An electrical control system of artificial intelligence

Abstract

This invention discloses an artificial intelligence-based electrical control system, relating to the field of electrical control system technology. It includes a data acquisition module, a data analysis module, a turbidity prediction model generation module, a judgment module, a prediction module, and a control module. It solves the technical problem of being unable to predict the future trend of pool water turbidity and the time it takes for turbidity to reach a threshold based on the pool's current water volume and turbidity. The invention establishes a pool turbidity prediction model by analyzing historical pool water turbidity, water volume, and personnel data. This model predicts the future trend of pool water turbidity and the time it takes for turbidity to reach a threshold, marking the predicted duration as the threshold-exceeding prediction duration. Based on this threshold-exceeding prediction duration, the time range for disinfectant application is determined, and then the control module controls the disinfectant application within this time range.

Description

Technical Field

[0001] This invention relates to the field of electrical control system technology, and more specifically to an artificial intelligence-based electrical control system. Background Technology

[0002] Electrical systems are closely related to our daily lives. With the maturity of artificial intelligence technology, it has been applied to all aspects of electrical systems, effectively contributing to improving the quality of our daily lives; and with the development of society and science and technology, the application areas of artificial intelligence technology are expanding.

[0003] Patent publication number CN112835398A discloses an artificial intelligence electrical control system, including an AI control system, a swimming pool system, an operation display system, a network communication module, and an alarm system. The swimming pool system includes a swimming pool, a filtration chamber, electrical equipment, and an electrical sensing system. The electrical equipment includes a circulating water pump and a water injection control valve. The circulating water pump and the AI ​​control system are connected via data communication. A drain outlet is located at the bottom of the swimming pool, connected to a drain pipe system, which is connected to the circulating water pump. The circulating water pump is connected to the filtration chamber. This invention rationally sets the circulation speed of the circulating water pump according to the number of swimmers, thereby saving energy while ensuring water quality and providing safety for swimmers. Simultaneously, by detecting people lying at the bottom of the pool, it can promptly detect potential drowning hazards in the swimming pool, enabling search and rescue and alarm functions, thus improving swimmer safety.

[0004] However, while the above-mentioned solution can detect the cleanliness of the swimming pool water using a cleanliness sensor and adjust the circulation speed of the circulating water pump through an AI control system to maintain the cleanliness of the swimming pool water, it cannot predict the trend of turbidity changes in the pool water and the time when the turbidity reaches the threshold based on the current water volume and turbidity of the pool. When the turbidity of the pool water exceeds the threshold, the addition of disinfectant to the pool will result in untimely cleaning and disinfection of the pool water, causing the pool water to temporarily exceed the standard value. Based on this, an artificial intelligence electrical control system is proposed. Summary of the Invention

[0005] The purpose of this invention is to provide an artificial intelligence-based electrical control system that solves the technical problem of being unable to predict the trend of turbidity changes and the time when turbidity reaches the threshold in the pool water in the future based on the existing water volume and turbidity of the pool, resulting in untimely cleaning and disinfection of the pool water and causing the pool water to temporarily exceed the standard value.

[0006] The objective of this invention can be achieved through the following technical solutions: An artificial intelligence-based electrical control system includes: The data acquisition module is used to acquire data on pool water turbidity, pool water volume, and personnel in the pool within a time range n1, and send it to the data analysis module. The personnel data includes the status value of the number of people in the pool and the duration of the corresponding status value. The data analysis module is used to divide the time range n1 equally into x standard time periods T1, then analyze the pool personnel data within the x standard time periods, thereby obtaining the personnel heat values ​​corresponding to the x standard time periods, and sending them to the turbidity prediction model generation module. The turbidity prediction model generation module is used to acquire and analyze the human heat value and pool water turbidity corresponding to x standard time periods, generate a turbidity prediction model based on the analysis results, and send the turbidity prediction model to the prediction module. The determination module is used to acquire and analyze the data of personnel in the pool within the time range n2, and generate a prediction signal based on the analysis results, and output it to the prediction module. The prediction module receives the prediction signal and acquires and analyzes the data of people in the pool within a time range n2. Based on the analysis results, it obtains the heat value of people corresponding to time range n2. At the same time, it acquires the turbidity and water volume of the pool water within time range n2. The heat value of people, turbidity and water volume of the pool water corresponding to time range n2 are input into the turbidity prediction model for calculation, thereby obtaining the corresponding over-threshold prediction duration, and the over-threshold prediction duration is input into the control module. The control module is used to acquire the predicted duration of exceeding the threshold and determine the time range for disinfectant administration based on the predicted duration of exceeding the threshold.

