Tobacco production monitoring method and system, electronic equipment and storage medium

Abstract

The invention provides a tobacco production monitoring method and system, electronic equipment and a storage medium, and relates to the technical field of tobacco production. The method comprises the following steps: acquiring actual measurement data corresponding to different indexes to be measured in each stage of representing tobacco production; according to the actually measured data, determining a dynamic deviation tensor representing the deviation degree between the actually measured production state of each stage of tobacco production and the ideal production state at the current moment; according to the actually measured data and the dynamic deviation tensor, determining a comprehensive deviation state parameter of the to-be-measured index based on a preset deviation judgment strategy; and according to the actually measured data, the dynamic deviation tensor and the comprehensive deviation state parameter, generating monitoring feedback information of the to-be-measured index. Therefore, the problems of high labor cost and low efficiency of a traditional tobacco production monitoring mode can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of tobacco production, and in particular to a tobacco production monitoring method, system, electronic equipment and storage medium. Background Art

[0002] The tobacco industry's production process encompasses over ten key steps, including tobacco leaf fermentation, tobacco silk processing, and tobacco rolling and packaging. Over 200 process parameters, including temperature and humidity, material moisture content, and equipment operating parameters, directly impact the sensory quality and smoke composition stability of cigarettes. Statistics show that a single cigarette production line generates over 100,000 pieces of monitoring data per hour. Achieving real-time, coordinated monitoring of multiple processes and indicators has become a core challenge in ensuring consistent product quality.

[0003] Traditionally, tobacco production quality monitoring at each stage relies on manual spot checks, with output or alarms generated based on the correlation between the sampled data and fixed thresholds. For example, in the tobacco-making process, the moisture content of each tobacco leaf is manually checked every 30 minutes, or in the tobacco-wrapping process, the packaging defect rate of each batch of tobacco packs is manually checked every 30 minutes.

[0004] In actual applications, the above-mentioned traditional monitoring methods rely on manual operations. Due to the numerous production processes, a large number of staff need to be dispatched to conduct random inspections and result summaries, resulting in high labor costs and low efficiency. Summary of the Invention

[0005] In view of this, the purpose of the embodiments of the present application is to provide a tobacco production monitoring method, system, electronic device and storage medium, which can improve the problems of high labor cost and low efficiency in traditional tobacco production monitoring methods.

[0006] To achieve the above technical objectives, the technical solutions adopted in this application are as follows:

[0007] In a first aspect, an embodiment of the present application provides a tobacco production monitoring method, the method comprising:

[0008] Obtaining measured data corresponding to different indicators to be measured at each stage of tobacco production;

[0009] Determining, based on the measured data, a dynamic deviation tensor representing the degree of deviation between the measured production state and the ideal production state at each stage of tobacco production at the current moment;

[0010] Determine the comprehensive deviation state parameter of the indicator to be measured based on the measured data and the dynamic deviation tensor and a preset deviation judgment strategy;

[0011] Monitoring feedback information of the indicator to be measured is generated according to the measured data, the dynamic deviation tensor and the comprehensive deviation state parameter.

[0012] In conjunction with the first aspect, in some optional embodiments, obtaining measured data corresponding to different indicators to be measured at each stage of tobacco production includes:

[0013] Acquire data obtained by detecting different indicators to be measured at each stage of tobacco production as initial measured data;

[0014] A data matrix is ​​constructed with the initial measured data as elements as the measured data, wherein the row data of the data matrix represent data of different tobacco production stages, and the column data of the data matrix represent data of different indicators.

[0015] In conjunction with the first aspect, in some optional embodiments, determining, based on the measured data, a dynamic deviation tensor representing the degree of deviation between the measured production state and the ideal production state at each stage of tobacco production at the current moment includes:

[0016] Obtaining reference parameters that characterize ideal process parameters of the indicator to be measured;

[0017] The reference parameter is used as the initial dynamic deviation tensor, and the initial dynamic deviation is iteratively updated based on the time series to obtain the dynamic deviation tensor at the current moment. The iterative update of the initial dynamic deviation is expressed as follows:

[0018]

[0019] Where S i,j (t) represents the dynamic deviation tensor of the jth indicator to be measured in the i-th production stage of tobacco production at time t, λ represents the trainable learning rate, M i,j (h) represents the measured data of the jth indicator to be measured in the i-th production stage of tobacco production at time h.

