A temperature measuring device for water heater energy efficiency testing

Abstract

The present invention relates to a temperature measuring device for water heater energy efficiency testing, and relates to the field of temperature measurement technology. The device comprises a high-precision RTD sensor, a data acquisition module, an intelligent control unit and a data visualization unit. The high-precision RTD sensor is used to measure the temperature of the water heater in real time, and the data acquisition module obtains temperature data at a high frequency, and pre-processes the collected signal data to ensure data continuity and accuracy. The intelligent control unit processes and optimizes the temperature data in combination with time series prediction algorithms such as LSTM or GRU. Through data preprocessing, time series prediction and real-time correction, the measurement accuracy and response speed are significantly improved. The data visualization unit displays and records temperature data in real time, which is convenient for users to monitor and analyze. The device can predict temperature changes in advance and perform dynamic corrections, reduce the impact of environmental interference, optimize the water heater energy efficiency test process, improve test efficiency and accuracy, and reduce equipment maintenance costs and extend service life.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature measurement, and in particular to a temperature measurement device for water heater energy efficiency testing, especially combining a time series prediction algorithm to improve temperature measurement accuracy and response speed. Background Art

[0002] At present, the temperature measurement devices used for water heater energy efficiency testing mainly include thermocouples, resistance temperature detectors (RTDs) and infrared thermometers. These devices have their own advantages and disadvantages. For example, thermocouples have fast response speed but low accuracy, RTDs have high accuracy but slow response speed, and infrared thermometers are convenient for non-contact measurement but are easily affected by the environment. The existing technologies generally have problems such as slow measurement response speed, poor environmental adaptability, and limited data processing capabilities, which affect the accuracy and efficiency of water heater energy efficiency testing.

[0003] In order to overcome the above problems, a variety of optimization solutions have been proposed in the prior art, but the results are still unsatisfactory. For example, although increasing the number of measurement points can improve the measurement accuracy, it also increases the complexity and cost of the system. In addition, traditional control algorithms have limitations in processing real-time responses to temperature changes and cannot effectively cope with rapidly changing temperature environments. Summary of the invention

[0004] In view of the shortcomings of the existing temperature measurement device for water heater energy efficiency test, the present invention provides a temperature measurement device for water heater energy efficiency test to improve the measurement accuracy and response speed and optimize the test process. The device mainly combines high-precision RTD sensors and advanced time series prediction algorithms (such as LSTM or GRU) to process temperature data, thereby achieving more accurate and efficient energy efficiency testing.

[0005] The structure of the temperature measuring device includes the following parts:

[0006] 1. High-precision RTD sensor: used to measure the temperature of the water heater in real time. RTD sensor has the advantages of high accuracy and stability, suitable for long-term use.

[0007] 2. Data acquisition module: used to collect and record the data of RTD sensor. This module can obtain temperature data at a high frequency to ensure the continuity and accuracy of the data.

[0008] 3. Intelligent control unit: The core part, combined with the time series prediction algorithm, processes and optimizes the collected temperature data.

[0009] 4. Data visualization unit: used to display and record temperature data in real time for user monitoring and analysis.

[0010] Among them, the time series prediction algorithm is one of the core technologies of the present invention. By predicting the time series of temperature data, the temperature change trend can be estimated in advance and dynamic correction can be performed. The specific implementation steps are as follows:

[0011] (1) Data preprocessing:

[0012] Denoising: Use methods such as Moving Average Filter or Kalman Filter to denoise the collected temperature data and eliminate random noise in the data. in, Indicates the current time t The filtered temperature data; Before i The original temperature data at each moment; N Indicates the average size of the window movement during filtering.

[0013] Smoothing: Exponential smoothing is used to smooth the data to further improve the stability of the data. in, S t Represents the smoothed temperature data at the current time t; α is the smoothing factor, ranging from 0 to 1.

[0014] Normalization: Normalize the temperature data to make the data meet the input requirements of subsequent algorithms. in, is the normalized temperature data, max( x ) and min( x ) are the maximum and minimum values ​​in the data set, respectively.

