Food powder production monitoring system based on Internet of Things

Abstract

The invention discloses a food powder production monitoring system based on the Internet of Things, which constructs a workshop three-dimensional model through a production area division module and divides the workshop three-dimensional model into a plurality of production areas, detects and classifies powder characteristics in different areas through a powder characteristic classification module, and predicts future production demands by combining historical data and market demands through a production trend prediction module. The environment perception analysis module monitors the environment in real time and analyzes the influence of the environment on production, the production regulation and control decision module formulates a regulation and control scheme according to prediction and analysis results, and the visual presentation module displays production layout, classification results, prediction data and the regulation and control scheme. According to the system, comprehensive monitoring, accurate analysis and intelligent regulation and control of the food powder production process are realized, and the production efficiency and the product quality are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of food production monitoring, and more specifically, to a food powder production monitoring system based on the Internet of Things. Background Art

[0002] In the field of food powder production, with the development of Internet of Things technology, the monitoring and management of the production process have become more and more intelligent. There are many deficiencies in traditional production monitoring methods, which are difficult to meet the refined management requirements of modern food powder production. On the one hand, the regional division of the production workshop is not precise enough, and it is impossible to make a reasonable spatial division according to the production process and equipment layout, resulting in poor coordination in the production process and affecting production efficiency. On the other hand, for the detection and classification of powder characteristics, the detection indicators of traditional methods are limited and the classification is not precise enough, which cannot provide an accurate basis for subsequent production regulation; at the same time, in terms of production trend prediction, traditional methods mainly rely on historical production data, lacking comprehensive consideration of external factors such as market demand, and the prediction results have low accuracy, making it difficult to effectively guide the formulation of production plans. In addition, the production environment has an important impact on the quality of powder, but the traditional monitoring system does not comprehensively monitor and analyze environmental factors, and cannot accurately grasp the relationship between the environment and production, so it is difficult to formulate effective environmental control strategies. Summary of the Invention

[0003] In order to overcome the problems of inaccurate division of existing production areas, inaccurate classification of powder characteristics, low accuracy of production trend prediction, incomplete monitoring and analysis of environmental factors, and lack of intelligent production regulation means, etc., the food powder production monitoring system based on the Internet of Things designed by the present invention can effectively solve the above technical problems.

[0004] To solve the above technical problems, the technical solution of the present invention is as follows:

[0005] A food powder production monitoring system based on the Internet of Things, comprising:

[0006] A production area division module, configured to obtain the spatial model of a food powder production workshop, and automatically divide the workshop into multiple production areas according to the production process and equipment layout;

[0007] A powder characteristic classification module, configured to obtain the physical and chemical characteristics of food powder in different production areas, and classify the powder according to these characteristics to obtain multiple powder categories;

[0008] A production trend prediction module, configured to obtain the historical production data in the production process of food powder in each production area, and combine the market demand data to predict the future production demand;

[0009] An environmental perception analysis module, which is used to obtain the environmental information of each production area through multiple sensors, and analyze this environmental information to obtain the influencing factors of the environment on powder production;

[0010] A production regulation decision-making module, which is used to determine the regulation plan for food powder production according to the production trend prediction results and environmental influencing factors;

[0011] A visualization presentation module, which is used to display the production area layout, powder characteristic classification results, production trend prediction data, and production regulation plan.

[0012] Preferably, the production area division module includes:

[0013] A workshop model construction unit, which is used to obtain the point cloud data of the food powder production workshop through three-dimensional laser scanning technology, and construct a three-dimensional space model of the workshop using reverse engineering software;

[0014] A process analysis unit, which is used to analyze the production process of food powder, and determine the sequence and mutual relationship of each production link;

[0015] A region definition unit, which is used to divide the workshop into multiple production areas according to the workshop space model and production process.

[0016] Preferably, the workshop model construction unit specifically obtains the point cloud data of the production workshop through a three-dimensional laser scanner, and then performs point cloud processing and three-dimensional model construction using Geomagic software;

[0017] The process analysis unit specifically models and analyzes the food powder production process through Petri nets;

[0018] The region definition unit specifically divides the workshop into different production areas according to the workshop three-dimensional model and the Petri net analysis results using a space division algorithm.

