Intelligent air conditioning system for hospital and control method

Abstract

The invention discloses a hospital intelligent air conditioning system and a control method, the system comprises an information monitoring module, a performance analysis module, a demand prediction module and a signal management module, air conditioning system performance evaluation is carried out by collecting air conditioning operation information, and a correlation influence function between the air conditioning operation performance and application scene information is established, so that the performance of the air conditioning system is evaluated. Therefore, different medical areas of the hospital are regulated in a targeted mode by monitoring application scene information, the air conditioner operation performance and the local application effect are guaranteed, and then the application efficiency of an air conditioner system of the hospital is guaranteed; by introducing meteorological platform data and combining historical data, application scene information is predicted, the air conditioner operation performance conditions of the whole hospital air conditioner system and the local medical area are evaluated and predicted, electric power resources are allocated and regulated in advance, stable electric power resource supply operation in the peak period is guaranteed, and the power supply efficiency is improved. Finally, the stable, efficient and flexible energy-saving intelligent air conditioner control effect is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of air conditioning control, and in particular to an intelligent air conditioning system and a control method for hospitals. Background Art

[0002] The intelligent air conditioning system for hospitals is an important facility to improve the comfort of the medical environment, energy-saving efficiency and ensure air quality. There are different medical areas in the hospital, and the personnel in and out of different medical areas are different, which makes the density of people in the medical area different. For example, the outpatient hall, waiting room, treatment room, medical laboratory, medical technology building, etc. The large medical equipment (such as MRI, CT, etc.) in the medical technology building will generate heat during use, and effective cooling and heating control is required to maintain the normal service life of the equipment; therefore, due to the different application scenarios of medical areas, the requirements for air conditioning systems will be different between areas, and there will be differences in the power resource allocation schemes when the air conditioning system performs cooling or heating operations; However, the current hospital air conditioning system has limited real-time monitoring capabilities for the environment and cannot perform fine regional temperature control. It may cause overcooling or overheating in key places such as wards or operating rooms, affecting patient comfort and treatment effects, resulting in high system energy consumption. When running for a long time, it increases the hospital's operating costs and causes the hospital air conditioning system to have low application efficiency. In addition, the shortage of electricity resources during peak hours will cause the air conditioning application effect in the medical area to be unstable, making it difficult to meet the constant temperature requirements of medical staff, patients and medical equipment. In view of the above technical defects, a solution is now proposed. Summary of the invention

[0003] The purpose of the present invention is to solve the defects of the prior art, such as limited real-time monitoring capability of air conditioners, insufficient refinement of regional temperature control, and the resulting low application efficiency and unstable effect of air conditioning systems. The present invention monitors application scenario information to evaluate the priority of medical areas and performs corresponding real-time regulation to ensure the operating performance of air conditioners and the application effect of local areas, thereby ensuring the application efficiency of hospital air conditioning systems. The present invention introduces meteorological platform data and combines historical data to perform advance configuration and adaptive regulation of power resources to ensure stable supply and operation of power resources during peak periods, and ultimately achieves stable, efficient, and flexible energy-saving intelligent air conditioning control effects.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions: A hospital intelligent air conditioning control method comprises the following steps: Step 1: Collect air-conditioning operation information and application scenario information: divide the hospital into N0 medical areas, collect information from any medical area a, and obtain the air-conditioning operation information and application scenario information of the medical area a; the air-conditioning operation information includes energy consumption parameters and mode parameters; the application scenario information includes external factor parameters and internal factor parameters; Step 2: Build a system performance evaluation model: perform regional performance analysis based on the air conditioning operation information of medical area a to evaluate the air conditioning operation performance of medical area a, and then conduct a comprehensive analysis based on the air conditioning operation performance of N0 medical areas to evaluate the performance of the hospital air conditioning system; Step 3: Construct a performance impact analysis model: by building a correlation impact function between the air conditioning operation performance of medical area a and the application scenario information, the priority of the medical area is evaluated by monitoring the application scenario information, and the corresponding real-time control signal is generated and output; Step 4: Construct a power demand forecasting model: By introducing meteorological platform data and combining historical data analysis, obtain the forecast data set of application scenario information, and substitute it into the associated influence function to evaluate the forecast impact of the air conditioning operation performance of medical area a and the forecast impact of the hospital air conditioning system performance, and then integrate and evaluate the power forecast demand degree, generate and output the corresponding forecast management signal; Step 5, receive the signal and perform corresponding control management operations: when a real-time control signal is received, the hospital air-conditioning system is regionally configured and controlled in real time; when a predictive management signal is received, the power resources of the hospital air-conditioning system are overall configured and controlled in advance.

[0005] Furthermore, the specific process of building the system performance evaluation model is as follows: Sa1, performing regional performance analysis based on the air conditioning operation information of medical area a to evaluate the air conditioning operation performance of medical area a; Set the information collection period Tc to collect the air conditioner operation information regularly, and extract the air conditioner operation information of n0 information collection periods Tc; Sa1-1, obtain the regional air conditioning operation energy consumption index through the energy consumption parameters of medical area a, and evaluate the energy consumption level of air conditioning operation in the area; Sa1-2, obtain the regional air conditioning operation status index through the mode parameters of medical area a, and evaluate the air conditioning operation mode status in the area; Sa1-3, by combining the regional air conditioning operation energy consumption index ENGa and the regional air conditioning operation status index RUNa of medical area a, the air conditioning operation performance coefficient PerA of medical area a is obtained; Sa2, and then conduct a comprehensive analysis through the air conditioning operation performance of N0 medical areas, and combine the air conditioning operation performance coefficient PerA of N0 medical areas to obtain the hospital air conditioning system performance index PerH to evaluate the performance of the hospital air conditioning system.

