Remote diagnosis method and system based on automatic intelligent temperature control

Abstract

The invention relates to the technical field of wall-hanging stove temperature control, in particular to a remote diagnosis method and system based on automatic intelligent temperature control. Dividing to obtain a use cycle, and obtaining use parameters of the wall-hanging stove at the end of the use cycle; dividing the water supply pipe into a first pipeline, a second pipeline and a third pipeline; constructing a first incrustation scale prediction model, and identifying the wall-hanging stove use parameters of the first pipeline and the third pipeline to obtain first incrustation scale data and third incrustation scale data; constructing a second scale prediction model, and identifying use parameters of the second pipeline wall-hanging stove to obtain second scale data; obtaining final incrustation data according to the first incrustation data, the second incrustation data and the third incrustation data, and measuring and calculating to obtain an incrustation early warning coefficient for early warning; and a heating parameter correction model is constructed, corrected heating parameters are obtained according to the final-period water scale data, and adjustment is conducted. According to the invention, through identification, early warning and correction of the scale in the wall-hanging stove, the temperature control precision of the wall-hanging stove is ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of wall-mounted boiler temperature control, and in particular to a remote diagnosis method and system based on automated intelligent temperature control. Background Art

[0002] A wall-mounted boiler is a common household appliance, mainly used to provide indoor heating and domestic hot water. It generally uses gas as the main fuel and is also called a gas wall-mounted boiler.

[0003] Wall-mounted boilers have many advantages. In terms of indoor heating, wall-mounted boilers can provide stable and uniform indoor temperature through radiators or floor heating systems, avoiding the uneven hot and cold phenomena common in traditional heating equipment, and effectively improving heating comfort. In terms of providing hot water, wall-mounted boilers can quickly heat the water source and accurately adjust the water temperature, providing users with instant and stable hot water supply without waiting for the water heater to preheat; therefore, they are very popular.

[0004] However, as the wall-mounted boiler is used for a longer time, the water pipes are prone to scale due to the influence of water quality, water pipe material and changes in water temperature during heating; scale adheres to the surface of the water pipes, affecting the movement of water in the water pipes and the heating process, resulting in errors in the water temperature control accuracy of the wall-mounted boiler.

[0005] In the prior art, a temperature sensor is mainly installed at the water outlet to collect the water temperature data of the water outlet; then the water temperature data of the water outlet is compared with the expected water temperature data and feedback adjustment is performed to maintain the water temperature of the water outlet of the wall-mounted boiler near the expected water temperature. However, this method will cause the wall-mounted boiler to heat the water flow for too long, reduce the accuracy of water flow temperature control, and affect the user experience.

[0006] To this end, a remote diagnosis method and system based on automated intelligent temperature control is proposed. Summary of the invention

[0007] The object of the present invention is to provide a remote diagnosis method and system based on automatic intelligent temperature control, which obtains a usage cycle by dividing the wall-mounted boiler according to the usage rules; at the end of the usage cycle, obtains the usage parameters of the wall-mounted boiler; divides the water supply pipe of the wall-mounted boiler to obtain a first pipe, a second pipe and a third pipe; constructs a first scale prediction model, identifies the wall-mounted boiler usage parameters of the first pipe and the third pipe respectively, and obtains first scale data and third scale data; constructs a second scale prediction model, identifies the wall-mounted boiler usage parameters of the second pipe, and obtains second scale data; obtains end-of-period scale data based on the first scale data, the second scale data and the third scale data; calculates the scale warning coefficient based on the initial scale data and the end-of-period scale data, and issues an early warning; constructs a heating parameter correction model to identify the initial water temperature, the expected water temperature and the end-of-period scale data, and obtains the corrected heating parameters; adjusts the next usage cycle based on the corrected heating parameters; the present invention ensures the accuracy and efficiency of the temperature control of the wall-mounted boiler through the identification, early warning and correction of scale in the wall-mounted boiler.

[0008] To achieve the above objectives, the present invention provides a remote diagnosis method based on automated intelligent temperature control, comprising: S10. Divide the boiler into cycles according to the usage pattern to obtain the usage cycle; at the end of the usage cycle, obtain the boiler usage parameters; the boiler usage parameters include initial scale data, water pipe parameters, water flow parameters and water quality parameters; S20. Divide the water supply pipe of the wall-mounted boiler into a first pipe, a second pipe and a third pipe; the first pipe is a water inlet pipe, the second pipe is a heat exchange pipe, and the third pipe is a water outlet pipe; S30. Constructing a first scale prediction model, identifying the wall-mounted boiler usage parameters of the first pipeline and the third pipeline, respectively, to obtain first scale data and third scale data; S40. Construct a second scale prediction model, identify the wall-mounted boiler usage parameters of the second pipeline; divide the second pipeline according to the temperature change data during the use period to obtain variable temperature sub-areas; obtain scale sub-data, water pipe sub-parameters, water flow sub-parameters and water quality sub-parameters of the variable temperature sub-areas according to the wall-mounted boiler usage parameters of the second pipeline, identify and obtain variable temperature scale sub-data, and obtain second scale data according to the variable temperature scale sub-data; S50. According to the first scale data, the second scale data and the third scale data, the end scale data is obtained; according to the initial scale data and the end scale data, the scale warning coefficient is calculated and an early warning is issued; S60. Construct a heating parameter correction model to identify the end-of-period scale data, the initial water temperature of the next use cycle, and the expected water temperature to obtain a corrected heating parameter; and perform temperature control adjustment according to the corrected heating parameter.