[0015] (2) Time series prediction:

[0016] LSTM model: Long Short-Term Memory (LSTM) is a deep learning model suitable for processing time series data. LSTM can effectively capture the long-term dependency of temperature changes through the memory and forget mechanism. in, h t represents the hidden state at the current moment; σ is the enabling activation function; W h is the weight matrix; h t-1 is the hidden state at the previous moment; x t is the input data at the current moment; b h is the bias term.

[0017] GRU model: The Gated Recurrent Unit (GRU) is a simplified LSTM model with similar time series processing capabilities but higher computational efficiency. in, z t represents the output of the update gate; W z is the weight matrix; b z is the bias term.

[0018] (3) Real-time correction:

[0019] Deviation calculation: Compare the predicted temperature data with the real-time measurement data and calculate the deviation:

[0020] in, is the temperature deviation, T measure For real-time temperature data, T predicted The predicted temperature data.

[0021] Dynamic correction: Use PID controller to correct the deviation in real time and adjust the parameters of the measurement system:

[0022] in, P ( t ) is the corrected control parameter, k p , k i , k d are the proportional, integral and differential coefficients respectively.

[0023] According to the corrected data, the sampling frequency of the RTD sensor and the response speed of the data processing module are adjusted in real time to ensure that the system can respond quickly to temperature changes.

[0024] The collected temperature data is recorded in the data visualization unit and a graphical representation of the temperature data is displayed in real time.

[0025] Compared with the prior art, one or more of the above technical solutions have the following beneficial effects:

[0026] (1) Combining high-precision RTD sensors and intelligent control algorithms to improve the accuracy of temperature measurement and ensure the reliability of water heater energy efficiency test results. Traditional temperature measurement devices are often unable to accurately reflect the actual energy efficiency of water heaters due to limitations on sensor accuracy and environmental interference. However, by introducing time series prediction algorithms such as LSTM or GRU, the present invention can more accurately predict and correct temperature data, significantly improving measurement accuracy.

[0027] (2) Through the time series prediction algorithm, the temperature change is estimated in advance and corrected in real time, which improves the dynamic response capability of the system and can reflect the temperature change more quickly. Traditional methods usually rely on fixed sampling frequency and data processing methods, which makes it difficult to provide fast and accurate response when the temperature changes drastically. The present invention ensures that the measurement system can respond quickly and maintain efficient operation under various working conditions by adaptively adjusting the sampling frequency and processing speed.

[0028] (3) Reduce the impact of environmental changes on temperature measurement, optimize the water heater energy efficiency test process, and improve test efficiency and accuracy. During the test process, traditional measurement devices are often affected by factors such as ambient temperature fluctuations and sensor drift, resulting in unstable measurement results. The present invention can dynamically compensate for these interference factors through an intelligent control unit and a real-time correction mechanism to ensure the stability of the test process and the consistency of the results.

[0029] (4) By improving measurement accuracy and response speed, the need for manual intervention and debugging is reduced, and the equipment maintenance cost is reduced. Traditional temperature measurement devices are prone to problems such as sensor aging and data drift during long-term use, requiring frequent maintenance and calibration, which increases the cost of use. By introducing advanced prediction and correction algorithms, the present invention can extend the service life of the equipment and reduce the maintenance frequency, thereby saving costs and improving economic benefits.

[0030] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 It is a structural schematic diagram of a temperature measuring device for water heater energy efficiency testing mentioned in the present invention;

[0032] Figure 2 A flowchart showing the specific operation steps of the temperature measuring device for testing the energy efficiency of water heaters mentioned in the present invention; DETAILED DESCRIPTION

[0033] In order to better understand the present invention, the content of the present invention is further explained below in conjunction with the drawings and implementations. However, the content of the present invention is not limited to the following scenarios. The present invention is further explained below in conjunction with the drawings.

