Central air conditioning billing device and system

Abstract

The present invention discloses a central air conditioning billing device and system, which includes a control unit and a sensor detection unit, a user interface unit, and an operating condition adjustment unit connected thereto; a first and a second neural network are established in the control unit to respectively model the cooling capacity characteristics of the terminal unit and the cooling characteristics of rooms in different orientations, and the cooling capacity of the terminal unit and the cooling consumption of the room under actual operating conditions are predicted based on the two models; and the predicted actual cooling consumption is corrected based on the differences in cooling consumption characteristics of rooms in different orientations, and then the central air conditioning costs are apportioned. The present invention can dynamically reflect the changes in the cooling capacity of the terminal unit, and improves the measurement accuracy compared to the terminal detection method; through the design of the model structure and the correction coefficient formula, effective compensation is achieved for various influencing factors such as sunlight and heat transfer from adjacent rooms. The present invention can accurately measure the actual cooling capacity of the central air conditioning terminal unit under different operating conditions, and achieve fair billing based on the effective cooling consumption, which is conducive to the economical use of air conditioners.

Description

Technical Field

[0001] The present invention relates to the field of central air-conditioning metering and billing, and in particular to a central air-conditioning billing device and system. Background Art

[0002] A central air conditioning system consists of a heat and cold source system, a heat and cold transmission system, and an air conditioning system. In summer, the cooling system provides the required cooling for the air conditioning system to offset the indoor heat load; in winter, the heating system provides cooling for the air conditioning system to offset the indoor heat load. Central air conditioning systems deliver cooling from the main unit to each terminal unit via refrigerant pipes. The refrigerant can be water, air, or a refrigerant. For example, a water-cooled central air conditioner uses a single main unit connected to multiple fan coil units via chilled water pipes to deliver cooling to different rooms to achieve indoor air conditioning.

[0003] The most prominent feature of central air conditioning is that it provides a comfortable working and living environment. With the rapid development of air conditioning demand in large domestic public buildings, more and more office buildings, shopping malls, serviced apartments and other buildings have begun to install central air conditioning systems.

[0004] In the new century, humanity faces two major challenges: energy shortages and environmental degradation. Construction, industrial production, and transportation are my country's three largest energy-consuming sectors, accounting for approximately 30% of national energy consumption. Air conditioning, cooling, and heating systems account for 50% to 60% of total building energy consumption. Energy-saving measures for central air conditioning in public buildings can effectively reduce building energy consumption and achieve sustainable development. However, many places still use the traditional, simple area-based billing method for central air conditioning. While this method is simple and convenient, many people do not consider whether air conditioning use is energy-efficient. This leads to the phenomenon of running air conditioners even when no one is around, resulting in energy waste.

[0005] If energy metering is adopted, and users pay only for what they use, it can awaken people's awareness of energy conservation. Adopting a reasonable billing method can change consumers' energy consumption habits. Therefore, choosing and adopting a reasonable central air conditioning billing method is of great significance in energy conservation.

[0006] Central air conditioning was initially charged based on area, leading to wasted energy. To address this, a new household-based billing system has been proposed in recent years. This system aims to rationally allocate costs to each room, achieving reasonable billing and thus reducing the severe waste of electricity and the persistently high energy consumption of buildings.

[0007] Chilled water metering is a new technology for measuring and allocating cooling capacity for central air conditioning. There are two types of chilled water metering. One involves installing a water meter at the outlet of the fan coil unit to measure the chilled water flow rate within the fan coil unit. This method simply addresses the issue of varying chilled water flow rates depending on usage, but it doesn't account for the inlet and outlet temperatures of the chilled water. The other method, on the other hand, assumes the chilled water flow rate remains constant and only measures the inlet and outlet temperature difference, charging the user as long as the air conditioner is turned on. These methods, including the subsequently improved energy meter method, measure a few fixed parameters at the end-user end. This method fails to reflect the impact of changes in the central air conditioning system's overall operating conditions on the cooling supply at the end-user end, making it difficult to reflect the user's actual cooling consumption.

[0008] Taking water-cooled central air conditioners as an example, another issue that needs to be noted in traditional cooling capacity metering is that the temperature difference between the supply and return water is much smaller than that of heating. Therefore, this requires the measurement accuracy of the temperature sensor to be higher. Undoubtedly, the use of high-precision sensors at each end will greatly increase user costs; and the use of ordinary sensors generally has the problem of large sampling fluctuations and inaccurate measurement.

[0009] The promotion of high-cost energy meters is difficult. According to surveys, most of the newly built apportioned billing systems for various types of central air-conditioning cooling capacity are based on indirect billing or equivalent billing projects, and time-based billing is the most common type of indirect or equivalent billing. The cooling capacity equivalent or cumulative usage of time-based metering is the estimated quantity under rated test conditions, such as the Chinese patent with publication number CN 100504338C. Its basic principle is to accumulate the working time of each wind speed at the terminal. Time-based billing starts from the fact that the cooling capacity is proportional to the temperature difference between the inlet and outlet water of the fan coil unit, as well as the water volume. The fan coil unit wind speed is regarded as an influencing factor of the temperature difference. It is believed that the greater the wind speed, the greater the air volume flow rate, and thus the greater the cooling capacity equivalent. For a fan coil unit with three wind speed levels V: high, medium and low, the cooling capacity equivalent is calculated based on the time-based metering. H 、V M 、V L The cooling capacity of a constant fan coil unit is:

[0010] Q=K H t H +K M t M +K L t L ,

[0011] Among them, t H , t M , t L is the opening time of the two-way valve at high, medium and low wind speeds (s), K H , K M , K Lis the proportional coefficient (kJ / s) at high, medium and low wind speeds. The two-way valve itself is a switch component. By detecting the opening and closing of each two-way valve, the cumulative opening time of the two-way valve within a certain period of time and the different wind speed gears can be obtained. It can be seen that in the time-based measurement method, the cooling capacity delivered by each terminal fan of the central air conditioner is calculated based on the cumulative value of the time of opening the two-way valve switch at different wind speeds. The key to this method is how to obtain K H , K M , K L The current method is to use estimated empirical or theoretical values, or to use the coefficient values ​​calculated by the fan coil manufacturer based on rated conditions such as a dry bulb temperature of 27°C, a wet bulb temperature of 19.5°C, and a chilled water inlet temperature of 7°C, and the cooling capacity at each airflow rate.

[0012] This method of calculating the cooling capacity under dynamic conditions using a fixed coefficient can obviously only be used for estimation and cannot be used for accurate measurement.

[0013] Measuring the cooling capacity of central air conditioning systems is the foundation of cooling billing, but many factors must be considered from measurement to billing. For typical buildings, cooling costs cannot be calculated simply by multiplying the cooling capacity used by the unit price. The impact of heat transfer between different locations in the air-conditioned rooms and between households must also be considered.

[0014] Because room heat loads are dependent on factors such as environmental parameters, solar radiation, and the heat transfer characteristics of the supporting structure, room heat loads can vary significantly depending on their orientation (e.g., south vs. north), or at different heights (e.g., top, middle, or bottom floors). Therefore, centralized cooling systems should adjust the cooling capacity or unit price for these rooms based on their location and orientation. Inter-unit heat transfer is also a significant factor. If adjacent rooms are underutilized or vacant, the cooling load in the air-conditioned room will increase. If charging solely based on cooling capacity, the cooling charges for rooms of the same size will vary significantly, which is also unfair.

[0015] However, because multiple factors, such as sunlight, structure, and adjacent rooms, interact and interact, it's difficult to independently distinguish the impact of each factor. Existing billing methods often rely on empirical coefficients. For example, in his dissertation, "Research on Issues Related to Metered Heating," Tian Yuchen of Tianjin University combined reference standards to apply statistical methods to calculate correction coefficients for each household, based on different building structures, room types, and orientations. He performed case studies on correction coefficients for rooms in different locations in non-energy-efficient residences, assigning correction coefficients ranging from 0.55 to 1.00 for nine room types. This example calculation provides only a rough guideline and cannot accurately quantify the cooling consumption of rooms in different orientations within a specific building.

[0016] Therefore, the industry urgently needs a set of devices and systems that can accurately measure the cooling equivalent of central air-conditioning terminals under actual working conditions and make corrections to the cooling consumption of rooms in different directions, so as to implement a reasonable apportionment and billing device and system based on cooling consumption and quantitatively correct environmental factors, so as to achieve the goal of paying more for more use and paying less for less use, thereby ultimately improving the energy-saving awareness of the majority of users and achieving the goal of energy saving and environmental protection. Summary of the Invention

[0017] In view of this, the purpose of the present invention is to provide a device and system that can accurately measure the cooling capacity of the terminal unit in the central air conditioner and bill the room after quantitative correction of the cooling capacity, so as to achieve reasonable and effective billing according to the actual cooling capacity.

[0018] The technical solution of the present invention is to provide a central air conditioning billing device with the following structure, which includes: a control unit, and a sensing detection unit, a user interface unit and an operating condition adjustment unit connected to the control unit;

[0019] The sensing detection unit detects the working condition and environmental conditions of the central air conditioner;

[0020] The control unit is configured to:

[0021] First, the cooling equivalent of the central air-conditioning terminal unit is measured and modeled.

[0022] The first neural network is established in the control unit, taking the room where the terminal unit is located as the heat load, the working conditions of the central air-conditioning system as the input, and the equivalent cooling capacity per unit time of the terminal unit in this room as the output.

[0023] Using the cooling capacity calculated by the reference air conditioning unit in the system under the same heat load conditions as the cooling capacity equivalent of the terminal unit, collecting first data samples under different operating conditions and training the first neural network;

[0024] Secondly, the rooms cooled by central air conditioning are classified by location type, and a cooling consumption model is established for each type of room.

[0025] The current room temperature and outdoor temperature during cooling are used as two scalars, as well as a vector consisting of the room temperature values ​​in the six directions of the current room (front, back, left, right, up, down) as inputs, and the equivalent cooling consumption per unit time of the room as output. A second neural network is established for each room in the control unit.

[0026] Adaptively control the terminal unit in the current room to maintain the room temperature unchanged in stages. When the working conditions are approximately stable, collect second data samples of the second neural network under different input conditions. The output of the samples is predicted by the first neural network, and training is performed based on the collected data samples;

[0027] Based on the offline cooling and consumption model, the cost of central air conditioning is allocated by time period when applied online.

[0028] First, calculate the correction coefficient based on the cooling consumption model and the current room working conditions. Where i is the current room number, room number i = any integer from 1 to N, N is the total number of rooms, p i 、p i0 For The mapping output of the second neural network when it is the input vector, is the current working condition of room i, The current room temperature and outdoor temperature The same, and the indoor temperature values ​​of the room in the six directions of the current room are taken as the current room temperature;

[0029] Then calculate the cost of room i in time period d:

[0030] in, PF is the cooling capacity per unit time equivalent of the terminal unit predicted by the first neural network in the current room i (t) The accumulated cooling capacity during this period, Q jd is the cooling capacity of room j during this period, k j3 is the corresponding coefficient of room j, C d The total cost to be shared for central air conditioning during this period.

[0031] In another embodiment of the present invention, a central air-conditioning billing device of the following structure is further provided, comprising: a control unit, and a sensing detection unit, a user interface unit, and an operating condition adjustment unit connected to the control unit;

[0032] The sensing detection unit detects the working condition and environmental conditions of the central air conditioner;

[0033] The control unit is configured to:

[0034] First, the cooling equivalent of the central air-conditioning terminal unit is measured and modeled.