[0020] In conjunction with the first aspect, in some optional implementations, determining the comprehensive deviation state parameter of the indicator to be measured based on the measured data and the dynamic deviation tensor and a preset deviation judgment strategy includes:

[0021] Determine the deviation direction based on the measured data and the dynamic deviation tensor:

[0022] D i,j (t)=sign(M i,j (t)-S i,j (t))

[0023] Where D i,j (t) represents the deviation direction, sign(x) is the sign function, which outputs +1 when x>0, -1 when x<0, and 0 when x=0;

[0024] Determine the deviation amplitude based on the measured data and the dynamic deviation tensor:

[0025]

[0026] Where, δ j It represents the allowable deviation threshold of the j-th indicator, Θ(x) is a unit step function, which outputs 1 when x ≥ 0, otherwise it outputs 0;

[0027] Determine the comprehensive deviation state parameter according to the deviation direction and the deviation amplitude:

[0028] Ψ i,j (t) = D i,j (t)·A i,j (t)

[0029] Where, i,j (t) represents the comprehensive deviation state parameter.

[0030] In conjunction with the first aspect, in some optional implementations, generating monitoring feedback information of the indicator to be measured based on the measured data, the dynamic deviation tensor, and the comprehensive deviation state parameter includes:

[0031] Fill the measured data, the dynamic deviation tensor and the comprehensive deviation state parameter into the semantic template to obtain the monitoring feedback information:

[0032] F i,j (t) = Γ i,j (Ψ i,j (t),M i,j (t),S i,j (t),δ j ,Q i,j (t))

[0033]

[0034] Where, Γ i,j (·) Generates functions for predefined texts.

[0035] In conjunction with the first aspect, in some optional implementations, the method further includes:

[0036] A decision result is determined based on the measured data and the dynamic deviation tensor.

[0037] In conjunction with the first aspect, in some optional implementations, determining a decision result based on the measured data and the dynamic deviation tensor includes:

[0038] For different stages of tobacco production, the comprehensive risk index of each production stage is determined based on the measured data and the dynamic deviation tensor:

[0039]

[0040] Where R i (t) represents the comprehensive risk index of the i-th production stage, K represents the number of indicators to be measured in the i-th production stage, β j represents the risk weight of the jth indicator to be measured, and tanh(·) is the hyperbolic tangent function;

[0041] Determining, based on the comprehensive risk index, a processing decision for each production stage as the decision result;

[0042] Among them, when the comprehensive risk index is less than a first preset risk threshold, the monitoring feedback information is sent to a designated terminal; when the comprehensive risk index is greater than or equal to the first preset risk threshold and less than a second preset risk threshold, the designated indicator to be measured is adjusted until the comprehensive risk index is less than the first preset risk threshold; when the comprehensive risk index is greater than or equal to the second preset risk threshold, a shutdown command is triggered.

[0043] In a second aspect, an embodiment of the present application further provides a tobacco production monitoring system, the system comprising:

[0044] An acquisition unit, used to acquire measured data corresponding to different indicators to be measured at each stage of tobacco production;

[0045] A first determining unit is configured to determine, based on the measured data, a dynamic deviation tensor representing the degree of deviation between the measured production state and the ideal production state at each stage of tobacco production at a current moment;

[0046] A second determining unit is configured to determine a comprehensive deviation state parameter of the indicator to be measured based on the measured data and the dynamic deviation tensor and a preset deviation judgment strategy;

[0047] A generating unit is used to generate monitoring feedback information of the indicator to be measured based on the measured data, the dynamic deviation tensor and the comprehensive deviation state parameter.

[0048] In a third aspect, an embodiment of the present application further provides an electronic device, comprising a processor and a memory coupled to each other, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the electronic device executes the above method.

[0049] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, wherein a computer program is stored in the computer-readable storage medium. When the computer program is run on a computer, the computer executes the above method.

[0050] The invention adopting the above technical solution has the following advantages:

[0051] In the technical solution provided by the present application, first, the measured data corresponding to the different indicators to be measured in each stage of tobacco production are obtained. Then, based on the measured data, a dynamic deviation tensor is determined to characterize the degree of deviation between the measured production state and the ideal production state at each stage of tobacco production at the current moment, and based on the measured data and the dynamic deviation tensor, a comprehensive deviation state parameter of the indicator to be measured is determined based on a preset deviation judgment strategy. Finally, based on the measured data, the dynamic deviation tensor and the comprehensive deviation state parameter, monitoring feedback information of the indicator to be measured is generated. In this way, by automatically collecting and comparing the degree of deviation between the measured data and the calibrated ideal process parameters, corresponding monitoring feedback information is generated, thereby achieving the purpose of real-time monitoring of tobacco production quality and improving the problems of high labor cost and low efficiency in traditional tobacco production monitoring methods. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] The present application may be further illustrated by the non-limiting embodiments provided in the accompanying drawings. It should be understood that the following drawings illustrate only certain embodiments of the present application and are therefore not to be construed as limiting the scope of the present application. It is understood that a person skilled in the art can derive other relevant drawings from these drawings without inventive effort.

