Weight detection parameter calibration method and device, computer equipment and storage medium

Abstract

The invention relates to a weight detection parameter calibration method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring weight detection microwave sensor data, cigarette making machine production process data and offline comprehensive test board data, and calculating the weight of the cigarette making machine according to the weight detection microwave sensor data, the cigarette making machine production process data and the offline comprehensive test board data through a pre-constructed statistical inference model. The method comprises the steps of generating statistics of to-be-calibrated weight detection parameters, determining a prediction parameter setting range and a parameter prediction value corresponding to each weight detection parameter according to probability distribution information of the statistics, and performing parameter diagnosis on each weight detection parameter according to the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter. Under the condition that any current parameter diagnosis result represents that calibration is needed, a corresponding prediction parameter setting range is sent to a cigarette making machine main control system for calibration. By adopting the method, the calibration timeliness rate and the calibration accuracy of the weight detection parameters are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of bale equipment detection, in particular to a weight detection parameter prediction method and device, computer equipment, computer readable storage medium and computer program product. BACKGROUND

[0002] In the current cigarette production process, cigarette weight online detection is an important detection device in the cigarette production process, and the detection calibration slope and weight correction are key parameters affecting detection accuracy. However, the instability of external environment such as brand replacement and tobacco structure change will cause the cigarette weight detection instrument to drift, linear change and other problems.

[0003] However, the existing weight detection mainly relies on the method of manpower abstraction to calibrate the weight detection parameters, and it is difficult to determine when the weight detection needs to be calibrated. That is, the existing weight detection parameter calibration method has the problem of low calibration timeliness. SUMMARY

[0004] Therefore, it is necessary to provide a weight detection parameter calibration method, device, computer equipment, computer readable storage medium and computer program product capable of improving calibration timeliness to solve the above technical problems.

[0005] In a first aspect, the present application provides a weight detection parameter calibration method, comprising:

[0006] In the cigarette production process, the weight detection microwave sensor data, cigarette machine production process data and offline comprehensive test bench data are obtained;

[0007] According to the weight detection microwave sensor data, the cigarette machine production process data and the offline comprehensive test bench data, a statistical quantity of the to-be-calibrated weight detection parameter is generated by a pre-constructed statistical inference model, and a prediction parameter setting range and a parameter prediction value corresponding to each weight detection parameter are determined according to the probability distribution information of the statistical quantity;

[0008] According to the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter, the parameter diagnosis of each weight detection parameter is performed;

[0009] In the case that the parameter diagnosis result of any current weight detection parameter indicates that calibration is needed, the prediction parameter setting range corresponding to the current weight detection parameter is sent to the cigarette machine main control system to automatically complete the calibration of the current weight detection parameter.

[0010] In one embodiment, according to the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter, the parameter diagnosis of each weight detection parameter comprises:

[0011] obtaining a standard parameter setting range and a parameter target value corresponding to each weight detection parameter;

[0012] performing parameter diagnosis on each weight detection parameter based on the standard parameter setting range, the parameter target value, the predicted parameter setting range, and the parameter prediction value corresponding to each weight detection parameter.

[0013] In one of the embodiments, in the case that the parameter diagnosis result of any one current weight detection parameter indicates that calibration is needed, the predicted parameter setting range is sent to the cigarette machine main control system, including:

[0014] In the case that the predicted parameter range corresponding to the current weight detection parameter is not within the corresponding standard parameter setting range, or the parameter prediction value corresponding to the current weight detection parameter is different from the corresponding parameter target value, it is determined that the parameter diagnosis result of the current weight detection parameter indicates that calibration is needed.

[0015] The standard parameter setting range, the predicted parameter setting range, and the parameter target value corresponding to the current weight detection parameter are sent to the cigarette machine main control system.

[0016] In one exemplary embodiment, the method further comprises:

[0017] In the case that the predicted parameter setting range corresponding to the current weight detection parameter is within the corresponding standard parameter setting range, and the parameter prediction value corresponding to the current weight detection parameter is the same as the corresponding parameter target value, it is determined that the parameter diagnosis result of the current weight detection parameter indicates that calibration is not needed.

[0018] In one embodiment, the method further comprises:

[0019] The parameter diagnosis result is sent to the cigarette machine through a TCP / IP communication mode; the cigarette machine is used to display the parameter diagnosis result through a man-machine interface.