[0006] Furthermore, the specific process of evaluating the energy consumption of air conditioning in the area is as follows: The energy consumption parameters include current, voltage and electric power. The current, voltage and electric power of medical area a are marked as Ia, Ua and Pa respectively; Sa1-101, build the energy consumption parameter analysis sub-model, the specific process is as follows: Mark any indicator of the energy consumption parameter as e, and construct a change curve Se of the indicator e through the data value Me of the indicator e in n0 information collection cycles Tc, where the abscissa of the change curve Se is the information collection cycle Tc, and the ordinate is the data value Me of the indicator e, so as to analyze the curve increase rate Ks, the fluctuation coefficient σs and the curve mean Jm of the change curve Se. The specific process is as follows: By calculating the average value Me of the data values ​​of n0 indicators e, the curve mean Jm is obtained, and by calculating the variance Me of the data values ​​of n0 indicators e, the fluctuation coefficient σs is obtained; By extracting any point E1 and its adjacent point E2 of the change curve Se, the slope Ke of point E1 is obtained through the coordinates of point E1 and point E2, and then the slope of n0 points is averaged to obtain the curve increase rate Ks; By combining the curve increase rate Ks, the fluctuation coefficient σs and the curve mean Jm of the change curve Se, the evaluation index MentE of the energy consumption index e is obtained and output; Sa1-102, substitute the energy consumption parameters of n0 information collection cycles Tc into the energy consumption parameter analysis sub-model; Substitute the current Ia as the index e into the energy consumption parameter analysis sub-model, output the evaluation index MentE of the index e, and mark it as the current energy consumption coefficient MEi; Substitute the voltage Ua as the index e into the energy consumption parameter analysis sub-model, output the evaluation index MentE of the index e, and mark it as the voltage energy consumption coefficient MEu; Substitute the electric power Pa as the index e into the energy consumption parameter analysis sub-model, output the evaluation index MentE of the index e, and mark it as the power energy consumption coefficient MEp; By combining the current energy consumption coefficient MEi, the voltage energy consumption coefficient MEu and the power energy consumption coefficient MEp, the regional air conditioning operation energy consumption index ENGa of the medical area a is obtained; Set the evaluation interval of the regional air-conditioning operation energy consumption index ENGa, and evaluate the air-conditioning operation energy consumption level in the region through interval comparison.

[0007] Furthermore, the specific process of evaluating the air conditioning operation mode status in the area is as follows: Sa1-2, obtain the regional air conditioning operation status index through the mode parameters of medical area a, and evaluate the air conditioning operation mode status in the area; The mode parameters include cooling temperature difference, heating temperature difference and dehumidification wind speed; the cooling temperature difference, heating temperature difference and dehumidification wind speed of medical area a are marked as , , Vsf; The cooling temperature difference is obtained by calculating the average value of the mode parameters of n0 information collection cycles Tc , Heating temperature difference and the average index of dehumidification wind speed Vsf, and are marked as Pcd, Pht, and Pvs respectively; The cooling temperature difference of the current information collection period Tc , Heating temperature difference Combined with the dehumidification wind speed Vsf and its corresponding average index, the regional air conditioning operation status index RUNa of medical area a is obtained; Set the evaluation interval of the regional air conditioning operation status index RUNa, and evaluate the air conditioning operation mode status in the area through interval comparison.

[0008] Furthermore, the specific process of building a performance impact analysis model is as follows: Sb1, build the correlation influence function Fin between the air conditioning operation performance coefficient PerA of medical area a and the internal factor parameters; Sb2, build the correlation influence function Fou between the hospital air conditioning system performance index PerH and external factor parameters; Sb3, by monitoring application scenario information, evaluates the priority of medical areas, generates and outputs corresponding real-time control signals; Among them, the overall evaluation is performed through the association influence function Fou to monitor the comprehensive influence of the external factor vector group OUve on the hospital air-conditioning system performance index PerH; and then the local evaluation is performed through the association influence function Fin to monitor the influence of the internal factor vector group INve on the air-conditioning operation performance coefficient PerA.

[0009] Furthermore, the specific analysis process of the association influence function Fin is as follows: The internal factor parameters include indoor temperature w1, indoor humidity w2, personnel density w3 and equipment heat w4. The internal factor vector group INve is obtained through the indoor temperature w1, indoor humidity w2, personnel density w3 and equipment heat w4. Mark any vector of the internal factor vector group INve as W, construct a correlation curve Sw between the vector W and the air conditioner operation performance coefficient PerA, and fit the correlation function Fw of the vector W; By obtaining the corresponding correlation function for all vectors of the internal factor vector group INve, a correlation influence function Fin between the air conditioner operation performance coefficient PerA and the internal factor vector group INve is comprehensively generated; Furthermore, the specific analysis process of the association influence function Fou is as follows: The external factor parameters include outdoor temperature z1, outdoor humidity z2, outdoor wind speed z3 and solar radiation intensity z4. The external factor vector group OUve is obtained through the outdoor temperature z1, outdoor humidity z2, outdoor wind speed z3 and solar radiation intensity z4; Mark any vector of the external factor vector group OUve as Z, construct the correlation curve Sz between the vector Z and the performance index PerH of the hospital air conditioning system, and fit the correlation function Fz of the vector Z; The corresponding correlation function is obtained by all vectors of the external factor vector group OUve, and the correlation influence function Fou between the hospital air-conditioning system performance index PerH and the external factor vector group OUve is comprehensively generated.

