Cigarette making machine equipment health evaluation method, device, equipment and medium

Abstract

The invention discloses a cigarette making machine equipment health evaluation method and device, equipment and a medium. The method comprises the following steps: fitting a subsystem health degree index calculation model, a shutdown health degree index calculation model and a consumption health degree index calculation model based on cigarette making machine equipment health degree evaluation sample data, a regression model and an analytic hierarchy process; obtaining health degree evaluation associated data of the current cigarette making machine; determining an index layer vector according to the health degree evaluation associated data, a subsystem health degree index calculation model, a shutdown health degree index calculation model and a consumption health degree index calculation model; and determining a criterion layer judgment matrix, and determining a health degree evaluation result of the cigarette making machine equipment according to the criterion layer judgment matrix and the index layer vector. According to the technical scheme, the accuracy of the health evaluation result of the cigarette making machine equipment can be effectively improved, and the troubleshooting efficiency and timeliness are greatly improved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment health evaluation, and in particular to a method, device, equipment and medium for evaluating the health of cigarette making machine equipment. Background Art

[0002] In the field of tobacco manufacturing, the cigarette rolling machine is an important equipment in the cigarette production process. During its operation, the equipment health evaluation system is crucial.

[0003] At present, the preventive maintenance management system is generally adopted to carry out regular maintenance of all equipment. There is a lack of in-depth analysis of the failure characteristics of each component of the equipment, resulting in numerous and inaccurate maintenance tasks and the risk of over-maintenance. Post-fault responsive maintenance has a serious impact on equipment spare parts management and production planning, reducing production efficiency. The equipment status perception and health assessment system is imperfect, making it difficult to discover potential hidden dangers during daily inspections, affecting the judgment and decision-making ability of operating and maintenance personnel. The equipment operation status data has not been effectively transmitted to the relevant responsible persons, and maintenance personnel and managers lack the necessary data support when making decisions, which restricts the timeliness of problem solving and management efficiency, resulting in insufficient data-driven decision-making application capabilities. Summary of the invention

[0004] The present invention provides a cigarette making machine equipment health evaluation method, device, equipment and medium, which can solve the problems of poor timeliness and low troubleshooting efficiency in existing troubleshooting based on cigarette making machine equipment health evaluation results.

[0005] According to one aspect of the present invention, a method for evaluating the health of a cigarette making machine is provided, comprising:

[0006] Based on the sample data of cigarette machine equipment health evaluation, regression model and hierarchical analysis method, the subsystem health index calculation model, shutdown health index calculation model and consumption health index calculation model are fitted;

[0007] Obtain the health evaluation related data of the current cigarette making machine;

[0008] Determine the indicator layer vector according to the health evaluation related data, the subsystem health index calculation model, the shutdown health index calculation model and the consumption health index calculation model;

[0009] Determine the criterion layer judgment matrix, and determine the cigarette machine equipment health evaluation result based on the criterion layer judgment matrix and the indicator layer vector.

[0010] According to another aspect of the present invention, a device for evaluating the health of a cigarette making machine is provided, comprising:

[0011] The calculation model fitting module is used to fit the subsystem health index calculation model, the shutdown health index calculation model and the consumption health index calculation model based on the cigarette machine equipment health evaluation sample data, regression model and hierarchical analysis method;

[0012] A data acquisition module is used to acquire health evaluation related data of the current cigarette making machine;

[0013] An indicator layer vector determination module is used to determine the indicator layer vector according to the health evaluation associated data, the subsystem health index calculation model, the shutdown health index calculation model and the consumption health index calculation model;

[0014] The equipment health evaluation determination module is used to determine the criterion layer judgment matrix, and determine the cigarette machine equipment health evaluation result according to the criterion layer judgment matrix and the indicator layer vector.

[0015] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0016] at least one processor; and

[0017] a memory communicatively connected to the at least one processor; wherein,

[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the cigarette making machine equipment health assessment method described in any embodiment of the present invention.

[0019] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, wherein the computer instructions are used to enable a processor to implement the cigarette making machine equipment health evaluation method described in any embodiment of the present invention when executed.

[0020] The technical solution of the embodiment of the present invention is to fit the subsystem health index calculation model, the downtime health index calculation model and the consumption health index calculation model based on the cigarette machine equipment health evaluation sample data, regression model and hierarchical analysis method, so as to obtain the health evaluation related data of the current cigarette machine, and then determine the index layer vector and the criterion layer judgment matrix according to the health evaluation related data, the subsystem health index calculation model, the downtime health index calculation model and the consumption health index calculation model, and determine the cigarette machine equipment health evaluation result according to the criterion layer judgment matrix and the index layer vector. In this solution, the hierarchical analysis method is used to split the equipment health evaluation into consumption health, downtime health and subsystem health, strengthen the mining and utilization of existing equipment data and process data, improve the health evaluation system of cigarette machine equipment, solve the problems of poor timeliness and low troubleshooting efficiency in the existing troubleshooting based on the health evaluation results of cigarette machine equipment, and effectively improve the accuracy of the health evaluation results of cigarette machine equipment, and greatly improve the troubleshooting efficiency and timeliness.

[0021] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0023] Figure 1 A flowchart of a method for evaluating the health of a cigarette making machine provided in Example 1 of the present invention;

[0024] Figure 2 A flowchart of a method for evaluating the health of a cigarette making machine provided in Embodiment 2 of the present invention;

[0025] Figure 3 A schematic diagram of a flow chart for determining a healthy function of a feed strip provided in the second embodiment of the present invention;

[0026] Figure 4 A schematic diagram of a process for determining a curling forming health function provided in the second embodiment of the present invention;

[0027] Figure 5 Schematic diagram of the process of determining the filter tip installation health function provided in the second embodiment of the present invention

[0028] Figure 6A schematic diagram of the structure of a cigarette making machine equipment health evaluation device provided in Embodiment 3 of the present invention;

[0029] Figure 7 A schematic diagram of the structure of an electronic device that can be used to implement an embodiment of the present invention is shown. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0032] Embodiment 1

[0033] Figure 1 This is a flowchart of a method for evaluating the health of a cigarette making machine provided in the first embodiment of the present invention. This embodiment can be applied to the case of improving the troubleshooting efficiency of cigarette making machine equipment. The method can be executed by a health evaluation device for cigarette making machine equipment. The health evaluation device for cigarette making machine equipment can be implemented in the form of hardware and / or software. The health evaluation device for cigarette making machine equipment can be configured in an electronic device. Figure 1 As shown, the method includes:

[0034] Step 110: Based on the cigarette machine equipment health evaluation sample data, regression model and hierarchical analysis method, a subsystem health index calculation model, a shutdown health index calculation model and a consumption health index calculation model are fitted.