[0007] As a further aspect of the present invention: the specific method for obtaining the population heat values ​​corresponding to x standard time periods is as follows: B1: Divide the time range n1 into x standard time periods equally, and select one standard time period as the target time period. Here, x is the number of standard time periods, and x≥1. B2: Label the status values ​​of the number of people in the pool in the target time period as R1, R2, ..., Ro, respectively, where o represents the number of people corresponding to the status value of the number of people in the pool in the target time period, and o≥1; The durations of the state values ​​corresponding to the number of people in the target time period are labeled as T1, T2, ..., To; B3: Through formula , calculate the population heat value M1 corresponding to the target time period, where S is the effective area of ​​the swimming pool; B4: Repeat steps B1-B3 to obtain the population heat values ​​corresponding to x standard time periods, and label them as M1, M2, ..., Mx in sequence.

[0008] As a further aspect of the present invention: the effective area of ​​the swimming pool S = A1×L + A2×W, where L and W are the length and width of the swimming pool, respectively. The length and width of the swimming pool are both measured manually, and A1 and A2 are both measurement correction coefficients of the swimming pool.

[0009] As a further aspect of the present invention, the specific steps for generating the turbidity prediction model are as follows: C1: Obtain the turbidity of the pool water for x standard time periods and label them as HZ1, HZ2, ..., HZx respectively; Obtain the water storage volume of the pool for x standard time periods and label them as V1, V2, ..., Vx respectively; C2: Modeling is done using a multiple linear regression model. The general form of a multiple linear regression model is: Where HZa is the pool water turbidity corresponding to the standard time period, Ma is the human heat value corresponding to the standard time period, Tt is the standard duration corresponding to the standard time period, Va is the pool water storage capacity, β0, β1 and β2 are regression coefficients, ε is the error term, and here x≥a≥1; C3: Input the pool water turbidity HZ1, HZ2, ..., HZx corresponding to x standard time periods, the pool water storage volume V1, V2, ..., Vx, and the personnel heat values ​​M1, M2, ..., Mx into the multiple linear regression model in step C2 for regression analysis, thereby obtaining the corresponding values ​​of the project coefficients β0, β1, and β2, and labeling them as β3, β4, and β5 respectively. At the same time, substitute the pool water turbidity threshold HY into the model to obtain the pool water turbidity prediction model. Here, HY represents the turbidity threshold of the pool water.

[0010] As a further aspect of the present invention: Va = A2 × (S × Ga), where Ga is the corresponding water level height of the pool within a standard time period, the pool water level height is obtained by a water level sensor installed in the pool, and A2 is the deviation coefficient.

[0011] As a further aspect of the present invention, the specific steps for determining the generation of the prediction signal are as follows: D1: Label the pool population status values ​​within the time range n2 as U1, U2, ..., Uj, where j represents the population corresponding to the pool population status value within the time range n2, and j≥1; The durations of the state values ​​corresponding to the number of people within the time range n2 are labeled as H1, H2, ..., Hj, respectively; D2: Obtain all the number of people state values ​​Ui that satisfy the condition Ui≥Uy from U1, U2, ..., Uj. At the same time, obtain the total duration of the state value corresponding to all the number of people state values ​​that satisfy the condition Ui≥Uy and mark it as P1. When P1 < Hy, no processing is performed. When P1 ≥ Hy, a prediction signal is generated. Here, Uy and Hy are preset values, and j ≥ i ≥ 1.

[0012] As a further aspect of the present invention, the specific method for obtaining the prediction duration beyond the threshold is as follows: E1: After obtaining the prediction signal, use the formula Calculate the personnel heat value Ms corresponding to the time range n2, and obtain the pool water storage volume corresponding to the time range n2 and mark it as Vs; E2: Input Ms and Vs into the pool water turbidity prediction model By performing calculations, the corresponding value of Tt can be obtained, and it is marked as the over-threshold prediction duration TY.