[0010] Furthermore, the specific process of constructing the power demand forecasting model is as follows: Set the data prediction period Ty, take the data prediction period Ty as the time length, and extract the two time nodes t1 and t2 before and after the current time node t0; The predicted values ​​of the external factor parameters at time node t2 are obtained through the meteorological platform; the predicted values ​​of the internal factor parameters are obtained through periodic analysis of historical data, and the internal factor parameters at time node t1 are used as the predicted values ​​of the internal factor parameters at time node t2; The predicted values ​​of the external factor parameters and the predicted values ​​of the internal factor parameters are integrated and marked as a predicted number set of application scenario information; Substitute the predicted value of the external factor parameter into the correlation influence function Fou to obtain the electricity external demand index DEou, and use the electricity external demand index DEou to evaluate the predicted influence of the external factor parameter on the hospital air conditioning system performance index PerH; Substitute the predicted value of the internal factor parameter into the correlation influence function Fin to obtain the internal power demand index DEin, and use the internal power demand index DEin to evaluate the predicted influence of the internal factor parameters of the medical area a on the air conditioning operation performance of the medical area; By combining the electricity external demand index DEou and the electricity internal demand index DEin, the electricity forecast demand coefficient DEeng is obtained; An evaluation interval of the power forecast demand coefficient DEeng is set, and any evaluation interval is marked as δg. When the power forecast demand coefficient DEeng is located in the evaluation interval δg, a g-level forecast management signal is generated.

[0011] An intelligent air conditioning system for a hospital, comprising an information monitoring module, a performance analysis module, a demand prediction module and a signal management module, wherein the information monitoring module, the performance analysis module, the demand prediction module and the signal management module are communicatively connected, and the system applies the above-mentioned intelligent air conditioning control method for a hospital; The information monitoring module is used to collect air-conditioning operation information and application scenario information; The performance analysis module is used to build system performance evaluation models and performance impact analysis models, and output real-time control signals; The demand forecasting module is used to build a power demand forecasting model and output forecasting management signals; The signal management module is used to receive signals and perform corresponding control management operations.

[0012] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are: The present invention evaluates the performance of the air conditioning system by collecting air conditioning operation information, and by building a correlation influence function between the air conditioning operation performance and the application scenario information, thereby evaluating the priority of the medical area by monitoring the application scenario information and performing corresponding real-time regulation, and by performing targeted regulation on different medical areas of the hospital, ensuring the air conditioning operation performance and the application effect of the local area, thereby ensuring the application efficiency of the hospital air conditioning system; The present invention introduces meteorological platform data and combines it with historical data to predict application scenario information and substitute it into the associated influence function, evaluate and predict the air-conditioning operation performance of the hospital's overall air-conditioning system and the local air-conditioning operation performance of the medical area, and configure power resources in advance and adaptively regulate them to ensure stable power resource supply and operation during peak periods, ultimately achieving stable, efficient, and flexible energy-saving intelligent air-conditioning control effects. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] Figure 1 A schematic diagram showing the steps of the method flow of the present invention is shown; Figure 2 A connection diagram of the system modules of the present invention is shown. DETAILED DESCRIPTION