[0035] The first neural network is established in the control unit, taking the room where the terminal unit is located as the heat load, the working conditions of the central air-conditioning system as the input, and the equivalent cooling capacity per unit time of the terminal unit in this room as the output.

[0036] Using the cooling capacity calculated by the reference air conditioning unit in the system under the same heat load conditions as the cooling capacity equivalent of the terminal unit, collecting first data samples under different operating conditions and training the first neural network;

[0037] Secondly, the rooms cooled by central air conditioning are classified by location type, and a cooling consumption model is established for each type of room.

[0038] The current room temperature and outdoor temperature during cooling are used as two scalars, as well as a vector consisting of the room temperature values ​​in the six directions of the current room (front, back, left, right, up, down) as inputs, and the equivalent cooling consumption per unit time of the room as output. A second neural network is established for each room in the control unit.

[0039] Adaptively control the terminal unit in the current room to maintain the room temperature unchanged in stages. When the working conditions are approximately stable, collect second data samples of the second neural network under different input conditions. The output of the samples is predicted by the first neural network, and training is performed based on the collected data samples;

[0040] Based on the offline cooling and consumption model, the cost of central air conditioning is allocated by time period when applied online.

[0041] First calculate the conversion coefficient based on the current room conditions Where i is the current room number, s i 、s j are the areas of the i-th and j-th rooms respectively, the room numbers i, j = any integer from 1 to N, N is the total number of rooms, p i 、p j Room i and j are As input vector When they each correspond to the mapping output of the second neural network, is the current working condition of room i,

[0042] And calculate the comfort factor Where p ic For room i As input vector When it corresponds to the mapping output of the second neural network, the working condition and The only difference is that the current room temperature is a preset comfort temperature;

[0043] Then calculate the cost of room i in time period d:

[0044] Among them, k j1 、k j2 is the corresponding coefficient of room j, C d The total cost to be shared for central air conditioning during this period.

[0045] Preferably, the comfortable temperature may be 25 degrees Celsius during cooling and 18 degrees Celsius during heating.

[0046] Preferably, the room number corresponding to the max() function can be obtained offline first.

[0047] As a preference, in the calculation of the correction coefficient for the dth time period, the input vector of the second neural network is The values ​​of each parameter are the average values ​​within the period.

[0048] As a preference, the cooling capacity Q during this period is id Obtained by discrete short-period accumulation.

[0049] Preferably, a solar radiation intensity parameter is added to the input of the second neural network.

[0050] Preferably, the central air conditioner is a water-cooled central air conditioner, the terminal unit is a terminal damper, and the first neural network takes as input the four scalar quantities of the central air conditioner host's chilled water supply flow, the supply and return water temperature difference, the current temperature and humidity of the room, and a vector consisting of the opening state values ​​of all terminal dampers;

[0051] Preferably, the central air conditioner is a full-air central air conditioner, the terminal unit is a terminal windshield, and the first neural network takes as input the air flow rate of the central air conditioner main unit's air outlet, the supply and return air temperature difference, the current temperature and humidity of the room, and a vector consisting of the opening state values ​​of all terminal windshields;

[0052] Preferably, the central air conditioner is a variable refrigerant flow central air conditioner, the terminal unit is an indoor unit, and the first neural network takes as input a vector consisting of the central air conditioner host power, indoor unit power, current temperature and humidity of the room, and the fan on state values ​​of all terminal units;

[0053] Preferably, when collecting the first data sample: a target temperature is set according to the initial temperature of the room, the terminal windshield fan driver is controlled to operate to adjust the room temperature to the target temperature and obtain the current humidity as the target humidity; after the room is maintained at the target temperature for a period of time, the reference air conditioning unit and the terminal windshield are respectively used as cold sources to work for a certain period of time to collect samples, and the room temperature is maintained at the target temperature when the two cold sources are working separately, wherein the terminal unit fan works in PWM mode, and when the reference air conditioning unit is working, the humidity is also maintained at the target humidity through the working condition adjustment unit.

[0054] Based on the working characteristics and working conditions of the reference air conditioning unit, the cooling power consumption is calculated and divided by the average PWM duty cycle of the terminal damper or the terminal unit fan, and the obtained value is used as the cooling capacity equivalent per unit time when the terminal damper or the terminal unit fan is currently open at the state value F.

[0055] As a preference, when a room has multiple terminal units, the cooling consumption of the current room during this period is Among them F i It is the collection of all wind screens in the current room.

[0056] As a preference, the cost sharing of central air conditioning also includes a portion shared by area, so the cost of the i-th room in the d-th time period is:

[0057]

[0058] Among them, C d0 This is the basic cost of central air conditioning.

[0059] Preferably, the control unit is provided with a main processing module, which includes a sample extraction module for collecting data samples of the second neural network. The sample extraction module is configured to: periodically and continuously collect the heat load conditions and cooling consumption parameters of the central air-conditioning cooling room, and search for periods in which the input quantities of the second neural network vary within a preset fluctuation threshold, and store the data of the filtered periods into the data sample set of the second neural network.

[0060] Preferably, the preset fluctuation threshold is ±5%.

[0061] Preferably, the preset fluctuation threshold includes a first fluctuation threshold and a second fluctuation threshold. When the change of the second neural network input within a period exceeds the first fluctuation threshold but is less than the second fluctuation threshold, the sample value of the input within this period is taken as its time average value within this period.

[0062] As a preferred method, the outdoor temperature t w For example, the average outdoor temperature in period T, i.e. its time average value, is Preferably, the first fluctuation threshold and the second fluctuation threshold are ±2% and ±5% respectively.

[0063] Preferably, each sample data of the first neural network is collected in the following manner:

[0064] After the room is kept at the target temperature for a period of time, the driver is turned off and the timing is started. The reference air conditioning unit is controlled to maintain the room temperature at the target temperature from t = 0 to t = T1. At the same time, the operating condition adjustment unit is controlled to keep the room humidity at the target humidity. The cooling power q(t) is calculated based on the operating characteristics and operating conditions of the reference air conditioning unit and its cooling capacity in the first period is accumulated.

[0065] Turn off the reference air conditioning unit and start timing again. After setting the fan's wind speed opening state value F, control the driver to work in PWM mode and maintain the room temperature at the target temperature from t=0 to t=T2 in the second period. Calculate the equivalent time Where Δ(t) is the PWM value,

[0066] The driver is turned off again and the timing is restarted. The reference air conditioning unit is controlled to maintain the room temperature at the target temperature during the third period from t=0 to t=T1. The working condition adjustment unit is controlled to maintain the room humidity at the target humidity. The cooling capacity of the third period is calculated again.

[0067] Calculate the cooling capacity per unit time of the wind speed under the current working conditions:

[0068] Preferably, the sensing unit is provided with a flow detection module, a temperature detection module at the inlet of the chilled water / cold air supply main pipe of the central air-conditioning host, and a temperature detection module at the outlet end of the return water / return air main pipe connected to the host.

[0069] A plurality of temperature detection modules located at different positions in the room are arranged at the same height and are respectively located on two vertical diagonal lines.

[0070] Preferably, the number of the plurality of temperature detection modules is 3 to 6 and the height thereof is about 2 meters.

[0071] Preferably, the humidity is sensed by a humidity detection module in the sensing unit which is arranged in the middle of the room return air duct.

[0072] Corresponding to the three gears of low, medium and high fan speed, the wind gear opening state value can be respectively set as the three normalized values ​​of the fan power corresponding to the three gears.

[0073] As a preference, when the driver works in PWM mode, the equivalent time can also be calculated by multiplying the normalized speed of the fan motor at different wind speeds by the integral of the power-on duty cycle Δ(t) within the cycle. Where k(t) is the normalized speed. If the maximum speed is 1, the value for other speeds is the ratio of the speed value to the maximum speed.

[0074] Preferably, the temperature difference threshold is a value between 0.1°C and 0.5°C.

[0075] Preferably, the temperature difference between the target temperature and the initial temperature is ≥5°C;

[0076] In the same central air-conditioning system, a first neural network is established for each model of terminal unit and training samples are collected separately.

[0077] Preferably, the reference air conditioning unit adopts a hot and cold air conditioner; if the ratio of the equivalent time dT to the second period length T2 is less than the duty cycle threshold Δs, when collecting the sample, within the second period time range, the reference air conditioning unit is also controlled to work in the heating mode from τ = 0 to τ = T3, and the thermal equivalent of the heating is recorded. Accordingly, the cooling capacity per unit time of the air gear under the current working conditions is calculated as follows:

[0078]

[0079] Preferably, an electric heating module can be set in the reference air conditioning unit to control the electric heating module to generate heat within the time range from τ=0 to τ=T3, and record the thermal equivalent of heating Q3=pr·T3, where pr is the heating power of the electric heating module (kW, i.e., kJ / s), and PF is calculated similarly.

[0080] Preferably, within the time ranges of T1 and T2, the heating module can be turned on with known power and heat calculation can be performed.

[0081] Preferably, the rated cooling power of the reference air conditioning unit is 0.85 to 1.15 times the cooling capacity of the maximum windshield of the terminal fan.

[0082] Preferably, for the same model terminal units, they are further subdivided into small categories based on the horizontal distance and vertical distance between the terminal units and the inlet of the refrigerant supply main pipeline of the central air-conditioning host. A first neural network is established for each of the small categories and training samples are collected separately.

[0083] Preferably, the working condition adjustment unit is provided with a uniform temperature module, which includes a base, a vertical rotation axis, an angled support arm, a horizontal rotation axis, and a pitchable bracket having two sections of support arms movably connected by bolts. A retractable support rod is connected between the outer ends of the two sections of the support arms, which is at an acute angle to the axis of the horizontal rotation axis. A uniform temperature fan is carried at the end of the pitchable bracket.

[0084] The control unit is also configured to control the operation of the temperature uniforming module so that the temperature uniforming fan shaft moves in a spatial spiral line to transmit the cold air blown out by the central air-conditioning terminal unit and / or the reference air conditioning unit to all directions of the room until the temperature difference of the multiple temperature detection modules in the room is less than the temperature difference threshold.

[0085] Preferably, the temperature uniforming fan has a cover on the back.

[0086] Preferably, the sensing detection unit is provided with an image acquisition module;

[0087] The control unit further includes an input module, an image processing module, a fan processing module, a mapping module and an output module, and the control unit is further configured to:

[0088] The image processing module analyzes the room orientation features based on the room image acquired by the image acquisition module and extracts two mutually perpendicular diagonal lines;

[0089] The main processing module responds to events and schedules other modules;

[0090] The fan processing module adjusts the PWM wave duty cycle value of the driver according to the average value of the multiple temperatures at different positions in the room;

[0091] The mapping module establishes the first and second neural networks, wherein the input layers of the first and second neural networks receive their input quantities from the main processing module respectively, and the output quantities of their respective output layers are transmitted to the iterative learning unit and the main processing module respectively through the first connection matrix and the second connection matrix; when the first and second neural networks are trained offline, the iterative learning unit adjusts the connection weights of the first and second neural networks based on the actual value of the unit time cooling capacity equivalent and the network output value input by the main processing module and the first and second neural networks respectively through the first connection matrix; during online metering, the first connection matrix is ​​disconnected, and the first and second neural networks respectively predict the unit time cooling capacity equivalent and output them to the main processing module through the second connection matrix, which is then processed and analyzed by the main processing module and output through the output module.