[0013] As a further aspect of the present invention, the specific method for determining the delivery time range is as follows: The time point when the prediction signal is generated is obtained and marked as TD. Then, the delivery time range [TD+K1, TD+TY-K2] is generated by combining the prediction duration TY and TD, where K1 and K2 are preset values.

[0014] The beneficial effects of this invention are: This invention establishes a pool turbidity prediction model by analyzing historical pool water turbidity, water volume, and personnel data. This model predicts the future trend of pool water turbidity and the duration of turbidity reaching a threshold over a future period, marking the predicted duration as the threshold exceedance prediction duration. Based on this threshold exceedance prediction duration, the time range for disinfectant administration is determined. Then, a control module controls the disinfectant administration within this time range. This ensures timely disinfection of the pool, maintaining pool water turbidity within the threshold for a long period and preventing brief instances of turbidity exceeding the threshold, thus further guaranteeing the stability and safety of the pool water quality. Attached Figure Description

[0015] The invention will now be further described with reference to the accompanying drawings.

[0016] Figure 1 This is a schematic diagram of the system structure of an artificial intelligence electrical control system according to the present invention; Figure 2 This is a schematic diagram of the structure of an artificial intelligence electrical control system according to the present invention. Detailed Implementation

[0017] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0018] Example 1 Please see Figures 1-2 As shown, the present invention is an artificial intelligence electrical control system, comprising a data acquisition module, a data analysis module, a turbidity prediction model generation module, a judgment module, a prediction module, and a control module; The data acquisition module is used to acquire data on pool water turbidity, pool water volume, and personnel in the pool within a time range n1, and send it to the data analysis module. The personnel data includes the status value of the number of people in the pool and the duration of the corresponding status value. The pool occupancy status value refers to the number of swimmers present in the swimming pool, which can be acquired and counted through a people flow monitoring system or cameras. The status value duration refers to the duration corresponding to the number of swimmers present in the swimming pool, which is counted and recorded by a timing module installed in the people flow monitoring system or cameras. The pool water turbidity refers to the average turbidity of the pool water within the corresponding time period, which is monitored and acquired by a turbidity sensor installed in the pool. The pool water volume refers to the average volume of water in the pool within the corresponding time period. Here, the time range n1 refers to the pool usage time of 8 hours counting backward from the moment the data is acquired. Data within the current time frame of data acquisition is not included. n1 = 8 hours. The data analysis module is used to equally divide the time range n1 into x standard time periods, then analyze the pool personnel data within each x standard time period to obtain the personnel heat value corresponding to each x standard time period, and send it to the turbidity prediction model generation module. The specific method for obtaining the personnel heat value corresponding to each x standard time period is as follows: B1: Divide the time range n1 into x standard time periods equally, and select one standard time period as the target time period. Here, x is the number of standard time periods, and x≥1. B2: Label the status values ​​of the number of people in the pool in the target time period as R1, R2, ..., Ro, respectively, where o represents the number of people corresponding to the status value of the number of people in the pool in the target time period, and o≥1; The durations of the state values ​​corresponding to the number of people in the target time period are labeled as T1, T2, ..., To; B3: Through formula , calculate the population heat value M1 corresponding to the target time period, where S is the effective area of ​​the swimming pool; The effective area of ​​the swimming pool is S = A1 × L + A2 × W, where L and W are the length and width of the pool, respectively. Here, the pool is assumed to be rectangular, and other shapes are not considered. The length and width of the pool are measured manually. A1 and A2 are measurement correction coefficients for the pool, and the specific values ​​are determined by relevant staff based on experience. B4: Repeat steps B1-B3 to obtain the population heat values ​​corresponding to x standard time periods, and label them as M1, M2, ..., Mx in sequence; The turbidity prediction model generation module is used to acquire and analyze the human heat index and pool water turbidity corresponding to x standard time periods, generate a turbidity prediction model based on the analysis results, and send the turbidity prediction model to the prediction module. The specific steps for generating the