[0009] The initial scale data is the scale distribution data of the water supply pipe at the beginning of the use cycle of the wall-mounted boiler; The water pipe parameters include water pipe inner diameter data, water pipe inner surface roughness and water pipe structure data; The water flow parameters include water flow velocity data and water flow temperature data; The water quality parameters include pH value and hardness data.

[0010] The training process of the first scale prediction model is: Acquire historical usage parameters of the wall-mounted boiler, divide the historical usage parameters according to usage cycles, and obtain a historical cycle division data set; The historical period division data set includes historical initial scale data, historical end-of-period scale data, historical water pipe parameters, historical water flow parameters and historical water quality parameters; The data set is divided according to the historical period to train and tune the model to obtain a first scale prediction model.

[0011] The second scale prediction model includes a water pipe temperature identification layer, a variable temperature area division layer, a regional data identification layer and a regional scale identification layer; The water pipe temperature identification layer collects temperature data of the second pipe during the use period through the temperature detection device to obtain temperature change data of the temperature changing with time; The temperature-varying area division layer identifies the temperature variation data of the second pipeline by a clustering algorithm, takes the temperature value and the temperature variation law as clustering features, and obtains temperature clustering data; divides the second pipeline according to the temperature clustering data to obtain the temperature-varying sub-areas; The regional data recognition layer collects scale sub-data, water pipe sub-parameters, water flow sub-parameters and water quality sub-parameters of the variable temperature sub-region according to the wall-mounted boiler usage parameters of the second pipeline; The regional scale identification layer obtains variable temperature scale sub-data based on the scale sub-data of the variable temperature sub-region, water pipe sub-parameters, water flow sub-parameters and water quality sub-parameters; and obtains second scale data based on the variable temperature scale sub-data of all variable temperature sub-regions.

[0012] The process of the scale warning coefficient is as follows: according to the initial scale data of the first pipeline, the second pipeline and the third pipeline, the first initial scale thickness, the second initial scale thickness and the third initial scale thickness are obtained; according to the end-of-period scale data of the first pipeline, the second pipeline and the third pipeline, the first end-of-period scale thickness, the second end-of-period scale thickness and the third end-of-period scale thickness are obtained; The scale warning coefficient is calculated according to the first initial scale thickness, the second initial scale thickness, the third initial scale thickness, the scale thickness at the end of the first period, the scale thickness at the end of the second period, and the scale thickness at the end of the third period; The calculation formula of the scale warning coefficient is: ; in, Indicates scale warning coefficient; Indicates Weight; Indicates Scale thickness at the end of the period; Indicates Scale threshold; Indicates Initial scale thickness.

[0013] The training process of the heating parameter correction model is: Performing a heating test on the water supply pipeline to obtain a test data set; the test data set includes a heating target temperature, an input water temperature, test scale data, and a test heating parameter; The test heating parameters are the parameters of the wall-mounted boiler for heating the water flow from the input water temperature to the heating target temperature when testing the scale data, including gas parameters, wind pressure parameters and water pressure parameters; The model is trained according to the test data set to obtain a heating parameter correction model.

[0014] The present invention also proposes a remote diagnosis system based on automated intelligent temperature control, comprising: The data collection module divides the period according to the usage rule of the wall-mounted boiler to obtain the usage period; at the end of the usage period, the usage parameters of the wall-mounted boiler are obtained; the usage parameters of the wall-mounted boiler include initial scale data, water pipe parameters, water flow parameters and water quality parameters; The pipeline division module divides the water supply pipe of the wall-mounted boiler into a first pipeline, a second pipeline and a third pipeline; the first pipeline is a water inlet pipeline, the second pipeline is a heat exchange pipeline, and the third pipeline is a water outlet pipeline; The first identification module constructs a first scale prediction model, identifies the wall-mounted boiler usage parameters of the first pipeline and the third pipeline respectively, and obtains the first scale data and the third scale data; The second identification module constructs a second scale prediction model to identify the wall-mounted boiler usage parameters of the second pipeline; divides the second pipeline according to the temperature change data during the usage period to obtain variable temperature sub-areas; obtains scale sub-data, water pipe sub-parameters, water flow sub-parameters and water quality sub-parameters of the variable temperature sub-areas according to the wall-mounted boiler usage parameters of the second pipeline, identifies the variable temperature scale sub-data, and obtains the second scale data according to the variable temperature scale sub-data; The scale warning module obtains the final scale data according to the first scale data, the second scale data and the third scale data; calculates the scale warning coefficient according to the initial scale data and the final scale data, and issues a warning; The parameter adjustment module constructs a heating parameter correction model to identify the end-of-period scale data, the initial water temperature of the next use cycle, and the expected water temperature to obtain the corrected heating parameters; and adjusts the temperature control according to the corrected heating parameters.

[0015] The wall-mounted boiler usage parameters in the data collection module specifically include: The initial scale data is the scale distribution data of the water supply pipe at the beginning of the use cycle of the wall-mounted boiler; the water pipe parameters include water pipe inner diameter data, water pipe inner surface roughness and water pipe structure data; the water flow parameters include water flow velocity data and water flow temperature data; the water quality parameters include pH value and hardness data.

[0016] The training process of the first scale prediction model in the first recognition module is: Acquire historical usage parameters of the wall-mounted boiler, divide the historical usage parameters according to usage cycles, and obtain a historical cycle division data set; The historical period division data set includes historical initial scale data, historical end-of-period scale data, historical water pipe parameters, historical water flow parameters and historical water quality parameters; The data set is divided according to the historical period to train and tune the model to obtain a first scale prediction model.

