Fodder whole-process production data acquisition method and system of smart factory

Abstract

The invention relates to the technical field of data processing, in particular to a feed full-process production data acquisition method and system for a smart factory, and the method comprises the steps: obtaining production data corresponding to each data acquisition device at each production stage in a feed production process; obtaining a position influence coefficient of each data acquisition device in each production stage in combination with the position information of the data acquisition devices according to the data difference between the production data corresponding to the data acquisition devices at adjacent positions in each production stage; according to the similar condition between the position influence coefficients of different data acquisition devices in each production stage, and in combination with the fluctuation condition of the environment information, obtaining a data condition effective index of each production stage; and according to the data condition effective index of each production stage, whether the data acquisition frequency is adjusted is analyzed, and a data acquisition method is determined. According to the invention, the data acquisition frequency can be adaptively adjusted to optimize the data acquisition method, and the effectiveness of data acquisition is improved.

Description

Technical Field

[0001] The present invention relates to the field of data processing technology, and in particular to a method and system for collecting feed production data throughout a smart factory. Background Art

[0002] With the development of the livestock and poultry farming industry, complete feed production lines have become an essential tool for improving farming efficiency. The workflow of a complete feed production line primarily includes five key steps: cleaning, crushing, mixing, granulation, and packaging, forming a complete and efficient production system. IoT technology and data acquisition systems play a vital role in the entire feed production process of smart factories. IoT technology interconnects various sensors and devices, monitoring key parameters such as temperature, humidity, flow, and pressure, enabling real-time data transmission and monitoring, ensuring the normal operation of the production environment and equipment, and enabling remote management and control.

[0003] In the actual production of multiple feed types, varying feed ratios can cause changes in physical properties across multiple stages of the feed process, including moisture content and particle size. This can impact the efficiency and quality of feed ingredients within that stage of production. These changes can occur through adhesion, accumulation, and impact in conveyor pipes, leading to reduced conveying efficiency, decreased pelleting quality, and even increased equipment vibration. This impact not only impacts feed production efficiency and quality, but also shortens equipment life. Existing methods employing fixed-frequency data collection processes are susceptible to environmental, locational, and other objective factors, resulting in poor data collection effectiveness. Summary of the Invention

[0004] In order to solve the technical problem that the existing methods for collecting data on the entire feed production process have poor effectiveness, the present invention aims to provide a method and system for collecting data on the entire feed production process in a smart factory. The technical solutions adopted are as follows:

[0005] In a first aspect, the present invention provides a method for collecting feed production data throughout a smart factory, comprising:

[0006] Through different data collection devices in each production stage of the feed production process, the production data corresponding to each data collection device is obtained;

[0007] According to the difference in data monitoring between the production data corresponding to the data acquisition devices at adjacent positions in each production stage, combined with the location information of each data acquisition device in each production stage, the position influence coefficient of each data acquisition device in each production stage is obtained;

[0008] Based on the similarity between the position influence coefficients of different data acquisition devices in each production stage and the fluctuation of environmental information in each production stage, the effective index of data status in each production stage is obtained;

[0009] According to the effective indicators of data status in each production stage, analyze whether to adjust the data collection frequency and determine the data collection method for each data collection device.

[0010] Preferably, the position influence coefficient of each data acquisition device in each production stage is obtained based on the difference in data monitoring between the production data corresponding to the data acquisition devices at adjacent positions in each production stage, combined with the position information of each data acquisition device in each production stage, and specifically includes:

[0011] Obtaining a position correlation factor for each data acquisition device in each production stage based on the difference between the fluctuation of production data corresponding to each data acquisition device in each production stage and the fluctuation of production data corresponding to data acquisition devices at adjacent positions;

[0012] Determining a relative distance factor for each data acquisition device in each production stage based on the distance between the location of each data acquisition device in each production stage and the output location of the corresponding production stage;

[0013] Based on the ratio between the position correlation factor and the relative distance factor, a position influence coefficient of each data acquisition device in each production stage is determined.

[0014] Preferably, obtaining the position correlation factor of each data acquisition device in each production stage based on the difference between the fluctuation of production data corresponding to each data acquisition device in each production stage and the fluctuation of production data corresponding to data acquisition devices at adjacent positions specifically includes:

[0015] For each production stage, determining the monitoring difference degree of each production data corresponding to each data acquisition device based on the difference between each production data corresponding to each data acquisition device and the mean of all production data;

[0016] Based on the difference between the mean of the monitoring difference of all production data corresponding to each data acquisition device and the mean of the monitoring difference of all production data corresponding to the data acquisition devices at adjacent positions, the position correlation factor of each data acquisition device in each production stage is determined.

[0017] Preferably, the data status effectiveness indicator for each production stage is obtained based on the similarity between the position influence coefficients of different data acquisition devices in each production stage and the fluctuation of environmental information in each production stage, specifically including:

[0018] Based on the similarity between the position influence coefficients of different data acquisition devices in each production stage, the data acquisition devices in the same production stage are clustered. According to the clustering of the data acquisition devices in the clustering results corresponding to each production stage, the category fluctuation coefficient of each production stage is obtained;

[0019] Determine the abnormal sensitivity factor for each production stage based on the location influence coefficient and category fluctuation coefficient of all data acquisition devices in each production stage;

[0020] Acquire environmental data at the location of each data acquisition device in each production stage under different production parameters to form an environmental data sequence for each production stage under different production parameters;

[0021] According to the difference between the environmental data sequence of each production stage under different production parameters and the equilibrium situation of the environmental data sequence of the same production stage under all production parameters, combined with the abnormal sensitivity factor, the effective index of the data status of each production stage is obtained.

[0022] Preferably, obtaining the category fluctuation coefficient of each production stage according to the clustering of the data acquisition devices in the clustering results corresponding to each production stage specifically includes:

[0023] For each production stage, the proportion of the number of data acquisition devices contained in each cluster in the clustering results is obtained as the category ratio of each cluster in the clustering results, and the degree of dispersion of all category ratios in the production stage is taken as the category fluctuation coefficient of the corresponding production stage.

[0024] Preferably, the difference between the environmental data sequence of each production stage under different production parameters and the equilibrium situation of the environmental data sequence of the same production stage under all production parameters is combined with the abnormal sensitivity factor to obtain the effective indicator of the data status of each production stage, which specifically includes:

[0025] The environmental equilibrium sequence is determined based on the mean of the environmental data at the same data acquisition device location under all production parameters in each production stage; the effective index of the data status of each production stage is determined based on the difference distance between the environmental data sequence of each production stage and the environmental equilibrium sequence and the ratio relationship between the abnormal sensitivity factors under all production parameters.

[0026] Preferably, the determination of the abnormal sensitivity factor for each production stage based on the position influence coefficient and category fluctuation coefficient of all data acquisition devices in each production stage specifically includes:

[0027] The ratio between the mean of the position influence coefficients of all data acquisition devices in each production stage and the category fluctuation coefficient is used as the abnormal sensitivity factor of each production stage.

[0028] Preferably, the step of analyzing whether to adjust the data collection frequency and determining the data collection method of each data collection device based on the data status effectiveness index of each production stage specifically includes:

[0029] When the data status validity indicator of each production stage does not meet the validity condition, the data collection operation is performed after adjusting the data collection frequency of the data collection device of the production stage; when the data status validity indicator of each production stage meets the validity condition, the data collection operation is performed at the current data collection frequency.

[0030] Preferably, the validity condition is specifically: the data status validity index of the production stage is greater than or equal to a preset validity threshold.

[0031] In a second aspect, the present invention provides a feed production data collection system for a smart factory. The system is used to implement the steps of a feed production data collection method for a smart factory. The feed production data collection system for a smart factory specifically includes:

[0032] The data acquisition module is used to obtain the production data corresponding to each data acquisition device through different data acquisition devices in each production stage of the feed production process;

[0033] A position feature analysis module is used to obtain the position influence coefficient of each data acquisition device in each production stage based on the difference in data monitoring between the production data corresponding to the data acquisition devices at adjacent positions in each production stage and the position information of each data acquisition device in each production stage;

[0034] The effective feature analysis module is used to obtain the effective indicators of the data status of each production stage based on the similarities between the position influence coefficients of different data acquisition devices in each production stage and the fluctuation of environmental information in each production stage;

[0035] The collection method determination module is used to analyze whether to adjust the data collection frequency based on the data status effectiveness indicators of each production stage and determine the data collection method of each data collection device.

[0036] The embodiments of the present invention have at least the following beneficial effects:

[0037] The present invention first obtains production data from each data acquisition device at different production stages, providing a data foundation for subsequent adaptive feature analysis of different production stages. Then, the data monitoring differences between adjacent data acquisition locations within the same production stage are analyzed. Combined with the corresponding data acquisition location information, the position influence coefficient of the data acquisition device is preliminarily determined, measuring the direct impact of data anomalies corresponding to the data acquisition location on output quality. Furthermore, based on the similarities in the position influence levels of different data acquisition devices within the same production stage, combined with changes in environmental information, the effectiveness of the data monitored in real time at each production stage is comprehensively reflected. Ultimately, the data status effectiveness index is used to analyze whether the data acquisition frequency needs to be adjusted to optimize the data acquisition method. By conducting an in-depth analysis of the changing relationship between the position information of the data acquisition device, the present invention can adaptively adjust the data acquisition frequency to optimize the data acquisition method, thereby improving the effectiveness of data acquisition to a certain extent, allowing manufacturers to monitor and optimize the feed ratio in real time. This data monitoring process can ensure that the physical properties of the feed meet standards and improve the production quality of the feed. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. 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 paying any creative work.

[0039] Figure 1 This is a flowchart of the steps of a method for collecting feed production data throughout the entire process of a smart factory provided by the present invention;

[0040] Figure 2 is a flowchart of the steps of the method for obtaining the position influence coefficient provided by the present invention;

[0041] Figure 3 It is a flowchart of the steps of the method for obtaining effective indicators of data status at each production stage provided by the present invention;

[0042] Figure 4 This is a structural diagram of a feed full-process production data acquisition system for a smart factory provided by the present invention. DETAILED DESCRIPTION

[0043] In order to further illustrate the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following, in combination with the accompanying drawings and preferred embodiments, describes in detail the specific implementation method, structure, characteristics and effects of a feed full-process production data collection method and system for a smart factory proposed by the present invention.

[0044] Before introducing the specific solutions provided in the embodiments of the present application, the specific process of the entire production process in the present application is explained to facilitate understanding by those skilled in the art, and does not limit the use in the present application.

[0045] The workflow of the complete feed production line mainly includes five key processes: cleaning, crushing, mixing, granulation and packaging, as follows:

[0046] (1) Cleaning process: Feed raw materials are cleaned by mechanized equipment to remove impurities, sand, and other substances that are not conducive to animal digestion. After cleaning, the raw materials usually need to be dried to remove excess water to avoid moisture problems in subsequent processing.

[0047] (2) Crushing process: The cleaned feed ingredients are fed into a crusher for pulverization. The purpose of crushing is to process the raw materials into uniform particle size, which helps improve the efficiency of subsequent mixing and processing. Different types of feed ingredients require different crushing levels to ensure optimal processing results and animal digestion and absorption rate.

[0048] (3) Mixing process: Various crushed feed ingredients and additives such as vitamins and minerals are mixed according to a preset formula. This process is usually performed by a mixer to ensure that the different ingredients are evenly blended and achieve a balanced nutritional composition.

[0049] (4) Granulation: After the mixed raw materials enter the granulation process, the mixed feed is pressed into granules. This process not only increases the density of the feed, making it easier to store and transport, but also improves the digestibility and absorption rate of the feed. During the granulation process, the control of temperature and pressure is crucial, which can effectively promote the adhesion of the feed, making it easier for animals to digest.

[0050] (5) Packaging: The finished feed is automatically packaged through the packaging process. The packaging equipment measures the pellets, bags them, and seals them, ensuring that each bag is of uniform weight and that the packaging is intact. The packaging materials used are generally moisture-proof and rust-proof to extend the shelf life of the feed. After packaging, the finished feed is labeled and stored in the warehouse for shipment or distribution to customers.

[0051] In the following description, different references to "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.

[0052] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0053] The following describes in detail a method and system for collecting data on the entire feed production process in a smart factory provided by the present invention with reference to the accompanying drawings.

[0054] See also Figure 1 , which shows a flowchart of a method for collecting feed production data throughout a smart factory according to an embodiment of the present invention. The method includes the following steps:

[0055] Step S100: obtaining production data corresponding to each data acquisition device through different data acquisition devices in each production stage of the feed production process.

[0056] During feed production, the accuracy of sensor device setup and the layout of sensor installation locations significantly impact the effectiveness of data collection. This is especially true in multi-recipe production scenarios, where differences in raw material ratios can lead to variations in physical properties like moisture content and particle size, potentially causing problems such as adhesion, accumulation, and impact in transmission pipelines. The manifestation of these anomalies in production data is closely related to the correlation between sensor device locations. Therefore, it is necessary to carefully analyze the data correlations between sensor device locations to optimize data collection strategies and enhance control over the production process.

[0057] Taking into account that the environmental data and raw material production status data in each production stage have a direct relationship with controlling the quality of finished products and semi-finished products in the corresponding production stage, different data acquisition devices are set up in each production stage of the entire feed production process to monitor the production data of the processing process in each production stage in real time.

[0058] As a specific example, different types of sensors are used as data acquisition devices, and the number of sensors set is selected according to the process length of different production stages. The production data collected by the sensors in the feed product production process is extracted and stored in the order of the production process. The sampling period is set to 1 hour, and the data is collected every 5 minutes. The production data refers to the data collected by the corresponding sensor. In order to avoid the dimensionality problem affecting the subsequent data analysis results, this embodiment standardizes all the collected data. The method of data standardization is a well-known technology and will not be introduced in detail here.

[0059] More specifically, in some embodiments, temperature sensors, humidity sensors, flow sensors, etc. may be installed during the production phase of the cleaning process; vibration sensors, current sensors, and pressure sensors may be installed during the production phase of the crushing process; torque sensors, temperature sensors, and current sensors may be installed during the production phase of the stirring process; temperature sensors, pressure sensors, humidity sensors, and laser particle size analyzers may be installed during the production phase of the granulation process; and weight sensors and visual inspection cameras (for extracting target size data) may be installed during the production phase of the packaging process. The type and location of sensors vary according to different feed production requirements and can be determined by the implementer based on the specific implementation scenario.

[0060] At this point, production data from each data collection device within each preset sampling period is available for each production stage, enabling real-time monitoring of production conditions during that stage. This implementation primarily addresses the correlation and impact between data collected by different data collection devices within the same production stage, adaptively adjusting the data collection frequency to improve the effectiveness of collected data.

[0061] Step S200, based on the difference in data monitoring between the production data corresponding to the data acquisition devices at adjacent positions in each production stage, combined with the location information of each data acquisition device in each production stage, obtain the position influence coefficient of each data acquisition device in each production stage.

[0062] The accuracy of data acquisition devices is easily affected by their location. Production issues such as adhesion and accumulation often lead to coordinated changes in data from adjacent locations. For example, a blockage in one location can affect data collection results at both preceding and following locations. The degree of difference in the performance of data collected by data acquisition devices at two different locations can reflect the current state of data collection. Whether this is due to adhesion, accumulation, and other issues that permeate the production process at adjacent locations, causing data synchronization anomalies, or reflecting actual production process issues and the differences in data changes caused by location.

[0063] Based on this, for any production stage, within a data collection cycle, we first analyze the discreteness or fluctuation of the production data collected by the data collection device corresponding to each position. Then, we quantify the characteristic analysis results of the first stage by comparing the differences between the discreteness or fluctuation analysis results of the data corresponding to two adjacent positions. That is, we use the position correlation factor to characterize the correlation between the change in the data collected by the corresponding data collection device and the data collection position. Furthermore, we combine the distance between each data collection device and the output position of the production stage in which it is located to finally quantify the position influence coefficient corresponding to each data collection device. The closer the data collection position is to the semi-finished product output position in the production stage, the greater the direct impact of its data on the quality of the semi-finished product. The position influence coefficient further comprehensively reflects the impact of the data collection situation at the location of the data collection device on the output quality of the production stage.

[0064] Step S300 , obtaining a data status validity indicator for each production stage based on the similarity between the position influence coefficients of different data acquisition devices in each production stage and the fluctuation of environmental information in each production stage.

[0065] Throughout the entire feed production process, pelleting quality and the quality of semi-finished products at each stage are highly dependent on the rationality of the production process setup. This is specifically manifested in the synergistic effects of key processes such as cleaning, crushing, mixing, and pelleting. For example, the particle size distribution of corn kernels during the crushing stage directly affects the uniformity of the mixing process, which in turn determines the structural strength and nutrient retention of the finished pellets. This multi-stage indirect influence makes the location of data monitoring a key factor in capturing quality fluctuations.

[0066] Process parameters (e.g., crusher speed, mixing time) at each production stage (e.g., crushing, mixing) have a dominant direct impact on semi-finished product quality. The location of monitoring equipment (e.g., crusher outlet vs. mixer inlet) determines the sensitivity and representativeness of data collection. If abnormalities in monitoring data from different locations within the same production stage are highly similar, this suggests the anomaly likely stems from issues with upstream process parameter settings rather than the monitoring location itself.

[0067] Based on this feature, we first analyze the similarities between the position influence coefficients of different data acquisition devices in the same production stage, and determine the stability of the influence of the data monitoring position in each production stage. Combined with the position influence coefficient of the data acquisition device in each production stage, we can more accurately and intuitively reflect the sensitivity of the data monitoring position to the perception of production quality anomalies, that is, determine the final anomaly sensitivity factor.

[0068] Furthermore, considering the discrepancy between equipment operating data and product quality data in the multi-ratio feed production scenario of a smart factory, which stems from differences in the physical properties of the formulated raw materials, this discrepancy reflects the effectiveness of data monitoring that impacts the entire production process in multiple ways.

[0069] For example, the physical properties of feed formulations with varying ratios can interfere with the production process in multiple ways. Specifically, adding high-fat or high-protein ingredients can increase feed viscosity, while raw materials with higher humidity can cause the feed to absorb moisture after mixing, increasing the risk of sticking. Furthermore, uneven particle shape and size, as well as compression during transportation, can increase contact pressure between particles, leading to sticking. The greater the discrepancy in the obtained formulation process data, the more significant the potential impact of formulation adjustments on final quality.

[0070] Comparing equipment operating data with product quality data shows that while recipe changes can alter process parameters like feed ratio and mixing time, the set parameters for core equipment (such as crushers and granulators) typically remain constant. This fixed parameter, variable input allows equipment operating data to more purely reflect changes in the material's physical properties, rather than fluctuations in the equipment's own state.

[0071] If the anomaly patterns in monitoring data for different formulations within a production phase are highly similar, this indicates that the data monitoring location settings for that production phase are unable to effectively distinguish formulation-specific anomalies and their monitoring value needs to be reassessed. For specific formulations, such as high-viscosity feeds, the monitoring data at a particular phase may be significantly differentiating. In this case, the monitoring strategy needs to be optimized for each formulation individually, such as increasing the sampling frequency.

[0072] Based on this characteristic, the analysis process for the effectiveness of data monitoring at each production stage further incorporates the data monitoring process corresponding to different feed ratios during feed production. It can be understood that each feed ratio formula corresponds to a complete feed production process, meaning that the analysis process for abnormal sensitivity factors at each production stage corresponding to each feed ratio is the same.

[0073] Based on the analysis of the impact of each data monitoring location under different feed ratios, combined with the deviation of environmental data in the feed production process, a comprehensive analysis of the effectiveness of the data collected at the data monitoring location in each production stage is conducted, and finally the effective indicators of the data status in each production stage are determined.

[0074] Step S400 : analyzing whether to adjust the data collection frequency based on the data status validity index of each production stage, and determining the data collection method of each data collection device.

[0075] For each production stage, when the value of the data status validity index is larger, it reflects that the data collected in the corresponding production stage is more effective, indicating that at the collection frequency corresponding to the data collection device set in the production stage, it is of great significance to conduct real-time monitoring of the status of the feed product production process. This reflects that the data collection parameter settings are more reasonable at this time, so there is no need to adjust the data collection frequency too much to continue the real-time monitoring process.

[0076] The smaller the value of the data status effectiveness indicator, the less effective the data collected in the corresponding production stage, indicating that data monitoring at the current data collection frequency has certain deficiencies, such as quality impact being underestimated or environmental differences not being captured. At this time, it is necessary to further increase the data collection frequency to more carefully capture the detailed features reflected in the data. Increasing the data collection frequency can effectively monitor abnormal conditions in the production process.

[0077] Based on this, when the data status validity indicator of each production stage does not meet the validity condition, the data collection frequency of the data collection device of the production stage is adjusted before the data collection operation is performed; when the data status validity indicator of each production stage meets the validity condition, the data collection operation is performed at the current data collection frequency. The validity condition is specifically: the data status validity indicator of the production stage is greater than or equal to a preset validity threshold.

[0078] The data status validity indicator during the production phase failing to meet the validity condition means that the data collected during the production phase does not meet the validity requirement. Furthermore, the data status validity indicator during the production phase meeting the validity condition means that the data collected during the production phase meets the validity requirement. As a specific example, considering that the value of the data status validity indicator is a normalized value, in this embodiment, the validity threshold is set to 0.2. Implementers can set this threshold based on specific implementation scenarios.

[0079] When the data status effectiveness index of each production stage is smaller and less than the effective threshold, it means that the effectiveness of the data monitoring result is low at this time, and the data collection process or data collection strategy needs to be adjusted. This embodiment increases the data collection frequency to capture the detailed characteristics of the production process in more detail. The specific adjustment operation can be determined by relevant professional staff. It is also possible to set different levels of data collection frequency. When the data status effectiveness index of the production stage is less than the effective threshold, the data collection frequency corresponding to the data collection device in the production stage is increased by one level. The higher the level, the higher the data collection frequency, and the frequency intervals between adjacent levels are the same.

[0080] When the data status effectiveness index of each production stage is larger and greater than or equal to the effectiveness threshold, it means that the data collection strategy at this time is more appropriate, and the data collection results can more effectively monitor the production process. Therefore, there is no need to adjust the data collection frequency at this time, and the production process can be continuously monitored.

[0081] In some embodiments, as Figure 2 As shown, the method for obtaining the position influence coefficient in step S200 can be implemented by steps S201 to S203.

[0082] Step S201 , obtaining a position correlation factor of each data acquisition device in each production stage based on the difference between the fluctuation of production data corresponding to each data acquisition device in each production stage and the fluctuation of production data corresponding to data acquisition devices at adjacent positions.

[0083] In this embodiment, any production stage is taken as an example for explanation. In the first step, based on the difference between each production data corresponding to each data acquisition device and the mean of all production data, the monitoring difference degree of each production data corresponding to each data acquisition device is determined.

[0084] It can be understood that in step S100, multiple production data within a data collection cycle are obtained by each data collection device, and then the deviation between each production data and the mean of the overall production data can be monitored to reflect the degree of data difference corresponding to each production data. The monitoring difference degree of any production data of any data collection device within a data collection cycle can be specifically expressed as where X i,n It represents the nth production data of the i-th data acquisition device in a data acquisition cycle in any production stage, It represents the mean value of all production data of the i-th data acquisition device in a data acquisition cycle in any production stage.

[0085] In the second step, based on the difference between the mean of the monitoring difference of all production data corresponding to each data acquisition device and the mean of the monitoring difference of all production data corresponding to the data acquisition devices at adjacent positions, the position correlation factor of each data acquisition device in each production stage is determined.

[0086] It can be understood that the degree of data difference is calculated for each production data corresponding to each data acquisition device, reflecting the data deviation corresponding to each production data, and then the data deviation of the overall production data of the data acquisition device within a data acquisition cycle is represented by the mean value. Then, the difference in data deviation between the data acquisition devices at two adjacent positions is used to measure whether the degree of data deviation between a data acquisition device and the data acquisition device at its adjacent position is consistent.

[0087] More specifically, this embodiment calculates the absolute difference between the mean of the monitored differences of all production data corresponding to each data acquisition device and the mean of the monitored differences of all production data corresponding to adjacent data acquisition devices, and normalizes the calculated absolute difference to obtain the position correlation factor corresponding to each data acquisition device. The normalization method can be either maximum or minimum normalization, and the implementer can select this method based on the specific implementation scenario.

[0088] The greater the difference in the degree of deviation between the production data collected by two adjacent data acquisition devices, the greater the difference in the characteristic fluctuations of the data collected at the two locations. The more likely the difference in the data fluctuations is due to different locations. The smaller the difference in the degree of deviation between the production data collected by two adjacent data acquisition devices, the more consistent the characteristic fluctuations of the data collected at the two locations. The more likely the difference in the data fluctuations is due to various conditions such as adhesion, accumulation, and impact between different locations.

[0089] Based on this, the position correlation factor characterizes the correlation between the data fluctuation and position distribution of the data acquisition devices at different positions. The larger the value of the position correlation factor of the data acquisition device, the greater the impact of the abnormal performance between the data collected at the corresponding position and the data collected at other positions on the location of the data acquisition device.

[0090] It should be noted that this embodiment mainly analyzes the degree of data deviation between each data acquisition device and the data acquisition device corresponding to the next adjacent position in the production process. If the last data acquisition device cannot obtain the next adjacent position, the data feature performance between the data acquisition device and the data acquisition device corresponding to the previous adjacent position can be analyzed.

[0091] Step S202 : determining a relative distance factor of each data acquisition device in each production stage based on the distance between the location of each data acquisition device in each production stage and the output location of the corresponding production stage.

[0092] For any data acquisition device, the closer it is to the semi-finished product output location, the greater the direct impact of the data performance at that location on the semi-finished product quality. The farther the data acquisition device is from the semi-finished product output location, the smaller the direct impact of the data performance at that location on the semi-finished product quality.

[0093] In this embodiment, the relative distance factor is calculated based on the location of each data acquisition device in each production stage and the number of data acquisition devices included in the output location of that production stage. For example, the relative distance factor corresponding to the data acquisition device closest to the output location of a production stage is 1, meaning that the data acquisition device closest to the output location of that production stage is the only data acquisition device between it and the output location.

[0094] In other embodiments, the implementer may also select other methods to determine the relative distance factor according to the specific implementation scenario. For example, in the production process, the actual distance between each data acquisition device and the output location of the production stage is determined as the corresponding relative distance factor, etc.

[0095] Step S203 : determining the position influence coefficient of each data acquisition device in each production stage based on the ratio between the position correlation factor and the relative distance factor.

[0096] Specifically, for any production stage, the ratio of each data acquisition device's location correlation factor to its relative distance factor is used to determine the location influence coefficient for each data acquisition device. The location influence coefficient combines the direct impact of the monitoring location and the spatial distance, representing the significance of the impact of the data acquisition device's data monitoring location on quality. A larger value indicates a greater impact from the data acquisition device's data monitoring location.

[0097] In some embodiments, as Figure 3 As shown, the method for obtaining the data status validity indicator of each production stage in step S300 can be implemented by steps S301 to S304.

[0098] Step S301: Based on the similarity between the position influence coefficients of different data acquisition devices in each production stage, the data acquisition devices in the same production stage are clustered, and the category fluctuation coefficient of each production stage is obtained according to the aggregation of the data acquisition devices in the clustering results corresponding to each production stage.

[0099] Specifically, for any production stage, the Euclidean distance between the position influence coefficients of every two data acquisition devices is used as the classification metric distance to perform density clustering on all data acquisition devices to obtain the clustering results corresponding to each production stage, which includes one or more cluster clusters. The density clustering can adopt the DBSCAN clustering algorithm, which is a well-known technology. The specific implementation method will not be introduced in detail here. In other embodiments, the implementer can also select a suitable density clustering algorithm according to the specific implementation scenario.

[0100] More specifically, in a production stage, the position influence coefficients corresponding to all data acquisition devices are used as sample points to form a data set, reflecting the distribution of influence intensity of different data monitoring positions. The data acquisition devices corresponding to position influence coefficients with similar values are grouped into the same cluster through the density clustering algorithm. Within the same cluster, the data monitoring positions of the data acquisition devices have similar influence on the output quality.

[0101] Furthermore, in order to measure the stability of the impact of the data monitoring locations of all data acquisition devices on output quality in each production stage, the method for obtaining the category fluctuation coefficient is as follows: for each production stage, the proportion of the number of data acquisition devices contained in each cluster in the clustering results is obtained as the category ratio of each cluster in the clustering results, and the degree of dispersion of all category ratios in the production stage is used as the category fluctuation coefficient of the corresponding production stage.

[0102] For any production stage, if the location influence coefficients of most data acquisition devices are close, it means that the degree of influence of the data monitoring locations of most data acquisition devices on the output quality is relatively similar. Then, at the data clustering result level, most data acquisition devices are distributed in one cluster, and the number of data acquisition devices contained in other clusters is relatively small.

[0103] In this embodiment, for any production stage, the ratio of the total number of data acquisition devices contained in each cluster in the clustering result to the total number of data acquisition devices contained in the production stage is used as the category ratio of each cluster in the clustering result, and the variance of the category ratios of all clusters corresponding to the production stage is calculated to obtain the category fluctuation coefficient of the production stage, that is, the variance is used to measure the degree of discreteness of the data.

[0104] When the impact levels of most data acquisition devices are similar, in the clustering results for the corresponding production stage, the category ratio of one cluster is larger, while the category ratios of other clusters are smaller. In this case, the variance of the category ratios of all clusters is larger, and the corresponding category fluctuation coefficient is larger. When the impact levels of each data acquisition device are different within a production stage, the category ratios of each cluster are closer in the clustering results for the corresponding production stage. In this case, the variance of the category ratios of all clusters is smaller, and the corresponding category fluctuation coefficient is smaller.

[0105] Based on this, the category fluctuation coefficient corresponding to the production stage reflects the stability and variability of the impact of the corresponding position of the data acquisition device on the output quality.

[0106] Step S302 : determining the abnormal sensitivity factor of each production stage based on the position influence coefficients and category fluctuation coefficients of all data acquisition devices of each production stage.

[0107] In this embodiment, the ratio between the mean of the position influence coefficients of all data acquisition devices in each production stage and the category fluctuation coefficient is used as the abnormal sensitivity factor of each production stage.

[0108] A larger value for the category fluctuation coefficient indicates a higher consistency and similarity in the degree of influence across multiple data monitoring locations. In this case, the impact patterns of data monitoring at different locations within a production phase are highly similar. To a certain extent, the data monitoring locations within that production phase cannot be effectively distinguished, and the corresponding data collection results have a low sensitivity to data anomalies. Furthermore, a smaller mean value for the position influence coefficient corresponding to a production phase indicates a lower sensitivity to data anomalies at all data monitoring locations within that production phase due to location influence, and the smaller the value of the anomaly sensitivity factor.

[0109] A larger value for the category fluctuation coefficient indicates a lower consistency and less similarity in the degree of influence across data monitoring locations. In this case, the impact patterns of data monitoring at different locations within a production phase differ significantly, and to a certain extent, the data collection results for that production phase are more sensitive to data anomalies. Furthermore, a larger mean value for the position influence coefficient corresponding to a production phase indicates a higher sensitivity to data anomalies across all data monitoring locations within that production phase due to location influence, and a larger value for the anomaly sensitivity factor.

[0110] Step S303 , obtaining environmental data of the location of each data acquisition device in each production stage under different production parameters, and forming an environmental data sequence for each production stage under different production parameters.

[0111] In this embodiment, different production parameters refer to different feed ratios. Environmental data can include temperature and humidity data. Environmental data for each data acquisition device location is recorded sequentially according to the feed production process. To prevent dimensionality issues from affecting data analysis results, each environmental data set is also standardized. Furthermore, considering that data monitoring for each production stage requires a complete data acquisition cycle, this embodiment uses the mean value of the environmental data at each data acquisition device location within a data acquisition cycle as the value of the environmental data sequence element.

[0112] That is, for any production stage, for each data acquisition device, the mean of all temperature data and the mean of all humidity data within a data acquisition cycle are calculated, which are respectively used as different types of environmental data of the data acquisition device. Then, according to the production process sequence of the production stage, the temperature data and humidity data of all data acquisition devices are arranged in sequence to form the environmental data sequence of the production stage.

[0113] It should be noted that the data monitoring process for each production parameter, that is, for each feed ratio, is exactly the same. The same method can be used to obtain the environmental data series for each production stage during the production process for each feed ratio. For similar reasons, the abnormal sensitivity factor for each production stage during the production process for each feed ratio can also be obtained using the same method as steps S301 and S302.

[0114] Step S304, based on the difference between the environmental data sequence of each production stage under different production parameters and the equilibrium situation of the environmental data sequence of the same production stage under all production parameters, combined with the abnormal sensitivity factor, obtain the data status effectiveness index of each production stage.

[0115] In the first step, the environmental equilibrium sequence is determined based on the mean of the environmental data at the same data acquisition device location under all production parameters in each production stage.

[0116] To provide a data foundation for subsequent analysis of the environmental impact of different feed ratios during the same production phase, it is first necessary to determine the equilibrium of the corresponding environmental data under all feed ratios and characterize the typical environmental conditions under different feed ratios. For example, for any production phase, a data acquisition device corresponds to one piece of environmental data under each production parameter. The mean of all environmental data of the same type under all production parameters at the i-th data acquisition device is calculated as the environmental equilibrium parameter of the same type for the i-th data acquisition device. The environmental equilibrium parameters of all data acquisition devices in the production phase then sequentially form an environmental equilibrium sequence. It is understood that the types of environmental data include temperature and humidity.

[0117] In the second step, based on the difference distance between the environmental data series and the environmental equilibrium series of each production stage and the ratio relationship between the abnormal sensitivity factors under all production parameters, the effective indicators of the data status of each production stage are determined.

[0118] In this embodiment, for each production parameter in any production stage, the DTW distance between the environmental data sequence of that production stage and the environmental equilibrium sequence is calculated to measure the degree of deviation between the actual production environment and the overall baseline state, eliminating the interference of environmental fluctuations on quality. The larger the deviation value, the more significant the environmental fluctuation. As a specific example, the data status effectiveness indicator for any production stage can be specifically expressed as:

[0119]

[0120] Among them, SC k Indicates the effective indicator of data status at the k-th production stage, ZY k,m It represents the abnormal sensitivity factor of the kth production stage under the mth production parameter, i.e., feed ratio, S k,m represents the environmental data sequence of the kth production stage under the mth production parameter, S k represents the environmental equilibrium sequence of the kth production stage, DTW(S k,m ,S k ) represents the DTW distance between sequences, M represents the number of feed ratio types, that is, the number of production parameter types, Norm is the normalization function, ε0 is the preset minimum hyperparameter, and its value is (0, 0.1). It is used to avoid the extreme value of 0 in the DTW distance that affects the result of data calculation, that is, to avoid the situation where the denominator is 0. In this embodiment, it can be set to 0.01.

[0121] For each production stage, the data monitoring results corresponding to the data acquisition device can both sensitively respond to abnormal quality conditions, that is, the larger the value of the abnormal sensitivity factor, and at the same time be able to resist environmental interference, that is, the smaller the value of the environmental deviation value, the higher the effectiveness of data acquisition, that is, the larger the value of the corresponding data status effectiveness indicator.

[0122] The data status effectiveness index of each production stage can comprehensively reflect the effectiveness of the data monitoring process of all data acquisition devices in the production stage.

[0123] In some embodiments, as Figure 4 As shown, a feed production data collection system for the entire process of a smart factory is also provided. The system is used to implement the steps of the aforementioned feed production data collection method for the entire process of a smart factory. The feed production data collection system for the entire process of a smart factory specifically includes:

[0124] The data acquisition module is used to obtain the production data corresponding to each data acquisition device through different data acquisition devices in each production stage of the feed production process;

[0125] A position feature analysis module is used to obtain the position influence coefficient of each data acquisition device in each production stage based on the difference in data monitoring between the production data corresponding to the data acquisition devices at adjacent positions in each production stage and the position information of each data acquisition device in each production stage;

[0126] The effective feature analysis module is used to obtain the effective indicators of the data status of each production stage based on the similarities between the position influence coefficients of different data acquisition devices in each production stage and the fluctuation of environmental information in each production stage;

[0127] The collection method determination module is used to analyze whether to adjust the data collection frequency based on the data status effectiveness indicators of each production stage and determine the data collection method of each data collection device.

[0128] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the scope of the technical solutions of the embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A method for collecting data on the entire feed production process in a smart factory, characterized in that: The method comprises the following steps: Through different data collection devices in each production stage of the feed production process, the production data corresponding to each data collection device is obtained; According to the difference in data monitoring between the production data corresponding to the data acquisition devices at adjacent positions in each production stage, combined with the location information of each data acquisition device in each production stage, the position influence coefficient of each data acquisition device in each production stage is obtained; Based on the similarity between the position influence coefficients of different data acquisition devices in each production stage and the fluctuation of environmental information in each production stage, the effective index of data status in each production stage is obtained; According to the effective indicators of data status in each production stage, analyze whether to adjust the data collection frequency and determine the data collection method for each data collection device.

2. The method for collecting feed production data in a smart factory according to claim 1, characterized in that: The position influence coefficient of each data acquisition device in each production stage is obtained based on the difference in data monitoring between the production data corresponding to the data acquisition devices at adjacent positions in each production stage, combined with the position information of each data acquisition device in each production stage, specifically including: Obtaining a position correlation factor for each data acquisition device in each production stage based on the difference between the fluctuation of production data corresponding to each data acquisition device in each production stage and the fluctuation of production data corresponding to data acquisition devices at adjacent positions; Determining a relative distance factor for each data acquisition device in each production stage based on the distance between the location of each data acquisition device in each production stage and the output location of the corresponding production stage; Based on the ratio between the position correlation factor and the relative distance factor, a position influence coefficient of each data acquisition device in each production stage is determined.

3. The method for collecting feed production data in a smart factory according to claim 2, characterized in that: The position correlation factor of each data acquisition device in each production stage is obtained based on the difference between the fluctuation of the production data corresponding to each data acquisition device in each production stage and the fluctuation of the production data corresponding to the data acquisition device at the adjacent position, specifically including: For each production stage, determining the monitoring difference degree of each production data corresponding to each data acquisition device based on the difference between each production data corresponding to each data acquisition device and the mean of all production data; Based on the difference between the mean of the monitoring difference of all production data corresponding to each data acquisition device and the mean of the monitoring difference of all production data corresponding to the data acquisition devices at adjacent positions, the position correlation factor of each data acquisition device in each production stage is determined.

4. The method for collecting feed production data in a smart factory according to claim 1, characterized in that: The effective indicators of the data status of each production stage are obtained based on the similarity between the position influence coefficients of different data acquisition devices in each production stage and the fluctuation of environmental information in each production stage, specifically including: Based on the similarity between the position influence coefficients of different data acquisition devices in each production stage, the data acquisition devices in the same production stage are clustered. According to the clustering of the data acquisition devices in the clustering results corresponding to each production stage, the category fluctuation coefficient of each production stage is obtained; Determine the abnormal sensitivity factor for each production stage based on the location influence coefficient and category fluctuation coefficient of all data acquisition devices in each production stage; Acquire environmental data at the location of each data acquisition device in each production stage under different production parameters to form an environmental data sequence for each production stage under different production parameters; According to the difference between the environmental data sequence of each production stage under different production parameters and the equilibrium situation of the environmental data sequence of the same production stage under all production parameters, combined with the abnormal sensitivity factor, the effective index of the data status of each production stage is obtained.

5. The method for collecting feed production data in a smart factory according to claim 4, characterized in that: The category fluctuation coefficient of each production stage is obtained according to the clustering of the data acquisition devices in the clustering results corresponding to each production stage, specifically including: For each production stage, the proportion of the number of data acquisition devices contained in each cluster in the clustering results is obtained as the category ratio of each cluster in the clustering results, and the degree of dispersion of all category ratios in the production stage is taken as the category fluctuation coefficient of the corresponding production stage.

6. The method for collecting feed production data in a smart factory according to claim 4, characterized in that: The difference between the environmental data sequence of each production stage under different production parameters and the equilibrium situation of the environmental data sequence of the same production stage under all production parameters is combined with the abnormal sensitivity factor to obtain the effective index of the data status of each production stage, which specifically includes: The environmental equilibrium sequence is determined based on the mean of the environmental data at the same data acquisition device location under all production parameters in each production stage; the effective index of the data status of each production stage is determined based on the difference distance between the environmental data sequence of each production stage and the environmental equilibrium sequence and the ratio relationship between the abnormal sensitivity factors under all production parameters.

7. The method for collecting feed production data in a smart factory according to claim 4, characterized in that: The abnormal sensitivity factor of each production stage is determined based on the position influence coefficient and category fluctuation coefficient of all data acquisition devices in each production stage, specifically including: The ratio between the mean of the position influence coefficients of all data acquisition devices in each production stage and the category fluctuation coefficient is used as the abnormal sensitivity factor of each production stage.

8. The method for collecting feed production data in a smart factory according to claim 1, characterized in that: The analysis of whether to adjust the data collection frequency based on the effective indicators of the data status of each production stage and determining the data collection method of each data collection device specifically includes: When the data status validity indicator of each production stage does not meet the validity condition, the data collection operation is performed after adjusting the data collection frequency of the data collection device of the production stage; when the data status validity indicator of each production stage meets the validity condition, the data collection operation is performed at the current data collection frequency.

9. The method for collecting feed production data in a smart factory according to claim 8, characterized in that: The validity condition is specifically: the data status validity index of the production stage is greater than or equal to a preset validity threshold.

10. A feed production data collection system for a smart factory, characterized by: The system is used to implement the steps of a method for collecting feed production data throughout a smart factory as described in any one of claims 1 to 9. The smart factory feed production data collection system includes: The data acquisition module is used to obtain the production data corresponding to each data acquisition device through different data acquisition devices in each production stage of the feed production process; A position feature analysis module is used to obtain the position influence coefficient of each data acquisition device in each production stage based on the difference in data monitoring between the production data corresponding to the data acquisition devices at adjacent positions in each production stage and the position information of each data acquisition device in each production stage; The effective feature analysis module is used to obtain the effective indicators of the data status of each production stage based on the similarities between the position influence coefficients of different data acquisition devices in each production stage and the fluctuation of environmental information in each production stage; The collection method determination module is used to analyze whether to adjust the data collection frequency based on the data status effectiveness indicators of each production stage and determine the data collection method of each data collection device.

Images