CN116108355B - Management method for cloud hot water monitoring platform data - Google Patents
Management method for cloud hot water monitoring platform data Download PDFInfo
- Publication number
- CN116108355B CN116108355B CN202310383723.3A CN202310383723A CN116108355B CN 116108355 B CN116108355 B CN 116108355B CN 202310383723 A CN202310383723 A CN 202310383723A CN 116108355 B CN116108355 B CN 116108355B
- Authority
- CN
- China
- Prior art keywords
- sequence
- scale
- time
- influence
- matching
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B31/00—Predictive alarm systems characterised by extrapolation or other computation using updated historic data
Abstract
The invention relates to the technical field of data processing, and provides a management method of cloud hot water monitoring platform data, which comprises the following steps: acquiring temperature data of a user; obtaining a scale affecting sequence, a water injection affecting sequence and a standard temperature sequence; obtaining the sequence average slope of the scale influencing sequences, obtaining the sequence average slope difference of each scale influencing sequence, obtaining the weight of a scale influencing model, obtaining the average time span, and constructing a scale influencing model; and (3) slicing the temperature data to obtain a time slice sequence, obtaining scale correction factors in the time slice, obtaining a first matching sequence and a second matching sequence which are user influence correction factors through matching the sequences with the real-time sequence, obtaining a final scale influence model according to the user influence correction factors and the scale influence model, and managing the data according to the final scale influence model. The invention analyzes the influence of the use times of different users on the scale so as to obtain the management statistics of the data more accurately.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to a management method of cloud hot water monitoring platform data.
Background
Along with the gradual trend of people to intelligent life, a corresponding solution is also provided for solving the hot water supply problem. The existing resident cloud hot water monitoring platform is used for realizing intelligent management by carrying out data acquisition and storage on the data of the water heater. The existing water heater depends on the limitation of sensors such as a temperature alarm and a water level sensor, and when the sensors are abnormal or the alarm is not processed, serious problems are easily caused.
The existing cloud hot water monitoring platform is mainly used for realizing abnormal early warning by judging threshold values or analyzing real-time data in the process of monitoring the state data of the water heater, but in different time periods, the abnormal threshold values are different in data intervals of abnormal early warning of the data of the water heater in different service lives, and when the water habits of users are different, the abnormal early warning is caused to have errors, and the water injection behavior of the users does not influence scale in the existing scheme.
Disclosure of Invention
The invention provides a cloud hot water monitoring platform data management method, which aims to solve the problems that when water habits of agents are different, abnormal early warning errors exist due to different abnormal threshold values of data of existing water heaters with different service lives, the adopted technical scheme is as follows:
the invention provides a management method of cloud hot water monitoring platform data, which comprises the following steps:
acquiring historical temperature data and real-time temperature data of each user;
for historical temperature data of a target user, obtaining a plurality of scale influence sequences, a plurality of water injection influence sequences and a standard temperature sequence; obtaining a sequence average slope of each scale influencing sequence through the slope of a DTW connecting line from the scale influencing sequence and the standard temperature sequence, obtaining a sequence average slope difference of each scale influencing sequence according to the difference between the sequence average slope of each scale influencing sequence and the sequence average slope of the first scale influencing sequence on a time sequence, obtaining a scale influencing model weight according to the sequence average slope differences, obtaining an average time span according to the number of the scale influencing sequences, and constructing a scale influencing model of a target user according to the average time span and the scale influencing model weight;
obtaining a plurality of time slices, wherein each time slice comprises a plurality of average time spans, each time slice is used as a time slice sequence, and scale correction factors of each average time span of each user are obtained according to the sequence average slope of the first water injection influence sequence and the sequence average slope of the last water injection influence sequence of each time slice, the scale influence model and each average time span of each time slice, wherein the scale correction factors of all average time spans in the same time slice are the same, and the scale correction factors of the average time spans in the time slice are the scale correction factors of the time slices;
according to the real-time temperature data of the target user, a real-time sequence is obtained, the time slice sequences of the target user and the other users except the target user in the plurality of users are respectively matched with the real-time sequence to select a first matching sequence and a second matching sequence, and scale correction factors corresponding to the first matching sequence and the second matching sequence are obtained; taking the scale correction factors corresponding to the first matching sequences as first influence factors and the scale correction factors corresponding to the second matching sequences as second influence factors; according to the first influence factor and the second influence factor, the DTW distance between the first matching sequence and the real-time sequence, and the DTW distance between the second matching sequence and the real-time sequence, the user influence correction factor of the target user is obtained;
and obtaining a final scale influence model according to the user influence correction factors and the scale influence model, and judging whether the target user cleans the scale according to the final scale influence model.