[0020] In one of the embodiments, the weight detection microwave sensor data, the cigarette machine production process data, and the offline comprehensive test bench data are obtained, including:

[0021] In the cigarette production process, the original weight detection microwave sensor data, the original cigarette machine production process data, and the original offline comprehensive test bench data are obtained;

[0022] The abnormal data in the original weight detection microwave sensor data, the original cigarette machine production process data, and the original offline comprehensive test bench data are removed, and standardized processing is performed to obtain processed weight detection microwave sensor data, processed cigarette machine production process data, and processed offline comprehensive test bench data;

[0023] The weight detection microwave sensor data, the cigarette machine production process data and the offline comprehensive test bench data are time-synchronized based on the collection frequency of the processed cigarette machine production process data.

[0024] In a second aspect, the application further provides a weight detection parameter calibration device, comprising:

[0025] The weight detection microwave sensor data, the cigarette machine production process data and the offline comprehensive test bench data are acquired in the cigarette production process;

[0026] The prediction module is configured to generate a statistic of the weight detection parameter to be calibrated according to the weight detection microwave sensor data, the cigarette machine production process data and the offline comprehensive test bench data through a pre-constructed statistical inference model, and determine a prediction parameter setting range and a parameter prediction value corresponding to each weight detection parameter according to probability distribution information of the statistic.

[0027] The diagnosis module is configured to perform parameter diagnosis on each weight detection parameter according to the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter.

[0028] The calibration module is configured to send the prediction parameter setting range corresponding to the current weight detection parameter to the cigarette machine main control system to automatically complete calibration of the current weight detection parameter when the parameter diagnosis result of any one current weight detection parameter indicates that calibration is needed.

[0029] In a third aspect, the application further provides a computer device, comprising a memory and a processor, the memory storing a computer program, and the processor realizing the following steps when executing the computer program:

[0030] The weight detection microwave sensor data, the cigarette machine production process data and the offline comprehensive test bench data are acquired in the cigarette production process;

[0031] The prediction module is configured to generate a statistic of the weight detection parameter to be calibrated according to the weight detection microwave sensor data, the cigarette machine production process data and the offline comprehensive test bench data through a pre-constructed statistical inference model, and determine a prediction parameter setting range and a parameter prediction value corresponding to each weight detection parameter according to probability distribution information of the statistic.

[0032] The diagnosis module is configured to perform parameter diagnosis on each weight detection parameter according to the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter.

[0033] In the case that the parameter diagnosis result of any one current weight detection parameter indicates that calibration is needed, the prediction parameter setting range corresponding to the current weight detection parameter is sent to the cigarette machine main control system to automatically complete calibration of the current weight detection parameter.

[0034] In a fourth aspect, the present application also provides a computer readable storage medium having a computer program stored thereon, the computer program being executed by a processor to implement the following steps:

[0035] In the cigarette production process, weight detection microwave sensor data, cigarette machine production process data, and offline comprehensive test bench data are acquired.

[0036] Through a pre-constructed statistical inference model, statistical quantities of the weight detection parameters to be calibrated are generated according to the weight detection microwave sensor data, the cigarette machine production process data, and the offline comprehensive test bench data, and prediction parameter setting ranges and parameter prediction values corresponding to each weight detection parameter are determined according to probability distribution information of the statistical quantities.

[0037] Parameter diagnosis is performed on each weight detection parameter according to the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter.

[0038] In the case that the parameter diagnosis result of any one current weight detection parameter indicates that calibration is needed, the prediction parameter setting range corresponding to the current weight detection parameter is sent to the cigarette machine main control system to automatically complete calibration of the current weight detection parameter.

[0039] In a fifth aspect, the present application also provides a computer program product comprising a computer program, the computer program being executed by a processor to implement the following steps:

[0040] In the cigarette production process, weight detection microwave sensor data, cigarette machine production process data, and offline comprehensive test bench data are acquired.

[0041] Through a pre-constructed statistical inference model, statistical quantities of the weight detection parameters to be calibrated are generated according to the weight detection microwave sensor data, the cigarette machine production process data, and the offline comprehensive test bench data, and prediction parameter setting ranges and parameter prediction values corresponding to each weight detection parameter are determined according to probability distribution information of the statistical quantities.

[0042] Parameter diagnosis is performed on each weight detection parameter according to the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter.

[0043] In the case that the parameter diagnosis result of any one current weight detection parameter indicates that calibration is needed, the prediction parameter setting range corresponding to the current weight detection parameter is sent to the cigarette machine main control system to automatically complete calibration of the current weight detection parameter.

