System for controlling intelligent industrial equipment by using Internet information transmission

Abstract

The invention discloses a system for controlling intelligent industrial equipment by using Internet information transmission, which relates to the technical field of industrial equipment control and comprises a data acquisition module, a data processing module, an intelligent prediction module, a control decision module and a communication module. According to the invention, by collecting multi-dimensional data, integrating equipment states, environmental parameters, historical data and other information and integrating the equipment states, environmental parameters and historical data through an LSTM algorithm in the intelligent prediction module, the fault type, time and part are accurately predicted, a basis is provided for equipment maintenance, a reasonable production plan is formulated, and the production efficiency is improved. When the intelligent prediction module predicts that the equipment may have a fault, the control decision module can timely adjust the operation parameters of the equipment, start the standby equipment and avoid the occurrence of the equipment fault, and through prediction and intervention in advance, the equipment fault rate can be remarkably reduced, the production efficiency and the product quality can be improved, and greater economic benefits can be brought to enterprises.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial equipment control, and particularly to a system for intelligent industrial equipment control using Internet information transmission. Background Art

[0002] In today's industrial production field, intelligent industrial equipment control plays a crucial role. Intelligent industrial equipment control aims to achieve efficient and precise management of industrial equipment, improve production efficiency, ensure product quality, and reduce production costs. Through advanced technical means, the operating status of equipment is monitored in real time, and equipment parameters are adjusted in a timely manner to adapt to different production requirements.

[0003] With the continuous development of information technology, using Internet information transmission for intelligent industrial equipment control has become a trend. This method has many remarkable effects and significance. First of all, Internet information transmission can realize the real-time transmission and sharing of equipment data, enabling the status information of equipment to quickly circulate between different locations and different departments. This helps enterprise managers and technicians to timely understand the operating conditions of equipment and make more accurate decisions. Secondly, using Internet information transmission can achieve remote control, greatly improving the flexibility and convenience of equipment control. No matter where one is, as long as there is a network connection, the equipment can be monitored and operated, significantly reducing the management costs of enterprises.

[0004] At present, there are still certain defects in the existing industrial equipment control systems when using Internet information transmission for intelligent control. The existing industrial equipment control systems often can only process single-dimensional data and cannot comprehensively consider various information such as equipment status, environmental parameters, and historical data, resulting in inaccurate prediction of equipment failures and unreasonable production plans, affecting production efficiency and product quality. Therefore, it is necessary to propose a system for intelligent industrial equipment control using Internet information transmission to solve the problems in the prior art. Summary of the Invention

[0005] The purpose of the present invention is to make up for the deficiencies of the prior art and provide a system for intelligent industrial equipment control using Internet information transmission. It can process multi-dimensional data and perform intelligent prediction, comprehensively considering various information such as equipment status, environmental parameters, and historical data, predicting equipment failures and optimizing production plans. Through early prediction and intervention, the equipment failure rate can be significantly reduced, production efficiency and product quality can be improved, bringing greater economic benefits to enterprises.

[0006] To solve the above technical problems, the present invention provides the following technical solution: A system for controlling intelligent industrial equipment using Internet information transmission, the system includes a data acquisition module, a data processing module, an intelligent prediction module, a control decision module and a communication module. The data acquisition module is responsible for collecting multi-dimensional data of equipment status data, environmental parameter data and production process data, and transmitting it to the data processing module. The data processing module cleans, transforms and stores the collected data. The intelligent prediction module is used to analyze and predict multi-dimensional data of equipment status, environmental parameters and historical data using the long short-term memory network (LSTM) algorithm, including predicting equipment failures and optimizing production plans. The control decision module formulates corresponding control decisions according to the prediction results of the intelligent prediction module to control and adjust industrial equipment. The communication module uses Internet information transmission technology to achieve data communication and remote control between the system modules;

[0007] The intelligent prediction module includes a data input unit, an LSTM algorithm unit and a prediction result output unit; the control decision module includes a prediction result receiving unit, an equipment control strategy formulation unit, a production plan adjustment unit and a control instruction sending unit. The prediction result receiving unit receives the prediction results output by the intelligent prediction module and verifies and evaluates them. The equipment control strategy formulation unit formulates corresponding equipment control strategies according to the equipment failure prediction results. The production plan adjustment unit adjusts the production plan based on the prediction results of production plan optimization. The control instruction sending unit sends the formulated control instructions to the equipment control module and the production management system, and tracks and feedbacks the execution status of the instructions.