[0014] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0015] Embodiment 1: like Figure 1-Figure 2 As shown, a hospital intelligent air conditioning control method comprises the following steps: S1, collecting air-conditioning operation information and application scenario information: dividing the hospital into N0 medical areas, collecting information from any medical area a, and obtaining the air-conditioning operation information and application scenario information of the medical area a; wherein the air-conditioning operation information includes energy consumption parameters and mode parameters; the application scenario information includes external factor parameters and internal factor parameters; The energy consumption parameters include current, voltage and electric power. The current, voltage and electric power of medical area a are marked as Ia, Ua and Pa respectively; The mode parameters include cooling temperature difference, heating temperature difference and dehumidification wind speed; the cooling temperature difference, heating temperature difference and dehumidification wind speed of medical area a are marked as , , Vsf; Internal factor parameters include indoor temperature w1, indoor humidity w2, personnel density w3 and equipment heat w4; External factor parameters include outdoor temperature z1, outdoor humidity z2, outdoor wind speed z3 and solar radiation intensity z4; S2, building a system performance evaluation model: performing regional performance analysis based on the air conditioning operation information of medical area a, evaluating the air conditioning operation performance of medical area a, and then conducting a comprehensive analysis based on the air conditioning operation performance of N0 medical areas to evaluate the performance of the hospital air conditioning system; The specific process of building a system performance evaluation model is as follows: Sa1, performing regional performance analysis based on the air conditioning operation information of medical area a to evaluate the air conditioning operation performance of medical area a; Set the information collection period Tc to collect the air conditioner operation information regularly, and extract the air conditioner operation information of n0 information collection periods Tc; Sa1-1, obtain the regional air conditioning operation energy consumption index through the energy consumption parameters of medical area a, and evaluate the energy consumption level of air conditioning operation in the area; Sa1-101, build the energy consumption parameter analysis sub-model, the specific process is as follows: Mark any indicator of the energy consumption parameter as e, and construct a change curve Se of the indicator e through the data value Me of the indicator e in n0 information collection cycles Tc, where the abscissa of the change curve Se is the information collection cycle Tc, and the ordinate is the data value Me of the indicator e, so as to analyze the curve increase rate Ks, the fluctuation coefficient σs and the curve mean Jm of the change curve Se. The specific process is as follows: By calculating the average value Me of the data values ​​of n0 indicators e, the curve mean Jm is obtained: ; And by calculating the variance of the data values ​​Me of n0 indicators e, we can obtain the volatility coefficient σs: ; By extracting any point E1 and its adjacent point E2 of the change curve Se, and obtaining the slope Ke of point E1 through the coordinates of point E1 and point E2: , where the coordinates of the marked point E1 are (Xe1, Ye1), and the coordinates of the point E2 are (Xe2, Ye2). Then, the slopes of n0 points are averaged to obtain the curve increase rate Ks: ; By combining the curve increase rate Ks, the fluctuation coefficient σs and the curve mean Jm of the change curve Se, the evaluation index MentE of the energy consumption index e is obtained and output: ; in, and They are the conversion coefficients of the curve increase rate Ks and the curve mean Jm, and the preset and are all greater than 1, and the conversion coefficient is obtained by preset after a large amount of data experimental measurement; when the curve increase rate Ks of the change curve Se is higher, the fluctuation coefficient σs and the curve mean Jm are higher, it means that the overall growth trend of the energy consumption index e is higher, the fluctuation range is larger, and the overall index level is higher, indicating that the energy consumption growth trend of the energy consumption index e is obvious, the stability is low, and the energy consumption is higher, and then the comprehensive evaluation of the energy consumption index e is higher; Sa1-102, substitute the energy consumption parameters of n0 information collection cycles Tc into the energy consumption parameter analysis sub-model; Substitute the current Ia as the index e into the energy consumption parameter analysis sub-model, output the evaluation index MentE of the index e, and mark it as the current energy consumption coefficient MEi; Substitute the voltage Ua as the index e into the energy consumption parameter analysis sub-model, output the evaluation index MentE of the index e, and mark it as the voltage energy consumption coefficient MEu; Substitute the electric power Pa as the index e into the energy consumption parameter analysis sub-model, output the evaluation index MentE of the index e, and mark it as the power energy consumption coefficient MEp; By combining the current energy consumption coefficient MEi, the voltage energy consumption coefficient MEu and the power energy consumption coefficient MEp, the regional air conditioning operation energy consumption index ENGa of the medical area a is obtained: ; in, , and They are the weight coefficients of the current energy consumption coefficient MEi, the voltage energy consumption coefficient MEu and the power energy consumption coefficient MEp, and the preset , and All are greater than 1; when the current energy consumption coefficient MEi, voltage energy consumption coefficient MEu and power energy consumption coefficient MEp are higher, the regional air conditioning operation energy consumption index ENGa of medical area a is higher, and the regional air conditioning operation energy consumption level of the medical area a is higher; Set the evaluation interval of regional air conditioning operation energy consumption index ENGa, and evaluate the air conditioning operation energy consumption level in the region through interval comparison; Sa1-2, obtain the regional air conditioning operation status index through the mode parameters of medical area a, and evaluate the air conditioning operation mode status in the area; The cooling temperature difference is obtained by calculating the average value of the mode parameters of n0 information collection cycles Tc , Heating temperature difference and the average index of dehumidification wind speed Vsf, and are marked as Pcd, Pht, and Pvs respectively; Among them, the cooling temperature difference The average index Pcd: ; Heating temperature difference Average index Pht: ; Average index Pvs of dehumidification wind speed Vsf: ; The cooling temperature difference of the current information collection period Tc , Heating temperature difference Combined with the dehumidification wind speed Vsf and its corresponding average index, the regional air conditioning operation status index RUNa of medical area a is obtained: ; in, , and Refrigeration temperature difference , Heating temperature difference and the weight coefficient of the dehumidification wind speed Vsf, and preset , and are greater than 0; when the cooling temperature difference , Heating temperature difference When the dehumidification wind speed Vsf and its corresponding average index are higher, the regional air conditioning operation status index RUNa of medical area a is higher, indicating that the cooling, heating and dehumidification effects in the air conditioning operation mode are better, and then the regional air conditioning operation mode state of medical area a is better; Set the evaluation interval of the regional air conditioning operation status index RUNa, and evaluate the air conditioning operation mode status in the region by comparing the intervals; Sa1-3, by combining the regional air conditioning operation energy consumption index ENGa and the regional air conditioning operation status index RUNa of medical area a, the air conditioning operation performance coefficient PerA of medical area a is obtained:

[0016] Among them, λ1 and λ2 are the weight coefficients of the regional air conditioning operation status index RUNa and the regional air conditioning operation energy consumption index ENGa, respectively, and both λ1 and λ2 are preset to be greater than 0; when the regional air conditioning operation status index RUNa is higher and the regional air conditioning operation energy consumption index ENGa is lower, the air conditioning operation performance coefficient PerA is higher, indicating that the air conditioning operation performance of medical area a is better; Sa2, then conduct a comprehensive analysis of the air conditioning operation performance of N0 medical areas to evaluate the performance of the hospital air conditioning system; By combining the air conditioning operation performance coefficients PerA of N0 medical areas, the hospital air conditioning system performance index PerH is obtained: ; Among them, φa refers to the conversion coefficient of the air conditioning operation performance coefficient PerA, and φa is greater than 0 and ; σP refers to the standard deviation of the air conditioning operation performance coefficient PerA of N0 medical areas; when the air conditioning operation performance coefficient PerA of N0 medical areas is higher and the standard deviation σP of the air conditioning operation performance coefficient PerA is lower, the hospital air conditioning system performance index PerH is higher, indicating that the overall level of air conditioning operation performance of N0 medical areas is higher, and the difference in air conditioning operation performance between medical areas is smaller, and thus the performance of the hospital air conditioning system is better; S3, building a performance impact analysis model: by building a correlation impact function between the air conditioning operation performance of medical area a and the application scenario information, the priority of the medical area is evaluated by monitoring the application scenario information, and the corresponding real-time control signal is generated and output; The specific process of building a performance impact analysis model is as follows: Sb1, build the correlation influence function between the air conditioning operation performance coefficient PerA of medical area a and the internal factor parameters; The internal factor vector group INve is obtained through indoor temperature w1, indoor humidity w2, personnel density w3 and equipment heat w4: ; Mark any vector of the internal factor vector group INve as W, take vector W as the horizontal coordinate and air conditioning operation performance coefficient PerA as the vertical coordinate, construct the correlation curve Sw between vector W and air conditioning operation performance coefficient PerA, and fit the correlation function Fw of vector W: ; Substitute the vector W into the correlation function Fw to obtain the corresponding air conditioning operation performance coefficient PerA; By synchronously performing curve fitting on all vectors of the internal factor vector group INve, the corresponding correlation function is obtained, and the correlation influence function Fin between the air conditioning operation performance coefficient PerA and the internal factor vector group INve is comprehensively generated: ; Among them, ρin is the internal factor conversion coefficient, and ρin is preset to be greater than 0; It refers to the proportion of the correlation function value Fw of vector W in the sum of the correlation function values ​​of all vectors, that is, the influence of vector W on the air conditioner operation performance coefficient PerA. By weighted summation and assigning corresponding conversion constants, the comprehensive influence of all vectors of the internal factor vector group INve on the air conditioner operation performance coefficient PerA is evaluated. The higher the correlation influence function Fin, the higher the comprehensive influence. The correlation functions of indoor temperature w1, indoor humidity w2, personnel density w3 and equipment heat generation w4 are marked as Fw1, Fw2, Fw3, and Fw4 respectively; Then it can be deduced that, ; Sb2, build the correlation influence function between the hospital air conditioning system performance index PerH and external factor parameters; The external factor vector group OUve is obtained through outdoor temperature z1, outdoor humidity z2, outdoor wind speed z3 and solar radiation intensity z4: ; Mark any vector of the external factor vector group OUve as Z, take vector Z as the horizontal coordinate and hospital air conditioning system performance index PerH as the vertical coordinate, construct the correlation curve Sz between vector Z and hospital air conditioning system performance index PerH, and fit the correlation function Fz of vector Z: ; Substitute the vector Z into the correlation function Fz to obtain the corresponding hospital air conditioning system performance index PerH; By synchronously performing curve fitting on all vectors of the external factor vector group OUve, the corresponding correlation function is obtained, and the correlation influence function Fou between the hospital air conditioning system performance index PerH and the external factor vector group OUve is comprehensively generated: ; Among them, ρou is the external factor conversion coefficient, and ρou is preset to be greater than 0; It refers to the proportion of the correlation function value Fz of vector Z in the sum of the correlation function values ​​of all vectors, that is, the influence of vector Z on the performance index PerH of the hospital air-conditioning system. By weighted summation and assigning corresponding conversion constants, the comprehensive influence of all vectors of the external factor vector group OUve on the performance index PerH of the hospital air-conditioning system is evaluated. The higher the correlation influence function Fou is, the higher the comprehensive influence is. The correlation functions of outdoor temperature z1, outdoor humidity z2, outdoor wind speed z3 and solar radiation intensity z4 are marked as Fz1, Fz2, Fz3 and Fz4 respectively; Then it can be deduced that, ; Sb3, through the association influence function Fou, the overall evaluation is carried out to monitor the comprehensive influence of the external factor vector group OUve on the performance index PerH of the hospital air conditioning system, and the threshold H1 of the hospital's association influence function Fou is set. When the association influence function Fou exceeds the threshold H1, a level I real-time control signal of the air conditioning system is generated. By receiving the level I real-time control signal, the air conditioning system is controlled as a whole. The specific control operation is as follows: By monitoring application scenario information, evaluating the priority of medical areas, and generating and outputting corresponding real-time control signals; A threshold value H2 of the correlation influence function Fin of the medical area a is set. When the correlation influence function Fin exceeds the threshold value H2, it is determined that the air conditioning operation performance of the medical area a is poor, and a level II real-time control signal of the medical area a is generated. The medical area a is locally controlled by the level II real-time control signal. The association influence function values ​​of N0 medical areas are compared synchronously and sorted in descending order, so as to extract m0 medical areas with poor air conditioning operation performance. The higher the association influence function value, the higher the priority of the medical area, and the air conditioning mode of the medical area is regulated first; By adjusting the air conditioning mode of m0 medical areas according to the priority, the overall control of the hospital air conditioning system is achieved. The air conditioning mode control operation is flexibly adjusted according to the actual situation. For example, adaptive adjustment is made according to the internal factor parameters of the medical area. When the indoor temperature w1, indoor humidity w2, personnel density w3 and equipment heat generation w4 are high, the refrigeration compressor of the air conditioning system of the medical area is strengthened; S4, constructing a power demand forecasting model: by introducing meteorological platform data and combining historical data analysis, obtaining a forecast data set of application scenario information, and substituting it into the associated influence function, evaluating the forecast degree of the air conditioning operation performance of medical area a, and the forecast influence degree of the hospital air conditioning system performance, and then integrating and evaluating the power forecast demand degree, generating and outputting the corresponding forecast management signal; The specific process of building a power demand forecasting model is as follows: Set the data prediction period Ty, take the data prediction period Ty as the time length, and extract the two time nodes t1 and t2 before and after the current time node t0; Obtain the predicted value of the external factor parameter at time node t2 through the meteorological platform, that is, the external factor parameter corresponding to the data prediction cycle after the current time node; Obtain the predicted values ​​of the internal factor parameters through periodic analysis of historical data, and use the internal factor parameters at time node t1 as the predicted values ​​of the internal factor parameters at time node t2; Among them, time node t1 is located in the historical period of current time node t0, and the time length between time node t1 and current time node t0 is a data prediction period, time node t2 is located in the future period of current time node t0, and the time length between time node t2 and current time node t0 is also a data prediction period; The predicted values ​​of the external factor parameters and the predicted values ​​of the internal factor parameters are integrated and marked as a predicted number set of application scenario information; the predicted number set of application scenario information includes the predicted values ​​of the external factor parameters and the predicted values ​​of the internal factor parameters; Substitute the predicted values ​​of the external factor parameters into the associated influence function Fou to obtain the electricity external demand index DEou: , where REZ refers to the set of predicted values ​​of external factor parameters, set REZ= ; The power external demand index DEou is used to evaluate the predicted influence of external factor parameters on the hospital air conditioning system performance index PerH. The higher the power external demand index DEou is, the higher the predicted influence of external factor parameters on the hospital air conditioning system performance is, indicating that the hospital air conditioning power resource demand is greater under the influence of external factors. Substitute the predicted values ​​of the internal factor parameters into the associated influence function Fin to obtain the internal electricity demand index DEin: , where REW refers to the set of predicted values ​​of internal factor parameters, set REW= ; The internal power demand index DEin is used to evaluate the predicted influence of the internal factor parameters of medical area a on the air conditioning operation performance of the medical area. The higher the internal power demand index DEin is, the higher the predicted influence of the internal factor parameters on the air conditioning operation performance of the medical area is, indicating that the medical area air conditioning power resource demand is greater under the influence of internal factors. By combining the electricity external demand index DEou and the electricity internal demand index DEin, the electricity forecast demand coefficient DEeng is obtained: ; The evaluation interval of the power forecast demand coefficient DEeng is set, and any evaluation interval is marked as δg. When the power forecast demand coefficient DEeng is in the evaluation interval δg, a g-level forecast management signal is generated to perform targeted configuration and regulation of the power resources in the medical area a. Among them, the configuration and control operation is to set specific parameters in combination with the predicted data set of the application scenario information. For example, when the power prediction demand coefficient DEeng is higher, the priority of the medical area is higher, so that the air-conditioning system will give priority to investing part of the power resources in the medical area for air-conditioning operation, such as pre-cooling and blowing, before the peak period of power consumption, so as to configure and control the power resources of the hospital air-conditioning system in advance as a whole, ensure the stable operation of power resource supply during the peak period, and finally achieve a stable, efficient and flexible energy-saving intelligent air-conditioning control effect; S5, receives the signal and performs corresponding control and management operations: When a real-time control signal is received, the hospital's air-conditioning system is configured and controlled in a targeted area in real time; when a predictive management signal is received, the power resources of the hospital's air-conditioning system are configured and controlled in advance as a whole.