[0044] The weight detection parameter calibration method, device, computer equipment, computer readable storage medium and computer program product, in the cigarette production process, acquire the weight detection microwave sensor data, cigarette machine production process data and offline comprehensive test bench data, generate the statistics of the weight detection parameter to be calibrated through the statistical inference model constructed in advance according to the weight detection microwave sensor data, cigarette machine production process data and offline comprehensive test bench data, and determine the prediction parameter setting range and parameter prediction value corresponding to each weight detection parameter according to the probability distribution information of the statistics. According to the prediction parameter setting range and parameter prediction value corresponding to each weight detection parameter, the parameter diagnosis is performed on each weight detection parameter. In the case that the parameter diagnosis result of any current weight detection parameter represents the need for calibration, the prediction parameter setting range corresponding to the current weight detection parameter is sent to the cigarette machine main control system to automatically complete the calibration of the current weight detection parameter. The statistical inference model is used to realize the fusion of the collected multi-source data, and the probability distribution information of the statistics obtained by the fusion is used to obtain the prediction parameter setting range and parameter prediction value corresponding to each weight detection parameter. Finally, the prediction information is used for parameter diagnosis, and in the case that the parameter diagnosis result of the current weight detection parameter represents the need for calibration, the prediction parameter setting range corresponding to the current weight detection parameter is sent to the cigarette machine main control system to automatically calibrate the current weight detection parameter, thereby improving the calibration timeliness and calibration accuracy of the weight detection parameter. BRIEF DESCRIPTION OF DRAWINGS

[0045] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related art, the drawings needed to be used in the description of the embodiments of the present application or the related art will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other related drawings can be obtained by those skilled in the art without creative labor.

[0046] Figure 1 An application environment diagram of the weight detection parameter calibration method in an embodiment;

[0047] Figure 2 A flowchart of the weight detection parameter calibration method in an embodiment;

[0048] Figure 3 A flowchart of the weight detection parameter calibration method in another embodiment;

[0049] Figure 4 A structure diagram of a data acquisition and integration system in an embodiment;

[0050] Figure 5 A structure block diagram of the weight detection parameter calibration device in an embodiment;

[0051] Figure 6 Figure 1 is a schematic diagram of the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0052] For the purpose, technical solutions and advantages of the present application to be more clear, the present application is further described in detail below in combination with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0053] The weight detection parameter calibration method provided by the embodiments of the present application can be applied to the application environment as shown in Figure 1 The detection device 102 communicates with the offline comprehensive test bench and the cigarette machine host system through the switch, wherein the cigarette machine host system communicates with the weight detection microwave sensor and the quality detection system, and the cigarette machine host system can control and monitor the automatic production process of the device. The data storage system can store the data required to be processed by the detection device 102. The data storage system can be integrated on the detection device 102, or can be placed on the cloud or other network servers. In the cigarette production process, the detection device 102 acquires the weight detection microwave sensor data collected by the weight detection microwave sensor, the cigarette production process data collected by the cigarette machine host system, and the offline comprehensive test bench data collected by the offline comprehensive test bench, and generates a statistical quantity of the weight detection parameter to be calibrated according to the weight detection microwave sensor data, the cigarette production process data and the offline comprehensive test bench data through a pre-constructed statistical inference model, and determines the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter according to the probability distribution information of the statistical quantity, and performs parameter diagnosis on each weight detection parameter according to the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter. In the case that the parameter diagnosis result of any one current weight detection parameter represents the need for calibration, the detection device 102 sends the prediction parameter setting range corresponding to the current weight detection parameter to the cigarette machine host system to automatically complete the calibration of the current weight detection parameter. The detection device 102 can be an intelligent cigarette machine industrial computer.

[0054] In one exemplary embodiment, as shown in Figure 2 A weight detection parameter calibration method is provided, and the detection device 102 in Figure 1 is taken as an example to illustrate the method, which includes the following steps S201 to S204. Wherein:

[0055] Step S201, in the cigarette production process, acquiring weight detection microwave sensor data, cigarette production process data and offline comprehensive test bench data.

[0056] The weight detection microwave sensor data can be understood as change information of dielectric constant, and the dielectric constant can be understood as a measure of the ability of a material to store electrical energy in an electric field. Under the condition of known and fixed conditions (for example, container size, material type, and stable bulk density), the weight of the material is proportional to its volume and density. The density and moisture content of the material directly affect its dielectric constant. The cigarette machine production process data can be understood as various data collected during the production of cigarettes. The offline comprehensive test bench data can be understood as corresponding report data generated after the cigarette machine main control system inputs various analog measurement signals.

[0057] Exemplarily, in the cigarette production process, the detection equipment 102 obtains the cigarette machine production process data and the weight detection sensor data collected by the weight detection sensor from the cigarette machine main control system through the switch, and obtains the offline comprehensive test bench data from the offline comprehensive test bench through the switch.

[0058] In step S202, according to the weight detection microwave sensor data, the cigarette machine production process data, and the offline comprehensive test bench data, a statistical quantity of the weight detection parameter to be calibrated is generated by using a pre-constructed statistical inference model, and a prediction parameter setting range and a parameter prediction value corresponding to each weight detection parameter are determined according to probability distribution information of the statistical quantity.

[0059] The statistical quantity can be understood as a change chart of the numerical value of the weight detection parameter to be calibrated changing over time, the probability distribution information can be understood as the distribution of the weight detection parameter to be calibrated at each numerical value, the prediction parameter setting range can be understood as the numerical value range in which the weight detection parameter should be predicted, and the parameter prediction value can be understood as the best parameter selected value in this range.

[0060] Optionally, the detection equipment 102 constructs a statistical quantity of the weight detection parameter to be calibrated according to the weight detection microwave sensor data, the cigarette machine production process data, and the offline comprehensive test bench data by using a pre-constructed statistical inference model, and predicts the parameter setting range and the parameter value according to the probability distribution information of each weight detection parameter to be calibrated in the statistical quantity, to determine a prediction parameter setting range and a parameter prediction value corresponding to each weight detection parameter.

[0061] In step S203, according to the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter, a parameter diagnosis is performed on each weight detection parameter.

[0062] The parameter diagnosis can be a diagnosis process of whether the weight detection parameter can ensure that the cigarette production meets the quality standard.

[0063] Optionally, the standard parameter setting range and the parameter target value corresponding to each weight detection parameter are acquired, it is judged whether the prediction parameter setting range corresponding to each weight detection parameter is completely attributed to the standard parameter setting range corresponding to each weight detection parameter, and it is judged whether the parameter prediction value corresponding to each weight detection parameter is equal to the parameter target value corresponding to each weight detection parameter.

[0064] In step S204, in the case that the parameter diagnosis result of any one current weight detection parameter indicates that calibration is needed, the prediction parameter setting range corresponding to the current weight detection parameter is sent to the cigarette machine main control system to automatically complete calibration of the current weight detection parameter.

[0065] For example, in the case that the parameter diagnosis result of any one current weight detection parameter indicates that calibration is needed, i.e. the prediction parameter setting range corresponding to the current weight detection parameter is not within the standard parameter setting range corresponding to the current weight detection parameter, or the parameter prediction value corresponding to the current weight detection parameter is not equal to the parameter target value corresponding to the current weight detection parameter, the prediction parameter setting range, the standard parameter setting range and the parameter target value corresponding to the current weight detection parameter are sent to the cigarette machine main control system to automatically complete calibration of the current weight detection parameter.

[0066] In the above weight detection parameter calibration method, in the cigarette production process, weight detection microwave sensor data, cigarette machine production process data and offline comprehensive test bench data are acquired, a statistical inference model is constructed in advance, the statistical inference model is used to generate a statistic of a weight detection parameter to be calibrated according to the weight detection microwave sensor data, the cigarette machine production process data and the offline comprehensive test bench data, the probability distribution information of the statistic is determined according to the statistic, the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter are determined according to the probability distribution information of the statistic, parameter diagnosis is performed on each weight detection parameter, in the case that the parameter diagnosis result of any one current weight detection parameter indicates that calibration is needed, the prediction parameter setting range corresponding to the current weight detection parameter is sent to the cigarette machine main control system to automatically complete calibration of the current weight detection parameter. The statistical inference model is used to realize fusion of the collected multi-source data, the probability distribution information of the statistic obtained by fusion is used to obtain the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter, finally, the prediction information is used for parameter diagnosis, and in the case that the parameter diagnosis result of the current weight detection parameter indicates that calibration is needed, the prediction parameter setting range corresponding to the current weight detection parameter is sent to the cigarette machine main control system to automatically complete calibration of the current weight detection parameter, thereby improving the calibration timeliness and calibration accuracy of the weight detection parameter.

[0067] In one embodiment, the parameter diagnosis of each weight detection parameter is performed according to the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter, including: obtaining the standard parameter setting range and the parameter target value corresponding to each weight detection parameter; performing the parameter diagnosis of each weight detection parameter based on the standard parameter setting range, the parameter target value, the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter.

[0068] The standard parameter setting range can be understood as a value range of the weight detection parameter meeting the quality standard of cigarette production, and the parameter target value can be understood as an optimal value of the weight detection parameter when the quality of the cigarette production reaches the best in the standard parameter setting range.

[0069] Optionally, the detection device 102 obtains the standard parameter setting range and the parameter target value corresponding to each weight detection parameter, judges whether the prediction parameter setting range corresponding to each weight detection parameter is in the standard parameter setting range corresponding to each weight detection parameter, and whether the parameter prediction value corresponding to each weight detection parameter is equal to the parameter target value corresponding to each weight detection parameter.

[0070] Based on the foregoing embodiments, by comparing the prediction setting range with the standard setting range, and comparing the parameter prediction value with the parameter target value, the deviation trend can be quickly found, and the timeliness and accuracy of online parameter adjustment are improved.

[0071] In one embodiment, in the case that the parameter diagnosis result of any one of the current weight detection parameters indicates that calibration is needed, the prediction parameter setting range is sent to the cigarette machine main control system, including: in the case that the prediction parameter range corresponding to the current weight detection parameter is not in the corresponding standard parameter setting range, or the parameter prediction value corresponding to the current weight detection parameter is different from the corresponding parameter target value, it is determined that the parameter diagnosis result of the current weight detection parameter indicates that calibration is needed; the standard parameter setting range, the prediction parameter setting range and the parameter target value corresponding to the current weight detection parameter are sent to the cigarette machine main control system.

[0072] The cigarette machine main control system can be understood as a core control unit of the cigarette machine production line.

[0073] Exemplarily, in the case that the prediction parameter range corresponding to the current weight detection parameter is not within the standard parameter setting range (including the case that the end value is within the range or not), or the parameter prediction value of the current weight detection parameter is different from the parameter target value corresponding thereto, the parameter diagnostic result represented by any of the aforementioned conditions, the detection device 102 determines that the parameter diagnostic result of the current weight detection parameter represents the need for calibration, and sends the standard parameter setting range, the prediction parameter setting range and the parameter target value corresponding to the current weight detection parameter to the cigarette machine main control system to automatically complete the calibration of the current weight detection parameter.

[0074] According to the above-mentioned embodiment, the full-automatic process from diagnosis to execution reduces manual intervention, improves response speed and consistency, and reduces the impact of long-term deviation and drift on production line quality by directly driving parameter calibration of the prediction parameter and target difference that does not meet the standard range.

[0075] In an exemplary embodiment, the method further comprises: in the case that the prediction parameter setting range corresponding to the current weight detection parameter is within the corresponding standard parameter setting range, and the parameter prediction value corresponding to the current weight detection parameter is the same as the parameter target value corresponding thereto, determining that the parameter diagnostic result of the current weight detection parameter represents the need for calibration.

[0076] Optionally, in the case that the prediction parameter setting range corresponding to the current weight detection parameter is within the corresponding standard parameter setting range, and the parameter prediction value corresponding to the current weight detection parameter is the same as the parameter target value corresponding thereto, the detection device 102 determines that the parameter diagnostic result of the current weight detection parameter represents the need for calibration, and returns to continue real-time acquisition of multi-source data, realizing real-time parameter prediction diagnosis and parameter calibration for the weight detection parameter.

[0077] Based on the foregoing embodiments, in the case that calibration is not needed, the system continues to perform real-time acquisition, feature extraction and prediction diagnosis of multi-source data at a high frequency, ensuring seamless monitoring of the production process, and further ensuring the continuity of quality assurance in the production phase.

[0078] In an embodiment, the method further comprises: sending the parameter diagnostic result to the cigarette machine through a TCP / IP communication mode; and the cigarette machine is configured to display the parameter diagnostic result through a man-machine interface.

[0079] The TCP / IP communication mode can be understood as a set of communication protocols, which can include several layers of protocol composition and cover the communication process from application to physical layer.

[0080] Exemplarily, the detection device 102 sends the parameter diagnosis results of each weight detection parameter to the cigarette making machine through a TCP / IP communication mode, and the cigarette making machine displays the parameter diagnosis results to the operator through a man-machine interface, thereby ensuring the transparency of the parameter prediction diagnosis process and facilitating the operator to perform auxiliary operations of parameter calibration in a timely manner according to the parameter diagnosis results, so as to ensure the quality of cigarette production.

[0081] In one of the embodiments, the weight detection microwave sensor data, the cigarette making machine production process data and the offline comprehensive test bench data are acquired, including: acquiring original weight detection microwave sensor data, original cigarette making machine production process data and original offline comprehensive test bench data in the cigarette production process; removing abnormal data in the original weight detection microwave sensor data, the original cigarette making machine production process data and the original offline comprehensive test bench data, and performing standardization processing to obtain processed weight detection microwave sensor data, processed cigarette making machine production process data and processed offline comprehensive test bench data; and performing time synchronization on the processed cigarette making machine production process data and the processed offline comprehensive test bench data based on the acquisition frequency of the processed cigarette making machine production process data, to obtain the weight detection microwave sensor data, the cigarette making machine production process data and the offline comprehensive test bench data.

[0082] Optionally, in the cigarette production process, the detection device 102 acquires original weight detection microwave sensor data from the weight detection microwave sensor, original cigarette making machine production process data from the cigarette making machine master control system, and original offline comprehensive test bench data from the offline comprehensive test bench, and then removes abnormal data in the original weight detection microwave sensor data, the original cigarette making machine production process data and the original offline comprehensive test bench data, and performs a series of standardization processing such as format unification, to obtain processed weight detection microwave sensor data, processed cigarette making machine production process data and processed offline comprehensive test bench data, and finally performs time synchronization on the processed cigarette making machine production process data and the processed offline comprehensive test bench data based on the acquisition frequency of the processed cigarette making machine production process data, to obtain the weight detection microwave sensor data, the cigarette making machine production process data and the offline comprehensive test bench data.

[0083] According to the above embodiments, by performing abnormal data removal on the original multi-source data, the effectiveness and usability of the data are improved, and at the same time, the data standardization processing is also performed, thereby accelerating the data coupling progress. Based on the acquisition frequency of the cigarette making machine production process data, the timestamps of the offline test bench data are coordinated and aligned, so as to facilitate synchronous sampling and comparative analysis. Through the foregoing data preprocessing means, the coupling analysis on the multi-source data is accelerated, thereby ensuring the timeliness of the weight detection parameter prediction diagnosis and parameter calibration, and realizing the effective improvement of the quality of cigarette production.

[0084] In one exemplary embodiment, as shown in Figure 3 A specific implementation of a weight detection parameter calibration method is provided. It mainly consists of three parts: multi-source data acquisition and processing system, weight detection calibration parameter diagnosis and prediction system, alarm output and parameter self-adjusting system. The system operation process is as follows:

[0085] I. Multi-source data acquisition and processing:

[0086] Based on the intelligent cigarette machine system (TIMS, Tobacco Intelligent Machine System); the system structure is as follows Figure 4 The TIMS system integrates the weight detection microwave sensor, cigarette machine production process data and offline comprehensive test bench data through the switch; the weight detection microwave sensor and the cigarette machine main control system communicate through the EtherCat bus to collect and align data, and the offline comprehensive test bench data and the cigarette machine production data are aligned and synchronized through time synchronization.

[0087] II. Weight detection calibration parameter diagnosis and prediction system:

[0088] The parameter diagnosis and prediction system uses a statistical inference model. After data processing, the statistical quantity of the to-be-calibrated parameter is constructed, the statistical distribution is inferred, and the parameter setting range and estimated value are predicted using statistical estimation methods. Through experimental testing, the parameter prediction accuracy is more than 95%. After a certain number of cigarettes are produced, the system can diagnose and predict calibration and output the determination result and parameter setting value.

[0089] III. Parameter output system:

[0090] The weight detection calibration parameter diagnosis and prediction system output is connected to the cigarette machine MLP (human-machine interface) using TCP / IP communication. When receiving the modification of the weight detection calibration parameter, the automatic weight detection diagnosis modifies the parameter and sends it to the IPC program.

[0091] The overall system is installed on the intelligent cigarette machine system (TIMS). After the application installation is completed, the system program is started, and after the cigarette machine production, the multi-source data acquisition and processing system starts to work, real-time acquisition of weight detection microwave sensor, cigarette machine production process data and offline comprehensive test bench data is completed, and then the processed data is transmitted to the weight detection calibration parameter diagnosis and prediction system to determine whether the current weight detection parameter needs to be modified. If it needs to be modified, it is sent to the cigarette machine main control system through the interface to automatically modify the parameter and complete the weight online detection calibration.

[0092] Compared with the prior art, the present application has the following technical advantages:

[0093] 1. Time synchronization and alignment of multi-source data ensures consistency in parameter diagnosis and prediction over time, improving the response speed and accuracy of online parameter tuning.

[0094] 2. By collecting data from different sources and coupling the multi-source data, a set of statistical quantities for the weight detection parameters to be calibrated is obtained. Based on the probability distribution information of the statistical quantities, information prediction for each weight detection parameter is achieved, thereby improving the accuracy of the prediction information. This helps with subsequent parameter diagnosis and calibration, and ultimately ensures the production quality of cigarettes.

[0095] 3. Fully automated parameter diagnosis and calibration avoid the problems of low frequency of manual calibration and the manpower and cigarette consumption caused by manual monitoring and testing. This further ensures the stability of product quality.

[0096] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0097] Based on the same inventive concept, this application also provides a weight detection parameter calibration device for implementing the weight detection parameter calibration method described above. The solution provided by this device is similar to the implementation described in the above method; therefore, the specific limitations in one or more weight detection parameter calibration device embodiments provided below can be found in the limitations of the weight detection parameter calibration method described above, and will not be repeated here.

