Wall-mounted boiler intelligent control system and method

Abstract

The invention relates to the technical field of intelligent equipment, and discloses an intelligent control system and method for a wall-mounted boiler, and the method comprises the steps: collecting the heat supply information of a control region; generating first two-dimensional structure data according to the collected heat supply information; the first two-dimensional structure data are input into M boiler control models, and control parameters representing all heating equipment of all rooms in the next control period are output; controlling the operation of all the heating equipment in the corresponding room through the control parameters, output by the boiler control model, of all the heating equipment in the room in the next control period; according to the intelligent control method for the wall-mounted boiler, a plurality of rooms need to be supplied with heat in a control area and comprise various heat supply devices, and the associated influence of the heat supply devices in the area is comprehensively considered, so that the optimal cooperative control strategy of the wall-mounted boiler in each room can be learned, the whole system can meet the temperature requirement and the user preference, and the intelligent control method for the wall-mounted boiler can be realized. And meanwhile, the total energy consumption is minimized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent equipment, and more specifically, to an intelligent control system and method for a wall-mounted boiler. Background Art

[0002] Wall-mounted boilers are one of the most widely used devices in home heating systems. Due to the dynamic changes in the environment and user needs, how to effectively control the operation of the boiler to achieve a balance between energy saving and environmental protection and user comfort has always been a challenge. Traditional control methods such as PID controllers are simple and effective, but they require a lot of experience in parameter debugging and cannot adapt to complex and changing working conditions. Summary of the invention

[0003] The present invention provides an intelligent control system and method for a wall-mounted boiler, which solves the technical problem that the traditional control method in the related art cannot adapt to complex and changeable working conditions.

[0004] The present invention provides an intelligent control method for a wall-mounted boiler, comprising the following steps:

[0005] Step 100, collecting heating information of the control area, the heating information includes wall-mounted boiler information and room information of each room, the room information includes house attributes, house status, indoor heating equipment information and user information, wherein the user information includes user preference information;

[0006] Step 200, generating No. 1 two-dimensional structure data from the collected heating information, the No. 1 two-dimensional structure data including No. 1 data matrix and No. 1 relationship matrix, one unit of the No. 1 data matrix represents No. 1 one-dimensional structure data of an independent object, the independent objects include rooms and wall-mounted boilers, one unit of the No. 1 data matrix representing a room only includes the room information of the room, and one unit of the No. 1 data matrix representing a wall-mounted boiler only includes the wall-mounted boiler information of the wall-mounted boiler;

[0007] The element in the i-th row and j-th column of the No. 1 relationship matrix represents the association between the i-th unit of the No. 1 data matrix and the independent object represented by the j-th unit. If there is an association, the value of this element of the No. 1 relationship matrix is ​​1, otherwise it is 0;

[0008] There is a relationship between rooms when: the rooms have the same attributes and are adjacent in space;

[0009] The relationship between a room and a wall-mounted boiler means that the wall-mounted boiler will participate in controlling the temperature of the room;

[0010] Step 300, inputting the No. 1 two-dimensional structure data into M boiler control models, where M is the total number of rooms in the control area, and the boiler control model comprises a first intermediate layer, a second intermediate layer and a first output layer, wherein the first intermediate layer inputs the No. 1 one-dimensional structure data and outputs the first intermediate representation data to the second intermediate layer, the second intermediate layer also inputs the No. 1 relationship matrix, the second intermediate layer outputs the second intermediate representation data to the first output layer, and the first output layer outputs the control parameters of all heating equipment in the room within the next control cycle;

[0011] Step 400, controlling the operation of all heating equipment in the corresponding room by using the control parameters of all heating equipment in the room in the next control cycle output by the boiler control model.

[0012] Furthermore, indoor heating equipment includes floor heating, air conditioning, and electric heaters.

[0013] Furthermore, all heating equipment includes wall-mounted boilers and indoor heating equipment.

[0014] Furthermore, the calculation formula of the first intermediate layer is as follows:

[0015] h t =tanh(W hh h t-1 +W xh x t +b h )

[0016] where h t represents the tth first intermediate representation data output by the first intermediate layer, h t-1 represents the t-1th first intermediate representation data, x t represents the tth data item of the one-dimensional structure data, W hh and W xh are the first and second weight parameters, b h is the first bias parameter and tanh is the hyperbolic tangent function.

