Self-adaptive control method and system for electric flow regulating valve

Abstract

The invention relates to the technical field of water saving, and provides a self-adaptive control method and system for an electric flow regulating valve, and the method comprises the steps: collecting the opening degree of the flow regulating valve in a heat supply secondary pipe network and different types of pipe network data of different monitoring points, and matching the flow regulating valve with the monitoring points; determining the interference fluctuation possibility of the monitoring points at the acquisition moment, and determining to-be-identified moments of all the monitoring points; determining an abnormal transmission chain of a real heat supply demand, a to-be-regulated degree of a flow regulating valve at the real heat supply demand, and a pipe network regulation influence degree at a to-be-identified moment; and determining an adjustment coefficient of the to-be-identified moment, and realizing opening control of the flow control valve by combining the opening of the flow control valve at the to-be-identified moment and all similar acquisition moments. According to the invention, self-adaptive control of the opening of the flow regulating valve can be realized.

Description

Technical Field

[0001] This invention relates to the field of water-saving technology, specifically to an adaptive control method and system for an electric flow regulating valve. Background Technology

[0002] Installing flow regulating valves and performing precise adjustments in the secondary heating network is a core element in achieving stable, energy-efficient, and comfortable operation of the heating system. As the "last mile from the heat source to the user," the secondary network inherently suffers from hydraulic imbalance, heat load fluctuations, and variable operating conditions. Flow regulating valves can allocate hydraulic flow as needed, match heat load demands, resolve hydraulic imbalances, ensure the stability of the system's basic circulation, and adapt to dynamic changes in heat load, thus achieving on-demand heating and energy conservation.

[0003] Generally, the control intensity of different flow regulating valves in the secondary heating network is determined by the test results based on the physical flow simulation model. However, the actual heat demand of users corresponding to different flow regulating valves varies, and the existing flow regulating valve control methods cannot respond to the actual heat demand of users, which may exacerbate the pressure fluctuations of the main pipeline. Summary of the Invention

[0004] This invention provides an adaptive control method and system for an electric flow regulating valve to solve the problem that the flow regulating valve cannot respond to the user's actual heat demand during the regulation process, which easily aggravates the pressure fluctuation of the main pipeline. The specific technical solution adopted is as follows: In a first aspect, one embodiment of the present invention provides an adaptive control method for an electric flow regulating valve, the method comprising the following steps: Collect the opening degree of flow regulating valves in the secondary heating network and different types of network data at different monitoring points, and match the flow regulating valves with the monitoring points. The network data includes temperature, flow rate and pressure. Based on the changes in the trend of the same type of pipeline data at the monitoring point within a monitoring cycle prior to the collection time, and the correlation between all different types of pipeline data, the possibility of interference fluctuations at the monitoring point at the collection time is determined, and the time to be identified for all monitoring points is determined. For each monitoring point at the time of data collection, based on the flow rate at the monitoring point at the time of data collection, the flow regulating valve matched with the monitoring point, and the possibility of interference fluctuations, the abnormal transmission chain of the actual heating demand and the degree of need for regulation of the flow regulating valve in the actual heating demand are determined. The degree of need for regulation is used to characterize the effectiveness of regulation. For the monitoring point corresponding to the time to be identified, based on the abnormal transmission chain of the corresponding actual heating demand, the degree of need for regulation, and the matched flow regulating valve and monitoring point, the influence of pipeline regulation at the time to be identified is determined. Based on the degree of regulation and the probability of interference fluctuations, similar acquisition times are determined for the time to be identified. Based on the actual heating demand corresponding to the similar acquisition times, the probability of interference fluctuations of the acquisition times during abnormal heating demand periods, and the influence of pipeline regulation, the regulation coefficient for the time to be identified is determined. The regulation coefficient is the degree of adjustment of the opening of the flow regulating valve. By combining the opening of the flow regulating valve at the time to be identified and all similar acquisition times, the opening control of the flow regulating valve is achieved.

[0005] Furthermore, the method for determining the probability of interference fluctuations at the monitoring point at the time of data acquisition is as follows: Any monitoring point is designated as the target monitoring point, and any type of pipeline data from the target monitoring point is designated as the target pipeline data. Based on all target pipeline data collected by the target monitoring point within a monitoring cycle prior to the collection time, a target pipeline data sequence for the target monitoring point at the collection time is established. All collection times within a monitoring cycle prior to the collection time are designated as historical collection times. The mean of the absolute values ​​of the differences between all corresponding values ​​in the target pipeline data sequences at the collection time and all historical collection times is calculated and designated as the historical average difference of the target pipeline data at the collection time. The absolute value of the difference between the target pipeline data at the acquisition time and the previous adjacent acquisition time is recorded as the adjacent difference of the target pipeline data at the acquisition time. The positive correlation between the historical average difference and adjacent differences of the target pipeline data at the time of collection is denoted as the probability of abnormal fluctuations in the target pipeline data at the time of collection.

[0006] Furthermore, the method for determining the abnormal transmission chain of the actual heating demand is as follows: For each monitoring point at the time of data collection, the time when the water flow at the monitoring point passes through the monitoring point and the upstream and downstream adjacent monitoring points is determined based on the flow rate at the monitoring point at the time of data collection and the pipeline length between the monitoring point and the upstream and downstream adjacent monitoring points. When the determined time of data collection is the time to be identified, the determined time of data collection is recorded as the abnormal marked time of data collection, and the monitoring point corresponding to the abnormal pipeline data of the abnormal marked time of data collection is recorded as the abnormal marked monitoring point. The abnormal pipeline data is pipeline data with an abnormal fluctuation probability greater than the preset abnormal fluctuation threshold. The longest time period divided by all abnormal marker collection times determined at the same collection time is recorded as the abnormal heating demand period. The abnormal heating demand periods are arranged according to the chronological order of the collection times corresponding to the abnormal heating demand, so as to obtain the abnormal transmission chain of the actual heating demand.

