Indoor unit, method and device for detecting operation capacity of indoor unit and multi-split air conditioning system

Abstract

The invention discloses an indoor unit, an operation capacity detection method and device of the indoor unit and a multi-split air conditioning system.The operation capacity detection method of the indoor unit comprises the steps that a preset operation condition is input into a first temperature reaching probability prediction model and a second temperature reaching probability prediction model to obtain a first temperature reaching probability and a second temperature reaching probability, the first temperature reaching probability prediction model is obtained by training first operation data when the operation capability of the indoor unit is normal, the second temperature reaching probability prediction model is obtained by training second operation data of the indoor unit, and the obtaining time of the second operation data is later than the obtaining time of the first operation data; and when it is determined that the difference between the first temperature reaching probability and the second temperature reaching probability meets the preset difference, it is determined that the operation capacity of the indoor unit is reduced. The method can find that the operation capability of the indoor unit is reduced before the user perceives, so that corresponding measures are taken for the indoor unit, and the user experience is improved.

Description

Technical Field

[0001] This application relates to the field of air conditioning technology, and in particular to an indoor unit and a method, device, and multi-split system for detecting its operating capacity. Background Technology

[0002] Air conditioner indoor units can experience a decline in capacity due to factors such as clogged filters, dirty evaporators, insufficient refrigerant, changes in the installation environment, and system aging. Regardless of the cause, this decline directly impacts the user experience. Currently, the detection of decreased cooling / heating capacity relies primarily on user perception. Often, users only notice the decline when the unit's cooling / heating capacity has severely decreased, leading to a poor user experience. Summary of the Invention

[0003] This invention aims to at least partially solve one of the technical problems in related technologies. Therefore, the first objective of this invention is to propose a method for detecting the operational capability of an indoor unit. This method uses a first temperature-reaching probability prediction model and a second temperature-reaching probability prediction model to predict the probability of reaching a preset operating condition. Based on the difference between the first and second temperature-reaching probabilities, it determines whether the operational capability of the indoor unit has decreased, achieving timely detection of operational capability. This allows for the discovery of a decrease in the indoor unit's operational capability before the user perceives it, enabling appropriate measures to be taken to improve the user experience.

[0004] The second objective of this invention is to propose a training method for a temperature probability prediction model.

[0005] A third objective of this invention is to provide a computer-readable storage medium.

[0006] The fourth objective of this invention is to provide an electronic device.

[0007] The fifth objective of this invention is to provide an indoor unit operation capability detection device.

[0008] The sixth objective of this invention is to provide a training device for a temperature probability prediction model.

[0009] The seventh objective of this invention is to provide an indoor unit.

[0010] The eighth objective of this invention is to provide a multi-unit system.

[0011] To achieve the above objectives, a method for detecting the operating capability of an indoor unit is proposed according to a first aspect embodiment of the present invention, comprising: inputting preset operating conditions into a first temperature reach probability prediction model and a second temperature reach probability prediction model respectively to obtain a first temperature reach probability and a second temperature reach probability, wherein the first temperature reach probability prediction model is trained using first operating data of the indoor unit when its operating capability is normal, and the second temperature reach probability prediction model is trained using second operating data of the indoor unit, wherein the acquisition time of the second operating data is later than the acquisition time of the first operating data; and determining that the operating capability of the indoor unit has decreased when the difference between the first temperature reach probability and the second temperature reach probability meets a preset difference.

[0012] According to the indoor unit operation capability detection method of this invention, preset operating conditions are input into a first temperature reach probability prediction model and a second temperature reach probability prediction model to obtain a first temperature reach probability and a second temperature reach probability. The first temperature reach probability prediction model is trained using first operating data of the indoor unit when its operation capability is normal, and the second temperature reach probability prediction model is trained using second operating data of the indoor unit. The second operating data is acquired later than the first operating data. If the difference between the first and second temperature reach probabilities meets a preset difference, it is determined that the indoor unit's operation capability has decreased. Therefore, by using the first and second temperature reach probability prediction models to predict the temperature reach probability under preset operating conditions, and judging whether the indoor unit's operation capability has decreased based on the difference between the first and second temperature reach probabilities, timely detection of operation capability is achieved. This allows for the detection of a decrease in the indoor unit's operation capability before the user perceives it, enabling appropriate measures to be taken to improve the user experience.

[0013] According to one embodiment of the present invention, determining that the difference between the first probability of reaching a temperature and the second probability of reaching a temperature satisfies a preset difference includes: determining a t-statistic based on the first probability of reaching a temperature and the second probability of reaching a temperature; determining a probability value based on the t-statistic; and determining that the difference between the first probability of reaching a temperature and the second probability of reaching a temperature satisfies the preset difference when the probability value is less than the preset probability value.

[0014] According to one embodiment of the present invention, determining the t-statistic based on a first temperature-reaching probability and a second temperature-reaching probability includes: determining a first mean and a first variance of the first temperature-reaching probability, and determining a second mean and a second variance of the second temperature-reaching probability; determining a pooled variance based on the first variance, the sample size of the first temperature-reaching probability, the second variance, and the sample size of the second temperature-reaching probability; and determining the t-statistic based on the first mean, the second mean, and the pooled variance.

[0015] According to one embodiment of the present invention, the method further includes: determining that the indoor unit's operating capability is normal if the difference between the first temperature reach probability and the second temperature reach probability does not meet a preset difference.

[0016] To achieve the above objectives, a training method for a temperature rise probability prediction model is proposed according to a second aspect of the present invention, comprising: acquiring indoor unit operating data; filtering the operating data to obtain a training dataset; and training a Bayesian model based on the training dataset to obtain a temperature rise probability prediction model.

[0017] According to the training method of the temperature rise probability prediction model of the present invention, the operating data of the indoor unit is acquired, and the operating data is filtered to obtain a training dataset. A Bayesian model is then trained based on the training dataset to obtain the temperature rise probability prediction model. Therefore, the temperature rise probability prediction model is constructed based on the operating data. Different indoor units can use their corresponding operating data to construct their own temperature rise probability prediction models. Thus, the temperature rise probability prediction model has strong adaptability, thereby reducing the impact of the installation location of the indoor and outdoor units and the building envelope structure on the performance of different indoor units.

