Residential water time-of-use probability and flow prediction method and apparatus

Abstract

This invention provides a method for predicting the time-series probability and flow rate of residential water use, comprising: acquiring water use information, including the number of households, number of water users, measured flow rate, and total equivalent of sanitary fixtures; obtaining the actual time-series probability of residential water use based on the measured flow rate and constructing a residential water use time-series probability database; constructing a correlation model between the total equivalent of sanitary fixtures and the time-series water output probability; obtaining the time-series water output probability corresponding to the total equivalent of sanitary fixtures for the project to be predicted at each time point; obtaining the converted total equivalent of sanitary fixtures through a sanitary fixtures conversion model; constructing a time-series flow rate calculation model and setting a dynamic water supply guarantee rate to obtain the number of sanitary fixtures simultaneously used at each time point; and calculating the time-series flow rate based on the number of sanitary fixtures simultaneously used at each time point and the rated flow rate corresponding to the sanitary fixtures. This invention can accurately obtain the time-series flow rate of residential water use.

Description

Technical Field

[0001] This invention belongs to the field of intelligent water supply control, and specifically relates to a method and device for predicting the timing probability and flow rate of residential water use. Background Technology

[0002] Traditional variable frequency (VFD) and booster pump systems in my country are designed based on the second-by-second flow rate of secondary water supply buildings, resulting in energy consumption that is 2 to 10 times higher than the average energy consumption of water companies. The optimal energy consumption standard for secondary water supply energy conservation is 0.64 kW / m³.MPa, while field test data shows 2.0 to 3.0 kW / m³.MPa. This is because pump control relies solely on traditional system pressure to control the VFD pumps, leading to high pump energy consumption. Existing water supply methods cannot accurately reflect the probability of residential water usage, making it impossible to achieve energy conservation goals due to the high energy consumption of existing pumps. Summary of the Invention

[0003] To address the shortcomings of existing technologies, this invention provides a method and apparatus for predicting the temporal probability and flow rate of residential water use, which can accurately obtain the temporal flow rate of residential water use.

[0004] This invention provides a method for predicting the temporal probability and flow rate of residential water use, comprising:

[0005] Obtain water usage information, which includes the number of households, the number of people using water, the actual flow rate, and the total equivalent of sanitary fixtures;

[0006] Based on the measured flow rate, the actual residential water consumption time series probability is obtained and a residential water consumption time series probability database is constructed.

[0007] A correlation model between the total number of equivalent sanitary fixtures and the time-series water output probability is constructed using the aforementioned residential water use time-series probability database;

[0008] The time-series water discharge probability corresponding to the total number of equivalent sanitary fixtures and the time-series water discharge probability correlation model is obtained for each time period.

[0009] Input the total equivalent of sanitary appliances for the project to be predicted into the sanitary appliance equivalent conversion model to obtain the converted total equivalent of sanitary appliances;

[0010] A time-series flow calculation model was constructed and a dynamic water supply guarantee rate was set to obtain the equivalent number of sanitary fixtures used simultaneously at each time point.

[0011] The time-series flow rate is obtained based on the number of sanitary fixtures used simultaneously at each time point and the rated flow rate corresponding to the sanitary fixture equivalent.

[0012] Furthermore, the water usage information also includes: the rated flow rate of the sanitary fixture equivalent and real-time flow data of the residence.

[0013] Furthermore, the water usage database includes one or more of the following: number of water users, actual number of residents in a residence at a certain time, total number of sanitary fixtures equivalent, time-series water output probability of sanitary fixtures, influence coefficient of number of water users on time-series water output probability, influence coefficient of total number of sanitary fixtures equivalent on time-series water output probability, minimum value of water supply equivalent for sanitary fixtures installed in a residence, and greatest common divisor of water supply equivalent for sanitary fixtures installed in a residence.

[0014] Furthermore, the formula for calculating the actual residential water usage time-series probability is as follows:

[0015]

[0016] In the formula: The time-series probability of actual residential water usage is expressed in % (%). The unit of the real-time residential flow data is L / s; This indicates the total equivalent of the sanitary fixtures; This indicates the rated flow rate of one sanitary fixture equivalent.

[0017] Furthermore, the correlation model between the total number of equivalent sanitary fixtures and the time-series water output probability includes: a first correlation model, a second correlation model, and a third correlation model, wherein the first correlation model is constructed using the residential water use time-series probability database, and specifically includes:

[0018]

[0019] In the formula: The sequential probability of simultaneous outflow of water equivalent from residential sanitary fixtures is expressed in % (%). express The actual number of residents in the residential building at any given time; This indicates the total equivalent of the sanitary fixtures; This represents the coefficient representing the influence of the number of water users on the probability of water discharge over time. This represents the influence coefficient of the total equivalent number of sanitary fixtures on the probability of time-series water discharge.

[0020] Furthermore, the second correlation model specifically includes the average probability of water discharge and the confidence interval;

[0021] Wherein, the average water discharge probability The calculation formula is as follows:

[0022]

[0023] In the formula, Indicates the number of days;

[0024] The confidence interval The calculation formula is as follows:

[0025] First, based on the average water output probability... Calculate the standard deviation of the sample :

[0026]

[0027] Recalculate the standard error SE:

[0028]

[0029] Next, calculate the critical value ∆:

[0030]

[0031] In the formula: Indicates degrees of freedom. ; This indicates the significance level corresponding to the confidence level.

[0032] Finally, the confidence interval is obtained.

[0033]

[0034]

[0035] In the formula: This represents the lower limit of the confidence interval; This represents the upper limit of the confidence interval.

[0036] Furthermore, the third correlation model is obtained by fitting the second correlation model. The third correlation model reflects the correspondence between the total number of equivalent sanitary appliances and the probability of water use at different times, specifically including:

[0037] .

[0038] Further, the total number of sanitary ware equivalents for the project to be predicted is input into the sanitary ware equivalent conversion model to obtain the converted total number of sanitary ware equivalents, specifically including:

[0039] Using the conversion coefficient K of the water supply equivalent of the sanitary fixture, the equivalent conversion model of the sanitary fixture is constructed to obtain:

[0040]

[0041] In the formula, N represents the total number of converted sanitary fixture equivalents, and K represents the conversion coefficient of the water supply equivalent of the sanitary fixtures. This represents the total number of sanitary fixtures equivalent for the project to be predicted;

[0042] The conversion factor for the water supply equivalent of the sanitary fixtures can be calculated using the following formula:

[0043]

[0044] In the formula: This represents the minimum water supply equivalent for the sanitary fixtures installed in the residence. This represents the greatest common divisor of the water supply equivalents of the sanitary fixtures installed in the residence.

[0045] Furthermore, constructing the time-series flow calculation model and obtaining the equivalent number of sanitary fixtures used simultaneously specifically includes:

[0046] First calculate for all The total number of converted sanitary fixtures equivalents, any The probability equations for simultaneous use are shown below:

[0047]

[0048] In the formula: This indicates that at time t, The total number of converted sanitary fixtures used simultaneously The probability of one equivalent; Indicates in In the total equivalent of each sanitary fixture, each time there is The number of combinations in which each equivalent can be used simultaneously. ;

[0049] Based on this calculation, at time t, The total number of converted sanitary ware equivalents simultaneously uses 0, 1, 2, ... The probability of using a number of sanitary fixtures simultaneously;

[0050] Finally, the equivalent number of sanitary fixtures used simultaneously is determined by the following inequality. :

[0051]

[0052] In the formula: —This refers to the water supply guarantee rate.