Further, the method for obtaining the scale influence sequence, the plurality of water injection influence sequences and the standard temperature sequence comprises the following steps:
for the collected historical data of each user, removing data meeting a natural water temperature drop model from all data, removing data with raised temperature, forming a sequence by continuous data with water temperature drop speed being greater than normal drop speed, and forming a sequence by continuous data with water temperature drop speed being less than normal drop speed, and forming a scale influence sequence; peak temperature is set toThe end temperature isCalculating a temperature every 1s by using a natural water temperature drop model, and taking all the obtained temperatures as a standard temperature sequence according to time sequence, whereinThe time corresponding to the temperature drop to the end temperature after the stop of heating is indicated.
Further, the method for obtaining the sequence average slope of each scale influencing sequence by using the slope of the DTW connecting line of the scale influencing sequence and the standard temperature sequence comprises the following steps:
and matching the scale influence sequence with the standard temperature sequence through the DTW, wherein a connecting line exists between each data point in the scale influence sequence and a matching connecting point, calculating the slope of each connecting line, and calculating the average value of all the connecting lines as the average slope of the sequence.
Further, the method for obtaining the average time span according to the number of scale influencing sequences comprises the following steps:
and obtaining the total time of all the water heaters of each user from the beginning to the counting end, and obtaining the number of scale affecting sequences of each user, wherein the ratio of the total time to the number of the scale affecting sequences is taken as an average time span.
Further, the scale correction factor is obtained by the following formula:
in the method, in the process of the invention,is used as a scale correction factor,the sequence average slope of the first water-filling effect sequence of the time slice is represented,the sequence average slope of the last water-filling effect sequence of the time slice is represented,representing a scale impact model,an average time span is represented by a time span,the time slices are shown for a total of h average time spans.
Further, the method for matching the time slice sequences of the target user and the other users except the target user with the real-time sequences to select the first matching sequence and the second matching sequence respectively includes:
and performing DTW matching on all time slice sequences of the target user and the real-time sequence, marking the time slice sequence with the smallest distance as a first matching sequence, performing DTW matching on all time slice sequences of other users and the real-time sequence, and marking the time slice sequence with the smallest distance as a second matching sequence.
Further, the method for obtaining the user influence correction factor of the target user from the DTW distance between the first matching sequence and the real-time sequence according to the first influence factor and the second influence factor, wherein the DTW distance between the second matching sequence and the real-time sequence comprises the following steps:
in the method, in the process of the invention,for the DTW distance of the first matching sequence from the real-time sequence,for the DTW distance of the second matching sequence from the real-time sequence,as a first distance-affecting factor,as a second distance-influencing factor,as a first influencing factor, the first value of the first influence factor,as a second influencing factor, the first influencing factor,the correction factor is influenced for the user.
The beneficial effects of the invention are as follows: according to the invention, by analyzing the historical temperature data, the scale influence sequence, the water injection influence sequence and the standard temperature sequence are obtained, the three temperature sequences represent three different characteristic information, and further data processing is carried out based on the three characteristic information, so that the obtained scale influence model contains more information with reference property, and the scale influence model is more in line with the water habit characteristics of the corresponding user. Further to make the scale impact model more accurate, the user's scale correction factor is analyzed over time and temperature. The method comprises the steps of obtaining a first matching sequence and a second matching sequence matched with other users by combining the real-time temperature sequences, and further obtaining final user influence correction factors; the user influence correction factors are analyzed through water consumption data of other users and real-time data of target users, the accuracy of the scale influence model can be further adjusted, the water consumption habit and water consumption characteristics of the corresponding users can be accurately represented by the final scale influence model, and further accurate early warning is achieved, and the problem that early warning is inaccurate due to the fact that water consumption habits of different users are different and fixed abnormal threshold values are used for early warning is avoided.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, it being obvious that the drawings in the description below are only some embodiments of the invention, and that other drawings can be obtained according to these drawings without inventive faculty for a person skilled in the art.