[0017] Furthermore, the calculation formula of the second intermediate layer is as follows:

[0018]

[0019] where k v The second intermediate representation data of the vth unit of the data matrix No. 1, M (v) is the set of cells associated with the vth cell of data matrix 1, The nth first intermediate representation data output when the first structural data of the vth unit of the first data matrix is ​​input into the first intermediate layer, c v is a normalization constant, σ is the sigmoid function, Wk Represents the third weight parameter.

[0020] Furthermore, the calculation formula of the first output layer is as follows:

[0021] y v =σ(W y k v +b y )

[0022] where y v represents the first output vector, and its cth component value represents the probability value of the cth strategy. The strategy with the largest probability value is selected as the output. The strategy group contains all executable strategies. A strategy includes a set of operating parameters of all heating equipment in the room. v The second intermediate representation data of the vth unit of the data matrix No. 1, W y is the out weight parameter, b y is the out bias parameter, and σ represents the sigmoid function.

[0023] Furthermore, the training method of the boiler control model includes the following steps:

[0024] Step 101, initializing the parameters of the boiler control model;

[0025] Step 102: Observe the heating information S at time t t , strategy A executed at time t t , heating information S at time t+1 t+1 , execute strategy A t Rewards received R t ;

[0026] Step 103, then calculate the policy error:

[0027]

[0028] where δ t represents the policy error at time t, γ represents the discount coefficient, γ∈[0,1], represents the boiler control model input S t+1 The maximum probability value in the first output vector output when represents the boiler control model input S t The first output vector outputted when t is t corresponds to strategy A t The probability value of

[0029]

[0030] where r i represents the user satisfaction value of the i-th room, E totalRepresents the total heating energy consumption of the control area, T i , denote the actual temperature and expected temperature of the ith room, respectively, e ,λ c represent the energy consumption and temperature difference weight coefficients respectively;

[0031] Step 104, updating the boiler control model, the updated formula is as follows:

[0032]

[0033] β∈[0,1], β represents the step size of deep learning, ← represents the transfer update;

[0034] Step 105, iterate steps 102-104 until the boiler control model converges or the number of iterations reaches a set value.

[0035] Furthermore, a number-one one-dimensional structure data includes n data items sorted by time, and the t-th data item represents the heating information of the corresponding independent object collected at the t-th moment.

[0036] Further, including:

[0037] Data collection center, which is used to collect heating information of the control area;

[0038] A data generation module, which is used to generate a first two-dimensional structure data from the collected heating information;

[0039] A strategy generation module, which is used to input the No. 1 two-dimensional structure data into M boiler control models, and output control parameters representing all heating equipment in all rooms in the next control cycle respectively;

[0040] The control execution module is used to control the operation of all heating equipment in the corresponding room through the control parameters of all heating equipment in the room within the next control cycle output by the boiler control model.

[0041] The present invention provides a computer storage medium for storing computer-readable instructions, which can execute the aforementioned intelligent control method for a wall-mounted boiler when the computer-readable instructions are read.

[0042] The beneficial effects of the present invention are:

[0043] There are multiple rooms in the control area that need heating and contain multiple heating equipment. By comprehensively considering the associated impacts of the heating equipment in the area, the intelligent control method for wall-mounted boilers of the present invention can learn the optimal collaborative control strategy for the wall-mounted boilers in each room, so that the system as a whole can meet the temperature requirements and user preferences while minimizing total energy consumption. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a flow chart of an intelligent control method for a wall-mounted boiler of the present invention. DETAILED DESCRIPTION

[0045] The subject matter described herein will now be discussed with reference to example implementations. It should be understood that the discussion of these implementations is only to enable those skilled in the art to better understand and implement the subject matter described herein, and the functions and arrangements of the elements discussed may be changed without departing from the scope of protection of the present specification. Various examples may omit, replace, or add various processes or components as needed. In addition, the features described in some examples may also be combined in other examples.

[0046] At least one embodiment of the present invention discloses an intelligent control method for a wall-mounted boiler. Figure 1 As shown, the following steps are included:

[0047] Step 100, collecting heating information of the control area, the heating information includes wall-mounted boiler information and room information of each room, the room information includes house attributes, house status, indoor heating equipment information and user information, wherein the user information includes user preference information;

[0048] In one embodiment of the present invention, the indoor heating equipment includes floor heating, air conditioning, electric heater and other heating equipment installed indoors.

