Method, device and system for controlling moisture at outlet of shredded stalk drying machine

Abstract

The present invention provides a method, device and system for controlling the outlet moisture of a stalk shred machine, the method comprising: inputting the current control data into a control prediction model, obtaining the valve opening value output by the control prediction model, and the outlet moisture prediction value corresponding to the valve opening value; after converting the valve opening value into a control signal, sending the control signal to the stalk shred machine to be controlled, so that the stalk shred machine to be controlled can adjust the opening of the main valve at the next moment according to the control signal; when it is determined that the difference between the outlet moisture actual value and the outlet moisture prediction value is less than or equal to a first preset threshold value, using the control prediction model to make a next prediction on the next control data. The method, device and system for controlling the outlet moisture of the stalk shred machine provided by the present invention improve the control accuracy and stability of the whole machine, can accurately control the outlet moisture of the stalk shred machine, and ensure moisture stability.

Description

Technical Field

[0001] The invention relates to the technical field of tobacco manufacturing, and in particular to a method, device and system for controlling moisture at an outlet of a shredded stem drying machine. Background Art

[0002] The function of tobacco drying equipment is to remove excess moisture from the product through baking and dehumidification, so as to control the taste of tobacco products. The moisture content of tobacco shreds directly affects the flexibility and processing resistance of tobacco shreds, which is related to the consumption of tobacco shreds and the sensory comfort of tobacco shreds in the production process. Therefore, a complete predictive control system for the moisture content of the tobacco shreds outlet of the tobacco drying equipment is crucial.

[0003] At present, the more mainstream control method is to track the outlet moisture and set value, use a simple PID algorithm in real time and add some sequential logic to control, so that the outlet moisture is stable near the set value. Because there are many interference factors affecting the outlet moisture of tobacco in the drying process, each control loop is relatively independent, and the corresponding control process has strong nonlinearity, uncertainty, coupling and hysteresis, it is difficult to achieve true closed-loop automatic control. Therefore, the control accuracy and stability of tobacco drying equipment on the whole equipment are poor, which is not conducive to system improvement and maintenance, resulting in the quality of tobacco being affected and the overall quality of tobacco being reduced. Summary of the invention

[0004] The invention provides a method, device and system for controlling the moisture at the outlet of a shredded stalk drying machine, which are used to solve the defects of poor control accuracy and stability of the whole machine in the prior art.

[0005] The present invention provides a method for controlling moisture at an outlet of a shredded stalk drying machine, comprising:

[0006] Inputting the control data into the control prediction model, obtaining the valve opening value output by the control prediction model, and the outlet moisture prediction value corresponding to the valve opening value;

[0007] After converting the valve opening value into a control signal, the control signal is sent to the to-be-controlled dried shredded stem machine, so that the to-be-controlled dried shredded stem machine can adjust the opening of the main valve at the next moment according to the control signal;

[0008] When it is determined that the difference between the actual outlet moisture value and the outlet moisture prediction value is less than or equal to the first preset threshold, using the control prediction model to make a next prediction for the next control data;

[0009] Among them, the control data of this time is determined by the operating status of the control device corresponding to each control parameter of the dried shredded stem machine to be controlled at the current moment; the control prediction model is trained based on the sample control data, the outlet moisture data corresponding to the sample control data and the valve opening value corresponding to the sample control data at the corresponding time sequence.

[0010] According to a method for controlling the moisture content at the outlet of a shredded stem drying machine provided by the present invention, the control prediction model comprises an independent control layer, a joint control layer and a moisture prediction layer;

[0011] Input the current control data into the independent control layer, and obtain the control amount of each control parameter output by the independent control layer at the next moment;

[0012] Inputting the control amount of each control parameter at the next moment into the joint control layer, and obtaining the valve opening value output by the joint control layer;

[0013] The valve opening value is input into the moisture prediction layer to obtain the outlet moisture prediction value output by the moisture prediction layer.

[0014] According to a method for controlling the moisture at the outlet of a shredded stem drying machine provided by the present invention, after sending the next control data to the shredded stem drying machine to be controlled, the method further comprises:

[0015] Acquire production data of the shredded stem drying machine to be controlled under the action of the control signal;

[0016] determining a degree of production variance based on historical production data and the production data;

[0017] When it is determined that the degree of production difference is greater than or equal to a second preset threshold, issuing an alarm message;

[0018] Among them, the production data at least includes control data and actual outlet moisture value; the historical production data is queried from the batch database based on batch information; the batch database includes production data of various types of tobacco in the production process of corresponding batches; the batch information is determined based on the current control data.

[0019] According to a method for controlling the moisture at the outlet of a shredded stem drying machine provided by the present invention, before inputting the control data into the control prediction model, the method further comprises:

[0020] In the case where the batch information is used to match the production data corresponding to the batch information from the batch database, the control data corresponding to each time sequence in the production data is sequentially converted into a control signal;

[0021] The control signal is sent to the dried shredded stem machine to be controlled, so that the dried shredded stem machine to be controlled can adjust the opening of the main valve at the next moment according to the control signal;

[0022] The production data at least includes control data and actual value of outlet moisture; the batch database includes production data of various types of tobacco in the production process of corresponding batches; and the batch information is determined based on the current control data.

[0023] A method for controlling moisture at an outlet of a shredded stem drying machine according to the present invention also includes:

[0024] Generate a control signal based on the valve opening value input by the user terminal;

[0025] The control signal is sent to the dried shredded stem machine to be controlled, so that the dried shredded stem machine to be controlled can adjust the opening of the main valve at the next moment according to the control signal.