[0017] An intelligent air conditioning system for a hospital, comprising an information monitoring module, a performance analysis module, a demand prediction module and a signal management module, wherein the information monitoring module, the performance analysis module, the demand prediction module and the signal management module are communicatively connected, and the system applies the above-mentioned intelligent air conditioning control method for a hospital; The information monitoring module is used to collect air-conditioning operation information and application scenario information; The performance analysis module is used to build system performance evaluation models and performance impact analysis models, and output real-time control signals; The demand forecasting module is used to build a power demand forecasting model and output forecasting management signals; The signal management module is used to receive real-time control signals and prediction management signals, and perform corresponding control management operations respectively.

[0018] To summarize, the present invention evaluates the performance of the air-conditioning system by collecting air-conditioning operation information, and by building a correlation influence function between the air-conditioning operation performance and the application scenario information, thereby evaluating the priority of the medical area by monitoring the application scenario information and performing corresponding real-time regulation, and performing targeted regulation on different medical areas of the hospital to ensure the air-conditioning operation performance and local application effect, thereby ensuring the application efficiency of the hospital air-conditioning system; the present invention introduces meteorological platform data and combines historical data to predict the application scenario information and substitute it into the correlation influence function, evaluates and predicts the air-conditioning operation performance of the hospital air-conditioning system as a whole and the local air-conditioning operation performance of the medical area, and performs advance configuration and regulation of power resources to ensure stable supply and operation of power resources during peak periods, and ultimately achieves stable, efficient, and flexible energy-saving intelligent air-conditioning control effects.

[0019] The size of the interval and threshold is set to facilitate comparison. The size of the threshold depends on the amount of sample data and the number of bases set by technical personnel in this field for each group of sample data; as long as it does not affect the proportional relationship between the parameter and the quantized value.