[0008] Further, the data input unit receives multi-dimensional data from the data processing module, classifies, organizes and performs quality inspection on it to prepare for subsequent analysis. The LSTM algorithm unit uses the long short-term memory network algorithm to train and learn the input data. The output gate calculation formula is o t =σ(W o ·[h t-1 ,x t +b o ), where W o is the output gate weight matrix, b o is the output gate bias term, [h t-1 ,x t represents the vector concatenation of h t-1 and x t . The hidden state h t =o t ⊙tanh(C t ). In equipment failure prediction, the input data is defined as X=(X 1 ,X 2,…,X t ), the hidden state sequence H = (h 1 , h 2 , …, h t ) is obtained through LSTM calculation. Finally, the fault prediction result P = σ(W P ·h t + b P ) is obtained through the fully connected layer and the activation function, where W P is the weight matrix of the fully connected layer for fault prediction, b P is the bias term for fault prediction. P represents the probability of equipment failure. In the production plan optimization, the input data is defined as X = (X 1 , X 2 , …, X t ). The hidden state sequence H = (h 1 , h 2 , …, h t ) is obtained through LSTM calculation. Finally, the production plan parameter Y = W Y ·h t + b Y is obtained through the fully connected layer, where W Y is the weight matrix of the fully connected layer for production plan optimization, b Y is the bias term for production plan optimization. The prediction result output unit sorts and outputs the results obtained through model analysis and prediction. For the equipment fault prediction result, the confidence formula is C = 1 - P. For the production plan optimization result, the production efficiency improvement ratio formula is R = (E 2 - E 1 ) / E 1 .

[0009] Furthermore, the data acquisition module collects the equipment status data by installing various sensors on industrial equipment, including temperature sensors to collect the temperature values of key parts of the equipment, vibration sensors to monitor the vibration of the equipment, current sensors and voltage sensors to collect the operating current and voltage data of the equipment. The equipment control system transmits the equipment operating parameters, fault codes, and maintenance record data to the data acquisition module through the communication interface. The data acquisition module collects the environmental parameter data by installing temperature sensors, humidity sensors, air pressure sensors, and noise sensors in the environment where the equipment is located. For special environmental parameters, corresponding air quality sensors and dust sensors are used for collection.

[0010] Furthermore, the data acquisition module collects the production process data by installing a production counter on the production line to collect production data, collecting product quality data through quality inspection equipment, and collecting energy consumption data of the equipment during the production process through energy metering equipment.

[0011] Furthermore, the data processing module cleans, transforms, and stores the collected data. Data cleaning includes outlier handling. For a certain data point considered as an outlier, direct deletion and median replacement methods are used for processing. Data transformation includes format unification and data normalization. Format unification converts the data collected from different data sources into a unified data format. Data normalization performs normalization processing on the data. Data storage uses a database for data storage, establishes data indexes to improve query efficiency, formulates a data backup strategy, and establishes a data recovery mechanism.

[0012] Furthermore, the communication module uses Internet information transfer technology to achieve data communication and remote control between the system modules. The communication module adopts reliable Internet communication protocols, compresses and encrypts the transmitted data, and establishes a stable network connection management mechanism. The communication protocols include TCP / IP, HTTP, and MQTT. The ZIP algorithm is used for data compression, and symmetric encryption algorithms are used for encryption. The status of the network connection is detected through a heartbeat mechanism. When the network connection is interrupted, it automatically attempts to reconnect.

[0013] Furthermore, the communication module ensures data security through identity authentication, access control, and encrypted data storage. Username / password authentication is used for identity authentication. Role-based access control (RBAC) and attribute-based access control (ABAC) are used for access control. Database-level encryption technology is used to encrypt the sensitive data stored in the database.

[0014] Furthermore, in the device control strategy formulation unit of the control decision module, control strategies are formulated according to the severity of the faults. Define the fault severity index S, and determine the control strategy by combining the importance parameter I of the device and the production impact factor F. S = αI + βF, where α and β are weight coefficients, and their value ranges are both [0, 1], and α + β = 1. Their values can be obtained through machine learning training on historical device fault data and production impact data. When S < S 0 a strategy of adjusting the device operation parameters is adopted. Define the device operation parameter as P, and the adjustment amount as ΔP. The adjustment amount is determined according to the empirical formula ΔP = γS, where γ is an adjustment coefficient. When S > S 0 the standby device is started, and the startup priority P of the standby device is calculated p = ηS, where η is a priority coefficient. S 0 is a preset threshold, and its value is determined according to the device type and production requirements.

