Apparatus, method and system for predicting service life of components in environmental equipment

Abstract

The present application provides an apparatus, method and system for predicting the service life of a component in an environmental device, the apparatus comprising: an air quality acquisition unit for acquiring information relating to gas quality within a predetermined space within at least one predetermined time period; the gas circulation state acquisition part is used for acquiring gas flow circulation state information of gas in the preset space; and the prediction part is used for predicting the service life information of components in the environmental equipment based on the information related to the gas quality in the preset space and the gas flow circulation state information. Therefore, under different use conditions, the loss condition of the component can be accurately detected at low cost, so that a user can reasonably replace the component.

Description

Technical Field

[0001] The present application relates to the field of electromechanical technology, and in particular to a device, method and system for predicting the service life of components in environmental equipment. Background Art

[0002] Environmental equipment is an electrical appliance used to improve the indoor environment and enhance the comfort of living environment in modern life. Common environmental equipment includes air conditioners, humidifiers, fresh air equipment, etc.

[0003] Environmental equipment usually has components for processing the air in the surrounding environment, such as filters or heat exchange components. These components have a certain service life. After the service life is exceeded, the energy consumption of the environmental equipment will increase significantly, or it will be difficult to achieve the expected effect of improving the environment.

[0004] It should be noted that the above introduction to the technical background is only for the convenience of providing a clear and complete description of the technical solutions of the present application and for the convenience of understanding by those skilled in the art. It cannot be considered that the above technical solutions are well known to those skilled in the art simply because they are described in the background technology section of the present application. Summary of the invention

[0005] In the prior art, whether the filter has reached its service life can be determined based on the usage time of the filter, or the clogging condition of the filter can be detected by light to determine whether the filter needs to be replaced.

[0006] The inventor of the present application has found that the above methods for determining whether the filter needs to be replaced have some limitations: for example, due to the different pollutant concentrations and wind speeds in the environment, the method of judging the wear of the filter by the use time of the filter is not accurate; for another example, using light to detect the blockage of the filter requires the installation of special lighting devices and detection devices, which increases the cost. Therefore, how to accurately and cost-effectively detect the wear of the filter is a problem that needs to be solved.

[0007] In order to solve at least the above-mentioned technical problems or similar technical problems, the embodiments of the present application provide a device, method and system for predicting the service life of components in environmental equipment. The device for predicting the service life of components in environmental equipment predicts the service life information of components in environmental equipment based on information related to gas quality and airflow circulation status information in a predetermined space. Thus, under different usage conditions, the wear of components can be accurately and cost-effectively detected, so that users can reasonably replace the components.

[0008] According to one aspect of an embodiment of the present application, a device for predicting the service life of a component in an environmental device is provided, wherein the environmental device is at least partially disposed in a predetermined space, and the device comprises:

[0009] an air quality acquisition unit, which acquires information related to gas quality in the predetermined space within at least one predetermined time period;

[0010] a gas circulation state acquisition unit, which acquires the gas circulation state information of the gas in the predetermined space; and

[0011] A prediction unit predicts service life information of components in the environmental equipment based on the information related to the gas quality in the predetermined space and the gas flow circulation state information.

[0012] According to one aspect of an embodiment of the present application, a system for predicting the service life of components in environmental equipment is provided, comprising the device for predicting the service life of components in environmental equipment as described in the aforementioned embodiment and a display unit, wherein the display unit displays the service life information of the components in the environmental equipment.

[0013] According to one aspect of an embodiment of the present application, a method for predicting the service life of a component in an environmental device is provided, wherein the environmental device is at least partially disposed in a predetermined space, the method comprising:

[0014] Acquiring information related to gas quality in the predetermined space within at least one predetermined time period;

[0015] Acquiring airflow circulation state information of the gas in the predetermined space; and

[0016] Based on the information related to the gas quality in the predetermined space and the airflow circulation state information, the service life information of the components in the environmental equipment is predicted.

[0017] The beneficial effect of the embodiments of the present application is that the device for predicting the service life of components in environmental equipment predicts the service life information of components in environmental equipment based on information related to gas quality and airflow circulation status information in a predetermined space. Therefore, under different usage conditions, the wear and tear of components can be accurately and cost-effectively detected, so that users can reasonably replace the components.

[0018] With reference to the following description and accompanying drawings, the specific embodiments of the present application are disclosed in detail, indicating the way in which the principles of the present application can be adopted. It should be understood that the embodiments of the present application are not limited in scope. Within the scope of the terms of the appended claims, the embodiments of the present application include many changes, modifications and equivalents.

[0019] Features described and / or illustrated with respect to one embodiment may be used in the same or similar manner in one or more other embodiments, combined with features in other embodiments, or substituted for features in other embodiments.

[0020] It should be emphasized that the term “include / comprises” when used herein refers to the presence of features, integers, steps or components, but does not exclude the presence or addition of one or more other features, integers, steps or components. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The elements and features described in one figure or one implementation of the present application embodiment may be combined with the elements and features shown in one or more other figures or implementations. In addition, in the accompanying drawings, similar reference numerals represent corresponding parts in several figures and can be used to indicate corresponding parts used in more than one implementation.

[0022] The included drawings are used to provide a further understanding of the embodiments of the present application, which constitute a part of the specification, are used to illustrate the implementation methods of the present application, and together with the text description, explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0023] Figure 1 is a schematic diagram of a device for predicting the service life of a component in an environmental device according to an embodiment of the first aspect of the present application;

[0024] Figure 2 It is a schematic diagram of the neural network model used by the prediction unit 3;

[0025] Figure 3 is another schematic diagram of a device for predicting the service life of a component in an environmental device in an embodiment of the first aspect of the present application;

[0026] Figure 4 is a schematic diagram of the neural network model used by the prediction unit 3a;

[0027] Figure 5 It is a schematic diagram of the components in the predicted environment equipment in Example 1;

[0028] Figure 6 It is a schematic diagram of airflow circulation status information at each predetermined position in the predetermined space;

[0029] Figure 7 is a schematic diagram of a system for predicting the service life of components in environmental equipment according to an embodiment of the second aspect;

[0030] Figure 8 is a schematic diagram of a method for predicting the service life of a component in an environmental device according to an embodiment of the third aspect;

[0031] Fig. 9is another schematic diagram of a method for predicting the service life of a component in an environmental device according to an embodiment of the third aspect. DETAILED DESCRIPTION

[0032] The foregoing and other features of the present application will become apparent through the following description with reference to the accompanying drawings. In the description and the accompanying drawings, specific embodiments of the present application are specifically disclosed, which show some embodiments in which the principles of the present application can be adopted. It should be understood that the present application is not limited to the described embodiments. On the contrary, the present application includes all modifications, variations and equivalents falling within the scope of the attached claims. Various embodiments of the present application are described below in conjunction with the accompanying drawings. These embodiments are exemplary only and are not limitations of the present application.

[0033] In the embodiments of the present application, the terms "first", "second", etc. are used to distinguish different elements in terms of title, but do not indicate the spatial arrangement or temporal order of these elements, etc., and these elements should not be limited by these terms. The term "and / or" includes any one and all combinations of one or more of the associated listed terms. The terms "comprising", "including", "having", etc. refer to the presence of the stated features, elements, components or components, but do not exclude the presence or addition of one or more other features, elements, components or components.