[0049] Step 200, generating No. 1 two-dimensional structure data from the collected heating information, the No. 1 two-dimensional structure data including No. 1 data matrix and No. 1 relationship matrix, one unit of the No. 1 data matrix represents No. 1 one-dimensional structure data of an independent object, the independent objects include rooms and wall-mounted boilers, one unit of the No. 1 data matrix representing a room only includes the room information of the room, and one unit of the No. 1 data matrix representing a wall-mounted boiler only includes the wall-mounted boiler information of the wall-mounted boiler;

[0050] The element in the i-th row and j-th column of the No. 1 relationship matrix represents the association between the i-th unit of the No. 1 data matrix and the independent object represented by the j-th unit. If there is an association, the value of this element of the No. 1 relationship matrix is ​​1, otherwise it is 0;

[0051] The relationship between rooms means that the rooms have the same attributes and are adjacent in space (upper and lower or surrounding);

[0052] The relationship between a room and a wall-mounted boiler means that the wall-mounted boiler will participate in controlling the temperature of the room;

[0053] A one-dimensional structure data includes n data items sorted by time, and the t-th data item represents the heating information of the corresponding independent object collected at the t-th moment;

[0054] Step 300, inputting the No. 1 two-dimensional structure data into M boiler control models, where M is the total number of rooms in the control area, and the boiler control model comprises a first intermediate layer, a second intermediate layer and a first output layer, wherein the first intermediate layer inputs the No. 1 one-dimensional structure data and outputs the first intermediate representation data to the second intermediate layer, the second intermediate layer also inputs the No. 1 relationship matrix, the second intermediate layer outputs the second intermediate representation data to the first output layer, and the first output layer outputs the control parameters of all heating equipment in the room within the next control cycle;

[0055] Step 400, controlling the operation of all heating equipment in the corresponding room by using the control parameters of all heating equipment in the room in the next control cycle output by the boiler control model.

[0056] In one embodiment of the present invention, all heating equipment includes wall-mounted boilers and indoor heating equipment.

[0057] At least one embodiment of the present invention provides an intelligent control system for a wall-mounted boiler, comprising:

[0058] Data collection center, which is used to collect heating information of the control area;

[0059] A data generation module, which is used to generate a first two-dimensional structure data from the collected heating information;

[0060] A strategy generation module, which is used to input the No. 1 two-dimensional structure data into M boiler control models, and output control parameters representing all heating equipment in all rooms in the next control cycle respectively;

[0061] The control execution module is used to control the operation of all heating equipment in the corresponding room through the control parameters of all heating equipment in the room within the next control cycle output by the boiler control model.

[0062] At least one embodiment of the present invention provides a computer storage medium for storing computer-readable instructions, which can execute the aforementioned intelligent control method for a wall-mounted boiler when the computer-readable instructions are read.

[0063] In one embodiment of the present invention, the calculation formula of the first intermediate layer is as follows:

[0064] h t =tanh(W hh h t-1 +W xh x t +b h )

[0065] where h trepresents the tth first intermediate representation data output by the first intermediate layer, h t-1 represents the t-1th first intermediate representation data, x t represents the tth data item of the one-dimensional structure data, W hh and W xh are the first and second weight parameters, b h is the first bias parameter and tanh is the hyperbolic tangent function.

[0066] In one embodiment of the present invention, the calculation formula of the second intermediate layer is as follows:

[0067]

[0068] where k v The second intermediate representation data of the vth unit of the data matrix No. 1, M (v) is the set of cells associated with the vth cell of data matrix 1, The nth first intermediate representation data output when the first structural data of the vth unit of the first data matrix is ​​input into the first intermediate layer, c v is a normalization constant, σ is the sigmoid function, W k Represents the third weight parameter.

[0069] In one embodiment of the present invention, the calculation formula of the first output layer is as follows:

[0070] y v =σ(W y k v +b y )

[0071] where y v represents the first output vector, and its cth component value represents the probability value of the cth strategy. The strategy with the largest probability value is selected as the output. The strategy group contains all executable strategies. A strategy includes a set of operating parameters of all heating equipment in the room. v The second intermediate representation data of the vth unit of the data matrix No. 1, W y is the out weight parameter, b y is the out bias parameter, and σ represents the sigmoid function.

[0072] The training method of the boiler control model includes the following steps:

[0073] Step 101, initializing the parameters of the boiler control model;

[0074] Step 102: Observe the heating information S at time t t , strategy A executed at time t t, heating information S at time t+1 t+1 , execute strategy A t Rewards received R t ;

[0075] Step 103, then calculate the policy error:

[0076]

[0077] where δ t represents the policy error at time t, γ represents the discount coefficient, γ∈[0,1], Denotes the boiler control model input S t+1 The maximum probability value in the first output vector output when Denotes the boiler control model input S t The first output vector outputted when t is t corresponds to strategy A t The probability value of

[0078]

[0079] where r i represents the user satisfaction value of the i-th room, E total Represents the total heating energy consumption of the control area, T i , denote the actual temperature and expected temperature of the ith room, respectively, e ,λ c They represent the energy consumption and temperature difference weight coefficients respectively, the sum of which is 1. The default values ​​are 0.4 and 0.6.

[0080] Step 104, updating the boiler control model, the updated formula is as follows:

[0081]

[0082] β∈[0,1], β represents the step size of deep learning, ← represents the transfer update;

[0083] Step 105, iterate steps 102-104 until the boiler control model converges or the number of iterations reaches a set value, the default value of which is 30.

[0084] The present invention provides a computer storage medium for storing computer-readable instructions, which can execute the aforementioned intelligent control method for a wall-mounted boiler when the computer-readable instructions are read.

[0085] At least one embodiment of the present invention discloses an intelligent control system for a wall-mounted boiler, comprising:

[0086] An information collection module collects heating information of the control area, the heating information includes wall-mounted boiler information and room information of each room, the room information includes house attributes, house status, indoor heating equipment information and user information, wherein the user information includes user preference information;

[0087] A data generation module generates No. 1 two-dimensional structure data from the collected heating information, wherein the No. 1 two-dimensional structure data includes No. 1 data matrix and No. 1 relationship matrix, wherein one unit of the No. 1 data matrix represents No. 1 one-dimensional structure data of an independent object, wherein the independent objects include rooms and wall-mounted boilers, and one unit of the No. 1 data matrix representing a room only includes the room information of the room, and one unit of the No. 1 data matrix representing a wall-mounted boiler only includes the wall-mounted boiler information of the wall-mounted boiler;

[0088] The element in the i-th row and j-th column of the No. 1 relationship matrix represents the association between the i-th unit of the No. 1 data matrix and the independent object represented by the j-th unit. If there is an association, the value of this element of the No. 1 relationship matrix is ​​1, otherwise it is 0;

[0089] The distributed control module inputs the No. 1 two-dimensional structure data into M boiler control models, where M is the total number of rooms in the control area, and the boiler control model includes a first intermediate layer, a second intermediate layer, and a first output layer, wherein the first intermediate layer inputs the No. 1 one-dimensional structure data and outputs the first intermediate representation data to the second intermediate layer, the second intermediate layer also inputs the No. 1 relationship matrix, the second intermediate layer outputs the second intermediate representation data to the first output layer, and the first output layer outputs the control parameters of all heating equipment in the room within the next control cycle;

[0090] The execution control module controls the operation of all heating equipment in the corresponding room through the control parameters of all heating equipment in the room within the next control cycle output by the boiler control model.

[0091] The above describes an embodiment of the present invention, but this embodiment is not limited to the above-mentioned specific implementation mode. The above-mentioned specific implementation mode is merely illustrative and not restrictive. Under the guidance of this embodiment, ordinary technicians in this field can also make more forms of equivalent embodiments, all of which are within the protection of this embodiment.

Claims

1. A wall-mounted boiler intelligent control method, characterized in that: The following steps are involved: Step 100, collecting heating information of the control area, the heating information includes wall-mounted boiler information and room information of each room, the room information includes house attributes, house status, indoor heating equipment information and user information, wherein the user information includes user preference information; Step 200, generating No. 1 two-dimensional structure data from the collected heating information, the No. 1 two-dimensional structure data including No. 1 data matrix and No. 1 relationship matrix, one unit of the No. 1 data matrix represents No. 1 one-dimensional structure data of an independent object, the independent objects include rooms and wall-mounted boilers, one unit of the No. 1 data matrix representing a room only includes the room information of the room, and one unit of the No. 1 data matrix representing a wall-mounted boiler only includes the wall-mounted boiler information of the wall-mounted boiler; The element in the i-th row and j-th column of the No. 1 relationship matrix represents the association between the i-th unit of the No. 1 data matrix and the independent object represented by the j-th unit. If there is an association, the value of this element of the No. 1 relationship matrix is ​​1, otherwise it is 0; There is a relationship between rooms when: the rooms have the same attributes and are adjacent in space; The relationship between a room and a wall-mounted boiler means that the wall-mounted boiler will participate in controlling the temperature of the room; Step 300, inputting the No. 1 two-dimensional structure data into M boiler control models, where M is the total number of rooms in the control area, and the boiler control model comprises a first intermediate layer, a second intermediate layer and a first output layer, wherein the first intermediate layer inputs the No. 1 one-dimensional structure data and outputs the first intermediate representation data to the second intermediate layer, the second intermediate layer also inputs the No. 1 relationship matrix, the second intermediate layer outputs the second intermediate representation data to the first output layer, and the first output layer outputs the control parameters of all heating equipment in the room within the next control cycle; Step 400, controlling the operation of all heating equipment in the corresponding room by using the control parameters of all heating equipment in the room in the next control cycle output by the boiler control model.