[0034] This embodiment demonstrates a specific application of a temperature measurement device for water heater energy efficiency testing. The system consists of a high-precision RTD sensor, a data acquisition module, an intelligent control unit, and a display and recording unit, and combines time series prediction algorithms such as LSTM or GRU to achieve real-time temperature monitoring and correction, and improve measurement accuracy and response speed.

[0035] See also Figure 1 , shown is a temperature measuring device for water heater energy efficiency testing provided by the present invention, and the entire device system may specifically include the following parts:

[0036] Specifically, a high-precision RTD sensor is installed at a key position of the water heater to measure the temperature of the water heater in real time. The RTD sensor is then connected through a data acquisition module, which is responsible for collecting temperature data at a high frequency and transmitting the data to the intelligent control unit.

[0037] Preferably, the intelligent control unit has a built-in time series prediction algorithm, which can process and optimize the collected temperature data. A data visualization unit is also built to display temperature data in real time and record test results, which is convenient for operators to monitor and analyze.

[0038] Furthermore, the specific use steps of the temperature measurement device for water heater energy efficiency testing provided by the present invention are as follows:

[0039] Step 1: System installation and initialization. Install the high-precision RTD sensor at the water inlet and outlet of the water heater or other key locations to ensure that the sensor can accurately measure the temperature inside the water heater; connect the data acquisition module and connect the acquisition module to the intelligent control unit; start the system and perform initialization settings, including sensor calibration, data acquisition frequency setting, etc.; finally. Output the collected and processed data to the numerical visualization unit interface through the bus, and display the data to be output in real time.

[0040] Step 2: Data acquisition and preprocessing. During the test, the data acquisition module collects temperature data from the RTD sensor at a set frequency (e.g., once per second). The collected data is transmitted to the intelligent control unit via a cable for preprocessing.

[0041] Furthermore, the preprocessing steps include denoising, smoothing and normalization. A moving average filter or a Kalman filter is used to denoise the data and eliminate random noise. The following is the calculation formula of the moving average filter. in, Indicates the current time t The filtered temperature data; Before i The original temperature data at each moment; N Indicates the average size of the window movement during filtering, that is, the number of moments used to calculate the average value.

[0042] Then, the data is smoothed using exponential smoothing to further improve the stability of the data. in, S t Represents the smoothed temperature data at the current time t; α is the smoothing factor (0<α<1), which controls the weight of the current temperature data and the past temperature data; x t Represents the original temperature data at the current moment; S t-1 Indicates the smoothed temperature data of the previous moment.

[0043] Step 3: Time series prediction of temperature data. After completing the data preprocessing, the data is transmitted to the intelligent control unit. The intelligent control unit then uses the LSTM model or GRU model to perform time series prediction on the preprocessed temperature data.

[0044] Specifically, the LSTM model uses memory gates to decide which past information to forget and which current information to remember, capturing the long-term dependencies of temperature changes. in, h t represents the hidden state at the current moment; σ is the enabling activation function; W h is the weight matrix; h t-1 is the hidden state at the previous moment; x t is the input data at the current moment; b h is the bias term.

[0045] The GRU model controls the fusion of current information and past information through the update gate, determines the update degree of the current hidden state, and realizes efficient time series processing. in, z t represents the output of the update gate; W z is the weight matrix; b z is the bias term.

[0046] Step 4: Real-time correction and control. Finally, compare the predicted temperature data with the real-time measured temperature data and calculate the temperature deviation: in, is the temperature deviation, T measure For real-time temperature data, T predicted The predicted temperature data.

[0047] The PID controller is used to correct the deviation in real time and adjust the parameters of the measurement system:

[0048] in, P ( t ) is the corrected control parameter, kp , k i , k d are the proportional, integral and differential coefficients respectively.

[0049] The corrected data is used to adaptively adjust the sampling frequency of the RTD sensor and the response speed of the data processing module to ensure that the system can quickly respond to temperature changes.

[0050] Step 5: Data visualization and analysis. The corrected temperature data is displayed in real time through the data visualization unit, and the test results are recorded. Users can observe the temperature changes through the display screen and conduct subsequent analysis by recording the data.