[0007] Furthermore, the method for determining the degree of control required by the flow regulating valve in relation to actual heating demand is as follows: The number of monitoring points that match the flow control valve among the abnormal transmission chain of the actual heating demand is denoted as the first number. The ratio of the first number to the total number of monitoring points that match the flow control valve is denoted as the abnormal number ratio matched by the flow control valve. The average interference fluctuation probability of the flow control valve is denoted as the average interference fluctuation probability of the flow control valve, which is the average value of the interference fluctuation probability of the monitoring points matched with the flow control valve at all collection times within the abnormal transmission chain of the actual heating demand. The negative correlation between the duration of actual heating demand, the ratio of abnormal flow control valve matching, and the average disturbance fluctuation probability of the flow control valve is denoted as the degree of control required for the flow control valve in response to actual heating demand.

[0008] Furthermore, the method for obtaining the network regulation impact at the time to be identified is as follows: The number of anomaly marker monitoring points contained in the anomaly propagation chain corresponding to the monitoring point at the time to be identified is denoted as the number of anomaly markers at the time to be identified. Identify the flow control valve corresponding to the monitoring point at the time to be identified, and record the maximum length of the pipeline between the abnormal marker monitoring point and the identified flow control valve in the abnormal transmission chain of multiple monitoring points at the time to be identified as the maximum hydraulic path at the time to be identified. The ratio of the degree of regulation required for the actual heating demand at the time to be identified to the degree of regulation required for the most recent actual heating demand before the time to be identified is denoted as the corresponding degree of regulation required for the time to be identified. The positive correlation between the number of anomaly markers, the maximum hydraulic path, and the corresponding degree of regulation at the time to be identified is recorded as the network regulation influence at the time to be identified.

[0009] Furthermore, the method for determining the similar acquisition time is as follows: Based on the degree of controllability of the actual heating demand determined by the flow regulating valve at the time of data acquisition, and the possibility of interference fluctuations at all monitoring points matched with the flow regulating valve at the time of data acquisition, a state vector of the flow regulating valve at the time of data acquisition is established. Record any time to be identified as the target acquisition time. Calculate the cosine similarity of the state vectors of the flow control valve at each acquisition time within the monitoring cycle before the target acquisition time and the target acquisition time. Record the acquisition times within the monitoring cycle before the target acquisition time that have a cosine similarity greater than the preset similarity threshold as similar acquisition times of the target acquisition time.

[0010] Furthermore, the specific calculation method for the adjustment coefficient at the time to be identified is as follows: Based on the actual heating demand corresponding to similar collection times and the probability of interference fluctuations during collection times in periods of abnormal heating demand, the effective regulation index of the target collection time is calculated. The average value of the network regulation influence at all similar acquisition times at the target acquisition time is used as the denominator, and the product of the degree of regulation to be controlled by the flow regulating valve at the target acquisition time and the regulation effectiveness index is used as the numerator. The normalized value of the fraction is recorded as the regulation coefficient at the target acquisition time.

[0011] Furthermore, the method for obtaining the effective adjustment index at the target acquisition time is as follows: The duration of the actual heating demand corresponding to the flow regulating valve at similar sampling times is recorded as the first duration of the similar sampling time. The average value of the interference fluctuation probability of all monitoring points corresponding to the flow regulating valve at the last collection time of the abnormal heating demand period corresponding to similar collection time is denoted as the first average value at similar collection time. The maximum value of the interference fluctuation probability of all abnormal marker monitoring points in the abnormal transmission chain corresponding to the flow control valve at the similar acquisition time is recorded as the first maximum value at the similar acquisition time. The effective adjustment index at the target acquisition time is calculated. The effective adjustment index is negatively correlated with the first duration and the first mean, and positively correlated with the first maximum value.

[0012] Furthermore, the method for controlling the opening of the flow regulating valve by combining the opening of the valve at the time to be identified and all similar acquisition times includes the following specific methods: The average value of the opening of the flow control valve at all similar acquisition times at the target acquisition time is recorded as the valve opening threshold at the target acquisition time. When the opening of the flow control valve at the target acquisition time is greater than the valve opening threshold at the target acquisition time, the control coefficient at the target acquisition time is updated to the opposite of the original value. The product of the adjustment coefficient at the target acquisition time and the maximum value of the single adjustment of the flow control valve opening is recorded as the first product at the target acquisition time. The opening of the flow control valve at the target acquisition time is adjusted to be the sum of the opening of the flow control valve at the target acquisition time and the first product at the target acquisition time.

[0013] Secondly, embodiments of the present invention also provide an adaptive control system for an electric flow regulating valve, including a memory, a processor, and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the steps of any of the methods described above.