[0019] Preferably, the powder characteristic classification module includes:

[0020] A characteristic detection unit, which is used to detect the particle size distribution of the powder using a laser particle size analyzer, measure the fluidity of the powder through a rheometer, determine the density of the powder using a densitometer, and analyze the component content of the powder using a high performance liquid chromatograph;

[0021] A data processing unit, which is used to perform standardization processing on the detected powder characteristic data;

[0022] A classification algorithm unit, which is used to use the clustering algorithm in deep learning to classify the powder into different categories according to the standardized powder characteristic data.

[0023] Preferably, the classification algorithm unit specifically adopts the DBSCAN algorithm combined with an adaptive neighborhood radius adjustment strategy to automatically adjust the clustering parameters according to the distribution of powder characteristic data, and classify the powder into coarse powder, fine powder, and special powder.

[0024] Preferably, the production trend prediction module includes:

[0025] A historical data collection unit for collecting historical production data related to the operation data, output data, and quality inspection data of equipment in each production area through Internet of Things sensors;

[0026] A market data acquisition unit for collecting market information such as demand data and price data of food powder through web scraping technology;

[0027] A prediction model construction unit for using the historical production data and market data as inputs, and constructing a production trend prediction model using a long short-term memory network to predict future output demand and product quality indicators.

[0028] Preferably, the environmental perception and analysis module includes:

[0029] A sensor deployment unit for deploying environmental monitoring sensors such as temperature sensors, humidity sensors, and air quality sensors in each production area;

[0030] A data collection unit for real-time collecting environmental data of each sensor;

[0031] An impact analysis unit for using the grey relational analysis method to analyze the correlation between environmental data and powder production quality and output, and determining the influencing factors of the environment on powder production.

[0032] Preferably, the production regulation decision module includes:

[0033] A regulation strategy generation unit for formulating a production process optimization plan, an equipment parameter adjustment plan, and an environmental control strategy according to the production trend prediction result and environmental impact factors;

[0034] A plan evaluation unit for evaluating the regulation strategy using simulation technology and predicting the regulation effect;

[0035] A decision execution unit for sending the evaluated regulation strategy to the production equipment control system to execute production regulation.

[0036] Preferably, the prediction model construction unit specifically adopts a bidirectional LSTM network, combined with an attention mechanism, to perform feature extraction and time series analysis on historical production data and market data, and predict the output demand and product quality indicators for a specific future time period;

[0037] The impact analysis unit specifically calculates the grey correlation degree between environmental factors and production indicators through grey correlation analysis, and determines temperature, humidity, and dust concentration as the main influencing factors;

[0038] The regulation strategy generation unit specifically adopts a multi-objective optimization algorithm, with the maximization of output, the optimization of quality, and the minimization of cost as the objectives, to generate an optimal production regulation strategy.

[0039] Preferably, the solution evaluation unit specifically uses ANSYS simulation software to perform virtual simulation on the production process, equipment operation, and environmental changes, and evaluate the impact of the regulation strategy on production efficiency, product quality, and cost;

[0040] The decision execution unit specifically sends the regulation strategy to the PLC control system through the industrial Ethernet to achieve remote control and automatic regulation of production equipment.

[0041] Compared with the prior art, the beneficial effects of the present invention are as follows: The Internet of Things-based food powder production monitoring system of the present invention, through the workshop model construction unit, process analysis unit, and area definition unit of the production area division module, uses 3D laser scanning technology and Petri net analysis to accurately divide the production area and solve the problem of inaccurate area division; the characteristic detection unit, data processing unit, and classification algorithm unit of the powder characteristic classification module, combined with the deep learning clustering algorithm, accurately classify the powder characteristics and improve the classification accuracy; the production trend prediction module integrates historical data and market demand, and uses a long short-term memory network to improve the prediction accuracy; the environmental perception analysis module deploys a variety of sensors and uses grey correlation analysis to comprehensively monitor and analyze environmental factors; the production regulation decision module generates and evaluates the regulation strategy, and uses a multi-objective optimization algorithm and simulation technology to achieve intelligent production regulation; the system effectively solves the problems of area division, characteristic classification, trend prediction, environmental monitoring, and regulation means in existing production monitoring, and improves production efficiency and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only exemplary, and for those of ordinary skill in the art, other implementation drawings can be obtained by extending according to the provided drawings without creative efforts.

