CN114182510A - Clothes dryer control method and device, clothes dryer and storage medium - Google Patents
Clothes dryer control method and device, clothes dryer and storage medium Download PDFInfo
- Publication number
- CN114182510A CN114182510A CN202111682898.1A CN202111682898A CN114182510A CN 114182510 A CN114182510 A CN 114182510A CN 202111682898 A CN202111682898 A CN 202111682898A CN 114182510 A CN114182510 A CN 114182510A
- Authority
- CN
- China
- Prior art keywords
- clothes
- dryer
- clothes dryer
- model
- parameters
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
- D06F58/00—Domestic laundry dryers
- D06F58/32—Control of operations performed in domestic laundry dryers
- D06F58/34—Control of operations performed in domestic laundry dryers characterised by the purpose or target of the control
- D06F58/36—Control of operational steps, e.g. for optimisation or improvement of operational steps depending on the condition of the laundry
- D06F58/38—Control of operational steps, e.g. for optimisation or improvement of operational steps depending on the condition of the laundry of drying, e.g. to achieve the target humidity
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
- D06F34/00—Details of control systems for washing machines, washer-dryers or laundry dryers
- D06F34/04—Signal transfer or data transmission arrangements
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
- D06F34/00—Details of control systems for washing machines, washer-dryers or laundry dryers
- D06F34/14—Arrangements for detecting or measuring specific parameters
- D06F34/26—Condition of the drying air, e.g. air humidity or temperature
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06F—LAUNDERING, DRYING, IRONING, PRESSING OR FOLDING TEXTILE ARTICLES
- D06F2105/00—Systems or parameters controlled or affected by the control systems of washing machines, washer-dryers or laundry dryers
- D06F2105/62—Stopping or disabling machine operation
Landscapes
- Engineering & Computer Science (AREA)
- Textile Engineering (AREA)
- Computer Networks & Wireless Communication (AREA)
- Control Of Washing Machine And Dryer (AREA)
Abstract
The invention discloses a clothes dryer control method, a clothes dryer control device, a clothes dryer and a storage medium, and relates to the technical field of clothes dryers, wherein the method comprises the following steps: acquiring operation parameters of working components in the clothes dryer; the operation parameters are used as input parameters of a preset prediction model, so that the preset prediction model generates a prediction result based on the input parameters, and the prediction result is used for representing the drying degree of clothes in the clothes dryer; and controlling the operation state of the dryer according to the prediction result. According to the clothes drying method and device, the algorithm model replaces an entity sensor to predict the state of the clothes in the clothes drying process, the drying program of the clothes is determined based on the operation parameters of the working parts of the clothes dryer, the detection precision of the drying process is improved, and the influence of environmental factors can be avoided.
Description
Technical Field
The invention relates to the technical field of clothes dryers, in particular to a clothes dryer control method and device, a clothes dryer and a storage medium.
Background
At present, most of clothes dryers adopt sensors to detect the state of clothes in the clothes dryer, and after the clothes are dried, the clothes dryer is controlled to stop. For example, when the metal strip contacts with clothes, the moisture content of the load is different, and the resistance value is different, so that the drying humidity value of the load can be deduced by utilizing the change rule of the contact resistance value of the load. However, such a mode is easily influenced by environment and working conditions, the detection assembly is easy to break down, the detection value is unstable and influences the accuracy of clothes drying control, and the condition that clothes are not dried or the clothes are easily wrinkled is easy to occur, so that the user experience is influenced.
Disclosure of Invention
The invention mainly aims to provide a clothes dryer control method, a clothes dryer control device, a clothes dryer and a storage medium, and aims to solve the technical problem that in the prior art, the clothes drying control accuracy is not high.
To achieve the above object, the present invention provides a control method of a dryer, comprising:
acquiring operation parameters of working components in the clothes dryer;
the operation parameters are used as input parameters of a preset prediction model, so that the preset prediction model generates a prediction result based on the input parameters, and the prediction result is used for representing the drying degree of clothes in the clothes dryer; and the number of the first and second groups,
and controlling the operation state of the dryer according to the prediction result.
Optionally, the predicting result includes a moisture content of the laundry, and the operation state of the dryer is controlled according to the predicting result, including:
and when the moisture content of the clothes is less than or equal to the set moisture content, controlling the clothes dryer to stop.
Optionally, the predicting result includes relative humidity of air after the drying air passes through the clothes, and the operation state of the clothes dryer is controlled according to the predicting result, including:
and when the relative humidity of the air is less than or equal to the set relative humidity of the air, controlling the clothes dryer to stop.
Optionally, the method includes using the operation parameter as an input parameter of a preset prediction model, so that the preset prediction model generates a prediction result based on the operation parameter, and further includes:
acquiring temperature and humidity parameters of an environment where a clothes dryer is located and temperature parameters of a space where clothes in the clothes dryer are located; and the number of the first and second groups,
and taking the temperature and humidity parameters, the temperature parameters and the operation parameters as input parameters of a preset prediction model, so that the preset prediction model generates a prediction result based on the input parameters.
Optionally, before the operating parameter is used as an input parameter of the preset prediction model and the preset prediction model generates the prediction result based on the input parameter, the method further includes:
acquiring operation data of working components of the clothes dryer under different working conditions;
constructing an initial algorithm model, wherein the initial algorithm model is used for reflecting the mapping relation between the drying degree of clothes in the clothes dryer and operation data; and the number of the first and second groups,
and training the constructed initial algorithm model according to the operation data to obtain a preset prediction model.
Optionally, constructing an initial algorithm model includes:
constructing an initial algorithm model based on a multilayer perceptron model; the multilayer perceptron model is provided with an input layer, a plurality of hidden layers and an output layer, the hidden layers adopt linear rectification functions, the activation functions of the output layers adopt linear functions, the multilayer perceptron model adopts a mean square error function as a loss function, and the multilayer perceptron model adopts a self-adaptive moment estimation algorithm as an optimization algorithm.