[0017] The training process of the heating parameter correction model in the parameter adjustment module is as follows: Performing a heating test on the water supply pipeline to obtain a test data set; the test data set includes a heating target temperature, an input water temperature, test scale data, and a test heating parameter; The test heating parameters are the parameters of the wall-mounted boiler that heat the water flow from the input water temperature to the heating target temperature when testing the scale data; including gas parameters, wind pressure parameters and water pressure parameters; The model is trained according to the test data set to obtain a heating parameter correction model.

[0018] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention constructs a first scale prediction model based on the fact that the water flow temperature in the first pipeline and the third pipeline is relatively stable; the initial scale data, water pipe parameters, water flow parameters and water quality parameters of the first pipeline and the third pipeline are identified by the first scale prediction model to accurately obtain the first scale data and the third scale data.

[0019] 2. The present invention identifies the temperature data change of the second pipeline during the use period to obtain temperature change data; identifies the temperature value and temperature change law of the temperature change data through a clustering algorithm to obtain temperature clustering data; then divides the second pipeline according to the temperature clustering data to obtain variable temperature sub-areas; accurately divides the areas with similar temperature distribution and change law, and accurately identifies the second scale data.

[0020] 3. The present invention sets corresponding scale thresholds for the first pipe, the second pipe and the third pipe respectively; measures the scale abnormality of the first pipe, the second pipe and the third pipe according to the scale data at the end of the period, the scale increase during the period and the scale threshold; and then integrates the scale abnormality of the first pipe, the second pipe and the third pipe through weights to obtain a scale warning coefficient; accurately identifies and warns of scale abnormalities in the water supply pipe.

[0021] 4. The present invention obtains the relationship between the heating parameters and the scale data during the process of heating the water flow of the wall-mounted boiler, and trains to obtain a heating parameter correction model; the initial water temperature, the expected water temperature and the scale data at the end of the period are identified by the heating parameter correction model to obtain the corrected heating parameters; by correcting the heating parameters, the water flow with the initial water temperature can be accurately heated to the expected temperature in the next use cycle, effectively improving the temperature control accuracy of the wall-mounted boiler. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A flow chart of a remote diagnosis method based on automated intelligent temperature control according to the present invention; Figure 2 is a schematic structural diagram of a second scale prediction model of the present invention; Figure 3 It is a structural schematic diagram of a remote diagnosis system based on automated intelligent temperature control of the present invention; Figure 4 This is a schematic diagram of the second pipeline division of the present invention.

[0023] In the figure: 11, second pipeline; 12, first section; 13, second section; 14, sub-pipeline. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0025] Embodiment 1 The present invention is a remote diagnosis method based on automated intelligent temperature control, the process of which is as follows: Figure 1 As shown, including: S10. Divide the boiler into cycles according to the usage pattern to obtain a usage cycle; at the end of the usage cycle, obtain the boiler usage parameters; the boiler usage parameters include initial scale data, water pipe parameters, water flow parameters and water quality parameters.

[0026] In the process of dividing the usage cycle, the usage pattern of the wall-mounted boiler is used as the basis; specifically, the usage cycle can be divided according to "day", "month", "quarter" and "year", etc., or it can be differentiated according to the specific usage pattern.

[0027] The initial scale data is the scale distribution data of the water supply pipe at the beginning of the use cycle of the wall-mounted boiler, which is obtained by detection by ultrasonic detection equipment; the water pipe parameters include water pipe inner diameter data, water pipe inner surface roughness and water pipe structure data; water pipe structure data is the distribution data of the water pipe in space; the water pipe inner surface roughness is obtained by detection by roughness detection equipment. The water flow parameters include water flow velocity data and water flow temperature data.

[0028] The water quality parameters include pH value and hardness data. The acidity and alkalinity of water affects the solubility of minerals such as calcium and magnesium in the water. A higher pH value will cause the precipitation of calcium and magnesium ions in the water, thereby increasing the formation of scale; the formation of scale usually begins to increase significantly when the pH value is greater than 7. The water hardness data is usually determined by the concentration of calcium and magnesium ions dissolved in the water. The higher the hardness, the greater the rate and thickness of scale formation. Among them, water quality parameters are the key factors affecting scale formation, and the mineral components in the water directly affect the rate and thickness of scale formation.

[0029] The present invention divides the use cycle according to the use pattern of the wall-mounted boiler to obtain the use cycle; collects the use parameters of the wall-mounted boiler during the use cycle, including initial scale data, water pipe parameters, water flow parameters and water quality parameters; accurately identifies the use of the wall-mounted boiler during the use cycle, and provides a data basis for subsequent scale identification.

[0030] S20. Divide the water supply pipe of the wall-mounted boiler into a first pipe, a second pipe and a third pipe; the first pipe is a water inlet pipe, the second pipe is a heat exchange pipe, and the third pipe is a water outlet pipe.

[0031] During the heating process of the wall-mounted boiler, the flow process of water can be summarized as: cold water enters the wall-mounted boiler, water exchanges heat with the heat exchanger, and hot water flows out of the wall-mounted boiler; the pipe through which the cold water enters the wall-mounted boiler is used as the water inlet pipe, that is, the first pipe; the pipe through which the water exchanges heat with the heat exchanger is used as the heat exchange pipe, that is, the second pipe; the pipe through which the hot water flows out of the wall-mounted boiler is used as the water outlet pipe, that is, the third pipe.

[0032] S30. Construct a first scale prediction model, identify the wall-mounted boiler usage parameters of the first pipeline and the third pipeline respectively, and obtain first scale data and third scale data.