[0043] Figure 1 It is a structural diagram of an Internet of Things-based food powder production monitoring system. SPECIFIC EMBODIMENTS

[0044] The drawings are only for illustrative purposes and should not be construed as a limitation of this patent;

[0045] To better illustrate this embodiment, some components in the drawings are omitted, enlarged or reduced, which do not represent the dimensions of the actual product;

[0046] For those skilled in the art, it is understandable that some well-known structures and their descriptions in the drawings may be omitted.

[0047] The technical solution of the present invention will be further described below in conjunction with the drawings and embodiments.

[0048] Embodiment

[0049] The food powder production monitoring system based on the Internet of Things, as Figure 1 shown, includes:

[0050] A production area division module, configured to obtain the spatial model of the food powder production workshop, and automatically divide the workshop into multiple production areas according to the production process and equipment layout;

[0051] A powder property classification module, configured to obtain the physical and chemical properties of the food powder in different production areas, and classify the powder according to these properties to obtain multiple powder categories;

[0052] A production trend prediction module, configured to obtain the historical production data in the production process of the food powder in each production area, and combine the market demand data to predict the future production demand;

[0053] An environment perception and analysis module, configured to obtain the environmental information of each production area through a variety of sensors, and analyze this environmental information to obtain the influencing factors of the environment on powder production;

[0054] A production regulation decision module, configured to determine the regulation plan for food powder production according to the production trend prediction result and environmental influencing factors;

[0055] A visualization presentation module, configured to display the production area layout, powder property classification results, production trend prediction data, and production regulation plan.

[0056] The production area division module includes:

[0057] A workshop model construction unit, configured to obtain the point cloud data of the food powder production workshop through three-dimensional laser scanning technology, and construct the three-dimensional space model of the workshop by using reverse engineering software;

[0058] A process analysis unit, configured to analyze the production process of the food powder, and determine the sequence and mutual relationship of each production link;

[0059] A region definition unit, configured to divide the workshop into multiple production areas according to the workshop space model and production process.

[0060] The workshop model construction unit specifically obtains the point cloud data of the production workshop through a 3D laser scanner, and then uses Geomagic software for point cloud processing and 3D model construction;

[0061] The process analysis unit specifically models and analyzes the food powder production process through a Petri net;

[0062] The area definition unit specifically divides the workshop into different production areas by using a space division algorithm according to the workshop 3D model and the Petri net analysis results.

[0063] Workshop model construction: Use a 3D laser scanner to scan the food powder production workshop to obtain accurate point cloud data. Import these data into Geomagic software. After point cloud processing and 3D model construction, a 3D space model of the workshop is obtained. For example, for a certain flour production workshop, the 3D coordinate information of all equipment, pipelines, and building structures in the workshop is obtained through scanning, and a virtual 3D model identical to the actual workshop is constructed.

[0064] Process analysis: Use a Petri net to model and analyze the food powder production process. Taking bread flour production as an example, determine the sequence and mutual relationship of each production link from raw material reception, grinding, mixing, packaging, etc., and construct a Petri net model of the production process to clearly display the material flow and logical relationship between each link.

[0065] Area definition: According to the workshop 3D model and the Petri net analysis results, use a space division algorithm to divide the workshop into different production areas. For example, the area where flour grinding equipment is concentrated is divided into a grinding area, and the area where mixing equipment is located is divided into a mixing area, etc. Each area has a clear boundary and functional positioning to achieve refined management of the production process.

[0066] The powder property classification module includes:

[0067] The property detection unit is used to detect the particle size distribution of the powder by using a laser particle size analyzer, measure the fluidity of the powder through a rheometer, determine the density of the powder by using a densitometer, and analyze the component content of the powder by using a high performance liquid chromatograph;

[0068] The data processing unit is used to perform standardization processing on the powder property data obtained by detection;

[0069] The classification algorithm unit is used to classify the powder into different categories by using the clustering algorithm in deep learning according to the standardized powder property data.