Optionally, obtaining operation data of the working components of the clothes dryer under different working conditions includes:
establishing a dynamic simulation model, wherein the dynamic simulation model comprises the simulation of the heat and mass exchange process of clothes in the clothes dryer and the simulation of the surface moisture-separating and heat-exchanging process of a condenser;
calibrating the dynamic simulation model based on the actual operation data of the clothes dryer; and the number of the first and second groups,
and generating the operation data of the working parts under different working conditions based on the calibrated dynamic simulation model.
In addition, to achieve the above object, the present invention also proposes a dryer control apparatus including:
the acquisition module is used for acquiring the operating parameters of working components in the clothes dryer;
the prediction module is used for taking the operation parameters as input parameters of a preset prediction model, so that the preset prediction model generates a prediction result based on the input parameters, and the prediction result is used for representing the drying degree of clothes in the clothes dryer; and the number of the first and second groups,
and the driving module is used for controlling the operation state of the clothes dryer according to the prediction result.
Further, to achieve the above object, the present invention also proposes a clothes dryer including: the clothes dryer control method comprises a memory, a processor and a clothes dryer control program which is stored on the memory and can run on the processor, wherein the clothes dryer control program realizes the clothes dryer control method when being executed by the processor.
In addition, in order to achieve the above object, the present invention further provides a storage medium having a dryer control program stored thereon, wherein the dryer control program, when executed by a processor, implements the dryer control method as described above.
According to the method, the operation parameters of the working components in the clothes dryer are obtained, then the operation parameters are used as the input parameters of the preset prediction model, the preset prediction model generates the prediction result based on the input parameters, the prediction result is used for representing the drying degree of clothes in the clothes dryer, and finally the operation state of the clothes dryer is controlled according to the prediction result. According to the clothes drying method and device, the algorithm model replaces an entity sensor to predict the state of the clothes in the clothes drying process, the drying program of the clothes is determined based on the operation parameters of the working parts of the clothes dryer, the detection precision of the drying process is improved, and the influence of environmental factors can be avoided.
Drawings
FIG. 1 is a schematic diagram of a dryer in a hardware environment according to an embodiment of the present invention;
FIG. 2 is a schematic structural view of an embodiment of a dryer according to the present invention;
FIG. 3 is a schematic flow chart of a first embodiment of a dryer control method of the present invention;
FIG. 4 is a statistical chart of the virtual prediction accuracy of the relative humidity of the outlet air of the drum of the clothes dryer according to the embodiment;
FIG. 5 is a statistical diagram of the virtual prediction accuracy of the moisture content of the laundry in the clothes dryer according to the embodiment;
FIG. 6 is a schematic flow chart of a second embodiment of a dryer control method of the present invention;
FIG. 7 is a schematic diagram of a preset predictive model training process according to the present invention;
fig. 8 is a block diagram showing the construction of a first embodiment of a clothes dryer control apparatus according to the present invention.
The reference numbers illustrate:
| reference numerals | Name (R) | Reference numerals | Name (R) |
| 1001 | Processor with a memory having a plurality of |
3 | Circulating |
| 1002 | |
4 | |
| 1003 | |
5 | |
| 1004 | |
100 | |
| 1005 | |
200 | |
| 1 | |
300 | |
| 2 | Heating device |
The implementation, functional features and advantages of the objects of the present invention will be further explained with reference to the accompanying drawings.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Referring to fig. 1, fig. 1 is a schematic diagram of a dryer structure in a hardware operating environment according to an embodiment of the present invention.
As shown in fig. 1, the dryer may include: a processor 1001, such as a Central Processing Unit (CPU), a communication bus 1002, a user interface 1003, a network interface 1004, and a memory 1005. Wherein a communication bus 1002 is used to enable connective communication between these components. The user interface 1003 may include a Display screen (Display), and the optional user interface 1003 may further include a standard wired interface and a wireless interface, and the wired interface for the user interface 1003 may be a USB interface in the present invention. The network interface 1004 may optionally include a standard wired interface, a Wireless interface (e.g., a Wireless-Fidelity (Wi-Fi) interface). The Memory 1005 may be a Random Access Memory (RAM) Memory or a Non-volatile Memory (NVM), such as a disk Memory. The memory 1005 may alternatively be a storage device separate from the processor 1001.
As shown in FIG. 1, a memory 1005, identified as one type of computer storage medium, may include an operating system, a network communication module, a user interface module, and a dryer control program.
In the clothes dryer shown in fig. 1, the network interface 1004 is mainly used for connecting a background server and performing data communication with the background server; the user interface 1003 is mainly used for connecting user equipment; the dryer calls a dryer control program stored in the memory 1005 through the processor 1001 and performs the dryer control method provided by the embodiment of the present invention.
Referring to fig. 2, fig. 2 is a schematic structural view of an embodiment of a dryer according to the present invention. The dryer includes a drum 1, a heater 2, a circulation fan 3, a condenser 4, and a cooling fan 5. Closed endless air is driven by circulating fan 3, heats up after heater 2 heats, then gets into in the cylinder 1 and contact with the clothing and take place heat and mass exchange process, and moisture in the clothing constantly gets into the circulated air current, and the air has absorbed behind the clothing moisture temperature reduction and become high humid state and come out from cylinder 1, later get into condenser 4 and cooling new trend heat transfer, high humid air is at condenser 4 surface cooling and precipitation moisture to realize cooling dehumidification effect. The circulating air is continuously driven by the circulating fan 3 after coming out of the condenser 4, is heated by the heater 2 again and then enters the roller 1 for dehumidification, and the continuous clothes drying working process is realized in such a circulating way. In the open cooling air circulation, fresh air is driven by a cooling fan 5 to pass through a condenser 4 to complete a cooling task, and then the temperature is increased and directly discharged into the atmosphere. The configuration shown in fig. 2 does not constitute a limitation of the dryer, and may include more or fewer components than those shown, or some components may be combined, or a different arrangement of components.