[0035] Among them, the sample data for evaluating the health of cigarette making machine equipment can be used to train a model for calculating the health of cigarette making machines, and can be sample data selected from existing cigarette making machine equipment data and process data. The subsystem health index calculation model can be a model for calculating the comprehensive health of key subsystems and external sensors of cigarette making machine equipment. Optionally, key subsystems may include but are not limited to a feeding and strip forming subsystem, a rolling and forming subsystem, and a filter tip installation subsystem. The subsystem in the text is a general term for key subsystems and external sensors. The shutdown health index calculation model can be a model for calculating the shutdown health of a cigarette making machine. The shutdown health can be an indicator for evaluating the health status of the equipment based on the shutdown situation of the cigarette making machine. The consumption health index calculation model can be a model based on calculating the consumption health of a cigarette making machine. The consumption health of a cigarette making machine can be based on the scrap rate data of the cigarette making machine to judge the health of the cigarette making machine.

[0036] In an embodiment of the present invention, the subsystem health, downtime health and consumption health can be used as dimensions for evaluating the equipment health of a cigarette making machine, and then the analytic hierarchy process is used to perform weight measurement on the above three healths based on the sample data of the equipment health evaluation of the cigarette making machine, and the calculation model is further fitted through a regression model to obtain the subsystem health index calculation model, the downtime health index calculation model and the consumption health index calculation model.

[0037] Step 120: Obtain health evaluation related data of the current cigarette making machine.

[0038] Among them, the health evaluation associated data can be used as relevant equipment data for evaluating the equipment health of the current cigarette making machine.

[0039] In an embodiment of the present invention, the operation-related data of the original equipment components of the current cigarette making machine can be collected through the data collection component, and the operation-related data of the original equipment components of the current cigarette making machine can be combined with the data collected by the external sensors of the current cigarette making machine to form health evaluation related data.

[0040] Step 130: Determine the indicator layer vector according to the health evaluation associated data, the subsystem health index calculation model, the shutdown health index calculation model and the consumption health index calculation model.

[0041] Among them, the indicator layer vector can be used to store the corresponding weights of the device health evaluation dimensions.

[0042] In an embodiment of the present invention, the data related to the subsystem health, shutdown health and consumption health in the health evaluation associated data can be input into the subsystem health index calculation model, the shutdown health index calculation model and the consumption health index calculation model in sequence to obtain the indicator layer vectors of different equipment health evaluation dimensions.

[0043] Step 140: determine the criterion layer judgment matrix, and determine the cigarette machine equipment health evaluation result according to the criterion layer judgment matrix and the indicator layer vector.

[0044] The criterion layer judgment matrix can be a criterion layer judgment matrix determined by using the hierarchical analysis method and health evaluation related data. The cigarette machine equipment health evaluation result can be used to describe the evaluation result of the current health status of the cigarette machine.

[0045] In an embodiment of the present invention, the analytic hierarchy process can be used to determine the judgment matrix of the criterion layer constructed in the analytic hierarchy process, that is, the criterion layer judgment matrix, based on the health evaluation related data. Then, based on the criterion layer judgment matrix and the indicator layer vector, the synthetic weight of each layer element to the target layer is calculated and sorted to obtain the health evaluation result of the cigarette making machine equipment.

[0046] The technical solution of the embodiment of the present invention is to fit the subsystem health index calculation model, the downtime health index calculation model and the consumption health index calculation model based on the cigarette machine equipment health evaluation sample data, regression model and hierarchical analysis method, so as to obtain the health evaluation related data of the current cigarette machine, and then determine the index layer vector and the criterion layer judgment matrix according to the health evaluation related data, the subsystem health index calculation model, the downtime health index calculation model and the consumption health index calculation model, and determine the cigarette machine equipment health evaluation result according to the criterion layer judgment matrix and the index layer vector. In this solution, the hierarchical analysis method is used to split the equipment health evaluation into consumption health, downtime health and subsystem health, strengthen the mining and utilization of existing equipment data and process data, improve the health evaluation system of cigarette machine equipment, solve the problems of poor timeliness and low troubleshooting efficiency in the existing troubleshooting based on the health evaluation results of cigarette machine equipment, and effectively improve the accuracy of the health evaluation results of cigarette machine equipment, and greatly improve the troubleshooting efficiency and timeliness.

[0047] Embodiment 2

[0048] Figure 2 This is a flowchart of a method for health evaluation of cigarette machine equipment provided in the second embodiment of the present invention. This embodiment is refined based on the above embodiment. In this embodiment, the indicator layer vector is determined based on the health evaluation related data, the subsystem health index calculation model, the shutdown health index calculation model and the consumption health index calculation model. The indicator layer vector can specifically include the first indicator layer vector, the second indicator layer vector and the third indicator layer vector. Figure 2 As shown, the method includes:

[0049] Step 210: Based on the cigarette machine equipment health evaluation sample data, regression model and hierarchical analysis method, a subsystem health index calculation model, a shutdown health index calculation model and a consumption health index calculation model are fitted.

[0050] In an optional embodiment of the present invention, based on the cigarette machine equipment health evaluation sample data, regression model and hierarchical analysis method, a subsystem health index calculation model, a shutdown health index calculation model and a consumption health index calculation model are fitted, which may include: fitting a shutdown health index calculation model and a consumption health index calculation model based on the internal sample data of the cigarette machine unit in the cigarette machine equipment health evaluation sample data, regression model and hierarchical analysis method; fitting a subsystem health index calculation model based on the key measuring point external monitoring device sample data in the cigarette machine equipment health evaluation sample data, the internal sample data of the cigarette machine unit, and the regression model.