[0033] The first scale prediction model is constructed based on a deep neural network model, and its training process is as follows: Obtain historical usage parameters of the wall-mounted boiler, divide the historical usage parameters according to the usage cycle, and obtain a historical cycle division data set; the historical cycle division data set includes historical initial scale data, historical end-of-period scale data, historical water pipe parameters, historical water flow parameters, and historical water quality parameters; The data set is divided according to the historical period to train and tune the model to obtain a first scale prediction model.

[0034] The first pipe and the third pipe are respectively an inlet pipe and an outlet pipe. During the passage of water, the pipe has little effect on the water flow temperature. The present invention constructs a first scale prediction model based on the characteristic that the water flow temperature in the first pipe and the third pipe is relatively stable. The initial scale data, water pipe parameters, water flow parameters and water quality parameters of the first pipe and the third pipe are identified by the first scale prediction model to accurately obtain the first scale data and the third scale data.

[0035] S40. Construct a second scale prediction model to identify the usage parameters of the wall-mounted boiler of the second pipeline; divide the second pipeline according to the temperature change data during the usage period to obtain variable temperature sub-areas; obtain scale sub-data, water pipe sub-parameters, water flow sub-parameters and water quality sub-parameters of the variable temperature sub-areas according to the usage parameters of the wall-mounted boiler of the second pipeline, identify and obtain variable temperature scale sub-data, and obtain second scale data based on the variable temperature scale sub-data.

[0036] The second scale prediction model is constructed based on a deep neural network model, and its structure is as follows: Figure 2 As shown, it includes a water pipe temperature identification layer, a variable temperature area division layer, a regional data identification layer and a regional scale identification layer; The water pipe temperature identification layer collects the temperature data of the second pipe during the use period through a temperature detection device to obtain temperature change data of the temperature changing over time; the temperature detection device includes a temperature sensor and an infrared temperature measuring device; The temperature-varying area division layer identifies the temperature variation data of the second pipeline by a clustering algorithm, takes the temperature value and the temperature variation law as clustering features, and obtains temperature clustering data; divides the second pipeline according to the temperature clustering data to obtain the temperature-varying sub-areas; The regional data recognition layer collects scale sub-data, water pipe sub-parameters, water flow sub-parameters and water quality sub-parameters of the variable temperature sub-region according to the wall-mounted boiler usage parameters of the second pipeline; The regional scale identification layer obtains variable temperature scale sub-data based on the scale sub-data of the variable temperature sub-region, water pipe sub-parameters, water flow sub-parameters and water quality sub-parameters; and obtains second scale data based on the variable temperature scale sub-data of all variable temperature sub-regions.

[0037] In order to verify the recognition effect of the second scale prediction model, a comparative experiment was conducted; There are two models in the comparison test, namely the first comparison model and the second comparison model; The first comparison model is the second scale prediction model described in the present invention, which obtains the temperature change data of the second pipeline, identifies the temperature change data of the second pipeline through a clustering algorithm, and divides it into variable temperature sub-areas; then identifies the scale data according to the variable temperature sub-areas to obtain the first comparison data. The second comparison model is based on the first model, without considering the temperature change and regional subdivision of the second pipeline, and directly identifies the initial scale data, water pipe parameters, water flow parameters and water quality parameters of the second pipeline to obtain the second comparison data.

[0038] The same verification data set is identified according to the first comparison model and the second comparison model respectively to obtain the first comparison data and the second comparison data. Then the data similarity between the first comparison data, the second comparison data and the actual scale data in the verification data set is used as the recognition accuracy. The obtained data is shown in Table 1.

[0039] Table 1 The effect verification data of the second scale prediction model

[0040] Through the above comparative experiments, it can be obtained that the scale recognition accuracy of the first comparative model is higher; that is, considering the water pipe temperature value and temperature change law for regional division and differentiated recognition, more accurate recognition results can be obtained.

[0041] The present invention identifies the temperature data change of the second pipeline during the use period to obtain temperature change data; identifies the temperature value and temperature change law of the temperature change data through a clustering algorithm to obtain temperature clustering data; then divides the second pipeline according to the temperature clustering data to obtain variable temperature sub-areas; accurately divides areas with similar temperature distribution and change law, and performs accurate scale identification.

[0042] S50. Obtain the final scale data according to the first scale data, the second scale data and the third scale data; calculate the scale warning coefficient according to the initial scale data and the final scale data, and issue a warning.

[0043] The process of the scale warning coefficient is as follows: According to the initial scale data of the first pipeline, the second pipeline and the third pipeline, a first initial scale thickness, a second initial scale thickness and a third initial scale thickness are obtained; according to the end-of-period scale data of the first pipeline, the second pipeline and the third pipeline, a first end-of-period scale thickness, a second end-of-period scale thickness and a third end-of-period scale thickness are obtained; The scale warning coefficient is calculated according to the first initial scale thickness, the second initial scale thickness, the third initial scale thickness, the scale thickness at the end of the first period, the scale thickness at the end of the second period, and the scale thickness at the end of the third period; The calculation formula of the scale warning coefficient is: ; in, Indicates scale warning coefficient; Indicates Weight; Indicates Scale thickness at the end of the period; Indicates Scale threshold; Indicates Initial scale thickness.

[0044] The present invention sets corresponding scale thresholds for the first pipeline, the second pipeline and the third pipeline respectively; measures the scale abnormality of the first pipeline, the second pipeline and the third pipeline according to the scale data at the end of the period, the scale increase during the period and the scale threshold; then integrates the scale abnormality of the first pipeline, the second pipeline and the third pipeline through weights to obtain a scale warning coefficient; and accurately identifies and warns of scale abnormalities in the water supply pipeline.

[0045] S60. Construct a heating parameter correction model to identify the end-of-period scale data, the initial water temperature of the next use cycle, and the expected water temperature to obtain a corrected heating parameter; and perform temperature control adjustment according to the corrected heating parameter.