Based on the above hardware structure, an embodiment of the dryer control method of the present invention is provided.
Referring to fig. 3, fig. 3 is a flowchart illustrating a first embodiment of a dryer control method according to the present invention.
In a first embodiment, the dryer control method includes the steps of:
step S10: and acquiring the operating parameters of the working components in the clothes dryer.
It should be understood that the main executing body of the present embodiment may be a controller in the clothes dryer, and the controller has functions of data processing, data communication, program operation, and the like. Or the execution main body of the embodiment may also be an intelligent control cloud platform, and the intelligent control cloud platform may monitor and control the operation state of the clothes dryer, communicate with the clothes dryer through a wireless network and the like, and has functions of data processing, data communication, program operation and the like. Of course, the executing subject of the present embodiment may also be other devices with similar functions, and the present embodiment is not limited to this. The present embodiment is described taking an execution subject as an example of a controller.
It should be noted that the operating parameter may be an operating parameter or a setting parameter of the working component. The dryer incorporates a number of operating components such as fans, drums or heaters. The operation parameters can comprise power parameters, air inlet temperature or air outlet temperature and the like; the setting parameter may include a setting gear and the like, and the setting parameter is a parameter which is input by a user when the dryer is used. The controller may obtain operating parameters of one or more operational components in the dryer.
In a specific implementation, the controller may communicate with a driver corresponding to the working component, and the controller obtains the corresponding operating parameter by reading a driving parameter of the driver. Or the controller is communicated with the man-machine interaction device, and when the user sets the parameters of the component, the controller records the set parameters, so that the corresponding operation parameters are obtained.
Since the present embodiment uses the algorithm model to predict the drying state of the laundry, the input parameters required for using the algorithm model after deployment are generally the same as the data used by the algorithm model in the training phase, and therefore the specific types of the operation parameters and the specific components involved can be determined according to the specific structure of the algorithm model. For example, the data used by the algorithm model in the training phase relate to the load weight, the circulation wind level set by the user operation, the cooling wind level and the heater gear level, and the components related to the operating parameters comprise the drum, the fan and the heater, and the operating parameters are the load weight, the circulation wind level set by the user operation, the cooling wind level and the heater gear level. Of course, to reduce the dependency of the dryer on additional detection devices (sensors, etc.), the operating parameters are typically variables that the dryer can monitor and record at low cost. The specific type of the operating parameters and the specific components involved may be set as desired, and the present embodiment is not limited in this regard.
Step S20: and taking the operation parameters as input parameters of a preset prediction model, and enabling the preset prediction model to generate a prediction result based on the input parameters, wherein the prediction result is used for representing the drying degree of clothes in the clothes dryer.
It should be noted that the prediction result may include a moisture content of the laundry or a relative humidity of air after the dry air passes through the laundry, which may both represent a drying degree of the laundry in the dryer, and the lower the moisture content of the laundry or the relative humidity of air after the dry air passes through the laundry, the drier the laundry.
In practical applications, it is found that when the load is the same, the cooling capacity of the condenser is reduced due to the increase of the ambient temperature, and therefore the relative humidity of the drum outlet air is increased when the clothes are dried. Therefore, it is not enough to judge that only the relative humidity signal is acquired in the automatic clothes drying algorithm, and because the actual working conditions are various, some deviation can be brought by indirectly judging the clothes drying degree through the relative humidity signal. Therefore, the present embodiment gives priority to the laundry moisture content as the prediction result. Of course, the prediction result may be other types of parameters, which is not limited in this embodiment.
It will be appreciated that the more parameters the predictive model is preset to input, the more reliable the output prediction results are generally. Therefore, besides the operation parameters of the working components as input parameters, the temperature and humidity parameters of the environment where the clothes dryer is located and the temperature parameters of the space where the clothes in the clothes dryer are located can be obtained and used as the input parameters.
As mentioned above, the relative humidity signal of the drum outlet air is easily affected by the ambient temperature during drying, so that the ambient temperature can be used as the input parameter of the prediction model to improve the accuracy of the preset prediction model. In addition, since a part of the operation parameters of the operation member is inputted by the operator, erroneous judgment is easily caused even when the parameters inputted by the operator do not match the actual conditions (for example, the user puts the laundry after spin-drying, but the operation parameters set for the dryer are the operation parameters corresponding to the laundry not spin-dried). Therefore, the temperature in the drum can also be used as an input parameter. The temperature near the clothes can reflect the actual state of the clothes during drying to a certain extent, and the influence on the prediction result when the parameter set by the user has deviation can be eliminated to a certain extent by adding the temperature parameter into the preset prediction model. It can be understood that, if the input parameters of the preset prediction model in the actual use stage need to be adjusted, training using the same parameters also needs to be performed in the training stage of the preset prediction model, so as to ensure the accuracy of the preset prediction model.
Step S30: and controlling the operation state of the dryer according to the prediction result.
It should be noted that the operation state mainly includes the start and stop of the dryer and the operation parameters of the internal components. That is, the controller may judge whether the laundry has been dried according to the prediction result, and control the dryer to stop after the laundry is dried. For example, the prediction result may be a moisture content of the laundry, and the dryer is controlled to be stopped when the moisture content of the laundry is less than or equal to a set moisture content. Wherein, the set water content is the water content of the clothes in a drying state. Or the prediction result can be the relative humidity of the air after the drying air flows through the clothes, and when the relative humidity of the air is less than or equal to the set relative humidity of the air, the clothes dryer is controlled to stop. Wherein, the set air relative humidity is the air relative humidity in the clothes drying state.
Referring to fig. 4, fig. 4 is a statistical diagram of the virtual prediction accuracy of the drum outlet air relative humidity of the clothes dryer according to the embodiment. As shown in FIG. 4, the error of the predicted value is basically within the error limit of + -5%, which indicates that the prediction model has a good effect, and the preset prediction model can more accurately predict the relative humidity of the air outlet of the drum of the clothes dryer.