[0051] Among them, the internal sample data of the cigarette making machine unit can be the operation-related sample data of the original equipment components of the cigarette making machine. The sample data of the key measuring point external monitoring equipment can be the sample data of the key monitoring points collected by the external sensors of the cigarette making machine. The sample data of the key measuring point external monitoring equipment can include but are not limited to vibration sensor signals, temperature sensor signals, voltage sensor signals, current sensor signals and proximity sensor signals. The sample data of the key measuring point external monitoring equipment can be stored in the local database.

[0052] In an embodiment of the present invention, the hierarchical analysis method can be used to perform weight measurement on the shutdown health and consumption health based on the internal sample data of the cigarette machine unit in the cigarette machine equipment health evaluation sample data, and further fit the calculation model through the regression model to obtain the shutdown health index calculation model and the consumption health index calculation model. The hierarchical analysis method can also be used to perform weight measurement on the subsystem health based on the key measurement point external monitoring device sample data in the cigarette machine equipment health evaluation sample data and the internal sample data of the cigarette machine unit, and further fit the calculation model through the regression model to obtain the subsystem health index calculation model.

[0053] It should be noted that the following principles should be followed for the selection of key monitoring points: component failure will cause serious downtime and affect normal production; components with high failure rates, high prices, long procurement cycles, and imported components; early deterioration inside the equipment that is not easy to detect (such as bearing and gear wear, etc.); equipment in dangerous or closed areas that can only be maintained during the shutdown period or shutdown state. Based on the above measurement point selection principles, the selected data collection points include but are not limited to the following measurement points: motor speed, synchronous pulley motor, paper cutting wheel, paper feeding roller, main transmission box motor radial, manipulator, manipulator fan, cigarette receiving wheel, second transmission box, cutter head, smoke outlet device, gluing device transmission bearing, electric control cabinet three-phase voltage, electric control cabinet three-phase current and residual current, electric control cabinet temperature.

[0054] Based on the acceleration data collected by the vibration sensor within one acquisition cycle, first-order integration and second-order integration are performed to obtain the velocity and displacement at each sampling point, and then the acceleration peak value, velocity effective value and displacement peak-to-peak value are calculated.

[0055] Based on the acceleration, velocity and displacement data calculated at each acquisition point, fast Fourier transform is performed to convert the time domain signal into a frequency domain signal to obtain the acceleration spectrum, velocity spectrum and displacement spectrum. The calculation formula of fast Fourier transform is as follows:

[0056] X(f)=∑ N-1 x(n)e -jπfn / N ; Where X(f) is the frequency domain signal, x(n) is the time domain signal, N is the number of sampling points in a sampling period, and the corresponding spectrum A(f) is finally obtained.

[0057] Calculate the amplitude spectrum from the frequency spectrum using the formula:

[0058] where Re(·) and Im(·) represent the real and imaginary parts of the complex number, respectively.

[0059] The power spectrum P(f) is calculated by calculating the square of the amplitude spectrum. The calculation formula is as follows: P(f) = |A(f)| 2 .

[0060] The envelope of the time domain signal is calculated using the Hilbert transform. The Hilbert transform can provide the instantaneous amplitude information of the signal. The calculation formula of the envelope signal E(t) is as follows:

[0061]

[0062] Perform fast Fourier transform on the envelope signal to obtain the envelope spectrum E(f);

[0063]

[0064] Optionally, the vibration sensor signals in the sample data of the external monitoring equipment at the key measuring points can be preprocessed by filtering and denoising, data resampling, time domain integration, time domain-frequency domain transformation, and data standardization, and the temperature sensor signals, voltage sensor signals, current sensor signals, and proximity sensor signals can be cleaned of missing values ​​and abnormal values, and then the vibration time domain features (acceleration peak, velocity effective value, displacement peak-to-peak value) and vibration frequency domain features (envelope spectrum, amplitude spectrum, power spectrum) can be extracted from the preprocessed vibration sensor signals. Based on the vibration time domain features and vibration frequency domain features, temperature, voltage, current, and speed, the regression model is trained using methods such as Bayesian optimization, and the parameters are optimized to obtain the health function e of the external sensor OD (ESHI). The Bayesian optimization method can quickly find the optimal health assessment point with a small number of samples, effectively reducing the number of samples required in actual operation, reducing the sensor operation load and cost, and is suitable for real-time or online health monitoring scenarios.

[0065] It should be understood that vibration, temperature, current, voltage and speed are important indicators of the equipment's operating status. Combining the vibration, temperature, current, voltage and proximity switch signals of key monitoring points, the equipment's health status can be evaluated from multiple dimensions, which improves the comprehensiveness of the equipment's health evaluation. Therefore, installing external monitoring equipment at key measuring points to sample the vibration, temperature, current, voltage and proximity switch signals of the cigarette machine during operation is a supplement and improvement to the equipment's status data. The vibration sensor signal as raw data is not in the format required by the model. Therefore, before using the vibration sensor signal of the cigarette machine for model training, the vibration sensor signal is first preprocessed by filtering and noise reduction, data resampling, window segmentation, time domain integration, time domain-frequency domain transformation, and data standardization to convert it into the format required by the model. Sensor failure or data transmission error may cause abnormal values, missing values ​​and other phenomena in the temperature, current, voltage and proximity switch sensor signals. Based on this, the temperature, current, voltage and proximity switch sensor signals are preprocessed for null values ​​and abnormal values ​​to ensure the accuracy and integrity of the data.