[0014] The beneficial effects of this invention are: Short-term fluctuations caused by temporary user interference do not change the actual heating demand in the area. However, changes in actual heating demand lead to continuous anomalies in multi-dimensional pipeline data. Therefore, during the regulation of flow control valves, it is necessary to distinguish between these two types of fluctuations, evaluate the likelihood that fluctuations in pipeline data at monitoring points within a monitoring cycle prior to the data collection time are caused by changes in actual heating demand, obtain the probability of interference fluctuations at the monitoring points at the data collection time, and determine the identification time for all monitoring points based on the probability of interference fluctuations. The identification time for a monitoring point is the time when the opening of the corresponding flow control valve needs to be regulated. Abnormal states at monitoring points within the secondary heating pipeline network will be transmitted upstream and downstream based on fluid continuity. Therefore, by combining the abnormal transmission states of the monitoring points corresponding to each flow control valve, the degree of regulation required by the flow control valve is analyzed. Specifically, the effectiveness of the flow control valve in regulating actual heating demand is evaluated, the degree of regulation required is obtained, and the pipeline regulation impact at the identification time is obtained. This method is used to evaluate the impact of flow control valve opening adjustment on other flow control valves in the pipeline network at the time to be identified. The greater the effectiveness of the flow control valve's adjustment in relation to the actual heating demand determined at each sampling time within a monitoring cycle prior to the sampling time, and the smaller the impact of the opening adjustment on other flow control valves in the pipeline network, the greater the degree of adjustment required for the flow control valve's opening. Therefore, when adjusting the flow control valve's opening, it is necessary to determine the degree of adjustment based on the effectiveness of the flow control valve in controlling the actual heating demand and the impact of the opening adjustment on other flow control valves in the pipeline network. This yields the adjustment coefficient at the time to be identified, and, combined with the openings of the flow control valves at the time to be identified and all similar sampling times, achieves flow control valve opening control. This addresses the problem of flow control valves failing to respond to actual user heat demand during adjustment, which can easily exacerbate pressure fluctuations in the main pipeline network, thus achieving adaptive control of the flow control valve opening. Attached Figure Description

[0015] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0016] Figure 1 This is a flowchart illustrating an adaptive control method for an electric flow regulating valve, as provided in one embodiment of 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] Please see Figure 1 The diagram illustrates an adaptive control method for an electric flow regulating valve according to an embodiment of the present invention, the method comprising the following steps: Step S001: Collect the opening degree of the flow regulating valve in the secondary heating network and different types of network data at different monitoring points, and match the flow regulating valve with the monitoring point. The network data includes temperature, flow rate and pressure.

[0019] Monitoring points are evenly distributed throughout the secondary heating network. A temperature sensor, flow sensor, and pressure sensor are installed at each monitoring point. These sensors collect data on temperature, flow rate, and pressure at each monitoring point, recording these values ​​as the network data for that point. Valve position sensors are installed on the flow control valves to collect the valve opening information.

[0020] Based on the pipeline network design diagram, extract the cross-sectional area of ​​the pipeline network between each adjacent monitoring point.

[0021] Wherein, the distance between adjacent monitoring points is the pipeline length between adjacent monitoring points in the pipeline network, and the distance between adjacent monitoring points is set by those skilled in the art, and this application does not impose any special restrictions; the units of temperature, flow rate and pressure of the monitoring points are respectively , and .

[0022] Preferably, in one embodiment of this application, when collecting pipeline network data and opening degree, this embodiment collects pipeline network data and opening degree once per minute, and uses seven days as a monitoring cycle. In practical applications, as other implementation methods, implementers can decide the sampling frequency and monitoring cycle value according to the actual situation, and this application does not impose any special restrictions.

[0023] Matching flow control valves and monitoring points involves measuring the distance between each monitoring point and each flow control valve, and selecting the flow control valve with the minimum distance as the matching flow control valve for the monitoring point.

[0024] The opening degree of the flow control valve and the pipeline network data are denoised separately. In this embodiment, EWMA (Exponentially Weighted Moving Average) filtering is used to denoise the opening degree of the flow control valve and the pipeline network data separately. The use of exponentially weighted moving average filtering for denoising is a well-known technique and will not be described in detail here. As other embodiments, based on achieving the goal of data denoising, implementers may use other methods in the prior art, such as median filtering, for data denoising. This application does not impose any special limitations.

[0025] Thus, the opening degree of the flow regulating valve in the secondary heating network and the network data of different types at different monitoring points are obtained.

[0026] Step S002: Based on the changes in the trend of the same type of pipeline data at the monitoring point within a monitoring cycle prior to the collection time, and the correlation between all different types of pipeline data, determine the possibility of interference fluctuations at the collection time of the monitoring point, and determine the time to be identified for all monitoring points.

[0027] In heating monitoring, it is necessary to distinguish between two types of abnormal data fluctuations: the first is short-term fluctuations caused by temporary user interference, which can recover on its own and do not change the actual heating demand in the area; the second is continuous anomalies in multi-dimensional pipeline data caused by changes in actual heating demand, in which case the inherent correlation between pipeline data of various dimensions will be broken. Therefore, it is necessary to combine the abnormal fluctuation characteristics of all types of pipeline data at the monitoring points to accurately distinguish between these two types of abnormal data fluctuations.

[0028] Any monitoring point is designated as the target monitoring point, and any type of pipeline data from the target monitoring point is designated as the target pipeline data. All target pipeline data collected by the target monitoring point within one monitoring cycle prior to the collection time are arranged sequentially to establish the target pipeline data sequence of the target monitoring point at the collection time.

[0029] The target pipeline data in the target pipeline data sequence is arranged in chronological order according to time periods.

[0030] Comparing the pipeline data sequences of the same type of pipeline data at different collection times from the same monitoring point, the greater the difference between the pipeline data sequence and the pipeline data with the same order in other pipeline data sequences, the less the pipeline data in the pipeline data sequence conforms to the user's actual usage habits, the greater the possibility of continuous data anomalies in the pipeline data sequence, and the greater the possibility that the anomaly is caused by multi-dimensional continuous pipeline data anomalies due to changes in actual heating demand.