Referring to fig. 5, fig. 5 is a statistical diagram of the virtual prediction accuracy of the clothes moisture content of the clothes dryer according to the embodiment. As shown in FIG. 5, the error of the predicted value of water content is within 10%, which indicates that the prediction model has a good effect. The moisture content is a parameter which can not be measured by a physical measurement sensor, but the moisture content is really a basis for judging whether the drying machine is stopped or not. Therefore, the preset prediction model can accurately predict the drying degree of the clothes in the drum of the clothes dryer.
The controller can also determine the clothes drying progress according to the prediction result and judge whether the residual time meets the set time of the user. For example, the drying time set by the user still remains 5 minutes, but it is determined that 7 minutes are still needed for drying the laundry without adjusting the operation conditions according to the prediction result; at this time, the operation parameters can be adjusted to accelerate the drying speed, such as increasing the heating power of the heater.
In the embodiment, the operation parameters of the working components in the clothes dryer are obtained, then the operation parameters are used as the input parameters of the preset prediction model, so that the preset prediction model generates the prediction result based on the input parameters, the prediction result is used for representing the drying degree of clothes in the clothes dryer, and finally the operation state of the clothes dryer is controlled according to the prediction result. According to the embodiment, the algorithm model replaces an entity sensor to predict the state of the clothes in the drying process, the drying program of the clothes is determined based on the operation parameters of the working parts of the clothes dryer, the detection precision of the drying process is improved, and the influence of environmental factors can be avoided.
Referring to fig. 6, fig. 6 is a flowchart illustrating a dryer control method according to a second embodiment of the present invention. Based on the above first embodiment, a second embodiment of a control method of a dryer of the present invention is proposed.
The embodiment mainly relates to a training process of a preset prediction model, and in order to ensure the prediction accuracy of the preset prediction model after deployment, the method further includes, before step S10:
step S01: and acquiring the operation data of the working parts of the clothes dryer under different working conditions.
It should be noted that the operation data is mainly used for training the preset prediction model. Usually, the acquisition mode of the operation data can be acquired by realizing measurement and physical simulation. Because the operation parameters of the clothes dryer system are highly coupled and always in an unstable state during operation, and meanwhile, the number of the factors influencing the actual working performance of the clothes dryer is large, including environmental working conditions, load states, user setting behaviors and the like, and the number of the factors is tens of thousands, the clothes dryer is driven to operate under different working conditions by means of experimental measurement, and time and labor are consumed for obtaining corresponding operation data. Therefore, the present embodiment preferentially adopts a physical simulation method to acquire the operating data.
During specific implementation, a dynamic simulation model is established firstly, wherein the dynamic simulation model comprises heat and mass exchange process simulation of clothes in the clothes dryer and surface moisture-separating and heat-exchanging process simulation of a condenser; calibrating the dynamic simulation model based on the actual operation data of the clothes dryer; and finally, generating the operation data of the working parts under different working conditions based on the calibrated dynamic simulation model.
The dynamic simulation model can be established by adopting a Modelica language, the Modelica is an open, object-oriented and equation-based computer language, can span different fields, and conveniently realizes the modeling of a complex physical system, and comprises the following steps: mechanical, electronic, electrical, hydraulic, thermal, control, and process oriented subsystem models. The modeling process based on the Modelica language has a mature technology, and the implementation mode is not described herein again.
The real machine operation data is data obtained by means of experimental measurement, and can comprise dynamic characteristics of clothes drying energy consumption, clothes drying time, temperature and humidity. The data volume required by the calibration process is not large, so the cost for acquiring the real machine operation data is low. The calibration process means that the dynamic characteristics of the clothes drying energy consumption, the clothes drying time, the temperature and the humidity of the simulation model are matched with a clothes dryer system, so that the simulation accuracy of the dynamic simulation model is improved.
Different working conditions mainly mean that clothes dried by the clothes dryer have different humidity and different temperature and humidity of the environment where the clothes dryer is located. Corresponding operation data are acquired by setting different working conditions in the dynamic simulation model. As an example, the operation data may include a drying time, a heating power, a drum intake air temperature, a drum outlet air temperature, a heating gear, a circulation air gear, a cooling windshield.
Step S02: and constructing an initial algorithm model, wherein the initial algorithm model is used for reflecting the mapping relation between the drying degree of the clothes in the clothes dryer and the operation data.
The construction of a surrogate model virtual prediction by a data algorithm can be considered as a supervised learning problem, with drum outlet air relative humidity or laundry moisture content as a target y, whose value is determined by some characteristic, i.e. the characteristic required to describe each data state is represented by x, which can be expressed as a function of x: y ═ f (x). Wherein, f (x) is a model obtained by training a data algorithm, data used by the training model comprises the characteristics and the target values of the corresponding state points, and the input target value is the true value of the comparison of the prediction results of the algorithm.
In this embodiment, the initial algorithm model may be constructed based on a multi-layered perceptron model. The multi-layered perceptron model has an input layer, a plurality of hidden layers, and an output layer. For example, a neural network model can be constructed using one input layer, three hidden layers, and one output layer.
In a specific implementation, the hidden layers all use a ReLU (Rectified Linear Unit) function, and the activation function of the output layer uses a Linear function. The loss function of the multilayer perceptron model adopts an MSE (Mean Square error) function, and the optimization algorithm is Adam (Adaptive motion Estimation). Various functions have mature technologies, and the detailed description of the embodiment is omitted.
Step S03: and training the constructed initial algorithm model according to the operation data to obtain a preset prediction model.