[0092] Preferably, the control unit further comprises a working condition processing module, which comprises a uniform temperature planning unit and a humidity adjustment unit.

[0093] The temperature uniformity planning unit plans a spiral trajectory for the wind direction of the temperature uniformity fan in the temperature uniformity module based on the diagonal line and controls the temperature uniformity module to supply air according to the trajectory in each time period.

[0094] Then, the moving speed of the temperature uniforming fan along the trajectory is controlled according to the temperature characteristics of the multiple temperature detection modules in the room, and the moving speed is inversely proportional to the temperature difference between the temperature in the corresponding direction and the target temperature.

[0095] Preferably, the reference air conditioning unit is provided with a dry-bulb and wet-bulb temperature detection module and an air supply volume detection module. The sensible cooling capacity under different working conditions is obtained according to standard tests and the parameters are recorded as a working characteristic table or curve. Based on the dry-bulb and wet-bulb temperatures and air supply volume of the current inlet and outlet air, the cooling capacity of the reference air conditioning unit in the current room is calculated by querying and interpolating the working characteristics.

[0096] Preferably, taking a water-cooled central air conditioner as an example, the first neural network adopts a BP neural network, and its model is:

[0097] The output of the jth node in the hidden layer is

[0098] The output of the output layer is

[0099] Among them, x1~x4 are the four scalars of the central air-conditioning host chilled water supply flow, supply and return water temperature difference, the current temperature and humidity of the room, x5~xn are the open state values ​​of all terminal units; the f() function is taken as the sigmoid function, w ij and v j are the connection weights from the input layer to the hidden layer and from the hidden layer to the output layer, θ j and θ are the hidden layer and output layer thresholds respectively, n and k are the number of nodes in the input layer and hidden layer respectively, and the gradient descent method is used for network training.

[0100] In another embodiment of the present invention, a central air conditioning billing system is provided, comprising:

[0101] User interface unit for entering parameters, initiating operations and human-computer interaction;

[0102] Driver for driving the fan corresponding to the central air-conditioning terminal unit;

[0103] A reference air conditioning unit whose operating characteristics have been obtained in advance and used as a reference for cooling capacity;

[0104] A sensor detection unit for detecting the working conditions and environment of the central air conditioning unit and the reference air conditioning unit;

[0105] A working condition adjustment unit for adjusting the operating conditions of the central air-conditioning terminal unit and the reference air-conditioning unit;

[0106] A control unit connected to the driver, the reference air conditioning unit, the sensing detection unit, the user interface unit, and the working condition adjustment unit; wherein the control unit is configured to:

[0107] First, the cooling equivalent of the terminal unit is measured and modeled.

[0108] The first neural network is established in the control unit, taking the room where the terminal unit is located as the heat load, the working conditions of the central air-conditioning system as the input, and the equivalent cooling capacity per unit time of the terminal unit in this room as the output.

[0109] Using the cooling capacity calculated by the reference air conditioning unit in the system under the same heat load conditions as the cooling capacity equivalent of the terminal unit, collecting first data samples under different operating conditions and training the first neural network;

[0110] Secondly, the rooms cooled by central air conditioning are classified by location type, and a cooling consumption model is established for each type of room.

[0111] The current room temperature and outdoor temperature during cooling are used as two scalars, as well as a vector consisting of the room temperature values ​​in the six directions of the current room (front, back, left, right, up, down) as inputs, and the equivalent cooling consumption per unit time of the room as output. A second neural network is established for each room in the control unit.

[0112] Adaptively control the terminal unit in the current room to maintain the room temperature unchanged in stages. When the working conditions are approximately stable, collect second data samples of the second neural network under different input conditions. The output of the samples is predicted by the first neural network, and training is performed based on the collected data samples;

[0113] Based on the offline cooling and consumption model, the cost of central air conditioning is allocated by time period when applied online.

[0114] First, calculate the correction coefficient based on the cooling consumption model and the current room working conditions. Where i is the current room number, room number i = any integer from 1 to N, N is the total number of rooms, p i 、p i0 For The mapping output of the second neural network when it is the input vector, is the current working condition of room i, The current room temperature and outdoor temperature The same, and the indoor temperature values ​​of the room in the six directions of the current room are taken as the current room temperature;

[0115] Then calculate the cost of room i in time period d:

[0116] in, PF is the cooling capacity per unit time equivalent of the terminal unit predicted by the first neural network in the current room i (t) The accumulated cooling capacity during this period, Q jd is the cooling capacity of room j during this period, k j3 is the corresponding coefficient of room j, C d The total cost to be shared for central air conditioning during this period.

[0117] Preferably, the driver is built into the terminal unit to drive the fan motor, and the control unit controls the terminal unit to operate in a PWM mode through the driver interface.

[0118] Preferably, the cost sharing calculation is replaced by:

[0119] First calculate the conversion coefficient based on the current room conditions Where i is the current room number, s i 、s j are the areas of the i-th and j-th rooms respectively, the room numbers i, j = any integer from 1 to N, N is the total number of rooms, p i 、p j Room i and j are As input vector When they each correspond to the mapping output of the second neural network, is the current working condition of room i,

[0120] And calculate the comfort factor Where p ic For room i As input vector When it corresponds to the mapping output of the second neural network, the working condition and The only difference is that the current room temperature is set to a preset comfort temperature such as 25 degrees Celsius;

[0121] Then calculate the cost of room i in time period d:

[0122] Among them, k j1 、k j2 is the corresponding coefficient of room j, C d The total cost to be shared for central air conditioning during this period.

[0123] Compared with the prior art, the device and system of the present invention have the following advantages: the present invention uses the rooms where the central air-conditioning terminal units are located, which are distributed in different locations, as the heat load, and uses the movable reference air-conditioning unit that has been calibrated in advance with high precision as a reference to measure and calibrate the cooling equivalent of the central air-conditioning terminal unit; and uses the calibrated terminal unit to measure the cooling power per unit area of ​​rooms in different orientations under similar conditions of sunlight and adjacent rooms, and obtains the correction coefficient of each room accordingly, thereby achieving the purpose of billing the central air-conditioning according to the actual cooling consumption and comfort level of the basic indoor heat load. The present invention uses key operating factors affecting the cooling supply of central air conditioning terminal units, such as the chilled water supply flow rate of the main unit, the supply and return water temperature difference, the current temperature and humidity of the room, and a vector consisting of the open state values ​​of all terminal units as input quantities, and uses the cooling capacity per unit time of the current fan speed in the room, i.e., the cooling capacity equivalent, as the output quantity, to establish a first neural network as a terminal unit metering mapping model. This model can reflect the impact of actual changes in the central air conditioning operating conditions on the cooling capacity of the terminal units and can dynamically reflect changes in the cooling capacity of the terminal units, overcoming the shortcomings of the prior art in estimating the actual changing fan speed cooling capacity with fixed coefficients. At the same time, the measurement points for the water supply temperature difference and flow rate are only set at the entrance and exit of the central air conditioning main unit chilled water supply pipeline, replacing the multi-point arrangement at each terminal. The detection of large flow rates relative to small flow rates at the terminal can reduce the relative error, and the significant reduction in measurement points allows the use of high-precision temperature difference detection to further reduce metering errors. Furthermore, the present invention categorizes fan terminals based on their model and their horizontal and vertical distances from the inlet of the central air conditioning unit's chilled water supply main. The model uses the power-on status of all terminal units as input, thereby decoupling the constraints between each fan terminal. In the shared billing process, the room cooling model, represented by a second neural network, uses air temperature and radiation factors as inputs to compensate for differences in sunlight exposure in rooms with different orientations. The room temperatures of adjacent rooms in six directions are used as input to reflect the impact of heat transfer from adjacent rooms on cooling consumption. Furthermore, correction coefficients are used to eliminate differences in the building envelope.

[0124] The present invention can accurately measure the actual cooling capacity of the central air-conditioning terminal unit under different working conditions, and realizes billing according to the effective cooling capacity consumed by the indoor heat load, which is conducive to the economical use of the air-conditioning. BRIEF DESCRIPTION OF THE DRAWINGS

[0125] Figure 1A 、 Figure 1B Two structural schematic diagrams of the central air-conditioning billing device and system of the present invention;

[0126] Figure 2 Schematic diagram of the structure of the control unit of the present invention;

[0127] Figure 3A This is a schematic diagram of the water-cooled central air conditioner structure. Figure 3BThis is a schematic diagram of the structure of a central air conditioner with variable refrigerant flow;

[0128] Figure 4A This is a schematic diagram of the cooling supply of the reference air conditioning unit. Figure 4B This is a schematic diagram of cooling for the terminal fan unit;

[0129] Figure 5A 、 Figure 5B Schematic diagram of temperature detection module distribution and uniform temperature processing;

[0130] Figure 6 It is a structural diagram of the temperature uniformity module;

[0131] Figure 7A This is a schematic diagram of the cooling capacity measurement mapping principle of the present invention; Figure 7B Schematic diagram of the cold conversion principle for the room;

[0132] Figure 8A is a structural diagram of the mapping module in the present invention, Figure 8B Schematic diagram of the first neural network structure;

[0133] Figure 9 Schematic diagram of the principle of regulating room temperature for the terminal unit.

[0134] In the figure: 1000 central air conditioning billing system, 100 central air conditioning billing device, 200 server, 300 terminal unit / terminal damper, 400 driver, 500 chilled water pipe; 600 reference air conditioning unit;

[0135] 120 sensing detection unit, 130 working condition adjustment unit, 140 user interface unit, 150 control unit;

[0136] 121 temperature detection module, 122 flow detection module, 123 image acquisition module, 124 electricity metering module;

[0137] 131 temperature uniformity module, 132 vertical rotation axis, 133 angled support arm, 134 horizontal rotation axis, 135 telescopic support rod, 136 pitching support, 137 fan cover, 138 temperature uniformity fan, 139 base;

[0138] 151 input module, 152 main processing module, 153 image processing module, 154 working condition processing module, 155 fan processing module, 156 output module, 157 storage module, 158 mapping module;

[0139] 1521 sample extraction unit, 1522 correction coefficient calculation unit, 1523 billing processing unit;

[0140] 1541 uniform temperature treatment unit, 1542 humidity control unit;

[0141] 1581 first neural network, 1582 first connection matrix, 1583 iterative learning unit, 1584 second connection matrix;

[0142] 310 fan, 320 fan coil, 330 return air vent; 340 indoor unit;

[0143] 610 outdoor unit module, 620 indoor unit module. DETAILED DESCRIPTION

[0144] The preferred embodiments of the present invention are described in detail below with reference to the accompanying drawings, but the present invention is not limited to these embodiments and covers any substitution, modification, equivalent method and solution made within the spirit and scope of the present invention.

[0145] In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can also fully understand the present invention without description of these details.

[0146] The present invention is described in more detail in the following paragraphs by way of example with reference to the accompanying drawings. It should be noted that the drawings are simplified and not to exact proportions, and are only used for the purpose of conveniently and clearly illustrating the embodiments of the present invention.

[0147] Example 1:

[0148] Central air conditioning is an air conditioner that achieves indoor air conditioning by supplying refrigerant to multiple cooling terminals in different rooms through air ducts, water pipes, or refrigerant pipes. Figure 3A As shown, water-cooled central air conditioners use water as refrigerant, while all-air central air conditioners are VAV variable air volume air conditioning systems, which control and adjust the temperature of a certain air-conditioned area by changing the air supply volume in the air duct rather than the air supply temperature, thereby adapting to changes in the load of the air-conditioned area. Figure 3B As shown, variable refrigerant flow central air conditioners, also known as VRV or VRF systems, control the refrigerant flow rate and achieve cooling or heating through direct evaporation or condensation of the refrigerant. Compared to the two heat exchange cycles of all-air and water-cooled central air conditioners, VRV or VRF systems require only a single heat exchange, resulting in higher efficiency. However, their single unit power is limited, making them suitable for smaller, centralized cooling / heating applications such as villas and localized floors of office buildings.