[0034] In the embodiments of the present application, the singular forms "a", "the", etc. include plural forms and should be broadly understood as "a kind" or "a type" rather than being limited to the meaning of "one"; in addition, the term "the" should be understood to include both singular and plural forms, unless the context clearly indicates otherwise. In addition, the term "according to" should be understood as "at least in part according to...", and the term "based on" should be understood as "at least in part based on...", unless the context clearly indicates otherwise.

[0035] Embodiments of the first aspect

[0036] The first aspect of the present application provides a device for predicting the service life of components in an environmental device, the device is used to predict the service life of components in the environmental device, the environmental device is arranged in a predetermined space, such as a predetermined indoor space, or an outdoor space.

[0037] Figure 1 It is a schematic diagram of a device for predicting the service life of components in environmental equipment according to an embodiment of the first aspect of the present application.

[0038] like Figure 1 As shown, the device 100 for predicting the service life of components in environmental equipment includes: an air quality acquisition unit 1, a gas circulation state acquisition unit 2 and a prediction unit 3.

[0039] The air quality acquisition unit 1 acquires information related to gas quality in the predetermined space within at least one predetermined time period; the gas circulation state acquisition unit 2 acquires airflow circulation state information of the gas in the predetermined space; the prediction unit 3 predicts the service life information of the components in the environmental equipment based on the information related to gas quality in the predetermined space acquired by the air quality acquisition unit 1 and the airflow circulation state information acquired by the gas circulation state acquisition unit 2.

[0040] Through the embodiments of the first aspect, even if the environmental equipment is under different usage conditions, the wear and tear of components can be accurately and inexpensively detected, so that the user can reasonably replace the component.

[0041] In the present application, the environmental equipment includes at least one of the following equipment: an air conditioner, a humidifier, a fresh air blower, an air purifier and a dust collector, etc.

[0042] In the present application, the components in the environmental equipment include components in the environmental equipment that process the gas in the predetermined space, for example, at least one of the following components:

[0043] Filters for indoor units of air conditioners, heat exchange components for outdoor units of air conditioners, filters for automobile air conditioners, purifier filters, fresh air fan filters, purification components based on negative ion technology, purification components based on streamer energy technology, and purification components based on high-voltage electrostatic sterilization technology, etc.

[0044] Among them, the types of the above-mentioned filters include: activated carbon filters, electrostatic filters, ordinary filters or high-performance filters, etc.

[0045] In at least one embodiment, the information related to gas quality obtained by the air quality acquisition unit 1 includes:

[0046] Distribution change information of gas quality parameters in the predetermined space before and after the environmental device is turned on; and / or

[0047] The time from when the environmental equipment is turned on to when the distribution of the gas quality parameter in the predetermined space reaches the predetermined condition.

[0048] Among them, the distribution of gas quality parameters in a predetermined space meets a predetermined condition, which may refer to the gas quality parameters in the predetermined space reaching a balanced distribution, for example: the difference in the rate of change of the gas quality parameters at multiple predetermined positions in the predetermined space is less than or equal to a first threshold; and / or, the rate of change of the gas quality parameters at each of the multiple predetermined positions in the predetermined space is less than or equal to a second threshold.

[0049] In at least one embodiment, the air quality acquisition unit 1 can obtain the gas quality parameters collected or stored by the air quality sensor from the air quality sensor arranged at a predetermined position in the predetermined space. The gas quality parameters include at least one of the following parameters: particulate matter (PM) concentration, dust concentration, mold concentration, volatile organic compound (VOC) concentration, temperature, humidity, carbon dioxide (CO2) concentration, oxygen concentration, and odor concentration.

[0050] In at least one embodiment, the air quality acquisition unit 1 obtains information related to gas quality within at least one predetermined time period, wherein the at least one predetermined time period includes: the current day; and / or, the first number of days before the current moment, for example, the day before the current moment; and / or, the second number of days before the current moment, for example, three days before the current moment; and / or, the third number of days before the current moment, for example, the week before the current moment; and / or, the fourth number of days before the current moment, for example, the month before the current moment. The first number is less than the second number, the second number is less than the third number, and the third number is less than the fourth number. In addition, the at least one predetermined time period may also include more time periods.

[0051] In at least one embodiment, the airflow circulation state information acquired by the gas circulation state acquisition unit 2 includes: the speed and / or direction of the airflow at a predetermined position in the predetermined space. For example, the gas circulation state acquisition unit 2 is based on the layout information in the predetermined space (for example, the area, apartment type, location, height, layout and other information in the predetermined space are acquired through a building information model or sensor information), and simulates the airflow direction at each predetermined position in the predetermined space according to computational fluid dynamics (CFD), and obtains the speed of the airflow at the predetermined position based on a wind speed sensor. Among them, the wind speed sensor can be, for example, an ultrasonic wind speed sensor, etc. In the present application, the gas circulation state acquisition unit 2 can acquire the airflow circulation state information at the current moment.

[0052] In at least one embodiment, the service life information of the component predicted by the prediction unit 3 includes: the service life coefficient of the component, and / or the time until the next replacement of the component. The service life coefficient can be expressed in the form of percentage or decimal, for example: when the service life coefficient is 0 (or 0%), it means that the component is in a brand new state; when the service life coefficient is 1 (or 100%), it means that the component has reached the end of its service life and needs to be replaced.

[0053] The prediction unit 3 may use a neural network to obtain the service life information of the component. Figure 2is a schematic diagram of the neural network, such as Figure 2 As shown, the neural network 31 includes:

[0054] A sub-neural network 311 for processing time series, a first convolution and pooling sub-neural network 312, a second convolution and pooling sub-neural network 313, a fully connected network 314, a normalization unit 315 and a time mapping unit 316.

[0055] The information related to the gas quality obtained by the air quality acquisition unit 1 and the airflow circulation state information obtained by the gas circulation state acquisition unit 2 are input into the neural network 31 .

[0056] The sub-neural network 311 for processing time series extracts time features for information related to gas quality, and the extracted time features are input into the first convolution and pooling sub-neural network 312, wherein the sub-neural network 311 for processing time series may use a long short-term memory (LSTM) network model, for example;

[0057] The first convolution and pooling sub-neural network 312 performs convolution processing (e.g., feature mixing) on ​​the extracted temporal features and reduces the feature dimension of the data;

[0058] The second convolution and pooling sub-neural network 313 performs convolution processing (e.g., feature mixing) on ​​the airflow circulation state information and reduces the feature dimension of the data. For example, the predetermined space can be divided into a plurality of three-dimensional sub-regions, each sub-region has a coordinate in the three-dimensional space, each sub-region corresponds to a three-dimensional data to represent the airflow circulation state information of the sub-region, and the three-dimensional data of the sub-region at each predetermined position can correspond to a numerical value for convolution calculation; through the second convolution and pooling sub-neural network 313, the influence coefficient of the current airflow circulation state on the information related to the gas quality of the day can be extracted;

[0059] The fully connected network 314 integrates and processes the features output by the first convolution and pooling sub-neural network 312 and the features output by the second convolution and pooling sub-neural network 313 and classifies them to output features related to the service life of the component and features related to the replacement time;

[0060] The features related to the service life of the component are input into the normalization unit 315, so as to obtain the service life coefficient, which is a numerical value indicating the confidence of the component life, wherein the normalization unit 315 can perform normalization processing based on the Softmax function;

[0061] The features related to the replacement time are input into the time mapping unit 316, so as to obtain the time until the next replacement of the component.