[0015] Furthermore, in the production plan adjustment unit of the control decision module, analyze and evaluate the production plan optimization suggestions in combination with the enterprise's production goals, resource constraints, and actual situation. Define the production objective function as G, the resource constraint condition as C, and the production plan variable as X. Solve the optimal production plan that meets the constraint conditions through an optimization algorithm, that is, maxG(X), s.t.C(X)≤0. The production objective function is to maximize production efficiency, that is, G(X) = E(X), where E(X) represents the production efficiency function, which is a linear function of the production plan variable X. where k i is a coefficient related to production tasks and resources, determined according to the actual production situation. n is the number of production plan variables. The resource constraint conditions include equipment availability, the number of personnel, and raw material supply.

[0016] Furthermore, in the control instruction sending unit of the control decision module, convert the equipment control strategy and production plan adjustment plan into specific control instructions. For the equipment control instruction, generate an equipment parameter adjustment instruction and a standby equipment startup instruction. If the equipment parameter P needs to be adjusted to a new value P ′ , then generate the instruction SetP(P′). For the production plan adjustment instruction, generate a production task allocation instruction and a production process change instruction. If the production task needs to be allocated from equipment A to equipment B, then generate the instruction AssignTask(A,B).

[0017] Compared with the prior art, the system for intelligent industrial equipment control using Internet information transmission has the following beneficial effects:

[0018] By collecting multi-dimensional data, integrating various information such as equipment status, environmental parameters, and historical data, and using the LSTM algorithm in the intelligent prediction module to comprehensively analyze equipment status, environmental parameters, and historical data, the present invention accurately predicts the fault type, time, and location, providing a basis for equipment maintenance. At the same time, a reasonable production plan is formulated. When the intelligent prediction module predicts that a device may malfunction, the control decision module can timely adjust the device operation parameters and start standby equipment to avoid the occurrence of equipment failures. Through early prediction and intervention, the equipment failure rate can be significantly reduced, production efficiency and product quality can be improved, and greater economic benefits can be brought to the enterprise.

[0019] Other advantages, objectives, and features of the present invention will be described to some extent in the subsequent specification, and to some extent, will be obvious to those skilled in the art based on the study of the following text, or can be taught from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the accompanying drawings required for the description of the embodiments or the prior art. Obviously, the accompanying drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other accompanying drawings can be obtained based on these drawings.

[0021] Figure 1 It is a schematic structural diagram of a system for controlling intelligent industrial equipment using Internet information transmission. Detailed implementation manners

[0022] The following will clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts belong to the scope of protection of the present invention.

[0023] Embodiment 1

[0024] In this embodiment, the system is applied to a large automobile manufacturing factory, which covers multiple workshops and has a wide variety of intelligent industrial equipment, including high-precision stamping machines, flexible welding robots, advanced painting equipment, and complex assembly production lines, etc. These equipment play key roles in different production links, and their stable operation is directly related to the production efficiency, product quality, and economic benefits of the factory.

[0025] Professional sensors are installed at key parts of various equipment. For example, vibration sensors are installed at key transmission parts of the stamping machine to monitor the vibration of the equipment in real time, temperature sensors are installed near the welding torch of the welding robot to monitor the temperature changes during the welding process, and flow sensors are installed at the paint gun of the painting equipment to master the paint spraying volume. At the same time, the control system of the equipment transmits status data such as operation parameters, fault codes, and maintenance records of the equipment to the data acquisition module through a communication interface.

[0026] Environmental monitoring equipment is set in different areas of the factory. Temperature sensors, humidity sensors, air pressure sensors, etc. are installed in the workshop to comprehensively collect environmental parameter data. For special production areas, such as the painting workshop, air quality sensors are also installed to monitor the concentration of harmful gases in the air to ensure the safety of the production environment.

[0027] Production process data is collected through automatic counting equipment and high-precision quality inspection equipment on the production line. The production counter accurately records the number of products in each production link. The quality inspection equipment uses advanced optical inspection technology and mechanical property testing equipment to comprehensively detect the dimensional accuracy, surface quality, mechanical properties, etc. of the products.

[0028] Use a variety of statistical methods to process the collected data for outliers. First, calculate the mean and standard deviation of various types of data. For the equipment operation status data, such as temperature values, if the deviation of a certain temperature data point from the mean exceeds a specific multiple of the standard deviation, it is marked as an outlier. For the marked outliers, methods such as direct deletion, replacement with the mean or median can be selected for processing according to the specific situation. For continuously occurring outliers, the system will issue an alarm to remind the technician to check whether there are potential faults in the equipment.