Fig. 1 is a flow chart of a method for managing cloud hot water monitoring platform data according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flowchart of a method for managing cloud hot water monitoring platform data according to an embodiment of the present invention is shown, and the method includes the following steps:
and S001, collecting temperature data.
In the use process of the water heater of the user, the water heater is provided with a hot water monitoring device, hot water temperature information is collected in real time, then the temperature change of each user is uploaded to the cloud platform, temperature data are stored in the cloud platform, the data of each user are stored independently, temperature time sequence data recorded by the water heater temperature sensor of each user are extracted through the cloud hot water monitoring device, and a water tank temperature change curve is obtained. The method comprises the steps of collecting real-time temperature data of a current water tank as data to be monitored, collecting temperature data of the water tank as historical temperature data in the historical use process of the water heater, and collecting the temperature data every 1s, wherein the counted historical temperature data is from the time when a certain time of scale is removed to the time when the next time of scale is removed. It should be noted that, because there are multiple users in one water supply system, the data of each user needs to be collected in the step of collecting temperature data, and the data processing methods used by the target user or other users except the target user in the subsequent analysis process are the same, in the following description, only the target user is taken as an example, and is not the data processing method of the exclusive target user, and the data processed by the data of other users need to be used in the subsequent model judgment process, so the data processing method of other users is not repeated.
Step S002, constructing a scale influence model through a scale influence sequence.
First, toIn this embodiment, when analyzing the generation of scale, the obtained temperature data of all the water tanks is not interesting when the water tank temperature is reduced normally, so that the normal water temperature reduction data needs to be detected first, and the data of the part of the temperature time sequence data is removed, so that the interesting data is reserved. When the water temperature reaches the peak value set by the water heater, the water heater stops heating, the water temperature in the water tank enters a natural cooling state, and when the water in the water tank enters the natural cooling state, the water temperature in the water tank reachesAt a temperature of celsius, the water heater is started to reheat the water in the water tank, and in this embodiment,. The natural drop model of water temperature is the existing function, as follows:
in the method, in the process of the invention,i.e. the heating in the water tankThe initial temperature that begins to naturally drop after celsius,can be indicative of the ambient temperature outside the tank,the thermal conductivity is shown as a reference value in the embodimentThe specific thermal conductivity is related to the material of the water heater and the thickness of scale on the surface, in this embodiment, the material of the water heater is copper,the time is represented by the time period of the day,indicating the first time after stopping heatingTemperature of water in the water tank at the moment.
Further, in the temperature monitoring data in one day, peak value detection is carried out on the data, the temperature of a plurality of times after the corresponding time of the peak value point is calculated by utilizing a natural falling model of the water temperature, then the real temperature in the water heater is obtained, the data point is deleted based on the calculated temperature and the real temperature, when the absolute value of the difference value between the calculated temperature and the real temperature is larger than 0.01, the data point at the moment is considered not to meet the normal water temperature falling data, otherwise, the normal water temperature falling data is met;
and (3) removing the data meeting the natural water temperature falling model from all the data in the historical temperature data of the target user, removing the data with the temperature rising, forming a sequence by continuous data with the water temperature falling speed being greater than the normal falling speed, namely a water injection influence sequence, and forming a sequence by continuous data with the water temperature falling speed being less than the normal falling speed, namely a scale influence sequence.
Peak temperature is set toThe end temperature isThe sequence meeting the natural descent model is recorded as a standard temperature sequence, and the temperature isWhen the value is the first value of the standard temperature sequence, the temperature isAt this time, the value is the last value of the standard temperature sequence, from the temperature ofFirstly, calculating a temperature value according to a natural water temperature drop model every 1s, and sequentially placing the calculated temperature values in a time sequenceAfter that, until the last temperature value isOne sequence obtained based on this was designated as a standard temperature sequence. Wherein the method comprises the steps ofThe time corresponding to the temperature drop to the end temperature after the stop of heating is indicated.