[0053] Furthermore, the time-series flow rate includes water consumption:

[0054] The water consumption is obtained based on the equivalent number of sanitary fixtures used simultaneously. :

[0055]

[0056] In the formula: This represents the rated flow rate of one sanitary fixture, in L / s.

[0057] Furthermore, the method for predicting the temporal probability and flow rate of residential water use also includes:

[0058] An evaluation model is constructed, and the predictive performance of water use probability and time-series flow rate is evaluated based on the evaluation model.

[0059] In another aspect, the present invention provides a residential water use time-series probability and flow prediction device, which is equipped with the above-mentioned residential water use time-series probability and flow prediction method, including:

[0060] The information acquisition module is used to acquire water usage information, which includes the number of households, the number of water users, the measured flow rate, and the total equivalent number of sanitary appliances.

[0061] The database construction module is used to obtain the actual residential water use time series probability based on the measured flow rate and construct a residential water use time series probability database.

[0062] The association model construction module is used to construct an association model between the total number of equivalent sanitary appliances and the time-series water output probability using the residential water use time-series probability database.

[0063] The time-series water output probability module is used to obtain the time-series water output probability corresponding to the total number of equivalent sanitary fixtures of the project to be predicted at each time point based on the correlation model between the total number of equivalent sanitary fixtures and the time-series water output probability.

[0064] The equivalent total number of sanitary appliances conversion module inputs the equivalent total number of sanitary appliances of the project to be predicted into the sanitary appliance equivalent conversion model to obtain the converted equivalent total number of sanitary appliances;

[0065] The time-series flow meter model building module is used to build a time-series flow calculation model and set a dynamic water supply guarantee rate to obtain the equivalent number of sanitary fixtures used simultaneously at each time point.

[0066] The prediction result output module is used to calculate the time-series flow rate based on the number of sanitary fixtures used simultaneously at each time point and the rated flow rate corresponding to the sanitary fixture equivalent.

[0067] Furthermore, a residential water use time-series probability and flow prediction device also includes:

[0068] The evaluation model building module is used to build an evaluation model and evaluate the prediction effect of water use probability and time series flow based on the evaluation model.

[0069] In another aspect, the present invention provides a computer-readable storage medium for storing a computer program that, when executed by a processor, implements the above-described method for predicting the timing probability and flow rate of residential water use.

[0070] In another aspect, the present invention provides a computer program product, wherein the computer program product stores a program or instructions, which, when executed by a processor, implement the above-described method for predicting the timing probability and flow rate of residential water use.

[0071] As can be seen from the above solutions, the advantages of the present invention are:

[0072] By acquiring water usage information including the number of households, number of water users, measured flow rate, and total equivalent of sanitary fixtures, the system uses measured water usage data as the basis for calculating water usage probability and time-series flow rate, thus improving the accuracy of these calculations. Based on the measured flow rate, the system obtains the actual residential water usage time-series probability and constructs a residential water usage time-series probability database, providing a basis for subsequent calculations of water usage probability and time-series flow rate, and ensuring the accuracy of these calculations. This method constructs a correlation model between the total number of sanitary fixture equivalents and the time-series water output probability using a residential water consumption time-series probability database. Based on this model, the time-series water output probability corresponding to the total number of sanitary fixture equivalents for the project under prediction at each time point is obtained. Next, the total number of sanitary fixture equivalents for the project under prediction is input into a sanitary fixture equivalent conversion model to obtain the converted total number of sanitary fixture equivalents. Then, a time-series flow calculation model is constructed, and a dynamic water supply guarantee rate is set to obtain the number of sanitary fixture equivalents used simultaneously at each time point. Finally, the time-series flow rate is calculated based on the number of sanitary fixture equivalents used simultaneously at each time point and the corresponding rated flow rate, ensuring the accuracy of the prediction results and thus meeting the requirements of precise and efficient control technology for secondary water supply pumps, thereby achieving energy conservation. This method can calculate the real-time flow changes in residential buildings based on the number of sanitary fixture equivalents used simultaneously, meeting the requirements of intelligent and refined precise and efficient control technology for secondary water supply pumps and achieving energy conservation. Attached Figure Description

[0073] Figure 1 A flowchart illustrating a residential water use time-series probability and flow prediction method provided by the present invention;

[0074] Figure 2 This is a flowchart illustrating another method for predicting the time series probability and flow rate of residential water use.

[0075] Figure 3 This is a flowchart illustrating another method for predicting the time series probability and flow rate of residential water use.

[0076] Figure 4 This is a probability diagram of the water supply equivalent usage within the monitoring range of water meter No. 1.

[0077] Figure 5 This is a histogram curve showing the probability distribution of water usage for water meter #1.

[0078] Figure 6 The water consumption calculation results are shown in the figure when the water supply guarantee rate is 75%.

[0079] Figure 7 The graph shows the water consumption calculation results when the water supply guarantee rate is 60%.

[0080] Figure 8 The water consumption calculation results are shown in the figure when the water supply guarantee rate is 65% and the equivalent conversion factor of sanitary ware K=4.

[0081] Figure 9 The graph shows the relationship between the average outflow probability of water supply equivalent and the total number of sanitary fixtures equivalent at time 0:05.

[0082] Figure 10 The graph shows the relationship between the average outflow probability of water supply equivalent and the total number of sanitary fixtures equivalent at time 0:10.

[0083] Figure 11 The graph shows the relationship between the average outflow probability of water supply equivalent and the total number of sanitary fixtures equivalent at time 0:15.

[0084] Figure 12 The graph shows the relationship between the average outflow probability of water supply equivalent and the total number of sanitary fixtures equivalent at time 0:20.

[0085] Figure 13 A graph showing the relationship between the maximum average outflow probability of water supply equivalent and the total number of sanitary fixtures equivalent;

[0086] Figure 14 The outflow probability and 95% confidence interval for the total equivalent of 79.5 sanitary fixtures at various times;

[0087] Figure 15 The graph shows the predicted water usage data for water meter No. 3 on Monday, with a confidence level of 95%.

[0088] Figure 16 The average outflow probability variation curve and operating condition classification result diagram of water meter No. 3 in the database;

[0089] Figure 17 The forecast diagram for Monday's water usage of water meter No. 3;

[0090] Figure 18 This is a diagram showing the actual water usage of water meter No. 3 on Monday.

[0091] Figure 19 A schematic diagram of a residential water use time-series probability and flow prediction device;

[0092] Figure 20 This is a schematic diagram of another residential water use time-series probability and flow prediction device.

[0093] In the attached figures, the following labels are used:

[0094] 10-Residential water use time-series probability and flow prediction device;

[0095] 11-Information Acquisition Module;

[0096] 12-Database building module;

[0097] 13-Relationship Model Construction Module;

[0098] 14-Time-series flow meter model building module;

[0099] 15 - Prediction Result Output Module;

[0100] 16-Evaluation model building module;

[0101] 17-Prediction result output module;

[0102] 18-Evaluation model building module. Detailed Implementation

[0103] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments to further understand the purpose, solution and effect of the present invention, but it is not intended to limit the scope of protection of the appended claims.

[0104] References to "embodiment," "another embodiment," "this embodiment," etc., in the specification refer to embodiments that may include specific features, structures, or characteristics, but not every embodiment must include these specific features, structures, or characteristics. Furthermore, such expressions do not refer to the same embodiment. Moreover, when describing specific features, structures, or characteristics in conjunction with embodiments, whether or not explicitly described, it is indicated that incorporating such features, structures, or characteristics into other embodiments is within the knowledge of those skilled in the art.