[0029] For data from different sources, perform unified format conversion, converting the data in different formats output by various sensors into a unified data format to facilitate subsequent analysis and processing. For example, convert the Fahrenheit data output by the temperature sensor into Celsius, and unify the timestamp format into the standard date and time format to ensure data consistency and comparability.

[0030] According to the scale and characteristics of the data, select a suitable database for storage. For large-scale structured data, such as equipment status data and production process data, use a relational database for storage, design a reasonable data table structure, including fields such as equipment number, timestamp, status parameters, etc., and establish indexes to improve data query efficiency. For unstructured or semi-structured data, such as equipment maintenance records and fault description texts, use a non-relational database for storage. At the same time, formulate a data backup strategy, perform full backups and incremental backups on the data regularly, and store the backup data in different physical locations or cloud storage to ensure data security and recoverability.

[0031] After the data input unit receives the data from the data processing module, it uses a data classification algorithm to classify and organize the data according to the type and attributes of the data. Classify the equipment operation status data into categories such as temperature, pressure, vibration, etc., classify the environmental parameter data into categories such as temperature, humidity, air quality, etc., and store the historical data according to the time series. At the same time, perform a preliminary quality check on the data. By setting data ranges and thresholds, detect outliers and error data. For example, for temperature data, set a normal temperature range. If the data exceeds this range, it is marked as an outlier and promptly fed back to the data processing module for reprocessing or marking.

[0032] In equipment fault prediction, assume the input data is a multi-dimensional data sequence X = (X 1 , X 2 , …, X t ) within a period of time. After LSTM calculation, the hidden state sequence H = (h 1 , h 2 , …, h t), and finally, the fault prediction result P = σ(W P ·h t +b P ) is obtained through the fully connected layer and the activation function, where W P is the weight matrix, b P is the bias term. By learning the historical fault data of the device, the current device status, and environmental parameters, the possible fault types, fault times, and fault locations of the device are predicted.

[0033] In the production plan optimization, the input data is also set as a multi-dimensional data sequence X = (X 1 , X 2 , …, X t ) within a period of time. After LSTM calculation, the hidden state sequence H = (h 1 , h 2 , …, h t ) is obtained. Finally, the production plan parameter Y = W Y ·h t +b Y is obtained through the fully connected layer, where W Y is the weight matrix, b Y is the bias term. By combining the device status, environmental parameters, and production process data, the production plan is optimized, and reasonable suggestions for production task allocation and production process optimization are proposed.

[0034] The prediction result output unit sorts and formats the results output by the LSTM. For the device fault prediction result, the confidence level is calculated. The confidence level calculation formula is C = 1 - P, where P is the probability of the fault occurrence. The fault type, possible occurrence time, location, etc. are presented in a clear report form, and the predicted probability and confidence level are attached. For the production plan optimization result, a detailed production task allocation plan, production process improvement measures, etc. are generated and presented in the form of charts or texts. At the same time, the production efficiency improvement ratio calculation formula is R = (E 2 - E 1 ) / E 1 , where E 1 is the production efficiency before optimization, and E 2 is the production efficiency after optimization.

[0035] The prediction result receiving unit continuously receives the prediction results output by the intelligent prediction module, and uses the data verification algorithm to check the integrity and rationality of the received prediction results. For the device fault prediction result, it checks whether necessary information such as the fault type, time, location, etc. is included. For the production plan optimization suggestions, it checks whether they meet the production goals and resource constraints of the enterprise. If it is found that the results are incomplete or unreasonable, it will promptly feedback to the intelligent prediction module and request re-prediction or adjustment.

[0036] The device control strategy formulation unit formulates corresponding device control strategies according to the device fault prediction results. It sets the fault severity index S and determines the control strategy by combining the device importance parameter I and the production impact factor F, that is, S = αI + βF. Here, α and β are weight coefficients. If S is small, a strategy of adjusting the device operation parameters can be adopted. Let the device operation parameter be P and the adjustment amount be ΔP. The adjustment amount is determined according to the empirical formula ΔP = γS, where γ is the adjustment coefficient. If S is large, it is necessary to start the standby device and calculate the startup priority P p = ηS, where η is the priority coefficient. Considering factors such as the safety, stability, and production efficiency of the device, the formulated control strategy is evaluated and optimized.