[0149] Without loss of generality, this embodiment will first be described using the apportioned billing of a water-cooled central air-conditioning system. In the water-cooled central air-conditioning system, the terminal device is a terminal unit, a terminal fan unit, or a terminal windshield.

[0150] As shown in FIG1 , the central air conditioning billing device 100 of the present invention includes a control unit 150, a sensor detection unit 120, a user interface unit 140, and an operating condition adjustment unit 130 connected to the control unit 150. Specifically, the present invention uses the room where the terminal unit / terminal damper 300 of the water-cooled central air conditioner is located as the heat load, and the reference air conditioning unit 600 is used as a reference for varying cooling capacity under different operating conditions in the room. The sensor detection unit 120 performs parameter detection on the operating conditions of the water-cooled central air conditioner and the reference air conditioning unit 600, as well as the cooling conditions of the room. The user interface unit 140 is used to input parameters and initiate operations, including displays during human-computer interaction, such as outputting and displaying the electricity bills shared by each household.

[0151] The water-cooled central air conditioning system consists of one or more cold and heat source systems and multiple terminal air conditioning systems. The operation process of the central air conditioning system is essentially a process of heat transfer. Figure 3A 、 Figure 4B As shown, the cold / heat source is the host. Taking cooling as an example, the host is cooled by the compressor, and the circulating water is cooled into chilled water after passing through the heat exchanger, and is transported to each terminal air conditioning system, i.e., the fan coil 320 in the figure, through the chilled water pipe 500; after the chilled water is supplied to each user room through the fan coil, the water temperature rises, and after circulating back to the heat exchanger, it is evaporated by the compressor refrigerant again to remove heat and then cooled to chilled water, thereby continuously removing heat from the room; at the same time, the compressor refrigerant is sucked into the compressor and compressed into high-pressure steam and then discharged to the condenser. The outdoor fan or cooling water system discharges the heat of the condenser, that is, secondary heat exchange is carried out on the condenser, and the hot air that takes away the heat emitted by the condenser is discharged to the outdoor environment.

[0152] refer to Figure 4B As shown, fan coil units 320 are widely used in places like hotels, shopping malls, office buildings, hospitals, and other facilities. They function as a heat exchange unit between indoor air and chilled water. Their operating principle is that a fan drives indoor air or a mixed outdoor air stream through fan 310. The air flows through a surface cooler (a curved pipe that flows through chilled water) where it is cooled and then delivered indoors, lowering the indoor temperature to meet user comfort requirements. Heat from people, equipment, and surrounding walls within the room heats the incoming cool air, raising its temperature. After this, the air passes through return air vents 330 and circulates back to fan coil units 320 for renewed heat exchange.

[0153] During the heat transfer process of the central air conditioner, the main unit delivers cooling energy to each terminal unit. Figure 7B As shown, in order to fairly bill the cooling capacity consumed by each room, two issues need to be addressed: How much cooling capacity does each room actually use?

[0154] However, how much difference can be made in the comfort level achieved by different rooms with the same cooling capacity due to factors such as sunlight, building envelope, and adjacent rooms? How can this difference be corrected? Furthermore, different users set different target temperatures. How can different temperatures be billed differently?

[0155] How much cooling capacity does each room consume through the terminal unit? This is the first question that must be answered when paying by energy consumption.

[0156] At present, the calculation of the cooling capacity of the terminal unit is based on monitoring the status of the three-speed switch of the fan, and is obtained by weighted summing the working hours of the high, medium and low wind speed gears. The weight of each gear, that is, the coefficient, can often only be obtained by using the data calibrated by the manufacturer under rated operating conditions.

[0157] This fixed-weight calculation method has obvious limitations. First, due to factors such as installation distance from the main unit, the actual air volume of different fans may differ from the nominal values ​​of each air volume setting. Second, and more critically, the operating conditions of water-cooled central air conditioning systems, including each terminal unit, change dynamically. Using a fixed value to calculate an actual variable is clearly unreasonable.

[0158] In each room that uses cooling, not only will there be a difference between the wind speed and the nominal value, but the total cooling capacity output by the main unit will also change. Moreover, the distribution of this total cooling capacity by each terminal unit is not a simple linear proportional relationship but is mutually restricted, that is, there is a nonlinear coupling relationship between each wind speed.

[0159] To this end, the present invention regards the water-cooled central air-conditioning system including each terminal unit as a whole, and regards the distribution of cooling capacity among each terminal unit as a black box. Based on nonlinear modeling theory, the mapping relationship between the key working conditions of the system and the refrigeration equivalent of the terminal unit is modeled.

[0160] To identify the model, a dataset must be collected. This requires obtaining the cooling capacity equivalent under different operating conditions. How is this obtained? Currently, the enthalpy difference method of the heat transfer medium is often used.

[0161] This method was first used in central air conditioning billing systems to construct heat meters to measure heating energy. A heat meter consists of a hot water flow meter, a pair of temperature sensors, and an integrator. Its operating principle is that hot water from a heat source flows into a heat exchange system at a relatively high temperature and flows out at a lower temperature. During this process, heat is exchanged and delivered to the user. The amount of heat received by a user over a given period of time can be calculated using the following equation:

[0162] E=∫K(Ts-Tr)dV,

[0163] Where E is the heat output of the heat exchange system, K is the correction coefficient for the specific gravity and specific heat of hot water, Ts and Tr are the supply and return water temperatures, respectively, and V is the hot water flow rate flowing through the heating system over a period of time.

[0164] The main errors in the enthalpy difference method come from the measurement of the working fluid flow rate and the determination of the enthalpy value, especially for small flow rates, where the measurement error is relatively large. Similarly, there are methods for calculating cooling capacity by detecting the air-side supply and return air. Compared to water-side metering, air-side metering reduces the accuracy requirements for temperature measurement equipment and instruments because its supply air temperature difference is much larger than the chilled water supply and return temperature difference. However, both air-side and water-side metering currently focus on setting measurement points on the working fluid supply and return lines at the end. Because the end flow rate is small and the fluctuations in temperature and flow parameters are much greater than those at the host end, there is a contradiction between sensor accuracy and instrument equipment cost.

[0165] Based on the above research, to improve model generalization and prediction accuracy, the present invention uses four scalar quantities—the chilled water supply flow rate of a water-cooled central air conditioner main unit, the supply and return water temperature difference, the current room temperature and humidity—as inputs, along with a vector consisting of the power-on status values ​​of all terminal units. The output is the equivalent cooling capacity per unit time (i.e., the cooling capacity equivalent) of the current fan speed in the room. A first neural network is established in the control unit as a terminal unit metering mapping model. The two key influencing factors, flow rate and temperature difference, require only a single measurement point. More importantly, the flow rate detected is on the main pipeline, which is much larger than the terminal flow rate, effectively improving measurement accuracy.

[0166] The present invention uses the room where the water-cooled central air-conditioning terminal unit is located as the heat load and uses the reference air conditioning unit as the reference object for the changing cooling capacity of the room under different working conditions to obtain the cooling capacity equivalent value in the data sample required for system identification.

[0167] Specifically, if Figure 7A As shown, the reference air conditioning unit, i.e., the reference machine, uses an integrated movable air conditioner. First, its sensible cooling capacity under different working conditions is obtained according to standard tests and the parameters are recorded as a working characteristic table or curve. A second mapping from the reference machine working condition to the cooling capacity is established, providing a basis for calculating the sample cooling capacity in the room where it works at the end of the windshield.

[0168] Then, under the conditions of various input combinations, the training samples of the first neural network are obtained offline. According to the characteristics of the cooling system of water-cooled central air conditioners that transmits cooling capacity from the main unit to the terminal unit, in order to solve the impact of system time lag and large inertia, combined with Figure 4A 、 Figure 4B As shown, the present invention configures the control unit to collect sample data of the terminal unit metering mapping model in the following manner:

[0169] The control unit drives the fan corresponding to the water-cooled central air-conditioning terminal unit through the driver;

[0170] The room where the water-cooled central air-conditioning terminal unit is located is used as the heat load, and the target temperature is set according to the initial temperature of the room. The working condition adjustment unit is used to make the temperature difference of multiple temperature detection modules located at different positions in the room in the sensor detection unit smaller than the temperature difference threshold. The control driver uses the central air-conditioning terminal fan to adjust the room temperature to the target temperature and obtain the current humidity as the target humidity.

[0171] After the room is kept at the target temperature for a period of time, the driver is turned off and the timing is started. The reference air conditioning unit is controlled to maintain the room temperature at the target temperature from t = 0 to t = T1. At the same time, the working condition adjustment unit is controlled to keep the room humidity at the target humidity. The cooling power q(t) is calculated based on the working characteristics and working conditions of the reference air conditioning unit and its cooling capacity in the first period is accumulated.

[0172] Turn off the reference air conditioning unit and start timing again. After setting the fan's wind speed opening state value F, control the driver to work in PWM mode and maintain the room temperature at the target temperature from t=0 to t=T2 in the second period. Calculate its equivalent time Where Δ(t) is the PWM value,

[0173] The driver is turned off again and the timing is restarted. The reference air conditioning unit is controlled to maintain the room temperature at the target temperature from t=0 to t=T1. At the same time, the working condition adjustment unit is controlled to keep the room humidity at the target humidity. The cooling capacity of the third period is calculated again.

[0174] Calculate the cooling capacity per unit time of the wind speed under the current working conditions:

[0175] Preferably, the duration of the third period can be different from that of the first period, for example, the difference between the two is within 20%. Preferably, the opening state value F is low speed, medium speed and high speed.

[0176] During the continuous sample collection process, the second period of data collection can be performed by simply changing the operating conditions of the water-cooled central air conditioning system. The first and third periods can be recollected every few samples. The first sample collection after changing the target temperature should be performed in three consecutive periods.

[0177] Combine Figure 7AAs shown, the present invention establishes a first neural network in the control unit, which serves as the first mapping from the operating state of the central air conditioning system's terminal unit to cooling capacity / cooling equivalent. To avoid errors caused by low terminal flow rates, the parameters of the measurement point at the main pipeline's high flow rate are used as the mapping input. In the working room, the terminal unit to be measured is measured based on equivalent cooling, through alternating cooling between the terminal unit and a reference air conditioning unit. Specifically, the cooling capacity of the reference air conditioning unit under the same operating conditions, obtained through the second mapping, is used as the cooling equivalent of the terminal unit. During this process, operating condition sensing and control are used to ensure that the heat load conditions of the two cooling sources, namely, the heat flux density entering the room under cooling, are the same, ensuring the reliability of the equivalent measurement.

[0178] Without loss of generality, when a water-cooled central air conditioning terminal unit is operating stably online, once the host configuration is finalized, the room's humidity will remain largely stable, primarily due to seasonal climate constraints. Therefore, the current room humidity during central air conditioning cooling is used as the target humidity, and the room humidity is maintained at this target when the reference air conditioning unit is providing cooling.