[0062] like Figure 1 As shown, the device 100 for predicting the service life of components in environmental equipment may also include: a neural network training unit 4. The neural network training unit 4 is used to train the neural network model used by the prediction unit 3. As a result, the prediction unit 3 can use the trained neural network model to predict the service life information of the components in the environmental equipment. In addition, the present application is not limited to this. For example, the neural network training unit 4 may not be a part of the device 100, that is, the neural network model can be trained outside the device 100 and sent to the prediction unit 3 for storage, and the prediction unit 3 uses the trained neural network model for prediction.

[0063] In the present application, the neural network training unit 4 can train the neural network model based on first training data, second training data and third training data, wherein: the first training data includes information related to the gas quality in the predetermined space within at least one first predetermined time period; the second training data includes airflow circulation state information of the gas in the predetermined space; the third training data includes service life information of components in the environmental equipment.

[0064] Among them, the at least one first predetermined time period involved in the first training data may include: the current day of the training data; and / or, the first number of days before the current moment of the training data, for example, the day before the current moment of the training data; and / or, the second number of days before the current moment of the training data, for example, three days before the current moment of the training data; and / or, the third number of days before the current moment of the training data, for example, the week before the current moment of the training data; and / or, the fourth number of days before the current moment of the training data, for example, the month before the current moment of the training data. Among them, the first number is less than the second number, the second number is less than the third number, and the third number is less than the fourth number. In addition, the at least one first predetermined time period may also include more time periods.

[0065] For example, in the process of training the neural network model, the neural network training unit 4 inputs the first training data and the second training data into the neural network model to be trained, obtains the output data of the neural network model, and adjusts the parameters of the neural network model (for example, the parameters may be the weights used by each node in the neural network model) according to the result of comparing the output data with the third training data. Thus, after multiple trainings, the loss function converges and the training process is completed.

[0066] In the process of training the neural network model, the root mean square can be used as the loss function of the neural network model. The loss function is, for example, in the following form:

[0067]

[0068] Among them, Loss represents the loss function; yi represents the output data of the neural network model; represents the third training data.

[0069] In at least one embodiment, the initial training data may come from a laboratory, whereby an initial neural network model may be trained based on the initial training data. Subsequently, the model may be retrained using data from the use process, so that the prediction results of the neural network model are more accurate.

[0070] like Figure 1 As shown, the device 100 for predicting the service life of a component in an environmental device may also include: an energy consumption calculation unit 5. The energy consumption calculation unit 5 calculates the cumulative energy consumption information of the environmental device since the component is installed and / or the current energy consumption information of the environmental device based on the service life information of the component in the environmental device. For example, the energy consumption calculation unit 5 may communicate with the environmental device in real time or periodically to collect the energy consumption information of the environmental device, and perform cumulative calculations on the collected energy consumption information (for example, integrating the power and the startup time) to obtain the above-mentioned cumulative energy consumption information; or, the energy consumption calculation unit 5 may calculate the current power of the environmental device based on the energy consumed during the most recent operation of the environmental device and the operating time; or, the energy consumption calculation unit 5 combines the current energy consumption information with the service life information of the component in the environmental device predicted by the prediction unit 3 to calculate the predicted energy consumption value of the environmental device if the component is not replaced.

[0071] In the present application, the device for predicting the service life of components in environmental equipment can also receive other information, so as to predict the service life information of components in environmental equipment.

[0072] Figure 3 is another schematic diagram of a device for predicting the service life of a component in an environmental device in an embodiment of the first aspect of the present application. Figure 3 As shown, the device 100a for predicting the service life of components in environmental equipment includes: an air quality acquisition unit 1, a gas circulation state acquisition unit 2, an outdoor air quality acquisition unit 20 and a prediction unit 3a.

[0073] The air quality acquisition unit 1 acquires information related to gas quality in the predetermined space within at least one predetermined time period; the gas circulation state acquisition unit 2 acquires airflow circulation state information of the gas in the predetermined space; the outdoor air quality acquisition unit 20 acquires information related to gas quality outside the predetermined space within the at least one predetermined time period; the prediction unit 3a predicts the service life information of components in the environmental equipment based on the information related to gas quality in the predetermined space acquired by the air quality acquisition unit 1, the airflow circulation state information acquired by the gas circulation state acquisition unit 2, and the information related to gas quality outside the predetermined space acquired by the outdoor air quality acquisition unit 20.

[0074] For the description of the air quality acquisition unit 1 and the gas circulation state acquisition unit 2, reference may be made to the aforementioned related contents.

[0075] The outdoor air quality acquisition unit 20 can obtain information related to the gas quality outside the predetermined space based on the meteorological information released by the meteorological information platform, or obtain information related to the gas quality outside the predetermined space based on the air quality data measured by a gas quality detection device arranged outside the predetermined space.

[0076] In at least one embodiment, the information related to the gas quality outside the predetermined space may include: the maximum value, and / or the minimum value, and / or the average value of the gas quality parameter outside the predetermined space in each predetermined time period. The gas quality parameter outside the predetermined space may include at least one of the following parameters: particulate matter (PM) concentration, dust concentration, mold concentration, volatile organic compound (VOC) concentration, temperature, humidity, carbon dioxide (CO2) concentration, oxygen concentration, odor concentration.

[0077] In the present application, the prediction unit 3a can predict the service life information of components in the environmental equipment based on the information related to the gas quality in the predetermined space obtained by the air quality acquisition unit 1, the airflow circulation state information obtained by the gas circulation state acquisition unit 2, and the information related to the gas quality outside the predetermined space obtained by the outdoor air quality acquisition unit 20. Therefore, for environmental equipment whose service life of components is related to the outdoor air quality (for example, equipment such as fresh air fans), the service life information of components can be accurately predicted.

[0078] In the present application, the prediction unit 3a can predict the service life information of the component based on the neural network model. For the description of the service life information, please refer to the above description.

[0079] Figure 4 is a schematic diagram of the neural network used by the prediction unit 3a, such as Figure 4 As shown, the neural network 31a includes:

[0080] A first sub-neural network 311 for processing time series, a second sub-neural network 311a for processing time series, a splicing processing unit 311b, a first convolution and pooling sub-neural network 312a, a second convolution and pooling sub-neural network 313, a fully connected network 314a, a normalization unit 315 and a time mapping unit 316.

[0081] The information related to the gas quality in the predetermined space obtained by the air quality acquisition unit 1, the airflow circulation state information obtained by the gas circulation state acquisition unit 2, and the information related to the gas quality outside the predetermined space obtained by the outdoor air quality acquisition unit 20 are input into the neural network 31a.

[0082] The first sub-neural network 311 for processing time series performs time feature extraction on the information related to the gas quality in the predetermined space, wherein the first sub-neural network 311 for processing time series may use a long short-term memory (LSTM) network model, for example;

[0083] The second sub-neural network 311a for processing the time series performs time feature extraction on the information related to the gas quality outside the predetermined space, wherein the second sub-neural network 311a for processing the time series may use a long short-term memory (LSTM) network model, for example;

[0084] The splicing processing unit 311b splices the features extracted by the sub-neural network 311 of the first processing time series with the features extracted by the sub-neural network 311a of the second processing time series to obtain spliced ​​features, for example, splicing the features with a dimension of N1 and the features with a dimension of N2 into features with a dimension of N=N1+N2;

[0085] The first convolution and pooling sub-neural network 312a performs convolution processing (e.g., feature mixing) on ​​the features output by the splicing processing unit 311b, and reduces the feature dimension of the data;

[0086] The second convolution and pooling sub-neural network 313 performs convolution processing (e.g., feature mixing) on ​​the airflow circulation state information and reduces the feature dimension of the data. For a detailed description of the second convolution and pooling sub-neural network 313, see Figure 2 Description of the same parts in

[0087] The fully connected network 314a integrates and processes the features output by the first convolution and pooling sub-neural network 312a and the features output by the second convolution and pooling sub-neural network 313, and classifies them to output features related to the service life of the component and features related to the replacement time;

[0088] The features related to the service life of the component are input into the normalization unit 315, so as to obtain a service life coefficient, which is a numerical value indicating the confidence of the component life, wherein the normalization unit 315 may perform normalization processing based on a Softmax function;

[0089] The features related to the replacement time are input into the time mapping unit 316, so as to obtain the time until the next replacement of the component.