[0046] The heating parameter correction model is constructed based on a deep neural network model, and its training process is as follows: Performing a heating test on the water supply pipeline to obtain a test data set; the test data set includes a heating target temperature, an input water temperature, test scale data, and a test heating parameter; The test heating parameters are the parameters of the wall-mounted boiler for heating the water flow from the input water temperature to the heating target temperature when testing the scale data, including gas parameters, wind pressure parameters and water pressure parameters; The model is trained according to the test data set to obtain a heating parameter correction model.

[0047] The present invention obtains the relationship between heating parameters and scale data during the process of heating water flow of a wall-mounted boiler, and trains to obtain a heating parameter correction model; the initial water temperature, the expected water temperature and the scale data at the end of the period are identified by the heating parameter correction model to obtain the corrected heating parameters; by correcting the heating parameters, the water flow with the initial water temperature can be accurately and quickly heated to the expected temperature in the next use cycle.

[0048] The remote diagnosis method based on automated intelligent temperature control can be applied to the temperature control device of a wall-mounted boiler, and current signals are received and output through the temperature control device; gas parameters, wind pressure parameters and water pressure parameters are controlled through the current signals.

[0049] The present invention also proposes a remote diagnosis system based on automatic intelligent temperature control, the structure of which is as follows: Figure 3 As shown, it includes: a data collection module, a pipeline division module, a first identification module, a second identification module, a scale warning module and a parameter adjustment module.

[0050] The data collection module divides the period according to the usage rule of the wall-mounted boiler to obtain the usage period; at the end of the usage period, the usage parameters of the wall-mounted boiler are obtained; the usage parameters of the wall-mounted boiler include initial scale data, water pipe parameters, water flow parameters and water quality parameters; The pipeline division module divides the water supply pipe of the wall-mounted boiler into a first pipeline, a second pipeline and a third pipeline; the first pipeline is a water inlet pipeline, the second pipeline is a heat exchange pipeline, and the third pipeline is a water outlet pipeline; The first identification module constructs a first scale prediction model, identifies the wall-mounted boiler usage parameters of the first pipeline and the third pipeline respectively, and obtains the first scale data and the third scale data; The second identification module constructs a second scale prediction model to identify the wall-mounted boiler usage parameters of the second pipeline; divides the second pipeline according to the temperature change data during the usage period to obtain variable temperature sub-areas; obtains scale sub-data, water pipe sub-parameters, water flow sub-parameters and water quality sub-parameters of the variable temperature sub-areas according to the wall-mounted boiler usage parameters of the second pipeline, identifies the variable temperature scale sub-data, and obtains the second scale data according to the variable temperature scale sub-data; The scale warning module obtains the final scale data according to the first scale data, the second scale data and the third scale data; calculates the scale warning coefficient according to the initial scale data and the final scale data, and issues a warning; The parameter adjustment module constructs a heating parameter correction model to identify the end-of-period scale data, the initial water temperature of the next use cycle, and the expected water temperature to obtain the corrected heating parameters; and adjusts the temperature control according to the corrected heating parameters.

[0051] The present invention obtains a use cycle by dividing the wall-mounted boiler according to the use rule; at the end of the use cycle, obtains the use parameters of the wall-mounted boiler; divides the water supply pipe of the wall-mounted boiler to obtain a first pipe, a second pipe and a third pipe; constructs a first scale prediction model, identifies the wall-mounted boiler use parameters of the first pipe and the third pipe respectively, and obtains first scale data and third scale data; constructs a second scale prediction model, identifies the wall-mounted boiler use parameters of the second pipe, and obtains second scale data; obtains end-of-period scale data according to the first scale data, the second scale data and the third scale data; calculates a scale warning coefficient according to the initial scale data and the end-of-period scale data, and issues a warning; constructs a heating parameter correction model to identify the initial water temperature, the expected water temperature and the end-of-period scale data, and obtains a corrected heating parameter; adjusts the next use cycle according to the corrected heating parameter to ensure the accuracy and efficiency of the temperature control of the wall-mounted boiler.

[0052] Embodiment 2 Factory A's main business is the design and production of wall-mounted boilers and related accessories. During the product testing of the wall-mounted boilers, Factory A found that as the usage time accumulated, scale would appear in the water supply pipes in the wall-mounted boilers, resulting in the heating efficiency being affected during the water heating process, giving users a bad experience.

[0053] In order to ensure the quality of the products, Factory A adopts the remote diagnosis method based on automated intelligent temperature control described in the present invention to identify, warn and correct the scale on the wall-mounted boiler pipes during use.

[0054] The process of the remote diagnosis method based on automated intelligent temperature control is as follows: Figure 1 As shown, including: S10. Divide the boiler into cycles according to the usage pattern to obtain the usage cycle; at the end of the usage cycle, obtain the boiler usage parameters; the boiler usage parameters include initial scale data, water pipe parameters, water flow parameters and water quality parameters; In the process of dividing the usage cycles, Factory A conducts regular inspections on the water pipes of the wall-mounted boilers every year, including using ultrasonic detection equipment to obtain scale distribution data in the water pipes; during the annual regular inspection period, Factory A divides the usage cycles according to spring, summer, autumn and winter, and obtains the first usage cycle, the second usage cycle, the third usage cycle and the fourth usage cycle.

[0055] The initial scale data is the scale distribution data of the water supply pipe of the wall-mounted boiler at the beginning of the first use cycle, which is obtained by testing with ultrasonic testing equipment; The water pipe parameters include water pipe inner diameter data, water pipe inner surface roughness and water pipe structure data; the water pipe structure data is the distribution data of the water pipe in space; the water pipe inner surface roughness is obtained by detection by roughness detection equipment.