turbidity prediction model are as follows: C1: Obtain the turbidity of the pool water for x standard time periods and label them as HZ1, HZ2, ..., HZx respectively; Obtain the water storage volume of the pool for x standard time periods and label them as V1, V2, ..., Vx respectively; C2: Modeling is done using a multiple linear regression model. The general form of a multiple linear regression model is: Where HZa is the pool water turbidity corresponding to the standard time period, Ma is the human heat value corresponding to the standard time period, Tt is the standard duration corresponding to the standard time period, Va is the pool water storage capacity, which refers to the average volume of the pool water within the corresponding standard time period, β0, β1 and β2 are all regression coefficients, ε is the error term, and the specific value of ε is determined by relevant staff based on experience. Here, x≥a≥1. Va = A3 × (S × Ga), where Ga is the corresponding water level height of the pool during the standard time period. The pool water level height is obtained by a water level sensor installed in the pool. A3 is the deviation coefficient, and the specific value is determined by relevant staff based on experience. C3: Input the pool water turbidity HZ1, HZ2, ..., HZx corresponding to x standard time periods, the pool water storage volume V1, V2, ..., Vx, and the personnel heat values ​​M1, M2, ..., Mx into the multiple linear regression model in step C2 for regression analysis, thereby obtaining the corresponding values ​​of the project coefficients β0, β1, and β2, and labeling them as β3, β4, and β5 respectively. At the same time, substitute the pool water turbidity threshold HY into the model to obtain the pool water turbidity prediction model. Here, HY is the turbidity threshold of the pool water, which is determined by relevant workers in accordance with relevant regulations; The determination module is used to acquire and analyze the data of personnel in the pool within a time range of n2, and generate a prediction signal based on the analysis results, and output it to the prediction module. The specific steps for determining and generating the prediction signal are as follows: The time range n2 is the period 15 minutes prior to the current time; data within the current time frame is not included. D1: Label the pooled population status values ​​in the personnel data within the time range n2 as U1, U2, ..., Uj, where j represents the number of people corresponding to the pooled population status values ​​within the time range n, and j≥1; The durations of the state values ​​corresponding to the number of people within the time range n2 are labeled as H1, H2, ..., Hj, respectively; D2: Obtain all the number of people state values ​​Ui that satisfy the condition Ui≥Uy from U1, U2, ..., Uj. At the same time, obtain the total duration of the state value corresponding to all the number of people state values ​​Ui that satisfy the condition Ui≥Uy, and mark it as P1. When P1<Hy, no processing is performed. When P1≥Hy, a prediction signal is generated. Here, Uy and Hy are preset values, which are determined by relevant staff, and j≥i≥1. The prediction module receives the prediction signal and analyzes the data on people in the pool within a time range n2. Based on the analysis results, it obtains the heat value of the people corresponding to time range n2. Simultaneously, it acquires the turbidity and water volume of the pool water within time range n2. These data are then input into the turbidity prediction model for calculation, thereby obtaining the corresponding over-threshold prediction duration. This over-threshold prediction duration is then input into the control module. The specific method for obtaining the over-threshold prediction duration is as follows: E1: After obtaining the prediction signal, use the formula Calculate the personnel heat value Ms corresponding to the time range n2, and obtain the pool water storage volume corresponding to the time range n2 and mark it as Vs; E2: Input Ms and Vs into the pool water turbidity prediction model The calculation is performed to obtain the value corresponding to Tt, and it is marked as the over-threshold prediction time TY, that is, the time required for the turbidity of the pool water to reach the turbidity threshold HY when the current personnel heat value Ms and the pool water storage volume are obtained and marked as Vs. The control module is used to acquire the predicted duration TY of exceeding the threshold and determine the disinfectant dosing time range based on the predicted duration TY. The specific method for determining the dosing time range is as follows: The time point when the prediction signal is generated is acquired and marked as TD. Then, the delivery time range [TD+K1, TD+TY-K2] is generated by combining the prediction duration TY and TD, where K1 and K2 are preset values ​​and the specific values ​​are determined by relevant staff based on experience. The disinfectant is administered within the specified time range [TD+K1, TD+TY-K2] by the control module. This ensures timely disinfection of the pool, keeps the turbidity of the pool water within the threshold for a long period, and avoids temporary exceedance of the threshold, thus further guaranteeing the hygiene and safety of the pool water.