[0179] For room temperature, the target temperature should be set based on the room's initial temperature under natural conditions without cooling. Preferably, the temperature difference between the target temperature and the initial temperature should be ≥ 5°C, and the load factor of the terminal unit during the sample collection period should be greater than the set value, such as 0.5 to 1 times the rated power.

[0180] During cooling, the ratio of the cold air inlet to the room surface area will cause a temperature gradient in the room, which may cause a deviation in the heat load when the two cooling sources are working. To reduce the heat load deviation, refer to Figure 5A 、 Figure 5B , and combined with Figure 6 As shown, the present invention sets multiple temperature detection modules 121 at different positions in the room, and uses the temperature uniformity module 131 in the working condition adjustment unit to make the temperature difference of these temperature detection modules less than the temperature difference threshold.

[0181] Specifically, if Figure 6 As shown, a temperature uniformity module 131 is provided in the working condition adjustment unit, which includes a base 139, a vertical rotation axis 132, an angled support arm 133, a horizontal rotation axis 134, and a pitchable bracket 136 having two sections of support arms movably connected by bolts, and a retractable support rod 135 is connected between the outer ends of the two sections of the support arms, which is at an acute angle to the axis of the horizontal rotation axis 134. A temperature uniformity fan 138 is carried at the end of the pitchable bracket 136. Preferably, a fan cover 137 is provided on the back of the temperature uniformity fan 138. An image acquisition module 123 is provided in the sensing detection unit, and the image acquisition module 123 can be set at the bottom of the angled support arm 133, so that a global image of the room can be obtained by rotating the vertical rotation axis 132.

[0182] See also Figure 2 As shown, preferably, the control unit 150 includes an input module 151, a main processing module 152, an image processing module 153, a working condition processing module 154, a fan processing module 155, a mapping module 158 and an output module 157, wherein the working condition processing module 154 further includes a uniform temperature planning unit 1541 and a humidity adjustment unit 1542. The control unit is further configured to:

[0183] The main processing module responds to events and schedules other modules;

[0184] Based on the room image captured by the image acquisition module, the image processing module 153 analyzes the room's orientation features and extracts two mutually perpendicular diagonal lines. These orientation features include the distribution and length of the room's structural ridges, as well as the orientation and distance of the cooling outlet, return air outlet, and temperature uniformity module 131 relative to the room's corners.

[0185] Combine Figure 5A 、 Figure 5B As shown, the uniform temperature planning unit 1541 in the working condition processing module 154 plans the operating trajectory for the uniform temperature module 131 based on the above-mentioned orientation characteristics, so that the axis of the uniform temperature fan 138, that is, the end it points to, moves in a spatial spiral line to transmit the cold air blown out by the central air-conditioning terminal unit and / or the reference air conditioning unit to various areas of the room until the temperature difference of multiple temperature detection modules in the room is less than the temperature difference threshold.

[0186] The trajectory planning can be based on the obtained room diagonal line, with the line from the cold air outlet to the farthest point in the room it can reach or the position directly opposite it as one of the main diagonals, and another straight line perpendicular to it as a secondary diagonal; then, a spiral trajectory can be planned with the main diagonal line as the axis. Figure 5A In the figure, the black dot is the air outlet at the corner. With the diagonal line where the dot is located as the center, a curve that moves in a spiral around the inner wall of the cone is planned as the target trajectory, where the main diagonal line is the center line of the cone. Figure 5B In the example, the air outlet is located in the middle of one wall. Using this wall as the cylindrical floor, a spiral curve is planned around the inner wall of the cylinder as the target trajectory, with the main diagonal line being the centerline of the cylinder. The planned target trajectory should avoid the return air outlet to minimize cooling loss.

[0187] Preferably, typical indoor orientation features can be summarized and classified, and the terminal trajectory curve of each orientation category can be planned based on geometric equations, and the output angles of each joint in the uniform temperature module, including the vertical rotation axis, horizontal rotation axis and retractable support rod, can be analyzed based on inverse kinematics.

[0188] Preferably, the joint angles corresponding to the trajectory can be stored as a data sequence through on-site teaching, and the joints can be controlled online in sequence according to this sequence.

[0189] By moving along the planned trajectory, each area of ​​the room can be cooled down as quickly as possible, reducing the temperature gradient between areas. The uniform temperature planning unit controls the uniform temperature module based on the planned trajectory. In each time period of sample collection, first, it operates at a uniform speed to generally reduce the temperature. In order to further reduce the regional temperature difference, as a preference, then, according to the temperature characteristics of multiple temperature detection modules in the room, the linear speed of the uniform temperature fan moving along the trajectory is changed, so that the linear speed is inversely proportional to the temperature difference between the temperature at its corresponding trajectory point and the target temperature. The temperature of each trajectory point can be obtained by interpolation calculation based on the temperature values ​​of multiple temperature measurement points. Through this speed planning, the uniformity of each spatial point of the room temperature can be improved, thereby ensuring the consistency of working conditions and improving the generalization ability of the measurement model.

[0190] The temperature-uniform module operates periodically. When the temperature difference between the highest and lowest temperatures detected by the multiple temperature detection modules falls below a temperature difference threshold, it stops operating and begins collecting data samples. If the temperature difference exceeds the threshold, it resumes operation, dynamically balancing the overall room temperature at the target temperature. Preferably, the temperature difference threshold is between 0.1°C and 0.3°C.

[0191] During the second period of the sample collection, the fan processing module in the control unit adjusts the PWM wave duty cycle of the driver according to the average of the multiple temperatures at different locations in the room, that is, the overall room temperature. Figure 9 As shown in the figure, according to the error value e(t) between the target temperature and the current overall room temperature, the fan processing module in the host unit calculates the PWM value of the fan driver based on the PID control law, and changes the fan speed by changing the driver power pulse width, so that the error value e(t) dynamically approaches 0.

[0192] The working condition processing module is also provided with a humidity adjustment part, which controls the operation of the humidity adjustment module in the working condition adjustment unit based on the monitoring of the humidity measuring points in the room, so that the humidity in the room is maintained at the target humidity.

[0193] Combine Figure 3A 、 Figure 5A 、 Figure 5B As shown, the sensing detection unit is provided with a humidity detection module in the middle of the return air duct of the room; a flow detection module 122 and a water temperature detection module 121 are provided at the inlet of the chilled water supply main pipe of the central air-conditioning host, and a water temperature detection module is provided at the outlet end of the return water main pipe where the host is connected; multiple temperature detection modules are provided at different positions in the room, and they can be set at the same height and located on two vertical diagonals.

[0194] Preferably, the number of the multiple temperature detection modules is 3 to 6, and the setting height is about 2 meters; the temperature values ​​of the multiple temperature detection modules can be averaged to serve as the current temperature of the room.

[0195] During a sample collection period, the central air conditioning unit's operating power can be adjusted to maintain a constant chilled water supply flow rate and supply / return water temperature difference. Preferably, these two parameters can be averaged during the sample collection period based on the proportional relationship between cooling capacity, temperature difference, and flow rate.

[0196] Preferably, the multiple temperature detection modules provided to control the consistency of the heat loads of the two cooling sources are only used for sample collection. Therefore, one of the temperature detection modules, such as the module near the return air temperature measurement point, can be selected as the current temperature of the room in the first neural network input during online application, thereby simplifying the system structure and facilitating actual operation.

[0197] For each terminal unit of the water-cooled central air conditioner, the wind speed opening state value can be taken as the three normalized fan power values ​​corresponding to the low, medium and high speed levels of the fan, for example, the highest power value is taken as 1, and the other two power levels are converted proportionally.

[0198] The cooling system of a water-cooled central air conditioner is a nonlinear hysteresis system. Therefore, changes in working parameters require some time to feed back their impact. Therefore, when collecting training samples, the present invention sets sampling conditions, allowing the system to enter a steady-state working state before sampling. When the reference air conditioning unit and the terminal unit are cooling, the working conditions in the room are maintained for a period of time so that the sampling eliminates the randomness of short-term sampling. At the same time, by sampling the reference air conditioning unit once before and after the terminal unit is cooling, the influence of slow fluctuations in working conditions on the sampled data is eliminated, thereby improving the prediction accuracy of the network model.

[0199] The first neural network established by training the collected sample set is used to predict the cooling capacity per unit time of the current wind speed in the field environment with the trained first neural network, and the predicted value is output through the output module. This value can be used as the basis for billing each terminal for water-cooled central air conditioning.

[0200] like Figure 7A As shown in Figure 1, the cooling capacity equivalent provided by the terminal unit under the same operating conditions, using the workroom as the heat load, is obtained by using the reference air conditioning unit through a second mapping. To this end, the operating characteristics of the portable reference air conditioning unit must be obtained through high-precision calibration in advance.

[0201] See also Figure 4AAs shown, a reference air conditioning unit 600 includes an outdoor unit module 610 and an indoor unit module 620. This reference air conditioning unit can be equipped with dry-bulb and wet-bulb temperature detection modules and air flow rate detection modules. A test device using the room-type air enthalpy method is established, based on room air conditioner standards. The sensible cooling capacity under different operating conditions is measured and recorded as an operating characteristic table or curve, which serves as the operating characteristics of the reference air conditioning unit. Then, when collecting samples, the cooling capacity of the reference air conditioning unit under the current operating conditions is calculated by querying and interpolating these operating characteristics based on the current inlet and outlet air dry-bulb and wet-bulb temperatures and air flow rate.

[0202] In the air enthalpy method, the calculation formula for sensible cooling capacity is:

[0203] φ sc =q m c pa ·(t a1 -t a2 ) / V n (1+W n ),

[0204] Among them, φ sc is the sensible cooling capacity (W), q m is the air supply volume at the measuring point (m 3 / s), V n is the specific volume of moist air at the measuring point (m 3 / kg), W n is the air humidity at the measuring point, t a1 and t a2 are the return air and supply air temperatures (°C), the constant pressure specific heat capacity c pa =1005+1846W n (J / (kg·K)).

[0205] In the reference air conditioning unit, dry-bulb and wet-bulb temperatures are measured by sensors placed in the insulation section of the supply and return air vents, respectively. The dry-bulb and wet-bulb sensors are used to detect the supply and return air temperatures and humidity. These parameters can also be acquired using temperature and relative humidity sensors. During training sample collection, the reference air conditioning unit, under the control of the control unit, adjusts its operating frequency to maintain the target room temperature.

[0206] Preferably, the operating characteristic data of the reference air conditioning unit is recorded in a table form, and the sensible cooling capacity under the current working condition is calculated based on the operating characteristic table lookup and multi-dimensional interpolation.

[0207] Preferably, the rated cooling power of the reference air conditioning unit is 0.85 to 1.15 times the cooling capacity of the maximum windshield of the terminal fan.

[0208] Combine Figure 8A 、 Figure 8B As shown, the control unit establishes a first neural network 1581 as a terminal unit metering mapping model in the mapping module 158. The input layer of the first neural network receives input from the main processing module 152, and the output of the output layer is transmitted to the iterative learning unit 1583 and the main processing module 152 through the first connection matrix 1582 and the second connection matrix 1584 respectively. When the first neural network is trained offline, the iterative learning unit 1583 adjusts the connection weights of the first neural network 1581 according to the actual value of the cooling capacity per unit time of the windshield and the network output value input by the main processing module 152 and the first neural network 1581 respectively through the first connection matrix 1582 until the learning is completed. When metering online, the first connection matrix 1582 is disconnected, and the first neural network 1581 predicts the cooling capacity per unit time of the windshield and outputs it to the main processing module 152 through the second connection matrix 1584. After processing and analysis by the main processing module 152, the output is output through the output module 156. Figure 1A 、 Figure 2 As shown, the output module can transmit the metering results to the user interface unit 140 for display, or store them in the server 200, where the server 200 can communicate with one or more systems of the present invention via a cloud platform. In the main processing module 152, the sample extraction unit 1521 controls the collection and screening of training samples, the correction coefficient calculation unit 1522 calculates the various coefficients for apportioned billing, and the billing processing unit 1523 performs distributed processing to apportion central air conditioning costs based on the operating conditions of each terminal unit.