[0031] All acquisition times within the monitoring cycle preceding the acquisition time are recorded as historical acquisition times. The mean of the absolute values ​​of the differences between the target monitoring point and all corresponding values ​​in the target pipeline data sequence at the acquisition time and all historical acquisition times is recorded as the historical average difference of the target pipeline data at the acquisition time. The absolute value of the difference between the target pipeline data at the acquisition time and the previous adjacent acquisition time is recorded as the adjacent difference of the target pipeline data at the acquisition time. The positive correlation result between the historical average difference of the target pipeline data at the acquisition time and the adjacent difference is recorded as the probability of abnormal fluctuations in the target pipeline data at the acquisition time.

[0032] It is understood that a positive correlation is applied to the historical average difference and adjacent differences of the target pipeline network data at the time of collection, ensuring that the historical average difference and adjacent differences are positively correlated with the probability of abnormal fluctuations. It is understood that the positive correlation in this application refers to the relationship between the independent variable and the dependent variable. The independent variable is the historical average difference and adjacent differences of the target pipeline network data at the time of collection, and the dependent variable is the probability of abnormal fluctuations of the target pipeline network data at the time of collection. The positive correlation means that the dependent variable increases (decreases) as the independent variable increases (decreases), and can be an additive relationship, a multiplicative relationship, etc.

[0033] Preferably, as an embodiment of this application, the normalized value of the product of the historical average difference and adjacent differences of the target pipeline network data at the time of acquisition is denoted as the probability of abnormal fluctuations in the target pipeline network data at the time of acquisition. Specifically, a function is set. ,in, The natural constant is represented by the product of the historical average difference and adjacent differences of the target pipeline network data at the time of acquisition. The value of the function will be determined by the value of the function. This is to account for the possibility of abnormal fluctuations in the target pipeline network data at the time of collection.

[0034] It should be noted that, for ease of calculation, all types of pipeline data involved in the calculation in this embodiment have undergone data preprocessing to eliminate the influence of dimensions. This embodiment uses the maximum-minimum normalization method to remove dimensions from each type of pipeline data. In practical applications, implementers can use other methods such as the sigmoid function for dimension removal, which are not limited here.

[0035] The same method can be used to obtain the probability of abnormal fluctuations in each type of pipeline data at each monitoring point during all monitoring times within a monitoring cycle prior to the data collection time.

[0036] The pipeline data corresponding to abnormal fluctuations that exceed the preset abnormal fluctuation threshold are recorded as abnormal pipeline data.

[0037] In this embodiment, the abnormal fluctuation threshold is set to 0.5. Based on the screening of abnormal pipeline network data, the implementer can set the value of the abnormal fluctuation threshold according to the requirements. This application does not impose any special restrictions.

[0038] The mean of the absolute values ​​of the correlation coefficients among all different types of pipeline data sequences at the target monitoring point at the time of acquisition is denoted as the pipeline data correlation degree of the target monitoring point at the time of acquisition. The absolute value of the difference between the pipeline data correlation degree of the target monitoring point at the time of acquisition and the preset pipeline data standard correlation degree is denoted as the pipeline data relative correlation degree of the target monitoring point at the time of acquisition.

[0039] In this embodiment, the Pearson correlation coefficient is used to calculate the correlation coefficient between different types of pipeline network data sequences. The calculation of the Pearson correlation coefficient is a well-known technique and will not be described in detail here.

[0040] Specifically, the process for determining the standard correlation degree of pipeline data is as follows: a person skilled in the art selects a normally operating secondary heating pipeline, calculates the pipeline data correlation degree of the target monitoring point at the time of data collection, and records it as the standard correlation degree of pipeline data.

[0041] The same method can be used to obtain the relative correlation of pipeline data at each monitoring point at the time of collection.

[0042] For the target monitoring point, the average probability of abnormal fluctuations of all types of pipeline network data at the time of collection is denoted as the average probability of abnormal fluctuations of the target monitoring point at the time of collection. The ratio of the number of abnormal pipeline network data to the total number of types of pipeline network data at the time of collection is denoted as the abnormal data ratio of the target monitoring point at the time of collection. The negative correlation processing result of the average probability of abnormal fluctuations, the abnormal data ratio, and the relative correlation of pipeline network data at the target monitoring point at the time of collection is denoted as the probability of interference fluctuations of the target monitoring point at the time of collection.

[0043] It is understood that negative correlation processing is applied to the average probability of abnormal fluctuations, the ratio of abnormal data, and the relative correlation of pipeline data at the target monitoring point at the time of data collection. This ensures that the average probability of abnormal fluctuations, the ratio of abnormal data, and the relative correlation of pipeline data are negatively correlated with the probability of disturbance fluctuations. It is understood that the negative correlation in this application refers to the relationship between the independent and dependent variables. The independent variables are the average probability of abnormal fluctuations, the ratio of abnormal data, and the relative correlation of pipeline data; the dependent variable is the probability of disturbance fluctuations at the target monitoring point at the time of data collection. The negative correlation means that the dependent variable decreases (increases) as the independent variable increases (decreases), and can be an inverse relationship, a subtraction relationship, etc.

[0044] Preferably, as an embodiment of this application, the product of the average abnormal fluctuation probability of the target monitoring point at the time of collection, the abnormal data ratio, and the relative correlation of the pipeline data is used as the denominator, and the number 1 is used as the numerator. The normalized value of the fraction is recorded as the interference fluctuation probability of the target monitoring point at the time of collection.

[0045] In the process of fraction calculation, in order to avoid the denominator being zero, a preset value needs to be added to the denominator. In this example, the preset value is 0.01.

[0046] It should be noted that this embodiment uses the maximum-minimum normalization method to calculate the normalized value. In practical applications, implementers may use other methods of existing technology, such as the tanh function or the sigmoid function, to calculate the normalized value, which is not limited here.