The target user has thus obtained a number of sub-sequences including a water flooding effect sequence and a scale effect sequence.
For a scale influencing sequence, the temperature reduction of the sequence is influenced by scale, the temperature reduction speed is lower than the reduction speed of normal temperature, and for a natural reduction model of water temperature, a matching relation between points in the DTW dynamic time regulation process is carried out between the scale influencing sequence and a standard temperature sequence, so as to obtain a scale influencing model.
For each scale influencing sequence, taking the jth scale influencing sequence as an example, calculating the average slope of the jth scale influencing sequence after being connected with all data points of the standard temperature sequence:
in the method, in the process of the invention,for scale to affect the slope of the line between the sequence's r data point and its DTW matching data point,the number of data points representing the jth scale affecting sequence,the slope of the DTW match line representing all data points of the jth scale affecting sequence versus the standard temperature sequence is noted as the sequence average slope. It should be noted that, according to the DTW dynamic time warping algorithm, each element between sequences is matched in the sequence-to-sequence matching process, a connection line can exist between the matched elements under a coordinate system, each connection line corresponds to a slope, and the method for calculating the slope under a specific coordinate system is a technical means well known to those skilled in the art, and will not be described herein.
Because the scale in the water heater is continuously increased in the use process of the water heater, when all the scale influencing sequences are ordered according to time, the first scale influencing sequence is the beginning of the scale influencing water heater, and the later scale influencing sequences have larger influence on the cooling of the water heater along with the time, so that the average slope of the sequence of the subsequent scale influencing sequences and the average slope of the sequence of the first scale influencing sequence are differed, and the formula is as follows:
in the method, in the process of the invention,is the average slope of the first scale-affected sequence after time ordering,is the average slope of the jth scale affecting sequence,the difference between the sequence average slope of the jth scale affecting sequence and the sequence average slope of the first scale affecting sequence is expressed as the sequence average slope difference of the jth scale affecting sequence;
the scale influencing sequence and the standard temperature sequence have the same length, and the scale influencing sequence and the standard temperature sequence have the same length, so that the curve corresponding to the scale influencing sequence is gradually decreasedThe matching line of the temperature sensor is moved backwards, so that the overall slope of the matching line is smaller, that is, the longer the scale influencing sequence is, the smaller the average value of the line slope of the DTW of the scale influencing sequence and the standard temperature sequence is, and thus the difference is larger and largerThe larger the scale, the slower the temperature drop corresponding to the scale influencing sequence, the more the scale, and the larger the influence on the temperature; thus can be differentiated by slope changeThe change in the effect of scale was measured.
And constructing the weight of the scale influence model according to the sequence average sequence difference of each scale influence sequence, wherein the formula is as follows:
in the method, in the process of the invention,indicating the number of scale affecting sequences,represents the average slope difference of the mth scale affecting sequence,expressed as the weight of the scale impact model,is the average value of the slope difference change, is used for representing the influence of time on scale,the larger the impact on the scale, the larger,the smaller the impact on scale.
The time span of the historical data collected from the water heater is recorded ast, t is the time from the time when the scale is removed to the time when the next time of scale removal begins in the historical data, the ratio of t to the number of scale influencing sequences is recorded as the average time spanThe obtained average time span comprises the scale influence sequence and other temperature descending or ascending data, and a scale influence model is formed according to the average time span and the weight of the scale influence model:
in the method, in the process of the invention,for the average time span of time it is,for scale to influence the model weight,representing a scale impact model. Wherein the method comprises the steps ofThe larger the impact on scale, the larger the time spanThe longer the influence range of the representation model characterization is, the wider the influence range is;the smaller the impact on scale, the smaller the time spanThe shorter the representation model characterization, the smaller the impact range,the degree of influence on the scale is expressed, and the larger the influence is on the scale content.
Based on the formula model obtained by the calculation, the water is conventionally passed throughIn the process of evaluating the scale at the speed of change of the temperature in the tank, because the influence of the scale on the temperature drop process in a long time sequence is weak, the difference measurement is performed through the matching of the dynamic regular midpoints, so that the influence of the scale is more obvious in appearance. In the dynamic normalization process, when the matching of the points changes, obvious slope changes occur, and the result is thatOnly part of the scale influencing sequence is included, but in the water heater the scale does not suddenly increase, but slowly increases, which is only taken into account in the calculation, and is thus radiated into the entire time sequence of the water heater.