[0026] The present invention also provides a device for controlling moisture at an outlet of a shredded stem drying machine, comprising:

[0027] A control prediction module, used for inputting the current control data into the control prediction model, obtaining the valve opening value output by the control prediction model, and the outlet moisture prediction value corresponding to the valve opening value;

[0028] A control conversion module, configured to convert the valve opening value into a control signal, and then send the control signal to the dried shredded stem machine to be controlled, so that the dried shredded stem machine to be controlled can adjust the opening of the main valve at the next moment according to the control signal;

[0029] A control judgment module, configured to use the control prediction model to make a next prediction for the next control data when it is determined that the difference between the actual outlet moisture value and the outlet moisture prediction value is less than or equal to a first preset threshold value;

[0030] Among them, the control data of this time is determined by the operating status of the control device corresponding to each control parameter of the dried shredded stem machine to be controlled at the current moment; the control prediction model is trained based on the sample control data, the outlet moisture data corresponding to the sample control data and the valve opening value corresponding to the sample control data at the corresponding time sequence.

[0031] The present invention also provides a control system for moisture at the outlet of a shredded stem drying machine, comprising at least one shredded stem drying machine and a control terminal, wherein the control terminal is used to execute the control method for moisture at the outlet of the shredded stem drying machine as described above.

[0032] The present invention also provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, a method for controlling moisture at the outlet of a dried shredded stem machine as described in any one of the above is implemented.

[0033] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for controlling the moisture at the outlet of the shredded stem drying machine as described in any one of the above is implemented.

[0034] The present invention also provides a computer program product, comprising a computer program, wherein when the computer program is executed by a processor, the computer program implements the method for controlling the moisture at the outlet of the shredded stem drying machine as described in any one of the above.

[0035] The control method, device and system for the outlet moisture of the dried stalk shred machine provided by the present invention use real-time control data as the input of the control prediction model, and the output result is the valve opening value at the next moment corresponding to the current operating state, and the outlet moisture prediction value estimated under the action of the valve opening value. The valve opening value is then encapsulated into the control signal, so that the actual outlet moisture value obtained by the joint action of each control device is controlled to be as close as possible to the outlet moisture prediction value through the opening adjustment of a total valve. The influence of each control parameter on the outlet moisture and the correlation between each control parameter are mined from the operating sample values ​​of each control device through a neural network, so that in the control logic, multiple control devices can be associated and controlled through a predicted valve opening value, which greatly improves the control accuracy and stability of the whole equipment, can accurately control the outlet moisture of the dried stalk shred machine, and ensure moisture stability. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 It is a schematic flow chart of a method for controlling moisture at the outlet of a shredded stalk drying machine provided by the present invention;

[0038] Figure 2 It is a structural schematic diagram of a device for controlling moisture at an outlet of a shredded stalk drying machine provided by the present invention;

[0039] Figure 3 It is a structural schematic diagram of a control system for moisture at the outlet of a shredded stalk drying machine provided by the present invention;

[0040] Figure 4It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] The terms "first", "second", etc. in this application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the terms used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of the same type, and the number of objects is not limited. For example, the first object can be one or more.

[0043] It should be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present invention, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0044] The terms “include” and “comprising” indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0045] Figure 1 1 is a flow chart of the method for controlling the moisture at the outlet of the shredded stalk drying machine provided by the present invention. Figure 1 As shown, the method for controlling the outlet moisture of the shredded stem drying machine according to the embodiment of the present invention comprises: step 101, inputting the current control data into the control prediction model, obtaining the valve opening value output by the control prediction model, and the outlet moisture prediction value corresponding to the valve opening value.

[0046] Among them, the control data of this time is determined by the operating state of the control device corresponding to each control parameter of the dried shredded stalk machine to be controlled at the current moment. The control prediction model is trained based on the sample control data, the outlet moisture data corresponding to the sample control data, and the valve opening value corresponding to the sample control data in the corresponding time sequence.

[0047] It should be noted that the execution body of the method for controlling the moisture content at the outlet of the shredded stem drying machine provided in the embodiment of the present invention is the control device for controlling the moisture content at the outlet of the shredded stem drying machine.

[0048] The method for controlling the moisture content at the outlet of the tobacco shreds drying machine provided in the embodiment of the present application is suitable for users to intelligently control the tobacco shreds drying machine through electronic devices, so as to ensure that the moisture content at the outlet is always at a relative set value during the tobacco shreds drying process.

[0049] The above-mentioned electronic devices can be implemented in various forms. For example, the electronic devices described in the embodiments of the present application may include mobile terminals such as mobile phones, smart phones, laptops, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), navigation devices, smart bracelets, smart watches, etc., and fixed terminals such as digital TVs, desktop computers, etc. Below, it is assumed that the electronic device is a mobile terminal. However, it will be understood by those skilled in the art that, in addition to components specifically used for mobile purposes, the construction according to the embodiments of the present application can also be applied to fixed-type terminals.

[0050] It should be noted that before step 101, when the dried shredded silk machine to be controlled is in operation, the control device for the moisture content at the outlet of the dried shredded silk machine receives the control data transmitted back in real time by the dried shredded silk machine to be controlled, and performs preprocessing operations such as timestamp alignment, parameter padding, mean supplementation, and outlier removal on the data.

[0051] Among them, the control data this time refers to the control parameter collection sensors built into each process point, which monitor the operating status of the control devices corresponding to each control parameter, and transmit the sampling values ​​of the control parameters in the current operating status as the control data this time to the control device for the moisture content at the outlet of the drying machine.

[0052] The embodiment of the present invention does not specifically limit the control parameters of the shredded stem drying machine.

[0053] Exemplarily, the shredded stem drying machine is composed of at least two parts: one is an online shredded stem expansion device for treating shredded stems (Steam Treated Stem, STS) with steam, and the other is a shredded stem drying fluidized bed.