[0056] The water flow parameters include water flow velocity data and water flow temperature data; the water quality parameters include pH value and hardness data.

[0057] S20. Divide the water supply pipe of the wall-mounted boiler into a first pipe, a second pipe and a third pipe; the first pipe is a water inlet pipe, the second pipe is a heat exchange pipe, and the third pipe is a water outlet pipe; S30. Constructing a first scale prediction model, identifying the wall-mounted boiler usage parameters of the first pipeline and the third pipeline, respectively, to obtain first scale data and third scale data; The training process of the first scale prediction model is: Obtain historical usage parameters of the wall-mounted boiler, divide the historical usage parameters according to the usage cycle, and obtain a historical cycle division data set; the historical cycle division data set includes historical initial scale data, historical end-of-period scale data, historical water pipe parameters, historical water flow parameters, and historical water quality parameters; The data set is divided according to the historical period to train and tune the model to obtain a first scale prediction model.

[0058] S40. Construct a second scale prediction model, identify the wall-mounted boiler usage parameters of the second pipeline; divide the second pipeline according to the temperature change data during the use period to obtain variable temperature sub-areas; obtain scale sub-data, water pipe sub-parameters, water flow sub-parameters and water quality sub-parameters of the variable temperature sub-areas according to the wall-mounted boiler usage parameters of the second pipeline, identify and obtain variable temperature scale sub-data, and obtain second scale data according to the variable temperature scale sub-data; The second scale prediction model is constructed based on a deep neural network model, and includes a water pipe temperature recognition layer, a variable temperature area division layer, a regional data recognition layer, and a regional scale recognition layer; The water pipe temperature identification layer collects temperature data of the second pipe during the use period through the temperature detection device to obtain temperature change data of the temperature changing with time; The collection process of temperature change data of Factory A is as follows: obtain the structural distribution of the second pipeline, divide it into sub-pipelines of equal length, detect and collect the temperature data of the sub-pipelines during their use cycle, and obtain temperature change sub-data; summarize the temperature change sub-data of all sub-pipelines to obtain the temperature change data of the second pipeline.

[0059] Taking the horizontally distributed second pipeline as an example, pipeline division is performed, such as Figure 4 As shown; the length of the second pipe 11 is obtained, which is 50 cm; the second pipe 11 is divided into sub-pipes of equal length, wherein the length of the sub-pipe 14 is 2 cm, and a total of 25 sub-pipes are obtained; the sub-pipe 14 is determined according to the first section 12 and the second section 13; the temperature data of the sub-pipe during the use period is detected and collected to obtain temperature change sub-data; the temperature change sub-data of all the sub-pipes are summarized to obtain temperature change data.

[0060] The temperature-varying area division layer identifies the temperature variation data of the second pipeline by a clustering algorithm, takes the temperature value and the temperature variation law as clustering features, and obtains temperature clustering data; divides the second pipeline according to the temperature clustering data to obtain temperature-varying sub-areas; The temperature change time data of the sub-pipelines are identified by a clustering algorithm, and clustered according to their temperature values ​​and temperature change rules to obtain temperature clustering data; the connected sub-pipelines in the temperature clustering data are divided into the same temperature change sub-area.

[0061] The regional data recognition layer collects scale sub-data, water pipe sub-parameters, water flow sub-parameters and water quality sub-parameters of the variable temperature sub-region according to the wall-mounted boiler usage parameters of the second pipeline; The regional scale identification layer obtains variable temperature scale sub-data based on the scale sub-data of the variable temperature sub-region, water pipe sub-parameters, water flow sub-parameters and water quality sub-parameters; and obtains second scale data based on the variable temperature scale sub-data of all variable temperature sub-regions.

[0062] S50. According to the first scale data, the second scale data and the third scale data, the end scale data is obtained; according to the initial scale data and the end scale data, the scale warning coefficient is calculated and an early warning is issued; The process of the scale warning coefficient is as follows: according to the initial scale data of the first pipeline, the second pipeline and the third pipeline, the first initial scale thickness, the second initial scale thickness and the third initial scale thickness are obtained; according to the end-of-period scale data of the first pipeline, the second pipeline and the third pipeline, the first end-of-period scale thickness, the second end-of-period scale thickness and the third end-of-period scale thickness are obtained; The scale thickness is the average value of the scale distribution data in the corresponding area.

[0063] The scale warning coefficient is calculated according to the first initial scale thickness, the second initial scale thickness, the third initial scale thickness, the scale thickness at the end of the first period, the scale thickness at the end of the second period, and the scale thickness at the end of the third period; The calculation formula of the scale warning coefficient is: ; in, Indicates scale warning coefficient; Indicates Weight; Indicates Scale thickness at the end of the period; Indicates Scale threshold; Indicates Initial scale thickness.

[0064] The initial scale thickness and final scale thickness of the first pipe, the second pipe and the third pipe during the first use cycle of the wall-mounted boiler are obtained; the scale threshold is then set according to the design parameters of the product and the relevant data of the scale fault; the obtained data are shown in Table 2.

[0065] Table 2 Scale data table of water supply pipes

[0066] S60. Construct a heating parameter correction model to identify the end-of-period scale data, the initial water temperature of the next use cycle, and the expected water temperature to obtain a corrected heating parameter; and perform temperature control adjustment according to the corrected heating parameter.