[0066] The time domain features and frequency domain features are extracted from the pre-processed vibration sensor signal. The time domain features and frequency domain features fully reveal the operating status of the cigarette machine from different dimensions. The time domain features are statistical information directly extracted from the vibration sensor signal data, reflecting the trend and amplitude distribution of the signal over time. The frequency domain features are information extracted after converting the signal from the time domain to the frequency domain by methods such as Fourier transform, which can reflect the spectral distribution characteristics of the signal and accurately locate the fault signal of a specific frequency. In the data-driven health evaluation method, the combination of time domain and frequency domain features provides the model with rich data features, significantly improving the accuracy of fault classification and prediction. The time series features and frequency domain features are the key steps to realize the health evaluation method of the cigarette machine equipment based on hierarchical analysis in the embodiment of the present invention. It enables the model to make full use of existing knowledge, adapt to specific environments, and improve the accuracy and efficiency of fault diagnosis, thereby bringing significant economic and operational benefits to the tobacco manufacturing field.

[0067] The data of the suction ribbon tensioning pressure index and the wind chamber negative pressure index are cleaned and standardized, and the abnormal detection models such as K nearest neighbor classification are trained. The distance algorithm is applied to the model to obtain the feeding strip health function f OD For the temperature index of sealer 1, the temperature index of sealer 2, the tension pressure index of cloth tape, the pressure index of automatic feed, and the total pressure index of compressed air, the generation method of the health function of feeding strip is used to determine the health function of rolling and forming g OD For the washboard temperature index, tipping paper temperature index, and compressed air total source pressure index data, the filter tipping health function h is determined using the generation method of the feed strip health function. OD Based on the health of the above three subsystems and external sensor devices, the regression algorithm or distance algorithm is applied, and combined with the corresponding measurement weight w (determined based on the hierarchical analysis method), the following subsystem health index calculation model (SHI) is constructed:

[0068] SHI=Dist[w T [f OD (VEHI)+g OD (SEHI)+h OD (MAXHI)+e OD (ESHI)]]×100%;

[0069] Where Dist represents the distance function.

[0070] The health of the feeding strip, the health of the rolling and forming, and the health of the filter tipping of the cigarette machine during operation may be affected by many factors, such as temperature, pressure, vibration, etc., and the relationship between these factors may be very complex and nonlinear. Therefore, an algorithm that can dynamically adapt to the state change of the equipment, effectively identify rare and irregular anomalies, and avoid the accuracy of noise data in the data is crucial to the health assessment. The K nearest neighbor classification algorithm is an instance-based non-parametric algorithm that does not require assumptions about the distribution of data. It only relies on the similarity between samples and determines whether the data point is abnormal by calculating the neighboring samples of each data point. It can dynamically identify abnormal situations, reduce the risk of equipment failure, and provide real-time and accurate health monitoring results. It should be understood that the subsystem health index calculated based on the hierarchical analysis method comprehensively considers the mutual influence between the subsystems and the performance of the overall system, can comprehensively reflect the operating health of the entire subsystem, and provide decision makers with an intuitive and comprehensive health evaluation. The evaluation results push the health status of the cigarette machine subsystem to the client in real time, which is crucial to ensure the effectiveness and practicality of the cigarette machine equipment monitoring and evaluation method. By calculating the total health index of the subsystem, managers can more accurately monitor the health status of the subsystem, perform timely and effective maintenance and optimization, and improve the long-term reliability and production efficiency of the equipment.

[0071] For example, it is obtained based on the equipment performance availability (OEE), average downtime duration (MTTR), average downtime interval (MTBF) and equipment-related information. The above downtime health index data are collected, and the downtime health index calculation model MDHI is constructed using a multivariate regression model:

[0072] MDHI=Dist[w OEE ·OEE+w MTTR MTTR+w MTBF MTBF]×100%;

[0073] Among them, w OEE 、w MTTR and w MTBF They are the weights of equipment performance utilization rate, average downtime duration and average downtime interval, respectively. The weights in this formula are determined based on the hierarchical analysis method.

[0074] Exemplarily, data on equipment performance availability index, average downtime duration index, and average downtime interval index are collected, and further data cleaning and standardization are performed.

[0075] Equipment performance utilization rate refers to the proportion of equipment operation time in a certain period of time to the total time. The calculation formula is as follows:

[0076]

[0077] Among them, equipment operating time refers to the actual operating time of the equipment (excluding non-operating time such as shutdown, overhaul, and maintenance), and total time refers to the total operating time of the equipment (including non-operating time such as shutdown, overhaul, and maintenance).

[0078] The average downtime refers to the average time from shutdown to resumption of normal operation after a device failure occurs. The calculation formula is as follows:

[0079]

[0080] The mean downtime interval is the expected time between one previous fault and the next fault in the system during normal operation. The calculation formula is as follows:

[0081]

[0082] The downtime health index calculated based on the hierarchical analysis method can quantify the downtime health of the equipment and provide a scientific basis for maintenance decisions. The downtime health index can predict the potential downtime risk of the equipment and help managers better arrange preventive maintenance or repairs. By monitoring the equipment performance utilization rate, it is possible to identify the factors that lead to inefficient operation of the equipment, take targeted measures to improve the equipment utilization rate and reduce downtime. By analyzing the average downtime interval and average downtime duration of the equipment, a personalized maintenance plan can be formulated based on the health status of the equipment to avoid excessive maintenance or ignoring problems.

[0083] Based on various consumption indicators, such as the rejection rate of too light cigarettes, the rejection rate of too heavy cigarettes, the rejection rate of soft points, the rejection rate of hard points, the rejection rate of light cigarette ends, the rejection rate of mouthpieces, the rejection rate of suction resistance, the rejection rate of ventilation, the rejection rate of tightness, the rejection rate of appearance, and the rejection rate of empty ends, with reference to the 6σ quality evaluation system standard, the regression analysis algorithm is applied for fitting, and then the distance algorithm is applied to evaluate the consumption health index calculation model (CHI):

[0084] CHI=Dist[∑w i ·Z i ]×100%; where w i represents the measurement weight of the i-th consumption index, and the weight in this formula is determined based on the hierarchical analysis method; Z i Represents the i-th consumption indicator.