[0054] The control parameter may be the actual moisture value at the STS inlet. The actual moisture value at the STS inlet is used to characterize the actual moisture value of the material before entering the dried shredded stem machine to be controlled.

[0055] The control parameter can be the amount of steam introduced into the STS. The amount of steam introduced into the STS is used to characterize the amount of steam added by the STS equipment. The steam allows the tobacco to be fully heated and humidified to prepare for subsequent drying and expansion.

[0056] The control parameter can be the actual value of the STS front scale. The actual value of the STS front scale is used to characterize the material flow rate of the tobacco before entering the equipment.

[0057] The control parameter may be the hot air temperature of zone 1. The hot air temperature of zone 1 is used to characterize a zone of the fluidized bed for drying the cut tobacco. The hot air temperature may be set at about 135°C to allow the cut tobacco to be dried for the first time.

[0058] The control parameter can be the hot air temperature of the second zone. The hot air temperature of the second zone is used to characterize the second zone of the fluidized bed for drying the cut tobacco. The hot air temperature can be set at about 120°C to allow the cut tobacco to be dried for the second time.

[0059] The control parameter may be the opening of the fresh air damper in zone 1. The opening of the fresh air damper in zone 1 is used to represent the control input point of the fresh air damper in zone 1 output from the digital output port of the PLC controller to the fresh air inlet damper in zone 1 of the cut stem drying fluidized bed.

[0060] The control parameter may be the opening of the fresh air door in the second zone. The opening of the fresh air door in the second zone is used to represent the control input point of the fresh air door in the second zone of the cut stem drying fluidized bed output from the digital output port of the PLC controller.

[0061] The control parameter can be the opening of the steam valve for the first zone temperature control. The opening of the steam valve for the first zone temperature control is used to control the steam flow of the heater for controlling the hot air temperature of the first zone of the stem drying fluidized bed.

[0062] The control parameter can be the opening of the steam valve for the second zone temperature control. The opening of the steam valve for the second zone temperature control is used to control the steam flow rate of the heater of the second zone hot air temperature of the stem drying fluidized bed.

[0063] The control parameter may be the actual value of moisture at the fluidized bed outlet. The actual value of moisture at the fluidized bed outlet is used to characterize the moisture of the tobacco after drying.

[0064] The control parameter may be the fluidized bed ambient temperature, which is used to characterize the ambient temperature of the fluidized bed when it is in operation.

[0065] The control parameter may be the fluidized bed ambient humidity. The fluidized bed ambient humidity is used to characterize the ambient humidity when the fluidized bed is in operation.

[0066] The control parameter may be the production leaf group batch number, which at least includes the tobacco type and production batch number. Different types have different characteristics and require different parameters.

[0067] It should be noted that the control prediction model can be a neural network model, and the structure and parameters of the neural network include but are not limited to the number of layers of the input layer, hidden layer and output layer of the neural network, and the weight parameters of each layer, etc. The embodiment of the present invention does not specifically limit the type and structure of the neural network.

[0068] For example, the control prediction model can be a neural network model consisting of an input layer, a hidden layer, and an output layer, where:

[0069] The input layer is at the front end of the entire network. It directly controls the corresponding control data each time and extracts the corresponding feature information.

[0070] The hidden layer can have one or more layers, and the input vector is calculated by weighted summation through its own neurons.

[0071] The output layer is the last layer, which is used to decode the vector obtained after weighted summation, output the valve opening value corresponding to the next control, and the outlet moisture prediction value under the effect of the valve opening value.

[0072] It should be noted that the sample data used to train the model includes the sample control data at each time corresponding to the sample data, the outlet moisture data corresponding to the sample control data, and the valve opening value corresponding to the sample control data at the corresponding time sequence. The sample data is divided into a training set and a test set according to a certain ratio.

[0073] Exemplarily, the ratio of the training set to the test set in the sample data includes, but is not limited to, 9:1, 8:2, etc., which is not specifically limited in the embodiment of the present invention.

[0074] Specifically, in step 101, the control device for the moisture at the outlet of the shredded stalk drying machine initializes the weight coefficients between the layers of the constructed control prediction model, and then inputs a set of sample data and the annotation content of the sample data in the training set into the neural network under the current weight coefficient, and calculates the output of each node of the input layer, hidden layer and output layer in turn. The cumulative error between the final output result of the output layer and the actual connection position state type is used to correct the weight coefficients between the input layer and the nodes of the hidden layer according to the gradient descent method. According to the above process, until all the sample data in the training set are traversed, the weight coefficients of the input layer and the hidden layer can be obtained.

[0075] The control device for the outlet moisture of the dried shredded meat machine restores the control prediction model according to the weight coefficients of the neural network input layer and the hidden layer, and inputs each set of control data received in real time into the trained control prediction model. It can predict the valve opening value to be adjusted for the next control, as well as the outlet moisture prediction value corresponding to the next moment under the action of the valve opening value.

[0076] Step 102: after converting the valve opening value into a control signal, the control signal is sent to the dried shredded meat machine to be controlled, so that the dried shredded meat machine to be controlled can adjust the opening of the main valve at the next moment according to the control signal.

[0077] Specifically, in step 102, the control device for the moisture at the outlet of the dried shredded stem machine converts the valve opening value into a control signal, and sends the control signal to the dried shredded stem machine to be controlled.

[0078] The dried shredded silk machine to be controlled receives and responds to the control signal, and writes the valve opening value carried in the control signal into the PLC program of the whole machine, so that the PLC controller adjusts the opening of the main valve to the predicted valve opening value at the next moment according to the timing, and then transmits the corresponding mechanical kinetic energy to each control device in the dried shredded silk machine to be controlled, thereby realizing the adjustment of the outlet moisture through the joint control of the entire drying process.