[0053] Figure 1 This is a structural block diagram of an electronic device provided in an embodiment of the present application.

[0054] Figure 2 A schematic flow chart of the tobacco production monitoring method provided in an embodiment of the present application.

[0055] Figure 3 This is a schematic diagram of the structure of the tobacco production monitoring system provided in an embodiment of the present application.

[0056] Icon: 100 - electronic device; 101 - processor; 102 - memory; 300 - tobacco production monitoring system; 310 - acquisition unit; 320 - first determination unit; 330 - second determination unit; 340 - generation unit. DETAILED DESCRIPTION

[0057] The present application will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be noted that similar or identical parts in the drawings or descriptions are numbered the same. Implementations not shown or described in the drawings are known to those of ordinary skill in the art. In the description of this application, the terms "first," "second," etc. are used solely to distinguish descriptions and are not to be construed as indicating or implying relative importance.

[0058] Please refer to Figure 1 In an embodiment of the present application, an electronic device 100 may include a processor 101 and a memory 102. The memory 102 stores a computer program, and when the computer program is executed by the processor 101, the electronic device 100 can perform the corresponding steps in the following tobacco production monitoring method.

[0059] In this embodiment, the processor 101 may be an integrated circuit chip having signal processing capabilities. The processor 101 may be a general-purpose processor. For example, the processor 101 may be a central processing unit (CPU), a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components, and may implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of the present application.

[0060] The memory 102 may be, but is not limited to, a random access memory, a read-only memory, a programmable read-only memory, an erasable programmable read-only memory, an electrically erasable programmable read-only memory, etc. In this embodiment, the memory 102 may be used to store measured data, dynamic deviation tensors, preset deviation judgment strategies, monitoring feedback information, decision results, etc. Of course, the memory 102 may also be used to store programs, which the processor 101 executes after receiving an execution instruction.

[0061] It is understandable that Figure 1 The structure of the electronic device 100 shown in FIG is only a schematic diagram of a structure. The electronic device 100 may also include Figure 1 More components shown. Figure 1 Each component shown in the figure can be implemented by hardware, software or a combination thereof.

[0062] In this embodiment, the electronic device 100 can be a personal computer, a laptop computer, a cloud server, a central control computer connected to the front-end equipment of each tobacco production line (such as a humidity sensor for collecting tobacco moisture content, a temperature sensor for collecting tobacco drying drum temperature, a camera and controller for collecting cigarette pack defect rate, etc.). It is used to obtain measured data corresponding to different indicators to be measured at each stage of tobacco production. Then, based on the measured data, a dynamic deviation tensor is determined to represent the degree of deviation between the measured production state and the ideal production state at each stage of tobacco production at the current moment. Based on the measured data and the dynamic deviation tensor, a comprehensive deviation state parameter of the indicator to be measured is determined based on a preset deviation judgment strategy. Finally, monitoring feedback information of the indicator to be measured is generated based on the measured data, the dynamic deviation tensor, and the comprehensive deviation state parameter. In this way, by automatically collecting and comparing the degree of deviation between the measured data and the calibrated ideal process parameters, corresponding monitoring feedback information is generated, thereby achieving the purpose of real-time monitoring of tobacco production quality.

[0063] Please refer to Figure 2 The present application also provides a tobacco production monitoring method, which can be applied to the electronic device 100 described above, and each step of the method is executed or implemented by the electronic device 100. The tobacco production monitoring method can include the following steps:

[0064] Step 210, obtaining measured data corresponding to different indicators to be measured at each stage of tobacco production;

[0065] Step 220: determining a dynamic deviation tensor representing the degree of deviation between the measured production state and the ideal production state at each stage of tobacco production at the current moment based on the measured data;

[0066] Step 230: determining the comprehensive deviation state parameter of the indicator to be measured based on the measured data and the dynamic deviation tensor and a preset deviation judgment strategy;

[0067] Step 240: Generate monitoring feedback information of the indicator to be measured based on the measured data, the dynamic deviation tensor and the comprehensive deviation state parameter.