[0019] Example 2 As a second embodiment of the present invention, in specific implementation, compared with embodiments one and two, the technical solution of this embodiment is to combine the solutions of embodiments one and two. The difference from embodiments one and two lies only in this embodiment: The system monitors the water temperature in the pool through a temperature monitoring module. When the water temperature in the pool is lower than the preset temperature range, the system will automatically start the hot water adding device and add hot water to the pool through the hot water inlet. During the process of hot water supply to the pool through the hot water inlet, a human detection sensor detects whether there are swimmers near the hot water inlet and marks the distance between them and the hot water inlet as K1. When K1 ≥ Ky, no action is taken; when K1 < Ky, hot water supply is stopped, and an alarm signal is generated to prevent swimmers from being scalded by hot water and reduce the possibility of scalding accidents. The alarm message is generated to alert relevant personnel that someone is approaching the hot water inlet and to warn swimmers who are near the hot water inlet to avoid being scalded by hot water.

[0020] Example 3 As a third embodiment of the present invention, in specific implementation, compared with embodiments one and two, the technical solution of this embodiment is to combine the solutions of embodiments one and two.

[0021] The working principle of this invention is as follows: Data on pool water turbidity, pool water volume, and personnel within the pool are acquired within a time range n1. This data is then analyzed to obtain personnel heat values ​​corresponding to x standard time periods. The personnel heat values ​​and pool water turbidity corresponding to these x standard time periods are acquired and analyzed to generate a turbidity prediction model. Similarly, data on personnel within the pool within a time range n2 are acquired and analyzed, and a prediction signal is generated based on the analysis results. The personnel heat values, pool water turbidity, and pool water volume corresponding to time range n2 are then input into the turbidity prediction model for calculation. The turbidity prediction model predicts the trend of pool water turbidity changes over a future period and determines the time required for turbidity to reach a threshold, marking this as the threshold-exceeding prediction time. This threshold-exceeding prediction time is input into the control module to determine the disinfectant dosing time range. The control module then controls the disinfectant dosing within this time range to ensure the stability and safety of the pool water quality.

[0022] The above formulas are all dimensionless calculations. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0023] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. An artificial intelligence-based electrical control system, characterized in that, include: The data acquisition module is used to acquire data on pool water turbidity, pool water volume, and personnel in the pool within a time range n1, and send it to the data analysis module. The personnel data includes the status value of the number of people in the pool and the duration of the corresponding status value. The data analysis module is used to divide the time range n1 equally into x standard time periods T1, then analyze the pool personnel data within the x standard time periods, thereby obtaining the personnel heat values ​​corresponding to the x standard time periods, and sending them to the turbidity prediction model generation module. The turbidity prediction model generation module is used to acquire and analyze the human heat value and pool water turbidity corresponding to x standard time periods, generate a turbidity prediction model based on the analysis results, and send the turbidity prediction model to the prediction module. The determination module is used to acquire and analyze the data of personnel in the pool within the time range n2, and generate a prediction signal based on the analysis results, and output it to the prediction module. The prediction module receives the prediction signal and acquires and analyzes the data of people in the pool within a time range n2. Based on the analysis results, it obtains the heat value of people corresponding to time range n2. At the same time, it acquires the turbidity and water volume of the pool water within time range n2. The heat value of people, turbidity and water volume of the pool water corresponding to time range n2 are input into the turbidity prediction model for calculation, thereby obtaining the corresponding over-threshold prediction duration, and the over-threshold prediction duration is input into the control module. The control module is used to acquire the predicted duration of exceeding the threshold and determine the time range for disinfectant administration based on the predicted duration of exceeding the threshold.