[0079] Step 103: When it is determined that the difference between the actual outlet moisture value and the predicted outlet moisture value is less than or equal to the first preset threshold, the control prediction model is used to perform a next prediction on the next control data.

[0080] Specifically, in step 103, the control device for the moisture content at the outlet of the shredded stem drying machine monitors the change trend of the moisture content at the outlet after the total valve opening is adjusted.

[0081] If the absolute value of the difference between the actual outlet moisture value under the action of the valve opening value and the outlet moisture predicted value predicted by the control prediction model is less than or equal to the first preset threshold, that is, the difference between the actual outlet moisture value and the outlet moisture predicted value is within an acceptable tolerance range, then the control prediction at the current moment is deemed successful, and the control prediction model can be used to make the next prediction for the next control data.

[0082] On the contrary, if the absolute value of the difference between the actual outlet moisture value under the action of the valve opening value and the outlet moisture prediction value predicted by the control prediction model is greater than the first preset threshold, that is, the gap between the actual outlet moisture value and the outlet moisture prediction value exceeds the acceptable tolerance range, then it is determined that the control prediction at the current moment has failed and needs to be adjusted again until the difference between the two meets the condition of the first preset threshold. Only then can the control prediction model be used to make the next prediction for the next control data.

[0083] It is understandable that the actual value of the outlet moisture and the predicted value of the outlet moisture corresponding to each moment may also be filled into the corresponding change curves respectively, and displayed visually in the user interface.

[0084] The embodiment of the present invention uses real-time control data as the input of the control prediction model, and the output result is the valve opening value at the next moment corresponding to the current operating state, and the outlet moisture prediction value estimated under the action of the valve opening value. The valve opening value is then encapsulated into the control signal, so that the actual outlet moisture value obtained by the joint action of each control device is as close as possible to the outlet moisture prediction value through the adjustment of the opening of a total valve. The influence of each control parameter on the outlet moisture and the correlation between each control parameter are mined from the operating sampling values ​​of each control device through a neural network, so that in the control logic, multiple control devices can be associated and controlled through a predicted valve opening value, which greatly improves the control accuracy and stability of the whole equipment, and can accurately control the outlet moisture of the shredded stalk drying machine to ensure moisture stability.

[0085] Based on any of the above embodiments, the control prediction model includes an independent control layer, a joint control layer and a moisture prediction layer.

[0086] The current control data is input into the independent control layer to obtain the control amount of each control parameter output by the independent control layer at the next moment.

[0087] The control amount of each control parameter at the next moment is input into the joint control layer to obtain the valve opening value output by the joint control layer.

[0088] The valve opening value is input into the moisture prediction layer to obtain the outlet moisture prediction value output by the moisture prediction layer.

[0089] Specifically, the control prediction model built into the control device for the outlet moisture of the shredded stalk drying machine consists of an input layer, a hidden layer, and an output layer. The hidden layer extracts and weights the features of the control data to obtain the control amount for the next control relative to the current control data, as well as the estimated outlet moisture under the control amount.

[0090] The embodiment of the present invention does not specifically limit the structure of the hidden layer.

[0091] Preferably, the hidden layer includes at least three layers, namely, an independent control layer, a joint control layer, and a moisture prediction layer. Among them:

[0092] The function of the independent control layer is to calculate the correlation between different control parameters from the current control data, calculate the influence of each control parameter on the outlet moisture through the correlation, and obtain the control amount that matches each control parameter with the influence degree.

[0093] The function of the joint control layer is to calculate the control correlation coefficient based on the corresponding relationship between the main valve and each control device, and then perform weighted summation on the control amount of each control parameter at the next moment to obtain the valve opening value of the main valve.

[0094] The function of the moisture prediction layer is to determine the outlet moisture prediction value corresponding to the valve opening value based on the corresponding relationship between the control quantity of each control device and the outlet moisture.

[0095] The embodiment of the present invention predicts the control amount of each control parameter at the next moment based on the current control data by the independent control layer, integrates each control amount into a valve opening value through the joint control layer, and then converts the valve opening value into an outlet moisture prediction value through the moisture prediction layer. Through the neural network, the influence of each control parameter on the outlet moisture and the correlation between each control parameter are mined from the operation sampling value of each control device, so that in the control logic, multiple control devices can be associated and controlled through a predicted valve opening value, which greatly improves the control accuracy and stability of the whole equipment, and can accurately control the outlet moisture of the shredded stalk drying machine to ensure moisture stability.

[0096] On the basis of any of the above embodiments, after sending the next control data to the dried shredded stem machine to be controlled, the method further includes: acquiring production data of the dried shredded stem machine to be controlled under the action of the control signal.

[0097] The production data at least includes control data and actual value of outlet moisture.

[0098] Specifically, after step 102, the control device for the outlet moisture of the dried shredded meat machine monitors in real time the actual production process of the dried shredded meat machine to be controlled under the action of the valve opening value, and receives the control data of each control device fed back in the actual production process and the actual value of the outlet moisture as production data.

[0099] Based on historical production data and production data, determine the degree of production variance.

[0100] The historical production data is retrieved from the batch database based on the batch information. The batch database includes the production data of various types of tobacco in the production process of the corresponding batch. The batch information is determined based on the current control data.

[0101] It should be noted that the control device for the moisture content at the outlet of the dried shredded stem machine can extract the batch information of the leaf group materials from the current control data, and use the batch information to query the historical production data of the same batch of materials in the production process in the batch database.

[0102] Specifically, the device for controlling the moisture at the outlet of the shredded stem drying machine subtracts the current production data from the historical production data to obtain the degree of production difference at the current moment relative to the historical moment.