Referring to fig. 7, fig. 7 is a schematic diagram of a preset prediction model training process according to the present invention. Step S40: and filtering missing values and repeated values in the simulation data. Wherein, the simulation data is the operation data of the working components. Step S50: and filtering the data at the time 0, wherein the time 0 is the time when the clothes dryer starts to operate. Step S60: and generating a training set and a testing set, wherein 70% of the data can be used as training data to form the training set by randomly extracting the filtered simulation data, and the rest 30% of the data can be used as testing data to form the testing set. Step S70: MLP (Multilayer Perceptron) training. The initial algorithm model calculates the training data to obtain output. Step S80: judging whether the mean square error is minimized, calculating the mean square error between the output and the actual value through a mean square error function, and if the mean square error does not reach the minimum value, entering the step S90: and updating the weight, and updating the weight by using an optimization algorithm to calculate the input again until the mean square error is minimized. If the mean square error reaches the minimum value, the process proceeds to step S100: the model is maintained. A model function is determined based on the current weight values. Step S110: and checking the test set. And inputting the test data into the stored model to obtain output. Step S120: and (5) counting the evaluation indexes. And (4) judging whether the stored model meets the requirements or not by counting the verification results, if so, training the results, and otherwise, returning to the training process.
As an example, the simulation experiment can be carried out by setting the working conditions of ambient temperature, humidity, load weight, initial water-containing state, circulating wind gear, cooling wind gear, heater gear and the like. And assuming that the moisture content of the clothes reaches 0.1%, the clothes are completely dried, and the simulation is finished. The simulation conditions may be as follows:
TABLE 1 simulation clothes drying condition parameters and value ranges thereof
Specifically, the state data at the initial time is filtered, and assuming that the remaining total valid data is 611159 pieces, 70% of the remaining total valid data is randomly extracted as training data, and the remaining 30% is used as prediction data. The input layer selects 7 variables from the recorded state variables as input parameters, namely clothes drying time, heating power, roller air inlet temperature, roller air outlet temperature, heating gear or heating power, circulating gear or rotating speed and cooling gear or rotating speed. And (5) training and predicting the relative humidity of the air outlet of the model roller and the water content of the clothes.
In the embodiment, the operation data of the working parts of the clothes dryer under different working conditions is obtained; and then constructing an initial algorithm model, wherein the initial algorithm model is used for reflecting the mapping relation between the drying degree of clothes in the clothes dryer and the operation data, and then training the constructed initial algorithm model according to the operation data to obtain a preset prediction model. The embodiment trains the algorithm model by using the operation data to obtain the preset prediction model, thereby realizing the virtual perception of the clothes drying process, avoiding the problems faced by adopting an entity sensor and improving the detection precision of the clothes.
Furthermore, an embodiment of the present invention also provides a storage medium having a dryer control program stored thereon, which when executed by a processor implements the steps of the dryer control method as described above. Since the storage medium may adopt the technical solutions of all the embodiments, at least the beneficial effects brought by the technical solutions of the embodiments are achieved, and are not described in detail herein.
Referring to fig. 8, fig. 8 is a block diagram showing a first embodiment of a control device of a clothes dryer according to the present invention. The embodiment of the invention also provides a control device of the clothes dryer.
In the present embodiment, the dryer control apparatus includes:
the acquisition module 100 is used for acquiring the operation parameters of the working components in the clothes dryer.
It should be noted that the operating parameter may be an operating parameter or a setting parameter of the working component. For example, for a component such as a fan, a roller, or a heater, the operation parameters may include a power parameter, an inlet air temperature, an outlet air temperature, or the like; the setting parameters may include setting a gear, etc. which are inputted by a user when the dryer is used.
In a specific implementation, the acquisition module 100 may communicate with a driver corresponding to the working component, and the controller obtains the corresponding operating parameter by reading a driving parameter of the driver. Or the acquisition module 100 is communicated with the human-computer interaction device, and when the user sets parameters for the component, the acquisition module 100 records the set parameters, so as to obtain corresponding operating parameters.
Since the present embodiment uses the algorithm model to predict the drying state of the laundry, the input parameters required for using the algorithm model after deployment are generally the same as the data used by the algorithm model in the training phase, and therefore the specific types of the operation parameters and the specific components involved can be determined according to the specific structure of the algorithm model. For example, the data used by the algorithm model in the training phase relate to the load weight, the circulation wind level set by the user operation, the cooling wind level and the heater gear level, and the components related to the operating parameters comprise the drum, the fan and the heater, and the operating parameters are the load weight, the circulation wind level set by the user operation, the cooling wind level and the heater gear level. Of course, to reduce the dependency of the dryer on additional detection devices (sensors, etc.), the operating parameters are typically variables that the dryer can monitor and record at low cost. The specific type of the operating parameters and the specific components involved may be set as desired, and the present embodiment is not limited in this regard.
The prediction module 200 is configured to use the operation parameter as an input parameter of a preset prediction model, so that the preset prediction model generates a prediction result based on the input parameter, and the prediction result is used for representing a drying degree of the laundry in the clothes dryer.
It should be noted that the prediction result may include a moisture content of the laundry or a relative humidity of air after the dry air passes through the laundry, which may both represent a drying degree of the laundry in the dryer, and the lower the moisture content of the laundry or the relative humidity of air after the dry air passes through the laundry, the drier the laundry.
In practical applications, it is found that when the load is the same, the cooling capacity of the condenser is reduced due to the increase of the ambient temperature, and therefore the relative humidity of the drum outlet air is increased when the clothes are dried. Therefore, it is not enough to judge that only the relative humidity signal is acquired in the automatic clothes drying algorithm, and because the actual working conditions are various, some deviation can be brought by indirectly judging the clothes drying degree through the relative humidity signal. Therefore, the present embodiment gives priority to the laundry moisture content as the prediction result. Of course, the prediction result may be other types of parameters, which is not limited in this embodiment.