2. The artificial intelligence electrical control system according to claim 1, characterized in that, The specific method for obtaining the popularity values ​​of people corresponding to x standard time periods is as follows: B1: Divide the time range n1 into x standard time periods equally, and select one standard time period as the target time period. Here, x is the number of standard time periods, and x≥1. B2: Label the status values ​​of the number of people in the pool in the target time period as R1, R2, ..., Ro, respectively, where o represents the number of people corresponding to the status value of the number of people in the pool in the target time period, and o≥1; The durations of the state values ​​corresponding to the number of people in the target time period are labeled as T1, T2, ..., To; B3: Through formula , calculate the population heat value M1 corresponding to the target time period, where S is the effective area of ​​the swimming pool; B4: Repeat steps B1-B3 to obtain the population heat values ​​corresponding to x standard time periods, and label them as M1, M2, ..., Mx in sequence.

3. The artificial intelligence electrical control system according to claim 2, characterized in that, The effective area of ​​the swimming pool is S = A1 × L + A2 × W, where L and W are the length and width of the pool, respectively. The length and width of the pool are measured manually, and A1 and A2 are measurement correction coefficients for the pool.

4. The artificial intelligence electrical control system according to claim 3, characterized in that, The specific steps for generating a turbidity prediction model are as follows: C1: Obtain the turbidity of the pool water for x standard time periods and label them as HZ1, HZ2, ..., HZx respectively; Obtain the water storage volume of the pool for x standard time periods and label them as V1, V2, ..., Vx respectively; C2: Modeling is done using a multiple linear regression model. The general form of a multiple linear regression model is: Where HZa is the pool water turbidity corresponding to the standard time period, Ma is the human heat value corresponding to the standard time period, Tt is the standard duration corresponding to the standard time period, Va is the pool water storage capacity, β0, β1 and β2 are regression coefficients, ε is the error term, and here x≥a≥1; C3: Input the pool water turbidity HZ1, HZ2, ..., HZx corresponding to x standard time periods, the pool water storage volume V1, V2, ..., Vx, and the personnel heat values ​​M1, M2, ..., Mx into the multiple linear regression model in step C2 for regression analysis, thereby obtaining the corresponding values ​​of the project coefficients β0, β1, and β2, and labeling them as β3, β4, and β5 respectively. At the same time, substitute the pool water turbidity threshold HY into the model to obtain the pool water turbidity prediction model. Here, HY represents the turbidity threshold of the pool water.

5. An artificial intelligence electrical control system according to claim 4, characterized in that, Va = A3 × (S × Ga), where Ga is the corresponding water level height of the pool during the standard time period. The pool water level height is obtained by a water level sensor installed in the pool, and A3 is the deviation coefficient.

6. An artificial intelligence electrical control system according to claim 5, characterized in that, The specific steps for determining the generation of the prediction signal are as follows: D1: Label the pool population status values ​​within the time range n2 as U1, U2, ..., Uj, where j represents the population corresponding to the pool population status value within the time range n2, and j≥1; The durations of the state values ​​corresponding to the number of people within the time range n2 are labeled as H1, H2, ..., Hj, respectively; D2: Obtain all the number of people state values ​​Ui that satisfy the condition Ui≥Uy from U1, U2, ..., Uj. At the same time, obtain the total duration of the state value corresponding to all the number of people state values ​​that satisfy the condition Ui≥Uy and mark it as P1. When P1 < Hy, no processing is performed. When P1 ≥ Hy, a prediction signal is generated. Here, Uy and Hy are preset values, and j ≥ i ≥ 1.

7. An artificial intelligence electrical control system according to claim 6, characterized in that, The specific method for obtaining the prediction duration beyond the threshold is as follows: E1: After obtaining the prediction signal, use the formula Calculate the personnel heat value Ms corresponding to the time range n2, and obtain the pool water storage volume corresponding to the time range n2 and mark it as Vs; E2: Input Ms and Vs into the pool water turbidity prediction model By performing calculations, the corresponding value of Tt can be obtained, and it is marked as the over-threshold prediction duration TY.

8. An artificial intelligence electrical control system according to claim 7, characterized in that, The specific method for determining the time range for distribution is as follows: The time point when the prediction signal is generated is obtained and marked as TD. Then, the delivery time range [TD+K1, TD+TY-K2] is generated by combining the prediction duration TY and TD, where K1 and K2 are preset values.

Images