[0105] The specification and subsequent claims use certain terms to refer to specific components or parts. Those skilled in the art will understand that users or manufacturers may use different names or terms to refer to the same component or part. This specification and claims do not distinguish components or parts by differences in name, but rather by differences in function. The terms "comprising" and "including" used throughout the specification and claims are open-ended and should be interpreted as "including but not limited to". Furthermore, the term "connection" here includes any direct and indirect electrical connection means. Indirect electrical connection means include connections via other means.

[0106] Figures 1 to 18The residential water use time-series probability and flow prediction method provided in this embodiment includes:

[0107] S1: Obtain water usage information, which includes the number of households, the number of people using water, the actual flow rate, and the total equivalent of sanitary fixtures;

[0108] In one embodiment, water usage information is obtained through methods such as surveys and visits;

[0109] S2: Obtain the actual residential water consumption time series probability based on the measured flow rate and construct a residential water consumption time series probability database;

[0110] S3: Construct a correlation model between the total number of equivalent sanitary fixtures and the probability of water output in time series using a residential water use time series probability database;

[0111] S4: Based on the correlation model between the total equivalent of sanitary fixtures and the time series water discharge probability, the time series water discharge probability of the project to be predicted at each time point is obtained;

[0112] S5: Input the total equivalent of sanitary fixtures for the project to be predicted into the sanitary fixtures equivalent conversion model to obtain the converted total equivalent of sanitary fixtures.

[0113] S6: Construct a time-series flow calculation model and set a dynamic water supply guarantee rate to obtain the equivalent number of sanitary fixtures used simultaneously at each time point;

[0114] S7: The time-series flow rate is calculated based on the number of sanitary fixtures used simultaneously at each time point and the rated flow rate corresponding to the sanitary fixture equivalent.

[0115] This embodiment improves the accuracy of water use probability and time-series flow rate calculations by acquiring water use information including the number of households, number of water users, measured flow rate, and total equivalent number of sanitary appliances. It uses measured water use data as the basis for calculating water use probability and time-series flow rate. Based on the measured flow rate, it obtains the actual residential water use time-series probability and constructs a residential water use time-series probability database, providing a basis for subsequent calculations of water use probability and time-series flow rate, and ensuring the accuracy of these calculations. This method utilizes a residential water use time-series probability database to construct a correlation model between the total number of equivalent sanitary fixtures and the time-series water output probability. Based on this correlation model, the time-series water output probability corresponding to the total number of equivalent sanitary fixtures for the project under prediction at each time point is obtained. Next, the total number of equivalent sanitary fixtures for the project under prediction is input into a sanitary fixture equivalent conversion model to obtain the converted total number of equivalent sanitary fixtures. Then, a time-series flow calculation model is constructed, and a dynamic water supply guarantee rate is set to obtain the number of sanitary fixtures simultaneously in use at each time point. Finally, the time-series flow rate is calculated based on the number of sanitary fixtures simultaneously in use at each time point and the corresponding rated flow rate, ensuring the accuracy of the prediction results and thus meeting the requirements of precise and efficient control technology for secondary water supply pumps, thereby achieving energy conservation. This method can calculate the real-time flow changes in residential buildings based on the number of sanitary fixtures simultaneously in use, meeting the requirements of intelligent and refined precise and efficient control technology for secondary water supply pumps, and achieving energy conservation.

[0116] In one embodiment, the water usage information also includes: rated flow rate of sanitary fixtures and real-time flow data of the residence.

[0117] In one embodiment, water usage information also includes information such as apartment type, obtained through surveys and visits, including apartment type, number of households, number of residents, and the availability of sanitary fixtures per household. It should be noted that the number of residents can also be referred to as the number of water users or simply the number of people using the water.

[0118] In one embodiment, the water usage database includes one or more of the following: number of water users, actual number of residents in a residence at a certain time, total number of sanitary fixtures equivalent, time-series water supply probability of sanitary fixtures, influence coefficient of number of water users on time-series water supply probability, influence coefficient of total number of sanitary fixtures equivalent on time-series water supply probability, minimum value of water supply equivalent for sanitary fixtures installed in a residence, and greatest common divisor of water supply equivalent for sanitary fixtures installed in a residence.

[0119] In one embodiment, the formula for calculating the actual residential water usage time-series probability is as follows:

[0120]

[0121] In the formula: The time-series probability of actual residential water usage is expressed in % (%). The unit for real-time residential traffic flow data is L / s; Indicates the total equivalent of sanitary fixtures; This indicates the rated flow rate of one sanitary fixture equivalent.

[0122] In one embodiment, this solution uses measured water usage data as the basis for calculating water usage probability. Water usage data monitoring equipment needs to be installed at the water inlet pipe of the community or residence to obtain real-time flow data of the residence. Regarding equipment selection, the performance parameter requirements for water data monitoring equipment are shown in Table 1:

[0123] Table 1 Performance Parameter Requirements for Water Use Data Monitoring Equipment

[0124]

[0125] In one embodiment, the correlation model between the total number of equivalent sanitary fixtures and the time-series water discharge probability includes: a first correlation model, a second correlation model, and a third correlation model, wherein the first correlation model is constructed using a residential water use time-series probability database and specifically includes:

[0126]

[0127] In the formula: The sequential probability of simultaneous outflow of water equivalent from residential sanitary fixtures is expressed in % (%). express The actual number of residents in the residential building at any given time; Indicates the total equivalent of sanitary fixtures; The coefficient representing the influence of the number of water users on the probability of water discharge in a given time series. This represents the influence coefficient of the total equivalent number of sanitary fixtures on the probability of time-series water discharge.

[0128] In one embodiment, the first association model is derived by fitting relevant data from a water database.

[0129] In one embodiment, the water usage database further includes: the number of households residing within the monitoring area and the configuration of sanitary fixtures equivalent per household. It should be noted that sanitary fixtures can refer to sanitary appliances or sanitary appliances in general, and the water usage database can also be called a residential time-series water usage probability database.

[0130] In one embodiment, the water usage database includes: the number of households living within the monitoring range, the configuration of sanitary fixtures equivalent per household, the number of people using water, the actual number of people living in the residence at a certain moment, the total number of sanitary fixtures equivalent, the time-series water output probability of sanitary fixtures, the influence coefficient of the number of people using water on the time-series water output probability, and the influence coefficient of the total number of sanitary fixtures equivalent on the time-series water output probability.

[0131] In one embodiment, the second association model specifically includes the average probability of water discharge and the confidence interval;

[0132] Among them, the average probability of water discharge The calculation formula is as follows:

[0133]

[0134] In the formula, Indicates the number of days;

[0135] Confidence interval The calculation formula is as follows:

[0136] First, based on the average water output probability Calculate the standard deviation of the sample :

[0137]

[0138] Recalculate the standard error SE:

[0139]

[0140] Next, calculate the critical value ∆:

[0141]

[0142] In the formula: Indicates degrees of freedom. ; This indicates the significance level corresponding to the confidence level.

[0143] Finally, the confidence interval is obtained.

[0144]

[0145]

[0146] In the formula: This indicates the lower limit of the confidence interval; This indicates the upper limit of the confidence interval.

[0147] In one embodiment, the second association model is the time-series probability of data with the same total number of equivalent sanitary appliances.

[0148] In one embodiment, the standard error reflects the magnitude of the sampling error and is the standard deviation of the sample statistic. When the population standard deviation σ is unknown, the formula for calculating the standard error SE of the mean is:

[0149] .

[0150] In one embodiment, the critical value is determined by the confidence level and the distribution type, the population standard deviation σ is unknown, and the critical value is calculated using the t-distribution type. The formula for calculating the critical value ∆ is as follows:

[0151]

[0152] In the formula: Indicates degrees of freedom. ; This indicates the significance level corresponding to the confidence level; where the significance levels of 90%, 95%, and 99% are the significance levels. The values ​​are 0.10, 0.05, and 0.01, respectively. —The t-distribution can be obtained by looking up the corresponding value in the t-table.