Thus, a scale influence model is obtained.
And S003, obtaining a final scale influence model according to the water injection influence sequence and the influence of different users on the scale.
The scale influence model obtained based on the steps only considers the influence condition of scale in the water tank under normal conditions. In practical use, because there are different usage habits of the user (in this embodiment, the usage habit of the user is that the temperature of the water tank drops sharply due to active water filling in the water tank), the scale influence model in the water tank may be inaccurate in prediction. It is necessary to further acquire the behavior influence factor of the target user from the data of the steep drop of the water temperature caused by the behavior of the user and correct the scale influence model of the target user.
For the water injection influence sequence, the influence of the user behavior on the scale influence model is measured through the difference of the user behaviors in different user water temperature data with similar scale influence weights, and the user influence correction factors of the target user are obtained. Acquiring water temperature data of different users, and determining user influence correction factors through frequency differences of user behaviors in the water temperature dataFor different users, the water injection times of the users are different, and for the water injection frequencyAnd measuring a user influence factor through temperature drop data difference in temperature drop data caused by water injection of the user, and carrying out self-adaptive optimization of different users on the scale influence model through water injection behavior frequency and time interval.
Firstly, slicing is performed from the time when some scale is removed to the time t when the next scale is removed in the historical data, the time for slicing is set to be D, in this embodiment, the time for slicing is set to be 7 days, namely, all the time of the water heater is divided into 7 days. Each time slice comprises a plurality of average time spans, and the average time spans are calculated through a water injection influence sequence.
Further, according to the sequence average slope of the first water injection influence sequence and the sequence average slope of the last water injection influence sequence of each time slice, the scale influence model and each average time span of each time slice, obtaining a scale correction factor corresponding to each average time span:
in the method, in the process of the invention,the sequence average slope of the first water-filling effect sequence of the time slice is represented,the sequence average slope of the last water-filling effect sequence of the time slice is represented,representing a scale impact model,an average time span is represented by a time span,representing a total of h average time spans for a time sliceAnd if h is not an integer, rounding down.For the entire time slice water injection i.e. the effect of scale on temperature,indicating the effect of naturally growing scale on temperature,the effect of water injection on scale growth throughout the time slice is shown,the effect of water flooding behavior on scale growth over an average time span is shown. And obtaining the sequence average slope of each water injection influence sequence by using the continuous slope of the DTW through the water injection influence sequence and the standard temperature sequence.
Further, byAndthe difference in (c) may represent a change in the course of a decrease in the water temperature of the injected water after being affected by scale in one time slice,indicating the effect of scale on the temperature drop in the absence of water injection over the whole time slice, b thus indicates the effect of water injection over an average time span on scale, i.e. the scale correction factor.
And for the user water tank temperature data monitored in real time, matching in historical temperature data through data in a latest time span, and taking the DTW distance between the current time slice sequence and each historical time slice sequence as an evaluation value of the matching degree.
Because there are differences in scale impact models in the sequence of different users during the assessment of scale in the tank, in practiceThe scale influence in the real-time data needs to be judged by the best matching time slice sequence data and the scale influence model acquired by the historical data of the user. Impact weight on scaleThe method comprises the steps that integral water temperature data are contained in the correction factors, and in the correction factors, real-time data of a current target user cannot find the best matching subsequence in historical data, so that the user behavior factors need to correct the user influence factors of the current target user through the best matching subsequence, when no water injection behavior is needed in the historical use process of the target user, when the water injection behavior of the user occurs in the real-time data, correction of the scale influence model is guaranteed, and therefore the cleaning time of scale in a water tank of the target user is guaranteed to be judged more accurately.
And taking the acquired real-time temperature data user as a target user, for other users which are not target users, namely non-target users, performing DTW matching on all time slice sequences of the target users and the real-time sequence, finding out a time slice sequence corresponding to the DTW minimum value as a first matching sequence, and performing DTW on all time slice sequences of the non-target users and the real-time sequence to find out the DTW minimum value as a second matching sequence. It should be noted that, the target user refers to a user facing when the data processing step needs to be executed, and is not a specific user, and other users may implement the same data processing method.