[0098] In one exemplary embodiment, such as Figure 5 As shown, a weight detection parameter calibration device is provided, including: an acquisition module 501, a prediction module 502, a diagnosis module 503, and a calibration module 504, wherein:

[0099] The acquisition module 501 is used to acquire data from the weight detection microwave sensor, the cigarette machine production process data, and the offline integrated test bench data during the cigarette production process.

[0100] The prediction module 502 is configured to generate a statistical quantity of the weight detection parameter to be calibrated according to the weight detection microwave sensor data, the cigarette machine production process data and the offline comprehensive test bench data by using a pre-constructed statistical inference model, and determine a prediction parameter setting range and a parameter prediction value corresponding to each weight detection parameter according to probability distribution information of the statistical quantity.

[0101] The diagnosis module 503 is configured to perform parameter diagnosis on each weight detection parameter according to the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter.

[0102] The calibration module 504 is configured to send the prediction parameter setting range corresponding to the current weight detection parameter to the cigarette machine main control system to automatically complete calibration of the current weight detection parameter in a case where the parameter diagnosis result of the current weight detection parameter indicates that calibration is needed.

[0103] In one embodiment, the diagnosis module 503 is further configured to acquire a standard parameter setting range and a parameter target value corresponding to each weight detection parameter, and perform parameter diagnosis on each weight detection parameter based on the standard parameter setting range, the parameter target value, the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter.

[0104] In one embodiment, the calibration module 504 is further configured to determine that the parameter diagnosis result of the current weight detection parameter indicates that calibration is needed in a case where the prediction parameter range corresponding to the current weight detection parameter is not within the corresponding standard parameter setting range, or the parameter prediction value corresponding to the current weight detection parameter is different from the corresponding parameter target value, and send the standard parameter setting range, the prediction parameter setting range and the parameter target value corresponding to the current weight detection parameter to the cigarette machine main control system.

[0105] In one exemplary embodiment, the weight detection parameter calibration apparatus is further configured to determine that the parameter diagnosis result of the current weight detection parameter indicates that calibration is not needed in a case where the prediction parameter setting range corresponding to the current weight detection parameter is within the corresponding standard parameter setting range, and the parameter prediction value corresponding to the current weight detection parameter is the same as the corresponding parameter target value.

[0106] In one embodiment, the weight detection parameter calibration apparatus is further configured to send the parameter diagnosis result to the cigarette machine through a TCP / IP communication mode, and the cigarette machine is configured to display the parameter diagnosis result through a man-machine interface.

[0107] In one embodiment, the acquisition module 501 is further configured to acquire, during the cigarette production process, raw weight detection microwave sensor data, raw cigarette machine production process data, and raw offline integrated test bench data; remove abnormal data from the raw weight detection microwave sensor data, raw cigarette machine production process data, and raw offline integrated test bench data, and perform standardization processing to obtain processed weight detection microwave sensor data, processed cigarette machine production process data, and processed offline integrated test bench data; and synchronize the processed cigarette machine production process data and processed offline integrated test bench data in time based on the acquisition frequency of the processed cigarette machine production process data to obtain weight detection microwave sensor data, cigarette machine production process data, and offline integrated test bench data.

[0108] Each module in the aforementioned weight detection parameter calibration device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in the processor of a computer device in hardware form or independent of it, or stored in the memory of a computer device in software form, so that the processor can call and execute the corresponding operations of each module.

[0109] In one exemplary embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, input / output (I / O) interfaces, and a communication interface. The processor, memory, and I / O interfaces are connected via a system bus, and the communication interface is also connected to the system bus via the I / O interfaces. The processor provides computational and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides the environment for the operating system and computer programs stored in the non-volatile storage media. The database stores data from microwave sensors for weight detection, data from the cigarette machine production process, data from the offline integrated testing platform, the predicted parameter setting ranges and predicted values ​​for each weight detection parameter, and parameter diagnostic results. The I / O interfaces are used for information exchange between the processor and external devices. The communication interface is used for communication with external terminals via a network connection. When executed by the processor, the computer program implements a weight detection parameter calibration method.

[0110] Those skilled in the art will understand that Figure 6The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0111] In one exemplary embodiment, a computer device is provided, including a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the weight detection parameter calibration method of the above-mentioned embodiments.

[0112] In one embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program is executed by a processor to implement the weight detection parameter calibration method of the above-mentioned embodiments.

[0113] In one embodiment, a computer program product is provided, including a computer program, and the computer program is executed by a processor to implement the weight detection parameter calibration method of the above-mentioned embodiments.

[0114] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant regulations.

[0115] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile memory and volatile memory. The non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. The volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, the RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, an artificial intelligence (AI) processor, etc., without being limited thereto.