[0070] The classification algorithm unit specifically adopts the DBSCAN algorithm combined with an adaptive neighborhood radius adjustment strategy to automatically adjust the clustering parameters according to the distribution of powder property data, and classify the powder into coarse powder, fine powder, and special powder.

[0071] Characteristic detection: Detection points are set in each production area. The particle size distribution of the powder is detected by a laser particle size analyzer, the fluidity of the powder is measured by a rheometer, the density of the powder is determined by a densitometer, and the component content of the powder is analyzed by a high-performance liquid chromatograph. For example, during the production process of bread flour, the particle size, fluidity, density, and component content of starch at different production stages are detected respectively to obtain comprehensive powder property data.

[0072] Data processing: The powder property data obtained from detection is standardized to eliminate the influence of dimension and dimension unit, making the data comparable. For example, the particle size data is normalized to the interval [0, 1], and the fluidity data is subjected to standardization transformation, etc., to provide a unified data format for the subsequent classification algorithm.

[0073] Classification algorithm: The DBSCAN algorithm combined with an adaptive neighborhood radius adjustment strategy is used to classify the powder. The clustering parameters are automatically adjusted according to the distribution of powder property data, and the powder is classified into different categories such as coarse powder, fine powder, and special powder. In the production of bread flour, this algorithm accurately classifies milk powder with different particle sizes and different component contents, providing a basis for subsequent production control.

[0074] The production trend prediction module includes:

[0075] Historical data collection unit: It is used to collect historical production data related to the operation data, output data, and quality inspection data of equipment in each production area through Internet of Things sensors;

[0076] Market data acquisition unit: It is used to collect market information such as demand data and price data of food powder on the market through web crawler technology;

[0077] Prediction model construction unit: It is used to take historical production data and market data as inputs, and use a long short-term memory network to construct a production trend prediction model to predict future production demand and product quality indicators.

[0078] Historical data collection: Historical production data related to the operation data of equipment in each production area, such as the rotation speed, temperature, power, etc. of the equipment, output data, and quality inspection data, is collected through Internet of Things sensors. Taking the production of bread flour as an example, data such as the monthly output, equipment operation status, and product quality inspection results in the past year are collected.

[0079] Market data acquisition: Collect demand data and price data of food powders in the market through web scraping technology, such as scraping e-commerce platforms, websites of market research institutions, etc., to obtain information such as the market demand, price trend, and consumer preferences of cookie powder.

[0080] Prediction model construction: Use historical production data and market data as inputs, and utilize Long Short-Term Memory (LSTM) networks to construct a production trend prediction model. For example, construct a neural network model containing multiple LSTM layers and fully connected layers to predict the production demand and product quality indicators of cookie powder for a specific future time period.

[0081] The environmental perception and analysis module includes:

[0082] Sensor deployment unit: Used to deploy environmental monitoring sensors related to temperature sensors, humidity sensors, and air quality sensors in each production area;

[0083] Data acquisition unit: Used to collect environmental data of each sensor in real time;

[0084] Impact analysis unit: Used to adopt the grey relational analysis method to analyze the relational between environmental data and powder production quality and output, and determine the influencing factors of the environment on powder production.

[0085] Sensor deployment: Deploy environmental monitoring sensors related to temperature sensors, humidity sensors, and air quality sensors in each production area. For example, in the flour production workshop, install a temperature sensor and a humidity sensor at the same interval, and install air quality sensors at key positions such as ventilation outlets to monitor environmental parameters in real time.

[0086] Data acquisition: Each sensor collects environmental data in real time and transmits the data to the environmental perception and analysis module through a wireless communication module. For example, the temperature sensor collects temperature data every minute, and the humidity sensor collects humidity data every fixed time period to ensure the timeliness and continuity of the data.

[0087] Impact analysis: Adopt the grey relational analysis method to analyze the relational between environmental data and powder production quality and output, and determine the influencing factors of the environment on powder production. For example, through analysis, it is found that there is a significant relationship between temperature and flour grinding efficiency, humidity and flour moisture content, and air quality and flour microbial indicators, and these environmental factors are determined as the main influencing factors.

