temperature variation range, the air cooling system has abnormal fluctuations.

[0036] Furthermore, the control module is used to:

[0037] Calculate a control coefficient and a frequency conversion range based on the real-time operation data and the real-time environment data;

[0038] Calculating a temperature error and an error change rate based on the real-time operating data and the target temperature;

[0039] Calculate PID parameters based on the temperature error, the error change rate and the fuzzy neural network;

[0040] The motor control amount is calculated based on the control coefficient, the frequency conversion range and the PID parameter.

[0041] Furthermore, the control module is used to:

[0042] Updating the parameters of the fuzzy neural network based on a preset error cost function and the gradient optimization algorithm;

[0043] The motor control quantity is dynamically adjusted based on the updated fuzzy neural network to perform variable frequency control on the motor. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 A schematic flow chart of a method for controlling the outlet temperature of a medium in a fractionation tower top air cooling system provided in an embodiment of the present invention;

[0045] Figure 2 A schematic diagram of a fuzzy neural network structure provided by an embodiment of the present invention;

[0046] Figure 3 A schematic diagram of an experimental device for controlling the outlet temperature of a medium in a fractionation tower top air cooling system according to an embodiment of the present invention;

[0047] Figure 4 A schematic diagram of outlet temperature and motor frequency variation provided by an embodiment of the present invention;

[0048] Figure 5 Another schematic diagram of outlet temperature and motor frequency variation provided by an embodiment of the present invention;

[0049] Figure 6 A schematic diagram of another outlet temperature and motor frequency change provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0050] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0051] The terms "first" and "second" and the like in the specification, claims and drawings of this application are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products or devices.

[0052] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0053] Example 1

[0054] See also Figure 1 , Figure 1 A schematic flow chart of a method for controlling the outlet temperature of a medium in a fractionation tower top air cooling system according to an embodiment of the present invention. The method comprises steps 101 to 103, which are as follows:

[0055] Step 101: Acquire real-time operation data and real-time environmental data of the air cooling system at the top of the fractionation tower;

[0056] In this embodiment, the real-time operation data and real-time environmental data of the air cooling system at the top of the fractionation tower and the tower environment are acquired in real time based on the temperature sensor and the flow sensor.

[0057] In this embodiment, the real-time operation data of the fractionation tower top air cooling system includes the medium feed temperature T in , Medium feed flow m flow and medium outlet temperature T out ; The real-time temperature data of the tower environment includes the ambient temperature T of the air cooling system at the top of the distillation tower env , Axial fan outlet temperature T windout .

[0058] Step 102: judging whether there is abnormal fluctuation in the air cooling system at the top of the fractionation tower based on the real-time operation data, the real-time environmental data and a preset temperature variation range;

[0059] In this embodiment, whether it is necessary to start frequency conversion control is determined based on the real-time operation data and the real-time environmental data. When the real-time operation data and the real-time environmental data meet the preset frequency conversion control conditions, the motor is subjected to frequency conversion control to adjust the medium outlet temperature.

[0060] In this embodiment, judging whether there is abnormal fluctuation in the air cooling system at the top of the fractionation tower based on the real-time operation data, the real-time environmental data and a preset temperature variation range includes:

[0061] When the medium outlet temperature is within the temperature variation range, if the sum of the change rates of the medium feed temperature, the medium feed flow rate and the ambient temperature is greater than a preset variation threshold, the air cooling system has abnormal fluctuations.

[0062] In this embodiment, when the medium outlet temperature is within the temperature variation range, whether the system fluctuates is determined based on the sum of the medium feed temperature, the medium feed flow rate and the rate of change of the ambient temperature, thereby suppressing the tendency of abnormal fluctuations in the air cooling system.

[0063] In this embodiment, judging whether there is abnormal fluctuation in the air cooling system at the top of the fractionation tower based on the real-time operation data, the real-time environmental data and a preset temperature variation range includes:

[0064] When the medium outlet temperature is not within the temperature variation range, the air cooling system has abnormal fluctuations.