[0153] In one embodiment, the third correlation model is obtained by fitting the second correlation model. The third correlation model reflects the correspondence between the total equivalent of different sanitary appliances and the probability of water use at different times, specifically including:

[0154] .

[0155] In one embodiment, the total number of sanitary fixture equivalents for the project to be predicted can be obtained according to a third association model.

[0156] In one embodiment, the total number of sanitary fixture equivalents for the project to be predicted is input into the sanitary fixture equivalent conversion model to obtain the converted total number of sanitary fixture equivalents, specifically including:

[0157] A conversion model for sanitary fixture equivalents is constructed using the conversion factor K of the sanitary fixture water supply equivalent.

[0158]

[0159] In the formula, N represents the total number of equivalent sanitary fixtures after conversion, and K represents the conversion coefficient of the water supply equivalent of sanitary fixtures. This represents the total number of sanitary fixtures equivalent for the project to be predicted.

[0160] The conversion factor for the water supply equivalent of sanitary fixtures can be calculated using the following formula:

[0161]

[0162] In the formula: This represents the minimum water supply equivalent required for installing sanitary fixtures in a residential building. This represents the greatest common divisor of the water supply equivalents for sanitary fixtures installed in a residential building.

[0163] In one embodiment, the water usage database originally only contained the water usage probabilities corresponding to the total number of sanitary fixtures (n1, n2, n3) at various times. The third association model here fits the water usage probabilities of sanitary fixtures at each time point to obtain a functional relationship between the number of sanitary fixtures (n1, n2, n3) and their usage probabilities at different times. This is then used to calculate the usage probabilities corresponding to the total number of other sanitary fixtures (n1, n2, n3) at different times. This enables the prediction of time-series water usage data for different projects.

[0164] In one embodiment, the third association model fits data with different total equivalents of sanitary fixtures to obtain a functional relationship between the water usage probability and the total equivalent of sanitary fixtures. This function can be used to obtain the correspondence between the total equivalent of sanitary fixtures and the water usage probability at different times and for different total equivalents of sanitary fixtures.

[0165] In one embodiment, the third association model fits data with different total numbers of sanitary fixtures to obtain a functional relationship between the water usage probability and the total number of sanitary fixtures. This function can be used to obtain the correspondence between the total number of sanitary fixtures and the water usage probability for different items to be predicted at different times.

[0166] In one embodiment, constructing a time-series flow calculation model and obtaining the equivalent number of sanitary fixtures used simultaneously specifically includes:

[0167] First calculate for all The total number of converted sanitary fixtures equivalents, any The probability equations for simultaneous use are shown below:

[0168]

[0169] In the formula: This indicates that at time t, The total number of converted sanitary fixtures used simultaneously The probability of one equivalent; Indicates in In the total number of converted sanitary fixture equivalents, each time there are The number of combinations in which each equivalent can be used simultaneously. ;

[0170] Based on this calculation, at time t, The total number of converted sanitary ware equivalents simultaneously uses 0, 1, 2, ... The probability of using a number of sanitary fixtures simultaneously;

[0171] Finally, the equivalent number of sanitary fixtures used simultaneously is determined by the following inequality. :

[0172]

[0173] In the formula: —This represents the water supply guarantee rate. It should be noted that this embodiment determines the water supply guarantee rate at each time point based on theories such as binomial distribution or Poisson distribution. The total number of converted sanitary fixtures equivalents and the number of simultaneously used. That is, the equivalent number of sanitary fixtures used simultaneously. This embodiment calculates the minimum value greater than the water supply guarantee rate using this formula, thereby determining... value.

[0174] In one embodiment, during the calculation of time-series flow using a binomial distribution, the water supply guarantee rate X is related to whether the current moment falls within a peak water usage period. For residential buildings, from midnight to 6 a.m., sanitary fixtures and equipment are rarely used, and the water supply guarantee rate X can be taken as a smaller value such as 60%, 65%, 70%, or 75% as needed; peak water usage occurs between 6 a.m. and 8 p.m. and between 6 p.m. and 8 p.m., and the water supply guarantee rate X can be taken as a larger value such as 80%, 85%, 90%, or 99%.

[0175] In one embodiment, the total number of sanitary ware equivalents of the project to be predicted and the converted total number of sanitary ware equivalents can also be referred to as the total number of sanitary ware equivalents. They are the same concept, except that the data included in the total number of sanitary ware equivalents are different.

[0176] In one embodiment, the time-series flow rate includes water consumption:

[0177] The water consumption is calculated based on the equivalent number of sanitary fixtures used simultaneously. :

[0178]

[0179] In the formula: This represents the rated flow rate of one sanitary fixture, in L / s.

[0180] In one embodiment, time-series flow includes water consumption at each time point and total water consumption.

[0181] In one embodiment, a calculation example is provided as follows: Assume that the average usage probability corresponding to the total number of sanitary fixtures equivalent to 68 at time t is 0.9417%, and the water supply guarantee rate at that time is 90%. Then, at that time, the probability that no sanitary fixture equivalent is used is:

[0182]

[0183] The probability of using one sanitary fixture equivalent simultaneously is:

[0184]

[0185] Continuing the calculations using the above method, the probability of using five sanitary fixtures simultaneously is shown in Table 2 below:

[0186] Table 2. Probability of simultaneous use of equivalent sanitary fixtures

[0187]

[0188] Starting from the point where the number of sanitary fixture equivalents is 0, the probability values ​​are summed up. The minimum value where the sum exceeds 0.9 is 1, meaning that at that moment, at most one sanitary fixture equivalent can be used.

[0189] In one embodiment, the residential water use time-series probability and flow prediction method further includes: sanitary appliance equivalent conversion coefficient K;

[0190] Specifically, a standard sanitary fixture, also known as a sanitary fixture equivalent or a sanitary fixture or water supply equivalent, has a rated flow rate. The flow rate is 0.2 L / s, which covers the flow range of most common sanitary appliances. According to binomial distribution theory, the core idea of ​​calculating water flow based on probability methods is to statistically analyze the probability of a single water usage event. During the calculation, the sanitary appliance equivalent must be an integer, which contradicts the current Chinese standards regarding sanitary appliance equivalents. When the water supply equivalent of one sanitary appliance occurs, it may cover the simultaneous occurrence of multiple sanitary appliances. For example, the equivalent of a toilet using a flush tank float valve in a residential building is 0.50, and the equivalent of a washbasin using a mixing faucet is 0.75. Therefore, the setting of the water supply equivalent should simultaneously consider the adaptability of the theoretical model and the characteristics of actual water usage scenarios. Thus, the optimization approach of using a "water supply equivalent conversion coefficient" is adopted to resolve the contradiction between theoretical calculations and current standards.

[0191] The converted water supply equivalent N of the sanitary fixture and the rated flow rate of one water supply equivalent of the sanitary fixture. The following provisions are made:

[0192]

[0193] In the formula: This represents the water supply equivalent of sanitary fixtures after conversion using a conversion factor. This represents the rated flow rate corresponding to the water supply equivalent of one sanitary fixture after conversion by the conversion factor; The conversion factor representing the water supply equivalent of sanitary fixtures can be calculated using the following formula:

[0194]

[0195] In the formula: This represents the minimum water supply equivalent required for installing sanitary fixtures in a residential building. This represents the greatest common divisor of the water supply equivalents for sanitary fixtures installed in a residential building.