The scale correction factor of the first matching sequence is noted as a first influencing factor and the scale correction factor of the second matching sequence is noted as a second influencing factor. It should be noted that, because the first matching sequence is a sequence obtained by matching the data of the target user, the corresponding first influence factor represents a scale correction factor of each average time span of the target user; the second matching sequence is obtained by matching the data of the non-target user, so that the corresponding second influence factor represents the scale correction factor of each average time span of the non-target user. And according to the first influence factor and the second influence factor, the DTW distance between the first matching sequence and the real-time sequence. The DTW distance between the second matching sequence and the real-time sequence obtains a user influence correction factor:
in the method, in the process of the invention,for the first matching sequence to be a first,for the second matching sequence to be a second matching sequence,for a real-time sequence,for the DTW distance of the first matching sequence from the real-time sequence,for the DTW distance of the second matching sequence from the real-time sequence,as a first distance-affecting factor,as a second distance-influencing factor,as a first influencing factor, the first value of the first influence factor,as a second influencing factor, the first influencing factor,the correction factor is influenced for the user.Representing the similarity of the historical data and the real-time data of the target user,representing similarity of non-target user historical data and real-time data,the impact of the historical data of the target user on the scale impact model,the influence of historical data of non-target users on a scale influence model is due toThe larger the representationThe more important it is that,the larger the representationThe more important, and thereforeThe comprehensive characteristics of historical data of target users and non-target users on the scale influence model are characterized, so that the model is more accurate.
The current real-time monitoring data is corrected through the water temperature data of other users based on the formula, so that accurate acquisition of a water tank scale influence model of the current user can be ensured through similar data of other users when the user is influenced by the behavior of the user for the first time.
After the corrected user influence factors are obtained, calculating a scale influence model of the user through the user influence factors, so as to judge the scale cleaning time.
So far, a final scale influence model is obtained.
And S004, judging the cleaning time of the water tank through a final scale influence model.
After the final scale influence model is obtainedAnd then counting the scale influence degree of a plurality of users when manually cleaning the scale through the cloud platform, wherein the method for acquiring the scale influence degree of other users is the same as the method for acquiring the scale influence degree of the target user, and the scale influence degree of each user can be acquired by changing the target user. The method comprises the steps that the average value of scale influence degrees of a plurality of users is used as a scale cleaning threshold value of a target user, the scale cleaning time is dynamically determined through real-time data of the users, along with the service time of a water heater of the users, scale is increasingly measured through influence factors brought by water injection behaviors of the users in a model, the scale influence of the current time slice is judged in real time through user influence correction factors, the scale cleaning time of a water tank of the users is accurately judged, when the scale influence degree is calculated through a final scale influence model by the target users, and when the scale influence degree is larger than the scale cleaning threshold value, a monitoring platform sends a prompt to the target users, namely, the time sent by prompt information is the cleaning time of the water tank.
So far, the cloud platform realizes the management of hot water data by storing the hot water temperature information of each user and calculating a final scale influence model, and achieves the prompting function of monitoring the scale cleaning in the use process of the water heater of the user.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, alternatives, and improvements that fall within the spirit and scope of the invention.