[0047] The same method can be used to obtain the probability of interference fluctuations at each monitoring point at the time of data collection.

[0048] The acquisition time corresponding to the probability of interference fluctuations exceeding the preset interference fluctuation threshold is recorded as the time to be identified for the corresponding monitoring point.

[0049] The time when the monitoring point is to be identified is the time when the opening of the flow regulating valve corresponding to the monitoring point needs to be adjusted; in this embodiment, the value of the interference fluctuation threshold is 0.5.

[0050] At this point, the time to be identified for all monitoring points has been determined.

[0051] Step S003: For each monitoring point at the time of data acquisition, based on the flow rate at the monitoring point at the time of data acquisition, the flow regulating valve matched with the monitoring point, and the possibility of interference fluctuations, determine the abnormal transmission chain of the actual heating demand and the degree of need for regulation of the flow regulating valve in the actual heating demand. The degree of need for regulation is used to characterize the effectiveness of regulation. For the monitoring point corresponding to the time to be identified, based on the abnormal transmission chain of the corresponding actual heating demand, the degree of need for regulation, and the matched flow regulating valve and monitoring point, determine the influence of pipeline regulation at the time to be identified.

[0052] The secondary heating network is a complex coupled hydraulic system susceptible to external disturbances. Hot water, as the medium in the secondary heating network, flows continuously. Any abnormal state at any monitoring point will be transmitted upstream and downstream due to fluid continuity. For example, if increased heat demand at a monitoring point leads to insufficient flow, it may cause changes in local circulation resistance, resulting in pressure fluctuations upstream and downstream of the monitoring point. Therefore, it is necessary to analyze the degree of control required by the flow control valves by considering the abnormal transmission status of the monitoring points corresponding to each flow control valve.

[0053] For each monitoring point at the time of data collection, the real-time flow velocity is obtained by dividing the flow rate at the monitoring point by the corresponding pipe cross-sectional area. Then, the time taken for the water to flow through the pipe network is determined by dividing the pipe network length by the real-time flow velocity. This is then used to estimate the time of data collection to reach the next monitoring point. When the determined time of data collection is the time to be identified, the determined time of data collection is recorded as the abnormal marked time of data collection. The monitoring point corresponding to the abnormal pipe network data at the abnormal marked time of data collection is recorded as the abnormal marked monitoring point. The longest time period divided by all the abnormal marked time collection times determined at the same time of data collection is recorded as the abnormal heating demand period. The abnormal marked monitoring points in the abnormal heating demand period are arranged in the order of the time collection times corresponding to the abnormal marked monitoring points to obtain the abnormal transmission chain of the real heating demand.

[0054] When the longest time period divided by all the abnormal marker collection times determined at the same collection time is multiple, multiple abnormal heating demand periods can be identified. The abnormal marker monitoring points in all abnormal heating demand periods are arranged in the order of the collection times corresponding to the abnormal marker monitoring points to obtain the abnormal transmission chain of the real heating demand.

[0055] Understandably, for each monitoring point at the time of data collection, the corresponding actual heating demand and the abnormal transmission chain of the actual heating demand can be determined.

[0056] The longer the abnormal transmission chain of actual heating demand and the longer the duration of actual heating demand, the greater the possibility of actual abnormalities occurring at each monitoring point within the abnormal transmission chain, and the more necessary it is to regulate the flow control valve.

[0057] The number of monitoring points that match the flow control valve among the anomaly marker monitoring points included in the anomaly transmission chain of the actual heating demand is denoted as the first quantity. The ratio of the first quantity to the total number of monitoring points that match the flow control valve is denoted as the anomaly quantity ratio matched by the flow control valve. The average value of the interference fluctuation probability of the anomaly marker monitoring points that match the flow control valve among the anomaly marker monitoring points included in the anomaly transmission chain of the actual heating demand at all sampling times within the actual heating demand is denoted as the average interference fluctuation probability of the flow control valve. The negative correlation result of the duration of the actual heating demand, the anomaly quantity ratio matched by the flow control valve, and the average interference fluctuation probability of the flow control valve is denoted as the degree of controllability of the flow control valve in the actual heating demand.

[0058] It is understood that a positive correlation is applied to the duration of actual heating demand, the ratio of abnormal flow control valve matching, and the average disturbance fluctuation probability of the flow control valve. This ensures that the duration of actual heating demand, the ratio of abnormal flow control valve matching, and the average disturbance fluctuation probability are all positively correlated with the degree of regulation required. It is understood that the positive correlation in this application refers to the relationship between the independent and dependent variables. The independent variables are the duration of actual heating demand, the ratio of abnormal flow control valve matching, and the average disturbance fluctuation probability of the flow control valve. The dependent variable is the degree of regulation required for the flow control valve in relation to actual heating demand. The positive correlation means that the dependent variable increases (decreases) as the independent variable increases (decreases), and can be an additive or multiplicative relationship.

[0059] Preferably, as an embodiment of this application, the normalized value of the reciprocal of the product of the actual heating demand duration, the ratio of the number of abnormal flow control valve matches, and the average disturbance fluctuation probability of the flow control valve is denoted as the degree of control required by the flow control valve in response to the actual heating demand. During the ratio calculation, to avoid the denominator being zero, a preset value is added to the denominator; in this embodiment, the preset value is 0.01. In this embodiment, the sigmoid function is used to calculate the normalized value. The sigmoid function is a well-known technique and will not be described in detail here. As other implementations, the implementer can use other methods from the prior art, such as the tanh function.

[0060] It is important to understand that the degree to which the flow control valve needs to be regulated in response to actual heating demand is used to evaluate the effectiveness of the flow control valve in regulating actual heating demand.

[0061] The secondary heating network is a closed-loop system. Therefore, when the opening of a flow control valve is adjusted, the flow rate in the area where the valve is located will change suddenly, disrupting the original hydraulic balance of the network and potentially interfering with the stable operation of other flow control valves. Therefore, it is necessary to analyze the data collected at various times within the previous monitoring cycle to evaluate the impact of the flow control valve's opening adjustment on the stability of other flow control valves in the network.

[0062] After determining the time to be identified for the monitoring point, the flow regulating valve corresponding to the monitoring point at the time to be identified needs to be adjusted. Therefore, for the monitoring point corresponding to the time to be identified, the corresponding actual heating demand and the abnormal transmission chain of the actual heating demand need to be determined.

[0063] It is important to understand that when the corresponding flow control valve is adjusted at the moment of identification, the longer the abnormal transmission chain and the farther the distance between the monitoring point corresponding to the abnormal transmission chain and the flow control valve, the wider the range and the deeper the impact of the flow control valve adjustment on the official website.

[0064] The number of anomaly-marked monitoring points contained in the anomaly transmission chain corresponding to the monitoring point at the time to be identified is recorded as the number of anomaly marks at the time to be identified. The flow regulating valve corresponding to the monitoring point at the time to be identified is identified, and the maximum value of the pipeline length between the anomaly-marked monitoring points contained in the anomaly transmission chain corresponding to multiple monitoring points at the time to be identified and the identified flow regulating valve is recorded as the maximum hydraulic path at the time to be identified. The ratio of the degree of regulation required for the actual heating demand at the time to be identified to the degree of regulation required for the most recent actual heating demand before the time to be identified is recorded as the corresponding degree of regulation required for the time to be identified. The positive correlation result between the number of anomaly marks, the maximum hydraulic path, and the corresponding degree of regulation required for the time to be identified is recorded as the pipeline regulation influence degree at the time to be identified.

[0065] In the process of calculating the ratio, in order to avoid the denominator being zero, a preset value needs to be added to the denominator. In this example, the preset value is 0.01.

[0066] Preferably, as an embodiment of this application, the product of the number of abnormal markers, the maximum hydraulic path, and the corresponding degree of regulation at the time to be identified is recorded as the network regulation influence at the time to be identified.

[0067] In calculating the maximum hydraulic path, the unit for pipeline length is meters. The pipeline length is only used as a substituted value in the calculation to address the issue of the dimensionless influence of the pipeline regulation impact. It can be understood that the pipeline regulation impact at the time to be identified is used to evaluate the degree of influence of the flow control valve's opening adjustment on other flow control valves within the pipeline network at that time.

[0068] At this point, the impact of pipeline regulation at the time to be identified is determined.

[0069] Step S004: Based on the degree of regulation and the possibility of interference fluctuations, determine the similar acquisition time of the time to be identified. Based on the actual heating demand corresponding to the similar acquisition time, the possibility of interference fluctuations of the acquisition time during the abnormal heating demand period, and the influence of pipeline regulation, determine the regulation coefficient of the time to be identified. The regulation coefficient is the degree of adjustment of the opening of the flow regulating valve. Combining the opening of the flow regulating valve of the time to be identified and all similar acquisition times, the opening control of the flow regulating valve is realized.

[0070] When adjusting the opening of a flow control valve, the degree of adjustment should be determined based on the effectiveness of the flow control valve in regulating actual heating demand and the impact of the opening adjustment on other flow control valves in the pipeline network.

[0071] The greater the effectiveness of the flow control valve in determining the actual heating demand at each sampling time within a monitoring cycle prior to the sampling time, and the smaller the impact of the opening control on other flow control valves in the pipeline network, the greater the degree of adjustment of the flow control valve's opening should be.

[0072] The state vector of the flow control valve at the time of acquisition is determined by the standardized processing result of the degree of control required for the actual heating demand determined by the flow control valve at the time of acquisition and the probability of interference fluctuations of all monitoring points matched with the flow control valve at the time of acquisition.

[0073] Record any time to be identified as the target acquisition time. Calculate the cosine similarity of the state vectors of the flow control valve at each acquisition time within the monitoring cycle before the target acquisition time and the target acquisition time. Record the acquisition times within the monitoring cycle before the target acquisition time that have a cosine similarity greater than the preset similarity threshold as similar acquisition times of the target acquisition time.

[0074] In this embodiment, the similarity threshold is set to 0.8.

[0075] The duration of the actual heating demand corresponding to the flow regulating valve at similar acquisition times is recorded as the first duration of the similar acquisition time; the average value of the interference fluctuation probability of all monitoring points corresponding to the flow regulating valve at the last acquisition time of the abnormal heating demand period corresponding to the similar acquisition time is recorded as the first average value of the similar acquisition time; the maximum value of the interference fluctuation probability of all abnormal marker monitoring points in the abnormal transmission chain corresponding to the flow regulating valve at the similar acquisition time is recorded as the first maximum value of the similar acquisition time; based on the first duration, first average value, and first maximum value of all similar acquisition times at the target acquisition time, the regulation effectiveness index of the target acquisition time is calculated, wherein the regulation effectiveness index is negatively correlated with the first duration and the first average value, and the regulation effectiveness index is positively correlated with the first maximum value.

[0076] It is understood that the positive and negative correlations in this application refer to the relationship between the independent and dependent variables. A positive correlation means that the dependent variable increases (decreases) as the independent variable increases (decreases), and can be an additive or multiplicative relationship. A negative correlation means that the dependent variable decreases (increases) as the independent variable increases (decreases), and can be an inverse relationship or a subtractive relationship.

[0077] Some embodiments of this application may be as follows: the first maximum value of similar acquisition times is used as the numerator, the product of the first duration and the first mean of similar acquisition times is used as the denominator, the value of the fraction is recorded as the first fraction of the target acquisition time, and the mean of the first fractions of all similar acquisition times of the target acquisition time is recorded as the adjustment effective index of the target acquisition time.

[0078] The similar sampling time refers to the sampling time at which the flow control valve's opening adjustment is similar to that at the target sampling time, based on the actual heating demand determined at each sampling time within a monitoring cycle prior to the target sampling time. The adjustment effectiveness index is used to evaluate the effectiveness of the adjustment at all similar sampling times of the target sampling time.

[0079] The average value of the network regulation influence at all similar acquisition times at the target acquisition time is used as the denominator, and the product of the degree of regulation to be controlled by the flow regulating valve at the target acquisition time and the regulation effectiveness index is used as the numerator. The normalized value of the fraction is recorded as the regulation coefficient at the target acquisition time.

[0080] In the process of fractional calculation, in order to avoid the denominator being zero, a preset value needs to be added to the denominator. In this embodiment, the preset value is 0.01. It should be noted that this embodiment uses the maximum and minimum value normalization method to calculate the normalized value. In actual application, the implementer can use other methods of existing technology such as the tanh function and the sigmoid function to calculate the normalized value, which is not limited here.

[0081] The difference between the temperature data of the target monitoring point at the target acquisition time and the target set temperature is obtained. If the difference is negative, the adjustment coefficient at the target acquisition time is kept positive. If the difference is positive, the adjustment coefficient at the target acquisition time is updated to the opposite of the original value. The product of the adjustment coefficient at the target acquisition time and the maximum value of the single adjustment of the flow control valve opening is recorded as the first product at the target acquisition time. The sum of the flow control valve opening at the target acquisition time and the first product at the target acquisition time is recorded as the target opening of the flow control valve at the target acquisition time.

[0082] The same method can be used to obtain the target opening degree of the flow control valve at any given moment.

[0083] The opening degree of the flow regulating valve at the time to be identified is adjusted to the target opening degree to achieve the opening degree control of the flow regulating valve.

[0084] This completes the control of the opening degree of the flow regulating valve.

[0085] Based on the same inventive concept as the above method, this embodiment of the invention also provides an adaptive control system for an electric flow regulating valve, including a memory, a processor, and a computer program stored in the memory and running on the processor. When the processor executes the computer program, it implements the steps of any one of the above-described adaptive control methods for an electric flow regulating valve.

[0086] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An adaptive control method for an electric flow regulating valve, characterized in that, The method includes the following steps: Collect the opening degree of flow regulating valves in the secondary heating network and different types of network data at different monitoring points, and match the flow regulating valves with the monitoring points. The network data includes temperature, flow rate and pressure. Based on the changes in the trend of the same type of pipeline data at the monitoring point within a monitoring cycle prior to the collection time, and the correlation between all different types of pipeline data, the possibility of interference fluctuations at the monitoring point at the collection time is determined, and the time to be identified for all monitoring points is determined. For each monitoring point at the time of data collection, based on the flow rate at the monitoring point at the time of data collection, the flow regulating valve matched with the monitoring point, and the possibility of interference fluctuations, the abnormal transmission chain of the actual heating demand and the degree of need for regulation of the flow regulating valve in the actual heating demand are determined. The degree of need for regulation is used to characterize the effectiveness of regulation. For the monitoring point corresponding to the time to be identified, based on the abnormal transmission chain of the corresponding actual heating demand, the degree of need for regulation, and the matched flow regulating valve and monitoring point, the influence of pipeline regulation at the time to be identified is determined. Based on the degree of regulation and the probability of interference fluctuations, similar acquisition times are determined for the time to be identified. Based on the actual heating demand corresponding to the similar acquisition times, the probability of interference fluctuations of the acquisition times during abnormal heating demand periods, and the influence of pipeline regulation, the regulation coefficient for the time to be identified is determined. The regulation coefficient is the degree of adjustment of the opening of the flow regulating valve. By combining the opening of the flow regulating valve at the time to be identified and all similar acquisition times, the opening control of the flow regulating valve is achieved.

2. The adaptive control method for an electric flow regulating valve according to claim 1, characterized in that, The method for determining the probability of interference fluctuations at the monitoring point at the time of data acquisition is as follows: Any monitoring point is designated as the target monitoring point, and any type of pipeline data from the target monitoring point is designated as the target pipeline data. Based on all target pipeline data collected by the target monitoring point within a monitoring cycle prior to the collection time, a target pipeline data sequence for the target monitoring point at the collection time is established. All collection times within a monitoring cycle prior to the collection time are designated as historical collection times. The mean of the absolute values ​​of the differences between all corresponding values ​​in the target pipeline data sequences at the collection time and all historical collection times is calculated and designated as the historical average difference of the target pipeline data at the collection time. The absolute value of the difference between the target pipeline data at the acquisition time and the previous adjacent acquisition time is recorded as the adjacent difference of the target pipeline data at the acquisition time. The positive correlation between the historical average difference and adjacent differences of the target pipeline data at the time of collection is denoted as the probability of abnormal fluctuations in the target pipeline data at the time of collection.