[0196] The time-series water output probability of sanitary fixtures is obtained by converting the water supply equivalent. It can be calculated using the following formula:

[0197]

[0198] As can be seen from the formula, although the size of the sanitary fixture equivalent is adjusted, the probability of water usage for a single sanitary fixture equivalent remains the same.

[0199] In one embodiment, such as Figure 2 As shown, the residential water use time-series probability and flow prediction method also includes:

[0200] S8: Build an evaluation model and evaluate the prediction effect of water use probability and time series flow based on the evaluation model.

[0201] In one embodiment, the evaluation model uses the Nash coefficient:

[0202] To evaluate the prediction accuracy of the model under different water supply guarantee rates, the prediction results are evaluated using the Nash coefficient. The formula for calculating the Nash coefficient is as follows:

[0203]

[0204] In the formula: Indicates the first The measured value of water consumption at each moment; —No. Predicted water consumption at a given time point; This represents the average value of the measured water consumption.

[0205] Nash coefficient The range of values ​​is , This indicates that the simulation results perfectly match the observed values, and the model's prediction accuracy is extremely high. This means that the simulation results are the same as the average of the observed values, that is, the model can only predict the average value and cannot reflect the actual change process; This indicates that the simulation results deviate more from the average of the observed values, and the model's prediction performance is poor. It is generally believed that... The model results are available at that time. The time-based model has good prediction performance.

[0206] In one embodiment, the evaluation model uses mean squared error:

[0207] Mean Squared Error (MSE) reflects the average deviation between predicted and actual values. Its calculation formula is as follows:

[0208]

[0209] In the formula: Indicates the first The measured value of water consumption at each moment; —No. Predicted water consumption at a given time point; This indicates the number of water usage data samples collected.

[0210] The mean squared error (MSE) is calculated by averaging the squared difference between each predicted value and the true value. The purpose of the MSE is to eliminate the cancellation between positive and negative errors, ensuring that all errors participate in the calculation as positive numbers, thus more comprehensively reflecting the accuracy of the prediction. A smaller MSE value indicates that the predicted value is closer to the true value, and the higher the model's prediction accuracy; conversely, a larger MSE value indicates a larger prediction error and a lower predictive ability of the model.

[0211] In one embodiment, the evaluation model uses root mean square error:

[0212] The root mean square error (RMSE) is a statistical metric used to measure the difference between the predicted and actual values ​​of a model. Its calculation formula is as follows:

[0213]

[0214] In the formula: Indicates the first The measured value of water consumption at each moment; —No. Predicted water consumption at a given time point; This indicates the number of water usage data samples collected.

[0215] RMSE (Real Error Correction) is calculated by taking the square root of the average squared deviations between predicted and actual values, directly reflecting the average error of the model's predictions. A smaller value indicates that the model's predictions are closer to the actual values, resulting in higher prediction accuracy; a larger value indicates a larger bias in the model, leading to lower prediction reliability. RMSE is an important evaluation criterion when comparing multiple models. By comparing the RMSE values ​​of different models, the model with the smallest prediction error and best performance can be selected, providing a quantitative basis for model optimization and selection.

[0216] In one embodiment, the evaluation model uses one or more of the following: Nash coefficient, mean square error, and root mean square error, to evaluate the prediction effect of water use probability and time series flow rate in turn. It also provides quantitative and improvement basis for the correlation model between the total number of sanitary ware equivalents and the time series water output probability of residential water use time series probability and flow rate prediction methods, and the construction of time series flow rate calculation models.

[0217] In one embodiment, such as Figure 3 As shown, the process of the residential water use time-series probability and flow prediction method is as follows: First, obtain residential building water use information, including: residential building water use monitoring, number of residents, sanitary fixture configuration, number of households, etc.; then, obtain the residential water use time-series probability through residential building water use monitoring; construct a residential building water use database based on the residential building water use information, including the equivalent number of sanitary fixtures and the number of water users. The equivalent number of sanitary fixtures represents the total number of equivalent sanitary fixtures, and the time-series water output probability of sanitary fixtures is obtained through the equivalent number of sanitary fixtures and the number of water users; next, construct a time-series flow calculation model based on the binomial distribution. This model can analyze the sanitary fixture configuration of the project to be predicted and obtain the equivalent number of sanitary fixtures and the number of water users. The equivalent number of sanitary fixtures represents the total number of equivalent sanitary fixtures for the project to be predicted. Further, after correction by the sanitary fixture equivalent conversion coefficient, and combined with the time-series water output probability of sanitary fixtures, obtain the time-series usage probability of the sanitary fixture equivalent. Through the dynamic water supply guarantee rate, obtain the number of sanitary fixtures used simultaneously, and finally obtain the residential building time-series flow.

[0218] In one embodiment, another calculation example is provided as follows:

[0219] Example 1: Determine the optimal water supply guarantee rate X and the equivalent conversion factor K for sanitary fixtures.

[0220] 1. Data Introduction

[0221] To verify the rationality and accuracy of the method for calculating time-series flow based on the time-series probability of individual sanitary fixture equivalent usage, and to clarify the optimal parameter values ​​for the water supply guarantee rate X and the sanitary fixture equivalent conversion coefficient K during model construction, this example directly uses the time-series water usage probability within the monitoring range of water meter No. 1, i.e., the actual residential water usage time-series probability, to conduct time-series flow calculation and analysis. The designed number of water users within the monitoring range of water meter No. 1 is 63 people, comprising 18 households. Each household is equipped with the following sanitary fixtures: a low-tank toilet, a double-valve shower, a double-valve washbasin, a double-valve faucet for the kitchen sink, and a faucet for the washing machine.

[0222] The time-series water usage probabilities calculated based on the actual water usage data of water meter No. 1 are as follows: Figure 4 The usage probability of the water supply equivalent within the monitoring range of water meter No. 1 is shown below; the frequency histogram of the probability distribution of residential water use is shown below. Figure 5 As shown.

[0223] 2. Determine the optimal water supply guarantee rate X

[0224] Based on the binomial distribution principle, calculate the equivalent number of sanitary appliances used simultaneously at each time point under guarantee rates of 80%, 75%, 70%, 65%, 60%, 55%, and 50%. The calculated flow rates at different times are shown in Table 3 below, with the results obtained without a guaranteed water supply rate.

[0225] Table 3. Calculation results of the model without water supply guarantee rate

[0226]

[0227] From the perspective of goodness-of-fit index, when the water supply guarantee rate is 75%, the Nash coefficient (NSE) of the model reaches its maximum value of 0.8353, which is closer to 1. This indicates that the model fits the measured water use data best under this parameter condition and can more accurately reflect the temporal variation characteristics of actual water use.

[0228] Analysis of error evaluation indicators shows that as the water supply guarantee rate decreases from 80% to 60%, the mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) generally show a downward trend, reaching their minimum values ​​at a guarantee rate of 60%, at 0.0030, 0.0546, and 0.0458 respectively. This indicates that the deviation between the calculated and measured values ​​is minimal at this guarantee rate. However, when the water supply guarantee rate further decreases to 55%, the various error indicators show a slight rebound, while the Nash coefficient drops significantly to 0.7758, reflecting that an excessively low water supply guarantee rate leads to a simultaneous deterioration in both model fitting and computational accuracy. The model calculation results at water supply guarantee rates of 75% and 60% are as follows. Figure 6 As shown;

[0229] From the perspective of goodness-of-fit index, when the water supply guarantee rate is 75%, the Nash coefficient (NSE) of the model reaches its maximum value of 0.8353, which is closer to 1. This indicates that the model fits the measured water use data best under this parameter condition and can more accurately reflect the temporal variation characteristics of actual water use.

[0230] Analysis of error evaluation indicators shows that as the water supply guarantee rate decreases from 80% to 60%, the mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) generally show a downward trend, reaching their minimum values ​​at a guarantee rate of 60%, at 0.0030, 0.0546, and 0.0458 respectively. This indicates that the deviation between the calculated and measured values ​​is minimal at this guarantee rate. However, when the water supply guarantee rate further decreases to 55%, the various error indicators show a slight rebound, while the Nash coefficient drops significantly to 0.7758, reflecting that an excessively low water supply guarantee rate leads to a simultaneous deterioration in both model fitting and computational accuracy. The model calculation results at water supply guarantee rates of 75% and 60% are as follows. Figure 7 As shown;

[0231] Depend on Figure 6 and Figure 7 The comparison shows that when the water supply guarantee rate is 60%, the model calculates all water consumption as 0 L / s, but the actual water consumption during this period shows a small fluctuation at low values ​​(not completely zero). After 5:50, the fluctuation trend of the calculated water consumption and the actual water consumption is basically consistent, which can match the change pattern of water load, but there are some minor differences in local values. Although the overall error is low with a 60% guarantee rate, the model shows a significant deviation in fitting the actual water consumption state during the nighttime period when water load is low.

[0232] The rated flow rate of one standard sanitary fixture's water supply equivalent is 0.2 L / s, which covers the flow range of most common sanitary fixtures. However, looking at the equivalent combinations of sanitary fixtures in each household within the monitoring range of water meter No. 1: except for the faucet at the washing machine, the equivalent of the other sanitary fixtures is less than 1; and the frequency of water use for washing machines in residences is relatively low, not every day. The core idea of ​​the probability method for calculating water flow is based on the statistical derivation of the probability of a single water use event, but this method requires the sanitary fixture equivalent to be an integer value. If the rule of "one standard sanitary fixture's water supply equivalent corresponds to a rated flow rate of 0.2 L / s" is still used for calculation, it cannot accurately represent the actual frequency of high-frequency water use events such as toilets, showers, washbasins, and sinks. This deviation will lead to insufficient fitting accuracy of the model under low flow conditions at night—for example... Figure 7 When the actual water consumption at 5:35 is 0.093 L / s, the model cannot accurately fit this value.

[0233] Table 4 Equivalent values ​​of sanitary fixtures for each household within the monitoring range of water meter No. 1

[0234]

[0235] 3. Determine the equivalent conversion factor K for sanitary fixtures.

[0236] Regarding the situation where a higher rated flow rate leads to a fitting deviation under low flow conditions at night, based on the configuration of sanitary fixtures in each household within the monitoring range of water meter No. 1, the minimum water supply equivalent of the sanitary fixtures can be determined. =0.5, the greatest common divisor of the water supply equivalent of sanitary fixtures =0.25.

[0237] The formula for calculating the equivalent conversion factor of sanitary fixture water supply can be obtained as follows:

[0238]

[0239]

[0240] The total number of sanitary fixture equivalents and rated flow rates after the conversion are shown in Table 5 below:

[0241] Table 5. Equivalent values ​​of sanitary fixtures for each household within the monitoring range of water meter No. 1, after conversion.

[0242]

[0243] Based on the binomial distribution principle, calculate the number of sanitary ware equivalents used simultaneously at each time point when the guarantee rate is 75% and 60% and the equivalent conversion factor for sanitary ware is 1, 2, and 4, respectively. The model calculates the flow rate at different times, and the calculation results are shown in Table 6 below:

[0244] Table 6. Calculation results of the model under different conversion coefficients and without water supply guarantee rate.

[0245]

[0246] Combining Tables 3 and 6, it can be seen that the introduction of the equivalent conversion factor K for sanitary appliances has a significant effect on improving the calculation accuracy of the model.

[0247] Without setting the conversion coefficient (Table 3), the maximum Nash coefficient (NSE) of the model is only 0.8353 (water supply guarantee rate 75%), and the various error indicators (MSE, RMSE, MAE) are generally at a high level. However, after introducing the conversion coefficient K (Table 6), the model performance is significantly improved: when K=2, the maximum Nash coefficient increases to 0.9265, which is 10.9% higher than the optimal value in Table 3; when K=4, the maximum Nash coefficient further increases to 0.9790, which is 17.2% higher than the optimal value in Table 3. At the same time, the mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) decrease by an order of magnitude compared with the optimal level in Table 3, which fully verifies the effectiveness of the conversion coefficient in correcting the flow calculation deviation of low equivalent sanitary appliances.

[0248] Comparing the calculation results of the two parameter sets K=2 and K=4, the model with K=4 performs better overall than that with K=2. Under the same water supply guarantee rate, the Nash coefficient and error index corresponding to K=4 are higher. For example, when the water supply guarantee rate is 65%, the Nash coefficient of the K=4 group reaches 0.9790, which is much higher than the 0.9217 of the K=2 group. Moreover, the mean square error of the former is only 0.0006, which is less than 50% of that of the latter (0.0013). It is clear that increasing the conversion coefficient can better adapt to the flow characteristics of low-equivalent high-frequency sanitary appliances and improve the model's ability to fit low-flow conditions.

[0249] In addition to introducing conversion coefficients, the model performance is also affected by the water supply guarantee rate. The optimal parameter combination is K=4 and a water supply guarantee rate of 65%. At this point, the model's Nash coefficient reaches a peak of 0.9790, and the mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) are all at low levels, balancing goodness of fit and error control accuracy. The model's calculation results are as follows: Figure 8 As shown:

[0250] Therefore, it is recommended that K=4 and a water supply guarantee rate of 65% be used as the optimal parameter combination for the model in this study. This combination can effectively solve the fitting deviation problem under low flow conditions. The calculated peak flow rate is 0.5 L / s, the measured peak flow rate is 0.47 L / s, and the error is 0.03 L / s. This provides reliable support for the accurate prediction of time-series flow rates in secondary water supply systems.

[0251] In one embodiment, yet another calculation example is also provided:

[0252] Example 2: Time Series Flow Forecasting

[0253] The residential building has 9 floors and is designed to accommodate 533 people in 152 households. Each household is equipped with the following sanitary fixtures: a low-tank toilet, a two-valve shower, a two-valve washbasin, a two-valve faucet for the kitchen sink, and a faucet for the washing machine. Water meter settings and monitoring ranges are shown in Table 7.

[0254] Table 7 Test System Composition Table

[0255]

[0256] First, the water usage data monitored by water meters 1 through 9 were stored in a database, and then grouped according to the total equivalent of sanitary fixtures within the monitoring range of the water meters, as shown in Table 8. The outflow probability of water supply equivalent corresponding to the total equivalent of sanitary fixtures at each time point was then statistically analyzed.

[0257] Table 8. Data grouping based on the total number of sanitary fixtures equivalent.

[0258]

[0259] After obtaining the water supply equivalent outflow probability corresponding to different total amounts of sanitary fixtures, the data is processed separately for weekdays and rest days. Taking the processing of the average water supply equivalent outflow probability and the total amount of sanitary fixtures at various times during a weekday as an example, and retaining the Monday water usage data from water meter No. 3, the model's predictive performance is validated. First, the relationship between the average water supply equivalent outflow probability and the total amount of sanitary fixtures at each time point is fitted. The relationship between the average water supply equivalent outflow probability and the total amount of sanitary fixtures at various times during a weekday is as follows: Figures 9 to 13 As shown, where, Figure 9 The fitted formula is y = -3E-041n(x) + 0.0057, R² = 0.9978, that is, the constant term is 0.057, the coefficient term is -0.001, and the coefficient of determination is 0.9978; Figure 10 The fitted formula is y = -0.0011n(x) + 0.0083, R² = 0.9718, that is, the constant term is 0.083, the coefficient term is -0.001, and the coefficient of determination is 0.9718; Figure 11 The fitted formula is y = -0.0071n(x) + 0.0309, R² = 0.9537, that is, the constant term is 0.0309, the coefficient term is -0.0071, and the coefficient of determination is 0.9537; Figure 12 The fitted formula is y = -0.0041n(x) + 0.0196, R² = 0.9188, that is, the constant term is 0.0196, the coefficient term is -0.0041, and the coefficient of determination is 0.9188; Figure 13 The fitted formula is y = -0.0091n(x) + 0.0509, R² = 0.9416, that is, the constant term is 0.0509, the coefficient term is -0.0091, and the coefficient of determination is 0.9416.

[0260] At a confidence level of 95%, based on the functional relationship between the average outflow probability at each time point and the total number of sanitary fixtures equivalent, the average outflow probability, lower confidence limit, and upper confidence limit of the outflow probability corresponding to the total number of sanitary fixtures equivalent of 79.5 at each time point are calculated as follows: Figure 14 As shown, the blue line represents the average outflow probability.

[0261] Based on the relationship between the outflow probability of water supply equivalent and the total number of sanitary fixtures equivalent at various times, the water consumption data of water meter No. 3 on Monday is predicted. The total number of sanitary fixtures equivalent within the monitoring range of water meter No. 3 is 79.5.

[0262] Furthermore, the model was set with a sanitary fixture equivalent conversion factor K=4, a water supply guarantee rate X=65% during off-peak water usage periods, and a water supply guarantee rate X=85% during peak water usage periods. After setting the conversion factor, the total number of sanitary fixture equivalents within the monitoring range of water meter No. 3 was 318, and the rated flow rate corresponding to one sanitary fixture equivalent was 0.05 L / s. The prediction results for Monday's water usage data for water meter No. 3 are shown below:

[0263] Figure 15 The model's prediction performance for weekly water usage data from water meter No. 3 is shown, with the blue line representing measured values ​​and the orange line representing predicted values. Quantitative analysis shows that the Nash coefficient of the prediction model is 0.5026. Further statistical analysis of the confidence intervals of the prediction results reveals that, out of a total of 288 water usage monitoring data points, 214 data points, or approximately 74.3%, have actual values ​​falling within the 95% confidence interval of the prediction results.

[0264] In one embodiment, an example calculation is also provided:

[0265] Example 3: Prediction of Water Use Conditions

[0266] The average outflow probability of sanitary fixtures at each time point in the water usage probability database is segmented to obtain the water usage change conditions, which are then compared with the water usage data of water meter No. 3 on Monday.

[0267] 1. Water usage condition classification

[0268] Using a segmented algorithm based on water usage conditions, such as... Figure 16 The average outflow probability variation curve of water meter No. 3 in the database is segmented, where the blue line represents the outflow probability and the orange line represents the average outflow probability. The results of the water use condition classification are shown in Table 9 below:

[0269] Table 9. Average outflow probability classification of water meter No. 3 in the database.

[0270]

[0271] Water usage forecast

[0272] Based on the operating condition classification results of the average outflow probability variation curve of water meter No. 3, the weekly water usage conditions of water meter No. 3 were predicted, and the predicted flow rates under each operating condition are shown in Table 10.

[0273] Table 10 Predicted Flow Rate under Operating Conditions of Water Meter No. 3

[0274]

[0275] The predicted operating flow rates are combined to obtain the predicted operating conditions and duration for water meter No. 3 as follows: Figure 17As shown in the figure, the blue line represents the measured value and the orange line represents the predicted value;

[0276] To further verify the reliability of the Monday water usage forecast for water meter No. 3, the Monday water usage data for water meter No. 3 was divided into different operating conditions. The results of the operating condition division are shown in Table 11 below:

[0277] Table 11 Results of the Classification of Measured Flow Rates for Water Meter No. 3

[0278]

[0279] By merging operating conditions with the same flow rate, the actual operating conditions and duration of water meter No. 3 are as follows: Figure 18 As shown;

[0280] The prediction results show that the model predicts a maximum flow rate of 0.25 L / s, which is only 0.02 L / s different from the measured maximum flow rate of 0.23 L / s, indicating a small deviation. Analysis of the overall prediction performance for water usage shows that by setting a dynamic water supply guarantee rate, the deviation between the predicted and actual monitored conditions in terms of peak flow rate is minimized.

[0281] In one embodiment, such as Figure 19 As shown, a residential water use time-series probability and flow prediction device 10 is also provided, which is equipped with the above-mentioned residential water use time-series probability and flow prediction method, including:

[0282] Information acquisition module 11 is used to acquire water usage information, including the number of households, number of water users, measured flow rate, and total equivalent number of sanitary appliances;

[0283] Database construction module 12 is used to obtain the actual residential water use time series probability based on the measured flow rate and construct a residential water use time series probability database.

[0284] The association model construction module 13 is used to construct an association model between the total number of equivalent sanitary appliances and the time-series water output probability using the residential water use time-series probability database.

[0285] The time-series water output probability module 14 is used to obtain the time-series water output probability corresponding to the total number of equivalent sanitary fixtures of the project to be predicted at each time point based on the correlation model between the total number of equivalent sanitary fixtures and the time-series water output probability.

[0286] The equivalent total number of sanitary appliances conversion module 15 inputs the equivalent total number of sanitary appliances of the project to be predicted into the sanitary appliance equivalent conversion model to obtain the converted equivalent total number of sanitary appliances.

[0287] The time-series flow meter model building module 16 is used to build a time-series flow calculation model and set a dynamic water supply guarantee rate to obtain the equivalent number of sanitary appliances used simultaneously at each time point.

[0288] The prediction result output module 17 is used to calculate the time-series flow rate based on the number of sanitary fixtures used simultaneously at each time point and the rated flow rate corresponding to the sanitary fixture equivalent.

[0289] In one embodiment, such as Figure 20 As shown, the residential water use time-series probability and flow prediction device 10 also includes:

[0290] The evaluation model building module 18 is used to build an evaluation model and evaluate the prediction effect of water use probability and time series flow based on the evaluation model.

[0291] This device embodiment can be implemented in conjunction with the implementation methods described above. The relevant technical details mentioned in the implementation methods of the above embodiments remain valid in the implementation methods of this device embodiment, and will not be repeated here to avoid repetition.

[0292] This invention also provides a computer-readable storage medium for storing a computer program that, when executed by a processor, implements the aforementioned method for predicting the temporal probability and flow rate of residential water use, and achieves the same technical effect.

[0293] This invention also provides a computer program product, which stores a program or instructions. When the program or instructions are executed by a processor, they implement the steps of the above-described method for predicting the temporal probability and flow rate of residential water use, and achieve the same technical effect.

[0294] Although embodiments of the present invention have been disclosed above, they are not limited to the applications listed in the specification and embodiments. They can be applied to various fields suitable for the present invention. For those skilled in the art, other modifications can be easily made. Therefore, without departing from the general concept defined by the claims and their equivalents, the present invention is not limited to the specific details and illustrations shown and described herein.