[0068] In the above-mentioned embodiment, first, the measured data corresponding to the different indicators to be measured at each stage of tobacco production are obtained. Then, based on the measured data, a dynamic deviation tensor is determined to characterize the degree of deviation between the measured production state and the ideal production state at each stage of tobacco production at the current moment. Based on the measured data and the dynamic deviation tensor, a comprehensive deviation state parameter of the indicator to be measured is determined based on a preset deviation judgment strategy. Finally, based on the measured data, the dynamic deviation tensor and the comprehensive deviation state parameter, monitoring feedback information of the indicator to be measured is generated. In this way, by automatically collecting and comparing the degree of deviation between the measured data and the calibrated ideal process parameters, corresponding monitoring feedback information is generated, thereby achieving the purpose of real-time monitoring of tobacco production quality and improving the problems of high labor cost and low efficiency in traditional tobacco production monitoring methods.

[0069] The following is a detailed description of the steps in the tobacco production monitoring method:

[0070] In step 210, the measured data can be collected in real time by a front-end device connected to the electronic device 100 in actual application and uploaded to the processor 101 of the electronic device 100 for subsequent generation of monitoring feedback information; alternatively, the measured data can be obtained by pre-entering a data matrix by the user during the testing phase and stored in the memory 102 of the electronic device 100, so that it can be called based on instructions initiated by the user through the processor 101 during the subsequent generation of monitoring feedback information. The method for obtaining the measured data is not specifically limited here.

[0071] In an optional embodiment, obtaining measured data corresponding to different indicators to be measured at each stage of tobacco production may include:

[0072] Acquire data obtained by detecting different indicators to be measured at each stage of tobacco production as initial measured data;

[0073] A data matrix is ​​constructed with the initial measured data as elements as the measured data, wherein the row data of the data matrix represent data of different tobacco production stages, and the column data of the data matrix represent data of different indicators.

[0074] Among them, the indicators to be measured can be temperature, humidity, equipment operating parameters, etc. in the tobacco production process.

[0075] In this way, by using the test data of the indicators to be measured at each stage of tobacco production as the initial measured data and constructing a data matrix based on the data stage and the type of the indicator to be measured, the measured data is obtained. This facilitates data retrieval and calculation in the subsequent generation of monitoring feedback information. It is understandable that null elements in the data matrix can be replaced with 0.

[0076] In step 220, based on the measured data, determining a dynamic deviation tensor representing the degree of deviation between the measured production state and the ideal production state at each stage of tobacco production at the current moment may include:

[0077] Obtaining reference parameters that characterize ideal process parameters of the indicator to be measured;

[0078] The reference parameter is used as the initial dynamic deviation tensor, and the initial dynamic deviation is iteratively updated based on the time series to obtain the dynamic deviation tensor at the current moment. The iterative update of the initial dynamic deviation is expressed as follows:

[0079]

[0080] Where S i,j (t) represents the dynamic deviation tensor of the jth indicator to be measured in the i-th production stage of tobacco production at time t, λ represents the trainable learning rate, M i,j (h) represents the measured data of the jth indicator to be measured in the i-th production stage of tobacco production at time h.

[0081] In this embodiment, the user's ideal process state is represented by the reference parameter, which is a comprehensive state that can include the process initial reference value calibrated from the process file, historical monitoring data from various sensors, etc.

[0082] In this embodiment, the speed at which the reference parameter affects the historical data is controlled by the learning rate, so that the reference parameter can adapt to process improvements or environmental changes, avoiding the hysteresis of traditional fixed thresholds.

[0083] In this way, this embodiment is based on a dynamic iterative update mechanism to adaptively adjust the benchmark parameters of the ideal production state, ensuring that the deviation tensor is optimized as the production environment changes, thereby improving the adaptability and accuracy of the monitoring model.

[0084] In step 230, determining the comprehensive deviation state parameter of the indicator to be measured based on the measured data and the dynamic deviation tensor and a preset deviation judgment strategy may include:

[0085] Determine the deviation direction based on the measured data and the dynamic deviation tensor:

[0086] D i,j (t)=sign(M i,j (t)-S i,j (t))

[0087] Where D i,j (t) represents the deviation direction, sign(x) is the sign function, which outputs +1 when x>0, -1 when x<0, and 0 when x=0;

[0088] Determine the deviation amplitude based on the measured data and the dynamic deviation tensor:

[0089]

[0090] Where, δ j represents the allowable deviation threshold of the j-th indicator (which can be determined according to the provisions of the national standard document), Θ(x) is a unit step function, which outputs 1 when x ≥ 0, otherwise it outputs 0;

[0091] Determine the comprehensive deviation state parameter according to the deviation direction and the deviation amplitude:

[0092] Ψ i,j (t) = D i,j (t)·A i,j (t)

[0093] Where, i,j (t) represents the comprehensive deviation state parameter, and its output value range is {-1, 0, +1}, representing negative deviation, normal and positive deviation respectively.