[0103] When it is determined that the degree of production difference is greater than or equal to the second preset threshold, an alarm message is issued.

[0104] Specifically, the control device for the moisture at the outlet of the shredded stem drying machine compares the degree of production difference with the second preset threshold value:

[0105] If the degree of production difference is less than the second preset threshold, it is determined that the production status at the current moment is relatively stable relative to the production status at the historical moment and no mutation has occurred.

[0106] If the degree of production difference is greater than or equal to the second preset threshold, it is determined that the production status at the current moment is less stable than the production status at the historical moment, and an alarm message needs to be issued in the user interface to inform the user that there may be an abnormal situation at present.

[0107] The embodiment of the present invention does not specifically limit the method of comparing the production difference degrees.

[0108] Optionally, the control device for the moisture content at the outlet of the dried shredded meat machine subtracts the actual value of the outlet moisture at each current moment from the actual value of the historical outlet moisture at the previous moment, and when the difference between the two exceeds a limited range of a second preset threshold, an alarm message is issued (for example, a text content "Current outlet moisture is abnormal" is popped up in the form of a pop-up window on the user interface).

[0109] Optionally, the control device for the moisture content at the outlet of the dried shredded meat machine subtracts the actual sampling value of the control parameter corresponding to a certain control device at each current moment from the historical control data at the previous moment, and when the difference between the two exceeds a limited range of a second preset threshold, an alarm message is issued (for example, the text content "Current control abnormality" pops up in the form of a pop-up window on the user interface).

[0110] The embodiment of the present invention monitors the actual production data of the controlled shredded stem drying machine in real time after receiving the control signal, and issues an alarm when the production difference between the historical production data and the actual production data does not meet the second preset threshold value, so as to timely guide the staff to make corresponding rectifications on the defective process nodes, eliminate the risk hazards in advance, and effectively avoid the waste of costs and resources.

[0111] Based on any of the above embodiments, before inputting the current control data into the control prediction model, it also includes: when using the batch information to match the production data corresponding to the batch information from the batch database, the control data corresponding to each time series in the production data is converted into a control signal in sequence.

[0112] The production data at least includes control data and actual value of outlet moisture. The batch database includes production data of various types of tobacco in the production process of corresponding batches. Batch information is determined based on this control data.

[0113] Specifically, before step 101, when receiving the control information, the control device for the moisture at the outlet of the shredded stalk drying machine can first extract the batch information therefrom, and use the batch information to query the batch database:

[0114] If the batch information is successfully matched in the batch database, that is, the batch database stores production data of the same batch, the same type and different leaf groups, then the production data under the matched complete production timeline will be converted into control signals in sequence according to the control data at the corresponding moment.

[0115] If the batch information fails to match in the batch database, that is, the batch database does not store production data of the same batch, the same type and different leaf groups, the control prediction model is used to predict the valve opening value at the next moment to control the outlet moisture of the dried shredded stem machine to be controlled.

[0116] The control signal is sent to the dried shredded stem machine to be controlled, so that the dried shredded stem machine to be controlled can adjust the opening of the main valve at the next moment according to the control signal.

[0117] Specifically, the control device for the moisture content at the outlet of the dried shredded stem machine can send control signals from different leaf groups of the same batch and type under the complete production timeline to the dried shredded stem machine to be controlled to perform the same production activities.

[0118] The embodiment of the present invention is based on batch information. When the production data corresponding to the batch information is matched from the batch database, the decision is made to convert the control data in the production data into control signals in sequence in order to perform similar production activities again. If the production information stored in the batch database can be successfully matched, the corresponding control signal is directly issued without additional planning and deployment, thereby improving control accuracy and efficiency.

[0119] Based on any of the above embodiments, the method further includes: generating a control signal based on the valve opening value input by the user terminal.

[0120] The control signal is sent to the dried shredded stem machine to be controlled, so that the dried shredded stem machine to be controlled can adjust the opening of the main valve at the next moment according to the control signal.

[0121] Specifically, before step 101, the device for controlling the moisture at the outlet of the shredded stem drying machine may first determine the current working mode according to the instruction issued by the user.

[0122] If the current working mode is manual mode, the control device of the outlet moisture of the dried stalks machine directly receives the valve opening value input by the user terminal and directly converts it into a control signal. The dried stalks machine to be controlled writes the valve opening value carried in the control signal into the PLC program of the whole machine, so that the PLC controller adjusts the opening of the main valve to the predicted valve opening value at the next moment according to the timing, and then transmits the corresponding mechanical kinetic energy to each control device in the dried stalks machine to be controlled, so as to adjust the outlet moisture through the joint control of the entire drying process.

[0123] It is understandable that if the current working mode is the simulation mode, the control device for the moisture content at the outlet of the shredded stem drying machine only receives the control data at each time sequence, and uses it as a training sample after marking, so that the user can retrain the control prediction model.

[0124] It is understandable that if the current working mode is the off mode, the control device for the moisture at the outlet of the shredded stem drying machine directly closes the entire program after issuing a shut-down command by selecting the corresponding control in the user interface.

[0125] The embodiment of the present invention is based on directly converting the valve opening value input by the user into a control signal under the corresponding working mode, and directly adjusting the opening of a main valve, so that the actual value of the outlet moisture obtained by the joint action of various control components is as close as possible to the predicted value of the outlet moisture. It can provide multiple operating modes and improve control accuracy and efficiency.

[0126] Figure 2 Schematic diagram of the structure of the control device for the moisture content at the outlet of the shredded stalk drying machine provided by the present invention. Figure 2 As shown, the device includes: a control prediction module 210, a control conversion module 220 and a control judgment module 230, wherein:

[0127] The control prediction module 210 is used to input the current control data into the control prediction model, and obtain the valve opening value output by the control prediction model, and the outlet moisture prediction value corresponding to the valve opening value.

