Service life prediction system and air conditioning system

Abstract

The invention discloses a service life prediction system and an air conditioning system, and the system comprises a data collection module which is used for collecting the operation data of a to-be-predicted device; the data analysis module is used for calculating the life loss of the to-be-predicted device according to the operation data; and the life prediction module is used for estimating the residual life of the to-be-predicted device according to the life loss. Compared with the prior art, the service life of the to-be-predicted device can be accurately predicted according to the environment parameters and the operation parameters of the to-be-predicted device, so that the to-be-predicted device is maintained and replaced in advance, the service life of the whole system is effectively prolonged, and fault risks and resource waste are reduced.

Description

Technical Field

[0001] The present invention relates to the field of refrigeration, and in particular to a life prediction system and an air-conditioning system. Background Art

[0002] Over the long term, air conditioning system components can age due to various factors, leading to performance degradation or even failure. This is especially true for vulnerable parts like seals and compressor lights, as their service life directly impacts the stability and reliability of the entire air conditioning system.

[0003] Traditional maintenance methods typically rely on regular replacement or repair, but this approach is often imprecise and can lead to wasted resources or increased risk of failure.

[0004] Therefore, how to design a life prediction system and air-conditioning system that can predict the remaining life of each component in the air-conditioning system so as to carry out maintenance and replacement in advance and reduce the risk of failure and waste of resources is a technical problem that needs to be solved urgently in the industry. Summary of the Invention

[0005] In view of the problem in the prior art that traditional maintenance methods rely on regular replacement or repair, which may lead to waste of resources or increased risk of failure, the present invention proposes a life prediction system and an air conditioning system.

[0006] The technical solution of the present invention is to propose a life prediction system, comprising:

[0007] A data acquisition module, the data acquisition module is used to collect operating data of the device to be predicted;

[0008] a data analysis module, configured to calculate the life loss of the device to be predicted based on the operating data;

[0009] A life prediction module is used to estimate the remaining life of the device to be predicted based on the life loss.

[0010] Furthermore, the data acquisition module includes a first acquisition device for acquiring environmental parameters of the device to be predicted, and a second acquisition device for acquiring operating parameters of the device to be predicted;

[0011] The sampling parameters of the second acquisition device are set according to the environmental parameters.

[0012] Furthermore, the data acquisition module performs the following actions when acquiring the operating data:

[0013] The weights of the operating parameters are set according to the environmental parameters.

[0014] Furthermore, the data acquisition module also performs the following actions when acquiring the operating data:

[0015] Determine whether the currently collected operating data exceeds a threshold range;

[0016] If so, the currently collected operating data is corrected and repaired.

[0017] Furthermore, the calculation model used by the data analysis module to calculate the life loss of the device to be predicted is:

[0018] y=β0+β1x1+β2x2+……+βpxp+ε

[0019] Where y is the life loss, x1, x2, ..., xp are operating data, β0, β1, ..., βp are proportional coefficients, and ε is the error value.

[0020] Furthermore, the calculation model for the life prediction module to estimate the remaining life of the device to be predicted is:

[0021] F=Ny;

[0022] Where F is the remaining life, N is the ideal service life of the device to be predicted, and y is the life loss.

[0023] Furthermore, the sampling parameters include at least sampling time, sampling frequency, and anti-interference capability.

[0024] Furthermore, the life prediction system also includes an adaptive learning module, which is used to train and optimize the calculation model for calculating life loss and the calculation model for calculating remaining life according to the batch gradient descent method.

[0025] Furthermore, the training model of the batch gradient descent method is:

[0026]

[0027] in, 、 For a single sample selected, is the gradient of the loss function for a single sample, m is the number of samples used for training, is the hypothesis function in the batch gradient descent method, is the weight vector.

[0028] The present invention also provides an air conditioning system, which includes the above-mentioned life prediction system.

[0029] Compared with the prior art, the present invention has at least the following beneficial effects:

[0030] The life prediction system proposed in the present invention comprises a data acquisition module, a data analysis module, and a life prediction module. These modules can collect environmental and operating parameters of the device to be predicted, calculate the life loss of the device to be predicted, and ultimately estimate the remaining life of the device to be predicted. When applied to an air conditioning system, the present invention can be used to calculate the life loss of each component in the air conditioning system and, based on this, predict the remaining life of each component, enabling early maintenance and replacement, effectively extending the service life of the air conditioning system.

[0031] In addition, the life prediction system proposed in the present invention also has an adaptive learning module, which can optimize the calculation models in the data analysis module and the life prediction module based on a large amount of operating data, thereby forming a calculation model that can accurately predict the remaining life of the device to be predicted, thereby improving the accuracy of the present invention in predicting the remaining life of the device to be predicted. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or descriptions of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0033] Figure 1 Schematic diagram of the overall module structure of the present invention;

[0034] Figure 2 It is a flowchart of the overall action of the present invention;

[0035] Figure 3 This is a module block diagram of the data acquisition module in the present invention. DETAILED DESCRIPTION

[0036] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0037] Thus, a feature indicated in this specification is intended to illustrate one of the features of one embodiment of the present invention, rather than to imply that every embodiment of the present invention must have the described feature. In addition, it should be noted that this specification describes many features. Although certain features can be combined together to illustrate possible system designs, these features can also be used in other, not explicitly described, combinations. Thus, unless otherwise noted, the described combinations are not intended to be limiting.

[0038] The principle and structure of the present invention are described in detail below with reference to the accompanying drawings and embodiments.

[0039] Over the long term, air conditioning system components will gradually age due to various factors, leading to performance degradation or even failure. This is especially true for vulnerable parts like seals and compressors, as their service life directly impacts the stability and reliability of the entire air conditioning system.

[0040] Current solutions to these issues rely on regular replacement or maintenance, but this approach is often imprecise and can lead to wasted resources or increased risk of failure.

[0041] Based on the problems existing in the existing technical solutions, the idea of ​​the present invention is to propose a life prediction system, which aims to predict the remaining life of the predicted device. The life prediction system of the present invention can be applied to the air-conditioning system to predict the remaining life of each component in the air-conditioning system, so as to facilitate users to perform maintenance and replacement of components in advance, thereby extending the service life of the entire air-conditioning system and reducing failure risks and resource risks.

[0042] See Figure 1 The life prediction system proposed in the present invention includes:

[0043] A data acquisition module, the data acquisition module is used to collect operating data of the device to be predicted;

[0044] A data analysis module, the data analysis module is used to calculate the life loss of the device to be predicted based on the operating data;

[0045] The life prediction module is used to estimate the remaining life of the device to be predicted based on the life loss.

[0046] As can be seen from the above configuration, the data acquisition module, data analysis module, and life prediction module in the present invention are in a hierarchical relationship. The data acquisition module can collect operating data of the device to be predicted, and then transmit the operating data to the data analysis module. The data analysis module can calculate the life loss of the device to be predicted based on the data. After calculating the life loss, the life prediction module can estimate the remaining life of the device to be predicted based on the data.

[0047] Among them, the life prediction system of the present invention can be applied to the air-conditioning system. At this time, the above-mentioned device to be predicted can be a component in the air-conditioning system, such as a seal ring, compressor, fan motor, etc. in the air-conditioning system. Through the life prediction system provided by the present invention, the remaining life of the above-mentioned seal rings, compressors, fan motors and other components can be accurately predicted. Users can maintain and replace components such as seal rings, compressors, fan motors, etc. according to the remaining life of the above-mentioned components, thereby avoiding the loss of the above-mentioned components, which leads to damage to the entire air-conditioning system, effectively extending the service life of the air-conditioning system, and reducing failure risks and resource risks.

[0048] It should be noted that the air conditioning system is only a preferred embodiment of the present invention, and the present invention is not limited to the above example. For example, the present invention can also be applied to electric vehicles to predict the remaining life of the engine, tires, bearings and other devices in the electric vehicle, so as to carry out maintenance and replacement in advance, thereby avoiding the problem that damage to the above components may cause failure of the entire electric vehicle.

[0049] In addition, since the present invention can predict the remaining life of each component, when a fault occurs in the air-conditioning system or electric vehicle, the specific faulty component can be determined based on the remaining life of each component in the air-conditioning system or electric vehicle, thereby improving the user's accuracy in locating the faulty component.

[0050] That is, the lifespan prediction system proposed by the present invention has the following beneficial effects:

[0051] It can accurately predict the life of the device to be predicted based on its environmental parameters and operating parameters, so that the device to be predicted can be maintained and replaced in advance, effectively extending the service life of the entire system and reducing the risk of failure and waste of resources.

[0052] See Figure 3 , the data acquisition module of the present invention includes a first acquisition device for acquiring environmental parameters of the device to be predicted, and a second acquisition device for acquiring operating parameters of the device to be predicted;

[0053] The sampling data of the second acquisition device is set according to the environmental parameters.

[0054] When predicting the life loss of a device, the factors that affect its life loss are mainly divided into environmental parameters and operating parameters. For example, for the sealing ring in the air conditioning system, due to the principle of thermal expansion and contraction, the sealing ring is affected differently under different temperatures and light intensities. Temperature and light intensity are environmental parameters, which means that the environmental parameters have an impact on the life loss of the sealing ring.

[0055] Similarly, for the compressor in the air conditioning system, the speed of the compressor rotor movement is different at different operating frequencies, resulting in different life loss of the compressor. The operating frequency is an operating parameter, which means that the operating parameter has an impact on the life loss of the compressor.

[0056] To this end, the present invention is provided with a first collection device and a second collection device, which are mainly used to collect the above-mentioned environmental parameters and operating parameters, obtain all operating data that may affect the remaining life of the device to be predicted, and thus accurately calculate the life loss of the device to be predicted for the estimation of the final remaining life.

[0057] The above-mentioned environmental parameters include temperature, humidity, light intensity, electromagnetic interference, and weather conditions. The specific environmental parameters to be considered can be selected according to actual needs, and are mainly selected as environmental parameters that will affect the remaining life of the device to be predicted;

[0058] For example, in the Middle East, the sulfur dioxide content in the air is high, which can corrode the heat exchange fins of the heat exchanger in the air conditioning system, thereby affecting the remaining life of the heat exchange fins of the heat exchanger in the air conditioning system. In this case, the above environmental parameters need to include the solubility or content of sulfur dioxide;

[0059] The specific first acquisition device is set according to actual needs. When the collected environmental parameters are temperature and humidity, the first acquisition device can be a temperature sensor and a humidity sensor;

[0060] When the collected environmental parameter is light intensity, the first collecting device may be a photothermal sensor;

[0061] The specific configuration of the first collecting device is not limited. As long as it is a device for collecting environmental parameters, it should be within the protection scope of the present invention.

[0062] The above operating parameters include operating frequency, operating mode, etc., and their specific selection is the same as that of environmental parameters. The main selection is the operating parameters that will affect the remaining life of the device to be predicted;

[0063] For example, for a compressor, its operating frequency will affect the remaining life of the compressor, so the above operating parameters need to include the operating frequency of the compressor;

[0064] The specific second acquisition device also needs to be set according to actual needs. For example, when the voltage of the operating parameter to be collected is a voltage sensor, the second acquisition device may be a voltage sensor.

[0065] For example, when the current of the operating parameter collected is a current sensor, the second collection device may be a current sensor;

[0066] Even for some parameters, such as operating frequency, the air conditioning system generally has a record of the operating frequency when the compressor is running. In this case, there is no need to set up an additional second collection device, and the operating frequency can be directly retrieved from the air conditioning system;

[0067] The specific configuration of the second acquisition device is not limited. As long as it is a device for collecting operating parameters, it should be within the scope of protection of the present invention.

[0068] In addition, the above setting also points out that the sampling parameters of the second acquisition device are set according to the environmental parameters;

[0069] The sampling parameters here generally include sampling time, sampling frequency, anti-interference ability, etc. This is because in some specific environments, such as places with different electromagnetic interference intensities, if sensors with the same anti-interference ability are used to collect operating parameters, when the electromagnetic interference is strong, the sensor's anti-interference ability may be poor, resulting in large errors in the collected data.

[0070] In this case, the environmental parameter is the electromagnetic interference intensity, and the sampling parameter is the anti-interference capability. At this time, the anti-interference capability selected by the sensor needs to be selected according to the environmental parameter, that is, the sampling parameter of the second acquisition device in the above text is set according to the environmental parameter;

[0071] For example, in windy weather, the blades of the air conditioning system's external fan will rotate forward and reverse due to the external wind. When driving the air conditioning system's external fan, the current on the three-phase motor will vary significantly due to different wind speeds or the presence or absence of wind. At this time, it is necessary to increase the sampling frequency of the current sensor on the three-phase motor to ensure the accuracy of the operating parameter sampling;

[0072] In this case, the environmental parameters are the size and intensity of the wind, and the sampling parameter is the sampling frequency. At this time, the sampling frequency selected by the current sensor needs to be selected according to the environmental parameters, that is, the sampling parameters of the second acquisition device mentioned above are set according to the environmental parameters;

[0073] In summary, the present invention, through the configuration of the first and second sampling devices, can obtain operating parameters of the device to be predicted based on the environmental parameters, thereby enabling subsequent calculation of life loss. Furthermore, when sampling the operating parameters, the present invention adjusts the sampling parameters based on the environmental parameters, significantly reducing the impact of environmental parameters on the sampling of the operating parameters and ensuring the accuracy of the sampling of the operating parameters.

[0074] Furthermore, the data acquisition module of the present invention also performs the following actions when acquiring the above-mentioned operating data:

[0075] Set the weights of operating parameters according to environmental parameters;

[0076] This setting is mainly used to improve the accuracy and robustness of operating parameter collection and ensure the rationality of operating parameter collection;

[0077] For example, for electric vehicles, when the environmental parameters are sunny and rainy, the electric vehicle runs in the same gear. The engine life loss in rainy days will be much higher than that in sunny days. When calculating the engine life loss, only the operating gear of the electric vehicle is calculated, and the impact of the environmental parameters under the operating gear of the electric vehicle is not considered;

[0078] The weights of the operating parameters are set according to the environmental parameters in the present invention to avoid errors in the calculation of life loss caused by the different effects of the same operating parameters on life loss when the environmental parameters are different.

[0079] Taking the above-mentioned electric car as an example, here the weight of the current gear of the electric car on a sunny day is 1, and the weight of the current gear of the electric car on a rainy day can be set to 1.4. Based on this, it can be avoided that the same gear has different effects on life loss under different environmental parameters on rainy and sunny days, thereby causing errors in the life loss calculation.

[0080] Furthermore, the data acquisition module of the present invention also performs the following actions when acquiring the above-mentioned operating data:

[0081] Determine whether the currently collected operating data exceeds a threshold range;

[0082] If so, the currently collected operating data is corrected and repaired.

[0083] This part of the setting in the present invention is used to avoid abnormal situations that occur during the operation data collection process, such as sensor failure and other factors, which may affect the collected operation data.

[0084] For air conditioning systems, their operating data generally show changes in continuity and integrity. Therefore, it is possible to determine whether the currently collected operating data is abnormal based on the operating data collected twice before and after.

[0085] In the present invention, the threshold interval can be set based on the 15% deviation of the previously collected data and the 15% deviation of the next collected data, so as to determine whether the currently collected operating data is abnormal. For example, if the previously collected data is 100 and the next collected data is 200, the range of the 15% deviation of the previously collected data is (85, 115) and the range of the 15% deviation of the next collected data is (170, 230). In this case, the threshold intervals set are (85, 115) and (170, 230). Assuming that the currently collected data is 150, it is determined that the data collected this time is not within the threshold interval and needs to be corrected and repaired.

[0086] On the contrary, if the data collected at the current time is 110, which is within the threshold range, the data can be considered normal;

[0087] The threshold intervals are set to 15% deviation of the previous data collection and 15% deviation of the next data collection. This can prevent sudden changes in the air conditioning system operating conditions from causing abrupt changes in the sampled operating parameters and misjudging abnormal operating parameters.

[0088] With this setting, regardless of whether the time when the air-conditioning system operating condition changes is between the previous sampling and the current sampling, or between the current sampling and the next sampling, if the operating parameters are normal, it can be guaranteed that the operating parameters fall within the threshold range, thus completely avoiding the misjudgment caused by the change in the air-conditioning system operating condition;

[0089] In the above judgment, the method for correcting and repairing the currently collected operating data is: using interpolation, smoothing or other data repair methods to correct it, so as to ensure the continuity and integrity of the operating data.

[0090] That is, based on the above configuration, the present invention can identify abnormal operating data during the collection process and correct it, thereby ensuring the continuity and integrity of all data.

[0091] See Figure 3 The present invention is based on the data acquisition module and the collection steps performed are:

[0092] 1. Parameter classification: divide the collected operating data into environmental parameters and operating parameters, and sample them separately;

[0093] 2. Dynamic environmental perception: monitoring environmental data and dynamically adjusting sensor output or calibration parameters based on environmental changes to eliminate errors. For example, real-time monitoring of light intensity can dynamically adjust the gain of the sensor used to collect light intensity under different light intensities to adapt to the environmental parameter collection requirements under different light intensities.

[0094] 3. Sampling parameter adjustment: dynamically adjust the sampling frequency or sensor parameters according to changes in environmental parameters. For example, when the environment changes drastically, increase the sampling frequency to capture more detailed information, or use a stronger filter to reduce the impact of noise when electromagnetic interference is strong.

[0095] 4. Set the weight ratio to combine the data collected by multiple sensors and perform data fusion in a weighted average manner to improve the accuracy and robustness of the data;

[0096] 5. Abnormal monitoring and processing: real-time monitoring of operating data to see if it exceeds the threshold range. If so, an alarm will be issued and corresponding remedial measures will be taken. The abnormal operating data monitored will be corrected using difference, smoothing or other data repair methods to ensure the continuity and integrity of the operating data.

[0097] Furthermore, the calculation model for the data analysis module in the present invention to calculate the life loss of the device to be predicted is:

[0098] y=β0+β1x1+β2x2+……+βpxp+ε

[0099] Where y is the life loss, x1, x2, ..., xp are operating data, β0, β1, ..., βp are proportional coefficients, and ε is the error value.

[0100] x1, x2, ..., xp may be different operating data. For example, for a sealing ring in an air conditioning system, the operating data may be sulfur dioxide solubility, temperature, pressure, operating time, etc.;

[0101] The selected operating data x1, x2, ... xp are the operating data that affect the life loss of the device to be predicted, such as the sealing ring in the air conditioning system, and the selected operating data are sulfur dioxide solubility, temperature, pressure, operating hours, etc.

[0102] β0, β1, ... βp are generally weights set based on the impact of different operating data on life loss;

[0103] The present invention can calculate the life loss of the device to be predicted based on the above calculation model, and use it to ultimately estimate the remaining life of the device to be predicted.

[0104] Furthermore, the calculation model for estimating the remaining life of the device to be predicted by the life prediction module in the present invention is:

[0105] F=Ny;

[0106] Where F is the remaining life, N is the ideal service life of the device to be predicted, and y is the life loss.

[0107] Here, the ideal service life of each component in the air conditioning system is generally marked when the component leaves the factory and is a known quantity. y is the life loss. Due to the influence of environmental parameters and operating parameters, it will vary greatly and is an unknown quantity. However, this life loss can be obtained through the previous life loss calculation model and used to calculate the remaining life.

[0108] After the remaining life of the device to be predicted is predicted using the above-mentioned remaining life calculation model, the device to be predicted can be replaced according to the remaining life of the device to be predicted. For example, when the life prediction system proposed in the present invention is applied to the remaining life prediction of various components in the field of air conditioning;

[0109] If the remaining life of a component is short, it needs to be replaced as soon as possible to avoid the remaining life becoming zero, causing damage to the sealing ring and thus affecting the operation of the air conditioning system;

[0110] If the remaining life of a component is long, it may not be replaced even if the component has been used for a long time;

[0111] If the remaining life of a component is zero, it needs to be replaced immediately to prevent damage to the component and affect the air conditioning system;

[0112] It can be seen from the above settings that after adopting the life prediction system proposed in the present invention, the remaining life information of components can be obtained. Components with a shorter remaining life can be replaced in time to avoid their damage affecting the operation of the air-conditioning system. Components with a longer remaining life can be temporarily replaced to save the maintenance cost of the air-conditioning system. Components whose remaining life is zero need to be replaced immediately to avoid damage to the component and the spread of damage to the air-conditioning system.

[0113] See Figure 1 Since many factors affect the life loss when predicting the remaining life, the specific life loss calculation model may also vary, which may lead to deviations in the remaining life estimation of the present invention. To optimize this problem, the life prediction system proposed in the present invention is equipped with an adaptive learning module. The adaptive learning module is used to train and optimize the calculation model for calculating the life loss and the calculation model for calculating the remaining life according to the batch gradient method;

[0114] Through the setting of the above-mentioned adaptive learning module, the present invention can continuously optimize the calculation model used to calculate life loss and the calculation model used to calculate the remaining life, thereby avoiding changes in the calculation model and deviations in the estimation of component life loss.

[0115] Among them, the training model of the batch gradient descent method in the present invention is:

[0116]

[0117] in, 、 For a single sample selected, is the gradient of the loss function for a single sample, m is the number of samples used for training, is the hypothesis function in the batch gradient descent method, is the weight vector.

[0118] Based on the adaptive learning module, the midpoint setting process of the present invention is:

[0119] 1. Build a data model using the existing database, which stores operating parameters and environmental parameters;

[0120] 2. Train the computational model using batch gradient descent. In each iteration, the entire training set is used to calculate the gradient, and then the parameters of the computational model are updated based on this gradient.

[0121] 3. Parameters are then called from the database, and feature weights are dynamically adjusted using the mathematical concept of random forests (building multiple decision trees and aggregating their predictions to make a final prediction. A key feature of random forests is that they can provide an assessment of feature importance). When training multiple decision trees, each decision tree uses a randomly selected subset of features during construction, and the importance of each feature is normalized so that its sum is 1.

[0122] 4. Update the parameters of the computational model based on the adjustment results of the adaptive learning module, and repeat the training and evaluation process. For example, environmental parameters such as temperature, humidity, and air corrosion, as well as operating parameters such as compressor current and fan speed, are updated using the existing batch gradient descent method. Here, each parameter can be understood as being determined by a regression function. The environmental parameters and operating parameters are then treated as a decision tree respectively, and the importance of each characteristic is standardized to ultimately obtain a computational model with the highest credibility. Here, it can be understood that the final computational model is determined by all environmental parameters and operating parameters. The proportions of these parameters vary according to their importance, and the final sum is 1.

[0123] In order to improve the prediction accuracy, the present invention can also introduce a robot learning algorithm to predict the life of components by training a model. For example, algorithms such as support vector machine (SVM) and random forest can be used to train a model that can accurately predict the life of components based on a large amount of operating data.

[0124] Furthermore, the life prediction system provided by the present invention also needs to support remote access, allowing maintenance personnel to view real-time life estimates and operating data via the Internet, facilitating remote monitoring and maintenance and reducing maintenance costs.

[0125] The life prediction system proposed in the present invention also includes an alarm module. When it is predicted that the life of the device to be predicted is about to expire, an alarm is automatically sent to maintenance personnel to provide early warning of potential failures and reduce unexpected downtime.

[0126] See Figure 2 , the overall workflow of the present invention is:

[0127] Collect environmental parameters and operating parameters and adjust them dynamically; this is achieved through the data acquisition module of the present invention, where dynamic adjustment refers to the adjustment of the above-mentioned sampling parameters according to the environmental parameters;

[0128] Parameter adjustment and mutual fusion and correction of data; this is achieved through the data acquisition module of the present invention. The parameter adjustment and mutual fusion and correction of data here are the actions of correcting and repairing the abnormal operation data of the squadron mentioned above, and setting corresponding weights for the operation parameters;

[0129] Calculate the life loss of components; this is achieved through the data analysis module of the present invention, executing the calculation model of life loss;

[0130] The ideal service life of the device to be predicted is subtracted from the life loss to obtain the remaining life of the device to be predicted; this is achieved by the life prediction module of the present invention and is executed based on the remaining life calculation model described above;

[0131] Training the computational model by batch gradient descent; which is implemented by the adaptive learning module of the present invention to update the computational model;

[0132] The importance of features is assessed using the idea of ​​random forests; this is achieved through the adaptive learning module of the present invention, which is used to set the relevant weights of the running data;

[0133] The adjustment results are used to update the model parameters, and the training is repeated until the model parameters do not change; this is achieved through the adaptive learning module in the present invention, which is the action flow for updating the team calculation model.

[0134] The present invention also provides an air conditioning system, which has the above-mentioned life prediction system.

[0135] Compared with the prior art, the present invention has at least the following beneficial effects:

[0136] The life prediction system proposed in the present invention comprises a data acquisition module, a data analysis module, and a life prediction module. These modules can collect environmental and operating parameters of the device to be predicted, calculate the life loss of the device to be predicted, and ultimately estimate the remaining life of the device to be predicted. When applied to an air conditioning system, the present invention can be used to calculate the life loss of each component in the air conditioning system and, based on this, predict the remaining life of each component, enabling early maintenance and replacement, effectively extending the service life of the air conditioning system.

[0137] In addition, the life prediction system proposed in the present invention also has an adaptive learning module, which can optimize the calculation models in the data analysis module and the life prediction module based on a large amount of operating data, thereby forming a calculation model that can accurately predict the remaining life of the device to be predicted, thereby improving the accuracy of the present invention in predicting the remaining life of the device to be predicted.

[0138] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A life prediction system, characterized in that: include: A data acquisition module, the data acquisition module is used to collect operating data of the device to be predicted; a data analysis module, configured to calculate the life loss of the device to be predicted based on the operating data; A life prediction module, configured to estimate the remaining life of the device to be predicted based on the life loss; The data acquisition module includes a first acquisition device for acquiring environmental parameters of the device to be predicted, and a second acquisition device for acquiring operating parameters of the device to be predicted; The sampling parameters of the second acquisition device are set according to the environmental parameters; When acquiring the operating data, the data acquisition module performs the following actions: Setting the weight of the operating parameter according to the environmental parameter; When acquiring the operating data, the data acquisition module further performs the following actions: Determine whether the currently collected operating data exceeds a threshold range; If so, the currently collected operating data is corrected and repaired.

2. The life prediction system according to claim 1, characterized in that The calculation model used by the data analysis module to calculate the life loss of the device to be predicted is: y=β0+β1x1+β2x2+……+βpxp+ε Where y is the life loss, x1, x2, ..., xp are operating data, β0, β1, ..., βp are proportional coefficients, and ε is the error value.

3. The life prediction system according to claim 1, characterized in that The calculation model used by the life prediction module to estimate the remaining life of the device to be predicted is: F=Ny; Where F is the remaining life, N is the ideal service life of the device to be predicted, and y is the life loss.

4. The life prediction system according to claim 1, characterized in that The sampling parameters include at least sampling time, sampling frequency, and anti-interference capability.

5. The life prediction system according to claim 1, characterized in that The life prediction system also includes an adaptive learning module, which is used to train and optimize the calculation model for calculating life loss and the calculation model for calculating remaining life according to the batch gradient descent method.

6. The life prediction system according to claim 5, characterized in that: The training model of the batch gradient descent method is: ； in, 、 For a single sample selected, is the gradient of the loss function for a single sample, m is the number of samples used for training, is the hypothesis function in the batch gradient descent method, is the weight vector.

7. An air conditioning system, characterized in that: The air conditioning system includes the life prediction system according to any one of claims 1 to 6.

Images