[0116] The technical features of the above embodiments can be combined in any manner. To make the description concise, not all possible combinations of the technical features in the above embodiments are described, but as long as the combinations of the technical features do not exist contradictions, they should be considered as the scope of the present application.

[0117] The above-described embodiments are merely illustrative of several embodiments of the present application, which are described in more detail and in a specific manner, but should not be construed as limiting the scope of the patent of the present application. It should be noted that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A method for calibrating weight detection parameters, characterized in that, The method comprises: In the cigarette production process, the weight detection microwave sensor data, the cigarette machine production process data and the offline comprehensive test bench data are acquired; Through a pre-constructed statistical inference model, a statistical quantity of a weight detection parameter to be calibrated is generated according to the weight detection microwave sensor data, the cigarette machine production process data and the offline comprehensive test bench data, and a prediction parameter setting range and a parameter prediction value corresponding to each weight detection parameter are determined according to probability distribution information of the statistical quantity; Parameter diagnosis is performed on each weight detection parameter according to the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter; In the case that the parameter diagnosis result of any current weight detection parameter indicates that calibration is needed, the prediction parameter setting range corresponding to the current weight detection parameter is sent to the cigarette machine main control system to automatically complete calibration of the current weight detection parameter.

2. The method of claim 1, wherein, The parameter diagnosis performed on each weight detection parameter according to the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter comprises: The standard parameter setting range and the parameter target value corresponding to each weight detection parameter are acquired; Parameter diagnosis is performed on each weight detection parameter based on the standard parameter setting range, the parameter target value, the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter.

3. The method of claim 2, wherein, The sending of the prediction parameter setting range to the cigarette machine main control system in the case that the parameter diagnosis result of any current weight detection parameter indicates that calibration is needed comprises: In the case that the prediction parameter range corresponding to the current weight detection parameter is not within the corresponding standard parameter setting range, or the parameter prediction value corresponding to the current weight detection parameter is different from the corresponding parameter target value, it is determined that the parameter diagnosis result of the current weight detection parameter indicates that calibration is needed; The standard parameter setting range, the prediction parameter setting range and the parameter target value corresponding to the current weight detection parameter are sent to the cigarette machine main control system.

4. The method of claim 3, wherein, The method further comprises: In the case that the prediction parameter setting range corresponding to the current weight detection parameter is within the corresponding standard parameter setting range, and the parameter prediction value corresponding to the current weight detection parameter is the same as the corresponding parameter target value, it is determined that the parameter diagnosis result of the current weight detection parameter indicates that calibration is not needed.

5. The method according to any one of claims 1 to 4, characterized in that, The method further comprises: The parameter diagnosis result is sent to the cigarette machine through a TCP / IP communication mode; the cigarette machine is configured to display the parameter diagnosis result through a man-machine interface.

6. The method of claim 1, wherein, The acquisition of the weight detection microwave sensor data, the cigarette machine production process data and the offline comprehensive test bench data comprises: In the cigarette production process, the original weight detection microwave sensor data, the original cigarette machine production process data and the original offline comprehensive test bench data are acquired; Remove the original weight detection microwave sensor data, original cigarette machine production process data and original offline comprehensive test platform data of abnormal data, and standardize to obtain the processed weight detection microwave sensor data, processed cigarette machine production process data and processed offline comprehensive test platform data; Based on the acquisition frequency of the processed cigarette machine production process data, the processed cigarette machine production process data and the processed offline comprehensive test platform data are time synchronized to obtain the weight detection microwave sensor data, the cigarette machine production process data and the offline comprehensive test platform data.

7. A weight detection parameter calibration apparatus, characterized by, The device comprises: An acquisition module is configured to acquire weight detection microwave sensor data, cigarette machine production process data and offline comprehensive test platform data during a cigarette production process; A prediction module is configured to generate a statistical quantity of a to-be-calibrated weight detection parameter according to the weight detection microwave sensor data, the cigarette machine production process data and the offline comprehensive test platform data by using a pre-constructed statistical inference model, and determine a prediction parameter setting range and a parameter prediction value corresponding to each weight detection parameter according to probability distribution information of the statistical quantity; A diagnosis module is configured to perform parameter diagnosis on each weight detection parameter according to the prediction parameter setting range and the parameter prediction value corresponding to each weight detection parameter; A calibration module is configured to send a prediction parameter setting range corresponding to a current weight detection parameter to a cigarette machine main control system to automatically complete calibration of the current weight detection parameter when a parameter diagnosis result of the current weight detection parameter indicates that calibration is needed.

8. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that, The processor executes the computer program to implement the steps of the method of any one of claims 1 to 6.

9. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

10. A computer program product comprising a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Images