[0090] like Figure 3 As shown, the device 100a for predicting the service life of components in environmental equipment may also include: a neural network training unit 4a. The neural network training unit 4a is used to train the neural network model used by the prediction unit 3a. Thus, the prediction unit 3a can use the trained neural network model to predict the service life information of the components in the environmental equipment. In addition, the present application is not limited to this. For example, the neural network training unit 4a may not be a part of the device 100a, that is, the neural network model can be trained outside the device 100a and sent to the prediction unit 3a for storage, and the prediction unit 3 uses the trained neural network model for prediction.

[0091] In the present application, the neural network training unit 4a can train the neural network model based on first training data, second training data, third training data and fourth training data, wherein: the first training data includes information related to the gas quality in the predetermined space within at least one first predetermined time period; the second training data includes airflow circulation state information of the gas in the predetermined space; the third training data includes service life information of components in the environmental equipment; the fourth training data includes information related to the gas quality outside the predetermined space within at least one first predetermined time period.

[0092] Among them, the at least one first predetermined time period involved in the first training data may include: the current day of the training data; and / or, the first number of days before the current moment of the training data, for example, the day before the current moment of the training data; and / or, the second number of days before the current moment of the training data, for example, three days before the current moment of the training data; and / or, the third number of days before the current moment of the training data, for example, the week before the current moment of the training data; and / or, the fourth number of days before the current moment of the training data, for example, the month before the current moment of the training data. Among them, the first number is less than the second number, the second number is less than the third number, and the third number is less than the fourth number. In addition, the at least one first predetermined time period may also include more time periods.

[0093] For example, in the process of training the neural network model, the neural network training unit 4a inputs the first training data, the second training data and the fourth training data into the neural network model to be trained, obtains the output data of the neural network model, and adjusts the parameters of the neural network model (for example, the parameters may be the weights used by each node in the neural network model) according to the result of comparing the output data with the third training data. Thus, after multiple trainings, the loss function converges and the training process is completed.

[0094] In the process of training the neural network model, the root mean square can be used as the loss function of the neural network model. The loss function is, for example, in the following form:

[0095]

[0096] Among them, Loss represents the loss function; yi represents the output data of the neural network model; represents the third training data.

[0097] In at least one embodiment, the initial training data may come from a laboratory, whereby an initial neural network model may be trained based on the initial training data. Subsequently, the model may be retrained using data from the use process, so that the prediction results of the neural network model are more accurate.

[0098] like Figure 3 As shown, the device 100a for predicting the service life of components in environmental equipment may also include: an energy consumption calculation unit 5. For the description of the energy consumption calculation unit 5, please refer to Figure 1 Description of the same unit in .

[0099] The working principle of the device 100 or 100a for predicting the service life of components in environmental equipment of the present application is described below in combination with several examples.

[0100] Example 1:

[0101] Figure 5 This is a schematic diagram of the components in the predicted environment equipment in Example 1. Figure 5 As shown, the environmental device 51 may be an air purifier, the component 52 may be a filter disposed in the air purifier, and the environmental device 51 is disposed in a predetermined space, which may be indoors. In addition, the present application is not limited thereto, the environmental device 51 may also be a humidifier or an air conditioner, and the component 52 may be a filter of a humidifier or an air conditioner, etc.

[0102] like Figure 5 As shown, the gas in the predetermined space enters the component 52 , and the gas processed by the component 52 is output from the component 52 .

[0103] In Example 1, the predetermined space has one or more environmental devices 51, for example; a plurality of wind speed sensors are arranged in the predetermined space for detecting the wind speed at a predetermined position; in addition, a plurality of gas quality sensors are also arranged in the predetermined space for detecting the gas quality.

[0104] In Example 1, the method of using the trained neural network model and the device 100 to predict the service life information of the filter in each environmental device 51 includes the following steps 1, 2 and 3.

[0105] Step 1: Obtain information related to gas quality in the predetermined space within at least one predetermined time period, for example:

[0106] 1) Changes in the distribution of indoor air quality parameters today (e.g., the distribution of air quality parameters before the environmental device 51 is turned on and the distribution of air quality parameters after the environmental device 51 is turned on when the distribution reaches a predetermined condition) and the turn-on time;

[0107] 2) changes in indoor air quality parameter distribution on the previous day (e.g., the distribution of air quality parameters before the environmental device 51 is turned on, and / or the distribution of air quality parameters when the environmental device 51 is turned off, and / or the distribution of air quality parameters when the environmental device 51 reaches a predetermined condition after the environmental device 51 is turned on) and the turn-on time;

[0108] 3) Changes in the distribution of indoor air quality parameters over the previous three days (e.g., the distribution of air quality parameters before the environmental device 51 is turned on, and / or the distribution of air quality parameters when the environmental device 51 is turned off, and / or the distribution of air quality parameters when the environmental device 51 is turned on and reaches a predetermined condition) and the turn-on time;

[0109] 4) Changes in indoor air quality parameter distribution in the previous week (i.e., seven days ago) (e.g., the distribution of air quality parameters before the environmental device 51 is turned on, and / or the distribution of air quality parameters when the environmental device 51 is turned off, and / or the distribution of air quality parameters when the environmental device 51 is turned on and reaches a predetermined condition) and the turn-on time;

[0110] 5) Changes in the indoor air quality parameter distribution in the previous month (i.e., the same day one month ago) (for example, the distribution of the air quality parameters before the environmental device 51 is turned on, and / or the distribution of the air quality parameters when the environmental device 51 is turned off, and / or the distribution of the air quality parameters when the environmental device 51 reaches a predetermined condition after the environmental device 51 is turned on) and the turn-on time.

[0111] The opening time refers to the length of time from when the environmental device 51 is turned on to when it is turned off, or the length of time from when the environmental device 51 is turned on to when the air quality parameter distribution reaches a predetermined condition.

[0112] The distribution of the gas quality parameters in the predetermined space meets the predetermined conditions, including:

[0113] The difference between the change rates of the gas quality parameters at multiple predetermined positions within the predetermined space is less than or equal to a first threshold; and / or, the change rates of the gas quality parameters at each of the multiple predetermined positions within the predetermined space are less than or equal to a second threshold.

[0114] Step 2, obtaining the airflow circulation state information of the gas in the predetermined space after the air quality parameters of the day are stable; for example, the gas circulation state acquisition unit 2 of the device 100 obtains the direction of the airflow at a predetermined position (for example, the predetermined position environmental equipment 51 has a predetermined distance) through simulation based on the layout information in the predetermined space, and obtains the speed of the airflow at the predetermined position based on the wind speed sensor, thereby obtaining the airflow circulation state information at each predetermined position in the predetermined space. Figure 6 It is a schematic diagram of the airflow circulation status information at each predetermined position in the predetermined space, such as Figure 6 As shown, the predetermined space can be divided into multiple subspaces, and the position of each subspace can be represented as coordinates (x, y, z), which can be the coordinates of the center point of the subspace, or the coordinates of a predetermined point in the subspace. Figure 6 The direction of the arrow indicates the direction of the airflow in each subspace, and the length of the arrow indicates the speed of the airflow in the subspace.