[0067] The training process of the heating parameter correction model is: Perform a heating test on the water supply pipeline to obtain a test data set; the test data set includes a heating target temperature, an input water temperature, test scale data and a test heating parameter; the test heating parameter is a wall-mounted boiler parameter setting for heating the water flow from the input water temperature to the heating target temperature under the condition of the test scale data; including gas parameters, wind pressure parameters and water pressure parameters; The model is trained according to the test data set to obtain a heating parameter correction model.

[0068] In order to verify the temperature control effect of the method of the present invention, a verification experiment is performed; the experiment includes two temperature control methods, namely the first temperature control method and the second temperature control method; The first temperature control method is a remote diagnosis method based on automated intelligent temperature control described in the present invention, in which the first pipe, the second pipe and the third pipe are obtained by dividing the water supply pipe of the wall-mounted boiler; the first pipe, the second pipe and the third pipe are respectively identified by the model to obtain the end-of-period scale data; and the heating parameter correction model is used to adjust the temperature control according to the end-of-period scale data, the initial water temperature and the expected water temperature; the second temperature control method is to set a temperature sensor at the water outlet to collect the water temperature data of the water outlet; and then compare and feedback-adjust based on the water temperature data of the water outlet and the expected water temperature.

[0069] A total of three groups of verification experiments were conducted. The initial water temperature of the first group of verification experiments was 12 degrees Celsius and the expected water temperature was 25 degrees Celsius; the initial water temperature of the second group of verification experiments was 15 degrees Celsius and the expected water temperature was 25 degrees Celsius; the initial water temperature of the third group of verification experiments was 18 degrees Celsius and the expected water temperature was 25 degrees Celsius. In the temperature control process of the water flow, the expected temperature range is set based on the expected water temperature, and the time when the water temperature at the water outlet first reaches the expected temperature range is used as the temperature control duration; the temperature control accuracy is obtained based on the difference between the average temperature of the water outlet and the expected water temperature from the time when the water temperature at the water outlet first reaches the expected temperature range to the end of the test; the calculation formula for the temperature control accuracy is: ; in, Indicates temperature control accuracy; Indicates the average water temperature; Indicates the desired water temperature.

[0070] In the three groups of verification experiments, multiple experiments were conducted respectively, and the average value of the experimental data was taken to measure the effect, and the experimental data obtained are shown in Table 3.

[0071] Table 3 Temperature control effect verification data table

[0072] From the data in Table 3, it can be seen that the temperature control time of the first temperature control method in the three groups of verification tests is shorter than that of the second temperature control method; at the same time, the temperature control accuracy of the first temperature control method is higher than that of the second temperature control method, that is, the first temperature control method can heat the water flow more accurately and efficiently.

[0073] Through the remote diagnosis method based on automated intelligent temperature control described in the present invention, Factory A can accurately identify and warn of scale based on the user's quarterly wall-mounted boiler usage during the annual regular inspection, and adjust the temperature control parameters according to the scale situation, thereby effectively improving the temperature control accuracy and efficiency of the wall-mounted boiler and ensuring the user experience.

[0074] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A remote diagnosis method based on automated intelligent temperature control, characterized in that: include: S10. Divide the boiler into cycles according to the usage pattern to obtain the usage cycle; at the end of the usage cycle, obtain the boiler usage parameters; the boiler usage parameters include initial scale data, water pipe parameters, water flow parameters and water quality parameters; S20. Divide the water supply pipe of the wall-mounted boiler into a first pipe, a second pipe and a third pipe; the first pipe is a water inlet pipe, the second pipe is a heat exchange pipe, and the third pipe is a water outlet pipe; S30. Constructing a first scale prediction model, identifying the wall-mounted boiler usage parameters of the first pipeline and the third pipeline, respectively, to obtain first scale data and third scale data; S40. Construct a second scale prediction model, identify the wall-mounted boiler usage parameters of the second pipeline; divide the second pipeline according to the temperature change data during the use period to obtain variable temperature sub-areas; obtain scale sub-data, water pipe sub-parameters, water flow sub-parameters and water quality sub-parameters of the variable temperature sub-areas according to the wall-mounted boiler usage parameters of the second pipeline, identify and obtain variable temperature scale sub-data, and obtain second scale data according to the variable temperature scale sub-data; S50. According to the first scale data, the second scale data and the third scale data, the end scale data is obtained; according to the initial scale data and the end scale data, the scale warning coefficient is calculated and an early warning is issued; S60. Construct a heating parameter correction model to identify the end-of-period scale data, the initial water temperature of the next use cycle, and the expected water temperature to obtain a corrected heating parameter; and perform temperature control adjustment according to the corrected heating parameter.

2. A remote diagnosis method based on automated intelligent temperature control according to claim 1, characterized in that: The initial scale data is the scale distribution data of the water supply pipe at the beginning of the use cycle of the wall-mounted boiler; The water pipe parameters include water pipe inner diameter data, water pipe inner surface roughness and water pipe structure data; The water flow parameters include water flow velocity data and water flow temperature data; The water quality parameters include pH value and hardness data.

3. The remote diagnosis method based on automated intelligent temperature control according to claim 1, characterized in that: The training process of the first scale prediction model is: Acquire historical usage parameters of the wall-mounted boiler, divide the historical usage parameters according to usage cycles, and obtain a historical cycle division data set; The historical period division data set includes historical initial scale data, historical end-of-period scale data, historical water pipe parameters, historical water flow parameters and historical water quality parameters; The data set is divided according to the historical period to train and tune the model to obtain a first scale prediction model.