[0128] The control conversion module 220 is used to convert the valve opening value into a control signal, and then send the control signal to the dried shredded stem machine to be controlled, so that the dried shredded stem machine to be controlled can adjust the opening of the main valve at the next moment according to the control signal.

[0129] The control judgment module 230 is used to use the control prediction model to make a next prediction for the next control data when it is determined that the difference between the actual outlet moisture value and the predicted outlet moisture value is less than or equal to the first preset threshold.

[0130] Among them, the control data of this time is determined by the operating state of the control device corresponding to each control parameter of the dried shredded stalk machine to be controlled at the current moment. The control prediction model is trained based on the sample control data, the outlet moisture data corresponding to the sample control data, and the valve opening value corresponding to the sample control data in the corresponding time sequence.

[0131] Specifically, the control prediction module 210 , the control conversion module 220 , and the control judgment module 230 are electrically connected in sequence.

[0132] The control prediction module 210 initializes the weight coefficients between each layer of the constructed control prediction model, and then inputs a set of sample data and the annotation content of the sample data in the training set into the neural network under the current weight coefficient, and calculates the output of each node of the input layer, hidden layer and output layer in turn. The cumulative error between the final output result of the output layer and its actual connection position state type is used to correct the weight coefficients between the input layer and the hidden layer nodes according to the gradient descent method. According to the above process, until all sample data in the training set are traversed, the weight coefficients of the input layer and the hidden layer can be obtained.

[0133] The control device for the outlet moisture of the dried shredded meat machine restores the control prediction model according to the weight coefficients of the neural network input layer and the hidden layer, and inputs each set of control data received in real time into the trained control prediction model. It can predict the valve opening value to be adjusted for the next control, as well as the outlet moisture prediction value corresponding to the next moment under the action of the valve opening value.

[0134] The control conversion module 220 converts the valve opening value into a control signal, and sends the control signal to the shredded stem drying machine to be controlled.

[0135] The control judgment module 230 monitors the outlet moisture change trend after the total valve opening is adjusted.

[0136] If the absolute value of the difference between the actual outlet moisture value under the action of the valve opening value and the outlet moisture predicted value predicted by the control prediction model is less than or equal to the first preset threshold, that is, the difference between the actual outlet moisture value and the outlet moisture predicted value is within an acceptable tolerance range, then the control prediction at the current moment is deemed successful, and the control prediction model can be used to make the next prediction for the next control data.

[0137] Optionally, the control prediction model includes an independent control layer, a joint control layer and a moisture prediction layer.

[0138] Accordingly, the control prediction module 210 includes an independent control unit, a joint control unit and a moisture prediction unit, wherein:

[0139] The independent control unit is used to input the current control data into the independent control layer and obtain the control amount of each control parameter output by the independent control layer at the next moment.

[0140] The joint control unit is used to input the control amount of each control parameter at the next moment into the joint control layer, and obtain the valve opening value output by the joint control layer.

[0141] The moisture prediction unit is used to input the valve opening value into the moisture prediction layer and obtain the outlet moisture prediction value output by the moisture prediction layer.

[0142] Optionally, the device further includes a production data monitoring module, a production difference degree determination module and an alarm module, wherein:

[0143] The production data monitoring module is used to obtain the production data of the shredded stem drying machine to be controlled under the action of the control signal.

[0144] The production difference degree determination module is used to determine the production difference degree based on historical production data and production data.

[0145] The alarm module is used to issue an alarm message when it is determined that the degree of production difference is greater than or equal to a second preset threshold.

[0146] The production data at least includes control data and actual value of outlet moisture. The historical production data is retrieved from the batch database based on the batch information. The batch database includes production data of various types of tobacco in the production process of the corresponding batch. The batch information is determined based on the current control data.

[0147] Optionally, the device further includes a batch information matching module and a first control module, wherein:

[0148] The batch information matching module is used to convert the control data corresponding to each time sequence in the production data into a control signal in sequence when the batch information is matched to the production data corresponding to the batch information from the batch database.

[0149] The first control module is used to send a control signal to the dried shredded stem machine to be controlled, so that the dried shredded stem machine to be controlled can adjust the opening of the main valve at the next moment according to the control signal.

[0150] The production data at least includes control data and actual value of outlet moisture. The batch database includes production data of various types of tobacco in the production process of corresponding batches. Batch information is determined based on this control data.

[0151] Optionally, the device further comprises an opening setting module and a second control module, wherein:

[0152] The opening setting module is used to generate a control signal based on the valve opening value input by the user terminal.

[0153] The second control module is used to send a control signal to the dried shredded stem machine to be controlled, so that the dried shredded stem machine to be controlled can adjust the opening of the main valve at the next moment according to the control signal.

[0154] The device for controlling the moisture at the outlet of the dried shredded stem machine provided in an embodiment of the present invention is used to execute the method for controlling the moisture at the outlet of the dried shredded stem machine mentioned above. Its implementation method is consistent with the implementation method of the method for controlling the moisture at the outlet of the dried shredded stem machine provided by the present invention, and can achieve the same beneficial effects, which will not be repeated here.

[0155] The embodiment of the present invention uses real-time control data as the input of the control prediction model, and the output result is the valve opening value at the next moment corresponding to the current operating state, and the outlet moisture prediction value estimated under the action of the valve opening value. The valve opening value is then encapsulated into the control signal, so that the actual outlet moisture value obtained by the joint action of each control device is as close as possible to the outlet moisture prediction value through the adjustment of the opening of a total valve. The influence of each control parameter on the outlet moisture and the correlation between each control parameter are mined from the operating sampling values ​​of each control device through a neural network, so that in the control logic, multiple control devices can be associated and controlled through a predicted valve opening value, which greatly improves the control accuracy and stability of the whole equipment, and can accurately control the outlet moisture of the shredded stalk drying machine to ensure moisture stability.