[0065] In this embodiment, by monitoring real-time operation data and environmental data, it is determined whether the medium outlet temperature of the distillation tower top air cooling system exceeds the preset temperature variation range, thereby identifying whether there is abnormal fluctuation in the system and adjusting the motor.

[0066] In this embodiment, when the medium outlet temperature is not within the temperature variation range, it means that the system may fluctuate, or when the medium outlet temperature is within the temperature variation range and the sum of the change rates of the medium feed temperature, the medium feed flow rate and the ambient temperature is greater than the preset change threshold value X%, it indicates that the real-time operation data and the real-time environmental data meet the preset frequency conversion control conditions. At this time, the air cooling system has abnormal fluctuations or an abnormal fluctuation trend, and the motor needs to be frequency-controlled to adjust the medium outlet temperature.

[0067] In this embodiment, when the medium outlet temperature of the air cooling system at the top of the distillation tower is within the tolerable temperature range set by the program, if the sum of the change rates of the medium feed temperature, the medium feed flow rate and the ambient temperature does not exceed X%, it means that the system is in a steady state and no frequency conversion control is required, and the fan motor maintains a constant speed.

[0068] In this embodiment, the temperature variation range is set based on the target temperature.

[0069] As a specific example of an embodiment of the present invention, the target temperature is set to 40°C, and the temperature variation range is 40±0.2°C.

[0070] In this embodiment, since the water pump flow of the distillation tower is not a constant single value, it may fluctuate. When the value of the change threshold is too small, the system will amplify the noise and frequently enter the control link, resulting in frequent control actions and wasting computing resources.

[0071] In this embodiment, the change threshold is 0.001. Based on the change threshold, the noise signal generated by the flow can be effectively filtered and the possible impact caused by the slow change of system parameters can be effectively reduced.

[0072] Step 103: When there is an abnormal fluctuation in the air cooling system at the top of the distillation tower, the motor control amount is calculated based on the real-time operation data, the preset target temperature and the preset fuzzy neural network; and the motor is frequency-controlled based on the motor control amount and the gradient optimization algorithm to complete the temperature control of the medium outlet of the air cooling system at the top of the distillation tower.

[0073] In this embodiment, the motor control amount is calculated based on the real-time operation data, the preset target temperature and the preset fuzzy neural network, including:

[0074] Calculate a control coefficient and a frequency conversion range based on the real-time operation data and the real-time environment data;

[0075] Calculating a temperature error and an error change rate based on the real-time operating data and the target temperature;

[0076] Calculate PID parameters based on the temperature error, the error change rate and the fuzzy neural network;

[0077] The motor control amount is calculated based on the control coefficient, the frequency conversion range and the PID parameter.

[0078] In this embodiment, the real-time operating data includes the medium feed temperature T in , Medium feed flow m flow and medium outlet temperature T out The real-time temperature data includes the ambient temperature T of the air cooling system at the top of the distillation tower. env , Axial fan outlet temperature

[0079] In this embodiment, the control coefficient is used to indicate the functional relationship between the temperature rotation speed and the outlet temperature difference under ideal static conditions, which is based on the medium feed flow rate m flow , Fan outlet temperature and medium outlet temperature T out Calculate, specifically:

[0080]

[0081] Among them, C flow is the specific heat capacity of the medium, C wind is the specific heat capacity of air, m flow is the medium feed flow rate, m windIt is used for the quality of convective heat exchange air. α is used to indicate that different control coefficients should be adopted when the temperature is too high or too low in order to quickly return to the target temperature.

[0082] In this embodiment, the frequency conversion range is used to set the upper limit of the frequency conversion f max And the frequency lower limit f min To prevent system fluctuations caused by over-adjustment, it is based on the medium feed flow m flow , target temperature T target and medium outlet temperature T out Calculate, specifically:

[0083]

[0084] Among them, C flow is the specific heat capacity of the medium, C wind is the specific heat capacity of air, m flow is the medium feed flow rate, m wind is the mass of air used for convective heat transfer.

[0085] In this embodiment, the temperature error and the error change rate are calculated based on the medium outlet temperature and the target temperature.

[0086] In this embodiment, the temperature error and the error change rate are used as input to the fuzzy neural network to calculate the PID (proportional-integral-differential) parameters. The PID parameters include the proportional parameter K p , integration parameter K i and the differential parameter K d PID control is a commonly used feedback control algorithm. PID control adjusts the control quantity through three parts: proportional, integral and differential, so that the output of the controlled object reaches the expected value.

[0087] Please refer to Figure 2 , Figure 2 A schematic diagram of a fuzzy neural network structure provided by an embodiment of the present invention.

[0088] In this embodiment, the fuzzy neural network structure is initialized. The fuzzy neural network includes an input layer, a fuzzification layer, a fuzzy rule layer, a normalization layer and a clarity layer. Before calculation, the fuzzy neural network parameters are initialized. The fuzzy neural network parameters include the central value c of each language description value. ij , membership function parameter σ ij ; Initialize the fuzzy control rule matrix w ij . Initialize the neural network learning rate β.

[0089] In this embodiment, during the fuzzy neural network calculation process:

[0090] At the input layer:

[0091] f i =x i =f 1 ,x=[e,ec](i=1,2) (4)

[0092] In the fuzzification layer:

[0093]

[0094] At the fuzzy rule level:

[0095]

[0096] In the normalization layer:

[0097]

[0098] In the clear layer:

[0099]

[0100] Based on the calculated PID parameters, K p =y1,K i =y2,K d =y3.

[0101] Among them, f i is the i-th output of each layer of the neural network. In particular, for the fuzzification layer, f ij is the j-th language description value of the i-th variable; x i is the i-th input variable of the neural network; f L is the output of the Lth layer of the neural network; σ ij is the membership degree of the i-th variable to the j-th language description value; c ij is the central value of the membership function of the j-th language description value of the i-th variable; σ ij is the mean square value of the membership function of the j-th language description value of the i-th variable; α j is the effectiveness of the jth fuzzy rule; is the effectiveness of the jth fuzzy rule after normalization; y i is the ith output of the neural network.

[0102] In this embodiment, the control increment Δu of the motor at the current moment is calculated based on the control coefficient, the frequency conversion range and the PID parameter, and the control amount at the current moment is calculated based on the control increment Δu at the current moment and the control amount u1 at the previous moment.

[0103] In this embodiment, the control increment at the current moment is:

[0104] Δu=η×[K p(e-e1)+K i e+K d (e-2e1+e2)] (9)

[0105] Among them, e1 is the temperature difference at the previous moment, and e2 is the temperature difference between the previous two moments. Therefore, the control quantity at the current moment is: u = u1 + Δu. u1 is the control quantity at the previous moment.

[0106] In this embodiment, by accurately calculating the real-time data and the target temperature, combined with the optimization of the PID parameters by the fuzzy neural network, high-precision control of the temperature can be achieved, and overshoot and oscillation can be reduced. By dynamically adjusting the PID parameters and the motor control amount, the system changes can be quickly responded to and the stability of the system can be maintained. Through the self-learning and optimization capabilities of the fuzzy neural network, the control strategy can be continuously optimized to improve the adaptability and robustness of the system.

[0107] The present invention uses real-time operation data, preset target temperature and fuzzy neural network to calculate accurate motor control quantity to achieve accurate control of the outlet temperature of the medium of the air cooling system at the top of the fractionating tower. This helps to improve the temperature control accuracy and the stability and operation efficiency of the air cooling system, ensuring that the outlet temperature of the medium of the air cooling system can be maintained within the set range under various working conditions.

[0108] In this embodiment, the variable frequency control of the motor based on the motor control amount and the gradient optimization algorithm includes:

[0109] Updating the parameters of the fuzzy neural network based on a preset error cost function and the gradient optimization algorithm;

[0110] The motor control quantity is dynamically adjusted based on the updated fuzzy neural network to perform variable frequency control on the motor.

[0111] In this embodiment, the error cost function is used to measure the error between the current motor control amount and the target control amount.

[0112] In this embodiment, the error cost function is

[0113]

[0114] In this embodiment, the parameters of the fuzzy neural network are calculated based on the error cost function and the gradient optimization algorithm, specifically:

[0115]

[0116] Among them, Δw k is the change of the fuzzy rule matrix, Δc ij is the change in the central value of the membership function; Δσ ijis the change in the mean square error of the membership function; β is the learning rate of the neural network; is the partial derivative of the error cost function with respect to the medium outlet temperature; It is the partial derivative of the medium outlet temperature with respect to the control quantity; It is the partial derivative of the control quantity to the output of the fifth layer of the neural network; It is the partial derivative of the fifth layer output of the neural network with respect to the fuzzy rule matrix; It is the partial derivative of the output of the fifth layer of the neural network to the output of the fourth layer of the neural network; It is the partial derivative of the output of the fourth layer of the neural network to the output of the third layer of the neural network.

[0117] In this embodiment, the change amount Δw based on the fuzzy rule matrix k , the change in the central value of the membership function Δc ij ; Change in mean square error of membership function Δσ ij The fuzzy neural network is updated, and based on the updated fuzzy neural network, a new motor control quantity is calculated, and the motor is frequency-controlled through a frequency converter.

[0118] In this embodiment, by calculating the gradient of the error cost function (i.e., the direction in which the error changes fastest), the parameters of the fuzzy neural network are gradually adjusted to minimize the error cost. Through the gradient optimization algorithm, the system can adaptively adjust the parameters of the fuzzy neural network, optimize the motor control amount, minimize the control error of the system, and thus achieve more precise control.

[0119] In this embodiment, through the gradient optimization algorithm and the error cost function, the system can continuously optimize the parameters of the fuzzy neural network, improve the accuracy of the motor control quantity, and reduce the control error. Dynamic adjustment of the parameters of the fuzzy neural network and the motor control quantity can make the system respond more quickly to changes in the external environment and fluctuations in the internal state. By optimizing the motor control quantity, the system can maintain stable operation and reduce system oscillation and instability caused by control errors.

[0120] The present invention uses a gradient optimization algorithm and an error cost function to adaptively adjust the parameters of the fuzzy neural network, optimize the motor control quantity, minimize the control error of the system, thereby achieving more precise control and efficient regulation of the motor variable frequency control.

[0121] In this embodiment, when the outlet temperature of the medium of the air cooling system at the top of the distillation tower is within the temperature variation range and the sum of the absolute values ​​of the errors within ten seconds is less than or equal to a preset first threshold, the frequency conversion control is stopped.

[0122] In this embodiment, when the outlet temperature of the medium of the air cooling system at the top of the distillation tower is within the temperature variation range, and the sum of the absolute values ​​of the errors within ten seconds is less than or equal to 1, the average error is within 0.1°C.

[0123] The embodiment of the present invention also provides a medium outlet temperature control device of a fractionation tower top air cooling system, comprising: a data acquisition module, a monitoring module and a control module;

[0124] The data acquisition module is used to obtain real-time operation data and real-time environmental data of the air cooling system at the top of the fractionation tower;

[0125] The monitoring module is used to determine whether there is abnormal fluctuation in the air cooling system at the top of the fractionation tower based on the real-time operation data, the real-time environmental data and a preset temperature variation range;

[0126] The control module is used to calculate the motor control quantity based on the real-time operation data, the preset target temperature and the preset fuzzy neural network when there is an abnormal fluctuation in the air cooling system at the top of the distillation tower; and to perform frequency conversion control on the motor based on the motor control quantity and the gradient optimization algorithm to complete the temperature control of the medium outlet of the air cooling system at the top of the distillation tower.

[0127] The present invention determines whether the system has abnormal fluctuations by collecting real-time operation data of the fractionation tower top air cooling system and a preset temperature variation range. When the fractionation tower top air cooling system has abnormal fluctuations, the motor control amount is calculated based on preset control rules and preset control parameters, so as to perform variable frequency control on the motor according to the motor control amount and the gradient optimization algorithm, and find the optimal motor control amount through the gradient optimization algorithm to achieve efficient temperature control. The motor is frequency-controlled with real-time operation data, so as to achieve temperature control of the medium outlet of the fractionation tower top air cooling system, and improve the efficiency and adaptability of the medium outlet temperature control of the fractionation tower top air cooling system.

[0128] In this embodiment, the real-time operation data includes the medium feed temperature and the medium feed flow rate; the real-time environmental data includes the ambient temperature and the medium outlet temperature; the monitoring module is used to:

[0129] When the medium outlet temperature is within the temperature variation range, if the sum of the change rates of the medium feed temperature, the medium feed flow rate and the ambient temperature is greater than a preset variation threshold, the air cooling system has abnormal fluctuations.

[0130] In this embodiment, the monitoring module is used to:

[0131] When the medium outlet temperature is not within the temperature variation range, the air cooling system has abnormal fluctuations.

[0132] In this embodiment, the control module is used to:

[0133] Calculate a control coefficient and a frequency conversion range based on the real-time operation data and the real-time environment data;

[0134] Calculating a temperature error and an error change rate based on the real-time operating data and the target temperature;

[0135] Calculate PID parameters based on the temperature error, the error change rate and the fuzzy neural network;

[0136] The motor control amount is calculated based on the control coefficient, the frequency conversion range and the PID parameter.

[0137] In this embodiment, the control module is used to:

[0138] Updating the parameters of the fuzzy neural network based on a preset error cost function and the gradient optimization algorithm;

[0139] The motor control quantity is dynamically adjusted based on the updated fuzzy neural network to perform variable frequency control on the motor.

[0140] Please refer to Figure 3 , Figure 3 A schematic diagram of an experimental device for controlling the medium outlet temperature of a distillation tower top air cooling system provided in an embodiment of the present invention.

[0141] As a specific example of an embodiment of the present invention, the material of the air cooling system is circulating pure water, and the circulating water circulation volume of the device is 1.38t / h. The simulated heat source heats the circulating water to 53°C and then sends it into the circulating water pipeline. The initial frequency of the frequency converter is 0Hz, and the initial speed of the motor is 0RPM. At this time, the outlet logistics temperature of the cooling tower is 50.7°C. Start the upper computer program, and the data sensed by the sensor in real time is used as the initial operation data, and the data is acquired through the PLC. Since the outlet logistics temperature of 50.7°C is greater than the target setting temperature of 40°C, the monitoring module of the PLC determines that the motor speed needs to be controlled. After the control module obtains the frequency conversion control instruction of the monitoring module, it obtains the real-time operation data and real-time environmental data sensed by the sensors of the cooling tower and the surrounding environment of the tower from the PLC at a polling rate of 2Hz, and calculates the control quantity coefficient η and the frequency conversion upper limit f at the current moment. max , frequency lower limit f min , error e and error change rate ec; error e and error ec are used as inputs to obtain the current PID control parameter K through fuzzy neural network calculation p , K i , K d ; Calculate the control quantity change Δu at the current moment according to the obtained PID control parameters and control quantity coefficient, and transmit the control signal to the PLC to drive the inverter to act; At the same time, the control module will perform error back propagation according to the error cost function at this time, and update the module parameter c ij , σ ij With the matrix w kTo optimize the control effect. The control module will continue to cycle the above data collection-calculation-control process until the cooling tower outlet logistics temperature drops to the temperature tolerance range and there is no obvious temperature fluctuation. After the system reaches a steady state, the program process will be returned to the monitoring module.

[0142] Please refer to Figure 4 , Figure 4 A schematic diagram of outlet temperature and motor frequency changes provided by an embodiment of the present invention.

[0143] In this embodiment, after starting the host computer program, the program starts to perform frequency conversion control on the motor at the 4th second, and the circulating water outlet temperature of the cooling tower enters the temperature tolerance range and reaches a steady state at the 92nd second. The control process takes a total of 88 seconds, and the control temperature value is +0.03°C away from the target set temperature value.

[0144] As a specific example of an embodiment of the present invention, the material of the air cooling system is circulating pure water, and the circulating water circulation volume of the device is 1.04t / h. The circulating water is heated to 54°C by a simulated heat source and then sent into the circulating water pipeline. The initial frequency of the frequency converter is 19Hz, and the initial speed of the motor is 1330RPM. At this time, the outlet logistics temperature of the cooling tower is 40.53°C. Start the upper computer program, and the data sensed by the sensor in real time is used as real-time operation data and real-time environmental data. Since the outlet logistics temperature of 40.53°C is greater than the target set temperature of 40°C, the monitoring module determines that program intervention is required to control the motor speed. After the control module obtains the authorization of the monitoring module, it obtains the sensor sensing data of the cooling tower and the surrounding environment of the tower from the PLC at the current moment at a polling rate of 2Hz, and calculates the control quantity coefficient η and the frequency conversion upper limit f at the current moment. max , frequency lower limit f min , error e and error change rate ec; error e and error ec are used as inputs to obtain the current PID control parameter K through fuzzy neural network calculation p , K i , K d ; Calculate the control quantity change Δu at the current moment according to the obtained PID control parameters and control quantity coefficient, and transmit the control signal to the PLC to drive the inverter to act; At the same time, the control module will perform error back propagation according to the error cost function at this time, and update the module parameter c ij , σ ij With the matrix w k To optimize the control effect. The control module will continue to cycle the above data collection-calculation-control process until the cooling tower outlet logistics temperature drops to the temperature tolerance range and there is no obvious temperature fluctuation. After the system reaches a steady state, the program process will be returned to the monitoring module.

[0145] Please refer to Figure 5 , Figure 5Another schematic diagram of outlet temperature and motor frequency changes provided by an embodiment of the present invention.

[0146] After starting the host computer program, the program began to perform frequency conversion control on the motor at the 6th second, and the circulating water outlet temperature of the cooling tower entered the temperature tolerance range and reached a steady state at the 61st second. The control process took a total of 55 seconds, and the controlled temperature value was -0.05℃ away from the target set temperature value.

[0147] As a specific example of an embodiment of the present invention, the material of the air cooling system is circulating pure water, and the circulating water circulation volume of the device is 1.05t / h. The simulated heat source heats the circulating water to 54°C and then sends it into the circulating water pipeline. The initial frequency of the frequency converter is 20.5Hz, and the initial speed of the motor is 1435RPM. At this time, the outlet logistics temperature of the cooling tower is 39.03°C. Start the upper computer program, and the data sensed in real time by the sensor is transmitted to the data acquisition module of the program through the PLC as the initial data. Since the outlet logistics temperature of 39.03°C is less than the target set temperature of 40°C, the monitoring module determines that the program needs to intervene to control the motor speed. After the control module obtains the authorization of the monitoring module, it obtains the sensor sensing data of the cooling tower and the surrounding environment of the tower from the PLC at the current moment at a polling rate of 2Hz, and calculates the control quantity coefficient η and the frequency conversion upper limit f at the current moment. max , frequency lower limit f min , error e and error change rate ec; error e and error ec are used as inputs to obtain the current PID control parameter K through fuzzy neural network calculation p , K i , K d ; Calculate the control quantity change Δu at the current moment according to the obtained PID control parameters and control quantity coefficient, and transmit the control signal to the PLC to drive the inverter to act; At the same time, the control module will perform error back propagation according to the error cost function at this time, and update the module parameter c ij , σ ij With the matrix w k To optimize the control effect. The control module will continue to cycle the above data collection-calculation-control process until the cooling tower outlet logistics temperature drops to the temperature tolerance range and there is no obvious temperature fluctuation. After the system reaches a steady state, the program process will be returned to the monitoring module.

[0148] Please refer to Figure 6 , Figure 6 A schematic diagram of another outlet temperature and motor frequency change provided in an embodiment of the present invention.

[0149] After starting the host computer program, the program began to perform frequency conversion control on the motor at the 11th second, and the circulating water outlet temperature of the cooling tower entered the temperature tolerance range and reached a steady state at the 87th second. The control process took a total of 76 seconds, and the controlled temperature value was +0.14℃ away from the target set temperature value.

[0150] The present invention introduces a control coefficient, stipulates a specific fuzzy control logic, and cleverly adopts a control logic of significantly changing the control amount to obtain a rapid response of the system temperature to reduce the influence of the time lag characteristics of the temperature system and quickly approach the target set temperature; the control logic of reducing the gain of the control amount on the system response when the temperature is close to a certain degree of the set point is adopted to reduce the influence of the inertial characteristics of the temperature system and avoid overshoot of the system.

[0151] In an embodiment of the present invention, a terminal device is also provided, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor. When the processor executes the computer program, the above-mentioned method for controlling the medium outlet temperature of the distillation tower top air cooling system is implemented.

[0152] In an embodiment of the present invention, a computer-readable storage medium is also provided, the computer-readable storage medium including a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the above-mentioned method for controlling the medium outlet temperature of the distillation tower top air cooling system.

[0153] Exemplarily, the computer program may be divided into one or more modules, one or more modules are stored in a memory and executed by a processor to implement the present invention. One or more modules may be a series of computer program instruction segments capable of implementing specific functions, and the instruction segments are used to describe the execution process of the computer program in a terminal device.

[0154] The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor, a memory, and a display. Those skilled in the art will appreciate that the above components are merely examples of the terminal device and do not constitute a limitation on the terminal device. The terminal device may include more or fewer components than the components, or may combine certain components, or different components. For example, the terminal device may also include input and output devices, network access devices, buses, etc.

[0155] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0156] The memory can be used to store computer programs and / or modules. The processor implements various functions of the terminal device by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function (such as a sound playback function, a text conversion function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, text message data, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0157] Wherein, if the module based on the control of the outlet temperature of the medium of the air cooling system at the top of the fractionation tower is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc. Computer-readable media may include: any entity or device capable of carrying computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0158] The specific embodiments described above further illustrate the purpose, technical solutions and beneficial effects of the present invention. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for controlling the outlet temperature of a medium in a fractionation tower top air cooling system, characterized in that: include: Obtain real-time operation data and real-time environmental data of the air cooling system at the top of the fractionator; Determine whether there is abnormal fluctuation in the air cooling system at the top of the fractionation tower based on the real-time operation data, the real-time environmental data and a preset temperature variation range; When there is an abnormal fluctuation in the air cooling system at the top of the fractionating tower, the motor control amount is calculated based on the real-time operation data, the preset target temperature and the preset fuzzy neural network; The motor is frequency-controlled based on the motor control quantity and the gradient optimization algorithm to complete the temperature control of the medium outlet of the air cooling system at the top of the distillation tower.

2. A method for controlling the outlet temperature of a medium in a fractionation tower top air cooling system according to claim 1, characterized in that: The real-time operation data includes the medium feed temperature and the medium feed flow rate; the real-time environmental data includes the ambient temperature and the medium outlet temperature; The determining whether there is abnormal fluctuation in the air cooling system at the top of the fractionation tower based on the real-time operation data, the real-time environmental data and a preset temperature variation range includes: When the medium outlet temperature is within the temperature variation range, if the sum of the change rates of the medium feed temperature, the medium feed flow rate and the ambient temperature is greater than a preset variation threshold, the air cooling system has abnormal fluctuations.

3. A method for controlling the outlet temperature of a medium in a fractionation tower top air cooling system according to claim 2, characterized in that: The determining whether there is abnormal fluctuation in the air cooling system at the top of the fractionation tower based on the real-time operation data, the real-time environmental data and a preset temperature variation range includes: When the medium outlet temperature is not within the temperature variation range, the air cooling system has abnormal fluctuations.

4. A method for controlling the outlet temperature of a medium in a fractionation tower top air cooling system according to claim 3, characterized in that: The calculating of the motor control amount based on the real-time operation data, the preset target temperature and the preset fuzzy neural network includes: Calculate a control coefficient and a frequency conversion range based on the real-time operation data and the real-time environment data; Calculating a temperature error and an error change rate based on the real-time operating data and the target temperature; Calculate PID parameters based on the temperature error, the error change rate and the fuzzy neural network; The motor control amount is calculated based on the control coefficient, the frequency conversion range and the PID parameter.

5. A method for controlling the outlet temperature of a medium in a fractionation tower top air cooling system according to claim 4, characterized in that: The method of performing variable frequency control on the motor based on the motor control amount and the gradient optimization algorithm includes: Updating the parameters of the fuzzy neural network based on a preset error cost function and the gradient optimization algorithm; The motor control quantity is dynamically adjusted based on the updated fuzzy neural network to perform variable frequency control on the motor.

6. A medium outlet temperature control device for a fractionation tower top air cooling system, characterized in that: include: Data acquisition module, monitoring module and control module; The data acquisition module is used to obtain real-time operation data and real-time environmental data of the air cooling system at the top of the fractionation tower; The monitoring module is used to determine whether there is abnormal fluctuation in the air cooling system at the top of the fractionation tower based on the real-time operation data, the real-time environmental data and a preset temperature variation range; The control module is used to calculate the motor control amount based on the real-time operation data, the preset target temperature and the preset fuzzy neural network when there is an abnormal fluctuation in the air cooling system at the top of the fractionating tower; The motor is frequency-controlled based on the motor control quantity and the gradient optimization algorithm to complete the temperature control of the medium outlet of the air cooling system at the top of the distillation tower.

7. A device for controlling the outlet temperature of a medium in a fractionation tower top air cooling system according to claim 6, characterized in that: The real-time operation data includes the medium feed temperature and the medium feed flow rate; the real-time environmental data includes the ambient temperature and the medium outlet temperature; the monitoring module is used to: When the medium outlet temperature is within the temperature variation range, if the sum of the change rates of the medium feed temperature, the medium feed flow rate and the ambient temperature is greater than a preset variation threshold, the air cooling system has abnormal fluctuations.

8. A device for controlling the outlet temperature of a medium in a fractionation tower top air cooling system according to claim 7, characterized in that: The monitoring module is used for: When the medium outlet temperature is not within the temperature variation range, the air cooling system has abnormal fluctuations.

9. A device for controlling the outlet temperature of a medium in a fractionation tower top air cooling system according to claim 8, characterized in that: The control module is used for: Calculate a control coefficient and a frequency conversion range based on the real-time operation data and the real-time environment data; Calculating a temperature error and an error change rate based on the real-time operating data and the target temperature; Calculate PID parameters based on the temperature error, the error change rate and the fuzzy neural network; The motor control amount is calculated based on the control coefficient, the frequency conversion range and the PID parameter.

10. A medium outlet temperature control device for a fractionation tower top air cooling system according to claim 9, characterized in that: The control module is used for: Updating the parameters of the fuzzy neural network based on a preset error cost function and the gradient optimization algorithm; The motor control quantity is dynamically adjusted based on the updated fuzzy neural network to perform variable frequency control on the motor.

Images