[0209] Preferably, the first neural network adopts a BP first neural network, and its model is:

[0210] The output of the jth node in the hidden layer is

[0211] The output of the output layer is

[0212] Among them, x1~x4 are the four scalars of the central air-conditioning host chilled water supply flow, supply and return water temperature difference, the current temperature and humidity of the room, x5~xn are the open state values ​​of all terminal units; the f() function is taken as the sigmoid function, w ij and v j are the connection weights from the input layer to the hidden layer and from the hidden layer to the output layer, θ j and θ are the hidden layer and output layer thresholds respectively, n and k are the number of nodes in the input layer and hidden layer respectively, and the gradient descent method is used for network training.

[0213] As a preference, other redundant factors may be added to the network input, such as the air supply temperature of the terminal unit.

[0214] Because they share a common chilled water main pipeline, and the water supply pressure in the pipeline decreases gradually as the chilled water is distributed, the actual cooling capacity of a water-cooled central air conditioner fan coil terminal unit depends not only on the model and windshield position, but also on its distance from the central air conditioner. Therefore, for terminal units of the same model, they can be further subdivided into smaller categories based on the horizontal and vertical distances of the terminal windshield from the inlet of the central air conditioner's chilled water supply main pipeline. A first neural network is established for each subcategory, and training samples are collected separately, resulting in more accurate prediction and measurement of cooling capacity equivalent.

[0215] Preferably, for each category, a terminal unit is selected for sample acquisition and training. For the first neural network of each category's terminal unit, when collecting training samples, a room with slow and minimal ambient temperature fluctuations is selected as the heat load. This allows for continuous sample collection and shortens the sampling time for the overall sample set. To this end, rooms within buildings can be used as the collection environment. For rooms located in corners of buildings, sample collection is preferably performed at night or during daytime periods without direct sunlight.

[0216] Cooling capacity measurement is the basis for charging by cooling capacity in central air conditioning systems. However, in addition to measurement, many other factors need to be considered in billing. Figure 7B As shown, the cooling capacity required per unit area for cooling varies significantly between rooms located in different building orientations. For example, the first-floor lobby, with its less enclosing structure, delivers more cooling air to the surroundings. Rooms at the edges and top receive significantly greater solar radiation than rooms in the center, requiring more cooling capacity. Clearly, simply billing based on actual cooling capacity consumption would be unfair to rooms where environmental factors contribute to higher cooling capacity.

[0217] Therefore, it's necessary to analyze the cooling characteristics of rooms at different locations within the building and, based on this, calculate cooling compensation for rooms in these locations. This requires research on how to describe these cooling characteristics. For example, can a model be developed? And how? This model should capture the primary, quantifiable factors that cause variations in cooling consumption at different locations. Furthermore, these factors should be convertible to compensate for different room usage. Furthermore, even if a model can be developed, how should corrections be made based on this model? After extensive analysis and research, we determined that this correction should account for environmental factors and exclude the current setpoint or actual temperature of each room. Otherwise, the billing system will remain the same regardless of usage.

[0218] For this, see Figure 7BAs shown, the present invention uses two scalar variables during cooling: the current room temperature and the outdoor air temperature; and a vector consisting of the room's indoor temperature values ​​in six directions (front, back, left, right, top, and bottom) as inputs. The control unit uses the equivalent cooling capacity per unit time of the room's air damper as output. A second neural network is established for each room within the control unit, serving as a cooling model for each room. This model then predicts the equivalent cooling capacity per unit time for each room under near-operating conditions, and a correction coefficient is calculated based on this prediction. Finally, this correction coefficient is used to correct the actual cooling capacity predicted by the first neural network and then contribute to the deferred costs of the entire water-cooled central air conditioner.

[0219] Specifically, refer to Figure 8A 、 Figure 8B As well as the modeling process of the first neural network, the second neural network can also use a BP network. Among its nine inputs, x1-x2 are the current room temperature, outdoor temperature, and solar radiation intensity, three scalars; x3-x8 are the room temperatures in the six directions of the room: front, back, left, right, top, and bottom; and the output y(t) is the room's cooling capacity per unit time. To enable the use of the cooling supply equivalent of the first neural network to predict and calculate the cooling capacity equivalent, i.e., the required cooling capacity equivalent, the present invention achieves a balance between cooling supply and demand by maintaining the dynamic stability of the room temperature during sample collection. Therefore, the output of the second neural network is the cooling capacity per unit time equivalent of the room's airflow. When the terminal unit is providing cooling, room humidity is primarily affected by seasonal climate; however, the second neural network can also preferably include an input of indoor humidity. When an adjacent room is vacant, the temperature in that direction, such as the outdoor temperature, is used as the room's indoor temperature in that direction. Preferably, when the water-cooled central air conditioning system as a whole enters a stable operating state, the six-direction room temperature values ​​in the second neural network can also be replaced with the fan power-on status values ​​of the terminal units in the six-direction rooms. Preferably, a solar radiation intensity parameter is also added to the input of the second neural network.

[0220] When the operating conditions are approximately stable, data samples of the second neural network under different input conditions are collected, where the output is predicted by the first neural network corresponding to the terminal unit. The trained second neural network is trained based on the data samples and is used to predict the equivalent cooling consumption per unit time of each room under the current operating conditions.

[0221] To automatically collect data samples for the second neural network, the present invention incorporates a sample extraction module within the control unit's main processing module. This module periodically and continuously collects the heat load and cooling capacity parameters of the rooms being cooled by the water-cooled central air conditioner. Based on the inputs to the second neural network, the module searches for periods in which the amplitude of these variables changes within a preset fluctuation threshold, and stores the data from these filtered periods in the second neural network's data sample set. This automatic sample extraction allows for sample acquisition during the water-cooled central air conditioner's operation, eliminating the need for lengthy dedicated system startup and commissioning, significantly reducing data acquisition costs.

[0222] Preferably, the preset fluctuation threshold is ±5%, and the value of each input sample parameter is the arithmetic mean or median value within the period.

[0223] Preferably, the preset fluctuation threshold may further include two sets of threshold ranges, a first fluctuation threshold and a second fluctuation threshold. When the change in the second neural network input within a period exceeds the first fluctuation threshold but is less than the second fluctuation threshold, the sample value of the input within this period is taken as its time average value within this period. w For example, the average outdoor temperature in period T, i.e. its time average value, is

[0224] Preferably, the first fluctuation threshold and the second fluctuation threshold are ±2% and ±5% respectively.

[0225] When building the second neural network, a separate model can be created for each room. Preferably, rooms with the same orientation characteristics, such as the same type of room in the middle, can be represented by the same network. By sharing the model, the sample size can be further reduced, saving computation and modeling time.

[0226] After completing the above two modeling steps offline, the cost of water-cooled central air conditioners is allocated by time period during online application. Unlike existing methods, this method corrects the cooling capacity of rooms in different locations not by using fixed, statistically analyzed empirical values, but by performing real-time conversion based on the actual operating conditions of each room.

[0227] Specifically, first calculate the correction coefficient based on the cooling consumption model and the current room working conditions. Where i is the current room number, room number i = any integer from 1 to N, N is the total number of rooms, p i 、p i0 For The mapping output of the second neural network when it is the input vector, is the current working condition of room i, The current room temperature and outdoor temperature The same, and the indoor temperature values ​​of the room in the six directions of the current room are taken as the current room temperature;

[0228] Then calculate the cost of room i in time period d:

[0229] in, PF is the cooling capacity per unit time equivalent of the terminal unit predicted by the first neural network in the current room i (t) The accumulated cooling capacity during this period, Q jd is the cooling capacity of room j during this period, k j3 is the corresponding coefficient of room j, C d The total cost to be shared for central air conditioning during this period.

[0230] The correction factor inevitably involves the cooling characteristics and cooling equivalent of other rooms. At the same time, other rooms may have different room temperatures due to differences in power-on duration, environment, and set temperature. So, when calculating the correction factor for a particular room, should the cooling equivalent be determined based on the individual operating conditions?

[0231] After in-depth research, this paper uses the generalization characteristics of the room cooling model to uniformly predict the cooling consumption of the same room under working conditions without additional heat load in adjacent rooms. The predicted value is actually the cooling demand of the basic heat load inside the room, and the ratio of the cooling demand corresponding to the basic heat load inside the room to the actual cooling demand is used as the correction coefficient k. i3 In the central air conditioning cost sharing calculation formula, the actual cooling capacity of the room is multiplied by the correction factor k i3 , thus realizing the shared billing of cooling requirements corresponding to the basic heat load of each room in the billing, reflecting the fairness of billing. It can be understood that according to the cost sharing calculation formula, the correction coefficient k corresponding to the room near the edge of the building, the top and bottom floors, etc., which has a large external heat load introduced by the enclosure structure, is i3 The coefficient will be smaller than that of the central room of the building, so that billing compensation can be obtained through this coefficient.

[0232] At the same time, if the set temperature of the same room is lower at different times, the actual cooling capacity will inevitably be higher, and thus more costs will be incurred. Therefore, this device also embodies billing based on comfort, which helps guide reasonable consumption of cooling and achieve energy saving effects.

[0233] As a preference, in the calculation of the correction coefficient for the dth time period, the input vector of the second neural network is The parameters in the period are taken as the average value in the period; and the cooling capacity Q id It can be obtained by accumulating short periods in a discrete periodic system. The outdoor temperature can be taken as the current room temperature. The total cost to be shared can be calculated by time-sharing based on the system's electricity and water consumption.

[0234] When a room has multiple terminal units, the cooling consumption of the current room during this period Among them F i It is the collection of all wind screens in the current room.

[0235] It's understandable that all-air central air conditioners use air instead of cooling water as the refrigerant, compared to water-cooled central air conditioners. Therefore, the billing system for water-cooled central air conditioners in this embodiment is also applicable to all-air central air conditioners. Due to differences in cooling process details, the first neural network established in the billing control unit has been modified to take as input a vector consisting of four scalar quantities: the air flow rate at the main air outlet of the all-air central air conditioner, the supply and return air temperature difference, the current room temperature and humidity, and the opening status of all terminal dampers.

[0236] Example 2:

[0237] During the process of collecting the first neural network training samples, if the target temperature is initially set too high or too low, or the terminal unit power does not match the heat load of the room where it is located, the terminal fan operating condition will be limited to low power or high power state when collecting samples.

[0238] Therefore, in order to make the samples cover different load rate conditions of the terminal fan from low to high, in this embodiment, when the control unit controls the driver to work in PWM mode, during a sample collection period, the terminal unit state is switched to make it work in different gears, and the equivalent time is calculated by multiplying the normalized speed of the fan motor at different wind speeds by the integral of the power-on duty cycle Δ(t) within the period. Where k(t) is the normalized speed. If the maximum speed is 1, the value for other speeds is the ratio of the speed value to the maximum speed.