[0085] Optionally, data cleaning and standardization can be performed on various consumption indicators, and data from different sources can be cleaned and standardized to eliminate data deviations caused by measurement errors and equipment differences, so as to calculate consumption health more accurately.

[0086] In an optional embodiment of the present invention, based on the internal sample data of the cigarette machine unit in the sample data of the cigarette machine equipment health evaluation, the regression model and the hierarchical analysis method, the shutdown health index calculation model and the consumption health index calculation model are fitted, which may include: establishing the target layer, criterion layer and indicator layer of the cigarette machine equipment health evaluation according to the hierarchical analysis method; fitting the shutdown health index calculation model that passes the consistency test according to the indicator layer corresponding to the shutdown health in the criterion layer, the internal sample data of the cigarette machine unit and the regression model; fitting the consumption health index calculation model that passes the consistency test according to the indicator layer corresponding to the consumption health in the criterion layer, the internal sample data of the cigarette machine unit and the regression model.

[0087] Among them, the target layer, the criterion layer and the indicator layer are the hierarchical structures established by the hierarchical analysis method. For example, the target layer can be the health of the cigarette machine equipment. The criterion layer can include the subsystem health, the shutdown health and the consumption health. The indicator layer can be the subdivided indicators of the criterion layer. The indicator layer can include the evaluation criteria for each health subdivision, which can be adjusted as needed.

[0088] In an embodiment of the present invention, a hierarchical analysis method can be used to establish a hierarchical analysis structure for evaluating the health of cigarette machine equipment, that is, to establish a target layer, a criterion layer and an indicator layer, and obtain the indicator layer corresponding to the shutdown health in the criterion layer, and the indicator layer corresponding to the consumption health, so that according to the indicator layer corresponding to the shutdown health, the associated data of the consumption health evaluation is screened out from the internal sample data of the cigarette machine unit, and the associated data of the shutdown health evaluation is screened out from the internal sample data of the cigarette machine unit, and then the hierarchical analysis method is used to perform weight measurement and weight consistency test on the shutdown health according to the associated data of the shutdown health evaluation, so that the calculation model is fitted through the regression model to obtain the shutdown health index calculation model that passes the consistency test, and similarly, according to the associated data of the consumption health evaluation, the consumption health is weighted and the weight consistency test is performed, and the calculation model is fitted through the regression model to obtain the consumption health index calculation model that passes the consistency test.

[0089] In an optional embodiment of the present invention, a subsystem health index calculation model is fitted based on the key measuring point external monitoring device sample data, the internal sample data of the cigarette machine unit, and the regression model in the cigarette machine equipment health evaluation sample data. It can include: according to the indicator layer corresponding to the subsystem health in the criterion layer, the key measuring point external monitoring device sample data, the internal sample data of the cigarette machine unit, and the regression model, a subsystem health index calculation model that passes the consistency test is fitted.

[0090] In an embodiment of the present invention, the indicator layer corresponding to the subsystem health in the criterion layer can be obtained, so that according to the indicator layer corresponding to the subsystem health, the associated data of the subsystem health assessment can be screened out from the sample data of the external monitoring equipment of the key measuring points and the internal sample data of the cigarette machine unit, and then the hierarchical analysis method is used to perform weight measurement and weight consistency test on the subsystem health according to the associated data of the subsystem health assessment, so as to fit the calculation model through the regression model and obtain the subsystem health index calculation model that passes the consistency test.

[0091] In a specific example, a progressive hierarchical structure (target layer, criterion layer, and indicator layer) is established based on the hierarchical analysis method, and then a judgment matrix is ​​constructed. The importance of each element at the same level to a criterion in the previous level is compared pairwise to construct a judgment matrix. The relative weight of the compared element to the criterion is calculated through the judgment matrix, and a consistency check is performed to ensure that the weight is reasonable and available. The consistency check is performed through the consistency ratio CR, where RI is obtained by table lookup, and the synthetic weight of each layer element to the target layer is further calculated and sorted to achieve the establishment of a health evaluation method for cigarette making machine equipment based on hierarchical analysis.

[0092] Among them, when comparing any two elements A and B in the judgment matrix, the following criteria are followed: A and B are equally important (equally strong), with a scale of 1; A is slightly more important than B (slightly stronger), with a scale of 3; A is obviously more important than B (quite strong), with a scale of 5; A is strongly more important than B (extremely strong), with a scale of 7; A is extremely more important than B (absolutely strong), with a scale of 9; if it is the median of the above two adjacent judgments, the scale is 2, 4, 6, or 8; in particular, if the ratio of A to B is scaled t, then the ratio of B to A is 1 / t.

[0093] Consistency check in progress Among them, CI represents the consistency index, RI represents the average random consistency index, which is obtained by looking up the table, n represents the order of the above judgment matrix, and λ max Represents the maximum eigenvalue of the judgment matrix.

[0094] Step 220: Obtain health evaluation related data of the current cigarette making machine.

[0095] Step 230, calculate the first index layer vector and the second index layer vector according to the internal data of the cigarette making machine unit, the shutdown health index calculation model and the consumption health index calculation model.

[0096] The internal data of the cigarette making machine group may be the operation-related data of the original equipment components of the current cigarette making machine. The first index layer vector may be the weight vector of the index layer corresponding to the shutdown health. The second index layer vector may be the weight vector of the index layer corresponding to the consumption health.

[0097] In an embodiment of the present invention, relevant data of the indicator layer corresponding to the shutdown health and relevant data of the indicator layer corresponding to the consumption health can be parsed from the internal data of the cigarette machine unit, and then the relevant data of the indicator layer corresponding to the shutdown health can be input into the shutdown health index calculation model to obtain the first indicator layer vector, and the relevant data of the indicator layer corresponding to the consumption health can be input into the consumption health index calculation model to obtain the second indicator layer vector.

[0098] Step 240: Calculate the third indicator layer vector according to the internal data of the cigarette making machine unit, the data of the external monitoring equipment at the key measuring points and the subsystem health index calculation model.