Claims

1. A method for predicting the temporal probability and flow rate of residential water use, characterized in that, Include: Obtain water usage information, which includes the number of households, the number of people using water, the actual flow rate, and the total equivalent of sanitary fixtures; Based on the measured flow rate, the actual residential water consumption time series probability is obtained and a residential water consumption time series probability database is constructed. A correlation model between the total number of equivalent sanitary fixtures and the time-series water output probability is constructed using the aforementioned residential water use time-series probability database; The time-series water discharge probability corresponding to the total number of equivalent sanitary fixtures and the time-series water discharge probability correlation model is obtained for each time period. Input the total equivalent of sanitary appliances for the project to be predicted into the sanitary appliance equivalent conversion model to obtain the converted total equivalent of sanitary appliances; A time-series flow calculation model was constructed and a dynamic water supply guarantee rate was set to obtain the equivalent number of sanitary fixtures used simultaneously at each time point. The time-series flow rate is calculated based on the number of sanitary fixtures used simultaneously at each time point and the rated flow rate corresponding to the sanitary fixture equivalent.

2. The residential water use time-series probability and flow prediction method according to claim 1, characterized in that, The water usage information also includes: the rated flow rate of the sanitary fixtures and real-time flow data of the residence.

3. The method for predicting the temporal probability and flow rate of residential water use according to claim 1 or 2, characterized in that, The water usage database includes one or more of the following: number of water users, actual number of residents in a residence at a certain time, total number of sanitary fixtures equivalent, water supply probability of sanitary fixtures in a given time, influence coefficient of number of water users on water supply probability in a given time, influence coefficient of total number of sanitary fixtures equivalent on water supply probability in a given time, minimum value of water supply equivalent for sanitary fixtures installed in a residence, and greatest common divisor of water supply equivalent for sanitary fixtures installed in a residence.

4. The residential water use time-series probability and flow prediction method according to claim 3, characterized in that, The formula for calculating the actual residential water usage time-series probability is as follows: In the formula: The time-series probability of actual residential water usage is expressed in % (%). The unit of the real-time residential flow data is L / s; This indicates the total equivalent of the sanitary fixtures; This indicates the rated flow rate of one sanitary fixture equivalent.

5. The method for predicting the temporal probability and flow rate of residential water use according to claim 3, characterized in that, The correlation model between the total number of equivalent sanitary fixtures and the time-series water output probability includes: a first correlation model, a second correlation model, and a third correlation model, wherein the first correlation model is constructed using the residential water use time-series probability database and specifically includes: In the formula: The sequential probability of simultaneous outflow of water equivalent from residential sanitary fixtures is expressed in % (%). express The actual number of residents in the residential building at any given time; This indicates the total equivalent of the sanitary fixtures; This represents the coefficient representing the influence of the number of water users on the probability of water discharge over time. This represents the influence coefficient of the total equivalent number of sanitary fixtures on the probability of time-series water discharge.

6. The residential water use time-series probability and flow prediction method according to claim 5, characterized in that, The second correlation model specifically includes the average probability of water discharge and the confidence interval; Wherein, the average water discharge probability The calculation formula is as follows: In the formula, Indicates the number of days; The confidence interval The calculation formula is as follows: First, based on the average water output probability... Calculate the standard deviation of the sample : Recalculate the standard error SE: Next, calculate the critical value ∆: In the formula: Indicates degrees of freedom. ; This indicates the significance level corresponding to the confidence level. Finally, the confidence interval is obtained. In the formula: This represents the lower limit of the confidence interval; This represents the upper limit of the confidence interval.

7. The method for predicting the temporal probability and flow rate of residential water use according to claim 6, characterized in that, The third correlation model is obtained by fitting the second correlation model. The third correlation model reflects the correspondence between the total number of different sanitary fixtures and the probability of water use at different times, and specifically includes: 。 8. The method for predicting the temporal probability and flow rate of residential water use according to claim 1, characterized in that, The total equivalent of sanitary fixtures for the project to be predicted is input into the sanitary fixture equivalent conversion model to obtain the converted total equivalent of sanitary fixtures, specifically including: Using the conversion coefficient K of the water supply equivalent of the sanitary fixture, the equivalent conversion model of the sanitary fixture is constructed to obtain: In the formula, N represents the total number of converted sanitary fixture equivalents, and K represents the conversion coefficient of the sanitary fixture water supply equivalent. This represents the total number of sanitary fixture equivalents for the project to be predicted; The conversion factor for the water supply equivalent of the sanitary fixtures can be calculated using the following formula: In the formula: This represents the minimum water supply equivalent for the sanitary fixtures installed in the residence. This represents the greatest common divisor of the water supply equivalents of the sanitary fixtures installed in the residence.

9. The method for predicting the temporal probability and flow rate of residential water use according to claim 1, characterized in that, Constructing the time-series flow calculation model and obtaining the equivalent number of sanitary fixtures used simultaneously specifically includes: First calculate for all The total number of converted sanitary fixtures equivalents, any The probability equations for simultaneous use are shown below: In the formula: This indicates that at time t, The total number of converted sanitary fixtures used simultaneously The probability of one equivalent; Indicates in In the total equivalent of each sanitary fixture, each time there is The number of combinations in which each equivalent can be used simultaneously. ; Based on this calculation, at time t, The total number of converted sanitary ware equivalents simultaneously uses 0, 1, 2, ... The probability of using a number of sanitary fixtures simultaneously; Finally, the equivalent number of sanitary fixtures used simultaneously is determined by the following inequality. : In the formula: —This refers to the water supply guarantee rate.

10. The residential water use time-series probability and flow prediction method according to claim 9, characterized in that, The time-series flow rate includes water consumption: The water consumption is obtained based on the equivalent number of sanitary fixtures used simultaneously. : In the formula: This represents the rated flow rate of one sanitary fixture, in L / s.

11. The residential water use time-series probability and flow prediction method according to claim 1, characterized in that, Also includes: An evaluation model is constructed, and the predictive performance of water use probability and time-series flow rate is evaluated based on the evaluation model.

12. A residential water use time-series probability and flow prediction device, comprising the residential water use time-series probability and flow prediction method as described in any one of claims 1 to 11, characterized in that, include: The information acquisition module is used to acquire water usage information, which includes the number of households, the number of water users, the measured flow rate, and the total equivalent number of sanitary appliances. The database construction module is used to obtain the actual residential water use time series probability based on the measured flow rate and construct a residential water use time series probability database. The association model construction module is used to construct an association model between the total number of equivalent sanitary appliances and the time-series water output probability using the residential water use time-series probability database. The time-series water output probability module is used to obtain the time-series water output probability corresponding to the total number of sanitary fixtures equivalent for the project to be predicted at each time point based on the correlation model between the total number of sanitary fixtures equivalent and the time-series water output probability. The equivalent total number of sanitary appliances conversion module inputs the equivalent total number of sanitary appliances of the project to be predicted into the sanitary appliance equivalent conversion model to obtain the converted equivalent total number of sanitary appliances; The time-series flow meter model building module is used to build a time-series flow calculation model and set a dynamic water supply guarantee rate to obtain the equivalent number of sanitary fixtures used simultaneously at each time point. The prediction result output module is used to calculate the time-series flow rate based on the number of sanitary fixtures used simultaneously at each time point and the rated flow rate corresponding to the sanitary fixture equivalent.

13. The residential water use time-series probability and flow prediction device according to claim 12, characterized in that, Also includes: The evaluation model building module is used to build an evaluation model and evaluate the prediction effect of water use probability and time series flow based on the evaluation model.

14. A computer-readable storage medium, characterized in that, Used to store a computer program, which, when executed by a processor, implements the residential water use time-series probability and flow prediction method as described in any one of claims 1 to 10.

15. A computer program product, characterized in that, The computer program product stores a program or instructions that, when executed by a processor, implement the residential water use time-series probability and flow prediction method as described in any one of claims 1 to 10.

Images