A monitoring and management method and system for convenience food production equipment

Abstract

The present invention provides a method and system for monitoring and managing convenience food production equipment, relating to the technical field of intelligent monitoring of production equipment. The method comprises: obtaining multiple sets of production status monitoring data of a mixing device, constructing a disturbance time series matrix for each set of production status monitoring data; performing a time period disturbance evolution analysis on each disturbance time series matrix, and constructing a disturbance steady-state characteristic matrix corresponding to the multiple sets of production status monitoring data; performing a time period disturbance collaborative analysis on multiple equipment state parameters, and constructing a disturbance collaborative matrix for each set of production status monitoring data; combining the disturbance time series matrix and the disturbance steady-state characteristic matrix to correct and fuse the multiple disturbance collaborative matrices to generate a collaborative reference matrix; after obtaining the real-time monitoring data of the mixing device, analyzing the real-time monitoring data based on the collaborative reference matrix to generate an abnormality detection result for the mixing device. The present invention achieves accurate detection of minor anomalies in the mixing setting.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent monitoring of production equipment, and in particular to a monitoring and management method and system for convenience food production equipment. Background Art

[0002] In the modern convenience food production process, mixing equipment, as a core piece of equipment, is responsible for evenly mixing various ingredients, directly impacting the taste and quality of the food. During the mixing process, as materials are added, distributed, and continuously stirred, equipment parameters such as load and vibration exhibit complex trends over time. Mixing equipment monitoring systems typically utilize multiple sensors, such as current, torque, temperature, and vibration, to monitor equipment operating status in real time.

[0003] In the initial stages of mixing, uneven material addition and distribution can cause significant fluctuations in various parameters, manifesting as significant disturbances. For example, initially, material distribution within the mixing tank may be uneven, leading to increased fluctuations in parameters such as equipment load and torque. As the materials become more evenly mixed, the mixing process stabilizes, and disturbance fluctuations decrease. This dynamic disturbance trend often masks minor anomalies, making them difficult to detect using traditional equipment monitoring systems.

[0004] Furthermore, the variability of convenience food ingredients and random fluctuations during the mixing process further complicate the detection of subtle anomalies. Even under the same process, natural variations in ingredients, such as moisture content and particle size, can cause subtle disturbances during mixing. Some monitoring methods are often limited to simple threshold assessments of equipment status, easily overlooking performance changes caused by minor anomalies. This is particularly true of hidden anomalies masked by material variability, random fluctuations during mixing, and the evolution of disturbances. Summary of the Invention

[0005] To solve the above technical problems, the present invention proposes a method and system for monitoring and managing convenience food production equipment. It adopts a method based on the dynamic evolution and correlation analysis of the disturbance time series matrix, and combines it with the analysis of the changing characteristics of disturbance propagation to accurately capture subtle anomalies in the mixing process that are masked by factors such as material differences, thereby achieving high-precision anomaly detection of production equipment.

[0006] To achieve the above objectives, the present invention provides a first aspect of a method for monitoring and managing instant food production equipment, comprising:

[0007] Acquire multiple sets of production status monitoring data for mixing equipment in a convenience food production line, including time series detection data of multiple equipment status parameters. Perform state disturbance analysis on each set of production status monitoring data, extract the local disturbance feature sequence of each equipment state parameter, and construct a disturbance time series matrix for each set of production status monitoring data.

[0008] Perform time period disturbance evolution analysis on each disturbance time series matrix, calculate multiple steady-state characteristic parameters of the disturbance time series matrix in different local production periods, and construct disturbance steady-state characteristic matrices corresponding to multiple sets of production status monitoring data;

[0009] Based on the disturbance time series matrix, a time period disturbance collaborative analysis is performed on multiple equipment status parameters, multiple disturbance collaborative parameters of each equipment status parameter in different local production periods are calculated, and a disturbance collaborative matrix for each set of production status monitoring data is constructed;

[0010] The disturbance coordination matrix is ​​analyzed by combining the disturbance time series matrix and the disturbance steady-state characteristic matrix. The disturbance evaluation parameters of each equipment state parameter in different local production periods are calculated. Based on the disturbance evaluation parameters, multiple disturbance coordination matrices are corrected and integrated to construct coordination reference matrices corresponding to multiple sets of production state monitoring data.

[0011] After acquiring the real-time monitoring data of the mixing equipment, the real-time monitoring data is analyzed based on the collaborative reference matrix to generate an abnormality detection result of the mixing equipment.

[0012] Preferably, multiple steady-state characteristic parameters of the disturbance time series matrix in different local production periods are calculated, and disturbance steady-state characteristic matrices corresponding to multiple sets of production status monitoring data are constructed, including:

[0013] Performing a time period disturbance evolution analysis on multiple disturbance time series matrices based on multiple local production periods to determine multiple state disturbance parameters corresponding to the equipment state parameters in each local production period;

[0014] Divide the multiple state disturbance parameters in each local production period into discrete intervals, obtain the distribution frequency of the equipment state parameters in the local production period with respect to the multiple local discrete intervals, and calculate the disturbance distribution entropy value of the equipment state parameters in the local production period;

[0015] According to multiple disturbance time series matrices, the disturbance reference value of the equipment state parameter in each local production period is determined, and the disturbance reference value is optimized by the disturbance distribution entropy value to generate the steady-state characteristic parameter of the equipment state parameter in each local production period. According to the steady-state characteristic parameters corresponding to each equipment state parameter in multiple local production periods, the disturbance steady-state characteristic matrix is ​​generated.

[0016] Preferably, the disturbance coordination matrix is ​​analyzed in combination with the disturbance time series matrix and the disturbance steady-state characteristic matrix to calculate the disturbance evaluation parameters of each equipment state parameter in different local production periods, including:

[0017] A stirring characteristic vector of the production state monitoring data is constructed according to the disturbance time series matrix, the disturbance steady-state characteristic matrix and the disturbance synergy matrix, and stirring characteristic parameters of the production state monitoring data are calculated based on the stirring characteristic vector;

[0018] The disturbance effect accumulation parameters of the equipment state parameters in each local production period are calculated based on the disturbance time series matrix and the disturbance steady-state characteristic matrix. The following formula is used to calculate the disturbance evaluation parameters corresponding to multiple local production periods of the equipment state parameters under each set of production state monitoring data based on the disturbance effect accumulation parameters and the stirring characteristic parameters:

[0019] H i,j =δ·E i,j +(1-δ)·|D j -D μ |

[0020] Where H i,j represents the disturbance evaluation parameter of the i-th equipment state parameter in the production state monitoring data under the j-th local production period, δ represents the stirring characteristic parameter of the production state monitoring data, and E i,j D represents the cumulative parameter of the disturbance effect of the i-th equipment status parameter in the production status monitoring data in the j-th local production period, j represents the steady-state parameter of the period disturbance under the jth local production period in the production status monitoring data, D μ Represents the global disturbance steady-state parameters of production status monitoring data.

[0021] Preferably, the disturbance effect accumulation parameter further includes:

[0022] The disturbance effect accumulation parameter is calculated using the following formula:

[0023]

[0024] Where D i,j represents the local disturbance steady-state parameter of the i-th equipment state parameter in the production state monitoring data under the j-th local production period, C k.ij represents the disturbance coordination parameter between the i-th equipment state parameter in the production state monitoring data and the k-th equipment state parameter in the j-th local production period, e -(M-j) represents the disturbance attenuation factor of the jth local production period, n represents the total number of equipment state parameters, and M represents the total number of local production periods.

[0025] Preferably, multiple disturbance coordination matrices are corrected and integrated based on disturbance assessment parameters to construct coordination reference matrices corresponding to multiple sets of production status monitoring data, including:

[0026] According to the disturbance assessment parameters, the local fusion weight of the disturbance coordination matrix for each equipment state parameter in each local production period is determined. According to the local fusion weight of the equipment state parameter in each local production period, multiple disturbance coordination parameters of the equipment state parameter in the local production period are corrected to generate local coordination parameters of the equipment state parameter. The local coordination matrix corresponding to each group of production status monitoring data is constructed, and the multiple local coordination matrices are fused to generate coordination reference matrices corresponding to multiple groups of production status monitoring data.

[0027] Preferably, analyzing the real-time monitoring data based on the collaborative reference matrix to generate abnormality detection results of the stirring equipment includes:

[0028] Perform state disturbance analysis and time period disturbance collaborative analysis on the real-time monitoring data, construct a disturbance collaborative matrix corresponding to the real-time monitoring data, calculate the real-time collaborative parameters of the equipment state parameters in each local production period based on the disturbance collaborative matrix, perform time period anomaly detection on the equipment state parameters through the collaborative reference matrix and multiple real-time collaborative parameters of the equipment state parameters, and generate anomaly detection results for the mixing equipment.

[0029] A second aspect of the present invention provides a convenience food production equipment monitoring and management system, which is used to implement a convenience food production equipment monitoring and management method of the above-mentioned rights, comprising:

[0030] The local disturbance analysis module is used to obtain multiple sets of production status monitoring data of mixing equipment in the convenience food production line, including time series detection data of multiple equipment status parameters. It performs state disturbance analysis on each set of production status monitoring data, extracts the local disturbance feature sequence of each equipment status parameter, and constructs the disturbance time series matrix of each set of production status monitoring data.

[0031] The disturbance steady-state feature extraction module is used to perform period disturbance evolution analysis on each disturbance time series matrix, calculate multiple steady-state feature parameters of the disturbance time series matrix in different local production periods, and construct disturbance steady-state feature matrices corresponding to multiple sets of production status monitoring data;

[0032] The disturbance collaborative analysis module is used to perform period disturbance collaborative analysis on multiple equipment status parameters based on the disturbance time series matrix, calculate multiple disturbance collaborative parameters of each equipment status parameter in different local production periods, and construct a disturbance collaborative matrix for each set of production status monitoring data;

[0033] The disturbance state assessment module is used to analyze the disturbance coordination matrix by combining the disturbance time series matrix and the disturbance steady-state characteristic matrix, calculate the disturbance assessment parameters of each equipment state parameter under different local production periods, correct and fuse multiple disturbance coordination matrices based on the disturbance assessment parameters, and construct coordination reference matrices corresponding to multiple sets of production state monitoring data;

[0034] The state anomaly detection module is used to analyze the real-time monitoring data of the mixing equipment based on the collaborative reference matrix after acquiring the real-time monitoring data of the mixing equipment to generate an anomaly detection result of the mixing equipment.

[0035] The present invention has the following beneficial effects:

[0036] The present invention performs state disturbance analysis on multiple groups of production state monitoring data of mixing equipment, extracts the changes in disturbance characteristics of different equipment state parameters during the mixing process to construct multiple disturbance time series matrices, and accurately captures the evolution law of small disturbances in time and parameter dimensions by performing evolution analysis on the changes in disturbance characteristics, further explores the changes in the synergistic characteristics of different equipment state parameters in different mixing processing stages, evaluates the state evolution of equipment state parameters during the mixing process from the perspective of overall synergistic changes, and simultaneously performs disturbance propagation change characteristic analysis on each equipment state parameter, locally quantifies the chain propagation effect of local disturbances between equipment parameters, calculates disturbance evaluation parameters, and corrects and fuses the synergistic matrices of multiple batches, effectively overcoming the parameter state fluctuation change characteristics caused by natural fluctuations of materials, and finally uses the constructed synergistic reference matrix as a quantitative reference for the disturbance change characteristics of equipment state parameters, which is used to monitor the operating status of the mixing equipment in real time, accurately capture small anomalies masked by factors such as material differences during the mixing process, and realize high-precision anomaly detection of production equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] Figure 1 The present invention provides a flowchart of a method for monitoring and managing convenience food production equipment in one embodiment of the present invention.

[0038] Figure 2 This is a structural diagram of a convenience food production equipment monitoring and management system provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0039] In order to enable those skilled in the art to better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0040] See Figure 1 In one embodiment of the present invention, a method for monitoring and managing convenience food production equipment is provided, the method comprising the following steps:

[0041] Step S1: Acquire multiple sets of production status monitoring data of mixing equipment in a convenience food production line, perform state disturbance analysis on each set of production status monitoring data, extract the local disturbance feature sequence of each equipment state parameter, and construct a disturbance time series matrix for each set of production status monitoring data.

[0042] Exemplarily, each set of production status monitoring data represents a production batch of convenience foods related to the mixing process, and includes data from multiple sensors installed on the mixing equipment, such as current sensors, torque sensors, vibration sensors, and temperature sensors. The various device status parameters collected during the operation of the equipment, such as current, spindle torque, speed, and spindle temperature, correspond to corresponding time series detection data, i.e., information such as the device status parameter values ​​at different timestamps. A state disturbance analysis is performed on each set of production status monitoring data, for example, by calculating the deviation of each device status parameter from the normal fluctuation range of the mixing batch to extract disturbance information. Exemplarily, the mean value of each parameter after it stabilizes in the late stage of mixing is selected as a benchmark to calculate the difference between the device status parameter at different times in the time series data and the benchmark parameter, thereby obtaining multiple state disturbance parameters of the device state parameter at different time series. This constructs a local disturbance feature sequence that characterizes the disturbance variation characteristics of the device state parameter during the mixing process. Based on the local disturbance feature sequences of the multiple device state parameters, a disturbance time series matrix corresponding to each set of production status monitoring data is constructed.

[0043] Step S2: perform time period disturbance evolution analysis on each disturbance time series matrix, calculate multiple steady-state characteristic parameters of the disturbance time series matrix in different local production periods, and construct disturbance steady-state characteristic matrices corresponding to multiple groups of production status monitoring data.

[0044] For example, in order to capture the disturbance evolution pattern of the disturbance characteristics of different equipment state parameters during the mixing process, a period disturbance evolution analysis is performed on each disturbance time series matrix, and multiple steady-state characteristic parameters of each disturbance time series matrix in different local production periods are calculated.

[0045] In this process, considering that there is no obvious stage division for the state parameters of different equipment during the mixing process, that is, as the materials are gradually mixed evenly during the mixing process, the fluctuation of the equipment state parameters gradually decreases. In order to capture this dynamic process, the mixing process is pre-divided into multiple local production periods. For example, it is divided into multiple periods according to the actual mixing time. Each period contains multiple time steps in the time series data. Those skilled in the art can make reasonable divisions based on the actual mixing process duration. And based on multiple local production periods, a period disturbance evolution analysis is performed on multiple disturbance time series matrices. First, the multiple state disturbance parameters corresponding to each equipment state parameter in each local production period are determined from the multiple disturbance time series matrices. Taking into account the random fluctuations naturally existing in the equipment during the actual production process, in order to reduce the impact thereof, an uncertainty analysis is performed on the disturbance characteristics of the equipment state parameters in the local production period. First, multiple state disturbance parameters in each local production period are divided into discrete intervals, including determining the value range corresponding to the multiple state disturbance parameters, dividing the range into, for example, 10 equal parts to determine multiple local discrete intervals, and then performing statistical analysis on the multiple state disturbance parameters to obtain the distribution frequency of the equipment state parameters in the local production period with respect to the multiple local discrete intervals. Uncertainty analysis is performed on the equipment state parameters based on the multiple distribution frequencies, for example, calculating the information entropy corresponding to the multiple distribution frequencies to obtain the disturbance distribution entropy values ​​corresponding to the equipment state parameters in different local production periods.

[0046] Then, for multiple disturbance time series matrices, the disturbance reference value of the equipment state parameter in each local production period is determined based on the multiple disturbance time series matrices, which serves as a quantitative parameter of the disturbance intensity of the equipment state parameter in a specific period. For example, the mean of multiple state disturbance parameters in the local production period is taken as the corresponding disturbance reference value. The uncertainty distribution characteristics of the disturbance characteristics are further taken into consideration, and the disturbance reference value is optimized by the disturbance distribution entropy value. In this process, the disturbance distribution entropy values ​​corresponding to the equipment state parameters in different periods can be used as quantitative parameters to measure the degree of uncertainty of the disturbance characteristics, and the disturbance reference weights in different local production periods can be obtained. The disturbance reference values ​​in specific local production periods are weighted and optimized based on the multiple disturbance reference weights to generate the steady-state characteristic parameters of the equipment state parameters in each local production period. Finally, based on the steady-state characteristic parameters corresponding to each equipment state parameter in multiple local production periods, the disturbance steady-state characteristic matrix corresponding to the production status monitoring data is constructed.

[0047] Step S3: Perform time period disturbance coordination analysis on multiple equipment status parameters according to the disturbance time series matrix, calculate multiple disturbance coordination parameters of each equipment status parameter in different local production periods, and construct a disturbance coordination matrix for each set of production status monitoring data.

[0048] For example, considering that the synergistic characteristics between different equipment state parameters will change dynamically as the stirring process evolves, for example, in the early stage after the material is added, the current and torque may have a strong positive correlation, while the temperature and vibration do not change significantly. At the end of the stirring, the correlation between the current and vibration may increase. Therefore, a time period disturbance synergistic analysis is performed on multiple equipment state parameters based on the disturbance time series matrix to extract the pattern changes in the disturbance process and identify the associated features in different time periods. Specifically, for each local production period, the correlation between any two equipment state parameters is calculated to obtain the disturbance synergistic parameters corresponding to each equipment state parameter and the remaining equipment state parameters in each local production period, so as to analyze the stronger coupling relationship that may exist between different parameters in a specific period, and finally construct a disturbance synergistic matrix for each set of production status monitoring data regarding the disturbance synergistic characteristics between parameters in different local production periods.

[0049] Step S4: Analyze the disturbance coordination matrix in combination with the disturbance time series matrix and the disturbance steady-state characteristic matrix, calculate the disturbance evaluation parameters of each equipment state parameter under different local production periods, correct and fuse multiple disturbance coordination matrices based on the disturbance evaluation parameters, and construct coordination reference matrices corresponding to multiple groups of production status monitoring data.

[0050] For example, based on the disturbance time series matrix, the disturbance steady-state characteristic matrix, and the disturbance synergy matrix, the differences in mixing characteristics under different production state monitoring data are analyzed. The mixing impact caused by the initial material addition to the mixing equipment is considered, as well as the flow and deformation characteristics of the material under the operation of the mixing equipment, such as the viscosity of the material during the mixing process. At the same time, combined with the overall stability of the mixing equipment during the mixing process, the differences in mixing characteristics caused by the differences in the material addition under different production batches are analyzed. At the same time, the disturbance propagation changes of the equipment state parameters in different local time periods are further analyzed, and the evolution characteristics of the disturbance state are considered. Finally, the disturbance evaluation parameters of the equipment state parameters in different local production time periods are calculated to characterize the importance of the synergy characteristics of the equipment state parameters in different time periods. Based on the disturbance evaluation parameters, multiple disturbance synergy matrices can be corrected and fused. The data with high reference significance in the multiple disturbance synergy matrices are retained, and the content with low reference significance is discarded. The synergy reference matrix corresponding to multiple sets of production state monitoring data is fused, which contains the overall synergy correlation between each equipment state parameter and the other parameters in a specific time period.

[0051] Step S5: After acquiring the real-time monitoring data of the stirring device, the real-time monitoring data is analyzed based on the collaborative reference matrix to generate an abnormality detection result of the stirring device.

[0052] For example, state disturbance analysis and time period disturbance collaborative analysis are performed on real-time monitoring data to construct a disturbance collaborative matrix corresponding to the real-time monitoring data, which includes the overall collaborative correlation between each equipment state parameter and the remaining parameters in the current production process. Then, the reference value corresponding to the abnormal state assessment is determined according to the collaborative reference matrix. If there is a large deviation in the equipment state parameter, it is considered that there is a potential abnormality. The relevant equipment maintenance personnel can be guided to carry out timely maintenance and respond in advance to possible minor abnormalities in the mixing equipment, so as to avoid major abnormalities that affect the normal operation of the mixing equipment and the production efficiency of convenience foods.

[0053] As an optional implementation scheme, in the above step S4, the disturbance coordination matrix is ​​analyzed in combination with the disturbance time series matrix and the disturbance steady-state characteristic matrix to calculate the disturbance evaluation parameters of each equipment state parameter in different local production periods, specifically including:

[0054] The stirring characteristic vector of the production status monitoring data is constructed according to the disturbance time series matrix, the disturbance steady-state characteristic matrix and the disturbance synergy matrix, including extracting the stirring impact parameters of the production status monitoring data from the disturbance time series matrix, extracting the disturbance level parameters of the production status monitoring data from the disturbance steady-state characteristic matrix, extracting the stirring rheological parameters of the production status monitoring data from the disturbance synergy matrix, constructing the stirring characteristic vector of the production status monitoring data, and calculating the stirring characteristic parameters of the production status monitoring data based on the stirring characteristic vector.

[0055] Exemplarily, for the disturbance time series matrix, the disturbance levels of the vibration parameters of the stirring equipment in the first few local production periods representing the initial stage of material feeding and low material mixing degree, such as the average value of the vibration parameters in multiple local production periods, are used as quantitative parameters of the stirring impact brought by the material on the stirring equipment in the initial stage of stirring, to obtain the stirring impact parameters of the production status monitoring data, and considering that the rheological properties of the material in this process will show more significant changes, the synergistic relationship between the current and torque in this process is used to reflect the rheological properties of the material, and the average value of the disturbance synergistic parameters between the current and torque in this process is calculated as the stirring rheological parameters of the production status monitoring data, and at the same time, according to the steady-state characteristic parameters of the multiple equipment state parameters contained in the disturbance steady-state characteristic matrix, the standard deviation corresponding to the multiple steady-state characteristic parameters of each equipment state parameter is calculated and the average value of the multiple standard deviations is taken to characterize the average disturbance level of the stirring equipment during the material stirring process, to obtain the disturbance level parameters of the production status monitoring data, and to comprehensively evaluate the impact of material differences on the stirring process from multiple levels.

[0056] For the calculation of stirring characteristic parameters, after extracting the stirring characteristic vectors corresponding to multiple groups of production status monitoring data, the mean of multiple stirring characteristic vectors can be calculated as the benchmark material characteristic representation, and then the similarity parameter between the stirring characteristic vector of each group of production status monitoring data and the benchmark vector is calculated as the stirring characteristic parameter of each group of production status monitoring data, which represents the difference between the initial stirring state corresponding to the production status monitoring data and the overall level.

[0057] And according to the disturbance time series matrix and the disturbance steady-state characteristic matrix, the disturbance effect cumulative parameters of the equipment state parameters in each local production period are calculated.

[0058] Specifically, the disturbance effect cumulative parameter is calculated using the following formula:

[0059]

[0060] Where D i,j represents the local disturbance steady-state parameter of the i-th equipment state parameter in the production state monitoring data in the j-th local production period, that is, the steady-state characteristic parameter of the equipment state parameter calculated in the aforementioned step S2 in the local production period, C k.j represents the disturbance coordination parameter between the i-th equipment state parameter in the production state monitoring data and the k-th equipment state parameter in the j-th local production period, e -(M-j) represents the disturbance attenuation factor of the jth local production period, n represents the total number of equipment state parameters, and M represents the total number of local production periods. The above method quantifies the propagation effect of local disturbances in the time and parameter dimensions, which can be used to identify the cumulative amplification process of small anomalies. It is worth noting that under normal operating conditions, the various state parameters of the mixing equipment, such as torque, current, vibration, etc., will fluctuate within a certain range, and these fluctuations are affected by factors such as the mechanical characteristics of the equipment, material flow, and process parameters. The above calculation process comprehensively considers the synergy with other equipment state parameters and the disturbance attenuation characteristics. The local disturbance steady-state parameters finally determined can characterize the response characteristics of the equipment state parameters to the state changes of the mixing equipment, and serve as a baseline to identify whether they deviate from the historical state.

[0061] Finally, the following formula is used to calculate the disturbance assessment parameters corresponding to multiple local production periods of the equipment status parameters under each set of production status monitoring data based on the disturbance effect accumulation parameter and the stirring characteristic parameter:

[0062] H i,j =δ·E i,j +(1-δ)·|D j -D μ |

[0063] Where H i,jrepresents the disturbance evaluation parameter of the i-th equipment state parameter in the production state monitoring data under the j-th local production period, δ represents the stirring characteristic parameter of the production state monitoring data, and E i,j D represents the cumulative parameter of the disturbance effect of the i-th equipment status parameter in the production status monitoring data in the j-th local production period, j represents the steady-state parameter of the period disturbance under the jth local production period in the production status monitoring data, D μ The global disturbance steady-state parameters representing the production status monitoring data, wherein the period disturbance steady-state parameters under the local production period and the global disturbance steady-state parameters of the production status monitoring data can be calculated based on the disturbance steady-state characteristic matrix of the aforementioned steps. The disturbance steady-state characteristic matrix includes the steady-state characteristics of each equipment state parameter under different local production periods. The period disturbance steady-state parameters can be calculated according to the overall steady-state level of multiple equipment state parameters under the local production period. After integrating the disturbance steady-state parameters of multiple period periods, the overall level represented is used as the global disturbance steady-state parameter of the production status monitoring data.

[0064] The significance of the design of the disturbance assessment parameter lies in that when the initial characteristics of the materials being stirred are similar, the propagation of the disturbance characteristics of the equipment state parameters is taken as the dominant factor to evaluate the importance of the equipment state parameters at different time periods during the stirring process. The larger the disturbance assessment parameter, the stronger the synergistic relationship between the equipment state parameters and the other parameters in a specific time period. The disturbance has a greater impact in the current local production period. When the initial characteristics of the materials are relatively similar, the steady-state disturbance energy distribution of the mixing equipment can be described more accurately. When the material characteristics change, such as when the composition of materials in different batches is slightly different, the overall steady-state characteristics of the equipment are used as compensation for the equipment state to adapt to the disturbance fluctuations caused by the change in material characteristics and avoid the misjudgment of abnormal conditions due to material differences. Ultimately, the calculated disturbance assessment parameters can be used to achieve the correction and fusion of multiple disturbance synergy matrices.

[0065] As an optional implementation plan, multiple disturbance coordination matrices are modified and integrated based on disturbance assessment parameters to construct coordination reference matrices corresponding to multiple sets of production status monitoring data, specifically including:

[0066] According to the disturbance evaluation parameters, the local fusion weight W of the disturbance cooperation matrix for each equipment state parameter in each local production period is determined. i,j ,in:

[0067] It is worth noting that the disturbance assessment parameter measures whether the corresponding equipment state parameter has experienced a large disturbance effect in history, and at the same time measures whether the parameter deviates from the global steady state in the current period. The smaller the disturbance assessment parameter, the smaller the disturbance of the equipment state parameter in the period and the more stable the change. The synergistic relationship between the parameter and other parameters is more reliable because there is no large fluctuation. The data in its synergistic matrix can be used as a more stable reference benchmark. The larger the disturbance assessment parameter, the greater the disturbance of the equipment state parameter in the period, or the current disturbance has deviated from the global steady state. It may be caused by abnormal equipment state, changes in material properties, or drastic fluctuations in other state parameters. The synergistic relationship between the parameter and other parameters may be unstable and may be greatly affected by external interference. The data in its synergistic matrix has low reference value. The local fusion weights of the equipment state parameters determined in this way in different local production periods can retain high-reference synergistic data and make significant corrections to low-reference synergistic data.

[0068] In the process of perturbation coordination matrix through local fusion weights of equipment state parameters, for any local time period, multiple disturbance coordination parameters of equipment state parameters are summed and then weightedly corrected through local fusion weights, so as to generate local coordination parameters for each equipment state parameter in each local production time period, and construct a local coordination matrix of each disturbance coordination matrix. For the local coordination matrices corresponding to multiple groups of production status monitoring data, multiple local coordination weights of equipment state parameters in each local production time period are fused to obtain global coordination parameters, so as to construct coordination reference matrices corresponding to multiple groups of production status monitoring data, including the global coordination parameters of each equipment state parameter in each local production time period, which are used to evaluate the disturbance change relationship between each equipment state parameter and the rest of the parameters in a specific time period.

[0069] After obtaining the real-time monitoring data of the mixing equipment, the real-time monitoring data can be analyzed based on the collaborative reference matrix, including state disturbance analysis and time period disturbance collaborative analysis of the real-time monitoring data, and a disturbance collaborative matrix corresponding to the real-time monitoring data is constructed. According to the disturbance collaborative matrix, the real-time collaborative parameters of the equipment state parameters in each local production period are calculated, that is, the sum of the overall disturbance collaborative parameters between the equipment state parameters and the remaining parameters in the current period, which characterizes its overall coordination level in the current period. Then, the global collaborative parameters used as a reference in the current time period are determined through the collaborative reference matrix, and the equipment status parameters are detected for time period anomalies through the global collaborative parameters. If the deviation between the real-time collaborative parameters of the equipment status parameters and the global collaborative parameters is greater than the preset threshold, it is considered that there may be potential anomalies in the performance of the equipment status parameters in the current time period, so as to give an early warning. In this way, the real-time monitoring data is analyzed to generate anomaly detection results for the mixing equipment. The real-time data of each local production time period is analyzed in real time, which can well detect possible minor anomalies in the mixing equipment, and avoid the minor anomalies being covered up and not discovered in advance due to differences in material properties and the dynamic change trends of the status parameters of each equipment during the mixing process, resulting in the efficient production of convenience foods being affected due to the failure to carry out timely maintenance in the early stage of the anomaly.

[0070] See Figure 2 One embodiment of the present invention further provides a convenience food production equipment monitoring and management system, specifically a convenience food production equipment monitoring and management method for realizing the above-mentioned rights, the system comprising:

[0071] The local disturbance analysis module is used to obtain multiple sets of production status monitoring data of mixing equipment in the convenience food production line, including time series detection data of multiple equipment status parameters. It performs state disturbance analysis on each set of production status monitoring data, extracts the local disturbance feature sequence of each equipment status parameter, and constructs the disturbance time series matrix of each set of production status monitoring data.

[0072] The disturbance steady-state feature extraction module is used to perform period disturbance evolution analysis on each disturbance time series matrix, calculate multiple steady-state feature parameters of the disturbance time series matrix in different local production periods, and construct disturbance steady-state feature matrices corresponding to multiple sets of production status monitoring data;

[0073] The disturbance collaborative analysis module is used to perform period disturbance collaborative analysis on multiple equipment status parameters based on the disturbance time series matrix, calculate multiple disturbance collaborative parameters of each equipment status parameter in different local production periods, and construct a disturbance collaborative matrix for each set of production status monitoring data;

[0074] The disturbance state assessment module is used to analyze the disturbance coordination matrix by combining the disturbance time series matrix and the disturbance steady-state characteristic matrix, calculate the disturbance assessment parameters of each equipment state parameter under different local production periods, correct and fuse multiple disturbance coordination matrices based on the disturbance assessment parameters, and construct coordination reference matrices corresponding to multiple sets of production state monitoring data;

[0075] The state anomaly detection module is used to analyze the real-time monitoring data of the mixing equipment based on the collaborative reference matrix after acquiring the real-time monitoring data of the mixing equipment to generate an anomaly detection result of the mixing equipment.

[0076] The foregoing description is merely a detailed description of the present invention, which is intended to enable those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art. Portions not described in detail in this specification are well known to those skilled in the art.

Claims

1. A method for monitoring and managing instant food production equipment, characterized in that: include: Acquire multiple sets of production status monitoring data for mixing equipment in a convenience food production line, including time series detection data of multiple equipment status parameters. Perform state disturbance analysis on each set of production status monitoring data, extract the local disturbance feature sequence of each equipment state parameter, and construct a disturbance time series matrix for each set of production status monitoring data. Perform time period disturbance evolution analysis on each disturbance time series matrix, calculate multiple steady-state characteristic parameters of the disturbance time series matrix in different local production periods, and construct disturbance steady-state characteristic matrices corresponding to multiple sets of production status monitoring data; Based on the disturbance time series matrix, a time period disturbance collaborative analysis is performed on multiple equipment status parameters, multiple disturbance collaborative parameters of each equipment status parameter in different local production periods are calculated, and a disturbance collaborative matrix for each set of production status monitoring data is constructed; The disturbance coordination matrix is ​​analyzed by combining the disturbance time series matrix and the disturbance steady-state characteristic matrix. The disturbance evaluation parameters of each equipment state parameter in different local production periods are calculated. Based on the disturbance evaluation parameters, multiple disturbance coordination matrices are corrected and integrated to construct coordination reference matrices corresponding to multiple sets of production state monitoring data. After acquiring the real-time monitoring data of the mixing equipment, the real-time monitoring data is analyzed based on the collaborative reference matrix to generate an abnormality detection result of the mixing equipment.

2. A method for monitoring and managing instant food production equipment according to claim 1, characterized in that: Calculate multiple steady-state characteristic parameters of the disturbance time series matrix in different local production periods, and construct the disturbance steady-state characteristic matrix corresponding to multiple sets of production status monitoring data, including: Performing a time period disturbance evolution analysis on multiple disturbance time series matrices based on multiple local production periods to determine multiple state disturbance parameters corresponding to the equipment state parameters in each local production period; Divide the multiple state disturbance parameters in each local production period into discrete intervals, obtain the distribution frequency of the equipment state parameters in the local production period with respect to the multiple local discrete intervals, and calculate the disturbance distribution entropy value of the equipment state parameters in the local production period; According to multiple disturbance time series matrices, the disturbance reference value of the equipment state parameter in each local production period is determined, and the disturbance reference value is optimized by the disturbance distribution entropy value to generate the steady-state characteristic parameter of the equipment state parameter in each local production period. According to the steady-state characteristic parameters corresponding to each equipment state parameter in multiple local production periods, the disturbance steady-state characteristic matrix is ​​generated.

3. A method for monitoring and managing instant food production equipment according to claim 1, characterized in that: The disturbance coordination matrix is ​​analyzed by combining the disturbance time series matrix and the disturbance steady-state characteristic matrix to calculate the disturbance evaluation parameters of each equipment state parameter in different local production periods, including: A stirring characteristic vector of the production state monitoring data is constructed according to the disturbance time series matrix, the disturbance steady-state characteristic matrix and the disturbance synergy matrix, and stirring characteristic parameters of the production state monitoring data are calculated based on the stirring characteristic vector; The disturbance effect accumulation parameters of the equipment state parameters in each local production period are calculated based on the disturbance time series matrix and the disturbance steady-state characteristic matrix. The following formula is used to calculate the disturbance evaluation parameters corresponding to multiple local production periods of the equipment state parameters under each set of production state monitoring data based on the disturbance effect accumulation parameters and the stirring characteristic parameters: H i,j =δ·E i,j +(1-δ)·|D j -D μ | Where H i,j represents the disturbance evaluation parameter of the i-th equipment state parameter in the production state monitoring data under the j-th local production period, δ represents the stirring characteristic parameter of the production state monitoring data, and E i,j D represents the cumulative parameter of the disturbance effect of the i-th equipment status parameter in the production status monitoring data in the j-th local production period, j represents the steady-state parameter of the period disturbance under the jth local production period in the production status monitoring data, D μ Represents the global disturbance steady-state parameters of production status monitoring data.

4. A method for monitoring and managing instant food production equipment according to claim 3, characterized in that: For disturbance effect accumulation parameters, it also includes: The disturbance effect accumulation parameter is calculated using the following formula: Where D i,j represents the local disturbance steady-state parameter of the i-th equipment state parameter in the production state monitoring data under the j-th local production period, C k.ij represents the disturbance coordination parameter between the i-th equipment state parameter in the production state monitoring data and the k-th equipment state parameter in the j-th local production period, e -(M-j) represents the disturbance attenuation factor of the jth local production period, n represents the total number of equipment state parameters, and M represents the total number of local production periods.

5. The method for monitoring and managing instant food production equipment according to claim 1, characterized in that: Based on the disturbance assessment parameters, multiple disturbance coordination matrices are corrected and integrated to construct coordination reference matrices corresponding to multiple sets of production status monitoring data, including: According to the disturbance assessment parameters, the local fusion weight of the disturbance coordination matrix for each equipment state parameter in each local production period is determined. According to the local fusion weight of the equipment state parameter in each local production period, multiple disturbance coordination parameters of the equipment state parameter in the local production period are corrected to generate local coordination parameters of the equipment state parameter. The local coordination matrix corresponding to each group of production status monitoring data is constructed, and the multiple local coordination matrices are fused to generate coordination reference matrices corresponding to multiple groups of production status monitoring data.

6. A method for monitoring and managing instant food production equipment according to claim 5, characterized in that: Analyze real-time monitoring data based on the collaborative reference matrix to generate abnormal detection results for mixing equipment, including: Perform state disturbance analysis and time period disturbance collaborative analysis on the real-time monitoring data, construct a disturbance collaborative matrix corresponding to the real-time monitoring data, calculate the real-time collaborative parameters of the equipment state parameters in each local production period based on the disturbance collaborative matrix, perform time period anomaly detection on the equipment state parameters through the collaborative reference matrix and multiple real-time collaborative parameters of the equipment state parameters, and generate anomaly detection results for the mixing equipment.

7. A monitoring and management system for instant food production equipment, characterized in that: The system is used to implement the method for monitoring and managing instant food production equipment according to any one of claims 1 to 6, comprising: The local disturbance analysis module is used to obtain multiple sets of production status monitoring data of mixing equipment in the convenience food production line, including time series detection data of multiple equipment status parameters. It performs state disturbance analysis on each set of production status monitoring data, extracts the local disturbance feature sequence of each equipment status parameter, and constructs the disturbance time series matrix of each set of production status monitoring data. The disturbance steady-state feature extraction module is used to perform period disturbance evolution analysis on each disturbance time series matrix, calculate multiple steady-state feature parameters of the disturbance time series matrix in different local production periods, and construct disturbance steady-state feature matrices corresponding to multiple sets of production status monitoring data; The disturbance collaborative analysis module is used to perform period disturbance collaborative analysis on multiple equipment status parameters based on the disturbance time series matrix, calculate multiple disturbance collaborative parameters of each equipment status parameter in different local production periods, and construct a disturbance collaborative matrix for each set of production status monitoring data; The disturbance state assessment module is used to analyze the disturbance coordination matrix by combining the disturbance time series matrix and the disturbance steady-state characteristic matrix, calculate the disturbance assessment parameters of each equipment state parameter under different local production periods, correct and fuse multiple disturbance coordination matrices based on the disturbance assessment parameters, and construct coordination reference matrices corresponding to multiple sets of production state monitoring data; The state anomaly detection module is used to analyze the real-time monitoring data of the mixing equipment based on the collaborative reference matrix after acquiring the real-time monitoring data of the mixing equipment to generate an anomaly detection result of the mixing equipment.

Images