[0099] The third indicator layer vector may be a weight vector of the indicator layer corresponding to the health of the subsystem. The key measuring point external monitoring device data may be the key monitoring point data collected by the current cigarette machine external sensor. The key measuring point external monitoring device data and the key measuring point external monitoring device sample data correspond to the same key monitoring point.

[0100] In an embodiment of the present invention, relevant data of the indicator layer corresponding to the health of the subsystem can be parsed from the internal data of the cigarette machine unit and the data of the external monitoring equipment at the key measuring points, and then the relevant data of the indicator layer corresponding to the health of the subsystem can be input into the subsystem health index calculation model to obtain the third indicator layer vector.

[0101] Step 250: determine the criterion layer judgment matrix, and determine the cigarette making machine equipment health evaluation result according to the criterion layer judgment matrix and the indicator layer vector.

[0102] In an optional embodiment of the present invention, determining the criterion layer judgment matrix may include: obtaining the importance parameters of subsystem health, shutdown health and consumption health to the target layer; and calculating the criterion layer judgment matrix based on the importance parameters of subsystem health, shutdown health and consumption health to the target layer.

[0103] The importance parameter may be a parameter describing the importance of the criterion layer element to the target layer.

[0104] In an embodiment of the present invention, the importance parameters of subsystem health, shutdown health and consumption health to the target layer can be obtained, and then the calculation method of the judgment matrix in the hierarchical analysis method can be used to calculate the criterion layer judgment matrix based on the importance parameters of subsystem health, shutdown health and consumption health to the target layer.

[0105] In an optional embodiment of the present invention, determining the health evaluation result of the cigarette making machine equipment according to the criterion layer judgment matrix and the indicator layer vector may include: determining the subsystem health synthesis weight, the shutdown health synthesis weight and the consumption health synthesis weight according to the product of the criterion layer judgment matrix and the indicator layer vector; determining the cigarette making machine equipment health evaluation result according to the subsystem health synthesis weight, the shutdown health synthesis weight and the consumption health synthesis weight.

[0106] The subsystem health composite weight may be a composite weight of the subsystem health of the criterion layer to the target layer. The shutdown health composite weight may be a composite weight of the shutdown health of the criterion layer to the target layer. The consumption health composite weight may be a composite weight of the consumption health of the criterion layer to the target layer.

[0107] In an embodiment of the present invention, a regression model that has been pre-trained for fitting a matrix into a vector can be used to fit the indicator layer vectors corresponding to the three health levels into a one-dimensional vector, and then the fitted vector is matrix multiplied with the criterion layer judgment matrix to obtain the composite weights of the three health levels, namely, the subsystem health composite weight, the shutdown health composite weight and the consumption health composite weight. The subsystem health composite weight, the shutdown health composite weight and the consumption health composite weight are further sorted to determine the criterion layer factor that has the greatest impact on the health of the cigarette making machine equipment, thereby taking the composite weights of the three health levels and the criterion layer element with the greatest impact as the final cigarette making machine equipment health evaluation result.

[0108] Data analysis and modeling are carried out using the internal data of the cigarette machine unit and the data of external monitoring equipment at key measuring points. The hierarchical analysis method is used to split the equipment health evaluation into consumption health, shutdown failure health and subsystem overall health. The mining and utilization of existing equipment data and process data are strengthened, the key measuring point data are monitored, and the construction of an equipment health evaluation system is realized.

[0109] In a specific example, the internal sample data of the cigarette machine unit and the sample data of the external monitoring equipment at key measuring points are collected, and the vibration sensor signals, temperature sensor signals, voltage sensor signals, current sensor signals, and proximity sensor signals included in the data of the external monitoring equipment at key measuring points are stored in a local database. The vibration sensor signals are preprocessed by filtering and denoising, data resampling, time domain integration, time domain-frequency domain transformation, and data standardization, and the temperature sensor signals, current sensor signals, voltage sensor signals, and proximity switch sensor signals are preprocessed by data cleaning of missing values ​​and abnormal values. The time domain features (acceleration peak, velocity effective value, and displacement peak-to-peak value) and frequency domain features (envelope spectrum, amplitude spectrum, and power spectrum) are extracted from the preprocessed vibration data. Based on the above time domain features, frequency domain features, and temperature, voltage, current, and speed data, the external sensor equipment health index regression model is trained using Bayesian optimization and other methods, and the parameters are optimized to obtain the external sensor health function. The suction ribbon tensioning pressure index and the wind chamber negative pressure index data are collected, and the data are cleaned and standardized. The K nearest neighbor classification anomaly detection model is trained, and then the distance algorithm is applied to the model to determine the final feeding strip health function when the model expectations are met. The determination process of the feeding strip health function is as follows: Figure 3 The sealing device temperature index, the cloth tape tensioning pressure index, the automatic feed pressure index, and the compressed air total gas source pressure index data are collected. For the sealing device temperature index, the cloth tape tensioning pressure index, the automatic feed pressure index, and the compressed air total gas source pressure index data, the above method is used to obtain the roll forming health function. The specific process of determining the roll forming health function is as follows: Figure 4 The washboard temperature index, the tipping paper temperature index, and the compressed air total air source pressure index data are collected, and the filter tipping health function is obtained using the above method for the washboard temperature index, the tipping paper temperature index, and the compressed air total air source pressure index data. The specific process for determining the filter tipping health function is as follows: Figure 5 Based on the corresponding health functions of the above three subsystems and the health functions of external sensors, a subsystem health index calculation model is constructed by applying regression algorithm or distance algorithm and combining subsystem importance measurement.

[0110] Collect downtime health-related indicator data (equipment performance start-up rate, average downtime duration, average downtime interval), and use the multivariate regression model to build a downtime health index calculation model.

[0111] Based on various consumption indicators: scrap rate of too light cigarettes, scrap rate of too heavy cigarettes, scrap rate of soft points, scrap rate of hard points, scrap rate of light cigarette ends, scrap rate of mouthpieces, scrap rate of draw resistance, scrap rate of ventilation, scrap rate of tightness, scrap rate of appearance and scrap rate of empty ends, with reference to the 6σ quality evaluation system standard, the regression analysis algorithm is applied to fit the consumption health scoring equation, and then the distance algorithm is applied to determine the consumption health index calculation model.