[0018] According to one embodiment of the present invention, training a Bayesian model based on a training dataset includes: determining prior probabilities and Davin conditional probabilities based on the training dataset; and training the Bayesian model using the prior probabilities and Davin conditional probabilities.

[0019] According to one embodiment of the present invention, data filtering processing is performed on the operating data to obtain a training dataset, including: filtering the operating data of the indoor unit after it is turned on and within a preset time, and the operating data after the set temperature is changed and within a preset time, to obtain multiple operating datasets, wherein each operating dataset includes operating condition data and temperature reach data, the operating condition data is correlated with the probability of the indoor unit reaching the set temperature, and the temperature reach data is used to determine whether the indoor ambient temperature has reached the set temperature; determining the temperature reach result corresponding to each operating dataset based on the temperature reach data in each operating dataset, wherein the operating condition data and the corresponding temperature reach result in each operating dataset constitute a training dataset.

[0020] According to one embodiment of the present invention, the operating condition data includes at least one of indoor and outdoor ambient temperature, set temperature, fan speed, indoor ambient temperature and load rate, and the temperature reached data includes indoor ambient temperature and set temperature.

[0021] To achieve the above objectives, a computer-readable storage medium is provided according to a third aspect of the present invention, having stored thereon a computer program that, when processed by a processor, executes the indoor unit operation capability detection method of any of the foregoing embodiments or the temperature probability prediction model training method of any of the foregoing embodiments.

[0022] According to the computer-readable storage medium of the present invention, a computer program that executes the above-described method for detecting the operating capability of an indoor unit or for training a method for predicting the probability of reaching a certain temperature is used to predict the probability of reaching a certain temperature under preset operating conditions using a first probability prediction model and a second probability prediction model. The program then determines whether the operating capability of the indoor unit has decreased based on the difference between the first probability and the second probability, thereby enabling timely detection of the operating capability. This allows for the detection of a decrease in the operating capability of the indoor unit before the user perceives it, enabling appropriate measures to be taken for the indoor unit and thus improving the user experience.

[0023] To achieve the above objectives, an electronic device is provided according to a fourth aspect of the present invention, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the indoor unit operation capability detection method of any of the foregoing embodiments or the temperature probability prediction model training method of any of the foregoing embodiments.

[0024] According to the present invention, the electronic device executes a computer program of the above-mentioned indoor unit operation capability detection method or temperature probability prediction model training method through a processor. The program predicts the temperature probability under preset operating conditions through the first temperature probability prediction model and the second temperature probability prediction model, and determines whether the operation capability of the indoor unit has decreased based on the difference between the first temperature probability and the second temperature probability. This enables timely detection of operation capability, allowing the user to detect the decrease in the operation capability of the indoor unit before it is perceived, thereby taking corresponding measures to improve the user experience.

[0025] To achieve the above objectives, a device for detecting the operating capacity of an indoor unit is provided according to a fifth aspect embodiment of the present invention, comprising: an input module, configured to input preset operating conditions into a first temperature reach probability prediction model and a second temperature reach probability prediction model respectively to obtain a first temperature reach probability and a second temperature reach probability, wherein the first temperature reach probability prediction model is trained using first operating data of the indoor unit when its operating capacity is normal, and the second temperature reach probability prediction model is trained using second operating data of the indoor unit, and the acquisition time of the second operating data is later than the acquisition time of the first operating data; and a determination module, configured to determine that the operating capacity of the indoor unit has decreased when the difference between the first temperature reach probability and the second temperature reach probability meets a preset difference.

[0026] According to an embodiment of the present invention, the indoor unit's operational capability detection device inputs preset operating conditions into a first temperature reach probability prediction model and a second temperature reach probability prediction model via an input module to obtain a first temperature reach probability and a second temperature reach probability. The first temperature reach probability prediction model is trained using first operating data when the indoor unit's operational capability is normal, and the second temperature reach probability prediction model is trained using second operating data of the indoor unit. The acquisition time of the second operating data is later than the acquisition time of the first operating data. A determination module determines that the indoor unit's operational capability has decreased if the difference between the first and second temperature reach probabilities meets a preset difference. Thus, by predicting the temperature reach probability under preset operating conditions using the first and second temperature reach probability prediction models respectively, and judging whether the indoor unit's operational capability has decreased based on the difference between the first and second temperature reach probabilities, timely detection of operational capability is achieved. This allows for the detection of a decrease in the indoor unit's operational capability before the user perceives it, enabling appropriate measures to be taken to improve the user experience.

[0027] To achieve the above objectives, a training device for a temperature rise probability prediction model is provided according to a sixth aspect embodiment of the present invention, comprising: a first acquisition module for acquiring operating data of an indoor unit; a second acquisition module for filtering the operating data to obtain a training dataset; and a training module for training a Bayesian model based on the training dataset to obtain a temperature rise probability prediction model.

[0028] The training device for the temperature rise probability prediction model according to an embodiment of the present invention acquires the operating data of the indoor unit through a first acquisition module, filters the operating data through a second acquisition module, obtains a training dataset through a third acquisition module, and trains a Bayesian model based on the training dataset to obtain the temperature rise probability prediction model. Therefore, the temperature rise probability prediction model is constructed based on operating data, and different indoor units can use corresponding operating data to construct their own temperature rise probability prediction models. Thus, the temperature rise probability prediction model has strong adaptability, thereby reducing the impact of the installation location of the indoor and outdoor units and the building envelope structure on the performance of different indoor units.

[0029] To achieve the above objectives, an indoor unit is provided according to a seventh aspect embodiment of the present invention, comprising: the aforementioned electronic device, or the aforementioned indoor unit operation capability detection device, or the aforementioned temperature probability prediction model training device.

[0030] According to the embodiments of the present invention, the indoor unit employs the aforementioned electronic equipment, an indoor unit operation capability detection device, or a temperature probability prediction model training device. It uses a first temperature probability prediction model and a second temperature probability prediction model to predict the temperature probability under preset operating conditions, and determines whether the indoor unit's operation capability has decreased based on the difference between the first and second temperature probabilities. This enables timely detection of operation capability, allowing for the discovery of a decrease in the indoor unit's operation capability before the user perceives it, thus enabling appropriate measures to be taken to improve the user experience.

[0031] To achieve the above objectives, an eighth aspect of the present invention provides a multi-split air conditioning system, comprising: the aforementioned indoor unit.

[0032] According to the multi-split air conditioning system of the present invention, by using the above-mentioned indoor unit, the probability of reaching the temperature under preset operating conditions is predicted by the first temperature probability prediction model and the second temperature probability prediction model, respectively. The difference between the first temperature probability and the second temperature probability is used to determine whether the operating capacity of the indoor unit has decreased, so as to realize timely detection of the operating capacity. In this way, the decrease in the operating capacity of the indoor unit can be detected before the user perceives it, so as to take corresponding measures for the indoor unit and improve the user experience.

[0033] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0034] Figure 1 This is a flowchart illustrating a method for detecting the operating capability of an indoor unit according to an embodiment of the present invention;

[0035] Figure 2 This is a flowchart illustrating a training method for a Davin probability prediction model according to an embodiment of the present invention.

[0036] Figure 3 This is a flowchart illustrating a method for detecting the operating capability of an indoor unit according to a specific embodiment of the present invention;

[0037] Figure 4 This is a system schematic diagram of an electronic device according to an embodiment of the present invention;

[0038] Figure 5 This is a schematic diagram of the structure of an indoor unit operation capability detection device according to an embodiment of the present invention;

[0039] Figure 6 This is a schematic diagram of the structure of a training device for a probability prediction model of Davin according to an embodiment of the present invention;

[0040] Figure 7This is a system schematic diagram of an indoor unit according to an embodiment of the present invention;

[0041] Figure 8 This is a system schematic diagram of an indoor unit according to another embodiment of the present invention;

[0042] Figure 9 This is a system schematic diagram of an indoor unit according to another embodiment of the present invention;

[0043] Figure 10 This is a system schematic diagram of a multi-unit system according to an embodiment of the present invention. Detailed Implementation

[0044] Embodiments of the present invention are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and intended to explain the present invention, and should not be construed as limiting the present invention.

[0045] It should be noted that this application is based on the inventor's understanding and research into the following issues:

[0046] In related technologies, the detection methods for the decline in the cooling / heating capacity of indoor units mainly rely on user experience. This method lacks quantitative standards, and users typically only perceive the decline when it becomes severe, leading to a poor user experience due to the extended time required to detect the decrease. Furthermore, this method only detects the problem after it has already occurred. Alternatively, methods can measure the static pressure at a specific location on the indoor unit at different fan speeds to assess its operational capacity. This method is relatively accurate for detecting cooling / heating capacity declines caused by changes in fan static pressure, such as dirty heat exchangers or clogged filters, but it is less effective for other causes. Another method judges whether the indoor unit's heating / cooling capacity has declined based on the difference between the return air temperature and the set temperature and a preset threshold. This method uses the same preset threshold for all indoor units, which can easily lead to misdiagnosis due to different installation locations of indoor and outdoor units or different building envelope structures.

[0047] Based on this, embodiments of the present invention provide an indoor unit and its operational capability detection method, device, multi-split system, a training method and device for a temperature probability prediction model, electronic equipment, and storage medium. The method uses a first temperature probability prediction model and a second temperature probability prediction model to predict the temperature probability under preset operating conditions, and determines whether the indoor unit's operational capability has decreased based on the difference between the first and second temperature probabilities. This enables timely detection of operational capability, allowing for the discovery of a decrease in the indoor unit's operational capability before the user perceives it, thus enabling appropriate measures to be taken to improve the user experience.

[0048] The following description, with reference to the accompanying drawings, describes an indoor unit and its operation capability detection method and device, a multi-split air conditioning system, a training method and device for a temperature probability prediction model, electronic equipment, and a storage medium according to embodiments of the present invention.

[0049] Figure 1 This is a flowchart illustrating a method for detecting the operational capability of an indoor unit according to an embodiment of the present invention. Figure 1 As shown, the methods for testing the operating capacity of the indoor unit include:

[0050] S101, the preset operating conditions are input into the first temperature reach probability prediction model and the second temperature reach probability prediction model respectively to obtain the first temperature reach probability and the second temperature reach probability. The first temperature reach probability prediction model is trained using the first operating data of the indoor unit when its operating capacity is normal, and the second temperature reach probability prediction model is trained using the second operating data of the indoor unit. The acquisition time of the second operating data is later than the acquisition time of the first operating data.

[0051] Specifically, the operating capacity of an indoor unit typically decreases gradually with increasing operating time. The first set of operating data can be data from the period immediately following the unit's initial use (e.g., one year), while the second set of operating data represents the unit's most recent data, such as data from the most recent month or quarter. Therefore, the second temperature-reaching probability model can be rebuilt using monthly or quarterly data. The temperature-reaching probability is the probability that the indoor ambient temperature will reach the set temperature after a preset time. The temperature-reaching probability output by the first model can characterize the probability of the indoor unit reaching the set temperature when its operating capacity is normal, while the temperature-reaching probability output by the second model can characterize the most recent temperature-reaching probability. By inputting the same preset operating conditions into both the first and second models, the first and second temperatures-reaching probabilities are obtained. The preset operating conditions can be a random combination of outdoor ambient temperature, fan speed, set temperature, and indoor ambient temperature. For example, an outdoor ambient temperature of 34℃, a fan speed of level 5, a set temperature of 22℃, and an indoor ambient temperature of 25℃ constitutes one operating condition.

[0052] S102, if the difference between the first temperature reach probability and the second temperature reach probability meets the preset difference, it is determined that the operating capacity of the indoor unit has decreased.

[0053] Specifically, the probability of reaching the set temperature reflects the operating capability of the indoor unit. If the operating capability of the indoor unit decreases, the time it takes for the indoor ambient temperature to reach the set temperature will increase, and the probability of reaching the set temperature will decrease. Therefore, if the indoor unit's operating capability is normal, the second probability of reaching the set temperature should be close to the first probability of reaching the set temperature. Thus, the difference between the first and second probabilities of reaching the set temperature can be used to determine whether the operating capability of the indoor unit has decreased. When the difference between the first and second probabilities of reaching the set temperature meets a preset difference, it indicates that there is a significant difference between the first and second probabilities of reaching the set temperature, and therefore the operating capability of the indoor unit has decreased.

[0054] Furthermore, once it is determined that the indoor unit's operating capacity has decreased, the indoor unit can be marked on the cloud server, and a notification message can be sent to the user in a timely manner so that the user can perform maintenance, thereby reducing the energy wasted by the indoor unit.

[0055] In the above embodiments, the probability of reaching the set temperature under preset operating conditions is predicted using a first temperature-reaching probability prediction model and a second temperature-reaching probability prediction model, respectively. The difference between the first and second temperature-reaching probabilities is used to determine whether the indoor unit's operating capacity has decreased, enabling timely detection of operating capacity. This allows for the detection of a decline in the indoor unit's operating capacity before the user perceives it, allowing for appropriate measures to be taken to improve the user experience. Furthermore, the temperature-reaching probability is affected by various factors, resulting in a wider detection range compared to static pressure detection methods. Additionally, due to differences in installation location, usage habits, and building envelope, the temperature-reaching probability varies for each indoor unit under the same operating conditions. This method, by establishing a temperature-reaching probability prediction model for each indoor unit, offers better universality compared to detection methods using the same threshold, reducing missed detections and false detections. Moreover, the second temperature-reaching probability prediction model can self-update using second operating data, reducing the probability of inaccurate temperature-reaching predictions due to initial modeling.

[0056] In some embodiments, determining that the difference between the first probability of reaching a temperature and the second probability of reaching a temperature satisfies a preset difference includes: determining a t-statistic based on the first probability of reaching a temperature and the second probability of reaching a temperature; determining a probability value based on the t-statistic; and determining that the difference between the first probability of reaching a temperature and the second probability of reaching a temperature satisfies a preset difference when the probability value is less than a preset probability value.

[0057] Specifically, an independent samples t-test can be used to calculate the difference between the first and second probabilities of reaching a certain temperature, yielding a t-statistic. The corresponding probability value can then be looked up in a table. The t-statistic describes the degree of difference between the first and second probabilities of reaching a certain temperature; a larger t-statistic indicates a greater difference. The probability value is used to determine whether this difference is statistically significant. A preset probability value represents a preset significance level (e.g., 0.05). If the probability value is less than the preset probability value, it indicates that the difference between the first and second probabilities of reaching a certain temperature is statistically significant, and the difference is determined to meet the preset difference. If the probability value is greater than or equal to the preset probability value, it indicates that the difference may be caused by random error, and the difference is determined to not meet the preset difference.

[0058] In some embodiments, determining the t-statistic based on the first temperature-reaching probability and the second temperature-reaching probability includes: determining a first mean and a first variance of the first temperature-reaching probability, and determining a second mean and a second variance of the second temperature-reaching probability; determining the pooled variance based on the first variance, the sample size of the first temperature-reaching probability, the second variance, and the sample size of the second temperature-reaching probability; and determining the t-statistic based on the first mean, the second mean, and the pooled variance.

[0059] Specifically, the preset operating conditions include multiple operating conditions. These multiple operating conditions are sequentially input into the first temperature reach probability prediction model and the second temperature reach probability prediction model. The first and second temperature reach probability prediction models will output multiple temperature reach probabilities. Therefore, the first temperature reach probability and the second temperature reach probability each include multiple temperature reach probabilities. First, the first mean and first variance of the first temperature reach probability and the second mean and second variance of the second temperature reach probability are calculated. Then, the combined variance can be calculated according to formula (1):

[0060]

[0061] Among them, s1 2 Let n1 be the first variance, n2 be the sample size of the first probability of reaching the temperature, and s2 be the second variance. 2 n is the second variance, and n2 is the sample size for the second temperature probability.

[0062] After obtaining the combined variance s p 2 Then, the t-statistic can be calculated according to formula (2):

[0063]

[0064] in, The first mean, It is the second mean.

[0065] For example, suppose the first temperature reach probability prediction model is built based on the indoor unit's first operating data in September and October of the first year, and the second temperature reach probability prediction model is built based on the indoor unit's second operating data in the most recent month. Inputting the preset operating conditions into the first and second temperature reach probability prediction models respectively, the first temperature reach probability P1 is obtained as (0.48, 0.48, 0.48, 0.49, 0.47, 0.47, ... The first probability of reaching a certain temperature, P1, is (0.48, 0.48, 0.46, 0.46, 0.47, 0.47), and the second probability of reaching a certain temperature, P2, is (0.43, 0.44, 0.45, 0.46, 0.4, 0.42, 0.43, 0.44, 0.38, 0.39, 0.41, 0.42). The sample size n1 of the first probability of reaching a certain temperature, P1, is 12, and the sample size n2 of the second probability of reaching a certain temperature, P2, is 12. The first mean of the first probability of reaching a certain temperature, P1, is calculated. and first variance s1 2 And the second mean of the second temperature probability P2 Second variance s2 2 The sample size n1, sample size n2, and first variance s1 are given. 2 Second variance s2 2 Substitute into formula (1) to calculate the combined variance s p 2 Then combine the variances s p 2 Sample size n1, sample size n2, first mean Second mean Substituting into formula (2), we can calculate t = 6.87. By looking up the table, we can get the probability value p = 0.00000086. Since p is much less than 0.05, we can determine that the indoor unit's operating capacity has decreased.

[0066] In some embodiments, the method further includes: determining that the indoor unit's operating capability is normal if the difference between the first temperature reach probability and the second temperature reach probability does not meet a preset difference.

[0067] In other words, when the probability value is greater than or equal to the preset probability value, it means that the difference between the first temperature-reaching probability and the second temperature-reaching probability does not meet the preset difference. Therefore, the first temperature-reaching probability and the second temperature-reaching probability are similar, so the indoor unit's operating capability is normal.

[0068] In summary, the indoor unit operation capability detection method according to embodiments of the present invention predicts the probability of reaching the set temperature under preset operating conditions using a first temperature-reaching probability prediction model and a second temperature-reaching probability prediction model, respectively. It then determines whether the indoor unit's operation capability has decreased based on the difference between the first and second temperature-reaching probabilities, achieving timely detection of operation capability. This allows for the detection of a decrease in the indoor unit's operation capability before the user perceives it, enabling appropriate measures to be taken to improve the user experience. Furthermore, since the temperature-reaching probability is affected by various factors, the detection range is wider compared to static pressure detection methods. Moreover, because each indoor unit has different installation locations, usage habits, and building envelope structures, the temperature-reaching probability varies under the same operating conditions. This method, by establishing a temperature-reaching probability prediction model for each indoor unit, has better universality than detection methods using the same threshold, reducing missed detections and false detections.

[0069] Corresponding to the above embodiments, embodiments of the present invention also provide a training method for a temperature probability prediction model. For example... Figure 2 As shown, the training methods for the Darwin probability prediction model include:

[0070] S201, obtain the operating data of the indoor unit.

[0071] Specifically, the operating data may include indoor return air temperature, set temperature, fan speed, outdoor ambient temperature, operating mode, load rate, etc. When the indoor unit is an indoor unit in a multi-split system, the operating data may also include the indoor unit operating ratio.

[0072] It should be noted that the data types of the first and second running data are the same; only the acquisition time differs.

[0073] S202, the running data is filtered and processed to obtain the training dataset.

[0074] Specifically, the amount of operational data is quite large, and some of the data is irrelevant, such as operational data after the indoor ambient temperature has stabilized at the set temperature. Therefore, the operational data needs to be processed.

[0075] S203, train the Bayesian model based on the training dataset to obtain the Davin probability prediction model.

[0076] Specifically, the inference process of a Bayesian model is based on probability calculations. Therefore, a Bayesian model can clearly demonstrate how the model adjusts the estimate of the Darwin probability based on different factors. A Bayesian model can be a Naive Bayes model, which has a simple structure and high computational efficiency.

[0077] It should be noted that the first and second running data are filtered in the same way, and the first and second temperature probability prediction models are also constructed in the same way.

[0078] In the above embodiments, the temperature rise probability prediction model is built based on a variety of operating data. Different indoor units can use the corresponding operating data to build their own temperature rise probability prediction models. Therefore, the temperature rise probability prediction model has strong adaptability, thereby reducing the impact of the installation location of indoor and outdoor units and the building maintenance structure on the performance of different indoor units. Furthermore, the model is built using the Bayesian method, which is simple, highly interpretable, and does not require much computing power. Compared with other deep learning methods, it is easier to deploy.

[0079] In some embodiments, training a Bayesian model based on a training dataset includes: determining prior probabilities and Davin conditional probabilities based on the training dataset; and training the Bayesian model using the prior probabilities and Davin conditional probabilities.

[0080] Specifically, firstly, the prior probability P(Y=Ck)(Ck=0,1) is calculated based on the data distribution in the training dataset, where Ck is 0, the indoor ambient temperature has not reached the set temperature, and Ck is 1, the indoor ambient temperature has reached the set temperature. Then, the conditional probability of reaching the set temperature P(Xj=xjl|Y=Ck) is calculated based on the data distribution in the training dataset, where j represents different dimensions (e.g., outdoor ambient temperature, load rate, and indoor ambient temperature), and l represents different feature dimension categories. Then, the Bayesian model shown in formula (3) is trained using the prior probability and the conditional probability of reaching the set temperature.

[0081]

[0082] In some embodiments, data filtering processing is performed on the operating data to obtain a training dataset, including: filtering the operating data of the indoor unit after it is turned on and within a preset time, and the operating data after the set temperature is changed and within a preset time, to obtain multiple operating datasets, wherein each operating dataset includes operating condition data and temperature reach data, the operating condition data is correlated with the probability of the indoor unit reaching the set temperature, and the temperature reach data is used to determine whether the indoor ambient temperature has reached the set temperature; determining the temperature reach result corresponding to each operating dataset based on the temperature reach data in each operating dataset, wherein the operating condition data and the corresponding temperature reach structure in each operating dataset constitute the training dataset.

[0083] Specifically, the operating data is filtered out from the operating data within a preset time (N minutes) after each indoor unit is turned on or after the set temperature is changed. The operating dataset includes operating condition data and temperature reached. The operating condition data is the operating condition data that affects the probability of indoor temperature reaching but has a weak correlation. The temperature reached data is used to determine whether the indoor ambient temperature has reached the set temperature. Then, the temperature reached result is generated based on the temperature reached data in each operating dataset, thus forming a training dataset. Each training dataset includes operating condition data and temperature reached result. Therefore, multiple operating datasets form multiple training datasets, which constitute the training dataset.

[0084] In some embodiments, the operating condition data includes at least one of indoor and outdoor ambient temperature, set temperature, fan speed, indoor ambient temperature and load rate, and the temperature data includes indoor ambient temperature and set temperature.

[0085] It should be noted that the load rate is the load rate of the multi-split air conditioning system. The outdoor ambient temperature can be the average value or the ambient temperature measured by the local weather station. The indoor ambient temperature can be the indoor unit return air temperature before the set temperature is changed or the indoor ambient temperature measured by other indoor temperature sensors. If the absolute value of the difference between the indoor ambient temperature and the set temperature is less than the preset difference, it can be determined that the indoor ambient temperature has reached the set temperature, and therefore the temperature achievement result Y = 1; otherwise, the temperature achievement result Y = 0.

[0086] For example, we obtain the first operating data for September and October of the first year of operation of a multi-split air conditioning system in a certain region. This first operating data is then filtered to obtain the first operating condition data and the first temperature achievement result. The first operating condition data is two-dimensional data. We select features that influence the probability of temperature achievement, such as the outdoor ambient temperature T4 and the load rate of the multi-split air conditioning system. This data is then used as parameters in the Bayesian model for calculating conditional probabilities. First, according to Tables 1 and 2, the outdoor ambient temperature T4 and the load rate are converted into discrete values.

[0087] Table 1

[0088] T4 [10,30) [30,35) [35,46) Discrete value 1 2 3

[0089] Table 2

[0090] Load factor [0,0.4) [0.4,0.6) [0.6,0.8) [0.8,1.0) Discrete value 1 2 3 4

[0091] Then, the distribution of statistical data is analyzed, and the conditional probability and prior probability are calculated to obtain the parameters of the first Darwin probability model as shown in Table 3.