Claims (6)
1. The management method of the cloud hot water monitoring platform data is characterized by comprising the following steps of:
acquiring historical temperature data and real-time temperature data of each user;
for historical temperature data of a target user, obtaining a plurality of scale influence sequences, a plurality of water injection influence sequences and a standard temperature sequence; obtaining a sequence average slope of each scale influencing sequence through the slope of a DTW connecting line from the scale influencing sequence and the standard temperature sequence, obtaining a sequence average slope difference of each scale influencing sequence according to the difference between the sequence average slope of each scale influencing sequence and the sequence average slope of the first scale influencing sequence on a time sequence, obtaining a scale influencing model weight according to the sequence average slope differences, obtaining an average time span according to the number of the scale influencing sequences, and constructing a scale influencing model of a target user according to the average time span and the scale influencing model weight;
obtaining a plurality of time slices, wherein each time slice comprises a plurality of average time spans, each time slice is used as a time slice sequence, and scale correction factors of each average time span of each user are obtained according to the sequence average slope of the first water injection influence sequence and the sequence average slope of the last water injection influence sequence of each time slice, the scale influence model and each average time span of each time slice, wherein the scale correction factors of all average time spans in the same time slice are the same, and the scale correction factors of the average time spans in the time slice are the scale correction factors of the time slices;
according to the real-time temperature data of the target user, a real-time sequence is obtained, the time slice sequences of the target user and the other users except the target user in the plurality of users are respectively matched with the real-time sequence to select a first matching sequence and a second matching sequence, and scale correction factors corresponding to the first matching sequence and the second matching sequence are obtained; taking the scale correction factors corresponding to the first matching sequences as first influence factors and the scale correction factors corresponding to the second matching sequences as second influence factors; according to the first influence factor and the second influence factor, the DTW distance between the first matching sequence and the real-time sequence, and the DTW distance between the second matching sequence and the real-time sequence, the user influence correction factor of the target user is obtained;
obtaining a final scale influence model according to the user influence correction factors and the scale influence model, and judging whether a target user cleans the scale according to the final scale influence model;
the method for obtaining the average time span according to the number of scale influencing sequences comprises the following steps:
and obtaining the total time of all the water heaters of each user from the beginning to the counting end, and obtaining the number of scale affecting sequences of each user, wherein the ratio of the total time to the number of the scale affecting sequences is taken as an average time span.
2. The method for managing cloud hot water monitoring platform data according to claim 1, wherein the method for obtaining a plurality of scale influencing sequences, a plurality of water injection influencing sequences and a standard temperature sequence is as follows:
for the collected historical data of each user, removing data meeting a natural water temperature drop model from all data, removing data with raised temperature, forming a sequence by continuous data with water temperature drop speed being greater than normal drop speed, and forming a sequence by continuous data with water temperature drop speed being less than normal drop speed, and forming a scale influence sequence; peak temperature is set toThe end temperature is->Calculating a temperature every 1s by using a natural water temperature drop model, and taking all the obtained temperatures as a standard temperature sequence according to time sequence, wherein +.>Indicating that after stopping heatingThe temperature is reduced to the point corresponding to the end temperature.
3. The method for managing cloud hot water monitoring platform data according to claim 1, wherein the method for obtaining the average slope of each scale influencing sequence by using the slope of a DTW connection between the scale influencing sequence and the standard temperature sequence is as follows:
and matching the scale influence sequence with the standard temperature sequence through the DTW, wherein a connecting line exists between each data point in the scale influence sequence and a matching connecting point, calculating the slope of each connecting line, and calculating the average value of all the connecting lines as the average slope of the sequence.
4. The method for managing cloud hot water monitoring platform data according to claim 1, wherein the scale correction factor is obtained according to the formula:
in the method, in the process of the invention,is a scale correction factor, is->The sequence average slope of the first water-filling effect sequence of the time slice is represented,sequence average slope of last water injection influencing sequence representing time slice, +.>Scale influence model>Represents an average time span,/->The time slices are shown for a total of h average time spans.
5. The method for managing cloud hot water monitoring platform data according to claim 1, wherein the method for matching the time slice sequences of the target user and the other users except the target user with the real-time sequences to select the first matching sequence and the second matching sequence respectively comprises the following steps:
and performing DTW matching on all time slice sequences of the target user and the real-time sequence, marking the time slice sequence with the smallest distance as a first matching sequence, performing DTW matching on all time slice sequences of other users and the real-time sequence, and marking the time slice sequence with the smallest distance as a second matching sequence.