3. The adaptive control method for an electric flow regulating valve according to claim 1, characterized in that, The method for determining the abnormal transmission chain of the actual heating demand is as follows: For each monitoring point at the time of data collection, the time when the water flow at the monitoring point passes through the monitoring point and the upstream and downstream adjacent monitoring points is determined based on the flow rate at the monitoring point at the time of data collection and the pipeline length between the monitoring point and the upstream and downstream adjacent monitoring points. When the determined time of data collection is the time to be identified, the determined time of data collection is recorded as the abnormal marked time of data collection, and the monitoring point corresponding to the abnormal pipeline data of the abnormal marked time of data collection is recorded as the abnormal marked monitoring point. The abnormal pipeline data is pipeline data with an abnormal fluctuation probability greater than the preset abnormal fluctuation threshold. The longest time period divided by all abnormal marker collection times determined at the same collection time is recorded as the abnormal heating demand period. The abnormal heating demand periods are arranged according to the chronological order of the collection times corresponding to the abnormal heating demand, so as to obtain the abnormal transmission chain of the actual heating demand.

4. The adaptive control method for an electric flow regulating valve according to claim 3, characterized in that, The method for determining the degree of control required by the flow regulating valve based on actual heating demand is as follows: The number of monitoring points that match the flow control valve among the abnormal transmission chain of the actual heating demand is denoted as the first number. The ratio of the first number to the total number of monitoring points that match the flow control valve is denoted as the abnormal number ratio matched by the flow control valve. The average interference fluctuation probability of the flow control valve is denoted as the average interference fluctuation probability of the flow control valve, which is the average value of the interference fluctuation probability of the monitoring points matched with the flow control valve at all collection times within the abnormal transmission chain of the actual heating demand. The negative correlation between the duration of actual heating demand, the ratio of abnormal flow control valve matching, and the average disturbance fluctuation probability of the flow control valve is denoted as the degree of control required for the flow control valve in response to actual heating demand.

5. The adaptive control method for an electric flow regulating valve according to claim 1, characterized in that, The method for obtaining the network regulation impact at the time to be identified is as follows: The number of anomaly marker monitoring points contained in the anomaly propagation chain corresponding to the monitoring point at the time to be identified is denoted as the number of anomaly markers at the time to be identified. Identify the flow control valve corresponding to the monitoring point at the time to be identified, and record the maximum length of the pipeline between the abnormal marker monitoring point and the identified flow control valve in the abnormal transmission chain of multiple monitoring points at the time to be identified as the maximum hydraulic path at the time to be identified. The ratio of the degree of regulation required for the actual heating demand at the time to be identified to the degree of regulation required for the most recent actual heating demand before the time to be identified is denoted as the corresponding degree of regulation required for the time to be identified. The positive correlation between the number of anomaly markers, the maximum hydraulic path, and the corresponding degree of regulation at the time to be identified is recorded as the network regulation influence at the time to be identified.

6. The adaptive control method for an electric flow regulating valve according to claim 1, characterized in that, The method for determining the similar acquisition times is as follows: Based on the degree of controllability of the actual heating demand determined by the flow regulating valve at the time of data acquisition, and the possibility of interference fluctuations at all monitoring points matched with the flow regulating valve at the time of data acquisition, a state vector of the flow regulating valve at the time of data acquisition is established. Record any time to be identified as the target acquisition time. Calculate the cosine similarity of the state vectors of the flow control valve at each acquisition time within the monitoring cycle before the target acquisition time and the target acquisition time. Record the acquisition times within the monitoring cycle before the target acquisition time that have a cosine similarity greater than the preset similarity threshold as similar acquisition times of the target acquisition time.

7. The adaptive control method for an electric flow regulating valve according to claim 6, characterized in that, The specific calculation method for the adjustment coefficient at the time to be identified is as follows: Based on the actual heating demand corresponding to similar collection times and the probability of interference fluctuations during collection times in periods of abnormal heating demand, the effective regulation index of the target collection time is calculated. The average value of the network regulation influence at all similar acquisition times at the target acquisition time is used as the denominator, and the product of the degree of regulation to be controlled by the flow regulating valve at the target acquisition time and the regulation effectiveness index is used as the numerator. The normalized value of the fraction is recorded as the regulation coefficient at the target acquisition time.

8. The adaptive control method for an electric flow regulating valve according to claim 7, characterized in that, The method for obtaining the effective adjustment index at the target acquisition time is as follows: The duration of the actual heating demand corresponding to the flow regulating valve at similar sampling times is recorded as the first duration of the similar sampling time. The average value of the interference fluctuation probability of all monitoring points corresponding to the flow regulating valve at the last collection time of the abnormal heating demand period corresponding to similar collection time is denoted as the first average value at similar collection time. The maximum value of the interference fluctuation probability of all abnormal marker monitoring points in the abnormal transmission chain corresponding to the flow control valve at the similar acquisition time is recorded as the first maximum value at the similar acquisition time. The effective adjustment index at the target acquisition time is calculated. The effective adjustment index is negatively correlated with the first duration and the first mean, and positively correlated with the first maximum value.

9. The adaptive control method for an electric flow regulating valve according to claim 6, characterized in that, The method for controlling the opening of the flow regulating valve by combining the opening degree of the valve to be identified and all similar acquisition times includes the following specific methods: The average value of the opening of the flow control valve at all similar acquisition times at the target acquisition time is recorded as the valve opening threshold at the target acquisition time. When the opening of the flow control valve at the target acquisition time is greater than the valve opening threshold at the target acquisition time, the control coefficient at the target acquisition time is updated to the opposite of the original value. The product of the adjustment coefficient at the target acquisition time and the maximum value of the single adjustment of the flow control valve opening is recorded as the first product at the target acquisition time. The opening of the flow control valve at the target acquisition time is adjusted to be the sum of the opening of the flow control valve at the target acquisition time and the first product at the target acquisition time.

10. An adaptive control system for an electric flow regulating valve, comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method as claimed in any one of claims 1-9.

Images