[0020] The above formulas are all dimensionless and numerical calculations. The formula is a formula obtained by collecting a large amount of data and performing software simulation to obtain the most recent real situation. The preset parameters in the formula are set by technicians in this field according to actual conditions. The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A hospital intelligent air conditioning control method, characterized in that: The following steps are involved: Step 1: Collect air-conditioning operation information and application scenario information: divide the hospital into N0 medical areas, collect information from any medical area a, and obtain the air-conditioning operation information and application scenario information of the medical area a; the air-conditioning operation information includes energy consumption parameters and mode parameters; the application scenario information includes external factor parameters and internal factor parameters; Step 2: Build a system performance evaluation model: perform regional performance analysis based on the air conditioning operation information of medical area a to evaluate the air conditioning operation performance of medical area a, and then conduct a comprehensive analysis based on the air conditioning operation performance of N0 medical areas to evaluate the performance of the hospital air conditioning system; Step 3: Construct a performance impact analysis model: by building a correlation impact function between the air conditioning operation performance of medical area a and the application scenario information, the priority of the medical area is evaluated by monitoring the application scenario information, and the corresponding real-time control signal is generated and output; Step 4: Construct a power demand forecasting model: By introducing meteorological platform data and combining historical data analysis, obtain the forecast data set of application scenario information, and substitute it into the associated influence function to evaluate the forecast impact of the air conditioning operation performance of medical area a and the forecast impact of the hospital air conditioning system performance, and then integrate and evaluate the power forecast demand degree, generate and output the corresponding forecast management signal; Step 5, receive the signal and perform corresponding control management operations: when a real-time control signal is received, the hospital air-conditioning system is regionally configured and controlled in real time; when a predictive management signal is received, the power resources of the hospital air-conditioning system are overall configured and controlled in advance.

2. The intelligent air conditioning control method for a hospital according to claim 1, characterized in that: The specific process of building a system performance evaluation model is as follows: Sa1, performing regional performance analysis based on the air conditioning operation information of medical area a to evaluate the air conditioning operation performance of medical area a; Set the information collection period Tc to collect the air conditioner operation information regularly, and extract the air conditioner operation information of n0 information collection periods Tc; Sa1-1, obtain the regional air conditioning operation energy consumption index through the energy consumption parameters of medical area a, and evaluate the energy consumption level of air conditioning operation in the area; Sa1-2, obtain the regional air conditioning operation status index through the mode parameters of medical area a, and evaluate the air conditioning operation mode status in the area; Sa1-3, by combining the regional air conditioning operation energy consumption index ENGa and the regional air conditioning operation status index RUNa of medical area a, the air conditioning operation performance coefficient PerA of medical area a is obtained; Sa2, and then conduct a comprehensive analysis through the air conditioning operation performance of N0 medical areas, and combine the air conditioning operation performance coefficient PerA of N0 medical areas to obtain the hospital air conditioning system performance index PerH to evaluate the performance of the hospital air conditioning system.

3. The intelligent air conditioning control method for a hospital according to claim 2, characterized in that: The specific process of evaluating the energy consumption of air conditioning in the area is as follows: The energy consumption parameters include current, voltage and electric power. The current, voltage and electric power of medical area a are marked as Ia, Ua and Pa respectively; Sa1-101, build the energy consumption parameter analysis sub-model, the specific process is as follows: Mark any indicator of the energy consumption parameter as e, and construct a change curve Se of the indicator e through the data value Me of the indicator e in n0 information collection cycles Tc, where the abscissa of the change curve Se is the information collection cycle Tc, and the ordinate is the data value Me of the indicator e, so as to analyze the curve increase rate Ks, the fluctuation coefficient σs and the curve mean Jm of the change curve Se. The specific process is as follows: By calculating the average value Me of the data values ​​of n0 indicators e, the curve mean Jm is obtained, and by calculating the variance Me of the data values ​​of n0 indicators e, the fluctuation coefficient σs is obtained; By extracting any point E1 and its adjacent point E2 of the change curve Se, the slope Ke of point E1 is obtained through the coordinates of point E1 and point E2, and then the slope of n0 points is averaged to obtain the curve increase rate Ks; By combining the curve increase rate Ks, the fluctuation coefficient σs and the curve mean Jm of the change curve Se, the evaluation index MentE of the energy consumption index e is obtained and output; Sa1-102, substitute the energy consumption parameters of n0 information collection cycles Tc into the energy consumption parameter analysis sub-model; Substitute the current Ia as the index e into the energy consumption parameter analysis sub-model, output the evaluation index MentE of the index e, and mark it as the current energy consumption coefficient MEi; Substitute the voltage Ua as the index e into the energy consumption parameter analysis sub-model, output the evaluation index MentE of the index e, and mark it as the voltage energy consumption coefficient MEu; Substitute the electric power Pa as the index e into the energy consumption parameter analysis sub-model, output the evaluation index MentE of the index e, and mark it as the power energy consumption coefficient MEp; By combining the current energy consumption coefficient MEi, the voltage energy consumption coefficient MEu and the power energy consumption coefficient MEp, the regional air conditioning operation energy consumption index ENGa of the medical area a is obtained; Set the evaluation interval of the regional air-conditioning operation energy consumption index ENGa, and evaluate the air-conditioning operation energy consumption level in the region through interval comparison.