[0156] Figure 3 Schematic diagram of the structure of the control system of the moisture at the outlet of the shredded stalk drying machine provided by the present invention. Figure 3 As shown, the system includes at least one shredded stem drying machine 310 and a control terminal 320. The control terminal 320 is used to execute the above-mentioned method for controlling the moisture at the outlet of the shredded stem drying machine.

[0157] Specifically, the control system for the moisture content at the outlet of the dried shredded stem machine is composed of a control terminal 320 that is communicatively connected to one or more dried shredded stem machines 310 .

[0158] Among them, the communication connection methods include wired communication technology and wireless communication technology.

[0159] Wired communication technology includes but is not limited to serial ports, data lines, etc., and the embodiments of the present invention do not specifically limit this.

[0160] Wireless communication technology includes but is not limited to WIFI wireless cellular signals (2G, 3G, 4G, 5G), Bluetooth, Zigbee and the like, which are not specifically limited in the embodiments of the present invention.

[0161] For example, in the control system of the moisture at the outlet of the dried shredded stem machine, the control terminal 320 can communicate with the PLC of each dried shredded stem machine through the Internet of Things data acquisition gateway to obtain real-time data.

[0162] If the data is insufficient, smart sensors can be added to the PLC layer. The edge computing platform obtains IoT data in real time, performs model calculations and interface display, and the calculation results are closed-loop controlled to the PLC in real time.

[0163] The embodiment of the present invention uses real-time control data as the input of the control prediction model, and the output result is the valve opening value at the next moment corresponding to the current operating state, and the outlet moisture prediction value estimated under the action of the valve opening value. The valve opening value is then encapsulated into the control signal, so that the actual outlet moisture value obtained by the joint action of each control device is as close as possible to the outlet moisture prediction value through the adjustment of the opening of a total valve. The influence of each control parameter on the outlet moisture and the correlation between each control parameter are mined from the operating sampling values ​​of each control device through a neural network, so that in the control logic, multiple control devices can be associated and controlled through a predicted valve opening value, which greatly improves the control accuracy and stability of the whole equipment, and can accurately control the outlet moisture of the shredded stalk drying machine to ensure moisture stability.

[0164] Figure 4 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 4 As shown, the electronic device may include: a processor (processor) 410 , a communication interface (Communications Interface) 420 , a memory (memory) 430 and a communication bus 440 , wherein the processor 410 , the communication interface 420 , and the memory 430 communicate with each other through the communication bus 440 . The processor 410 can call the logic instructions in the memory 430 to execute a method for controlling the outlet moisture of the dried shredded meat machine, the method comprising: inputting the current control data into the control prediction model, obtaining the valve opening value output by the control prediction model, and the outlet moisture prediction value corresponding to the valve opening value; after converting the valve opening value into a control signal, sending the control signal to the dried shredded meat machine to be controlled, so that the dried shredded meat machine to be controlled can adjust the opening of the main valve at the next moment according to the control signal; when it is determined that the difference between the actual outlet moisture value and the predicted outlet moisture value is less than or equal to the first preset threshold value, using the control prediction model to make a next prediction on the next control data; wherein, the current control data is determined by the operating state of the control device corresponding to each control parameter of the dried shredded meat machine to be controlled at the current moment; the control prediction model is trained based on the sample control data, the outlet moisture data corresponding to the sample control data, and the valve opening value correspondingly marked on the sample control data at the corresponding time sequence.

[0165] In addition, the logic instructions in the above-mentioned memory 430 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc. Various media that can store program codes.

[0166] On the other hand, the present invention also provides a computer program product, which includes a computer program, which can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute the control method for controlling the outlet moisture of the dried shredded meat machine provided by the above methods, the method including: inputting the current control data into a control prediction model, obtaining the valve opening value output by the control prediction model, and the outlet moisture prediction value corresponding to the valve opening value; after converting the valve opening value into a control signal, sending the control signal to the dried shredded meat machine to be controlled, so that the dried shredded meat machine to be controlled can adjust the opening of the main valve at the next moment according to the control signal; when it is determined that the difference between the actual outlet moisture value and the predicted outlet moisture value is less than or equal to a first preset threshold value, using the control prediction model to make a next prediction for the next control data; wherein, the current control data is determined by the operating state of the control device corresponding to each control parameter of the dried shredded meat machine to be controlled at the current moment; the control prediction model is trained based on the sample control data, the outlet moisture data corresponding to the sample control data, and the valve opening value correspondingly marked on the sample control data at the corresponding time sequence.

[0167] On the other hand, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to execute the control method for controlling the outlet moisture of a dried shredded vegetable machine provided by the above-mentioned methods, the method comprising: inputting the current control data into a control prediction model, obtaining the valve opening value output by the control prediction model, and the outlet moisture prediction value corresponding to the valve opening value; after converting the valve opening value into a control signal, sending the control signal to the dried shredded vegetable machine to be controlled, so that the dried shredded vegetable machine to be controlled can adjust the opening of the main valve at the next moment according to the control signal; when it is determined that the difference between the actual outlet moisture value and the predicted outlet moisture value is less than or equal to a first preset threshold value, using the control prediction model to make a next prediction on the next control data; wherein, the current control data is determined by the operating state of the control device corresponding to each control parameter of the dried shredded vegetable machine to be controlled at the current moment; the control prediction model is trained based on the sample control data, the outlet moisture data corresponding to the sample control data, and the valve opening value correspondingly marked on the sample control data at the corresponding time sequence.