It will be appreciated that the more parameters the predictive model is preset to input, the more reliable the output prediction results are generally. Therefore, besides the operation parameters of the working components as input parameters, the temperature and humidity parameters of the environment where the clothes dryer is located and the temperature parameters of the space where the clothes in the clothes dryer are located can be obtained and used as the input parameters.
As mentioned above, the relative humidity signal of the drum outlet air is easily affected by the ambient temperature during drying, and therefore the ambient temperature can be considered to improve the accuracy of the preset prediction model. In addition, since a part of the operation parameters of the operation member is inputted by the operator, erroneous judgment is easily caused even when the parameters inputted by the operator do not match the actual conditions (for example, the user puts the laundry after spin-drying, but the operation parameters set for the dryer are the operation parameters corresponding to the laundry not spin-dried). Therefore, the temperature in the drum can also be used as an input parameter. The temperature near the clothes can reflect the actual state of the clothes during drying to a certain extent, and the influence on the prediction result when the parameter set by the user has deviation can be eliminated to a certain extent by adding the temperature parameter into the preset prediction model. It can be understood that, if the input parameters of the preset prediction model in the actual use stage need to be adjusted, training using the same parameters also needs to be performed in the training stage of the preset prediction model, so as to ensure the accuracy of the preset prediction model.
And a driving module 300 for controlling the operation state of the dryer according to the prediction result.
It should be noted that the operation state mainly includes the start and stop of the dryer and the operation parameters of the internal components. That is, the driving module 300 may determine whether the laundry has been dried according to the prediction result, and control the dryer to stop after the laundry is dried. For example, the prediction result may be the moisture content of the laundry, and the dryer is controlled to stop when the moisture content of the laundry reaches the set moisture content. Wherein, the set water content is the water content of the clothes in a drying state. Or the prediction result can be the relative humidity of the air after the drying air flows through the clothes, and the clothes dryer is controlled to stop when the relative humidity of the air reaches the set relative humidity. Wherein, the set relative humidity is the relative humidity of the air in the clothes drying state.
The driving module 300 may also determine a laundry drying progress according to the prediction result, and determine whether the remaining time satisfies the set time of the user. For example, the drying time set by the user still remains 5 minutes, but it is determined that 7 minutes are still needed for drying the laundry without adjusting the operation conditions according to the prediction result; at this time, the operation parameters can be adjusted to accelerate the drying speed, such as increasing the heating power of the heater.
In the embodiment, the operation parameters of the working components in the clothes dryer are obtained, then the operation parameters are used as the input parameters of the preset prediction model, so that the preset prediction model generates the prediction result based on the input parameters, the prediction result is used for representing the drying degree of clothes in the clothes dryer, and finally the operation state of the clothes dryer is controlled according to the prediction result. According to the embodiment, the algorithm model replaces an entity sensor to predict the state of the clothes in the drying process, the drying program of the clothes is determined based on the operation parameters of the working parts of the clothes dryer, the detection precision of the drying process is improved, and the influence of environmental factors can be avoided.
In one embodiment, the clothes dryer control device further comprises a training module, wherein the training module is used for acquiring the operation data of the working parts of the clothes dryer under different working conditions; constructing an initial algorithm model, wherein the initial algorithm model is used for reflecting the mapping relation between the drying degree of clothes in the clothes dryer and operation data; and training the constructed initial algorithm model according to the operation data to obtain a preset prediction model.
In one embodiment, the training module is further configured to construct an initial algorithm model based on the multi-layer perceptron model; the multilayer perceptron model is provided with an input layer, a plurality of hidden layers and an output layer, the hidden layers adopt linear rectification functions, the activation functions of the output layers adopt linear functions, the multilayer perceptron model adopts a mean square error function as a loss function, and the multilayer perceptron model adopts a self-adaptive moment estimation algorithm as an optimization algorithm.
In one embodiment, the training module is further configured to establish a dynamic simulation model, where the dynamic simulation model includes a heat and mass exchange process simulation of clothes in the clothes dryer and a condenser surface moisture desorption heat exchange process simulation; calibrating the dynamic simulation model based on real machine operation data of the clothes dryer; and generating the operation data of the working parts under different working conditions based on the calibrated dynamic simulation model.
Other embodiments or specific implementation manners of the clothes dryer control device of the present invention may refer to the above-mentioned method embodiments, so that at least all the advantages brought by the technical solutions of the above-mentioned embodiments are provided, and no further description is given here.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The use of the words first, second, third, etc. do not denote any order, but rather the words first, second, third, etc. are to be interpreted as names.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner. Based on such understanding, the technical solutions of the present invention or portions thereof that contribute to the prior art may be embodied in the form of a software product, where the computer software product is stored in a storage medium (e.g., a Read Only Memory (ROM)/Random Access Memory (RAM), a magnetic disk, an optical disk), and includes several instructions for enabling a terminal device (which may be a mobile phone, a computer, a server, or a network device) to execute the method according to the embodiments of the present invention.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A dryer control method characterized by comprising:
acquiring operation parameters of working components in the clothes dryer;
taking the operation parameters as input parameters of a preset prediction model, and enabling the preset prediction model to generate a prediction result based on the input parameters, wherein the prediction result is used for representing the drying degree of clothes in the clothes dryer; and the number of the first and second groups,
and controlling the operation state of the clothes dryer according to the prediction result.
2. The dryer control method of claim 1, wherein the prediction result includes a moisture content of the laundry, and the controlling of the operation state of the dryer according to the prediction result includes:
and when the moisture content of the clothes is less than or equal to the set moisture content, controlling the clothes dryer to stop.
3. The dryer control method of claim 1, wherein the prediction result includes a relative humidity of air after the dry air passes through the laundry, and the controlling the operation state of the dryer according to the prediction result includes:
and when the relative air humidity is less than or equal to the set relative air humidity, controlling the clothes dryer to stop.