4. The intelligent air conditioning control method for a hospital according to claim 3, characterized in that: The specific process of evaluating the air conditioning operation mode status in the area is as follows: Sa1-2, obtain the regional air conditioning operation status index through the mode parameters of medical area a, and evaluate the air conditioning operation mode status in the area; Mode parameters include cooling temperature difference, heating temperature difference and dehumidification wind speed; The cooling temperature difference, heating temperature difference and dehumidification wind speed of medical area a are marked as , , Vsf; The cooling temperature difference is obtained by calculating the average value of the mode parameters of n0 information collection cycles Tc , Heating temperature difference and the average index of dehumidification wind speed Vsf, and are marked as Pcd, Pht, and Pvs respectively; The cooling temperature difference of the current information collection period Tc , Heating temperature difference Combined with the dehumidification wind speed Vsf and its corresponding average index, the regional air conditioning operation status index RUNa of medical area a is obtained; Set the evaluation interval of the regional air conditioning operation status index RUNa, and evaluate the air conditioning operation mode status in the area through interval comparison.

5. The intelligent air conditioning control method for a hospital according to claim 4, characterized in that: The specific process of building a performance impact analysis model is as follows: Sb1, build the correlation influence function Fin between the air conditioning operation performance coefficient PerA of medical area a and the internal factor parameters; Sb2, build the correlation influence function Fou between the hospital air conditioning system performance index PerH and external factor parameters; Sb3, by monitoring application scenario information, evaluates the priority of medical areas, generates and outputs corresponding real-time control signals; Among them, the overall evaluation is performed through the association influence function Fou to monitor the comprehensive influence of the external factor vector group OUve on the hospital air-conditioning system performance index PerH; and then the local evaluation is performed through the association influence function Fin to monitor the influence of the internal factor vector group INve on the air-conditioning operation performance coefficient PerA.

6. The intelligent air conditioning control method for a hospital according to claim 5, characterized in that: The specific analysis process of the correlation influence function Fin of internal factors is as follows: The internal factor parameters include indoor temperature w1, indoor humidity w2, personnel density w3 and equipment heat w4. The internal factor vector group INve is obtained through the indoor temperature w1, indoor humidity w2, personnel density w3 and equipment heat w4. Mark any vector of the internal factor vector group INve as W, construct a correlation curve Sw between the vector W and the air conditioner operation performance coefficient PerA, and fit the correlation function Fw of the vector W; The corresponding correlation function is obtained for all vectors of the internal factor vector group INve, and the correlation influence function Fin between the air-conditioning operation performance coefficient PerA and the internal factor vector group INve is comprehensively generated.

7. The intelligent air conditioning control method for a hospital according to claim 6, characterized in that: The specific analysis process of the external factor correlation influence function Fou is as follows: The external factor parameters include outdoor temperature z1, outdoor humidity z2, outdoor wind speed z3 and solar radiation intensity z4. The external factor vector group OUve is obtained through the outdoor temperature z1, outdoor humidity z2, outdoor wind speed z3 and solar radiation intensity z4; Mark any vector of the external factor vector group OUve as Z, construct the correlation curve Sz between the vector Z and the performance index PerH of the hospital air conditioning system, and fit the correlation function Fz of the vector Z; The corresponding correlation function is obtained by all vectors of the external factor vector group OUve, and the correlation influence function Fou between the hospital air-conditioning system performance index PerH and the external factor vector group OUve is comprehensively generated.

8. The intelligent air conditioning control method for a hospital according to claim 7, characterized in that: The specific process of building a power demand forecasting model is as follows: Set the data prediction period Ty, take the data prediction period Ty as the time length, and extract the two time nodes t1 and t2 before and after the current time node t0; The predicted values ​​of the external factor parameters at time node t2 are obtained through the meteorological platform; the predicted values ​​of the internal factor parameters are obtained through periodic analysis of historical data, and the internal factor parameters at time node t1 are used as the predicted values ​​of the internal factor parameters at time node t2; The predicted values ​​of the external factor parameters and the predicted values ​​of the internal factor parameters are integrated and marked as a predicted number set of application scenario information; Substitute the predicted value of the external factor parameter into the correlation influence function Fou to obtain the electricity external demand index DEou, and use the electricity external demand index DEou to evaluate the predicted influence of the external factor parameter on the hospital air conditioning system performance index PerH; Substitute the predicted value of the internal factor parameter into the correlation influence function Fin to obtain the internal power demand index DEin, and use the internal power demand index DEin to evaluate the predicted influence of the internal factor parameters of the medical area a on the air conditioning operation performance of the medical area; By combining the electricity external demand index DEou and the electricity internal demand index DEin, the electricity forecast demand coefficient DEeng is obtained; An evaluation interval of the power forecast demand coefficient DEeng is set, and any evaluation interval is marked as δg. When the power forecast demand coefficient DEeng is located in the evaluation interval δg, a g-level forecast management signal is generated.

9. An intelligent air conditioning system for a hospital, characterized in that: The system comprises an information monitoring module, a performance analysis module, a demand prediction module and a signal management module, wherein the information monitoring module, the performance analysis module, the demand prediction module and the signal management module are communicatively connected with each other, and the system applies a hospital intelligent air conditioning control method as described in any one of claims 1 to 8 above; The information monitoring module is used to collect air-conditioning operation information and application scenario information; The performance analysis module is used to build system performance evaluation models and performance impact analysis models, and output real-time control signals; The demand forecasting module is used to build a power demand forecasting model and output forecasting management signals; The signal management module is used to receive signals and perform corresponding control management operations.

Images