[0239] For the same reason, this embodiment can also adopt the following method to obtain training samples. The reference air conditioning unit uses a hot and cold air conditioner; if the ratio of the equivalent time dT to the second time period T2 is less than the duty cycle threshold Δs, when collecting the sample, within the second time period, the reference air conditioning unit is also controlled to work in the heating mode from τ = 0 to τ = T3, and the thermal equivalent of the heating is recorded. Accordingly, the cooling capacity per unit time of the air gear under the current working conditions is calculated as follows:

[0240]

[0241] Preferably, an electric heating module can be provided in the reference air conditioning unit, and the electric heating module can be controlled to generate heat within the time range from τ=0 to τ=T3, and the thermal equivalent of heating Q3=pr·T3 is recorded, where pr is the heating power of the electric heating module (kW or kJ / s), and PF is calculated similarly.

[0242] Preferably, within the time ranges of T1 and T2, the heating module can be turned on with known power and heat calculation can be performed, thereby expanding the operating condition coverage of the reference air conditioning unit and the water-cooled central air-conditioning terminal unit.

[0243] The reference air conditioning unit's operating characteristics are a mapping from its operating conditions to sensible cooling capacity. In this embodiment, this mapping can also be represented by a third neural network, whose inputs can be the dry-bulb and wet-bulb temperatures of the inlet and outlet air and the air volume; preferably, the electrical power, the outdoor condenser temperature, the indoor evaporator temperature, and humidity; or preferably, the compressor operating frequency, the air supply motor power, and the supply and return air temperatures and humidity.

[0244] Taking into account factors such as the cost of central air conditioning equipment and installation, as well as the presence of shared rooms in buildings, some existing charges are based on a combination of fixed fees and operating expenses. Air conditioning system costs primarily include the following: a. Electricity costs for operating the air conditioning system (including electricity costs for equipment such as chillers, cooling towers, and water pumps); b. Water consumption for replenishment of the air conditioning system; c. Labor and management costs for operating the air conditioning system; d. Depreciation of the air conditioning system equipment; e. Maintenance and repair costs for the air conditioning system; f. Other additional fees and property management fees. Of these costs, the first three represent central air conditioning system operating costs, while the last three are essentially fixed values ​​throughout the system's operation, known as base fees.

[0245] Different from Example 1, this embodiment uses a combined charging method to divide the total deferred cost of the water-cooled central air conditioner into two parts. In addition to the actual cooling capacity allocation, it also includes an area allocation. The cost of room i in time period d is:

[0246]

[0247] Among them, C d1 and C d0 They are the operating costs and basic costs of central air conditioning respectively.

[0248] Example 3:

[0249] This embodiment provides another method for calculating the apportioned billing, and uses a variable refrigerant flow multi-split air conditioner as an example of a central air conditioner.

[0250] Variable refrigerant flow central air conditioning, also known as multi-split central air conditioning system, consists of one outdoor unit / unit connected to several direct evaporation indoor units of different or same type and capacity to form a single cooling / heating cycle air conditioning system, also referred to as VRV or VRF.

[0251] See also Figure 3B As shown, the original intention of VRF is direct expansion. There are no thick air ducts or water pipes from the main unit to the indoor unit. Instead, thin copper tubes are used to transmit the low-temperature liquid refrigerant compressed and expanded by the outdoor unit through long-distance transmission pipelines to the indoor unit as the terminal unit. In the indoor unit, the refrigerant enters the evaporator through an electronic expansion valve and quickly turns into gas, taking away the heat at the same time.

[0252] In a VRF system, the refrigerant flow rate is variable, depending on the indoor load. When the indoor load increases, a larger amount of refrigerant is delivered to the indoor units to provide more cooling / heating capacity, and vice versa. The main unit's compressor regulates the refrigerant flow rate required for the entire system, while electronic expansion valves control the refrigerant flow rate to individual indoor units. In the indoor units, fans also regulate the indoor air volume.

[0253] When different from Example 1, see Figure 1B As shown, in a VRF system, the diameter of the refrigerant transmission pipe is much smaller than that of water pipes, air ducts, etc., and the flow rate is even smaller. Therefore, an electricity metering module 124 is connected to the power supply circuit of each indoor unit 340 as a terminal unit.

[0254] Accordingly, when modeling the cooling equivalent of the terminal unit, the first neural network uses the four scalars of the central air-conditioning host power, the indoor unit power, the current temperature and humidity of the room, and the vector composed of the fan opening status values ​​of all terminal units as input, and uses the cooling equivalent per unit time of the terminal unit in the room, that is, the cooling equivalent, as output.

[0255] After the first and second neural networks complete the offline modeling of the terminal unit cooling and room cooling consumption, when applied online, this embodiment adopts another allocation method to bill the water-cooled central air conditioner by time period.

[0256] Specifically, first calculate the conversion coefficient based on the current room working conditions Where i is the current room number, s i 、s j are the areas of the i-th and j-th rooms respectively, the room numbers i, j = any integer from 1 to N, N is the total number of rooms, p i 、p j Room i and j are As input vector When they each correspond to the mapping output of the second neural network, is the current working condition of room i,

[0257] And calculate the comfort factor Where p ic For room i As input vector When it corresponds to the mapping output of the second neural network, the working condition and The only difference is that the current room temperature is set to a preset comfort temperature such as 25 degrees Celsius;

[0258] Then calculate the cost of room i in time period d:

[0259] Among them, k j1 、k j2 is the corresponding coefficient of room j, C d The total cost to be shared for central air conditioning during this period.

[0260] When calculating the conversion factor k i1 When , the max() function is used to find the room with the highest cooling consumption per unit area. Since the input quantity when mapping the cooling consumption is the same, that is, the working conditions are the same, the denominator corresponds to the room with the highest temperature and cooling consumption per unit area under the premise of achieving the same comfort level under the same external heat load; that is, the denominator corresponds to the room with the highest internal heat load. Therefore, the conversion coefficient k i1 The meaning of is the ratio of the internal heat load per unit area of ​​the current room i to the room with the largest internal heat load.

[0261] Since more cooling capacity is required to achieve a lower indoor temperature, this embodiment also introduces a comfort factor, which is the proportional coefficient k of the amount of cooling capacity required to achieve the current indoor temperature relative to a preset comfort temperature when other working conditions are the same. i2 For example, the comfort temperature may be 25 degrees Celsius during cooling and 18 degrees Celsius during heating.

[0262] This embodiment is based on the conversion coefficient k i1 The current working conditions of each room are converted to the room with the largest internal load, and the influence of heat load caused by different directions or orientations is cleverly avoided through proportional calculation; based on the generalization of the cooling model, the comfort coefficient k i2The model uses factors such as air temperature and the room temperatures of adjacent rooms in six directions as inputs, reflecting the differences in sunlight exposure in rooms with different orientations and the impact of adjacent rooms on cooling consumption. By normalizing the cooling equivalent per unit area of ​​each room under the same operating conditions, and proportionally correcting cooling consumption for different target room temperatures within the same room, the model compensates for differences in orientation, building envelope, and actual temperature.

[0263] Example 4:

[0264] Combine Figure 1A 、 Figure 4A 、 Figure 4B and Figure 7A 、 Figure 7B As shown, this embodiment provides a central air conditioning billing system 1000, which includes:

[0265] A user interface unit 140 for inputting parameters, initiating operations and human-computer interaction;

[0266] A driver 400 for driving the fan corresponding to the central air-conditioning terminal unit;

[0267] A reference air conditioning unit 600 whose operating characteristics have been pre-acquired and used as a reference for cooling capacity;

[0268] A sensing detection unit 120 for detecting the working conditions and environment of the central air conditioning unit and the reference air conditioning unit;

[0269] A working condition adjustment unit 130 for adjusting the working conditions of the central air conditioning terminal unit and the reference air conditioning unit;

[0270] A control unit 150 connected to the driver 400, the reference air conditioning unit 600, the sensing unit 120, the user interface unit 140, and the operating condition adjustment unit 130;

[0271] The control unit 150 is configured as follows:

[0272] First, the cooling equivalent of the terminal unit is measured and modeled.

[0273] The first neural network is established in the control unit, taking the room where the terminal unit is located as the heat load, the working conditions of the central air-conditioning system as the input, and the equivalent cooling capacity per unit time of the terminal unit in this room as the output.

[0274] Using the cooling capacity calculated by the reference air conditioning unit in the system under the same heat load conditions as the cooling capacity equivalent of the terminal unit, collecting first data samples under different operating conditions and training the first neural network;

[0275] Secondly, the rooms cooled by central air conditioning are classified by location type, and a cooling consumption model is established for each type of room.

[0276] The current room temperature and outdoor temperature during cooling are used as two scalars, as well as a vector consisting of the room temperature values ​​in the six directions of the current room (front, back, left, right, up, down) as inputs, and the equivalent cooling consumption per unit time of the room as output. A second neural network is established for each room in the control unit.

[0277] Adaptively control the terminal unit in the current room to maintain the room temperature unchanged in stages. When the working conditions are approximately stable, collect second data samples of the second neural network under different input conditions. The output of the samples is predicted by the first neural network, and training is performed based on the collected data samples;

[0278] Based on the offline cooling and consumption model, the cost of central air conditioning is allocated by time period when applied online.

[0279] First, calculate the correction coefficient based on the cooling consumption model and the current room working conditions. Where i is the current room number, room number i = any integer from 1 to N, N is the total number of rooms, p i 、p i0 For The mapping output of the second neural network when it is the input vector, is the current working condition of room i, The current room temperature and outdoor temperature The same, and the indoor temperature values ​​of the room in the six directions of the current room are taken as the current room temperature;

[0280] Then calculate the cost of room i in time period d:

[0281] in, PF is the cooling capacity per unit time equivalent of the terminal unit predicted by the first neural network in the current room i (t) The accumulated cooling capacity during this period, Q jd is the cooling capacity of room j during this period, k j3 is the corresponding coefficient of room j, C d The total cost to be shared for central air conditioning during this period.

[0282] See also Figure 1B As shown, when the central air conditioner is a VRF air conditioner, the driver is built into the terminal unit of the central air conditioner to drive the fan motor, and the control unit controls the terminal unit to operate in PWM mode through the driver interface.

[0283] As an advantage, the cost sharing calculation may also be replaced by:

[0284] First calculate the conversion coefficient based on the current room conditions Where i is the current room number, s i 、s j are the areas of the i-th and j-th rooms respectively, the room numbers i, j = any integer from 1 to N, N is the total number of rooms, p i 、p j Room i and j are As input vector When they each correspond to the mapping output of the second neural network, is the current working condition of room i,

[0285] And calculate the comfort factor Where p ic For room i As input vector When it corresponds to the mapping output of the second neural network, the working condition and The only difference is that the current room temperature is set to a preset comfort temperature such as 25 degrees Celsius;

[0286] Then calculate the cost of room i in time period d:

[0287] Among them, k j1 、k j2 is the corresponding coefficient of room j, C d The total cost to be shared for central air conditioning during this period.

[0288] To achieve fair billing based on cooling capacity, this invention first models the cooling capacity characteristics of terminal units and the cooling capacity characteristics of rooms at different locations. Based on two nonlinear models, the cooling capacity of terminal units and room cooling capacity are predicted and measured under actual operating conditions. The predicted actual cooling capacity is corrected based on the cooling capacity characteristics of rooms at different locations to account for differences in environmental influences at different locations. In the first modeling step, to avoid errors caused by measuring low air volume at the terminal during online applications, the invention uses the central air conditioning chilled water supply main as a measurement point, measuring its flow rate and the supply and return water temperature difference as inputs for the air metering mapping model. Furthermore, by controlling the consistency of heat load conditions, a reference air conditioning unit is used as a reference for calculating the cooling capacity of the terminal unit. The nonlinear mapping model is trained using a sample set, and the trained model is used to predict the cooling capacity of the central air conditioning terminal unit during online applications. In the second modeling step, the model parameter structure and correction coefficient formula are designed to effectively compensate for the effects of sunlight, maintenance structures, and adjacent rooms. The present invention can ensure metering accuracy without increasing costs, and realizes the decoupling of mutual constraints between the ends of each wind screen, and can accurately measure the dynamically changing cooling capacity; furthermore, by introducing compensation for actual working conditions in the correction calculation of cooling consumption in rooms in different orientations, fairness and rationality of billing are ensured.

[0289] It can be understood that after the cooling and heating working conditions are interchanged in the present invention, the present invention is also applicable to the shared billing of central air-conditioning terminal units in the heating season.

[0290] While several embodiments of the present invention have been described above, these embodiments are provided as examples and do not limit the scope of the invention. These embodiments may be implemented in various other ways, and various omissions, substitutions, combinations, and modifications may be made without departing from the spirit of the invention. These embodiments or modifications thereof are intended to be within the scope and spirit of the invention and are also intended to be within the scope of the invention as described in the claims and their equivalents.

Claims

1. A central air conditioning billing device comprising a control unit, a sensor detection unit connected to the control unit, a user interface unit, and an operating condition adjustment unit; The sensing detection unit detects the working condition and environmental conditions of the central air conditioner, and the control unit is configured to: First, the cooling equivalent of the central air-conditioning terminal unit is measured and modeled. The first neural network is established in the control unit, taking the room where the terminal unit is located as the heat load, the working conditions of the central air-conditioning system as the input, and the equivalent cooling capacity per unit time of the terminal unit in this room as the output. Using the cooling capacity calculated by the reference air conditioning unit in the system under the same heat load conditions as the cooling capacity equivalent of the terminal unit, collecting first data samples under different operating conditions and training the first neural network; Secondly, the rooms cooled by central air conditioning are classified by location type, and a cooling consumption model is established for each type of room. The current room temperature and outdoor temperature during cooling are used as two scalars, as well as a vector consisting of the room temperature values ​​in the six directions of the current room (front, back, left, right, up, down) as inputs, and the equivalent cooling consumption per unit time of the room as output. A second neural network is established for each room in the control unit. Adaptively control the terminal unit in the current room to maintain the room temperature unchanged in stages. When the working conditions are approximately stable, collect second data samples of the second neural network under different input conditions. The output of the samples is predicted by the first neural network, and training is performed based on the collected data samples; Based on the offline cooling and consumption model, the cost of central air conditioning is allocated by time period when applied online. First, calculate the correction coefficient based on the cooling consumption model and the current room working conditions. Where i is the current room number, room number i = any integer from 1 to N, N is the total number of rooms, p i 、p i0 For The mapping output of the second neural network when it is the input vector, is the current working condition of room i, The current room temperature and outdoor temperature The same, and the indoor temperature values ​​of the room in the six directions of the current room are taken as the current room temperature; Then calculate the cost of room i in time period d: in, PF is the cooling capacity per unit time equivalent of the terminal unit predicted by the first neural network in the current room i (t) The accumulated cooling capacity during this period, Q jd is the cooling capacity of room j during this period, k j3 is the corresponding coefficient of room j, C d The total cost to be shared for central air conditioning during this period.

2. The central air conditioning billing device according to claim 1, characterized in that: The central air conditioner is a water-cooled central air conditioner, and the terminal unit is a terminal damper. The first neural network takes as input the four scalars of the central air conditioner host's chilled water supply flow, the supply and return water temperature difference, the current temperature and humidity of the room, and the vector consisting of the opening state values ​​of all terminal dampers. When collecting the first data sample: a target temperature is set according to the initial temperature of the room, the terminal air damper fan driver is controlled to operate to adjust the room temperature to the target temperature and the current humidity is obtained as the target humidity; after the room is maintained at the target temperature for a period of time, the reference air conditioning unit and the terminal air damper are respectively operated as cold sources for a certain period of time to collect samples, and the room temperature is maintained at the target temperature when the two cold sources are working independently, wherein the terminal air damper works in PWM mode, and when the reference air conditioning unit is working, the humidity is also maintained at the target humidity through the working condition adjustment unit. Based on the working characteristics and working conditions of the reference air conditioning unit, the cooling power consumption is calculated and divided by the average PWM duty cycle of the terminal damper, and the obtained value is used as the cooling capacity equivalent per unit time when the terminal damper is currently open in the state value F.

3. The central air conditioning billing device according to claim 1, characterized in that: The central air conditioner is a full-air central air conditioner, and the terminal unit is a terminal windshield. The first neural network takes the air flow rate of the central air conditioner main unit, the supply and return air temperature difference, the current temperature and humidity of the room, and the vector consisting of the opening state values ​​of all terminal windshields as input. When collecting the first data sample: a target temperature is set according to the initial temperature of the room, the terminal air damper fan driver is controlled to operate to adjust the room temperature to the target temperature and the current humidity is obtained as the target humidity; after the room is maintained at the target temperature for a period of time, the reference air conditioning unit and the terminal air damper are respectively operated as cold sources for a certain period of time to collect samples, and the room temperature is maintained at the target temperature when the two cold sources are working independently, wherein the terminal air damper works in PWM mode, and when the reference air conditioning unit is working, the humidity is also maintained at the target humidity through the working condition adjustment unit. Based on the working characteristics and working conditions of the reference air conditioning unit, the cooling power consumption is calculated and divided by the average PWM duty cycle of the terminal damper, and the obtained value is used as the cooling capacity equivalent per unit time when the terminal damper is currently open in the state value F.

4. The central air conditioning billing device according to claim 1, characterized in that: The central air conditioner is a variable refrigerant flow central air conditioner, and the terminal unit is an indoor unit. The first neural network takes as input the central air conditioner host power, indoor unit power, the current temperature and humidity of the room, and a vector consisting of the fan start status values ​​of all terminal units. When collecting the first data sample: a target temperature is set according to the initial temperature of the room, the terminal unit is controlled to adjust the room temperature to the target temperature and the current humidity is obtained as the target humidity; after the room is maintained at the target temperature for a period of time, the reference air conditioning unit and the terminal unit are respectively operated as cold sources for a certain period of time to collect samples, and the room temperature is maintained at the target temperature when the two cold sources are working independently, wherein the terminal unit operates in a PWM mode, and when the reference air conditioning unit is working, the humidity is also maintained at the target humidity through the working condition adjustment unit. Based on the working characteristics and working conditions of the reference air conditioning unit, the cooling power consumption is calculated and divided by the average PWM duty cycle of the terminal unit fan, and the obtained value is used as the cooling capacity equivalent per unit time when the terminal unit fan is currently turned on at the state value F.

5. The central air conditioning billing device according to claim 1, characterized in that: The cost allocation for central air conditioning also includes the allocation based on area. The cost of room i in time period d is: Among them, C d0 This is the basic cost of central air conditioning.

6. The central air conditioning billing device according to claim 1, characterized in that: The control unit is provided with a main processing module, which includes a sample extraction module for collecting data samples of the second neural network. The sample extraction module is configured to: periodically and continuously collect the heat load conditions and cooling consumption parameters of the central air-conditioning cooling room, and search for periods in which the input parameter values ​​of the second neural network all change within a preset fluctuation threshold, and store the data of the filtered periods in the data sample set of the second neural network.

7. The central air conditioning billing device according to claim 2 or 3, characterized in that: The sensor detection unit is provided with a flow detection module, a temperature detection module located at the inlet of the cooling main pipe of the central air-conditioning host, and a temperature detection module at the outlet end of the return main pipe connected to the host. Multiple temperature detection modules located at different positions in the room are set at the same height and are located on two vertical diagonals. The humidity is sensed by a humidity detection module in the sensing unit, which is arranged in the middle of the room return air duct. Corresponding to the low, medium and high gears of the fan speed, the wind gear opening state value of the terminal unit fan can be respectively taken as the three normalized values ​​of the fan power corresponding to the three gears.

8. The central air conditioning billing device according to claim 7, characterized in that: The working condition adjustment unit is provided with a temperature uniformity module, which includes a base, a vertical rotation axis, an angled support arm, a horizontal rotation axis, and a pitchable bracket having two sections of support arms movably connected by bolts. A telescopic support rod is connected between the outer ends of the two sections of the support arms, which is at an acute angle to the axis of the horizontal rotation axis. A temperature uniformity fan is carried at the end of the pitchable bracket. The control unit is also configured to control the operation of the temperature uniforming module so that the temperature uniforming fan shaft moves in a spatial spiral line to transmit the cold air blown out by the central air-conditioning terminal unit and / or the reference air conditioning unit to all directions of the room until the temperature difference of the multiple temperature detection modules in the room is less than the temperature difference threshold.

9. Central air conditioning billing system, which includes: User interface unit for entering parameters, initiating operations and human-computer interaction; Driver for driving the fan corresponding to the central air-conditioning terminal unit; A reference air conditioning unit whose operating characteristics have been obtained in advance and used as a reference for cooling capacity; A sensor detection unit for detecting the working conditions and environment of the central air conditioning unit and the reference air conditioning unit; A working condition adjustment unit for adjusting the operating conditions of the central air-conditioning terminal unit and the reference air-conditioning unit; A control unit connected to the driver, the reference air conditioning unit, the sensing detection unit, the user interface unit, and the working condition adjustment unit; wherein the control unit is configured to: First, the cooling equivalent of the terminal unit is measured and modeled. The first neural network is established in the control unit, taking the room where the terminal unit is located as the heat load, the working conditions of the central air-conditioning system as the input, and the equivalent cooling capacity per unit time of the terminal unit in this room as the output. Using the cooling capacity calculated by the reference air conditioning unit in the system under the same heat load conditions as the cooling capacity equivalent of the terminal unit, collecting first data samples under different operating conditions and training the first neural network; Secondly, the rooms cooled by central air conditioning are classified by location type, and a cooling consumption model is established for each type of room. The current room temperature and outdoor temperature during cooling are used as two scalars, as well as a vector consisting of the room temperature values ​​in the six directions of the current room (front, back, left, right, up, down) as inputs, and the equivalent cooling consumption per unit time of the room as output. A second neural network is established for each room in the control unit. Adaptively control the terminal unit in the current room to maintain the room temperature unchanged in stages. When the working conditions are approximately stable, collect second data samples of the second neural network under different input conditions. The output of the samples is predicted by the first neural network, and training is performed based on the collected data samples; Based on the offline cooling and consumption model, the cost of central air conditioning is allocated by time period when applied online. First, calculate the correction coefficient based on the cooling consumption model and the current room working conditions. Where i is the current room number, room number i = any integer from 1 to N, N is the total number of rooms, p i 、p i0 For The mapping output of the second neural network when it is the input vector, is the current working condition of room i, The current room temperature and outdoor temperature The same, and the indoor temperature values ​​of the room in the six directions of the current room are taken as the current room temperature; Then calculate the cost of room i in time period d: in, PF is the cooling capacity per unit time equivalent of the terminal unit predicted by the first neural network in the current room i (t) The accumulated cooling capacity during this period, Q jd is the cooling capacity of room j during this period, k j3 is the corresponding coefficient of room j, C d The total cost to be shared for central air conditioning during this period.

Images