[0168] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0169] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0170] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for controlling the moisture at the outlet of a shredded stalk drying machine. It is characterized in that include: When the control device for the moisture content at the outlet of the dried stalk shreds machine receives the control data, the batch information is extracted from the control data, and the batch information is used to query the batch database; wherein, if the batch information is successfully matched in the batch database, that is, the batch database stores production data of different leaf groups of the same batch and type, the production data under the matched complete production timeline is converted into control signals in sequence according to the time sequence; if the batch information is not matched in the batch database, that is, the batch database does not store production data of different leaf groups of the same batch and type, the control prediction model is used to predict the valve opening value at the next moment to control the moisture content at the outlet of the dried stalk shreds machine to be controlled; Inputting the control data into the control prediction model, obtaining the valve opening value output by the control prediction model, and the outlet moisture prediction value corresponding to the valve opening value; After converting the valve opening value into a control signal, the control signal is sent to the to-be-controlled dried shredded stem machine, so that the to-be-controlled dried shredded stem machine can adjust the opening of the main valve at the next moment according to the control signal; When it is determined that the difference between the actual outlet moisture value and the outlet moisture prediction value is less than or equal to the first preset threshold, using the control prediction model to make a next prediction for the next control data; Among them, the control data for this time is determined by monitoring the operating status of the control device corresponding to each control parameter through the control parameter acquisition sensor built into each process point; and the sampled value of the control parameter in the current operating state is used as the control data for this time; the control prediction model is trained based on the sample control data, the outlet moisture data corresponding to the sample control data and the valve opening value corresponding to the sample control data at the corresponding time sequence.

2. The method for controlling the moisture at the outlet of the shredded stem drying machine according to claim 1, It is characterized in that The control prediction model includes an independent control layer, a joint control layer and a moisture prediction layer; Input the current control data into the independent control layer, and obtain the control amount of each control parameter output by the independent control layer at the next moment; Inputting the control amount of each control parameter at the next moment into the joint control layer, and obtaining the valve opening value output by the joint control layer; The valve opening value is input into the moisture prediction layer to obtain the outlet moisture prediction value output by the moisture prediction layer.

3. The method for controlling the moisture at the outlet of the shredded stem drying machine according to claim 2, It is characterized in that After sending the next control data to the to-be-controlled shredded stem drying machine, the method further includes: Acquire production data of the dried shredded stem machine to be controlled under the action of the control signal; determining a degree of production variance based on historical production data and the production data; When it is determined that the degree of production difference is greater than or equal to a second preset threshold, issuing an alarm message; Among them, the production data at least includes control data and actual outlet moisture value; the historical production data is queried from the batch database based on batch information; the batch database includes production data of various types of tobacco in the production process of corresponding batches; the batch information is determined based on the current control data.

4. The method for controlling the moisture at the outlet of the shredded stem drying machine according to any one of claims 1 to 3, It is characterized in that Also includes: Generate a control signal based on the valve opening value input by the user terminal; The control signal is sent to the dried shredded stem machine to be controlled, so that the dried shredded stem machine to be controlled can adjust the opening of the main valve at the next moment according to the control signal.

5. A device for controlling the moisture at the outlet of a shredded stalk drying machine. It is characterized in that include: The batch information matching module is used for extracting batch information from the current control data when the control device of the moisture content of the dried stalk shred machine outlet receives the current control data, and using the batch information to query in the batch database; wherein, if the batch information is successfully matched in the batch database, that is, the batch database stores production data of different leaf groups of the same batch and type, then the production data under the matched complete production timeline is converted into control signals in sequence according to the time sequence; if the batch information is not matched in the batch database, that is, the batch database does not store production data of different leaf groups of the same batch and type, then the control prediction model is used to predict the valve opening value at the next moment to control the moisture content of the dried stalk shred machine to be controlled; A control prediction module, used for inputting the current control data into the control prediction model, obtaining the valve opening value output by the control prediction model, and the outlet moisture prediction value corresponding to the valve opening value; A control conversion module, configured to convert the valve opening value into a control signal, and then send the control signal to the dried shredded stem machine to be controlled, so that the dried shredded stem machine to be controlled can adjust the opening of the main valve at the next moment according to the control signal; A control judgment module, configured to use the control prediction model to make a next prediction for the next control data when it is determined that the difference between the actual outlet moisture value and the outlet moisture prediction value is less than or equal to a first preset threshold value; Among them, the control data for this time is determined by monitoring the operating status of the control device corresponding to each control parameter through the control parameter acquisition sensor built into each process point; and the sampled value of the control parameter in the current operating state is used as the control data for this time; the control prediction model is trained based on the sample control data, the outlet moisture data corresponding to the sample control data and the valve opening value corresponding to the sample control data at the corresponding time sequence.

6. A control system for moisture at the outlet of a shredded stem drying machine, comprising at least one shredded stem drying machine, It is characterized in that It also includes a control terminal, which is used to execute the method for controlling the moisture content at the outlet of the shredded stem drying machine according to any one of claims 1 to 4.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, It is characterized in that When the processor executes the program, the method for controlling the moisture at the outlet of the dried shredded stem machine as claimed in any one of claims 1 to 4 is implemented.

8. A non-transitory computer-readable storage medium having a computer program stored thereon, It is characterized in that When the computer program is executed by a processor, the method for controlling the moisture at the outlet of the shredded stem drying machine as claimed in any one of claims 1 to 4 is implemented.

9. A computer program product comprising a computer program, It is characterized in that When the computer program is executed by a processor, the method for controlling the moisture at the outlet of the shredded stem drying machine as claimed in any one of claims 1 to 4 is implemented.

Images