[0112] This scheme applies the hierarchical analysis method to complete the weight measurement of the above three health index calculation models, and based on the three health index calculation models with completed weight measurement and the synthetic weights of each layer of elements of the current cigarette making machine to the target layer, they are sorted to achieve the establishment of a comprehensive evaluation index system and obtain the equipment health of the current cigarette making machine.

[0113] The technical solution of the embodiment of the present invention is to fit the subsystem health index calculation model, the shutdown health index calculation model and the consumption health index calculation model based on the cigarette machine equipment health evaluation sample data, regression model and hierarchical analysis method, so as to obtain the health evaluation related data of the current cigarette machine, and then calculate the first indicator layer vector and the second indicator layer vector according to the internal data of the cigarette machine unit, the shutdown health index calculation model and the consumption health index calculation model, and further calculate the third indicator layer vector according to the internal data of the cigarette machine unit, the data of the key measuring point external monitoring equipment and the subsystem health index calculation model, and determine the criterion layer judgment matrix, and determine the cigarette machine equipment health evaluation result according to the criterion layer judgment matrix and the indicator layer vector. In this scheme, the hierarchical analysis method is used to split the equipment health evaluation into consumption health, shutdown health and subsystem health, strengthen the mining and utilization of existing equipment data and process data, improve the health evaluation system of cigarette making machine equipment, and solve the problems of poor timeliness and low troubleshooting efficiency of the existing troubleshooting based on the health evaluation results of cigarette making machine equipment. It can effectively improve the accuracy of the health evaluation results of cigarette making machine equipment and greatly improve the troubleshooting efficiency and timeliness.

[0114] Embodiment 3

[0115] Figure 6 This is a schematic diagram of the structure of a cigarette machine equipment health evaluation device provided in Example 3 of the present invention. Figure 6 As shown, the device comprises:

[0116] The calculation model fitting module 310 is used to fit the subsystem health index calculation model, the shutdown health index calculation model and the consumption health index calculation model based on the cigarette machine equipment health evaluation sample data, the regression model and the hierarchical analysis method;

[0117] The data acquisition module 320 is used to acquire health evaluation related data of the current cigarette making machine;

[0118] The indicator layer vector determination module 330 is used to determine the indicator layer vector according to the health evaluation associated data, the subsystem health index calculation model, the shutdown health index calculation model and the consumption health index calculation model;

[0119] The equipment health evaluation determination module 340 is used to determine the criterion layer judgment matrix, and determine the cigarette machine equipment health evaluation result according to the criterion layer judgment matrix and the indicator layer vector.

[0120] The technical solution of the embodiment of the present invention is to fit the subsystem health index calculation model, the downtime health index calculation model and the consumption health index calculation model based on the cigarette machine equipment health evaluation sample data, regression model and hierarchical analysis method, so as to obtain the health evaluation related data of the current cigarette machine, and then determine the index layer vector and the criterion layer judgment matrix according to the health evaluation related data, the subsystem health index calculation model, the downtime health index calculation model and the consumption health index calculation model, and determine the cigarette machine equipment health evaluation result according to the criterion layer judgment matrix and the index layer vector. In this solution, the hierarchical analysis method is used to split the equipment health evaluation into consumption health, downtime health and subsystem health, strengthen the mining and utilization of existing equipment data and process data, improve the health evaluation system of cigarette machine equipment, solve the problems of poor timeliness and low troubleshooting efficiency in the existing troubleshooting based on the health evaluation results of cigarette machine equipment, and effectively improve the accuracy of the health evaluation results of cigarette machine equipment, and greatly improve the troubleshooting efficiency and timeliness.

[0121] Optionally, the calculation model fitting module 310 includes a first calculation model fitting unit and a second calculation model fitting unit. The first calculation model fitting unit is used to fit the shutdown health index calculation model and the consumption health index calculation model based on the internal sample data of the cigarette making machine unit in the cigarette making machine equipment health evaluation sample data, the regression model and the hierarchical analysis method. The second calculation model fitting unit is used to fit the subsystem health index calculation model based on the key measurement point external monitoring device sample data in the cigarette making machine equipment health evaluation sample data, the internal sample data of the cigarette making machine unit, and the regression model.

[0122] Optionally, the first calculation model fitting unit is specifically used to establish the target layer, criterion layer and indicator layer for evaluating the health of cigarette machine equipment according to the hierarchical analysis method; to fit a shutdown health index calculation model that passes the consistency test according to the indicator layer corresponding to the shutdown health in the criterion layer, the internal sample data of the cigarette machine unit and the regression model; to fit a consumption health index calculation model that passes the consistency test according to the indicator layer corresponding to the consumption health in the criterion layer, the internal sample data of the cigarette machine unit and the regression model.

[0123] Optionally, the second calculation model fitting unit is specifically used to fit a subsystem health index calculation model that passes the consistency test based on the indicator layer corresponding to the subsystem health in the criterion layer, the sample data of the key measuring point external monitoring equipment, the internal sample data of the cigarette making machine unit, and the regression model.

[0124] Optionally, the indicator layer vector determination module 330 is specifically used to calculate the first indicator layer vector and the second indicator layer vector based on the internal data of the cigarette machine unit, the shutdown health index calculation model and the consumption health index calculation model; and calculate the third indicator layer vector based on the internal data of the cigarette machine unit, the data of the key measuring point external monitoring equipment and the subsystem health index calculation model.

[0125] Optionally, the equipment health evaluation determination module 340 includes a criterion layer judgment matrix determination unit and a health evaluation result determination unit. The criterion layer judgment matrix determination unit is used to obtain the importance parameters of the subsystem health, the shutdown health, and the consumption health to the target layer; based on the importance parameters of the subsystem health, the shutdown health, and the consumption health to the target layer, calculate the criterion layer judgment matrix.

[0126] Optionally, a health evaluation result determination unit is used to determine the subsystem health composite weight, the shutdown health composite weight and the consumption health composite weight according to the product of the criterion layer judgment matrix and the indicator layer vector; and determine the health evaluation result of the cigarette making machine equipment according to the subsystem health composite weight, the shutdown health composite weight and the consumption health composite weight.

[0127] The cigarette making machine equipment health evaluation device provided in the embodiment of the present invention can execute the cigarette making machine equipment health evaluation method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0128] Embodiment 4

[0129] Figure 7A schematic diagram of an electronic device that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0130] like Figure 7 As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0131] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0132] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as a cigarette machine equipment health evaluation method.

[0133] In some embodiments, the cigarette making machine equipment health assessment method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the cigarette making machine equipment health assessment method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the cigarette making machine equipment health assessment method in any other appropriate manner (e.g., by means of firmware).

[0134] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0135] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0136] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0137] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0138] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0139] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of traditional physical hosts and VPS servers, which are difficult to manage and have weak business scalability.

[0140] The present application also discloses a computer program product, which includes a computer program. When the computer program is executed by a processor, the computer program implements the cigarette making machine equipment health evaluation method provided in any embodiment of the present application. The program product and the cigarette making machine equipment health evaluation method disclosed in each embodiment of the present application belong to the same inventive concept, so it will not be repeated here.

[0141] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0142] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for evaluating the health of a cigarette making machine, characterized in that: include: Based on the sample data of cigarette machine equipment health evaluation, regression model and hierarchical analysis method, the subsystem health index calculation model, shutdown health index calculation model and consumption health index calculation model are fitted; Obtain the health evaluation related data of the current cigarette making machine; Determine an indicator layer vector according to the health evaluation associated data, the subsystem health index calculation model, the shutdown health index calculation model and the consumption health index calculation model; A criterion layer judgment matrix is ​​determined, and a cigarette making machine equipment health evaluation result is determined according to the criterion layer judgment matrix and the indicator layer vector.

2. The method according to claim 1, characterized in that Based on the sample data of cigarette machine equipment health evaluation, regression model and hierarchical analysis method, the subsystem health index calculation model, shutdown health index calculation model and consumption health index calculation model are fitted, including: Based on the internal sample data of the cigarette making machine group in the cigarette making machine equipment health evaluation sample data, the regression model and the hierarchical analysis method, the shutdown health index calculation model and the consumption health index calculation model are fitted; Based on the key measuring point external monitoring equipment sample data in the cigarette making machine equipment health evaluation sample data, the cigarette making machine unit internal sample data, and the regression model, the subsystem health index calculation model is fitted.

3. The method according to claim 2, characterized in that Based on the internal sample data of the cigarette machine group in the cigarette machine equipment health evaluation sample data, the regression model and the hierarchical analysis method, the shutdown health index calculation model and the consumption health index calculation model are fitted, including: According to the analytic hierarchy process, a target layer, a criterion layer and an indicator layer for evaluating the health of cigarette making machine equipment are established; According to the indicator layer corresponding to the shutdown health degree in the criterion layer, the internal sample data of the cigarette machine unit and the regression model, a shutdown health degree index calculation model that passes the consistency test is fitted; According to the indicator layer corresponding to the consumption health degree in the criterion layer, the internal sample data of the cigarette machine group and the regression model, a consumption health degree index calculation model that passes the consistency test is fitted.

4. The method according to claim 3, characterized in that Based on the key measuring point external monitoring equipment sample data in the cigarette machine equipment health evaluation sample data, the cigarette machine unit internal sample data, and the regression model, the subsystem health index calculation model is fitted, including: According to the indicator layer corresponding to the subsystem health in the criterion layer, the sample data of the external monitoring equipment at the key measuring points, the internal sample data of the cigarette making machine unit, and the regression model, a subsystem health index calculation model that passes the consistency test is fitted.

5. The method according to claim 1, characterized in that: The indicator layer vector includes a first indicator layer vector, a second indicator layer vector and a third indicator layer vector. The indicator layer vector is determined according to the health evaluation associated data, the subsystem health index calculation model, the shutdown health index calculation model and the consumption health index calculation model, including: Calculate the first index layer vector and the second index layer vector according to the internal data of the cigarette machine unit, the shutdown health index calculation model and the consumption health index calculation model; The third indicator layer vector is calculated based on the internal data of the cigarette machine unit, the data of the external monitoring equipment at key measuring points and the subsystem health index calculation model.

6. The method according to claim 4, characterized in that Determine the criterion layer judgment matrix, including: Obtaining the importance parameters of the subsystem health, the shutdown health, and the consumption health to the target layer; Based on the subsystem health, the shutdown health and the consumption health, and the importance parameter of the target layer, the criterion layer judgment matrix is ​​calculated.

7. The method according to claim 4, characterized in that According to the criterion layer judgment matrix and the indicator layer vector, the health evaluation result of the cigarette making machine is determined, including: Determine the subsystem health synthesis weight, shutdown health synthesis weight and consumption health synthesis weight according to the product of the criterion layer judgment matrix and the indicator layer vector; The health evaluation result of the cigarette making machine equipment is determined according to the subsystem health synthesis weight, the shutdown health synthesis weight and the consumption health synthesis weight.

8. A cigarette making machine equipment health evaluation device, characterized in that: include: The calculation model fitting module is used to fit the subsystem health index calculation model, the shutdown health index calculation model and the consumption health index calculation model based on the cigarette machine equipment health evaluation sample data, regression model and hierarchical analysis method; A data acquisition module is used to acquire health evaluation related data of the current cigarette making machine; An indicator layer vector determination module, used to determine an indicator layer vector according to the health evaluation associated data, the subsystem health index calculation model, the shutdown health index calculation model and the consumption health index calculation model; The equipment health evaluation determination module is used to determine the criterion layer judgment matrix, and determine the cigarette machine equipment health evaluation result according to the criterion layer judgment matrix and the indicator layer vector.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the cigarette making machine equipment health assessment method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the cigarette making machine equipment health evaluation method according to any one of claims 1 to 7 when executed.

Images