[0115] Step 3: Input the information obtained in steps 1 and 2 into the neural network model used by the prediction unit 3 to obtain the service life information of component 52, which includes: the service life coefficient of component 52 (for example, expressed as a decimal or a fraction) and / or the time until the next replacement of component 52.

[0116] In Example 1, the neural network model used by the prediction unit 3 can be obtained through training, and the training can be performed based on the first training data, the second training data and the third training data.

[0117] The first training data includes: information related to gas quality in the predetermined space within at least one predetermined time period, for example:

[0118] 1) Changes in the indoor air quality parameter distribution on this day (i.e., the date of the first training data) (e.g., the distribution of the air quality parameters before the environmental device 51 is turned on, and / or the distribution of the air quality parameters when the environmental device 51 is turned off, and / or the distribution of the air quality parameters when the environmental device 51 is turned on and reaches a predetermined condition) and the turn-on time;

[0119] 2) changes in indoor air quality parameter distribution on the previous day (e.g., the distribution of air quality parameters before the environmental device 51 is turned on, and / or the distribution of air quality parameters when the environmental device 51 is turned off, and / or the distribution of air quality parameters when the environmental device 51 reaches a predetermined condition after the environmental device 51 is turned on) and the turn-on time;

[0120] 3) Changes in the distribution of indoor air quality parameters over the previous three days (e.g., the distribution of air quality parameters before the environmental device 51 is turned on, and / or the distribution of air quality parameters when the environmental device 51 is turned off, and / or the distribution of air quality parameters when the environmental device 51 is turned on and reaches a predetermined condition) and the turn-on time;

[0121] 4) Changes in indoor air quality parameter distribution in the previous week (i.e., seven days ago) (e.g., the distribution of air quality parameters before the environmental device 51 is turned on, and / or the distribution of air quality parameters when the environmental device 51 is turned off, and / or the distribution of air quality parameters when the environmental device 51 is turned on and reaches a predetermined condition) and the turn-on time;

[0122] 5) Changes in the indoor air quality parameter distribution in the previous month (i.e., the same day one month ago) (for example, the distribution of the air quality parameters before the environmental device 51 is turned on, and / or the distribution of the air quality parameters when the environmental device 51 is turned off, and / or the distribution of the air quality parameters when the environmental device 51 reaches a predetermined condition after the environmental device 51 is turned on) and the turn-on time.

[0123] The instructions on the start time and predetermined conditions are the same as above.

[0124] The second training data includes: airflow circulation state information of the gas in the predetermined space after the air quality parameters are stabilized on the current day (ie, the date of the second training data is the same as the date of the first training data).

[0125] The third training data includes: service life information of components in the environmental equipment. The third training data is the actual service life information of the components.

[0126] During the training process, the neural network training unit 4 can input the first training data and the second training data into the neural network model to obtain output data of the neural network model, and adjust the parameters of the neural network model according to the result of comparing the output data with the third training data.

[0127] Example 2:

[0128] In Example 2, the environmental device may be an outdoor unit of an air conditioner, and the component may be a heat exchange component disposed in the outdoor unit of the air conditioner. The environmental device is disposed in a predetermined space, and the predetermined space may be outdoors. In addition, the present application is not limited thereto, and the environmental device 51 may also be other devices disposed outdoors.

[0129] In Example 2, outdoor air exchanges heat with the heat exchange component, and the amount of dust on the heat exchange component will affect the heat exchange effect, thereby increasing energy consumption. Therefore, in Example 2, the device 100 is used to predict the service life information of the heat exchange component and other components, so that the component can be replaced in time to suppress the increase in energy consumption.

[0130] In Example 2, the predetermined space has one or more environmental devices 2, for example; multiple wind speed sensors are arranged in the predetermined space (for example, outdoors) for detecting the wind speed at the predetermined position; in addition, multiple gas quality sensors are arranged in the predetermined space for detecting the gas quality. In addition, the wind speed sensor and / or the gas quality sensor may not be arranged, and the wind speed and / or air quality parameters at the predetermined position may be obtained based on the meteorological information and other information released by the meteorological platform.

[0131] In Example 2, the method of using the trained neural network model and the device 100 to predict the service life information of the thermal exchange components in the environmental equipment includes the following steps 1, 2 and 3.

[0132] Step 1: Obtain information related to air quality in the predetermined space within at least one predetermined time period. The air quality may be air temperature, for example:

[0133] 1) Changes in the outdoor air quality parameter distribution on this day (i.e., the date of the first training data) (e.g., the distribution of the air quality parameter before the environmental device is turned on, and / or the distribution of the air quality parameter when the environmental device is turned off) and the turn-on time;

[0134] 2) changes in the distribution of outdoor air quality parameters on the previous day (e.g., the distribution of air quality parameters before the environmental equipment is turned on, and / or the distribution of air quality parameters when the environmental equipment is turned off) and the time of turning on;

[0135] 3) changes in the distribution of outdoor air quality parameters over the previous three days (e.g., the distribution of air quality parameters before the environmental equipment was turned on, and / or the distribution of air quality parameters when the environmental equipment was turned off) and the time of turning on;

[0136] 4) changes in outdoor air quality parameter distribution in the previous week (i.e., seven days ago) (e.g., the distribution of air quality parameters before the environmental equipment is turned on, and / or the distribution of air quality parameters when the environmental equipment is turned off) and the time of turning on;

[0137] 5) Changes in outdoor air quality parameter distribution in the previous month (i.e., the same day one month ago) (e.g., the distribution of air quality parameters before the environmental equipment is turned on, and / or the distribution of air quality parameters when the environmental equipment is turned off) and the turn-on time.

[0138] The start time refers to the length of time from when the environmental device is turned on to when it is turned off, or the length of time from when the environmental device is turned on to when a predetermined condition is met.

[0139] For example, when the outdoor unit is the outdoor unit of a fixed-frequency air conditioner, the start-up time refers to the length of time from the start of the outdoor unit to the time when the indoor temperature reaches a predetermined temperature and the outdoor unit stops running; for another example, when the outdoor unit is the outdoor unit of a variable-frequency air conditioner, the start-up time refers to the length of time from the start of the outdoor unit to the time when the indoor temperature reaches a predetermined temperature and the outdoor unit runs at a low frequency.

[0140] To predict the service life information of the heat exchange component of the outdoor unit of a certain air conditioner, the opening time of the outdoor unit is used.

[0141] Step 2: Obtain the airflow circulation status information of the gas in the predetermined space (ie, outdoors) within the day.

[0142] Step 3: Input the information obtained in steps 1 and 2 into the neural network model used by the prediction unit 3 to obtain the service life information of the component (e.g., the thermal exchange component), which includes: the service life coefficient of the component (e.g., expressed as a decimal or a fraction) and / or the time until the next replacement of the component 52.

[0143] In Example 2, the neural network model used by the prediction unit 3 can be obtained through training, and the training can be performed based on the first training data, the second training data and the third training data.