[0094] In this embodiment, the deviation status of the measured data is evaluated by using the difference between the measured data of the indicator to be measured and the dynamic deviation tensor representing the ideal process state after dynamic adjustment as a reference. Combined with quantitative analysis of the deviation direction and magnitude, the type of indicator anomaly (positive or negative deviation) and the degree to which the threshold is exceeded are accurately identified, providing a clear basis for targeted adjustments.

[0095] In step 240, generating monitoring feedback information of the indicator to be measured based on the measured data, the dynamic deviation tensor, and the comprehensive deviation state parameter may include:

[0096] Fill the measured data, the dynamic deviation tensor and the comprehensive deviation state parameter into the semantic template to obtain the monitoring feedback information:

[0097] F i,j (t) = Γ i,j (Ψ i,j (t),M i,j (t),S i,j (t),δ j ,Q i,j (t))

[0098]

[0099] Where, Γ i,j (·) Generates functions for predefined texts.

[0100] In this embodiment, after determining the measured data, dynamic deviation tensor and comprehensive deviation state parameters, the difference between the measured data and the dynamic deviation tensor is first quantified into a percentage value to obtain the deviation degree Q i,j (t).

[0101] Then the measured data, dynamic deviation tensor, comprehensive deviation state parameters, offset degree and allowable deviation threshold are filled into the preset semantic template to obtain monitoring feedback information.

[0102] For example, taking the semantic template of the moisture content index of cigarette tobacco as an example, the detection feedback information can be the moisture content of tobacco in stage i Ψ i,j (t), where the measured value is M i,j (t)%, dynamic deviation standard is S i,j (t)%, the allowable deviation threshold is ±δ j , the current offset is Q i,j (t)%.

[0103] In this way, feedback information is automatically generated through predefined semantic templates, converting technical data into highly readable guidance content, simplifying the user interpretation process and improving decision-making efficiency.

[0104] As an optional implementation, the method may further include:

[0105] A decision result is determined based on the measured data and the dynamic deviation tensor.

[0106] In this embodiment, determining a decision result based on the measured data and the dynamic deviation tensor may include:

[0107] For different stages of tobacco production, the comprehensive risk index of each production stage is determined based on the measured data and the dynamic deviation tensor:

[0108]

[0109] Where R i (t) represents the comprehensive risk index of the i-th production stage, K represents the number of indicators to be measured in the i-th production stage, β j represents the risk weight of the jth indicator to be measured, and tanh(·) is the hyperbolic tangent function;

[0110] Determining, based on the comprehensive risk index, a processing decision for each production stage as the decision result;

[0111] When the comprehensive risk index is less than a first preset risk threshold, the monitoring feedback information is sent to a designated terminal; when the comprehensive risk index is greater than or equal to the first preset risk threshold and less than a second preset risk threshold, a designated to-be-measured index is adjusted until the comprehensive risk index is less than the first preset risk threshold; and when the comprehensive risk index is greater than or equal to the second preset risk threshold, a shutdown instruction is triggered.

[0112] It can be understood that, in actual application, the output of the decision result can be non-single, for example, when the comprehensive risk index is greater than or equal to the second preset risk threshold, the monitoring feedback information can be sent to the designated terminal and the shutdown instruction can be triggered, and the specific execution mode of the decision result can be flexibly set according to user demand. Meanwhile, in order to quickly solve the risk that can occur in production and avoid the occurrence of production accidents, when the comprehensive risk index is greater than or equal to the first preset risk threshold, a prompt module (for example, a sound-light alarm, a display screen, a buzzer, etc.) connected with the electronic device 100 can send prompt information that the production equipment has a risk, so as to facilitate the user to timely understand the production situation.

[0113] In the embodiment, the first preset risk threshold and the second preset risk threshold can be flexibly set according to user demand, for example, 0.5, 1.0, 1.5, etc., and in the embodiment, the first preset risk threshold is 0.6 and the second preset risk threshold is 1.2.

[0114] The designated to-be-measured index in the embodiment can represent a to-be-measured index that contributes most to the deviation among all to-be-measured indexes in the same tobacco production stage. The calculation mode of the index is as follows:

[0115]

[0116] In the formula, i represents the designated to-be-measured index in the i th production stage.

[0117] Therefore, the decision result in the embodiment can be represented as:

[0118]

[0119] In the formula, Action i (t) represents the decision result of the i th production stage at t time.

[0120] In this way, through the hierarchical risk determination mechanism (early warning, parameter adjustment, shutdown), the risk is differentiated and processed, the production efficiency and safety are balanced, and excessive intervention or delay of key problems is avoided.

[0121] Based on the above technical solutions, the embodiment takes the wrapping stage (i = 2) as an example:

[0122] Input: M 2,3(t) = 88% (packaging sealing qualification rate), S 2,3 (t)=92%, δ3=5%, β3=0.4.

[0123] Update the initial dynamic deviation:

[0124] S 2,3 (t+1)=92%+0.2×(88%-92%)=91.2% (λ=0.2)

[0125] Then determine the deviation state parameters:

[0126] D 2,3 (t)=-1,A 2,3 (t)=1→Ψ 2,3 (t) = -1 (indicates negative deviation)

[0127] Then generate feedback information:

[0128]

[0129] F 2,3 (t)

[0130] ="The qualified rate of package sealing is negatively out of tolerance. The measured value is 88%, the dynamic deviation benchmark is 92%, and the allowable deviation threshold is

[0131] ±5%, current deviation is 80%"

[0132] Then calculate the comprehensive risk index of this production stage:

[0133]

[0134] Finally, the decision output is:

[0135] Since R2(t)=0.266<0.6, the feedback information only needs to be pushed to the designated terminal.

[0136] Please refer to Figure 3 The present application further provides a tobacco production monitoring system 300, which includes at least one software function module that can be stored in the form of software or firmware in the memory 102 or embedded in the operating system (OS) of the electronic device 100. The processor 101 is configured to execute the executable modules stored in the memory 102, such as the software function modules and computer programs included in the tobacco production monitoring system 300.

[0137] The tobacco production monitoring system 300 includes an acquisition unit 310, a first determination unit 320, a second determination unit 330, and a generation unit 340. The functions of each unit may be as follows:

[0138] An acquisition unit 310 is used to acquire measured data corresponding to different indicators to be measured at each stage of tobacco production;

[0139] A first determining unit 320 is configured to determine, based on the measured data, a dynamic deviation tensor representing the degree of deviation between the measured production state and the ideal production state at each stage of tobacco production at the current moment;

[0140] A second determining unit 330 is configured to determine a comprehensive deviation state parameter of the indicator to be measured based on the measured data and the dynamic deviation tensor and a preset deviation judgment strategy;

[0141] The generating unit 340 is configured to generate monitoring feedback information of the indicator to be measured based on the measured data, the dynamic deviation tensor and the comprehensive deviation state parameter.

[0142] Optionally, the acquiring unit 310 may also be configured to:

[0143] Acquire data obtained by detecting different indicators to be measured at each stage of tobacco production as initial measured data;

[0144] A data matrix is ​​constructed with the initial measured data as elements as the measured data, wherein the row data of the data matrix represent data of different tobacco production stages, and the column data of the data matrix represent data of different indicators.

[0145] Optionally, the first determining unit 320 may also be configured to:

[0146] Obtaining reference parameters that characterize ideal process parameters of the indicator to be measured;

[0147] The reference parameter is used as the initial dynamic deviation tensor, and the initial dynamic deviation is iteratively updated based on the time series to obtain the dynamic deviation tensor at the current moment. The iterative update of the initial dynamic deviation is expressed as follows:

[0148]

[0149] Where S i,j (t) represents the dynamic deviation tensor of the jth indicator to be measured in the i-th production stage of tobacco production at time t, λ represents the trainable learning rate, M i,j (h) represents the measured data of the jth indicator to be measured in the i-th production stage of tobacco production at time h.

[0150] Optionally, the second determining unit 330 may also be configured to:

[0151] Determine the deviation direction based on the measured data and the dynamic deviation tensor:

[0152] D i,j (t)=sign(M i,j (t)-S i,j (t))

[0153] Where D i,j (t) represents the deviation direction, sign(x) is the sign function, which outputs +1 when x>0, -1 when x<0, and 0 when x=0;

[0154] Determine the deviation amplitude based on the measured data and the dynamic deviation tensor:

[0155]

[0156] Where, δ j It represents the allowable deviation threshold of the j-th indicator, Θ(x) is a unit step function, which outputs 1 when x ≥ 0, otherwise it outputs 0;

[0157] Determine the comprehensive deviation state parameter according to the deviation direction and the deviation amplitude:

[0158] Ψ i,j (t) = D i,j (t)·A i,j (t)

[0159] Where, i,j (t) represents the comprehensive deviation state parameter.