4. The remote diagnosis method based on automated intelligent temperature control according to claim 1, characterized in that: The second scale prediction model includes a water pipe temperature identification layer, a variable temperature area division layer, a regional data identification layer and a regional scale identification layer; The water pipe temperature identification layer collects temperature data of the second pipe during the use period through the temperature detection device to obtain temperature change data of the temperature changing with time; The temperature-varying area division layer identifies the temperature variation data of the second pipeline by a clustering algorithm, takes the temperature value and the temperature variation law as clustering features, and obtains temperature clustering data; divides the second pipeline according to the temperature clustering data to obtain the temperature-varying sub-areas; The regional data recognition layer collects scale sub-data, water pipe sub-parameters, water flow sub-parameters and water quality sub-parameters of the variable temperature sub-region according to the wall-mounted boiler usage parameters of the second pipeline; The regional scale identification layer obtains variable temperature scale sub-data based on the scale sub-data of the variable temperature sub-region, water pipe sub-parameters, water flow sub-parameters and water quality sub-parameters; and obtains second scale data based on the variable temperature scale sub-data of all variable temperature sub-regions.

5. The remote diagnosis method based on automated intelligent temperature control according to claim 1, characterized in that: The process of the scale warning coefficient is as follows: according to the initial scale data of the first pipeline, the second pipeline and the third pipeline, the first initial scale thickness, the second initial scale thickness and the third initial scale thickness are obtained; according to the end-of-period scale data of the first pipeline, the second pipeline and the third pipeline, the first end-of-period scale thickness, the second end-of-period scale thickness and the third end-of-period scale thickness are obtained; the scale thickness is the average value of the corresponding pipeline scale data; The scale warning coefficient is calculated according to the first initial scale thickness, the second initial scale thickness, the third initial scale thickness, the scale thickness at the end of the first period, the scale thickness at the end of the second period, and the scale thickness at the end of the third period; The calculation formula of the scale warning coefficient is: ； in, Indicates scale warning coefficient; Indicates Weight; Indicates Scale thickness at the end of the period; Indicates Scale threshold; Indicates Initial scale thickness.

6. A remote diagnosis method based on automated intelligent temperature control according to claim 1, characterized in that: The training process of the heating parameter correction model is: Performing a heating test on the water supply pipeline to obtain a test data set; the test data set includes a heating target temperature, an input water temperature, test scale data, and a test heating parameter; The test heating parameters are the parameters of the wall-mounted boiler for heating the water flow from the input water temperature to the heating target temperature when testing the scale data, including gas parameters, wind pressure parameters and water pressure parameters; The model is trained according to the test data set to obtain a heating parameter correction model.

7. A remote diagnosis system based on automated intelligent temperature control, characterized in that: include: The data collection module divides the period according to the usage rule of the wall-mounted boiler to obtain the usage period; at the end of the usage period, the usage parameters of the wall-mounted boiler are obtained; the usage parameters of the wall-mounted boiler include initial scale data, water pipe parameters, water flow parameters and water quality parameters; The pipeline division module divides the water supply pipe of the wall-mounted boiler into a first pipeline, a second pipeline and a third pipeline; the first pipeline is a water inlet pipeline, the second pipeline is a heat exchange pipeline, and the third pipeline is a water outlet pipeline; The first identification module constructs a first scale prediction model, identifies the wall-mounted boiler usage parameters of the first pipeline and the third pipeline respectively, and obtains the first scale data and the third scale data; The second identification module constructs a second scale prediction model to identify the wall-mounted boiler usage parameters of the second pipeline; divides the second pipeline according to the temperature change data during the usage period to obtain variable temperature sub-areas; obtains scale sub-data, water pipe sub-parameters, water flow sub-parameters and water quality sub-parameters of the variable temperature sub-areas according to the wall-mounted boiler usage parameters of the second pipeline, identifies the variable temperature scale sub-data, and obtains the second scale data according to the variable temperature scale sub-data; A scale warning module obtains end-of-period scale data according to the first scale data, the second scale data and the third scale data; The scale warning coefficient is calculated based on the initial scale data and the final scale data to issue a warning; The parameter adjustment module constructs a heating parameter correction model to identify the end-of-period scale data, the initial water temperature of the next use cycle, and the expected water temperature to obtain the corrected heating parameters; and adjusts the temperature control according to the corrected heating parameters.

8. A remote diagnosis system based on automated intelligent temperature control according to claim 7, characterized in that: The wall-mounted boiler usage parameters in the data collection module specifically include: The initial scale data is the scale distribution data of the water supply pipe at the beginning of the use cycle of the wall-mounted boiler; the water pipe parameters include water pipe inner diameter data, water pipe inner surface roughness and water pipe structure data; the water flow parameters include water flow velocity data and water flow temperature data; the water quality parameters include pH value and hardness data.

9. The remote diagnosis system based on automated intelligent temperature control according to claim 7, characterized in that: The training process of the first scale prediction model in the first recognition module is: Acquire historical usage parameters of the wall-mounted boiler, divide the historical usage parameters according to usage cycles, and obtain a historical cycle division data set; The historical period division data set includes historical initial scale data, historical end-of-period scale data, historical water pipe parameters, historical water flow parameters and historical water quality parameters; The data set is divided according to the historical period to train and tune the model to obtain a first scale prediction model.

10. The remote diagnosis system based on automated intelligent temperature control according to claim 7, characterized in that: The training process of the heating parameter correction model in the parameter adjustment module is as follows: Performing a heating test on the water supply pipeline to obtain a test data set; the test data set includes a heating target temperature, an input water temperature, test scale data, and a test heating parameter; The test heating parameters are the parameters of the wall-mounted boiler that heat the water flow from the input water temperature to the heating target temperature when testing the scale data; including gas parameters, wind pressure parameters and water pressure parameters; The model is trained according to the test data set to obtain a heating parameter correction model.

Images