[0144] The first training data includes: information related to gas quality in the predetermined space within at least one predetermined time period, for example:

[0145] 1) Changes in the distribution of outdoor air quality parameters for the day (e.g., the distribution of air quality parameters before the environmental equipment is turned on, and / or the distribution of air quality parameters when the environmental equipment is turned off) and the time of turning on;

[0146] 2) changes in the distribution of outdoor air quality parameters on the previous day (e.g., the distribution of air quality parameters before the environmental equipment is turned on, and / or the distribution of air quality parameters when the environmental equipment is turned off) and the time of turning on;

[0147] 3) changes in the distribution of outdoor air quality parameters over the previous three days (e.g., the distribution of air quality parameters before the environmental equipment was turned on, and / or the distribution of air quality parameters when the environmental equipment was turned off) and the time of turning on;

[0148] 4) changes in outdoor air quality parameter distribution in the previous week (i.e., seven days ago) (e.g., the distribution of air quality parameters before the environmental equipment is turned on, and / or the distribution of air quality parameters when the environmental equipment is turned off) and the time of turning on;

[0149] 5) Changes in outdoor air quality parameter distribution in the previous month (i.e., the day one month ago) (e.g., the distribution of air quality parameters before the environmental device is turned on, and / or the distribution of air quality parameters when the environmental device is turned off) and the time of turning on. The description of the turning on time is the same as above.

[0150] The second training data includes: airflow circulation state information of the gas in the predetermined space (eg, outdoors) on the current day (ie, the date of the second training data is the same as the date of the first training data).

[0151] The third training data includes: service life information of components in the environmental equipment. The third training data is the actual service life information of the components.

[0152] During the training process, the neural network training unit 4 can input the first training data and the second training data into the neural network model to obtain output data of the neural network model, and adjust the parameters of the neural network model according to the result of comparing the output data with the third training data.

[0153] Example 3:

[0154] In Example 3, the environmental device may be a fresh air system, and the component may be a filter disposed in the fresh air system. The fresh air system is at least partially disposed in a predetermined space (for example, an air outlet of the fresh air system is located in the predetermined space), and the predetermined space may be indoors. In addition, the present application is not limited thereto, and the environmental device may also be other types of equipment, and the component may be other components that need to contact the gas outside the predetermined space, etc.

[0155] In Example 3, the predetermined space has, for example, one or more air outlets of environmental equipment; a plurality of wind speed sensors are arranged in the predetermined space for detecting the wind speed at predetermined positions; in addition, a plurality of gas quality sensors are also arranged in the predetermined space for detecting the gas quality.

[0156] In Example 3, the method of using the trained neural network model and the device 100a to predict the service life information of the filter in each environmental device includes the following steps 1, 2, 3 and 4.

[0157] Step 1: Obtain information related to gas quality in the predetermined space within at least one predetermined time period, for example:

[0158] 1) Changes in the distribution of indoor air quality parameters for the day (e.g., the distribution of air quality parameters before the environmental equipment is turned on and the distribution of air quality parameters after the environmental equipment is turned on when the predetermined conditions are met) and the time of turning on;

[0159] 2) changes in indoor air quality parameter distribution on the previous day (e.g., the distribution of air quality parameters before the environmental device is turned on, and / or the distribution of air quality parameters when the environmental device is turned off, and / or the distribution of air quality parameters when the environmental device is turned on and reaches a predetermined condition) and the turn-on time;

[0160] 3) Changes in the distribution of indoor air quality parameters over the previous three days (e.g., the distribution of air quality parameters before the environmental device is turned on, and / or the distribution of air quality parameters when the environmental device is turned off, and / or the distribution of air quality parameters when the environmental device is turned on and reaches a predetermined condition) and the time of turning on;

[0161] 4) Changes in indoor air quality parameter distribution in the previous week (i.e., seven days ago) (e.g., the distribution of air quality parameters before the environmental device is turned on, and / or the distribution of air quality parameters when the environmental device is turned off, and / or the distribution of air quality parameters when the environmental device is turned on and reaches a predetermined condition) and the turn-on time;

[0162] 5) Changes in the indoor air quality parameter distribution in the previous month (i.e., the same day one month ago) (e.g., the distribution of the air quality parameters before the environmental equipment is turned on, and / or the distribution of the air quality parameters when the environmental equipment is turned off, and / or the distribution of the air quality parameters when the environmental equipment is turned on and reaches a predetermined condition) and the turn-on time.

[0163] The opening time refers to the length of time from when the environmental device is turned on to when it is turned off, or the length of time from when the environmental device is turned on to when the air quality parameter distribution reaches a predetermined condition.

[0164] The distribution of the gas quality parameters in the predetermined space meets the predetermined conditions, including:

[0165] The difference between the change rates of the gas quality parameters at multiple predetermined positions within the predetermined space is less than or equal to a first threshold; and / or, the change rates of the gas quality parameters at each of the multiple predetermined positions within the predetermined space are less than or equal to a second threshold.

[0166] Step 2: Obtain information related to gas quality outside the predetermined space (e.g., outdoors) within at least one predetermined time period (e.g., the same predetermined time period as step 1), such as:

[0167] 1) Maximum value data, and / or minimum value data, and / or average value data of outdoor air quality parameters for the day;

[0168] 2) Maximum value data, and / or minimum value data, and / or average value data of outdoor air quality parameters on the previous day;

[0169] 3) Maximum value data, and / or minimum value data, and / or average value data of outdoor air quality parameters in the previous three days;

[0170] 4) Maximum value data, and / or minimum value data, and / or average value data of outdoor air quality parameters in the previous week (i.e., seven days ago);

[0171] 5) Data on the maximum value, and / or minimum value, and / or average value of outdoor air quality parameters in the previous month (i.e., the same day one month ago).

[0172] Step 3, obtaining the airflow circulation state information of the gas in the predetermined space after the air quality parameters are stable within the day; for example, the gas circulation state acquisition unit 2 of the device 100 obtains the direction of the airflow at a predetermined position (for example, the predetermined position environmental equipment has a predetermined distance) through simulation based on the layout information in the predetermined space, and obtains the speed of the airflow at the predetermined position based on the wind speed sensor, thereby obtaining the airflow circulation state information at each predetermined position in the predetermined space.

[0173] Step 4: Input the information obtained in steps 1, 2 and 3 into the neural network model used by the prediction unit 3a to obtain the service life information of the component, which includes: the service life coefficient of the component (for example, expressed as a decimal or a fraction) and / or the time until the next replacement of the component.

[0174] In Example 3, the neural network model used by the prediction unit 3a can be obtained through training, and the training can be performed based on the first training data, the second training data, the third training data and the fourth training data.

[0175] The first training data includes: information related to gas quality in the predetermined space within at least one predetermined time period, for example:

[0176] 1) Changes in the distribution of indoor air quality parameters on this day (i.e., the date of the first training data) (e.g., the distribution of air quality parameters before the environmental device is turned on, and / or the distribution of air quality parameters when the environmental device is turned off, and / or the distribution of air quality parameters when the environmental device is turned on and reaches a predetermined condition) and the turn-on time;

[0177] 2) changes in indoor air quality parameter distribution on the previous day (e.g., the distribution of air quality parameters before the environmental device is turned on, and / or the distribution of air quality parameters when the environmental device is turned off, and / or the distribution of air quality parameters when the environmental device is turned on and reaches a predetermined condition) and the turn-on time;

[0178] 3) Changes in the distribution of indoor air quality parameters over the previous three days (e.g., the distribution of air quality parameters before the environmental device is turned on, and / or the distribution of air quality parameters when the environmental device is turned off, and / or the distribution of air quality parameters when the environmental device is turned on and reaches a predetermined condition) and the time of turning on;

[0179] 4) Changes in indoor air quality parameter distribution in the previous week (i.e., seven days ago) (e.g., the distribution of air quality parameters before the environmental device is turned on, and / or the distribution of air quality parameters when the environmental device is turned off, and / or the distribution of air quality parameters when the environmental device is turned on and reaches a predetermined condition) and the turn-on time;

[0180] 5) Changes in the indoor air quality parameter distribution in the previous month (i.e., the same day one month ago) (e.g., the distribution of the air quality parameters before the environmental equipment is turned on, and / or the distribution of the air quality parameters when the environmental equipment is turned off, and / or the distribution of the air quality parameters when the environmental equipment is turned on and reaches a predetermined condition) and the turn-on time.

[0181] The instructions on the start time and predetermined conditions are the same as above.

[0182] The second training data includes: airflow circulation state information of the gas in the predetermined space after the air quality parameters are stabilized on the current day (ie, the date of the second training data is the same as the date of the first training data).

[0183] The third training data includes: service life information of components in the environmental equipment. The third training data is the actual service life information of the components.

[0184] The fourth training data includes: airflow circulation state information of the air outside the predetermined space on the current day (ie, the date of the second training data, which is the same as the date of the first training data).

[0185] During the training process, the neural network training unit 4a can input the first training data, the second training data and the third training data into the neural network model to be trained, obtain the output data of the neural network model, and adjust the parameters of the neural network model according to the result of comparing the output data with the third training data.

[0186] In an embodiment of the first aspect, the number of environmental devices may be one or more than two. Wherein, when the number of the environmental devices is more than two, each environmental device is at least partially disposed in the predetermined space, and the service life information of its components may be predicted for each environmental device. For example, a neural network model may be trained for each environmental device; or, a neural network model may be trained, and the neural network model outputs the service life information of each of the more than two environmental devices.

[0187] Embodiments of the second aspect

[0188] An embodiment of the second aspect provides a system for predicting the useful life of components in environmental equipment.

[0189] Figure 7 is a schematic diagram of a system for predicting the service life of components in environmental equipment according to an embodiment of the second aspect, such as Figure 7 As shown, the system 700 includes:

[0190] An apparatus 100 (or 100 a ) for predicting the service life of a component in an environmental device, and a display unit 200 .

[0191] The device 100 (or 100a) for predicting the service life of components in environmental equipment generates service life information of components in environmental equipment, and the display unit 200 displays the service life information of components in environmental equipment.

[0192] For the description of the device 100 (or 100a), reference may be made to the embodiment of the first aspect, and the description will not be repeated here.

[0193] In the present application, when the device 100 (or 100a) for predicting the service life of a component in an environmental device includes an energy consumption calculation unit 5, the display unit 200 also displays: the cumulative energy consumption information of the environmental device since the component was installed and / or the current energy consumption information of the environmental device.

[0194] In the present application, the display unit 200 also displays: information related to the gas quality in the predetermined space in the current time period, that is, at least a part of the information acquired by the air quality acquisition unit 1 .

[0195] like Figure 7 As shown, the system 700 further includes: an early warning module 701, and / or a recommendation module 702, and / or an information push module 703. Among them:

[0196] The warning module 701 is used to remind the component of the time to be replaced and / or the component has reached the end of its service life and / or the air quality exceeds the standard and other warning information;

[0197] The recommendation module 702 is used to recommend solutions for improving air quality, such as opening windows for ventilation and / or updating the layout of the space or replacing furniture, etc. For example, if the air in the predetermined space does not meet the standard for a long time and / or the environmental equipment is overloaded, then recommend new environmental equipment;

[0198] The information push module 703 sends information about the health effects of air quality and / or exposure to airborne particles.

[0199] Embodiments of the third aspect

[0200] The embodiment of the third aspect provides a method for predicting the service life of components in environmental equipment, corresponding to the device 100 or 100a in the embodiment of the first aspect.

[0201] Figure 8 is a schematic diagram of a method for predicting the service life of a component in an environmental device according to an embodiment of the third aspect, such as Figure 8 As shown, the method includes:

[0202] 801. Acquire information related to gas quality in the predetermined space within at least one predetermined time period;

[0203] 802. Acquire airflow circulation state information of the gas in the predetermined space; and

[0204] 803. Predict service life information of components in the environmental equipment based on the information related to gas quality in the predetermined space and the airflow circulation state information.

[0205] like Figure 8 As shown, the method also includes:

[0206] 804. Train a neural network model for predicting service life information of components in the environmental equipment.

[0207] Among them, the description of 803 and 804 can refer to the description of the prediction unit 3 and the neural network training unit 4 in the embodiment of the first aspect.

[0208] Fig. 9 is another schematic diagram of a method for predicting the service life of a component in an environmental device according to an embodiment of the third aspect. Fig. 9 As shown, the method includes:

[0209] 901. Acquire information related to gas quality in the predetermined space within at least one predetermined time period;

[0210] 902. Acquire airflow circulation state information of the gas in the predetermined space;

[0211] 903. Acquire information related to gas quality outside the predetermined space within the at least one predetermined time period; and

[0212] 904. Predict service life information of components in the environmental equipment based on the information related to gas quality in the predetermined space, the information related to gas quality outside the predetermined space, and the airflow circulation state information.

[0213] like Fig. 9 As shown, the method also includes:

[0214] 905. Train a neural network model for predicting service life information of components in the environmental equipment.

[0215] Among them, the description of 904 and 905 can refer to the description of the prediction unit 3a and the neural network training unit 4a in the embodiment of the first aspect.

[0216] In an embodiment of the second aspect, the number of environmental devices may be one or more than two. Wherein, when the number of the environmental devices is more than two, each environmental device is at least partially disposed in the predetermined space, and the service life information of its components may be predicted for each environmental device. For example, a neural network model may be trained for each environmental device; or, a neural network model may be trained, and the neural network model outputs the service life information of each of the more than two environmental devices.

[0217] The embodiment of the present application also provides a computer program, wherein when the program is executed in an electronic device, the program enables the electronic device to perform the function of the prediction unit 3 or 3a.

[0218] The embodiment of the present application further provides a storage medium storing a computer program, wherein the computer program enables the electronic device to execute the function of the prediction unit 3 or 3a.

[0219] The above devices and methods of the present application can be implemented by hardware, or by hardware combined with software. The present application relates to such a computer-readable program, which, when executed by a logic component, enables the logic component to implement the above-mentioned devices or components, or enables the logic component to implement the various methods or steps described above. The present application also relates to a storage medium for storing the above program, such as a hard disk, a magnetic disk, an optical disk, a DVD, a flash memory, etc.

[0220] The method / device described in conjunction with the embodiments of the present application may be directly embodied as hardware, a software module executed by a processor, or a combination of the two. For example, one or more of the functional block diagrams shown in the figure and / or one or more combinations of the functional block diagrams may correspond to various software modules of the computer program flow or to various hardware modules. These software modules may correspond to the various steps shown in the figure, respectively. These hardware modules may be implemented by solidifying these software modules, for example, using a field programmable gate array (FPGA).

[0221] The software module may be located in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. A storage medium may be coupled to a processor so that the processor can read information from the storage medium and write information to the storage medium; or the storage medium may be an integral part of the processor. The processor and the storage medium may be located in an ASIC. The software module may be stored in a memory of a mobile terminal or in a memory card that can be inserted into the mobile terminal. For example, if a device (such as a mobile terminal) uses a large-capacity MEGA-SIM card or a large-capacity flash memory device, the software module may be stored in the MEGA-SIM card or the large-capacity flash memory device.

[0222] For one or more of the functional blocks described in the drawings and / or one or more combinations of functional blocks, it can be implemented as a general-purpose processor, digital signal processor (DSP), application-specific integrated circuit (ASIC), field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic device, discrete hardware component or any appropriate combination thereof for performing the functions described in the present application. For one or more of the functional blocks described in the drawings and / or one or more combinations of functional blocks, it can also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in communication with a DSP, or any other such configuration.

[0223] The present application is described above in conjunction with specific implementation methods, but it should be clear to those skilled in the art that these descriptions are exemplary and are not intended to limit the scope of protection of the present application. Those skilled in the art can make various modifications and variations to the present application based on the spirit and principles of the present application, and these modifications and variations are also within the scope of the present application.

Claims

1. A device for predicting the service life of a component in an environmental device, wherein the environmental device is at least partially arranged in a predetermined space, characterized in that: The device comprises: an air quality acquisition unit, which acquires information related to gas quality in the predetermined space within at least one predetermined time period; a gas circulation state acquisition unit, which acquires the gas flow circulation state information of the gas in the predetermined space; and A prediction unit predicts service life information of components in the environmental equipment based on the information related to the gas quality in the predetermined space and the gas flow circulation state information.

2. The device according to claim 1, wherein: The service life information of the components includes: The service life coefficient of the component, and / or the time until the next replacement of the component.

3. The device according to claim 1, wherein: Information related to gas quality includes: Distribution change information of gas quality parameters in the predetermined space before and after the environmental device is turned on; and / or The time from when the environmental device is turned on to when the predetermined condition is met.

4. The device as claimed in claim 3, wherein: The distribution of the gas quality parameter in the predetermined space reaches a predetermined condition, including: The difference in the rate of change of the gas quality parameter at a plurality of predetermined positions within the predetermined space is less than or equal to a first threshold; and / or The change rate of the respective gas quality parameter at at least one predetermined position within the predetermined space is less than or equal to a second threshold.

5. The device according to claim 3, wherein: The gas quality parameter includes at least one of the following parameters: Particle concentration, dust concentration, mold concentration, volatile organic compound concentration, temperature, humidity, carbon dioxide concentration, oxygen concentration, odor concentration.

6. The device according to claim 1, wherein: The at least one predetermined time period comprises: the current day; and / or The first number of days before the current time; and / or The second number of days before the current time; and / or The third number of days before the current time; and / or The fourth number of days before the current time.

7. The device of claim 1, wherein: The airflow circulation state information includes: the speed and / or direction of the airflow at a predetermined position in the predetermined space.

8. The device according to claim 7, wherein: The gas circulation state acquisition unit acquires the direction of the airflow at the predetermined position through simulation based on layout information in the predetermined space, and acquires the speed of the airflow at the predetermined position based on a wind speed sensor.

9. The device of claim 1, wherein: The components of the environmental equipment include: Filters for indoor units of air conditioners, heat exchange components for outdoor units of air conditioners, filters for automobile air conditioners, purifier filters, fresh air fan filters, purification components based on negative ion technology, purification components based on streamer energy technology, or purification components based on high-voltage electrostatic sterilization technology.

10. The device of claim 9, wherein: The types of filters include: activated carbon filters, electrostatic filters, ordinary filters or high-performance filters.

11. The device of claim 1, wherein: The device also includes: an outdoor air quality acquisition unit, which acquires information related to the gas quality outside the predetermined space within the at least one predetermined time period; The prediction unit predicts service life information of components in the environmental equipment based on the information related to the gas quality in the predetermined space, the information related to the gas quality outside the predetermined space, and the airflow circulation state information.

12. The device of claim 11, wherein: The information related to the gas quality outside the predetermined space includes: The maximum value, minimum value, and / or average value of the gas quality parameter outside the predetermined space in each of the predetermined time periods.

13. The device of claim 1, wherein: The device also includes: A neural network training unit, which is used to train a neural network model, The prediction unit uses the trained neural network model to predict service life information of components in the environmental equipment.

14. The device of claim 13, wherein: The neural network training unit trains the neural network model based on the first training data, the second training data and the third training data, The first training data includes information related to gas quality in the predetermined space within at least one first predetermined time period, The second training data includes airflow circulation state information of the gas in the predetermined space, The third training data includes service life information of components in the environmental equipment.

15. The device of claim 14, wherein: The neural network training unit uses a root mean square as a loss function of the neural network model.

16. The device of claim 14, wherein: The neural network training unit inputs the first training data and the second training data into the neural network model to obtain output data of the neural network model, and adjusts the parameters of the neural network model according to the result of comparing the output data with the third training data.

17. The device of claim 14, wherein: The neural network training unit further trains the neural network model based on fourth training data, The fourth training data includes at least one piece of information related to gas quality outside the predetermined space within the first predetermined time period.

18. The device of claim 17, wherein: The neural network training unit inputs the first training data, the second training data and the fourth training data into the neural network model to obtain output data of the neural network model, and adjusts the parameters of the neural network model according to the result of comparing the output data with the third training data.

19. The device of claim 1, wherein: The device also includes: An energy consumption calculation unit calculates the accumulated energy consumption information of the environmental equipment since the components are installed and / or the current energy consumption information of the environmental equipment according to the service life information of the components in the environmental equipment.

20. A system for predicting the service life of a component in an environmental device, comprising a device for predicting the service life of a component in an environmental device according to any one of claims 1 to 19 and a display unit, in, The display unit displays service life information of components in the environmental equipment.

21. The system of claim 20, wherein: When the device for predicting the service life of a component in an environmental device includes an energy consumption calculation unit, the display unit further displays: the accumulated energy consumption information of the environmental device since the component was installed and / or the current energy consumption information of the environmental device.

22. The system of claim 20, wherein: The display unit also displays: information related to gas quality in a predetermined space during a current time period.

23. The system of claim 20, wherein: The system further comprises: An early warning module, which is used to remind the component of the time to be replaced and / or the component has reached the end of its service life and / or the air quality exceeds the standard; and / or A recommendation module for recommending how to obtain solutions to improve air quality; and / or An information push module that sends information about the health effects of air quality and / or exposure to airborne particles.

24. A method for predicting the service life of a component in an environmental device, the environmental device being at least partially arranged in a predetermined space, characterized in that: The method comprises: Acquiring information related to gas quality in the predetermined space within at least one predetermined time period; Acquiring airflow circulation state information of the gas in the predetermined space; and Based on the information related to the gas quality in the predetermined space and the airflow circulation state information, the service life information of the components in the environmental equipment is predicted.

25. The method of claim 24, wherein: The method further comprises: acquiring information related to gas quality outside the predetermined space within the at least one predetermined time period, Wherein, based on the information related to the gas quality in the predetermined space, the information related to the gas quality outside the predetermined space and the airflow circulation state information, the service life information of the components in the environmental equipment is predicted.

26. The method of claim 24 or 25, wherein: The method further comprises: A neural network model is trained to predict the service life information of components in the environmental equipment.

27. The method of claim 24 or 25, wherein: The number of the environmental equipment is more than two. Based on the information related to the gas quality in the predetermined space and the information on the airflow circulation state, the service life information of the components in each of the environmental equipment is predicted respectively; or, based on the information related to the gas quality in the predetermined space, the information related to the gas quality outside the predetermined space and the information on the airflow circulation state, the service life information of the components in each of the environmental equipment is predicted respectively.

Images