4. The clothes dryer control method of claim 1, wherein said using the operating parameter as an input parameter of a preset prediction model, causing the preset prediction model to generate a prediction result based on the operating parameter, further comprises:
acquiring temperature and humidity parameters of the environment where the clothes dryer is located and temperature parameters of the space where clothes in the clothes dryer are located; and the number of the first and second groups,
and taking the temperature and humidity parameters, the temperature parameters and the operation parameters as input parameters of a preset prediction model, so that the preset prediction model generates a prediction result based on the input parameters.
5. The dryer control method of any one of claims 1-4, wherein before the taking the operating parameter as an input parameter of a preset prediction model, the preset prediction model generating a prediction result based on the input parameter, further comprises:
acquiring operation data of working components of the clothes dryer under different working conditions;
constructing an initial algorithm model, wherein the initial algorithm model is used for reflecting the mapping relation between the drying degree of the clothes in the clothes dryer and the operation data; and the number of the first and second groups,
and training the constructed initial algorithm model according to the operating data to obtain a preset prediction model.
6. The clothes dryer control method of claim 5, wherein said constructing an initial algorithm model comprises:
constructing an initial algorithm model based on a multilayer perceptron model; the multilayer perceptron model is provided with an input layer, a plurality of hidden layers and an output layer, the hidden layers adopt linear rectification functions, the activation function of the output layer adopts a linear function, the multilayer perceptron model adopts a mean square error function as a loss function, and the multilayer perceptron model adopts an adaptive moment estimation algorithm as an optimization algorithm.
7. The clothes dryer control method of claim 5, wherein the obtaining of the operation data of the operating components of the clothes dryer under different working conditions comprises:
establishing a dynamic simulation model, wherein the dynamic simulation model comprises heat and mass exchange process simulation of clothes in the clothes dryer and condenser surface moisture-separating heat exchange process simulation;
calibrating the dynamic simulation model based on actual operation data of the clothes dryer; and the number of the first and second groups,
and generating the operation data of the working parts under different working conditions based on the calibrated dynamic simulation model.
8. A dryer control apparatus, characterized by comprising:
the acquisition module is used for acquiring the operating parameters of working components in the clothes dryer;
the prediction module is used for taking the operation parameters as input parameters of a preset prediction model, so that the preset prediction model generates a prediction result based on the input parameters, and the prediction result is used for representing the drying degree of clothes in the clothes dryer; and the number of the first and second groups,
and the driving module is used for controlling the operation state of the clothes dryer according to the prediction result.
9. A clothes dryer characterized by comprising: a memory, a processor, and a dryer control program stored on the memory and executable on the processor, the dryer control program when executed by the processor implementing the dryer control method of any one of claims 1 to 7.
10. A storage medium characterized in that the storage medium has a dryer control program stored thereon, which when executed by a processor implements the dryer control method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111682898.1A CN114182510A (en) | 2021-12-31 | 2021-12-31 | Clothes dryer control method and device, clothes dryer and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111682898.1A CN114182510A (en) | 2021-12-31 | 2021-12-31 | Clothes dryer control method and device, clothes dryer and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114182510A true CN114182510A (en) | 2022-03-15 |
Family
ID=80545560
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111682898.1A Pending CN114182510A (en) | 2021-12-31 | 2021-12-31 | Clothes dryer control method and device, clothes dryer and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114182510A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115294671A (en) * | 2022-08-08 | 2022-11-04 | 杭州哲达科技股份有限公司 | Air compressor outlet pressure prediction method and prediction system |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5172490A (en) * | 1991-02-28 | 1992-12-22 | Kabushiki Kaisha Toshiba | Clothes dryer with neurocontrol device |
| EP0707107A1 (en) * | 1994-10-11 | 1996-04-17 | ELECTROLUX ZANUSSI ELETTRODOMESTICI S.p.A. | Improvement in the arrangement used in a clothes drying apparatus to determine the drying time |
| US5560124A (en) * | 1991-12-10 | 1996-10-01 | Hart; Douglas R. S. | Automatic cycle terminator for dryers |
| US5899005A (en) * | 1997-03-13 | 1999-05-04 | General Electric Company | System and method for predicting the dryness of clothing articles |
| US20020184789A1 (en) * | 2001-05-25 | 2002-12-12 | Maytag Corporation | Self programming clothes dryter system |
| EP1559829A1 (en) * | 2004-01-28 | 2005-08-03 | CANDY S.p.A. | Drying method and device |
| WO2007077094A1 (en) * | 2005-12-30 | 2007-07-12 | Arcelik Anonim Sirketi | A dryer |
| WO2014076093A1 (en) * | 2012-11-16 | 2014-05-22 | Electrolux Home Products Corporation N.V. | Method of operating a heat pump laundry dryer and heat pump laundry dryer or heat pump washing machine having drying function |
| CN104562607A (en) * | 2015-01-21 | 2015-04-29 | 东华大学 | Dynamic feedback measuring and controlling platform used for researching technology of drying textiles in clothes dryer |
| EP2927366A1 (en) * | 2014-03-31 | 2015-10-07 | Electrolux Appliances Aktiebolag | Laundry treatment apparatus and method of operation |
| US20150322618A1 (en) * | 2012-11-16 | 2015-11-12 | Electrolux Home Products Corporation N.V. | Method of Operating a Heat Pump Laundry Dryer and Heat Pump Laundry Dryer or Heat Pump Washing Machine Having Drying Function |
