Process management system based on concrete steel mold and control method thereof

Abstract

The invention relates to the technical field of concrete molds, in particular to a process management system based on a concrete steel mold and a control method thereof, and the system comprises a mold information collection module which is used for collecting basic information of the concrete steel mold, including the number, position information, size parameters, material information, production batch, manufacturing date, latest maintenance date and the like of the mold; the data storage module is used for storing the collected mold information and comprises a structured database and an unstructured data storage system; according to accurate mold life prediction, multiple parameters influencing the mold life are comprehensively analyzed by applying multiple data analysis algorithms such as a linear regression algorithm, principal component analysis (PCA), K-means clustering, a decision-making tree and a random forest, the service life of the mold can be predicted more accurately, a mold replacement plan is optimized, and the service life of the mold can be predicted more accurately. Unnecessary advanced replacement or delayed replacement is avoided, and the production efficiency and the economic benefit are improved.

Description

Technical Field

[0001] The invention relates to the technical field of concrete moulds, in particular to a process management system based on concrete steel moulds and a control method thereof. Background Art

[0002] The use of concrete steel molds is becoming more and more common in modern construction projects and infrastructure construction; these molds play a key role in the production process of precast concrete components and directly affect the quality and production efficiency of the products; however, there are some challenges in the use and maintenance of concrete steel molds:

[0003] Mould loss and life prediction: Concrete steel moulds are affected by many factors during use, such as temperature, pressure, humidity, vibration, chemical corrosion, etc. These factors will cause the wear and loss of the mould. Traditional mould life prediction methods are relatively rough and cannot accurately assess the actual service life of the mould, resulting in early or delayed replacement of the mould during production, affecting production efficiency and cost control.

[0004] Mold status monitoring and abnormality detection: Existing mold management systems often lack the ability to monitor mold status in real time and are unable to promptly detect and handle abnormal conditions during mold use, such as parameter out-of-limit, sensor failure, etc. These problems may lead to production accidents and quality issues, and increase maintenance costs.

[0005] Production process optimization: The use process and production process of concrete steel molds are complex, involving the management of multiple links and parameters. The existing system is relatively inadequate in production process optimization, and it is difficult to make effective process adjustments and optimizations based on real-time data, which affects production efficiency and product quality.

[0006] Data analysis and decision support: Traditional mold management systems have limited data processing capabilities and lack advanced data analysis and modeling algorithms. They are unable to fully utilize the large amount of collected data for in-depth analysis and decision support, which limits the intelligence level of the system. Therefore, a process management system based on concrete steel molds and its control method are proposed to address the above problems. Summary of the invention

[0007] The purpose of the present invention is to provide a process management system based on concrete steel molds and a control method thereof, which can realize the full life cycle management of the molds, improve production efficiency, reduce maintenance costs, and enhance the intelligence level of the system by introducing advanced data collection, storage, analysis and prediction algorithms.

[0008] To achieve the above object, the present invention provides the following technical solutions:

[0009] Process management system based on concrete steel mold, including:

[0010] The mold information collection module is used to collect the basic information of the concrete steel mold, including the mold number, location information, size parameters, material information, production batch, manufacturing date, and the last maintenance date;

[0011] A data storage module, used to store the collected mold information, including a structured database and an unstructured data storage system;

[0012] The mold status monitoring module is used to monitor the use status of concrete steel molds in real time, including the collection and recording of physical parameters such as temperature, pressure, humidity, vibration, wear and chemical corrosion;

[0013] The production process management module is used to manage the use process of concrete steel molds in the production process, including mold scheduling, usage records, setting and adjustment of production process parameters, process optimization and production progress tracking;

[0014] The alarm module is used to send out an alarm signal when an abnormal situation is monitored, and provide a detailed abnormal report, including the alarm type, occurrence time, abnormal parameters and possible cause analysis;

[0015] User interface module, used to provide an interactive interface between the system and the user, including a graphical user interface (GUI), a mobile application interface, and a voice control interface;

[0016] The data processing module is used to clean, analyze and model the collected data, including the implementation of multiple data analysis algorithms and prediction models, which are used to predict mold life, optimize production processes and perform preventive maintenance.

[0017] Preferably, the mold information collection module includes:

[0018] A mold number collection unit is used to collect the unique number information of the concrete steel mold;

[0019] Mould position acquisition unit, used to collect and update the position information of concrete steel moulds in real time, including GPS positioning and production line position identification;

[0020] A mold state acquisition unit, used to collect current state information of the concrete steel mold through a sensor network, including a temperature sensor, a pressure sensor, a humidity sensor, an acceleration sensor, and a chemical corrosion detection sensor;

[0021] The data storage module comprises:

[0022] Relational database, used to store structured basic information and usage records of molds;

[0023] Non-relational databases (NoSQL) for storing unstructured sensor data and log information;

[0024] Distributed storage systems to improve the reliability and scalability of data storage;

[0025] The mold status monitoring module includes:

[0026] Multi-sensor fusion unit, used to fuse data from different sensors to improve data accuracy and reliability;

[0027] Real-time data processing unit, used to process and analyze sensor data in real time and generate mold status reports;

[0028] The production process management module includes:

[0029] Process definition unit, used to define and manage the use process and production process of concrete steel molds;

[0030] Process tracking unit, used to track the execution of concrete steel molds in the production process and generate process reports;

[0031] Process optimization unit, used to optimize the use process according to the data analysis results, including the adjustment of use frequency, maintenance plan and process parameters;

[0032] The alarm module comprises:

[0033] Anomaly detection unit, used to detect abnormal conditions of concrete steel molds, including parameter out-of-limit, sensor failure and abnormal pattern recognition;

[0034] An alarm signal issuing unit for issuing visual, audible and email alarm signals when an abnormal situation is detected;

[0035] Abnormal analysis unit, used to analyze abnormal situations and provide possible causes and solutions;

[0036] The user interface module comprises:

[0037] Display unit, used to display mold information, usage status, production process information and alarm information;

[0038] An input unit, used to receive instructions and feedback input by a user;

[0039] Mobile application interface for accessing and operating the system via a mobile device;

[0040] Voice control interface for operating the system via voice commands.

[0041] Preferably, the data processing module includes:

[0042] Data cleaning unit, used to clean and preprocess the collected data, including removing noise data, processing missing values ​​and standardizing data;

[0043] The data analysis algorithm unit is used to analyze the cleaned data, including linear regression, principal component analysis (PCA), K-means clustering, decision tree, and random forest algorithms.

[0044] Preferably, the linear regression algorithm is used to predict the service life and status of the mold:

[0045] The calculation formula is:

[0046] Where y is the predicted mold life or status, x i is the parameter that affects the mold life, β0 is a constant term, β i is the regression coefficient;

[0047] Specific parameters that affect mold life include:

[0048] Temperature (T): x1;

[0049] Pressure (P): x2;

[0050] Humidity (H): x3;

[0051] Vibration frequency (V): x4;

[0052] Use times (U): x5;

[0053] Chemical Corrosion (C): x6.

[0054] Preferably, the principal component analysis (PCA) algorithm is used for dimensionality reduction and data feature extraction:

[0055] The calculation formula is: Z = XW;

[0056] Among them, X is the standardized data matrix, W is the eigenvector matrix, and Z is the data matrix after dimensionality reduction.

[0057] Preferably, the K-means clustering algorithm is used to classify and group the usage status of the molds:

[0058] The calculation formula is:

[0059] Where k is the number of clusters, Ci is the i-th cluster, μ i is the center of the ith cluster, and x is the data point in the cluster.

[0060] Preferably, the decision tree algorithm is used to classify and predict according to mold parameters and states:

[0061] The calculation formula is: Information gain

[0062]

[0063] Among them, IG(T, a) is the information gain of attribute a, H(T) is the entropy of data set T, and T v is the subset whose value on attribute a is v.

[0064] Preferably, the random forest algorithm is used to improve the accuracy and stability of prediction:

[0065] The calculation formula is: Prediction based on the integrated results of multiple decision trees:

[0066]

[0067] Where M is the number of decision trees, h m (x) is the prediction result of the mth tree for sample x.

[0068] The control method of the process management system based on concrete steel mold includes the following steps:

[0069] Step 1: Collect basic information of concrete steel mold;

[0070] Step 2: Storing the collected mold information;

[0071] Step 3: Real-time monitoring of the use status of concrete steel molds;

[0072] Step 4: Manage the use of concrete steel molds in the production process;

[0073] Step 5: Send out an alarm signal when an abnormal situation is detected;

[0074] Step 6: Provide an interactive interface between the system and the user;

[0075] Step 7: Process and analyze the collected data.

[0076] Preferably, collecting basic information of concrete steel molds includes: collecting mold number information, location information and current status information; real-time monitoring of the usage status of concrete steel molds includes: collecting physical parameters such as temperature, pressure, humidity, vibration, etc. of concrete steel molds; analyzing the collected physical parameters and judging the status of the molds; managing the usage process of concrete steel molds in the production process includes: defining the usage process of concrete steel molds; tracking the execution of concrete steel molds in the production process; optimizing the usage process according to data analysis results; issuing an alarm signal when an abnormal situation is monitored includes: detecting abnormal conditions of concrete steel molds; issuing an alarm signal when an abnormal situation is detected; providing an interactive interface between the system and the user includes: displaying mold information, usage status and production process information; receiving instructions input by the user; processing and analyzing the collected data includes: cleaning and preprocessing the data; applying linear regression algorithm, principal component analysis (PCA) algorithm, K-means clustering algorithm, decision tree and random forest algorithm to analyze the data.

[0077] Compared with the prior art, the present invention has the following beneficial effects:

[0078] 1. In the present invention, by applying a variety of data analysis algorithms such as linear regression algorithm, principal component analysis (PCA), K-means clustering, decision tree and random forest, a comprehensive analysis of various parameters affecting the life of the mold is performed, which can more accurately predict the service life of the mold, optimize the mold replacement plan, avoid unnecessary early replacement or delayed replacement, and improve production efficiency and economic benefits.

[0079] 2. In the present invention, the system integrates a variety of sensors for real-time monitoring of physical parameters such as temperature, pressure, humidity, vibration, chemical corrosion, etc. of the mold. Through multi-sensor data fusion and real-time data processing, it can timely detect and warn of abnormal conditions of the mold, thereby reducing production accidents and quality problems.

[0080] 3. In the present invention, the use process and production process of concrete steel molds are comprehensively managed and optimized through the production process management module. Based on real-time data and data analysis results, the production parameters and process flow are adjusted to improve production efficiency and product quality.

[0081] 4. In the present invention, the system adopts advanced data cleaning, analysis and modeling techniques, including linear regression, principal component analysis (PCA), K-means clustering, decision tree and random forest algorithms, which can conduct in-depth analysis of large amounts of collected data, provide scientific decision support, and improve the intelligence level of the system. DETAILED DESCRIPTION

[0082] The present invention provides a technical solution:

[0083] Process management system based on concrete steel mold, including:

[0084] The mold information collection module is used to collect the basic information of the concrete steel mold, including the mold number, location information, size parameters, material information, production batch, manufacturing date, and the last maintenance date;

[0085] A data storage module, used to store the collected mold information, including a structured database and an unstructured data storage system;

[0086] The mold status monitoring module is used to monitor the use status of concrete steel molds in real time, including the collection and recording of physical parameters such as temperature, pressure, humidity, vibration, wear and chemical corrosion;

[0087] The production process management module is used to manage the use process of concrete steel molds in the production process, including mold scheduling, usage records, setting and adjustment of production process parameters, process optimization and production progress tracking;

[0088] The alarm module is used to send out an alarm signal when an abnormal situation is monitored, and provide a detailed abnormal report, including the alarm type, occurrence time, abnormal parameters and possible cause analysis;

[0089] User interface module, used to provide an interactive interface between the system and the user, including a graphical user interface (GUI), a mobile application interface, and a voice control interface;

[0090] The data processing module is used to clean, analyze and model the collected data, including the implementation of multiple data analysis algorithms and prediction models, which are used to predict mold life, optimize production processes and perform preventive maintenance.

[0091] In the present invention, the system integrates a variety of sensors for real-time monitoring of physical parameters of the mold, such as temperature, pressure, humidity, vibration, chemical corrosion, etc. Through multi-sensor data fusion and real-time data processing, it can timely detect and warn of abnormal conditions of the mold, thereby reducing production accidents and quality problems.

[0092] The mold information acquisition module includes:

[0093] A mold number collection unit is used to collect the unique number information of the concrete steel mold;

[0094] Mould position acquisition unit, used to collect and update the position information of concrete steel moulds in real time, including GPS positioning and production line position identification;

[0095] A mold state acquisition unit, used to collect current state information of the concrete steel mold through a sensor network, including a temperature sensor, a pressure sensor, a humidity sensor, an acceleration sensor, and a chemical corrosion detection sensor;

[0096] The data storage module comprises:

[0097] Relational database, used to store structured basic information and usage records of molds;

[0098] Non-relational databases (NoSQL) for storing unstructured sensor data and log information;

[0099] Distributed storage systems to improve the reliability and scalability of data storage;

[0100] The mold status monitoring module includes:

[0101] Multi-sensor fusion unit, used to fuse data from different sensors to improve data accuracy and reliability;

[0102] Real-time data processing unit, used to process and analyze sensor data in real time and generate mold status reports;

[0103] The production process management module includes:

[0104] Process definition unit, used to define and manage the use process and production process of concrete steel molds;

[0105] Process tracking unit, used to track the execution of concrete steel molds in the production process and generate process reports;

[0106] Process optimization unit, used to optimize the use process according to the data analysis results, including the adjustment of use frequency, maintenance plan and process parameters;

[0107] The alarm module comprises:

[0108] Anomaly detection unit, used to detect abnormal conditions of concrete steel molds, including parameter out-of-limit, sensor failure and abnormal pattern recognition;

[0109] An alarm signal issuing unit for issuing visual, audible and email alarm signals when an abnormal situation is detected;

[0110] Abnormal analysis unit, used to analyze abnormal situations and provide possible causes and solutions;

[0111] The user interface module comprises:

[0112] Display unit, used to display mold information, usage status, production process information and alarm information;

[0113] An input unit, used to receive instructions and feedback input by a user;

[0114] Mobile application interface for accessing and operating the system via a mobile device;

[0115] Voice control interface for operating the system via voice commands.

[0116] In the present invention, the use process and production process of concrete steel molds are comprehensively managed and optimized through the production process management module, and the production parameters and process flow are adjusted based on real-time data and data analysis results to improve production efficiency and product quality.

[0117] The data processing module comprises:

[0118] Data cleaning unit, used to clean and preprocess the collected data, including removing noise data, processing missing values ​​and standardizing data;

[0119] The data analysis algorithm unit is used to analyze the cleaned data, including linear regression, principal component analysis (PCA), K-means clustering, decision tree, and random forest algorithms.

[0120] In the present invention, the system adopts advanced data cleaning, analysis and modeling techniques, including linear regression, principal component analysis (PCA), K-means clustering, decision tree and random forest algorithms, which can conduct in-depth analysis of large amounts of collected data, provide scientific decision support, and improve the intelligence level of the system.

[0121] The linear regression algorithm is used to predict the service life and status of the mold:

[0122] The calculation formula is:

[0123] Where y is the predicted mold life or status, x i is the parameter that affects the mold life, β0 is a constant term, β i is the regression coefficient;

[0124] Specific parameters that affect mold life include:

[0125] Temperature (T): x1;

[0126] Pressure (P): x2;

[0127] Humidity (H): x3;

[0128] Vibration frequency (V): x4;

[0129] Use times (U): x5;

[0130] Chemical Corrosion (C): x6.

[0131] The principal component analysis (PCA) algorithm is used to reduce dimension and extract data features:

[0132] The calculation formula is: Z = XW;

[0133] Among them, X is the standardized data matrix, W is the eigenvector matrix, and Z is the data matrix after dimensionality reduction.

[0134] The K-means clustering algorithm is used to classify and group the dies using status:

[0135] The calculation formula is:

[0136] Where k is the number of clusters, Ci is the i-th cluster, μ i is the center of the ith cluster, and x is the data point in the cluster.

[0137] The decision tree algorithm is used to classify and predict based on mold parameters and status:

[0138] The calculation formula is: Information gain

[0139]

[0140] Among them, IG(T, a) is the information gain of attribute a, H(T) is the entropy of data set T, and T v is the subset whose value on attribute a is v.

[0141] The random forest algorithm is used to improve the accuracy and stability of predictions:

[0142] The calculation formula is: Prediction based on the integrated results of multiple decision trees:

[0143]

[0144] Where M is the number of decision trees, h m (x) is the prediction result of the mth tree for sample x.

[0145] In the present invention, by applying multiple data analysis algorithms such as linear regression algorithm, principal component analysis (PCA), K-means clustering, decision tree and random forest, a comprehensive analysis is performed on various parameters affecting the life of the mold, which can more accurately predict the service life of the mold, optimize the mold replacement plan, avoid unnecessary early replacement or delayed replacement, and improve production efficiency and economic benefits.

[0146] The control method of the process management system based on concrete steel mold includes the following steps:

[0147] Step 1: Collect basic information of concrete steel mold;

[0148] Step 2: Storing the collected mold information;

[0149] Step 3: Real-time monitoring of the use status of concrete steel molds;

[0150] Step 4: Manage the use of concrete steel molds in the production process;

[0151] Step 5: Send out an alarm signal when an abnormal situation is detected;

[0152] Step 6: Provide an interactive interface between the system and the user;

[0153] Step 7: Process and analyze the collected data.

[0154] Collecting basic information of concrete steel molds includes: collecting mold number information, location information and current status information; real-time monitoring of the usage status of concrete steel molds includes: collecting physical parameters such as temperature, pressure, humidity, vibration, etc. of concrete steel molds; analyzing the collected physical parameters and judging the status of the molds; managing the usage process of concrete steel molds in the production process includes: defining the usage process of concrete steel molds; tracking the execution of concrete steel molds in the production process; optimizing the usage process according to data analysis results; issuing an alarm signal when an abnormal situation is monitored includes: detecting abnormal conditions of concrete steel molds; issuing an alarm signal when an abnormal situation is detected; providing an interactive interface between the system and the user includes: displaying mold information, usage status and production process information; receiving instructions input by the user; processing and analyzing the collected data includes: cleaning and preprocessing the data; applying linear regression algorithm, principal component analysis (PCA) algorithm, K-means clustering algorithm, decision tree and random forest algorithm to analyze the data.

[0155] This article uses specific examples to illustrate the principles and implementation methods of the present invention. The above examples are only used to help understand the method and core ideas of the present invention. The above is only a preferred implementation of the present invention. It should be pointed out that due to the limitations of textual expression and the objective existence of infinite specific structures, ordinary technicians in this technical field can make several improvements, modifications or changes without departing from the principles of the present invention, and can also combine the above technical features in an appropriate manner; these improvements, modifications, changes or combinations, or the direct application of the inventive concept and technical solution to other occasions without improvement, should be regarded as the protection scope of the present invention.

Claims

1. The process management system based on concrete steel mold is characterized by: include: The mold information collection module is used to collect the basic information of the concrete steel mold, including the mold number, location information, size parameters, material information, production batch, manufacturing date, and the last maintenance date; A data storage module, used to store the collected mold information, including a structured database and an unstructured data storage system; The mold status monitoring module is used to monitor the use status of concrete steel molds in real time, including the collection and recording of physical parameters such as temperature, pressure, humidity, vibration, wear and chemical corrosion; The production process management module is used to manage the use process of concrete steel molds in the production process, including mold scheduling, usage records, setting and adjustment of production process parameters, process optimization and production progress tracking; The alarm module is used to send out an alarm signal when an abnormal situation is monitored, and provide a detailed abnormal report, including the alarm type, occurrence time, abnormal parameters and possible cause analysis; User interface module, used to provide an interactive interface between the system and the user, including a graphical user interface (GUI), a mobile application interface, and a voice control interface; The data processing module is used to clean, analyze and model the collected data, including the implementation of multiple data analysis algorithms and prediction models, which are used to predict mold life, optimize production processes and perform preventive maintenance.

2. The process management system based on concrete steel mold according to claim 1 is characterized in that: The mold information acquisition module includes: A mold number collection unit is used to collect the unique number information of the concrete steel mold; Mould position acquisition unit, used to collect and update the position information of concrete steel moulds in real time, including GPS positioning and production line position identification; A mold state acquisition unit, used to collect current state information of the concrete steel mold through a sensor network, including a temperature sensor, a pressure sensor, a humidity sensor, an acceleration sensor, and a chemical corrosion detection sensor; The data storage module comprises: Relational database, used to store structured basic information and usage records of molds; Non-relational databases (NoSQL) for storing unstructured sensor data and log information; Distributed storage systems to improve the reliability and scalability of data storage; The mold status monitoring module includes: Multi-sensor fusion unit, used to fuse data from different sensors to improve data accuracy and reliability; Real-time data processing unit, used to process and analyze sensor data in real time and generate mold status reports; The production process management module includes: Process definition unit, used to define and manage the use process and production process of concrete steel molds; Process tracking unit, used to track the execution of concrete steel molds in the production process and generate process reports; Process optimization unit, used to optimize the use process according to the data analysis results, including the adjustment of use frequency, maintenance plan and process parameters; The alarm module comprises: Anomaly detection unit, used to detect abnormal conditions of concrete steel molds, including parameter out-of-limit, sensor failure and abnormal pattern recognition; An alarm signal issuing unit for issuing visual, audible and email alarm signals when an abnormal situation is detected; Abnormal analysis unit, used to analyze abnormal situations and provide possible causes and solutions; The user interface module comprises: Display unit, used to display mold information, usage status, production process information and alarm information; An input unit, used to receive instructions and feedback input by a user; Mobile application interface for accessing and operating the system via a mobile device; Voice control interface for operating the system via voice commands.

3. The process management system based on concrete steel mold according to claim 1 is characterized in that: The data processing module comprises: Data cleaning unit, used to clean and preprocess the collected data, including removing noise data, processing missing values ​​and standardizing data; The data analysis algorithm unit is used to analyze the cleaned data, including linear regression, principal component analysis (PCA), K-means clustering, decision tree, and random forest algorithms.

4. The process management system based on concrete steel mold according to claim 3 is characterized in that: The linear regression algorithm is used to predict the service life and status of the mold: The calculation formula is: Where y is the predicted mold life or status, x i is the parameter that affects the mold life, β0 is a constant term, β i is the regression coefficient; Specific parameters that affect mold life include: Temperature (T): x1; Pressure (P): x2; Humidity (H): x3; Vibration frequency (V): x4; Number of uses (U): x5; Chemical Corrosion (C): x6.

5. The process management system based on concrete steel mold according to claim 3 is characterized in that: The principal component analysis (PCA) algorithm is used to reduce dimension and extract data features: The calculation formula is: Z = XW; Among them, X is the standardized data matrix, W is the eigenvector matrix, and Z is the data matrix after dimensionality reduction.

6. The process management system based on concrete steel mold according to claim 3 is characterized in that: The K-means clustering algorithm is used to classify and group the dies using status: The calculation formula is: Where k is the number of clusters, Ci is the i-th cluster, μ i is the center of the ith cluster, and x is the data point in the cluster.

7. The process management system based on concrete steel mold according to claim 1 is characterized in that: The decision tree algorithm is used to classify and predict based on mold parameters and status: The calculation formula is: Information gain Among them, IG(T, a) is the information gain of attribute a, H(T) is the entropy of data set T, and T v is the subset whose value on attribute a is v.

8. The process management system based on concrete steel mold according to claim 1 is characterized by: The random forest algorithm is used to improve the accuracy and stability of predictions: The calculation formula is: Prediction based on the integrated results of multiple decision trees: Where M is the number of decision trees, h m (x) is the prediction result of the mth tree for sample x.

9. A control method for a process management system based on a concrete steel mold, characterized in that: The following steps are involved: Step 1: Collect basic information of concrete steel mold; Step 2: Storing the collected mold information; Step 3: Real-time monitoring of the use status of concrete steel molds; Step 4: Manage the use of concrete steel molds in the production process; Step 5: Send out an alarm signal when an abnormal situation is detected; Step 6: Provide an interactive interface between the system and the user; Step 7: Process and analyze the collected data.

10. The control method of the process management system based on concrete steel mold according to claim 9 is characterized in that: Collecting basic information of concrete steel molds includes: collecting mold number information, location information and current status information; real-time monitoring of the usage status of concrete steel molds includes: collecting physical parameters such as temperature, pressure, humidity, vibration, etc. of concrete steel molds; analyzing the collected physical parameters and judging the status of the molds; managing the usage process of concrete steel molds in the production process includes: defining the usage process of concrete steel molds; tracking the execution of concrete steel molds in the production process; optimizing the usage process according to data analysis results; issuing an alarm signal when an abnormal situation is monitored includes: detecting abnormal conditions of concrete steel molds; issuing an alarm signal when an abnormal situation is detected; providing an interactive interface between the system and the user includes: displaying mold information, usage status and production process information; receiving instructions input by the user; processing and analyzing the collected data includes: cleaning and preprocessing the data; applying linear regression algorithm, principal component analysis (PCA) algorithm, K-means clustering algorithm, decision tree and random forest algorithm to analyze the data.

Images