[0088] The production regulation and decision-making module includes:

[0089] Regulation strategy generation unit: Used to formulate an optimized production process plan, equipment parameter adjustment plan, and environmental control strategy according to the production trend prediction results and environmental impact factors;

[0090] A solution evaluation unit, which is used to evaluate the regulation strategy by using simulation technology and predict the regulation effect;

[0091] A decision execution unit, which is used to send the evaluated regulation strategy to the production equipment control system to execute production regulation.

[0092] The prediction model construction unit specifically uses a bidirectional LSTM network, combines an attention mechanism, extracts features and performs time series analysis on historical production data and market data, and predicts the production demand and product quality indicators for a specific future time period;

[0093] The impact analysis unit specifically calculates the grey correlation degree between environmental factors and production indicators through grey correlation analysis, and determines that temperature, humidity and dust concentration are the main influencing factors;

[0094] The regulation strategy generation unit specifically uses a multi-objective optimization algorithm, with the goals of maximizing production, optimizing quality and minimizing cost, to generate the optimal production regulation strategy.

[0095] The solution evaluation unit specifically uses ANSYS simulation software to perform virtual simulation on the production process, equipment operation and environmental changes, and evaluate the impact of the regulation strategy on production efficiency, product quality and cost;

[0096] The decision execution unit specifically sends the regulation strategy to the PLC control system through industrial Ethernet to achieve remote control and automatic regulation of production equipment.

[0097] Regulation strategy generation: According to the production trend prediction results and environmental impact factors, formulate production process optimization plans, equipment parameter adjustment plans and environmental control strategies. For example, if it is predicted that the future market demand will increase, and at the same time it is found that the current environmental humidity is high and will affect product quality, formulate regulation strategies to improve equipment operation efficiency, adjust the production process sequence and reduce the workshop humidity.

[0098] Solution evaluation: Use simulation technology to evaluate the regulation strategy and predict the regulation effect. By establishing a digital simulation model of the production process, simulate the production situation after implementing the regulation strategy, predict the changes in indicators such as output, quality and cost, and evaluate the feasibility of the regulation strategy.

[0099] Decision execution: Send the evaluated regulation strategy to the production equipment control system to execute production regulation. Send the regulation strategy to the PLC control system through industrial Ethernet to control the adjustment of equipment operation parameters, such as changing the rotation speed of grinding equipment and adjusting the stirring time of mixing equipment, to achieve remote control and automatic regulation of production equipment.

[0100] The visualization presentation module displays the production area layout, powder property classification results, production trend prediction data, and production regulation plans in the form of intuitive charts, graphs, etc., and real-time displays the equipment operation status, powder particle size distribution histogram, production volume prediction curve, and regulation strategy execution status of each area in the workshop on the monitoring large screen, facilitating production management personnel to grasp the production dynamics in real time and make decisions in a timely manner.

[0101] The same or similar reference numerals correspond to the same or similar components;

[0102] The terms describing the positional relationship in the drawings are for illustrative purposes only and should not be construed as a limitation of this patent;

[0103] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention and are not intended to limit the implementation manners of the present invention. For those of ordinary skill in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to enumerate all the implementation manners here. Any modifications, equivalent replacements, and improvements made within the spirit and principle of the present invention shall be included in the protection scope of the claims of the present invention.

Claims

1. The food powder production monitoring system based on the Internet of Things is characterized by: include: The production area division module is used to obtain the spatial model of the food powder production workshop and automatically divide the workshop into multiple production areas according to the production process and equipment layout; The powder property classification module is used to obtain the physical and chemical properties of food powders in different production areas, and classify the powders according to these properties to obtain multiple powder categories; The production trend forecasting module is used to obtain historical production data of food powder production in each production area and forecast future production demand in combination with market demand data; The environmental perception and analysis module is used to obtain environmental information of each production area through a variety of sensors, and analyze the environmental information to obtain the factors affecting powder production; The production control decision module is used to determine the control plan for food powder production based on the production trend prediction results and environmental influencing factors; The visualization module is used to display the production area layout, powder property classification results, production trend prediction data and production control plan.

2. The food powder production monitoring system based on the Internet of Things according to claim 1 is characterized in that: The production area division module includes: A workshop model building unit, which is used to obtain point cloud data of a food powder production workshop through 3D laser scanning technology and build a 3D spatial model of the workshop using reverse engineering software; Process analysis unit, used to analyze the process flow of food powder production and determine the sequence and relationship of each production link; The area definition unit is used to divide the workshop into multiple production areas according to the workshop space model and production process.

3. The food powder production monitoring system based on the Internet of Things according to claim 2 is characterized in that: The workshop model building unit specifically obtains point cloud data of the production workshop through a 3D laser scanner, and then uses Geomagic software to perform point cloud processing and 3D model building; The process analysis unit specifically models and analyzes the food powder production process through Petri nets; The area definition unit divides the workshop into different production areas using a space partitioning algorithm based on the three-dimensional model of the workshop and the Petri net analysis results.

4. The food powder production monitoring system based on the Internet of Things according to claim 1 is characterized in that: The powder property classification module includes: The characteristic detection unit is used to detect the particle size distribution of the powder using a laser particle size analyzer, measure the powder fluidity through a rheometer, determine the powder density using a densitometer, and analyze the powder component content using a high performance liquid chromatograph; A data processing unit, used for standardizing the powder characteristic data obtained by detection; The classification algorithm unit is used to adopt a clustering algorithm in deep learning to classify the powder into different categories according to the standardized powder characteristic data.

5. The food powder production monitoring system based on the Internet of Things according to claim 4 is characterized in that: The classification algorithm unit specifically adopts the DBSCAN algorithm combined with an adaptive neighborhood radius adjustment strategy to automatically adjust clustering parameters according to the distribution of powder characteristic data, and classifies the powder into coarse powder, fine powder, and special powder.

6. The food powder production monitoring system based on the Internet of Things according to claim 1 is characterized in that: The production trend prediction module includes: A historical data collection unit, which is used to collect historical production data related to operation data, output data and quality inspection data of equipment in each production area through IoT sensors; A market data acquisition unit, used to collect market information on demand data and price data of food powder in the market through web crawler technology; The prediction model building unit is used to take historical production data and market data as input, use the long short-term memory network to build a production trend prediction model, and predict future production demand and product quality indicators.

7. The food powder production monitoring system based on the Internet of Things according to claim 6 is characterized in that: The environmental perception analysis module includes: A sensor deployment unit, used to deploy environmental monitoring sensors such as temperature sensors, humidity sensors, and air quality sensors in each production area; A data acquisition unit, used to collect environmental data from each sensor in real time; The impact analysis unit is used to analyze the correlation between environmental data and powder production quality and output using the grey correlation analysis method, and to determine the influencing factors of the environment on powder production.

8. The food powder production monitoring system based on the Internet of Things according to claim 7 is characterized in that: The production control decision module includes: The control strategy generation unit is used to formulate production process optimization plans, equipment parameter adjustment plans and environmental control strategies based on production trend prediction results and environmental influencing factors; The program evaluation unit is used to evaluate the control strategy and predict the control effect by using simulation technology; The decision execution unit is used to send the evaluated control strategy to the production equipment control system to execute production control.

9. The food powder production monitoring system based on the Internet of Things according to claim 8, characterized in that: The prediction model building unit specifically adopts a bidirectional LSTM network, combined with an attention mechanism, to perform feature extraction and time series analysis on historical production data and market data, and predict production demand and product quality indicators in a specific time period in the future; The impact analysis unit specifically calculates the grey correlation degree between environmental factors and production indicators through grey correlation analysis, and determines that temperature, humidity and dust concentration are the main influencing factors; The control strategy generation unit specifically adopts a multi-objective optimization algorithm to generate an optimal production control strategy with the goals of maximizing output, optimizing quality, and minimizing costs.

10. The food powder production monitoring system based on the Internet of Things according to claim 9, characterized in that: The solution evaluation unit specifically uses ANSYS simulation software to conduct virtual simulation of production processes, equipment operation and environmental changes, and evaluate the impact of control strategies on production efficiency, product quality and cost; The decision execution unit specifically sends the control strategy to the PLC control system via industrial Ethernet to achieve remote control and automated control of production equipment.

Images