[0092] Table 3

[0093] Prior probability probability value P(Y=0) 0.43 P(Y=1) 0.57 Conditional probability probability value <![CDATA[P(X T4 =1|Y=0)]]> 0.62 <![CDATA[P(X T4 =2|Y=0)]]> 0.34 <![CDATA[P(X T4 =3|Y=0)]]> 0.04 <![CDATA[P(X load =1|Y=0)]]> 0.37 <![CDATA[P(X load =2|Y=0)]]> 0.13 <![CDATA[P(X load =3|Y=0)]]> 0.27 <![CDATA[P(X load =4|Y=0)]]> 0.23 <![CDATA[P(X T4 =1|Y=0)]]> 0.40 <![CDATA[P(X T4 =2|Y=0)]]> 0.55 <![CDATA[P(X T4 =3|Y=0)]]> 0.05 <![CDATA[P(X load =1|Y=1)]]> 0.08 <![CDATA[P(X load =2|Y=1)]]> 0.10 <![CDATA[P(X load =3|Y=1)]]> 0.59 <![CDATA[P(X load =4|Y=1)]]> 0.23

[0094] Then, the Bayesian model shown in formula (3) is trained using the parameters in Table 3 to obtain the first Darwin probability model.

[0095] The second month's operating data for the multi-split air conditioning system was obtained. This second operating data underwent the same filtering process to obtain the second operating condition data and the second temperature achievement result. The second operating condition data included the outdoor ambient temperature T4 and the load rate of the multi-split air conditioning system. This data was then used as parameters in the Bayesian model for calculating conditional probabilities. First, according to Tables 1 and 2, the outdoor ambient temperature T4 and load rate were converted into discrete values. Then, the distribution of the statistical data was analyzed, and the conditional and prior probabilities were calculated to obtain the parameters of the second temperature achievement probability model, as shown in Table 4.

[0096] Table 4

[0097]

[0098]

[0099] Then, the Bayesian model shown in formula (3) is trained using the parameters in Table 4 to obtain the second Darwin probability model.

[0100] The technical solution of this application is further described in detail below with reference to specific implementation methods:

[0101] like Figure 3 As shown, the method for testing the operating capability of the indoor unit includes the following steps:

[0102] S301, acquire the first operating data of the indoor unit;

[0103] S302, the first running data is filtered and processed to obtain the first training dataset.

[0104] S303, determine the first prior probability and the first conditional probability of Dawen based on the first training dataset.

[0105] S304. The Bayesian model is trained using the first prior probability and the first DaWen conditional probability to obtain the first DaWen probability prediction model.

[0106] S305, acquire the second operating data of the indoor unit;

[0107] S306, The second running data is filtered and processed to obtain the second training dataset;

[0108] S307, determine the second prior probability and the second Davin conditional probability based on the second training dataset.

[0109] S308. The Bayesian model is trained using the second prior probability and the second Davin conditional probability to obtain the second Davin probability prediction model.

[0110] S309, input the preset operating conditions into the first temperature probability prediction model and the second temperature probability prediction model respectively to obtain the first temperature probability and the second temperature probability.

[0111] S310, based on the independent samples t-test method, calculates the probability value between the first probability of reaching temperature and the second probability of reaching temperature.

[0112] S311, determine whether the probability value is less than the preset probability value. If yes, proceed to step S312; otherwise, proceed to step S313.

[0113] S312 indicates a decrease in the operating capacity of the indoor unit.

[0114] S313 indicates that the indoor unit is operating normally.

[0115] In summary, the training method for the temperature rise probability prediction model according to embodiments of the present invention involves acquiring the operating data of the indoor unit, filtering and processing the operating data to obtain a training dataset, and training a Bayesian model based on the training dataset to obtain the temperature rise probability prediction model. Therefore, the temperature rise probability prediction model is constructed based on operating data, and different indoor units can utilize their corresponding operating data to construct their own temperature rise probability prediction models. Consequently, the temperature rise probability prediction model has strong adaptability, thereby reducing the impact of the installation location of the indoor and outdoor units and the building envelope structure on the performance of different indoor units.

[0116] Corresponding to the above embodiments, embodiments of the present invention also provide a computer-readable storage medium storing a computer program thereon, which, when processed by a processor, executes the indoor unit operation capability detection method of any of the foregoing embodiments or the temperature probability prediction model training method of any of the foregoing embodiments.

[0117] According to the computer-readable storage medium of the present invention, a computer program that executes the above-described method for detecting the operating capability of an indoor unit or for training a method for predicting the probability of reaching a certain temperature is used to predict the probability of reaching a certain temperature under preset operating conditions using a first probability prediction model and a second probability prediction model. The program then determines whether the operating capability of the indoor unit has decreased based on the difference between the first probability and the second probability, thereby enabling timely detection of the operating capability. This allows for the detection of a decrease in the operating capability of the indoor unit before the user perceives it, enabling appropriate measures to be taken for the indoor unit and thus improving the user experience.

[0118] Corresponding to the above embodiments, embodiments of the present invention also provide an electronic device. For example... Figure 4As shown, the electronic device 100 includes a memory 110, a processor 120, and a computer program stored in the memory 110 and executable on the processor 120. When the processor 120 executes the computer program, it implements the indoor unit operation capability detection method of any of the foregoing embodiments or the temperature probability prediction model training method of any of the foregoing embodiments.

[0119] According to the present invention, the electronic device executes a computer program of the above-mentioned indoor unit operation capability detection method or temperature probability prediction model training method through a processor. The program predicts the temperature probability under preset operating conditions through the first temperature probability prediction model and the second temperature probability prediction model, and determines whether the operation capability of the indoor unit has decreased based on the difference between the first temperature probability and the second temperature probability. This enables timely detection of operation capability, allowing the user to detect the decrease in the operation capability of the indoor unit before it is perceived, thereby taking corresponding measures to improve the user experience.

[0120] Corresponding to the above embodiments, embodiments of the present invention also provide an indoor unit operating capability detection device. For example... Figure 5 As shown, the indoor unit's operating capability detection device includes an input module 10 and a determination module 20.

[0121] The input module 10 is used to input preset operating conditions into the first temperature reach probability prediction model and the second temperature reach probability prediction model respectively to obtain the first temperature reach probability and the second temperature reach probability. The first temperature reach probability prediction model is trained using first operating data when the indoor unit is operating normally, and the second temperature reach probability prediction model is trained using second operating data of the indoor unit. The acquisition time of the second operating data is later than the acquisition time of the first operating data. The determination module 20 is used to determine that the operating capacity of the indoor unit has decreased when the difference between the first temperature reach probability and the second temperature reach probability meets the preset difference.

[0122] In some embodiments, the determining module 20 is further configured to: determine a t-statistic based on a first temperature-reaching probability and a second temperature-reaching probability; determine a probability value based on the t-statistic; and determine that the difference between the first temperature-reaching probability and the second temperature-reaching probability satisfies a preset difference if the probability value is less than a preset probability value.

[0123] In some embodiments, the determining module 20 is further configured to: determine a first mean and a first variance of the first temperature reach probability, and determine a second mean and a second variance of the second temperature reach probability; determine a pooled variance based on the first variance, the sample size of the first temperature reach probability, the second variance, and the sample size of the second temperature reach probability; and determine a t-statistic based on the first mean, the second mean, and the pooled variance.

[0124] In some embodiments, the determining module 20 is further configured to: determine that the indoor unit's operating capability is normal if the difference between the first temperature reach probability and the second temperature reach probability does not meet a preset difference.

[0125] It should be noted that the specific implementation of the indoor unit operation capability detection device in this embodiment of the invention corresponds one-to-one with the specific implementation of the indoor unit operation capability detection method in the foregoing embodiments of the invention, and will not be repeated here.

[0126] According to an embodiment of the present invention, the indoor unit's operational capability detection device inputs preset operating conditions into a first temperature reach probability prediction model and a second temperature reach probability prediction model via an input module to obtain a first temperature reach probability and a second temperature reach probability. The first temperature reach probability prediction model is trained using first operating data when the indoor unit's operational capability is normal, and the second temperature reach probability prediction model is trained using second operating data of the indoor unit. The acquisition time of the second operating data is later than the acquisition time of the first operating data. A determination module determines that the indoor unit's operational capability has decreased if the difference between the first and second temperature reach probabilities meets a preset difference. Thus, by predicting the temperature reach probability under preset operating conditions using the first and second temperature reach probability prediction models respectively, and judging whether the indoor unit's operational capability has decreased based on the difference between the first and second temperature reach probabilities, timely detection of operational capability is achieved. This allows for the detection of a decrease in the indoor unit's operational capability before the user perceives it, enabling appropriate measures to be taken to improve the user experience.

[0127] Corresponding to the above embodiments, embodiments of the present invention also provide a training device for a temperature probability prediction model. For example... Figure 6 As shown, the training device for the Davin probability prediction model includes: a first acquisition module 30, a second acquisition module 40, and a training module 50.

[0128] The first acquisition module 30 is used to acquire the operating data of the indoor unit; the second acquisition module 40 is used to filter and process the operating data to obtain a training dataset; and the training module 50 is used to train the Bayesian model based on the training dataset to obtain a peak temperature probability prediction model.

[0129] In some embodiments, the training module 50 is further configured to: determine the prior probability and the Davin conditional probability respectively based on the training dataset; and train the Bayesian model using the prior probability and the Davin conditional probability.

[0130] In some embodiments, the second acquisition module 40 is further configured to: filter out the operating data of the indoor unit after it is turned on and within a preset time, and the operating data after the set temperature is changed and within a preset time, from the operating data to obtain multiple operating datasets, wherein each operating dataset includes operating condition data and temperature reach data, the operating condition data is correlated with the probability of the indoor unit reaching the set temperature, and the temperature reach data is used to determine whether the indoor ambient temperature has reached the set temperature; determine the temperature reach result corresponding to each operating dataset based on the temperature reach data in each operating dataset, wherein the operating condition data and the corresponding temperature reach result in each operating dataset constitute a training dataset.

[0131] In some embodiments, the operating condition data includes at least one of indoor and outdoor ambient temperature, set temperature, fan speed, indoor ambient temperature and load rate, and the temperature data includes indoor ambient temperature and set temperature.

[0132] It should be noted that the specific implementation of the training device for the Dawen probability prediction model in this embodiment of the invention corresponds one-to-one with the specific implementation of the training method for the Dawen probability prediction model in the aforementioned embodiment of the invention, and will not be repeated here.

[0133] The training device for the temperature rise probability prediction model according to an embodiment of the present invention acquires the operating data of the indoor unit through a first acquisition module, filters the operating data through a second acquisition module, obtains a training dataset through a third acquisition module, and trains a Bayesian model based on the training dataset to obtain the temperature rise probability prediction model. Therefore, the temperature rise probability prediction model is constructed based on operating data, and different indoor units can use corresponding operating data to construct their own temperature rise probability prediction models. Thus, the temperature rise probability prediction model has strong adaptability, thereby reducing the impact of the installation location of the indoor and outdoor units and the building envelope structure on the performance of different indoor units.

[0134] Corresponding to the above embodiments, embodiments of the present invention also provide an indoor unit. For example... Figures 7 to 9 As shown, the indoor unit 400 includes: the aforementioned electronic device 100, or the aforementioned indoor unit operation capability detection device 200, or the aforementioned temperature probability prediction model training device 300.

[0135] According to the embodiments of the present invention, the indoor unit employs the aforementioned electronic equipment, an indoor unit operation capability detection device, or a temperature probability prediction model training device. It uses a first temperature probability prediction model and a second temperature probability prediction model to predict the temperature probability under preset operating conditions, and determines whether the indoor unit's operation capability has decreased based on the difference between the first and second temperature probabilities. This enables timely detection of operation capability, allowing for the discovery of a decrease in the indoor unit's operation capability before the user perceives it, thus enabling appropriate measures to be taken to improve the user experience.

[0136] Corresponding to the above embodiments, embodiments of the present invention also provide a multi-unit air conditioning system. For example... Figure 10 As shown, the multi-split system 500 includes the aforementioned indoor unit 400.

[0137] According to the multi-split air conditioning system of the present invention, by using the above-mentioned indoor unit, the probability of reaching the temperature under preset operating conditions is predicted by the first temperature probability prediction model and the second temperature probability prediction model, respectively. The difference between the first temperature probability and the second temperature probability is used to determine whether the operating capacity of the indoor unit has decreased, so as to realize timely detection of the operating capacity. In this way, the decrease in the operating capacity of the indoor unit can be detected before the user perceives it, so as to take corresponding measures for the indoor unit and improve the user experience.

[0138] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of computer-readable media include: an electrical connection having one or more wires (electronic device), a portable computer disk drive (magnetic device), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Alternatively, the computer-readable medium may be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in a computer memory.

[0139] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0140] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0141] Furthermore, the terms "first," "second," etc., used in the embodiments of this invention are for descriptive purposes only and should not be construed as indicating or implying relative importance, or implicitly specifying the number of technical features indicated in this embodiment. Therefore, features defined with terms such as "first" and "second" in the embodiments of this invention can explicitly or implicitly indicate that the embodiment includes at least one of those features. In the description of this invention, the word "multiple" means at least two or more, such as two, three, four, etc., unless otherwise explicitly specified in the embodiments.

[0142] In this invention, unless otherwise explicitly specified or limited in the embodiments, the terms "installation," "connection," "joining," and "fixing" appearing in the embodiments should be interpreted broadly. For example, a connection can be a fixed connection, a detachable connection, or an integral part; it can also be a mechanical connection, an electrical connection, etc. Of course, it can also be a direct connection, or an indirect connection through an intermediate medium, or it can be the internal communication of two components, or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific implementation.

[0143] Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for detecting the operating capability of an indoor unit, characterized in that, include: The preset operating conditions are input into the first temperature reach probability prediction model and the second temperature reach probability prediction model respectively to obtain the first temperature reach probability and the second temperature reach probability. The first temperature reach probability prediction model is trained using the first operating data of the indoor unit when its operating capacity is normal, and the second temperature reach probability prediction model is trained using the second operating data of the indoor unit. The acquisition time of the second operating data is later than the acquisition time of the first operating data. If the difference between the first temperature reach probability and the second temperature reach probability meets a preset difference, it is determined that the operating capability of the indoor unit has decreased.

2. The method according to claim 1, characterized in that, Determining that the difference between the first temperature reach probability and the second temperature reach probability satisfies a preset difference includes: The t-statistic is determined based on the first temperature reach probability and the second temperature reach probability; The probability value is determined based on the t-statistic; If the probability value is less than a preset probability value, the difference between the first temperature-reaching probability and the second temperature-reaching probability is determined to satisfy the preset difference.

3. The method according to claim 2, characterized in that, The t-statistic is determined based on the first probability of reaching the temperature and the second probability of reaching the temperature, including: Determine the first mean and first variance of the first temperature reach probability, and determine the second mean and second variance of the second temperature reach probability; The pooled variance is determined based on the first variance, the sample size of the first temperature probability, the second variance, and the sample size of the second temperature probability. The t-statistic is determined based on the first mean, the second mean, and the combined variance.

4. The method according to any one of claims 1-3, characterized in that, The method further includes: If the difference between the first temperature reach probability and the second temperature reach probability does not meet the preset difference, the indoor unit is determined to be operating normally.

5. A training method for a Davin probability prediction model, characterized in that, include: Obtain the operating data of the indoor unit; The running data is filtered to obtain a training dataset; The Bayesian model is trained based on the training dataset to obtain the Davin probability prediction model.

6. The method according to claim 5, characterized in that, Training the Bayesian model based on the training dataset includes: The prior probability and the conditional probability of reaching the temperature are determined based on the training dataset. The Bayesian model is trained using the prior probability and the Davin conditional probability.

7. The method according to claim 5, characterized in that, The running data is filtered to obtain a training dataset, including: The operation data of the indoor unit after it is turned on and within a preset time, and the operation data after the set temperature is changed and within a preset time are filtered from the operation data to obtain multiple operation datasets. Each operation dataset includes operation condition data and temperature reach data. The operation condition data is related to the probability of the indoor unit reaching the set temperature. The temperature reach data is used to determine whether the indoor ambient temperature has reached the set temperature. The temperature reach result corresponding to each running dataset is determined based on the temperature reach data in each running dataset, wherein the running condition data and the corresponding temperature reach structure in each running dataset constitute the training dataset.

8. The method according to claim 7, characterized in that, The operating condition data includes at least one of indoor and outdoor ambient temperature, set temperature, fan speed, indoor ambient temperature, and load rate, and the temperature reached data includes the indoor ambient temperature and the set temperature.

9. A computer-readable storage medium, characterized in that, It stores a computer program, which, when processed by a processor, executes the indoor unit's operating capability detection method as described in any one of claims 1-4 or the temperature probability prediction model training method as described in any one of claims 5-8.

10. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the indoor unit operation capability detection method according to any one of claims 1-4 or the training method for the temperature probability prediction model according to any one of claims 5-8.

11. A device for detecting the operating capacity of an indoor unit, characterized in that, include: The input module is used to input preset operating conditions into the first temperature reach probability prediction model and the second temperature reach probability prediction model respectively to obtain the first temperature reach probability and the second temperature reach probability. The first temperature reach probability prediction model is trained using the first operating data of the indoor unit when its operating capacity is normal, and the second temperature reach probability prediction model is trained using the second operating data of the indoor unit. The acquisition time of the second operating data is later than the acquisition time of the first operating data. The determination module is used to determine that the operating capacity of the indoor unit has decreased if the difference between the first temperature reach probability and the second temperature reach probability meets a preset difference.

12. A training device for a Davin probability prediction model, characterized in that, include: The first acquisition module is used to acquire the operating data of the indoor unit; The second acquisition module is used to filter and process the running data to obtain a training dataset; The training module is used to train the Bayesian model based on the training dataset to obtain the Davin probability prediction model.

13. An indoor unit, characterized in that, include: The electronic device according to claim 10, or the indoor unit operation capability detection device according to claim 11, or the temperature probability prediction model training device according to claim 12.

14. A multi-split air conditioning system, characterized in that, include: The indoor unit according to claim 13.

Images