[0160] Optionally, the generating unit 340 may also be configured to:

[0161] Fill the measured data, the dynamic deviation tensor and the comprehensive deviation state parameter into the semantic template to obtain the monitoring feedback information:

[0162] F i,j (t) = Γ i,j (Ψ i,j (t),M i,j (t),S i,j (t),δ j ,Q i,j (t))

[0163]

[0164] Where, Γ i,j (·) Generates functions for predefined texts.

[0165] Optionally, the tobacco production monitoring system 300 may further include a decision-making unit configured to:

[0166] A decision result is determined based on the measured data and the dynamic deviation tensor.

[0167] Optionally, the decision-making unit can also be used to:

[0168] For different stages of tobacco production, the comprehensive risk index of each production stage is determined based on the measured data and the dynamic deviation tensor:

[0169]

[0170] Where R i (t) represents the comprehensive risk index of the i-th production stage, K represents the number of indicators to be measured in the i-th production stage, β j represents the risk weight of the jth indicator to be measured, and tanh(·) is the hyperbolic tangent function;

[0171] Determine a processing decision for each production stage based on the comprehensive risk index as the decision result, the decision result including:

[0172] When the comprehensive risk index is less than a first preset risk threshold, the monitoring feedback information is sent to a designated terminal; when the comprehensive risk index is greater than or equal to the first preset risk threshold and less than a second preset risk threshold, the designated indicator to be measured is adjusted until the comprehensive risk index is less than the first preset risk threshold; when the comprehensive risk index is greater than or equal to the second preset risk threshold, a shutdown command is triggered.

[0173] It should be noted that those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the electronic device 100 described above can refer to the corresponding processes of each step in the aforementioned method, and will not be elaborated here.

[0174] The present application also provides a computer-readable storage medium that stores a computer program, which, when executed on a computer, causes the computer to execute the tobacco production monitoring method described in the above embodiment.

[0175] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented through hardware or by means of software plus a necessary general hardware platform. Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each implementation scenario of the present application.

[0176] In summary, the embodiment of the present application provides a tobacco production monitoring method, system, electronic device and storage medium. In the technical solution, first, the measured data corresponding to different to-be-measured indexes of each stage of tobacco production is obtained. Then, according to the measured data, a dynamic deviation tensor representing the deviation degree of the measured production state of each stage of tobacco production from the ideal production state at the current time is determined, and according to the measured data and the dynamic deviation tensor, a comprehensive deviation state parameter of the to-be-measured index is determined based on a preset deviation judgment strategy. Finally, according to the measured data, the dynamic deviation tensor and the comprehensive deviation state parameter, monitoring feedback information of the to-be-measured index is generated. In this way, by automatically collecting and comparing the deviation degree of the measured data and the calibrated ideal process parameters, corresponding monitoring feedback information is generated, the purpose of real-time monitoring of the quality of tobacco production is achieved, and the problems of high labor cost and low efficiency of the traditional tobacco production monitoring mode are improved.

[0177] In the embodiments provided in the present application, it should be understood that the disclosed system and method can also be implemented in other ways. The system and method embodiments described above are only illustrative. For example, the flowchart and block diagram in the drawings show the possible implementation architecture, function and operation of the system, method and computer program product according to the embodiments of the present application. In this regard, each block in the flowchart or block diagram can represent a module, a program segment or a part of code containing one or more executable instructions for implementing a specified logic function. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified function or action, or can be implemented by a combination of special-purpose hardware and computer instructions. In addition, the functional modules in each embodiment of the present application can be integrated together to form a separate part, or each module can exist independently, or two or more modules can be integrated to form a separate part.

[0178] The above only describes the embodiments of the present application and does not limit the protection scope of the present application. For those skilled in the art, the present application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A tobacco production monitoring method, characterized in that: The method comprises: Obtaining measured data corresponding to different indicators to be measured at each stage of tobacco production; Determining, based on the measured data, a dynamic deviation tensor representing the degree of deviation between the measured production state and the ideal production state at each stage of tobacco production at the current moment; Determine the comprehensive deviation state parameter of the indicator to be measured based on the measured data and the dynamic deviation tensor and a preset deviation judgment strategy; Monitoring feedback information of the indicator to be measured is generated according to the measured data, the dynamic deviation tensor and the comprehensive deviation state parameter.

2. The method according to claim 1, characterized in that Obtain measured data corresponding to different indicators to be measured at each stage of tobacco production, including: Acquire data obtained by detecting different indicators to be measured at each stage of tobacco production as initial measured data; A data matrix is ​​constructed with the initial measured data as elements as the measured data, wherein the row data of the data matrix represent data of different tobacco production stages, and the column data of the data matrix represent data of different indicators.

3. The method according to claim 1, characterized in that Determine, based on the measured data, a dynamic deviation tensor representing the degree of deviation between the measured production state and the ideal production state at each stage of tobacco production at the current moment, including: Obtaining reference parameters that characterize ideal process parameters of the indicator to be measured; The reference parameter is used as the initial dynamic deviation tensor, and the initial dynamic deviation is iteratively updated based on the time series to obtain the dynamic deviation tensor at the current moment. The iterative update of the initial dynamic deviation is expressed as follows: Where S i,j (t) represents the dynamic deviation tensor of the jth indicator to be measured in the i-th production stage of tobacco production at time t, λ represents the trainable learning rate, M i,j (h) represents the measured data of the jth indicator to be measured in the i-th production stage of tobacco production at time h.

4. The method according to claim 1, wherein According to the measured data and the dynamic deviation tensor, based on a preset deviation judgment strategy, a comprehensive deviation state parameter of the indicator to be measured is determined, including: Determine the deviation direction based on the measured data and the dynamic deviation tensor: D i,j (t)=sign(M i,j (t)-S i,j (t)) Where D i,j (t) represents the deviation direction, sign(x) is the sign function, which outputs +1 when x>0, -1 when x<0, and 0 when x=0; Determine the deviation amplitude based on the measured data and the dynamic deviation tensor: Where, δ j It represents the allowable deviation threshold of the j-th indicator, Θ(x) is a unit step function, which outputs 1 when x ≥ 0, otherwise it outputs 0; Determine the comprehensive deviation state parameter according to the deviation direction and the deviation amplitude: Ψ i,j (t)=D i,j (t)·A i,j (t) Where, i,j (t) represents the comprehensive deviation state parameter.

5. The method according to claim 1, wherein Generating monitoring feedback information of the indicator to be measured according to the measured data, the dynamic deviation tensor and the comprehensive deviation state parameter, including: Fill the measured data, the dynamic deviation tensor and the comprehensive deviation state parameter into the semantic template to obtain the monitoring feedback information: F i,j (t)=Γ i,j (Ψ i,j (t),M i,j (t),S i,j (t),δ j ,Q i,j (t)) Where, Γ i,j (·) Generates functions for predefined texts.

6. The method according to claim 1, characterized in that The method further comprises: A decision result is determined based on the measured data and the dynamic deviation tensor.

7. The method according to claim 6, characterized in that Determining a decision result based on the measured data and the dynamic deviation tensor includes: For different stages of tobacco production, the comprehensive risk index of each production stage is determined based on the measured data and the dynamic deviation tensor: Where R i (t) represents the comprehensive risk index of the i-th production stage, K represents the number of indicators to be measured in the i-th production stage, β j represents the risk weight of the jth indicator to be measured, and tanh(·) is the hyperbolic tangent function; Determining, based on the comprehensive risk index, a processing decision for each production stage as the decision result; Among them, when the comprehensive risk index is less than a first preset risk threshold, the monitoring feedback information is sent to a designated terminal; when the comprehensive risk index is greater than or equal to the first preset risk threshold and less than a second preset risk threshold, the designated indicator to be measured is adjusted until the comprehensive risk index is less than the first preset risk threshold; when the comprehensive risk index is greater than or equal to the second preset risk threshold, a shutdown command is triggered.

8. A tobacco production monitoring system, characterized in that: The system is used to implement the method according to any one of claims 1 to 7, and the system includes: An acquisition unit, used to acquire measured data corresponding to different indicators to be measured at each stage of tobacco production; A first determining unit is configured to determine, based on the measured data, a dynamic deviation tensor representing the degree of deviation between the measured production state and the ideal production state at each stage of tobacco production at a current moment; A second determining unit is configured to determine a comprehensive deviation state parameter of the indicator to be measured based on the measured data and the dynamic deviation tensor and a preset deviation judgment strategy; A generating unit is used to generate monitoring feedback information of the indicator to be measured based on the measured data, the dynamic deviation tensor and the comprehensive deviation state parameter.

9. An electronic device, characterized in that: The electronic device includes a processor and a memory coupled to each other, wherein a computer program is stored in the memory. When the computer program is executed by the processor, the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is run on a computer, the computer is caused to execute the method according to any one of claims 1 to 7.

Images