[0037] The production plan adjustment unit adjusts the production plan based on the prediction results of production plan optimization, analyzes and evaluates it in combination with the enterprise's production goals, resource constraints, and actual situation. Let the production objective function be G, the resource constraint condition be C, and the production plan variable be X. The optimal production plan that meets the constraint conditions is solved through an optimization algorithm, that is, maxG(X), s.t.C(X) ≤ 0. For example, the production objective function can be to maximize production efficiency, that is, G(X) = E(X), where E(x) represents the production efficiency function. The resource constraint conditions can include device availability, the number of personnel, raw material supply, etc. According to the evaluation results, a specific production plan adjustment plan is formulated, including reallocating production tasks, optimizing production processes, adjusting production schedules, etc.

[0038] The control instruction sending unit converts the device control strategy and the production plan adjustment plan into specific control instructions. For device control instructions, it generates device parameter adjustment instructions or standby device startup instructions. For example, if it is necessary to adjust the device parameter P to a new value P′, then the instruction SetP(P′) is generated. For production plan adjustment instructions, it generates production task allocation instructions, production process change instructions, etc. For example, if it is necessary to allocate the production task from device A to device B, then the instruction AssignTask(A,B) is generated. The control instructions are sent to the device control module and the production management system safely and accurately through the Internet communication module, and the execution status of the instructions is tracked and fed back to ensure that the control strategy and the production plan adjustment plan can be effectively executed.

[0039] A reliable Internet communication protocol, such as the MQTT protocol, is adopted to realize data communication between the system modules. The device status data is published to the message broker server through the MQTT protocol. The intelligent prediction module and the control decision module subscribe to the corresponding topics and receive the device status data in real time to ensure that the data can be transmitted quickly and accurately between different modules.

[0040] Compress and encrypt the transmitted data. The GZIP algorithm can be used to compress the data, reduce the data transmission volume, and improve the transmission efficiency. Then, the AES algorithm is used to encrypt the compressed data to prevent the data from being stolen or tampered with during transmission. By establishing a stable network connection and data transmission protocol, the security and integrity of the data are ensured.

[0041] Ensure data security through identity authentication, access control, and encrypted data storage. Username / password authentication can be used for identity authentication to ensure that only authorized users can access the system. Role-based access control (RBAC) can be used for access control, and different permissions are assigned according to the user's role to limit the user's access to system resources. Sensitive data stored in the database is encrypted for storage. Database-level encryption technology can be used, or the data can be encrypted at the application layer and then stored in the database to prevent data leakage.

[0042] In summary: By comprehensively collecting multi-dimensional information such as device status, environmental parameters, and historical data, and performing effective cleaning, transformation, and storage, high-quality data support is provided for intelligent prediction and control decisions, enabling a more accurate understanding of the device's operating conditions and production environment, improving the accuracy of device fault prediction and the rationality of production plans. Using the long short-term memory network (LSTM) algorithm, accurate prediction of device faults and optimization of production plans are achieved. Device faults are predicted in advance, enabling the factory to take timely measures to avoid the occurrence of device faults, reducing device maintenance costs and downtime. The optimized production plan improves production efficiency and product quality, bringing greater economic benefits to the enterprise. Using Internet information transmission technology, data communication and remote control between system modules are realized, improving the flexibility and scalability of the system, enabling factory managers to monitor the device operating status and production progress at any time, and timely adjusting production plans and control strategies. Through measures such as encryption, identity authentication, and access control of the communication module, the security of data during Internet transmission is ensured, preventing the data from being stolen or tampered with, ensuring the stability and reliability of the system, significantly reducing the device failure rate, improving production efficiency and product quality, bringing greater economic benefits to the enterprise, and at the same time, reducing device maintenance costs and downtime, and improving the utilization rate of devices and the continuity of production.

[0043] Example 2

[0044] In this example, the system is applied to a modern electronic manufacturing factory that mainly produces electronic devices such as smartphones. There are many intelligent industrial devices in the factory, such as highly automated SMT pick-and-place machines, wave soldering machines, and assembly lines. The efficient and stable operation of these devices is crucial for meeting market demands and ensuring product quality.

[0045] Install high-precision sensors on the SMT mounter, such as pressure sensors to monitor the pressure of the placement head, displacement sensors to monitor the placement position, and temperature sensors to monitor the temperature of key parts of the equipment. At the same time, the control system of the equipment transmits operating parameters such as placement speed and placement accuracy to the data acquisition module.

[0046] Arrange temperature sensors, humidity sensors, static electricity sensors, etc. in the factory environment to collect environmental parameter data. Since electronic manufacturing has extremely high requirements for the environment and static electricity may damage electronic components, the monitoring of static electricity sensors is particularly important.

[0047] Collect production process data through counting devices and inspection devices on the production line. For example, use optical inspection devices to detect the welding quality of PCB boards and functional test devices to detect the performance indicators of mobile phones, etc.

[0048] For various types of collected data, calculate their mean and standard deviation. If the deviation of a certain data point from the mean exceeds a specific multiple of the standard deviation, it is regarded as an outlier. For the pressure data of the SMT mounter, if extremely high or low values appear, it may mean a placement head failure or component damage, and processing is required. You can choose to replace the outlier with the mean or median, or issue an alarm to let the technician check the equipment.

[0049] Convert the data output by different sensors and devices into a unified format. For example, convert the Fahrenheit data of the temperature sensor to Celsius, and unify the timestamp to the standard format for subsequent analysis.

[0050] Select a suitable database for storage according to the characteristics and scale of the data. For structured data such as equipment status data and production process data, use a relational database for storage and establish indexes to improve query efficiency. For unstructured data such as equipment maintenance records, use a non-relational database for storage. At the same time, formulate a regular data backup strategy to ensure data security.

[0051] After the data input unit receives the data from the data processing module, it classifies and organizes them according to the data type. Classify the equipment operation status data into categories such as pressure, displacement, and temperature, classify the environmental parameter data into categories such as temperature, humidity, and static electricity, and store the historical data in time series. At the same time, conduct a preliminary quality inspection, set the data range and threshold, and detect outliers and error data.

[0052] In equipment fault prediction, let the input data be a multi-dimensional data sequence X=(X 1 ,X 2 ,…,X t ) within a period of time. After LSTM calculation, the hidden state sequence H=(h 1 ,h 2 ,…,ht ), and finally obtain the fault prediction result \(P = \sigma(W P \cdot h t + b P ) to predict the possible fault types of the SMT mounter, such as pick - and - place head wear, sensor failure, etc., as well as the time and location of the fault occurrence.

[0053] In the production plan optimization, also set the input data as a multi - dimensional data sequence \(X=(X 1 , X 2 , \cdots, X t ) within a period of time. After LSTM calculation, obtain the hidden state sequence \(H=(h 1 , h 2 , \cdots, h t ). Finally, obtain the production plan parameters \(Y = W Y \cdot h t + b Y to optimize the production task allocation and production process according to the equipment status, environmental parameters and production requirements, and improve production efficiency.

[0054] For the equipment fault prediction result, the prediction result output unit calculates the confidence level \(C = 1 - P\) and presents the fault information in the form of a report. For the production plan optimization result, it generates a detailed production task allocation plan and process improvement measures, and calculates the production efficiency improvement ratio \(R=(E 2 - E 1 ) / E 1 .

[0055] The prediction result receiving unit receives the output result of the intelligent prediction module and conducts integrity and rationality checks, checking whether the fault prediction result contains necessary information and whether the production plan optimization suggestions meet the production goals and resource constraints.

[0056] The equipment control strategy formulation unit formulates a control strategy according to the fault prediction result, sets the fault severity index \(S=\alpha I+\beta F\), where \(I\) is the equipment importance parameter and \(F\) is the production impact factor. If \(S\) is small, adjust the equipment operation parameters, such as reducing the placement speed, adjusting the temperature, etc., and set the adjustment amount as \(\Delta P=\gamma S\), where \(\gamma\) is the adjustment coefficient. If \(S\) is large, start the standby equipment and calculate the priority \(P p =\eta S\), where \(\eta\) is the priority coefficient.

[0057] The production plan adjustment unit adjusts the production plan according to the optimized prediction result of the production plan. Let the production objective function be G and the resource constraint condition be C. The optimal production plan is solved through an optimization algorithm, that is, maxG(X), s.t.C(X)≤0. For example, the production objective function is to maximize production efficiency G(X) = E(X), and the resource constraints include equipment availability, the number of personnel, etc. Specific production plan adjustment schemes are formulated, such as reallocating production tasks and optimizing the assembly process.

[0058] The control instruction sending unit converts the control strategy and the production plan adjustment scheme into specific control instructions. For equipment control instructions, parameter adjustment instructions or standby equipment startup instructions are generated. For production plan adjustment instructions, task assignment instructions, process change instructions, etc. are generated and sent to the corresponding equipment and management systems, and the instruction execution situation is tracked.

[0059] A reliable Internet communication protocol, such as the MQTT protocol, is adopted to realize data communication between modules. The device status data is published to the message broker server, and the intelligent prediction module and the control decision module subscribe to the corresponding topics to receive data in real time.

[0060] The transmitted data is compressed and encrypted. The GZIP algorithm is used to compress the data, and the AES algorithm is used to encrypt the data to ensure the secure transmission of the data.

[0061] Data security is guaranteed through methods such as identity authentication, access control, and encrypted storage of data. Username / password authentication and role-based access control are adopted, and sensitive data is encrypted and stored.

[0062] In summary: Considering equipment status, environmental parameters, and historical data comprehensively, the accuracy of fault prediction and the rationality of the production plan are improved. For example, by monitoring environmental static electricity and equipment temperature, it is possible to better prevent damage to electronic components and equipment failures. The LSTM algorithm is used to accurately predict equipment failures and optimize the production plan, taking preventive measures in advance to reduce equipment failure rates and maintenance costs, improve production efficiency and product quality, realize data communication and remote control, improve the flexibility and scalability of the system. Managers can monitor the production situation at any time, adjust strategies, ensure the security of data during transmission and storage, prevent data leakage and tampering, ensure the stable operation of the system, reduce equipment failure rates, improve production efficiency, meet market demands, and bring greater economic benefits to the enterprise.

[0063] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above-described exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the same elements of the claims are intended to be embraced within the present invention. Any reference signs in the claims should not be construed as limiting the claims involved.

Claims

1. A system for controlling intelligent industrial equipment using Internet information transmission, characterized in that: The system includes a data acquisition module, a data processing module, an intelligent prediction module, a control decision module and a communication module. The data acquisition module is responsible for collecting multi-dimensional data of equipment status data, environmental parameter data and production process data, and transmitting it to the data processing module. The data processing module cleans, converts and stores the collected data. The intelligent prediction module is used to analyze and predict the multi-dimensional data of equipment status, environmental parameters and historical data using the long short-term memory network LSTM algorithm, including predicting equipment failures and optimizing production plans. The control decision module formulates corresponding control decisions based on the prediction results of the intelligent prediction module to control and adjust the industrial equipment. The communication module uses Internet information transmission technology to realize data communication and remote control between the modules of the system. The intelligent prediction module includes a data input unit, an LSTM algorithm unit and a prediction result output unit; The control decision module includes a prediction result receiving unit, an equipment control strategy formulation unit, a production plan adjustment unit and a control instruction sending unit. The prediction result receiving unit receives the prediction result output by the intelligent prediction module and verifies and evaluates it. The equipment control strategy formulation unit formulates a corresponding equipment control strategy according to the equipment failure prediction result. The production plan adjustment unit adjusts the production plan according to the prediction result of the production plan optimization. The control instruction sending unit sends the formulated control instructions to the equipment control module and the production management system, and tracks and provides feedback on the execution of the instructions.

2. According to claim 1, a system for controlling intelligent industrial equipment using Internet information transmission is characterized in that: The data input unit receives multi-dimensional data from the data processing module and performs classification and quality inspection to prepare for subsequent analysis. The LSTM algorithm unit uses the long short-term memory network algorithm to train and learn the input data. The output gate calculation formula is o t =σ(W o ·[h t-1 ,x t ]+b o ), where W o is the output gate weight matrix, b o is the output gate bias term, [h t-1 ,x t ] means to set h t-1 and x t Concatenate by vector, hidden state h t =o t ⊙tanh(C t ), in equipment failure prediction, the input data is defined as X = (X1, X2, ..., X t ), the hidden state sequence H = (h1,h2,…,h t ), and finally the fault prediction result P = σ(W P ·h t +b P ), where W P is the weight matrix of the fault prediction fully connected layer, b P is the fault prediction bias term, P represents the probability of equipment failure. In production planning optimization, the input data is defined as X = (X1, X2, ..., X t ), the hidden state sequence H = (h1,h2,…,h t ), and finally obtain the production plan parameter Y = W through the fully connected layer Y ·h t +b Y , where W Y Optimize the fully connected layer weight matrix for production planning, b Y For the production plan optimization bias item, the prediction result output unit will organize and output the results obtained through model analysis and prediction. For the equipment failure prediction result, the confidence calculation formula is C=1-P. For the production plan optimization result, the production efficiency improvement ratio calculation formula is R=(E2-E1) / E1.

3. According to claim 1, a system for controlling intelligent industrial equipment using Internet information transmission is characterized in that: The data acquisition module collects equipment status data by installing various sensors on industrial equipment, including temperature sensors to collect temperature values ​​of key parts of equipment, vibration sensors to monitor equipment vibration conditions, current sensors and voltage sensors to collect equipment operating current and voltage data. The equipment control system transmits equipment operating parameters, fault codes and maintenance record data to the data acquisition module through a communication interface. The data acquisition module collects environmental parameter data by installing temperature sensors, humidity sensors, air pressure sensors and noise sensors in the environment where the equipment is located. Special environmental parameters are collected using corresponding air quality sensors and dust sensors.

4. A system for controlling intelligent industrial equipment using Internet information transmission according to claim 1, characterized in that: The data acquisition module collects production process data by installing a production counter on the production line to collect production data, collects product quality data through quality inspection equipment, and collects energy consumption data of equipment during the production process through energy metering equipment.

5. The system for controlling intelligent industrial equipment by using Internet information transmission according to claim 1 is characterized in that: The data processing module cleans, converts and stores the collected data, wherein data cleaning includes outlier processing. A data point is considered to be an outlier and is processed using direct deletion and median replacement methods. Data conversion includes format unification and data normalization. Format unification converts the collected data from different data sources into a unified data format. Data normalization normalizes the data. A database is used for data storage. Data indexes are established to improve query efficiency. A data backup strategy is formulated and a data recovery mechanism is established.

6. The system for controlling intelligent industrial equipment by using Internet information transmission according to claim 1 is characterized in that: The communication module uses Internet information transmission technology to achieve data communication and remote control between modules of the system. The communication module adopts reliable Internet communication protocols to compress and encrypt transmitted data and establish a stable network connection management mechanism. The communication protocols include TCP / IP, HTTP, and MQTT. The ZIP algorithm is used to compress data and the symmetric encryption algorithm is used for encryption. The status of the network connection is detected through the heartbeat mechanism. When the network connection is interrupted, it automatically attempts to reconnect.

7. A system for controlling intelligent industrial equipment using Internet information transmission according to claim 6, characterized in that: The communication module ensures data security through identity authentication, access control and data encryption storage. Identity authentication adopts username / password authentication, access control adopts role-based access control RBAC and attribute-based access control ABAC, and database-level encryption technology is used to encrypt and store sensitive data stored in the database.

8. The system for controlling intelligent industrial equipment by using Internet information transmission according to claim 1 is characterized in that: In the device control strategy formulation unit of the control decision module, the control strategy is formulated according to the severity of the fault. Define the fault severity index S, and determine the control strategy by combining the importance parameter I of the device and the production impact factor F. S = αI + βF, where α and β are weight coefficients, and the value ranges of both are [0, 1], and α + β = 1. Their values can be obtained through machine learning training on historical device fault data and production impact data. When S < S0, adopt the strategy of adjusting the device operation parameters. Define the device operation parameter as P, and the adjustment amount as ΔP. Determine the adjustment amount according to the empirical formula ΔP = γS, where γ is the adjustment coefficient. When S > S0, start the standby device and calculate the priority P p of starting the standby device = ηS, where η is the priority coefficient, and S0 is the preset threshold, and its value is determined according to the device type and production requirements.

9. The system for controlling intelligent industrial equipment by using Internet information transmission according to claim 1 is characterized in that: In the production plan adjustment unit of the control decision module, the production plan optimization suggestions are analyzed and evaluated in combination with the company's production goals, resource constraints and actual conditions. The production objective function is defined as G, the resource constraints are defined as C, and the production plan variable is defined as X. The optimal production plan that meets the constraints is solved through the optimization algorithm, that is, maxG(X), stC(X)≤0. The production objective function is to maximize production efficiency, that is, G(X)=E(X), where E(X) represents the production efficiency function, which is a linear function of the production plan variable X. where k i is a coefficient related to production tasks and resources, which is determined according to actual production conditions, n is the number of production plan variables, and resource constraints include equipment availability, number of personnel, and raw material supply.

10. The system for controlling intelligent industrial equipment by using Internet information transmission according to claim 1, characterized in that: In the control instruction sending unit of the control decision module, the equipment control strategy and production plan adjustment plan are converted into specific control instructions. For the equipment control instructions, the equipment parameter adjustment instructions and the standby equipment startup instructions are generated. The equipment parameter P needs to be adjusted to the new value P ′ , then generate the instruction SetP(P ′ ), for the production plan adjustment instruction, generate the production task allocation instruction and the production process change instruction. If the production task needs to be assigned from device A to device B, then generate the instruction AssignTask(A,B).

Images