[0051] Specifically, after the test, all recorded data is exported for analysis. By comparing real-time measurement data with predicted data, the measurement accuracy and response speed of the system are evaluated. Based on the analysis results, the LSTM or GRU model is optimized to further improve the performance of the system. With this data, users can make a more accurate assessment of the energy efficiency of the water heater and debug and optimize the equipment based on the test results.

[0052] In combination with the above embodiments, the temperature measurement device proposed in the present invention has higher accuracy and response speed compared with the traditional RTD temperature measurement device; by combining high-precision RTD sensors and advanced time series prediction algorithms (such as LSTM or GRU), the system can measure temperature changes more quickly and accurately. Algorithmic prediction can predict temperature fluctuations in advance and make dynamic adjustments, thereby improving the real-time and accuracy of the measurement. In addition, the system has a real-time correction mechanism that can automatically adjust the temperature measurement parameters during the measurement process to ensure the timeliness and accuracy of the data. This function reduces the impact of environmental changes on the measurement results and improves the reliability and consistency of the test.

[0053] In summary, the present invention significantly improves the accuracy and response speed of temperature measurement by combining high-precision RTD sensors and advanced time series prediction algorithms (such as LSTM and GRU), ensuring the reliability of water heater energy efficiency test results. Using these advanced algorithms, the system can predict temperature changes in advance and make dynamic adjustments, thereby optimizing the test process, reducing the impact of environmental changes on measurement results, and improving test efficiency and accuracy. In addition, through the real-time correction mechanism, the system can automatically adjust the temperature measurement during the measurement process to ensure the timeliness and accuracy of the data.

[0054] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0055] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the patent of the present invention. It should be pointed out that, for those of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A temperature measuring device for water heater energy efficiency testing, characterized in that: The device comprises: High-precision RTD sensor for real-time measurement of water heater temperature; Data acquisition module, used to collect and record the data of RTD sensor and pre-process the collected data; The intelligent control unit, combined with the time series prediction algorithm, processes and optimizes the pre-processed temperature data, and then adjusts the control parameters of the system in real time through the temperature correction module to ensure that the system responds quickly to temperature changes; Data visualization unit for real-time display and recording of temperature data; The time series forecast uses LSTM or GUR model to capture the long-term dependency of temperature changes through memory and forget mechanism; Among them, h t represents the hidden state at the current moment; σ is the enabling activation function; W h is the weight matrix; h t-1 is the hidden state at the previous moment; x t is the input data at the current moment; b h is the bias term; Among them, z t represents the output of the update gate; W z is the weight matrix; b z is the bias term; The input of the time series prediction model is the normalized temperature data, and the output is the predicted temperature value; The intelligent control unit compares the predicted temperature data with the real-time measurement data through the temperature correction module to calculate the temperature deviation; Where ΔT is the temperature deviation, T measure For real-time temperature data, T predicted is the predicted temperature data; Use PID controller to correct the deviation in real time and adjust the parameters of the measurement system; in, P ( t ) is the corrected control parameter, k p ,k i ,k d are the proportional, integral and differential coefficients respectively; The PID controller adjusts the sampling frequency of the RTD sensor and the response speed of the data processing module in real time according to the corrected data, ensuring that the system responds quickly to temperature changes.

2. The temperature measuring device according to claim 1, characterized in that: Data preprocessing includes denoising, smoothing and normalization; Among them, denoising uses a moving average filter to eliminate random noise: in, Indicates the current time t The filtered temperature data; Represents the original temperature data at the previous i moments; N Indicates the average size of the window movement during filtering; Then use exponential smoothing to improve data stability: in, S t represents the smoothed temperature data at the current time t; α is the smoothing factor, ranging from 0 to 1; Finally, the temperature data is normalized to meet the input requirements of the subsequent optimization algorithm: in, is the normalized temperature data, max(x) and min(x) are the maximum and minimum values ​​in the data set, respectively.

3. The temperature measuring device according to claim 1, characterized in that: The data visualization unit has the capability of visualizing temperature data.

Images