6. The method for managing cloud hot water monitoring platform data according to claim 1, wherein the method for obtaining the user influence correction factor of the target user from the DTW distance between the first matching sequence and the real-time sequence according to the first influence factor and the second influence factor comprises the following steps:
in the method, in the process of the invention,DTW distance for the first matching sequence to the real-time sequence,/->DTW distance for the second matching sequence to the real-time sequence,/->For the first distance influencing factor,/>For the second distance influencing factor,/>For the first influencing factor, +.>For the second influencing factor, +.>Influence correction factors for the user->For real-time sequence +.>For the first matching sequence, +.>Is the second matching sequence.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310383723.3A CN116108355B (en) | 2023-04-12 | 2023-04-12 | Management method for cloud hot water monitoring platform data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310383723.3A CN116108355B (en) | 2023-04-12 | 2023-04-12 | Management method for cloud hot water monitoring platform data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116108355A CN116108355A (en) | 2023-05-12 |
CN116108355B true CN116108355B (en) | 2023-06-20 |
Family
ID=86260099
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310383723.3A Active CN116108355B (en) | 2023-04-12 | 2023-04-12 | Management method for cloud hot water monitoring platform data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116108355B (en) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116340795B (en) * | 2023-05-29 | 2023-07-28 | 山东一然环保科技有限公司 | Operation data processing method for pure oxygen combustion heating furnace |
CN117387162B (en) * | 2023-12-11 | 2024-03-08 | 湖南康家环保科技有限公司 | Device and method for removing indoor formaldehyde and TVOC |
Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114704962A (en) * | 2022-04-07 | 2022-07-05 | 广东固特科技有限公司 | Water heater with self-cleaning function and ultrasonic cleaning device thereof |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2010261651A (en) * | 2009-05-07 | 2010-11-18 | Noritz Corp | Water heater |
US9410708B2 (en) * | 2012-01-12 | 2016-08-09 | Jon R. Taylor | Method and apparatus for automatic descaling of tankless water heaters |
CN105546830A (en) * | 2015-12-31 | 2016-05-04 | 天津市嘉尔屹科技发展有限公司 | Electric water heater water scale early warning device based on specific resistance measurement |
CN112001078A (en) * | 2020-08-22 | 2020-11-27 | 姚伟建 | Solar water heater intelligent analysis management system based on big data |
-
2023
- 2023-04-12 CN CN202310383723.3A patent/CN116108355B/en active Active
Patent Citations (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114704962A (en) * | 2022-04-07 | 2022-07-05 | 广东固特科技有限公司 | Water heater with self-cleaning function and ultrasonic cleaning device thereof |
Also Published As
Publication number | Publication date |
---|---|
CN116108355A (en) | 2023-05-12 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN116108355B (en) | Management method for cloud hot water monitoring platform data | |
CN107364097B (en) | Wear amount estimation device and wear amount estimation method for check valve of injection molding machine | |
CN107449156B (en) | Water consumption condition monitoring method for electric water heater and electronic equipment | |
RU2007140372A (en) | DEVICE AND METHOD FOR FORECASTING HUMAN TEMPERATURE | |
CN117093879A (en) | Intelligent operation management method and system for data center | |
CN115902647B (en) | Intelligent battery state monitoring method | |
CN102677740A (en) | Water distribution pressure control system | |
CN116881745B (en) | Pressure transmitter abnormality monitoring method based on big data | |
CN109784528A (en) | Water quality prediction method and device based on time series and support vector regression | |
CN108287043A (en) | Lung ventilator gas leakage quantity measuring method, device, storage medium and computer equipment | |
CN117332341B (en) | Intelligent management method and system for airplane wheel guard data based on Internet of things | |
WO2017211071A1 (en) | Temperature prediction method and apparatus thereof | |
CN105147256B (en) | One boar physiological status forecasting system and device | |
CN111802218A (en) | Automatic irrigation method and system for fruit trees | |
US20160275407A1 (en) | Diagnostic device, estimation method, non-transitory computer readable medium, and diagnostic system | |
CN116428635B (en) | Hot water supply data acquisition and transmission system and method based on environmental information | |
CN117235462A (en) | Intelligent fault prediction method for bag type packaging machine based on time sequence data analysis | |
CN108595814A (en) | A kind of precipitation generator based on day time scale | |
JPH08219828A (en) | Method and device for estimating inflow to dam | |
CN112733729B (en) | Model training and regression analysis method, device, storage medium and equipment | |
CN110322063A (en) | A kind of power consumption simulated prediction method and storage medium | |
JP5383767B2 (en) | Inflow amount prediction apparatus, inflow amount prediction method, and program | |
CN113974567B (en) | Method for calculating metabolic rate in sleeping process | |
CN116792370B (en) | TPB intelligent safety alarm method and system | |
CN111879415B (en) | Temperature measurement management method, device and system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |