Energy-saving control method and terminal for HVAC system of converter station

Abstract

The present invention discloses an energy-saving control method and terminal for a converter station heating and ventilation system. The method processes input historical environmental parameters between converter station equipment according to a prediction model to obtain predicted values ​​of the environmental parameters, introduces weight coefficients to process power grid operation data, and obtains weight coefficient groups under different power grid operating conditions. The predicted values ​​of the environmental parameters are further combined with the weight coefficient groups to obtain a relationship function, and the relationship function is optimized and calculated using a particle swarm algorithm. Finally, the optimal fan operating parameters are output to perform optimized control on the fan, thereby achieving maximum energy saving of the heating and ventilation system while ensuring that the environmental parameters between converter station equipment meet the normal operating conditions of each power equipment.

Description

Technical Field

[0001] The present invention relates to the technical field of converter station control, and in particular to an energy-saving control method and terminal for a heating and ventilation system of a converter station. Background Art

[0002] A converter station is a site within a high-voltage direct current (HVDC) transmission system that converts AC to DC and vice versa, ensuring safety, stability, and power quality. Each converter station contains a sealed equipment room. Because the equipment within this room generates heat during operation, dedicated HVAC equipment is required to maintain ventilation within the room and maintain a reasonable temperature.

[0003] Currently, the HVAC combination units used within the station operate 24 / 7 and lack energy-saving control capabilities. The equipment room is an enclosed building, and its HVAC system consists of both supply and exhaust components. The HVAC combination unit is an integrated air supply system that integrates a fan, filter, heater, humidifier, and cooling coil, delivering air at a specific temperature, humidity, and volume to the equipment room. The exhaust system primarily consists of exhaust fans located at the top or side walls of the equipment room. Linked supply and exhaust control maintains a slightly positive pressure within the equipment room. When equipment loads are low or outdoor temperatures are low, a lower ventilation volume can meet the requirements. Therefore, variable frequency control of the combination unit's motor can achieve energy savings while maintaining the optimal operating environment in the equipment room. Commonly controlled variables include temperature and humidity, adjusting the operating frequency of the combination unit's motor based on temperature and humidity conditions. However, this regulation method is relatively simple and suffers from hysteresis.

[0004] In the prior art, for example, the patent application number CN201720346355.5 discloses a linkage control system for fresh air and exhaust air, comprising a control processor, wherein the output end of the control processor is electrically connected to the input end of the air intake device, and the output end of the control processor is electrically connected to the input end of the exhaust device. The air intake device includes a first gas sensing module, and the exhaust device includes a second gas sensing module. The input end of the control processor is electrically connected to the output end of the first gas sensing module and the output end of the second gas sensing module, respectively. By sensing the flow of gas inside the air intake device and the exhaust device, the air intake device and the exhaust device are controlled. When it is sensed that the air intake device is operating, the exhaust device is controlled to operate by the control processor. Conversely, the air intake device is controlled to operate by the control processor, thereby achieving the advantage of linkage, thereby effectively solving the problem that the existing fresh air device and exhaust device cannot be started at the same time, resulting in poor indoor air circulation. However, this solution can only achieve linkage control of air supply and exhaust.

[0005] For example, patent application number CN201621209381.5 discloses a linked energy-saving system for a cold storage air conditioning system and an air shower tunnel exhaust system. The system comprises a cold storage air conditioning system, an air shower tunnel exhaust system, an air quality detector, and a multifunctional centralized controller. The cold storage air conditioning system includes an air conditioner with an air return terminal and an air supply terminal, while the air shower tunnel exhaust system includes an exhaust fan with an exhaust air inlet terminal and an exhaust air outlet terminal. The multifunctional centralized controller provides signal connections to the air quality detector, the air conditioner, and the exhaust fan, respectively. Preferably, the cold storage air conditioning system also includes a fresh air fan. It may also include various regulating valves and other components. The cold storage air conditioning system also includes a dehumidifier. Linking the cold storage air conditioning system with the air shower tunnel exhaust system adjusts indoor air quality, extending system life, minimizing operating energy consumption, and achieving optimal performance. The system features an ingenious design, a simple structure, and ease of use, making it suitable for large-scale deployment. However, this solution primarily controls various system components by monitoring indoor parameters such as temperature, humidity, cleanliness, and dustiness, but does not disclose specific energy-saving strategies or methods.

[0006] The patent application number CN202220829526.0 discloses a clean room pressure difference variable working condition rapid balancing control system, which belongs to the field of automation control technology. It includes multiple clean rooms, and the multiple clean rooms are respectively equipped with a constant air volume valve, a clean room pressure sensor and a variable air volume valve. The constant air volume valve is installed in the air inlet section of the clean room, the clean room pressure sensor is installed at any position of the clean room, and the variable air volume valve is installed in the exhaust section of the clean room; by using automation technology, the controller can monitor the clean room constant air volume valve and the variable air volume valve in real time, and record the stable opening of the clean room constant air volume valve and the variable air volume valve under different working conditions, so as to achieve the optimal opening stored in the memory of the controller after each subsequent startup, to perform initial positioning of the opening of the clean room constant air volume valve and the variable air volume valve, and then perform stable adjustment based on this opening, so that the clean room pressure difference can be quickly stabilized, so that the pressure gradient of the clean area can be quickly established. This solution achieves rapid adjustment of the pressure difference by pre-setting the initial opening of the air valves between each device under different working conditions. Although the air volume can be controlled by adjusting the air valves, the energy-saving effect is poor.

[0007] It can be seen that the existing technical solutions mainly focus on how to achieve the coordinated control of the supply and exhaust air systems and quickly achieve the control targets. However, they do not consider how to maximize the energy saving of the HVAC system while maintaining the operating requirements of the equipment room. Summary of the Invention

[0008] The technical problem to be solved by the present invention is to provide an energy-saving control method and terminal for the HVAC system of a converter station, so as to ensure the normal operation of the equipment room while maximizing the energy saving of the HVAC system.

[0009] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0010] A method for controlling energy conservation in a converter station heating and ventilation system, comprising the steps of:

[0011] Obtain historical environmental parameters between converter station equipment, grid operation data, and initial parameters of wind turbines;

[0012] Processing historical environmental parameters between equipment in the converter station according to the prediction model to obtain predicted values ​​of the environmental parameters;

[0013] Processing the power grid operation data according to a weight coefficient model to obtain a weight coefficient group;

[0014] Obtaining a relationship function according to the predicted value of the environmental parameter, the weight coefficient group and the initial parameters of the wind turbine;

[0015] The relationship function is optimized and calculated by a particle swarm algorithm to output the optimal wind turbine operating parameters;

[0016] The fan operating state is adjusted according to the optimal fan operating parameters.

[0017] In order to solve the above technical problems, another technical solution adopted by the present invention is:

[0018] A converter station HVAC system energy-saving control terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the processor implements the various steps of the above-mentioned converter station HVAC system energy-saving control method.

[0019] The beneficial effects of the present invention are as follows: by processing the input historical environmental parameters between converter station equipment according to the prediction model, the environmental parameter prediction values ​​are obtained, and the weight coefficients are introduced to process the power grid operation data to obtain the weight coefficient groups under different power grid operation conditions, and the environmental parameter prediction values ​​are further combined with the weight coefficient groups to obtain the relationship function, and the relationship function is optimized and calculated by the particle swarm algorithm, and finally the optimal fan operating parameters are output to implement optimal control of the fan, thereby ensuring that the environmental parameters between the converter station equipment meet the normal operating conditions of each power equipment and realizing maximum energy saving of the HVAC system. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flowchart of the steps of a method for controlling energy conservation in a converter station HVAC system according to an embodiment of the present invention;

[0021] Figure 2 This is a flow chart of control steps of a method for energy-saving control of a converter station HVAC system in an embodiment of the present invention;

[0022] Figure 3A flowchart of the relationship function solving steps of a method for energy-saving control of a converter station HVAC system according to an embodiment of the present invention;

[0023] Figure 4 Schematic diagram of the structure of an energy-saving control terminal for a HVAC system in a converter station according to an embodiment of the present invention. DETAILED DESCRIPTION

[0024] To illustrate the technical content, achieved objectives and effects of the present invention in detail, the following description is given in conjunction with the embodiments and accompanying drawings.

[0025] Please refer to Figure 1 , a method for energy-saving control of a HVAC system in a converter station, comprising the steps of:

[0026] Obtain historical environmental parameters between converter station equipment, grid operation data, and initial parameters of wind turbines;

[0027] Processing historical environmental parameters between equipment in the converter station according to the prediction model to obtain predicted values ​​of the environmental parameters;

[0028] Processing the power grid operation data according to a weight coefficient model to obtain a weight coefficient group;

[0029] Obtaining a relationship function according to the predicted value of the environmental parameter, the weight coefficient group and the initial parameters of the wind turbine;

[0030] The relationship function is optimized and calculated by a particle swarm algorithm to output the optimal wind turbine operating parameters;

[0031] The fan operating state is adjusted according to the optimal fan operating parameters.

[0032] From the above description, it can be seen that the beneficial effects of the present invention are: by processing the input historical environmental parameters between the converter station equipment according to the prediction model, the environmental parameter prediction values ​​are obtained, and the weight coefficients are introduced to process the power grid operation data to obtain the weight coefficient groups under different power grid operating conditions, and further combining the environmental parameter prediction values ​​with the weight coefficient groups to obtain the relationship function, and optimizing the relationship function through the particle swarm algorithm, and finally outputting the optimal wind turbine operating parameters to implement optimal control of the wind turbine, thereby ensuring that the environmental parameters between the converter station equipment meet the normal operating conditions of each power equipment and achieving maximum energy saving of the HVAC system.

[0033] Furthermore, the historical environmental parameters include temperature parameters, humidity parameters, pressure parameters and fan operation parameters;

[0034] The processing of the historical environmental parameters between the equipment in the converter station according to the prediction model to obtain the predicted values ​​of the environmental parameters includes:

[0035] Constructing prediction models between the temperature parameter, humidity parameter, and pressure parameter and the fan operating parameters respectively to obtain a temperature prediction model, a humidity prediction model, and a pressure prediction model;

[0036] Processing the temperature parameter according to the temperature prediction model to obtain a temperature parameter prediction value;

[0037] Processing the humidity parameter according to the humidity prediction model to obtain a humidity parameter prediction value;

[0038] Processing the pressure parameter according to the pressure prediction model to obtain a pressure parameter prediction value;

[0039] The environmental parameter prediction value is obtained according to the temperature parameter prediction value, the temperature parameter prediction value and the pressure parameter prediction value.

[0040] From the above description, it can be seen that by constructing a prediction model between the temperature parameters, humidity parameters and pressure parameters and the fan operating parameters, and processing the temperature parameters, humidity parameters and pressure parameters, the processed temperature parameter prediction values, humidity parameter prediction values ​​and pressure parameter prediction values ​​are integrated to obtain the environmental parameter prediction side, fully considering the temperature conditions, humidity conditions and pressure conditions between the equipment, so as to consider maintaining the normal operation of the equipment room while reasonably controlling the air supply and exhaust system motors, air valves and other equipment to maximize the energy saving of the HVAC system.

[0041] Furthermore, the temperature prediction model includes:

[0042] T(k+1)=f[x T (k),…,x T (kj),…,x T (k-d+1),

[0043] T(k),…,T(kj),…,T(k-d+1)];

[0044]

[0045] Where T(k+1) is the predicted value of the temperature parameter output between the converter station equipment at the next moment; d is the set delay step number; T(kj) is the temperature value between the converter station equipment output d moments ago, 0≤j≤d-1; x T (k) is the external input temperature parameter matrix; is the supply air temperature, is the air valve opening, is the fan frequency.

[0046] From the above description, it can be seen that the temperature prediction model is obtained based on the historical temperature values ​​and the temperature parameter matrix input from the outside by the fan, and the delay step parameter is set. Therefore, by adjusting the import amount of the delay step, the calculation accuracy of the temperature prediction model can be adjusted to meet different accuracy requirements.

[0047] Furthermore, the humidity prediction model includes:

[0048]

[0049]

[0050] Where H(k+1) is the predicted value of the humidity parameter output between the converter station equipment at the next moment; d is the set delay step number; H(kj) is the humidity value between the converter station equipment output d moments ago, 0≤j≤d-1; x H (k) is the external input humidity parameter matrix; is the supply air temperature, is the air valve opening, is the fan frequency, (kj) is the air valve opening and fan frequency output in the previous d moments.

[0051] From the above description, it can be seen that the humidity prediction model is obtained based on the historical humidity values ​​and the humidity parameter matrix input from the outside by the fan, and the delay step parameter is set. Therefore, by adjusting the import amount of the delay step, the calculation accuracy of the humidity prediction model can be adjusted to meet different accuracy requirements.

[0052] Furthermore, the pressure prediction model includes:

[0053]

[0054]

[0055] Where Q(k+1) is the predicted value of the pressure parameter output between the converter station equipment at the next moment; d is the set delay step number; Q(kj) is the pressure value between the converter station equipment output d moments ago, 0≤j≤d-1; x Q (k) is the external input pressure parameter matrix; is the supply air temperature, is the air valve opening, is the fan frequency.

[0056] From the above description, it can be seen that the pressure prediction model is obtained based on the historical pressure values ​​and the pressure parameter matrix input from the outside by the fan, and the delay step parameter is set. Therefore, by adjusting the import amount of the delay step, the calculation accuracy of the pressure prediction model can be adjusted to meet different accuracy requirements.

[0057] Furthermore, obtaining the environmental parameter prediction value according to the temperature parameter prediction value, the temperature parameter prediction value, and the pressure parameter prediction value includes:

[0058] F1=k1(T * -T(k+i)) 2 +k2(H * -T(k+i)) 2 +k3(Q * -Q(k+i)) 2 ;

[0059] Among them, k1, k2 and k3 are the weight coefficients of temperature, humidity and pressure between devices respectively; T* is the temperature reference value, H* is the humidity reference value, and Q* is the pressure reference value; Q(k+i) is the pressure parameter prediction value predicted and output between the converter station devices at the next moment; H(k+i) is the humidity parameter prediction value predicted and output between the converter station devices at the next moment; T(k+i) is the temperature parameter prediction value predicted and output between the converter station devices at the next moment.

[0060] From the above description, it can be seen that by setting different weight coefficients for temperature, humidity and pressure respectively, and limiting and weighting the output environmental parameter prediction values ​​through temperature parameter values, humidity parameter values ​​and pressure reference values, a more accurate environmental parameter prediction value can be output.

[0061] Furthermore, it also includes constructing the weight coefficient model:

[0062] Obtain environmental factors and initial weight coefficients;

[0063] A weight coefficient model is generated according to the environmental factors and the initial weight coefficients.

[0064] As can be seen from the above description, by obtaining a weight coefficient model from environmental factors and initial weight coefficients, the impact of different environmental factors on devices is taken into account, thereby improving the prediction accuracy of the prediction model.

[0065] Furthermore, the weight coefficient model includes:

[0066]

[0067] Among them, A j0 (j=1~3) is the initial value of the weight coefficient, which is the same, that is, A 10 =A 20 =A 30 ; A1(t) is the weight value corresponding to the predicted value of the environmental parameter; A2(t) and A3(t) are the weight values ​​corresponding to the initial parameters of the wind turbine; k(t) is the environmental factor;

[0068] The relationship function obtained according to the environmental parameter prediction value, the weight coefficient group and the initial parameters of the wind turbine includes:

[0069] C=A1F1+A2F2+A3F3;

[0070] Among them, A1, A2 and A3 are the weight coefficients of the relationship function; F1 is the predicted value of the environmental parameter; F2 and F3 are the initial parameters of the wind turbine.

[0071] From the above description, it can be seen that the three groups of weight coefficients composed of A1(t), A2(t) and A3(t) respectively control the weights of the predicted values ​​of environmental parameters and the initial parameters of the wind turbine, realize the weight distribution of different parameters, and improve the accuracy of the prediction model.

[0072] Furthermore, the environmental factors include:

[0073]

[0074] Among them, ki(t) is the deviation value corresponding to different operating environments of power equipment, gi(t) is the weight of each deviation value; and t is the independent variable of the environmental factor.

[0075] Another embodiment of the present invention provides a converter station HVAC system energy-saving control terminal, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the processor implements the various steps in the above-mentioned converter station HVAC system energy-saving control method.

[0076] The energy-saving control method for the HVAC system of a converter station of the present invention can be applied to control the environment between equipment in a converter station of a power transmission system. It can maximize the energy saving of the HVAC system while ensuring that the environmental parameters between equipment in the converter station meet the normal operating conditions of each power equipment. The following is an explanation of the specific implementation method:

[0077] Example 1

[0078] Please refer to Figure 1 , a method for energy-saving control of a converter station HVAC system, comprising the steps of:

[0079] S1. Obtain historical environmental parameters between equipment in the converter station, grid operation data, and initial parameters of the wind turbine; wherein the historical environmental parameters include temperature parameters, humidity parameters, pressure parameters, and wind turbine operation parameters; such as the temperature values, humidity values, and pressure values ​​corresponding to all moments between equipment before the time to be predicted, and wind turbine operation parameters such as supply air temperature, supply air humidity, supply air volume, air valve opening, and wind turbine frequency;

[0080] S2. Process the historical environmental parameters between the converter station devices according to the prediction model to obtain predicted values ​​of the environmental parameters. Specifically:

[0081] Please refer to Figure 2 , respectively construct relationship prediction models between temperature parameters, humidity parameters and pressure parameters and the wind turbine operating parameters, and obtain temperature prediction models, humidity prediction models and pressure prediction models; in a specific embodiment, the temperature, humidity and pressure of the equipment room are predicted by temperature multilayer perceptrons, humidity multilayer perceptrons and pressure multilayer perceptrons respectively; wherein the multilayer perceptron is a neural network structure, and the equipment room of the converter station is covered with temperature, humidity and pressure sensors; a large amount of training can be performed in advance using the data obtained by the sensors to obtain the corresponding multilayer perceptron model;

[0082] S21. Process the temperature parameter according to the temperature prediction model to obtain a temperature parameter prediction value; wherein the temperature prediction model includes:

[0083] T(k+1)=f[x T (k),…,x T (kj),…,x T (k-d+1),

[0084] T(k),…,T(kj),…,T(k-d+1)];

[0085]

[0086] Among them, T(k+1) is the predicted value of the temperature parameter output between the converter station equipment at the next moment; d is the set delay step number. By adjusting the import amount of the delay step number, the calculation accuracy of the temperature prediction model can be adjusted to meet different accuracy requirements. For example, the larger the value of the delay step number d, the more data parameters imported from the past moment, the more accurate the prediction result, but the calculation speed will be reduced and the model will be more complex; T(kj) is the temperature value between the converter station equipment output d moments ago, 0≤j≤d-1; x T (k) is the external input temperature parameter matrix; is the supply air temperature, is the air valve opening, is the fan frequency;

[0087] S22. Process the humidity parameter according to the humidity prediction model to obtain a humidity parameter prediction value; wherein the humidity prediction model includes:

[0088]

[0089]

[0090] Where H(k+1) is the predicted value of the humidity parameter output between the converter station equipment at the next moment; d is the set delay step number; H(kj) is the humidity value between the converter station equipment output d moments ago, 0≤j≤d-1; x H (k) is the external input humidity parameter matrix; is the supply air temperature, is the air valve opening, is the fan frequency;

[0091] S23. Processing the pressure parameter according to the pressure prediction model to obtain a pressure parameter prediction value; wherein the pressure prediction model includes:

[0092]

[0093]

[0094] Where Q(k+1) is the predicted value of the pressure parameter output between the converter station equipment at the next moment; d is the set delay step number; Q(kj) is the pressure value between the converter station equipment output d moments ago, 0≤j≤d-1; x Q (k) is the external input pressure parameter matrix; is the supply air temperature, is the air valve opening, is the fan frequency; f() in the above temperature prediction model, humidity prediction model, and pressure prediction model expresses the prediction model, and all the values ​​in f() are model inputs; the prediction model is applied to the particle swarm optimization to find the optimal solution for the air valve opening and frequency, and then output the control;

[0095] Obtaining the environmental parameter prediction value according to the temperature parameter prediction value, the temperature parameter prediction value, and the pressure parameter prediction value includes:

[0096] F1=k1(T * -T(k+i)) 2 +k2(H * -T(k+i)) 2 +k3(Q * -Q(k+i)) 2 ;

[0097] Among them, k1, k2 and k3 are the weight coefficients of temperature, humidity and pressure between devices respectively; T* is the temperature reference value, H* is the humidity reference value, and Q* is the pressure reference value; Q(k+i) is the predicted value of the pressure parameter output between the converter station devices at the next moment; H(k+i) is the predicted value of the humidity parameter output between the converter station devices at the next moment; T(k+i) is the predicted value of the temperature parameter output between the converter station devices at the next moment;

[0098] S3. Processing the power grid operation data according to a weight coefficient model to obtain a weight coefficient group. In an optional embodiment, the weight coefficient group is generated according to date, time, equipment load, and power supply status, and the obtained weight coefficient groups are: A1, A2, and A3.

[0099] S4. Obtain a relationship function based on the predicted environmental parameter value, the weight coefficient group, and the initial parameters of the wind turbine, specifically:

[0100] Get the relation function:

[0101] C=A1F1+A2F2+A3F3;

[0102] F2=P(k);

[0103] F3=f(k);

[0104] Among them, A1, A2 and A3 are the weight coefficients of the relationship function respectively; F1 is the predicted value of the environmental parameter; F2 and F3 are the initial parameters of the fan; P(k) is the air valve opening; f(k) is the fan frequency;

[0105] S5. Optimizing and calculating the relationship function using a particle swarm algorithm to output optimal fan operating parameters; that is, obtaining the fan frequency and air valve opening under the optimal solution by finding the optimal solution for the relationship function;

[0106] S6. Adjust the fan operating state according to the optimal fan operating parameters; apply the optimal fan frequency and air valve opening obtained in step S5 to actual combined machine control.

[0107] Example 2

[0108] This embodiment differs from the first embodiment in that the weight calculation model is limited. Specifically:

[0109] The weight coefficient group in step S3 is constructed as a variable weight coefficient; wherein A1 in the weight coefficient group reflects the control accuracy of the environmental parameter prediction value, and the air valve opening and fan frequency corresponding to A2 and A3 reflect the energy-saving control of the combined machine; if the current power equipment operating conditions require control reliability, the weight coefficient of A1 is more important; conversely, balancing the weight coefficients of A1, A2 and A3 on the basis of taking into account a certain control accuracy can achieve greater energy-saving effects; therefore, a dynamic variable weight calculation model is constructed based on the actual operation of the power grid, and its specific calculation process is as follows:

[0110] Obtaining environmental factors and initial weight coefficients, and generating a weight coefficient model based on the environmental factors and the initial weight coefficients;

[0111] The weight coefficient model includes:

[0112]

[0113] Among them, A j0 (j=1~3) is the initial value of the weight coefficient, and the initial value is the same, that is, A 10 =A 20 =A 30 ; A1(t) is the weight value corresponding to the predicted value of the environmental parameter; A2(t) and A3(t) are the weight values ​​corresponding to the initial parameters of the wind turbine; k(t) is the environmental factor;

[0114] The environmental factors include:

[0115]

[0116] Among them, k i (t) is the deviation value corresponding to different operating environments of the power equipment, gi(t) is the weight of each deviation value; t is the independent variable of the environmental factor; wherein, the k i (t) and g i (t) is set as follows:

[0117] 1) Deviation value setting for different operating environments of power equipment:

[0118]

[0119] Among them, if t = 1, k i (1) Take the date variable, the corresponding deviation value is 3; if t = 2, k i (2) Take the time variable, the corresponding deviation value is 5, and so on;

[0120] 2) Setting the weight of each deviation value

[0121] In an optional embodiment, different date weights are set according to the temperature conditions of different months in different regions. For example, the temperature is lowest from December to February each year, and the peak summer period is from June to October. The grid load is higher in winter and summer. The date weight values ​​are set as follows:

[0122] That is, the value of t is 1-12;

[0123] Set the time weight value based on the difference in power consumption during the day and at night. For example, if power consumption is lower at night, the control accuracy requirement for equipment operation can be reduced. In this case, set the time weight value as follows:

[0124] That is, the value of t is 0-24;

[0125] The load weight is set according to the ratio of actual load to rated load as follows, where P rateIt is the ratio of the current actual load to the rated load, that is, the value of t is 0-1:

[0126]

[0127] According to the power supply guarantee situation, the power supply guarantee weight value is set. B = 1 means it is in the power supply guarantee period, and B = 0 means it is in the non-power supply guarantee period, as follows:

[0128]

[0129] Please refer to Figure 3 , the relationship function is optimized and calculated by the particle swarm algorithm to output the optimal wind turbine operating parameters:

[0130] S1. Randomly set the search step size and initial position; wherein the initial position is a position vector whose elements include: the fan frequency and the air valve opening; wherein the fan frequency search range is 0-50 Hz, and the air valve opening search range is 0-100%, and the corresponding search range is used as the termination condition;

[0131] S2. Substitute the fan frequency and the air valve opening at the initial position, i.e., the randomly set position, into the relationship function; calculate the objective function value of each point, find the current individual extreme value Pb, and find the current global optimal solution Gb;

[0132] S3. Update the position and speed of each point. Update the speed and position of each point according to the following formula:

[0133] D=X*D+s1*t1*(P b -W)+s2*t2*(G b -W);

[0134] W=W+D;

[0135] Where D is the speed; X is the inertia weight; W is the current position (i.e., the current fan frequency and air valve opening); s1 and s2 are learning factors; t1 and t2 are random numbers distributed in the interval [0,1].

[0136] S4. Calculate the objective function value after the updated position, and determine the relationship between the current function value and the individual extreme value. If the former is better, update the position (fan frequency and air valve opening) and the individual extreme value and group extreme value. Otherwise, do not update.

[0137] S5. Determine whether the termination condition is met. If so, the calculation is terminated. If not, return to S3 to continue updating and iterating to find the optimal solution; that is, the optimal fan frequency and air valve opening are finally output.

[0138] Example 3

[0139] Please refer to Figure 4 , a converter station HVAC system energy-saving control terminal includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements each step of a converter station HVAC system energy-saving control method as described in Embodiment 1, 2, or 3.

[0140] In summary, the present invention provides a method and terminal for energy-saving control of a converter station HVAC system. The method combines the input temperature, humidity parameters, and pressure parameters with the air valve opening and the fan frequency according to the temperature prediction model, the humidity prediction model, and the pressure prediction model, thereby establishing a relationship between the fan operating parameters and the temperature, humidity, and pressure, and outputs the corresponding environmental parameter prediction value. At the same time, a weight coefficient is generated according to the date, time, load, and power supply situation. The environmental parameter prediction value is further combined with the weight coefficient group to obtain a relationship function, and the relationship function is optimized and calculated by the particle swarm algorithm. Finally, the optimal fan operating parameters are output to optimize the fan control, thereby ensuring that the environmental parameters between the converter station equipment meet the normal operating conditions of each power equipment and maximize the energy saving of the HVAC system.

[0141] The above descriptions are merely embodiments of the present invention and are not intended to limit the patent scope of the present invention. Any equivalent transformations made using the contents of the present invention's description and drawings, or directly or indirectly applied in related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for controlling energy conservation in a HVAC system of a converter station, characterized in that: Including steps: Obtain historical environmental parameters between converter station equipment, grid operation data, and initial parameters of wind turbines; Processing historical environmental parameters between equipment in the converter station according to the prediction model to obtain predicted values ​​of the environmental parameters; Processing the power grid operation data according to a weight coefficient model to obtain a weight coefficient group; Obtaining a relationship function according to the predicted value of the environmental parameter, the weight coefficient group and the initial parameters of the wind turbine; The relationship function is optimized and calculated by a particle swarm algorithm to output the optimal wind turbine operating parameters; Adjusting the fan operating state according to the optimal fan operating parameters; Wherein, the historical environmental parameters include temperature parameters, humidity parameters, pressure parameters and fan operating parameters; respectively construct prediction models between the temperature parameters, humidity parameters and pressure parameters and the fan operating parameters to obtain a temperature prediction model, a humidity prediction model and a pressure prediction model; obtain a temperature parameter prediction value, a temperature parameter prediction value and a pressure parameter prediction value according to the temperature prediction model, the humidity prediction model and the pressure prediction model; obtain the environmental parameter prediction value according to the temperature parameter prediction value, the humidity parameter prediction value and the pressure parameter prediction value; Obtaining the environmental parameter prediction value according to the temperature parameter prediction value, the humidity parameter prediction value, and the pressure parameter prediction value includes: ； Among them, k1, k2 and k3 are the weight coefficients of temperature, humidity and pressure in the equipment room respectively; is the temperature reference value, is the humidity reference value, is the pressure reference value; Q(k+1) is the predicted value of the pressure parameter predicted and outputted between the converter station equipment at the next moment; H(k+1) is the predicted value of the humidity parameter predicted and outputted between the converter station equipment at the next moment; T(k+1) is the predicted value of the temperature parameter predicted and outputted between the converter station equipment at the next moment; The weight coefficient model includes: ； Among them, A 10 、A 20 、A 30 is the initial value of the weight coefficient, which is the same as A 10 =A 20 =A 30 ; A1(t) is the weight value corresponding to the predicted value of the environmental parameter; A2(t) is the weight value corresponding to the initial parameter F2 of the wind turbine; A3(t) is the weight value corresponding to the initial parameter F3 of the wind turbine; k(t) is the environmental factor; The relationship function obtained according to the environmental parameter prediction value, the weight coefficient group and the initial parameters of the wind turbine includes: ； Among them, A1, A2 and A3 are the weight coefficients of the relationship function respectively; F1 is the predicted value of the environmental parameter; F2 and F3 are the initial parameters of the wind turbine; The environmental factors include: ； Among them, k i (t) is the deviation value corresponding to different operating environments of power equipment, g i (t) is the weight of each deviation value; t is the independent variable of environmental factors.

2. The energy-saving control method for a converter station HVAC system according to claim 1, characterized in that: The historical environmental parameters include temperature parameters, humidity parameters, pressure parameters and fan operation parameters; The processing of the historical environmental parameters between the equipment in the converter station according to the prediction model to obtain the predicted values ​​of the environmental parameters includes: Constructing prediction models between the temperature parameter, humidity parameter, and pressure parameter and the fan operating parameters respectively to obtain a temperature prediction model, a humidity prediction model, and a pressure prediction model; Processing the temperature parameter according to the temperature prediction model to obtain a temperature parameter prediction value; Processing the humidity parameter according to the humidity prediction model to obtain a humidity parameter prediction value; Processing the pressure parameter according to the pressure prediction model to obtain a pressure parameter prediction value; The environmental parameter prediction value is obtained according to the temperature parameter prediction value, the temperature parameter prediction value and the pressure parameter prediction value.

3. The energy-saving control method for a converter station HVAC system according to claim 2, characterized in that: The temperature prediction model includes: ； ； Where, T(k+1) is the predicted value of the temperature parameter output between the converter station equipment at the next moment; d is the set delay step number; T(kj) is the temperature value between the converter station equipment output at the previous j moments, 0≤j≤d-1; x T (k) is the external input temperature parameter matrix; is the supply air temperature, is the air valve opening, is the fan frequency.

4. The energy-saving control method for a converter station HVAC system according to claim 2, characterized in that: The humidity prediction model includes: ； ； Where H(k+1) is the predicted value of the humidity parameter output between the converter station equipment at the next moment; d is the set delay step number; H(kj) is the humidity value between the converter station equipment output at the previous j moments, 0≤j≤d-1; x H (k) is the external input humidity parameter matrix; is the supply air temperature, is the air valve opening, is the fan frequency.

5. The energy-saving control method for a converter station HVAC system according to claim 2, characterized in that: The pressure prediction model includes: ； ； Where Q(k+1) is the predicted value of the pressure parameter output between the converter station equipment at the next moment; d is the set delay step number; Q(kj) is the pressure value between the converter station equipment output at the previous j moments, 0≤j≤d-1; x Q (k) is the external input pressure parameter matrix; is the supply air temperature, is the air valve opening, is the fan frequency.

6. The energy-saving control method for a converter station HVAC system according to claim 1, characterized in that: It also includes constructing the weight coefficient model: Obtain environmental factors and initial weight coefficients; A weight coefficient model is generated according to the environmental factors and the initial weight coefficients.

7. A converter station HVAC system energy-saving control terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, each step of the energy-saving control method for a converter station HVAC system according to any one of claims 1 to 6 is implemented.

Images