2. The intelligent control method for a wall-mounted boiler according to claim 1 is characterized in that: Indoor heating equipment includes floor heating, air conditioning and electric heaters.

3. The intelligent control method for a wall-mounted boiler according to claim 1 is characterized in that: All heating equipment including wall-mounted boilers and indoor heating equipment.

4. The intelligent control method for a wall-mounted boiler according to claim 1 is characterized in that: The calculation formula for the first intermediate layer is as follows: h t =tanh(W hh h t-1 +W xh x t +b h ) where h t represents the tth first intermediate representation data output by the first intermediate layer, h t-1 represents the t-1th first intermediate representation data, x t represents the tth data item of the one-dimensional structure data, W hh and W xh are the first and second weight parameters, b h is the first bias parameter and tanh is the hyperbolic tangent function.

5. The intelligent control method for a wall-mounted boiler according to claim 4 is characterized in that: The calculation formula for the second intermediate layer is as follows: where k v The second intermediate representation data of the vth unit of the data matrix No. 1, M (v) is the set of cells associated with the vth cell of data matrix 1, The nth first intermediate representation data output when the first structural data of the vth unit of the first data matrix is ​​input into the first intermediate layer, c v is a normalization constant, σ is the sigmoid function, W k Represents the third weight parameter.

6. The intelligent control method for a wall-mounted boiler according to claim 5 is characterized in that: The calculation formula of the first output layer is as follows: y v =σ(W y k v +b y ) where y v represents the first output vector, and its cth component value represents the probability value of the cth strategy. The strategy with the largest probability value is selected as the output. The strategy group contains all executable strategies. A strategy includes a set of operating parameters of all heating equipment in the room. v The second intermediate representation data of the vth unit of the data matrix No. 1, W y is the out weight parameter, b y is the out bias parameter, and σ represents the sigmoid function.

7. The intelligent control method for a wall-mounted boiler according to claim 1 is characterized in that: The training method of the boiler control model includes the following steps: Step 101, initializing the parameters of the boiler control model; Step 102: Observe the heating information S at time t t , strategy A executed at time t t , heating information S at time t+1 t+1 , execute strategy A t Rewards received R t ; Step 103, then calculate the policy error: where δ t represents the policy error at time t, γ represents the discount coefficient, γ∈[0,1], represents the boiler control model input S t+1 The maximum probability value in the first output vector output when represents the boiler control model input S t The first output vector outputted when t is t corresponds to strategy A t The probability value of where r i represents the user satisfaction value of the i-th room, E total Indicates the total heating energy consumption of the control area, denote the actual temperature and expected temperature of the ith room, respectively, e ,λ c represent the energy consumption and temperature difference weight coefficients respectively; Step 104, updating the boiler control model, the updated formula is as follows: β∈[0,1], β represents the step size of deep learning, ← represents the transfer update; Step 105, iterate steps 102-104 until the boiler control model converges or the number of iterations reaches a set value.

8. The intelligent control method for a wall-mounted boiler according to claim 1 is characterized in that: A number one one-dimensional structure data includes n data items sorted by time, and the t-th data item represents the heating information of the corresponding independent object collected at the t-th moment.

9. The intelligent control system for a wall-mounted boiler according to claim 1, characterized in that: include: Data collection center, which is used to collect heating information of the control area; A data generation module, which is used to generate a first two-dimensional structure data from the collected heating information; A strategy generation module, which is used to input the No. 1 two-dimensional structure data into M boiler control models, and output control parameters representing all heating equipment in all rooms in the next control cycle respectively; The control execution module is used to control the operation of all heating equipment in the corresponding room through the control parameters of all heating equipment in the room within the next control cycle output by the boiler control model.

10. A computer storage medium, characterized in that: It is used to store computer-readable instructions, and when the computer-readable instructions are read, it can execute a wall-mounted boiler intelligent control method as described in any one of claims 1-8.

Images