| CN107974813A (en) * | 2017-11-17 | 2018-05-01 | 无锡小天鹅股份有限公司 | Drying time predictor method and device and dryer |
| WO2019185257A1 (en) * | 2018-03-30 | 2019-10-03 | Arcelik Anonim Sirketi | A laundry washer-dryer |
| US20190301071A1 (en) * | 2016-02-23 | 2019-10-03 | Electrolux Appliances Aktiebolag | Method for the determination of a laundry weight in a laundry treatment appliance |
| US20200032449A1 (en) * | 2018-07-27 | 2020-01-30 | Haier Us Appliance Solutions, Inc. | Dryer appliance and methods for communicating with a remote device |
| US20200087847A1 (en) * | 2019-08-21 | 2020-03-19 | Lg Electronics Inc. | Method and apparatus for drying laundry using intelligent washer |
| WO2020259848A1 (en) * | 2019-06-28 | 2020-12-30 | Electrolux Appliances Aktiebolag | Laundry drying machine and control method thereof |
-
2021
- 2021-12-31 CN CN202111682898.1A patent/CN114182510A/en active Pending
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5172490A (en) * | 1991-02-28 | 1992-12-22 | Kabushiki Kaisha Toshiba | Clothes dryer with neurocontrol device |
| US5560124A (en) * | 1991-12-10 | 1996-10-01 | Hart; Douglas R. S. | Automatic cycle terminator for dryers |
| EP0707107A1 (en) * | 1994-10-11 | 1996-04-17 | ELECTROLUX ZANUSSI ELETTRODOMESTICI S.p.A. | Improvement in the arrangement used in a clothes drying apparatus to determine the drying time |
| US5899005A (en) * | 1997-03-13 | 1999-05-04 | General Electric Company | System and method for predicting the dryness of clothing articles |
| US20020184789A1 (en) * | 2001-05-25 | 2002-12-12 | Maytag Corporation | Self programming clothes dryter system |
| EP1559829A1 (en) * | 2004-01-28 | 2005-08-03 | CANDY S.p.A. | Drying method and device |
| WO2007077094A1 (en) * | 2005-12-30 | 2007-07-12 | Arcelik Anonim Sirketi | A dryer |
| US20150322618A1 (en) * | 2012-11-16 | 2015-11-12 | Electrolux Home Products Corporation N.V. | Method of Operating a Heat Pump Laundry Dryer and Heat Pump Laundry Dryer or Heat Pump Washing Machine Having Drying Function |
| WO2014076093A1 (en) * | 2012-11-16 | 2014-05-22 | Electrolux Home Products Corporation N.V. | Method of operating a heat pump laundry dryer and heat pump laundry dryer or heat pump washing machine having drying function |
| EP2927366A1 (en) * | 2014-03-31 | 2015-10-07 | Electrolux Appliances Aktiebolag | Laundry treatment apparatus and method of operation |
| CN104562607A (en) * | 2015-01-21 | 2015-04-29 | 东华大学 | Dynamic feedback measuring and controlling platform used for researching technology of drying textiles in clothes dryer |
| US20190301071A1 (en) * | 2016-02-23 | 2019-10-03 | Electrolux Appliances Aktiebolag | Method for the determination of a laundry weight in a laundry treatment appliance |
| CN107974813A (en) * | 2017-11-17 | 2018-05-01 | 无锡小天鹅股份有限公司 | Drying time predictor method and device and dryer |
| WO2019185257A1 (en) * | 2018-03-30 | 2019-10-03 | Arcelik Anonim Sirketi | A laundry washer-dryer |
| US20200032449A1 (en) * | 2018-07-27 | 2020-01-30 | Haier Us Appliance Solutions, Inc. | Dryer appliance and methods for communicating with a remote device |
| WO2020259848A1 (en) * | 2019-06-28 | 2020-12-30 | Electrolux Appliances Aktiebolag | Laundry drying machine and control method thereof |
| US20200087847A1 (en) * | 2019-08-21 | 2020-03-19 | Lg Electronics Inc. | Method and apparatus for drying laundry using intelligent washer |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115294671A (en) * | 2022-08-08 | 2022-11-04 | 杭州哲达科技股份有限公司 | Air compressor outlet pressure prediction method and prediction system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106498678B (en) | Clothes dryer control method | |
| CN104805664A (en) | Washing-drying all-in-one machine and drying control method thereof | |
| CN107849797B (en) | The drying control method and system of dryer | |
| US9952567B2 (en) | Method for setting up a functionality for a control unit | |
| CN114182510A (en) | Clothes dryer control method and device, clothes dryer and storage medium | |
| Gao et al. | Fault detection and diagnosis method for cooling dehumidifier based on LS-SVM NARX model | |
| CN115167562B (en) | Machine room temperature control method and device | |
| Wei et al. | Enhancing the energy efficiency of domestic dryer by drying process optimization | |
| Islam et al. | Non-linear autoregressive neural network approach for inside air temperature prediction of a pillar cooler | |
| CN113156807A (en) | Control method and device of dryer, computer equipment and storage medium | |
| CN114814707A (en) | Intelligent ammeter stress error analysis method, equipment, terminal and readable medium | |
| CN109442680A (en) | Power estimating method, device and the computer readable storage medium of outdoor fan of air conditioner | |
| CN114065602A (en) | Temperature prediction method, model training method and related equipment | |
| Wang et al. | Development of an intelligent control system for wood drying processes | |
| CN113067340B (en) | Dynamic state estimation method and system for constant temperature control load system | |
| Ogawa et al. | Cooling control restraining effects due to ICT equipment utilization of disturbance based on model predictive control for modular data center | |
| CN114312213A (en) | Refrigerant capacity abnormality prediction method, apparatus, device and medium for vehicle | |
| KR20060095710A (en) | Method for controlling course of the clothes dryer | |
| JPH08117493A (en) | Clothes drier and method which judges drying time of clothes | |
| JP7496726B2 (en) | Defect cause estimation device and method | |
| Rosato et al. | Field performance of HVAC system under healthy and faulty conditions during the summer: Preliminary development of a simulation model based on artificial neural networks | |
| CN113584845A (en) | Blowing control method, system, circulating fan and computer readable storage medium | |
| CN113703498B (en) | Motor cooling regulation and control method and system based on air heat exchange | |
| CN114236276B (en) | Method and system for remotely testing electric appliance | |
| KR102719111B1 (en) | Deep learning based cooling system temperature prediction apparatus according to physical causality and method therefor |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |