Energy consumption evaluation method and system for heat pump system

Abstract

The present invention relates to the technical field of energy consumption assessment, and discloses an energy consumption assessment method and system for a heat pump system. The method comprises: determining a current energy consumption value based on output temperature data and indoor temperature data, obtaining historical output temperature data and historical indoor temperature data and determining a predicted energy consumption value based on a random forest model, analyzing each scale image to determine a comprehensive amount of scale in the evaporator, comparing the comprehensive amount of scale with historical scale data, judging whether the comprehensive amount of scale is correct based on the comparison result, determining a predicted amount of scale based on the historical scale data when the scale similarity is greater than or equal to a scale similarity threshold, determining a predicted amount of scale based on a scale correction set when the scale similarity is less than the scale similarity threshold, and determining a target predicted energy consumption value based on an energy consumption correction coefficient and the predicted energy consumption value. The present invention improves the reliability of energy consumption assessment of a heat pump system by analyzing the scale in the evaporator.

Description

Technical Field

[0001] The present invention relates to the technical field of energy consumption assessment, and in particular to an energy consumption assessment method and system for a heat pump system. Background Art

[0002] With the growth of population, the demand for heating in indoor residential areas is increasing. The heat pump system is a system that uses water resources to convert energy. Its energy consumption lies in the heat exchange made by electrical energy. Therefore, how to accurately evaluate energy consumption is crucial to optimizing the operating efficiency of the heat pump system and reducing energy waste.

[0003] Currently, energy consumption assessments for heat pump systems rely primarily on manual judgment, which can be inaccurate due to the varying experience of different testers. Furthermore, these assessments often overlook the impact of scale buildup on the evaporator during the heat pump cycle. Scale accumulation reduces heat conversion efficiency, requiring the heat pump system to consume more energy to maintain the same heat output. Existing energy consumption assessments fail to effectively analyze scale, leading to inaccurate results and an inability to effectively predict heat pump system energy consumption.

[0004] Therefore, how to provide an energy consumption evaluation method and system for a heat pump system is a technical problem that those skilled in the art urgently need to solve. Summary of the Invention

[0005] In view of this, the present invention proposes an energy consumption assessment method and system for a heat pump system, aiming to solve the problem that relying on manual experience will lead to insufficient accuracy of energy consumption assessment results, no effective analysis of scale, resulting in inaccurate energy consumption assessment results, and inability to effectively predict energy consumption of the heat pump system.

[0006] In one aspect, the present invention provides an energy consumption assessment method for a heat pump system, comprising:

[0007] Obtaining output temperature data of a heat pump system and indoor temperature data of a residential area, determining a current energy consumption value based on the output temperature data and the indoor temperature data, obtaining historical output temperature data and historical indoor temperature data and determining a predicted energy consumption value based on a random forest model;

[0008] Dividing the evaporator into a plurality of scale detection areas, obtaining a scale image of each scale detection area, analyzing each scale image to determine a comprehensive scale quantity of the evaporator, comparing the comprehensive scale quantity with historical scale data, and determining whether the comprehensive scale quantity is correct based on the comparison result; if the comprehensive scale quantity is determined to be incorrect, determining a scale similarity based on the comprehensive scale quantity and the historical scale data;

[0009] When the scale similarity is greater than or equal to the scale similarity threshold, the predicted scale quantity is determined based on the historical scale data; when the scale similarity is less than the scale similarity threshold, the historical scale data is divided into sets to determine a scale correction set, and the predicted scale quantity is determined based on the scale correction set;

[0010] An energy consumption correction coefficient of the predicted energy consumption value is set according to the predicted amount of scale, and a target predicted energy consumption value is determined according to the energy consumption correction coefficient and the predicted energy consumption value.

[0011] Furthermore, when obtaining the output temperature data of the heat pump system and the indoor temperature data of the residential area, and determining the current energy consumption value according to the output temperature data and the indoor temperature data, the method includes:

[0012] Obtaining a power input value and an output temperature value of the heat pump system, and obtaining an average indoor temperature of the residential area;

[0013] The current energy consumption value is obtained by the following formula:

[0014] ;

[0015] Among them, Z1 represents the current energy consumption value, P1 represents the power input value of the heat pump system, T1 represents the output temperature value, and T2 represents the average indoor temperature.

[0016] Furthermore, when obtaining historical output temperature data and historical indoor temperature data and determining the predicted energy consumption value based on the random forest model, it includes:

[0017] The historical output temperature data and the historical indoor temperature data are constructed into a data set, and the data set is divided into a training set and a test set. A grid search is used to find the establishment parameters of a random forest model, and a random forest model is established. The random forest model is fitted using the training set, and the test set is brought into the random forest model to calculate the accuracy of the predicted energy consumption value;

[0018] When the accuracy reaches a preset accuracy threshold, the current energy consumption value is substituted into the random forest model to determine the predicted energy consumption value.

[0019] Furthermore, when obtaining a scale image of each scale detection area and analyzing each scale image to determine the comprehensive amount of scale on the evaporator, the method includes:

[0020] Preprocessing the scale image of each scale detection area, wherein the preprocessing includes image noise reduction and image size adjustment, and determining a scale-processed image of each scale detection area according to the preprocessing result;

[0021] Extracting scale pixels from all scale-processed images, determining the scale pixel features of each scale pixel, and obtaining the feature mean of the scale pixel features;

[0022] The scale pixel points whose scale pixel characteristics are greater than the characteristic mean are divided into the first scale series, the scale pixel points whose scale pixel characteristics are equal to the characteristic mean are divided into the second scale series, and the scale pixel points whose scale pixel characteristics are less than the characteristic mean are divided into the third scale series;

[0023] A first scale quantity of scale pixels in the first scale series is counted, and a second scale quantity of scale pixels in the second scale series is counted. The comprehensive scale quantity of the evaporator is the sum of the first scale quantity and the second scale quantity.

[0024] Furthermore, when comparing the comprehensive amount of scale with historical scale data and judging whether the comprehensive amount of scale is correct based on the comparison result, the method includes:

[0025] The historical scale data includes the maximum historical scale comprehensive quantity, the average historical scale comprehensive quantity and all historical scale comprehensive quantities;

[0026] When the comprehensive amount of scale is greater than or equal to the maximum comprehensive amount of historical scale, it is determined that the comprehensive amount of scale is correct, and the comprehensive amount of scale is determined as the predicted amount of scale;

[0027] When the comprehensive amount of scale is less than the maximum comprehensive amount of historical scale, it is determined that the comprehensive amount of scale is incorrect.

[0028] Furthermore, when determining the scale similarity based on the comprehensive scale quantity and the historical scale data, the method includes:

[0029] The scale similarity is obtained by the following formula:

[0030] ;

[0031] Among them, S represents the scale similarity, G1 represents the comprehensive number of scale, G2 represents the maximum comprehensive number of scale in history, and G3 represents the mean comprehensive number of scale in history.

[0032] Furthermore, when the scale similarity is greater than or equal to the scale similarity threshold, the predicted scale quantity is determined based on the historical scale data; when the scale similarity is less than the scale similarity threshold, the historical scale data is divided into sets to determine a scale correction set, and the predicted scale quantity is determined based on the scale correction set, including:

[0033] Pre-set scale similarity threshold;

[0034] When the scale similarity is greater than or equal to the scale similarity threshold, the maximum value of the historical scale integrated quantity is determined as the scale prediction quantity;

[0035] The scale correction set includes a first scale correction set, a second scale correction set and a third scale correction set;

[0036] When the scale similarity is less than the scale similarity threshold, the historical scale integrated quantity greater than the mean of the historical scale integrated quantity is divided into the scale correction first set, the historical scale integrated quantity equal to the mean of the historical scale integrated quantity is divided into the scale correction second set, and the historical scale integrated quantity less than the mean of the historical scale integrated quantity is divided into the scale correction third set;

[0037] A scale prediction amount is determined according to the scale correction first set, the scale correction second set, and the scale correction third set.

[0038] Furthermore, when determining the predicted amount of scale according to the first scale correction set, the second scale correction set, and the third scale correction set, the method includes:

[0039] The predicted amount of scale is obtained by the following formula:

[0040] ;

[0041] Among them, K represents the predicted number of scale, G2 represents the maximum value of the historical comprehensive number of scale, Y1 represents the maximum value of the historical comprehensive number of scale in the first set of scale correction, Y2 represents the minimum value of the historical comprehensive number of scale in the first set of scale correction, U1 represents the maximum value of the historical comprehensive number of scale in the second set of scale correction, U2 represents the minimum value of the historical comprehensive number of scale in the second set of scale correction, I1 represents the maximum value of the historical comprehensive number of scale in the third set of scale correction, and I2 represents the minimum value of the historical comprehensive number of scale in the third set of scale correction.

[0042] Furthermore, when setting an energy consumption correction coefficient of the predicted energy consumption value according to the predicted amount of scale, and determining a target predicted energy consumption value according to the energy consumption correction coefficient and the predicted energy consumption value, the method includes:

[0043] Presetting a first preset scale prediction number and a second preset scale prediction number, wherein the first preset scale prediction number is greater than the second preset scale prediction number;

[0044] Presetting a first preset energy consumption correction coefficient, a second preset energy consumption correction coefficient, and a third preset energy consumption correction coefficient, wherein the first preset energy consumption correction coefficient is greater than the second preset energy consumption correction coefficient, and the second preset energy consumption correction coefficient is greater than the third preset energy consumption correction coefficient;

[0045] When the predicted amount of scale is greater than the first preset predicted amount of scale, the first preset energy consumption correction coefficient is used as the energy consumption correction coefficient of the predicted energy consumption value;

[0046] When the predicted scale amount is less than or equal to the first preset predicted scale amount and greater than the second preset predicted scale amount, the second preset energy consumption correction coefficient is used as the energy consumption correction coefficient of the predicted energy consumption value;

[0047] When the predicted scale amount is less than or equal to the second preset predicted scale amount, the third preset energy consumption correction coefficient is used as the energy consumption correction coefficient of the predicted energy consumption value;

[0048] The target predicted energy consumption value is the product of the predicted energy consumption value and the energy consumption correction coefficient.

[0049] Compared with existing technologies, the present invention has the following advantages: by acquiring historical output temperature data and historical indoor temperature data, it utilizes machine learning technology to accurately assess the energy consumption of heat pump systems. By performing image analysis on scale images and integrating historical scale data, the overall scale quantity is dynamically adjusted. If scale similarity deviates to a certain extent, the historical scale data is grouped to determine a scale correction set. This allows for accurate scale prediction, avoiding the risk of energy consumption errors caused by human neglect of scale, thereby improving the accuracy of heat pump system energy consumption assessments and effectively enhancing the reliability of energy consumption predictions for heat pump systems.

[0050] On the other hand, the present application also provides an energy consumption evaluation system for a heat pump system, which is used to apply the above-mentioned energy consumption evaluation method for a heat pump system, including:

[0051] an energy consumption acquisition module configured to acquire output temperature data of the heat pump system and indoor temperature data of the residential area, determine a current energy consumption value based on the output temperature data and the indoor temperature data, acquire historical output temperature data and historical indoor temperature data and determine a predicted energy consumption value based on a random forest model;

[0052] an energy consumption analysis module configured to divide the evaporator into a plurality of scale detection zones, obtain a scale image of each scale detection zone, analyze each scale image to determine a comprehensive scale quantity of the evaporator, compare the comprehensive scale quantity with historical scale data, determine whether the comprehensive scale quantity is correct based on the comparison result, and if the comprehensive scale quantity is determined to be incorrect, determine a scale similarity based on the comprehensive scale quantity and the historical scale data;

[0053] an energy consumption processing module configured to, when the scale similarity is greater than or equal to a scale similarity threshold, determine a predicted amount of scale based on historical scale data; and, when the scale similarity is less than the scale similarity threshold, divide the historical scale data into sets to determine a scale correction set, and determine the predicted amount of scale based on the scale correction set;

[0054] The energy consumption determination module is configured to set an energy consumption correction coefficient of the predicted energy consumption value according to the predicted amount of scale, and determine a target predicted energy consumption value according to the energy consumption correction coefficient and the predicted energy consumption value.

[0055] It is understandable that the above-mentioned energy consumption assessment method and system for a heat pump system have the same beneficial effects and will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Various other advantages and benefits will become apparent to those skilled in the art upon reading the detailed description of the preferred embodiment below. The accompanying drawings are for illustration purposes only and are not to be considered as limiting the present invention. The same reference symbols are used throughout the drawings to represent the same components. In the drawings:

[0057] Figure 1 A flow chart of an energy consumption evaluation method for a heat pump system provided in an embodiment of the present invention;

[0058] Figure 2 This is a functional block diagram of an energy consumption evaluation system for a heat pump system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0059] Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art. It should be noted that, unless there is a conflict, the embodiments of the present disclosure and the features in the embodiments can be combined with each other. The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.

[0060] See Figure 1 As shown, in some embodiments of the present application, this embodiment provides an energy consumption assessment method for a heat pump system, comprising:

[0061] S100: Obtain output temperature data of the heat pump system and indoor temperature data of the residential area, determine a current energy consumption value based on the output temperature data and the indoor temperature data, obtain historical output temperature data and historical indoor temperature data and determine a predicted energy consumption value based on a random forest model.

[0062] S200: Divide the evaporator into several scale detection areas, obtain a scale image of each scale detection area, analyze each scale image to determine the comprehensive scale quantity of the evaporator, compare the comprehensive scale quantity with historical scale data, and determine whether the comprehensive scale quantity is correct based on the comparison result. When it is determined that the comprehensive scale quantity is incorrect, determine the scale similarity based on the comprehensive scale quantity and historical scale data.

[0063] S300: When the scale similarity is greater than or equal to the scale similarity threshold, the predicted scale quantity is determined based on the historical scale data; when the scale similarity is less than the scale similarity threshold, the historical scale data is divided into sets to determine scale correction sets, and the predicted scale quantity is determined based on the scale correction sets.

[0064] S400: An energy consumption correction coefficient of the predicted energy consumption value is set according to the predicted amount of scale, and a target predicted energy consumption value is determined according to the energy consumption correction coefficient and the predicted energy consumption value.

[0065] Specifically, the output temperature data of the heat pump system and the indoor temperature data of the residential area are obtained to determine the current energy consumption value. The current energy consumption value reflects the actual energy consumption of the heat pump system, and the output temperature data of the heat pump system represents the actual output temperature value for the residential area. Since the current energy consumption value represents the energy consumption determined under the current circumstances and does not reflect the overall energy consumption of the heat pump system, historical output temperature data and historical indoor temperature data are obtained and predicted energy consumption values are determined based on a random forest model. This avoids energy consumption errors caused by relying on data at a single time and improves the accuracy of energy consumption assessment. The predicted energy consumption value represents the predicted comprehensive energy consumption of the heat pump system. During the heat energy conversion process of the heat pump system, a certain amount of scale is generated around the evaporator, which increases the energy consumption of the heat pump system. The evaporator is divided into several scale detection zones, preferably 10, which can be adjusted according to the actual size of the evaporator. An image acquisition device such as a camera is used to capture an image of each scale detection zone to obtain a scale image. These images are analyzed using an image algorithm to determine the total amount of scale in the evaporator. The obtained comprehensive scale quantity is compared with the historical scale data, and the correctness of the comprehensive scale quantity is judged based on the comparison results, which avoids the errors caused by accidental data, further improves the accuracy of energy consumption assessment, and effectively improves the reliability of energy consumption prediction for heat pump systems.

[0066] It can be understood that when the scale similarity is greater than or equal to the scale similarity threshold, it is considered that the gap with the historical scale data is not obvious, and the historical scale data can be directly used to determine the predicted scale quantity. When the scale similarity is less than the scale similarity threshold, it means that the gap with the historical scale data is relatively obvious, and the historical scale data needs to be further analyzed to obtain the scale correction set, and then the predicted scale quantity is determined based on the scale correction set. Since the presence of scale will affect heat exchange, it will affect the predicted energy consumption value. Therefore, setting the energy consumption correction coefficient of the predicted energy consumption value according to the predicted scale quantity can obtain an accurate target predicted energy consumption value, thereby improving the accuracy of energy consumption assessment and further improving the energy management of the heat pump system.

[0067] In some embodiments of the present application, obtaining output temperature data of a heat pump system and indoor temperature data of a residential area, and determining a current energy consumption value based on the output temperature data and the indoor temperature data includes: obtaining a power input value and an output temperature value of the heat pump system, obtaining an average indoor temperature of the residential area, and the current energy consumption value is obtained by the following formula:

[0068] ;

[0069] Among them, Z1 represents the current energy consumption value, P1 represents the power input value of the heat pump system, T1 represents the output temperature value, and T2 represents the average indoor temperature.

[0070] Specifically, the average indoor temperature of a residential area is the average indoor temperature of all users in the local residential area. The power input value of the heat pump system is determined by looking up the actual power input of the local heat pump system. Similarly, the output temperature value can be determined by looking up the actual output temperature of the local heat pump system. Calculating the current energy consumption value allows for a comprehensive assessment of the current energy consumption of the heat pump system, improving the reliability and accuracy of energy consumption assessments and laying a data foundation for subsequent forecasts.

[0071] In some embodiments of the present application, when obtaining historical output temperature data and historical indoor temperature data and determining the predicted energy consumption value based on the random forest model, it includes: constructing the historical output temperature data and historical indoor temperature data into a data set, and dividing the data set into a training set and a test set, using grid search to find the establishment parameters of the random forest model, establishing a random forest model, using the training set to fit the random forest model, bringing the test set into the random forest model and calculating the accuracy of the predicted energy consumption value, and when the accuracy reaches a preset accuracy threshold, substituting the current energy consumption value into the random forest model to determine the predicted energy consumption value.

[0072] Specifically, the dataset contains data from the heat pump system at different time periods and indoor temperature data at different time periods. 70% to 90% of the data in the dataset is used as the training set, and the rest is used as the test set. Ensuring that both the training and test sets contain data from multiple time periods improves the generalization ability of the model. Grid search establishes a random forest model by exhaustively searching for the model's parameters in the parameter space. Furthermore, using the training set to fit the random forest model reduces the risk of overfitting and improves the accuracy and stability of the random forest model. The test set is substituted into the random forest model to calculate the model's prediction accuracy. Accuracy reflects the model's performance on unknown data and is an indicator for evaluating model performance. After the model reaches the preset accuracy threshold, the current energy consumption value is substituted into the random forest model to determine the predicted energy consumption value. This avoids the risk of inaccurate energy consumption assessments due to reliance on human experience, thereby improving the accuracy and reliability of energy consumption predictions.

[0073] In some embodiments of the present application, when obtaining a scale image of each scale detection area and analyzing each scale image to determine the comprehensive scale quantity of the evaporator, it includes: preprocessing the scale image of each scale detection area, the preprocessing includes image denoising and image resizing, determining the scale processed image of each scale detection area based on the preprocessing result, extracting scale pixels of all scale processed images, and determining the scale pixel features of each scale pixel, obtaining the feature mean of the scale pixel features, dividing the scale pixel points whose scale pixel features are greater than the feature mean into the first scale series, dividing the scale pixel points whose scale pixel features are equal to the feature mean into the second scale series, and dividing the scale pixel points whose scale pixel features are less than the feature mean into the third scale series, counting the first scale quantity of the scale pixels in the first scale series, and counting the second scale quantity of the scale pixels in the second scale series, the comprehensive scale quantity of the evaporator is the sum of the first scale quantity and the second scale quantity.

[0074] Specifically, after acquiring scale images from image acquisition devices such as cameras, the scale images will have certain noise interference or other interference factors that affect the image quality. Image denoising can remove random noise in the image to ensure image quality, while adjusting the image size unifies the image resolution, reduces the complexity and computational complexity of image processing, and lays the image foundation for subsequent extraction. After preprocessing the image of each scale detection area, the scale pixel features of each scale pixel include hue, saturation, and brightness. The characteristic mean of the scale pixel features is obtained to obtain a standardized reference value, and each pixel can be divided into series. The first scale series, the second scale series, and the third scale series represent different degrees of scale in the evaporator. Scale pixels with larger scale pixel features indicate more serious scale conditions, while scale pixels with smaller scale pixel features indicate less severe scale conditions, which can be almost negligible. The sum of the first scale number and the second scale number can reflect the actual scale amount around the evaporator, providing data support for subsequent energy consumption evaluation.

[0075] It is understandable that traditional manual inspection will be affected by factors such as human experience, resulting in errors. By acquiring images and performing preprocessing, the reliability of energy consumption assessment is improved, and each scale pixel is finely divided. Especially when the scale distribution is more complex, the accuracy of scale quantity statistics is ensured, thereby improving the reliability of the comprehensive scale quantity.

[0076] In some embodiments of the present application, when comparing the comprehensive scale quantity with the historical scale data and judging whether the comprehensive scale quantity is correct based on the comparison result, it includes: the historical scale data includes the historical comprehensive scale maximum value, the historical comprehensive scale average value and all historical comprehensive scale quantities; when the comprehensive scale quantity is greater than or equal to the historical comprehensive scale maximum value, the comprehensive scale quantity is judged to be correct, and the comprehensive scale quantity is determined as the predicted scale quantity; when the comprehensive scale quantity is less than the historical comprehensive scale maximum value, the comprehensive scale quantity is judged to be incorrect.

[0077] Specifically, the maximum value of the historical scale comprehensive quantity in the historical scale data represents the maximum value of scale present in the evaporator at different periods, and the mean value of the historical scale comprehensive quantity in the historical scale data represents the average value of scale quantity during the operation of the evaporator at different periods. During the operation of the heat pump system, scale will not disappear without human removal, and as the heat pump system operates, scale will gradually accumulate. If the comprehensive scale quantity is less than the maximum value of the historical scale comprehensive quantity, it means that there is a certain deviation in the statistical results and the comprehensive scale quantity needs to be adjusted. When the comprehensive scale quantity is greater than or equal to the maximum value of the historical scale comprehensive quantity, it means that scale formation is met, and the comprehensive scale quantity is not adjusted, and the comprehensive scale quantity is directly determined as the scale prediction quantity. By judging the comprehensive scale quantity, the foundation is laid for the subsequent determination of the energy consumption correction factor.

[0078] In some embodiments of the present application, when determining the scale similarity based on the comprehensive scale quantity and historical scale data, the method includes:

[0079] The scale similarity is given by the following formula:

[0080] ;

[0081] Among them, S represents the scale similarity, G1 represents the comprehensive number of scale, G2 represents the maximum comprehensive number of scale in history, and G3 represents the mean comprehensive number of scale in history.

[0082] In some embodiments of the present application, when the scale similarity is greater than or equal to the scale similarity threshold, the predicted scale quantity is determined based on the historical scale data; when the scale similarity is less than the scale similarity threshold, the historical scale data is divided into sets to determine a scale correction set; and when determining the predicted scale quantity based on the scale correction set, it includes: presetting the scale similarity threshold; when the scale similarity is greater than or equal to the scale similarity threshold, determining the maximum value of the historical scale comprehensive quantity as the predicted scale quantity; the scale correction set includes a first scale correction set, a second scale correction set, and a third scale correction set; when the scale similarity is less than the scale similarity threshold, the historical scale comprehensive quantity greater than the average of the historical scale comprehensive quantity is divided into the first scale correction set, the historical scale comprehensive quantity equal to the average of the historical scale comprehensive quantity is divided into the second scale correction set, and the historical scale comprehensive quantity less than the average of the historical scale comprehensive quantity is divided into the third scale correction set; and the predicted scale quantity is determined based on the first scale correction set, the second scale correction set, and the third scale correction set.

[0083] In some embodiments of the present application, when determining the predicted scale quantity according to the first scale correction set, the second scale correction set, and the third scale correction set, the predicted scale quantity is obtained by the following formula:

[0084] ;

[0085] Among them, K represents the predicted number of scale, G2 represents the maximum value of the historical comprehensive number of scale, Y1 represents the maximum value of the historical comprehensive number of scale in the first set of scale correction, Y2 represents the minimum value of the historical comprehensive number of scale in the first set of scale correction, U1 represents the maximum value of the historical comprehensive number of scale in the second set of scale correction, U2 represents the minimum value of the historical comprehensive number of scale in the second set of scale correction, I1 represents the maximum value of the historical comprehensive number of scale in the third set of scale correction, and I2 represents the minimum value of the historical comprehensive number of scale in the third set of scale correction.

[0086] Specifically, when the scale similarity is greater than or equal to the preset scale similarity threshold, it indicates that the comprehensive scale quantity and historical scale data have a high degree of similarity. In this case, the comprehensive scale quantity is considered relatively accurate, and the maximum historical comprehensive scale quantity is directly used as the predicted scale quantity. When the scale similarity is less than the preset scale similarity threshold, it indicates that the comprehensive scale quantity and historical scale data differ significantly, and it is necessary to group the historical scale data into sets to determine a scale correction set to further refine the historical scale data. The historical scale data covers the entire historical comprehensive scale quantity of evaporators in different periods. Establishing a scale correction set based on the relationship between the mean historical comprehensive scale quantity and the historical comprehensive scale quantity can determine the distribution of the historical comprehensive scale quantity, thereby improving the accuracy and reliability of the scale prediction quantity.

[0087] In some embodiments of the present application, when an energy consumption correction coefficient of a predicted energy consumption value is set according to a predicted amount of scale, and a target predicted energy consumption value is determined according to the energy consumption correction coefficient and the predicted energy consumption value, the method includes: presetting a first preset predicted amount of scale and a second preset predicted amount of scale, the first preset predicted amount of scale being greater than the second preset predicted amount of scale, presetting a first preset energy consumption correction coefficient, a second preset energy consumption correction coefficient and a third preset energy consumption correction coefficient, the first preset energy consumption correction coefficient being greater than the second preset energy consumption correction coefficient, the second preset energy consumption correction coefficient being greater than the third preset energy consumption correction coefficient. Positive coefficient: when the predicted scale quantity is greater than the first preset scale predicted quantity, the first preset energy consumption correction coefficient is used as the energy consumption correction coefficient of the predicted energy consumption value; when the predicted scale quantity is less than or equal to the first preset scale predicted quantity and greater than the second preset scale predicted quantity, the second preset energy consumption correction coefficient is used as the energy consumption correction coefficient of the predicted energy consumption value; when the predicted scale quantity is less than or equal to the second preset scale predicted quantity, the third preset energy consumption correction coefficient is used as the energy consumption correction coefficient of the predicted energy consumption value; the target predicted energy consumption value is the product of the predicted energy consumption value and the energy consumption correction coefficient.

[0088] Specifically, by setting the first preset scale prediction number and the second preset scale prediction number and the corresponding energy consumption correction coefficient, the set scale prediction number takes into account the impact of scale to varying degrees, and effectively evaluates the impact of scale accumulation on the predicted energy consumption value of the evaporator, thereby dynamically selecting the corresponding energy consumption correction coefficient according to the scale condition of the evaporator, and thus obtaining an accurate target predicted energy consumption value. Especially when the amount of scale accumulation is large, it avoids the inability of a single standard energy consumption correction coefficient to fully reflect the target predicted energy consumption value of the heat pump system, avoids deviations in the evaluation caused by human experience, and improves the accuracy and reliability of energy consumption evaluation.

[0089] In summary, the present invention has the beneficial effect of accurately assessing the energy consumption of heat pump systems by acquiring historical output temperature data and historical indoor temperature data and utilizing machine learning techniques. By performing image analysis on scale images and integrating historical scale data, the overall scale quantity is dynamically adjusted. When scale similarity deviates to a certain extent, the historical scale data is grouped to determine a scale correction set, enabling accurate scale prediction. This avoids the risk of energy consumption errors caused by human neglect of scale, thereby improving the accuracy of heat pump system energy consumption assessments and effectively enhancing the reliability of energy consumption predictions for heat pump systems.

[0090] In another preferred embodiment based on the above embodiment, refer to Figure 2 As shown, this embodiment provides an energy consumption evaluation system for a heat pump system, which is used to apply the above-mentioned energy consumption evaluation method for a heat pump system, including:

[0091] an energy consumption acquisition module configured to acquire output temperature data of the heat pump system and indoor temperature data of the residential area, determine a current energy consumption value based on the output temperature data and the indoor temperature data, acquire historical output temperature data and historical indoor temperature data and determine a predicted energy consumption value based on a random forest model;

[0092] an energy consumption analysis module configured to divide the evaporator into a plurality of scale detection zones, obtain a scale image of each scale detection zone, analyze each scale image to determine a comprehensive scale quantity of the evaporator, compare the comprehensive scale quantity with historical scale data, determine whether the comprehensive scale quantity is correct based on the comparison result, and if the comprehensive scale quantity is determined to be incorrect, determine a scale similarity based on the comprehensive scale quantity and the historical scale data;

[0093] an energy consumption processing module configured to, when the scale similarity is greater than or equal to a scale similarity threshold, determine a predicted amount of scale based on historical scale data; and, when the scale similarity is less than the scale similarity threshold, divide the historical scale data into sets to determine a scale correction set, and determine the predicted amount of scale based on the scale correction set;

[0094] The energy consumption determination module is configured to set an energy consumption correction coefficient of the predicted energy consumption value according to the predicted amount of scale, and determine a target predicted energy consumption value according to the energy consumption correction coefficient and the predicted energy consumption value.

[0095] Specifically, the energy consumption acquisition module is responsible for determining the current energy consumption value based on the heat pump system's output temperature data and the indoor temperature data of the residential area. It also obtains historical output temperature data and historical indoor temperature data and uses a random forest model to determine the predicted energy consumption value. This improves the comprehensiveness of the heat pump system's energy consumption assessment and avoids the impact of errors in single data on the overall assessment. Furthermore, using the random forest model for prediction avoids the accumulation of errors caused by human experience. During the cooling water circulation process in the evaporator, due to the presence of salts and various microorganisms in the water, scale will form on the surface of the evaporator after the heat pump system has been running for a period of time, resulting in reduced heat transfer efficiency and thus affecting the energy consumption of the heat pump system. The energy consumption analysis module can quantitatively analyze the scale and compare it with historical scale data, laying a data foundation for subsequent processing. When the comprehensive scale quantity is determined to be incorrect, the system will determine the scale similarity based on the comprehensive scale quantity and historical scale data. The scale similarity represents the difference between the comprehensive scale quantity and the historical scale data. If the scale similarity is greater than or equal to the scale similarity threshold, it means that the comprehensive scale quantity and the historical scale data are slightly different, and the predicted scale quantity can be determined directly using the historical scale data. If the scale similarity is less than the scale similarity threshold, it means that the comprehensive scale quantity and the historical scale data are significantly different, and the historical scale data needs to be grouped to determine the predicted scale quantity, which improves the flexibility and pertinence of the system processing, ensures the reliability of the predicted scale quantity, and further improves the accuracy of energy consumption assessment.

[0096] It can be understood that after obtaining the accurate predicted amount of scale, the energy consumption determination module sets the energy consumption correction coefficient of the predicted energy consumption value, and determines the target predicted energy consumption value based on the energy consumption correction coefficient, which effectively addresses the impact of scale on energy consumption assessment. It can not only predict the energy consumption of the heat pump system, but also analyze the impact of scale accumulation, thereby accurately deriving the target predicted energy consumption value and improving the accuracy and reliability of energy consumption assessment.

[0097] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware. Furthermore, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0098] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 a process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0099] These computer program instructions may also be stored in a computer-readable storage device that can direct a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable storage device produce an article of manufacture comprising an instruction device that implements the process. Figure 1 a process or multiple processes and / or boxes Figure 1 The function specified in one or more boxes.

[0100] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operational steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing the instructions executed on the computer or other programmable device for implementing the process. Figure 1 a process or multiple processes and / or boxes Figure 1 A step that specifies a function in one or more boxes.

[0101] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered by the scope of protection of the claims of the present invention.

Claims

1. A method for evaluating energy consumption of a heat pump system, characterized in that: include: Obtaining output temperature data of a heat pump system and indoor temperature data of a residential area, determining a current energy consumption value based on the output temperature data and the indoor temperature data, obtaining historical output temperature data and historical indoor temperature data and determining a predicted energy consumption value based on a random forest model; Dividing the evaporator into a plurality of scale detection areas, obtaining a scale image of each scale detection area, analyzing each scale image to determine a comprehensive scale quantity of the evaporator, comparing the comprehensive scale quantity with historical scale data, and determining whether the comprehensive scale quantity is correct based on the comparison result; if the comprehensive scale quantity is determined to be incorrect, determining a scale similarity based on the comprehensive scale quantity and the historical scale data; When the scale similarity is greater than or equal to the scale similarity threshold, the predicted scale quantity is determined based on the historical scale data; when the scale similarity is less than the scale similarity threshold, the historical scale data is divided into sets to determine a scale correction set, and the predicted scale quantity is determined based on the scale correction set; An energy consumption correction coefficient of the predicted energy consumption value is set according to the predicted amount of scale, and a target predicted energy consumption value is determined according to the energy consumption correction coefficient and the predicted energy consumption value.

2. The energy consumption evaluation method for a heat pump system according to claim 1, characterized in that: When obtaining output temperature data of a heat pump system and indoor temperature data of a residential area, and determining a current energy consumption value according to the output temperature data and the indoor temperature data, the method includes: Obtaining a power input value and an output temperature value of the heat pump system, and obtaining an average indoor temperature of the residential area; The current energy consumption value is obtained by the following formula: ； Among them, Z1 represents the current energy consumption value, P1 represents the power input value of the heat pump system, T1 represents the output temperature value, and T2 represents the average indoor temperature.

3. The energy consumption evaluation method for a heat pump system according to claim 2, characterized in that: When obtaining historical output temperature data and historical indoor temperature data and determining the predicted energy consumption value based on the random forest model, the following steps are included: The historical output temperature data and the historical indoor temperature data are constructed into a data set, and the data set is divided into a training set and a test set. A grid search is used to find the establishment parameters of a random forest model, and a random forest model is established. The random forest model is fitted using the training set, and the test set is brought into the random forest model to calculate the accuracy of the predicted energy consumption value; When the accuracy reaches a preset accuracy threshold, the current energy consumption value is substituted into the random forest model to determine the predicted energy consumption value.

4. The energy consumption evaluation method for a heat pump system according to claim 3, characterized in that: When obtaining a scale image of each scale detection area and analyzing each scale image to determine the comprehensive amount of scale on the evaporator, the method includes: Preprocessing the scale image of each scale detection area, wherein the preprocessing includes image noise reduction and image size adjustment, and determining a scale-processed image of each scale detection area according to the preprocessing result; Extracting scale pixels from all scale-processed images, determining the scale pixel features of each scale pixel, and obtaining the feature mean of the scale pixel features; The scale pixel points whose scale pixel characteristics are greater than the characteristic mean are divided into the first scale series, the scale pixel points whose scale pixel characteristics are equal to the characteristic mean are divided into the second scale series, and the scale pixel points whose scale pixel characteristics are less than the characteristic mean are divided into the third scale series; A first scale quantity of scale pixels in the first scale series is counted, and a second scale quantity of scale pixels in the second scale series is counted. The comprehensive scale quantity of the evaporator is the sum of the first scale quantity and the second scale quantity.

5. The energy consumption evaluation method for a heat pump system according to claim 4, characterized in that: When comparing the comprehensive amount of scale with historical scale data and judging whether the comprehensive amount of scale is correct based on the comparison result, the method includes: The historical scale data includes the maximum historical scale comprehensive quantity, the average historical scale comprehensive quantity and all historical scale comprehensive quantities; When the comprehensive amount of scale is greater than or equal to the maximum comprehensive amount of historical scale, it is determined that the comprehensive amount of scale is correct, and the comprehensive amount of scale is determined as the predicted amount of scale; When the comprehensive amount of scale is less than the maximum comprehensive amount of historical scale, it is determined that the comprehensive amount of scale is incorrect.

6. The energy consumption evaluation method for a heat pump system according to claim 5, characterized in that: When determining the scale similarity based on the comprehensive scale quantity and the historical scale data, the method includes: The scale similarity is obtained by the following formula: ； Among them, S represents the scale similarity, G1 represents the comprehensive number of scale, G2 represents the maximum comprehensive number of scale in history, and G3 represents the mean comprehensive number of scale in history.

7. The energy consumption evaluation method for a heat pump system according to claim 6, characterized in that: When the scale similarity is greater than or equal to the scale similarity threshold, the predicted scale quantity is determined based on the historical scale data; when the scale similarity is less than the scale similarity threshold, the historical scale data is divided into sets to determine a scale correction set, and the predicted scale quantity is determined based on the scale correction set, including: Pre-set scale similarity threshold; When the scale similarity is greater than or equal to the scale similarity threshold, the maximum value of the historical scale integrated quantity is determined as the scale prediction quantity; The scale correction set includes a first scale correction set, a second scale correction set and a third scale correction set; When the scale similarity is less than the scale similarity threshold, the historical scale integrated quantity greater than the mean of the historical scale integrated quantity is divided into the scale correction first set, the historical scale integrated quantity equal to the mean of the historical scale integrated quantity is divided into the scale correction second set, and the historical scale integrated quantity less than the mean of the historical scale integrated quantity is divided into the scale correction third set; A scale prediction amount is determined according to the scale correction first set, the scale correction second set, and the scale correction third set.

8. The energy consumption evaluation method for a heat pump system according to claim 7, characterized in that: When determining the predicted amount of scale according to the first scale correction set, the second scale correction set, and the third scale correction set, the method includes: The predicted amount of scale is obtained by the following formula: ； Among them, K represents the predicted number of scale, G2 represents the maximum value of the historical comprehensive number of scale, Y1 represents the maximum value of the historical comprehensive number of scale in the first set of scale correction, Y2 represents the minimum value of the historical comprehensive number of scale in the first set of scale correction, U1 represents the maximum value of the historical comprehensive number of scale in the second set of scale correction, U2 represents the minimum value of the historical comprehensive number of scale in the second set of scale correction, I1 represents the maximum value of the historical comprehensive number of scale in the third set of scale correction, and I2 represents the minimum value of the historical comprehensive number of scale in the third set of scale correction.

9. The energy consumption evaluation method for a heat pump system according to claim 8, characterized in that: When an energy consumption correction coefficient of the predicted energy consumption value is set according to the predicted amount of scale, and a target predicted energy consumption value is determined according to the energy consumption correction coefficient and the predicted energy consumption value, the method includes: Presetting a first preset scale prediction number and a second preset scale prediction number, wherein the first preset scale prediction number is greater than the second preset scale prediction number; Presetting a first preset energy consumption correction coefficient, a second preset energy consumption correction coefficient, and a third preset energy consumption correction coefficient, wherein the first preset energy consumption correction coefficient is greater than the second preset energy consumption correction coefficient, and the second preset energy consumption correction coefficient is greater than the third preset energy consumption correction coefficient; When the predicted amount of scale is greater than the first preset predicted amount of scale, the first preset energy consumption correction coefficient is used as the energy consumption correction coefficient of the predicted energy consumption value; When the predicted scale amount is less than or equal to the first preset predicted scale amount and greater than the second preset predicted scale amount, the second preset energy consumption correction coefficient is used as the energy consumption correction coefficient of the predicted energy consumption value; When the predicted scale amount is less than or equal to the second preset predicted scale amount, the third preset energy consumption correction coefficient is used as the energy consumption correction coefficient of the predicted energy consumption value; The target predicted energy consumption value is the product of the predicted energy consumption value and the energy consumption correction coefficient.

10. An energy consumption evaluation system for a heat pump system, applied to the energy consumption evaluation method for a heat pump system according to any one of claims 1 to 9, characterized in that: include: an energy consumption acquisition module configured to acquire output temperature data of the heat pump system and indoor temperature data of the residential area, determine a current energy consumption value based on the output temperature data and the indoor temperature data, acquire historical output temperature data and historical indoor temperature data and determine a predicted energy consumption value based on a random forest model; an energy consumption analysis module configured to divide the evaporator into a plurality of scale detection zones, obtain a scale image of each scale detection zone, analyze each scale image to determine a comprehensive scale quantity of the evaporator, compare the comprehensive scale quantity with historical scale data, determine whether the comprehensive scale quantity is correct based on the comparison result, and if the comprehensive scale quantity is determined to be incorrect, determine a scale similarity based on the comprehensive scale quantity and the historical scale data; an energy consumption processing module configured to, when the scale similarity is greater than or equal to a scale similarity threshold, determine a predicted amount of scale based on historical scale data; and, when the scale similarity is less than the scale similarity threshold, divide the historical scale data into sets to determine a scale correction set, and determine the predicted amount of scale based on the scale correction set; The energy consumption determination module is configured to set an energy consumption correction coefficient of the predicted energy consumption value according to the predicted amount of scale, and determine a target predicted energy consumption value according to the energy consumption correction coefficient and the predicted energy consumption value.

Images