Intelligent detection and monitoring cloud service platform for industrial equipment

Abstract

The invention discloses an industrial equipment intelligent detection and monitoring cloud service platform, and relates to the technical field of industrial equipment detection and monitoring, and the platform comprises the following components: a data perception and transmission module, a data storage and management module, an association mining and causal analysis module, an anomaly detection and early warning module, and a prediction and decision support module. By integrating advanced data mining, correlation analysis and causal inference algorithms, potential laws and causal relationships in equipment operation data can be deeply mined, accurate assessment of the equipment health state is realized, and based on the analysis results, the platform can predict possible faults of the equipment in advance and provide early warning information for a user, so that the user experience is improved. An enterprise can take active maintenance measures, production interruption and loss caused by sudden equipment failures are avoided, and the reliability and the production efficiency of the equipment are remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial equipment detection and monitoring, and specifically to an intelligent detection and monitoring cloud service platform for industrial equipment. Background Art

[0002] With the efficient operation and reliability guarantee of industrial equipment becoming an important manifestation of enterprise competitiveness, a large amount of data is generated during the operation of industrial equipment. These data contain important information about the equipment status, performance, and potential faults. However, traditional industrial equipment detection and monitoring methods often rely on manual inspections and regular maintenance, which are not only inefficient but also difficult to capture the subtle changes and potential problems in equipment operation. Therefore, how to use modern information technology means to achieve intelligent detection and monitoring of industrial equipment has become a technical problem urgently to be solved in the current industrial field.

[0003] Traditional industrial equipment detection and monitoring technologies mainly rely on single-sensor data or simple data statistical methods, and it is difficult to comprehensively capture multi-dimensional information during equipment operation. In terms of data correlation mining and causal analysis, traditional technologies often have the following deficiencies: First, data collection is incomplete. Only relying on a few key parameters is difficult to reflect the overall operation status of the equipment; second, the data processing method is simple, lacking in-depth data mining and causal analysis capabilities, and it is difficult to reveal the potential relationships and fault roots between data; third, the early warning and prediction mechanisms are imperfect, unable to detect and prevent equipment failures in advance, resulting in long equipment downtime and high maintenance costs. Therefore, traditional technologies are difficult to meet the requirements of modern industry for intelligent, precise, and real-time equipment detection and monitoring.

[0004] In view of the above invention, it is necessary to optimize the existing intelligent detection and monitoring cloud service platform for industrial equipment. By integrating high-precision sensors, wireless transmission technology, distributed storage technology, and advanced data analysis algorithms, comprehensive collection, efficient storage, and in-depth analysis of industrial equipment operation data can be achieved. Therefore, it is of great significance to develop an intelligent detection and monitoring cloud service platform for industrial equipment that can comprehensively achieve the above characteristics. Summary of the Invention

[0005] The object of the present invention is to make up for the deficiencies of the prior art and provide an intelligent detection and monitoring cloud service platform for industrial equipment. It can collect equipment operation data in real time through multiple types of sensors, use wireless transmission technology to ensure the timeliness and reliability of data, then adopt distributed storage technology to ensure the security and scalability of data, and deeply mine the correlation rules and causal relationships between data through data mining algorithms. Finally, combine prediction algorithms to predict the future operation status of the equipment and provide intuitive display and decision support. It not only overcomes the limitations of traditional technologies in data correlation mining and causal analysis, but also significantly improves the intelligent level of industrial equipment detection and monitoring, providing strong technical support for the equipment management of enterprises.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: An intelligent detection and monitoring cloud service platform for industrial equipment, which includes the following components: a data perception and transmission module, a data storage and management module, an association mining and causal analysis module, an anomaly detection and warning module, a prediction and decision support module;

[0007] The data perception and transmission module uses high-precision sensors to collect various operation parameters of industrial equipment in real time, determines the sensor installation positions according to the characteristics and requirements of different industrial equipment, and sends the data to the cloud service platform through wireless transmission technology. At the same time, data encryption and verification technologies are used to verify the transmitted data;

[0008] The data storage and management module uses distributed storage technology to disperse and store a large amount of equipment operation data on multiple nodes, uses a database management system to classify and store and manage the data, at the same time uses indexing technology and partitioning technology to improve data query efficiency, and uses a combination of regular backup and real-time backup to ensure data security,

[0009] The association mining and causal analysis module analyzes the association rules between temperature changes, equipment energy consumption, and vibration frequency under specific working conditions, and establishes a data association model. Specifically, preprocess the collected data, remove noise data and outliers, select a data mining algorithm for association analysis, and its calculation formula is: Where C(T, E, V) represents the probability that temperature, energy consumption, and vibration frequency appear simultaneously, P(T), P(E), and P(V) respectively represent the probabilities that temperature, energy consumption, and vibration frequency appear alone, T, E, and V are the means of temperature, energy consumption, and vibration frequency respectively, and ω is an adjustment coefficient used to balance the contributions of the two parts. And use a causal inference algorithm to analyze the causal relationships between different data, providing a basis for predicting the impact of different data change trends on equipment performance and faults. Specifically, let the data item set be D = {X1, X2,..., X n}, for any two data items X i and Xj , define the causal relationship strength as R ij , where I Xi→Xj and I Xj→Xi are the causal influence coefficients of X i on X j and X j on X i respectively. C(X i , X j ) represents the probability that X i and X j appear simultaneously. P(X i ), P(X j ) represent the probabilities that X i and X j appear alone respectively. μ is an adjustment coefficient;

[0010] The anomaly detection and warning module uses anomaly detection algorithms to monitor data changes in real time. When an anomaly is detected, relevant personnel are notified for processing through SMS, email, and mobile APP push methods. At the same time, detailed information about the anomaly is recorded to provide a basis for subsequent analysis and processing;

[0011] The prediction and decision support module predicts the future operating state of the device using prediction algorithms based on the results of data correlation mining and causal analysis, and presents the analysis and processing results to users in the form of intuitive charts and reports.

[0012] Furthermore, the sensors in the data perception and transmission module include temperature sensors, pressure sensors, flow sensors, energy consumption sensors, and vibration sensors. The installation positions of the sensors are reasonably determined according to the characteristics and requirements of different industrial devices to enable accurate collection of key parameters.

[0013] Even further, the data encryption and verification technologies adopted by the data perception and transmission module include encrypting data using the AES encryption algorithm and verifying the transmitted data using CRC check codes.

[0014] Even further, the data storage and management module adopts distributed storage technologies, including the Hadoop distributed file system and Ceph, to disperse and store a large amount of device operation data on multiple nodes, thus effectively coping with the rapid growth of data volume and avoiding data loss caused by single-point failures

[0015] Furthermore, the data storage and management module uses database management systems, including MySQL and Oracle, to classify and store data. Different database tables are established according to the type and use of the data. At the same time, indexing technology and partitioning technology are adopted to partition and store data according to time or device type, enabling it to query and analyze data for specific time periods and specific types of devices. In addition, to prevent data loss, a combination of regular backup and real-time backup is used to back up data to different storage media, and a data recovery mechanism is established. When data is damaged or lost, the data can be quickly restored.

[0016] Furthermore, the anomaly detection and warning module uses anomaly detection algorithms to monitor data changes in real time. When an abnormal data combination appears, it can issue an alarm in a timely manner, quickly locate the root cause of the problem, and notify relevant personnel for processing through SMS, email, and mobile APP push. At the same time, detailed information about the abnormal situation is recorded to provide a basis for subsequent analysis and processing. To improve the accuracy of problem location, the results of data association mining and causal analysis are combined to determine the association relationship between abnormal data and other data, thereby judging the cause of the problem.

[0017] Furthermore, the anomaly detection and warning module uses an anomaly score calculation formula When the anomaly score exceeds a certain threshold, it is determined as an abnormal data combination. Among them, A represents the anomaly scores of temperature (T), energy consumption (E), and vibration frequency (V), T, E, and V respectively represent the average values of temperature, energy consumption, and vibration frequency, and S(T, E, V) is the association strength obtained from the association mining and causal analysis module.

[0018] Furthermore, the prediction and decision support module uses prediction algorithms to predict the future operating state of the device based on the results of data association mining and causal analysis. The algorithm formula is: Where F(t + Δt) represents the predicted value of the device's state at future time t + Δt, F(t) represents the device's state value at the current time t, n represents the number of factors affecting the device's state, α i represents the weight coefficient of the i-th factor, I i→F represents the causal influence coefficient of the i-th factor on the device's state, Δt represents the time interval, ∈ represents the random error term. This formula predicts the future operating state of the device based on the current device state and the causal influence coefficients of different factors.

[0019] Compared with the prior art, this industrial device intelligent detection and monitoring cloud service platform has the following beneficial effects:

[0020] 1. By integrating advanced data mining, correlation analysis, and causal inference algorithms, the present invention can deeply explore the potential patterns and causal relationships in the device operation data, achieving accurate assessment of the device health status. Based on these analysis results, the platform can predict in advance the possible faults of the device and provide warning information to users, enabling enterprises to take proactive maintenance measures, avoiding production interruptions and losses caused by sudden device failures, and significantly improving the reliability and production efficiency of the device.

[0021] 2. Through precise data analysis and fault prediction, the present invention can provide personalized maintenance suggestions and optimization plans for enterprises. Enterprises can formulate more scientific and reasonable maintenance plans according to the analysis results provided by the platform, achieving precise maintenance and on-demand maintenance. This can not only reduce unnecessary maintenance times and costs, but also improve maintenance efficiency and quality, extend the service life of the device, and bring significant economic benefits to enterprises.

[0022] 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 learned from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] 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 drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0024] Figure 1 It is a schematic diagram of an intelligent detection and monitoring cloud service platform for industrial equipment;

[0025] Figure 2 It is a flowchart of an intelligent detection and monitoring cloud service platform for industrial equipment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] 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.

[0027] Embodiment 1

[0028] This embodiment details the specific application of an intelligent detection and monitoring cloud service platform for industrial equipment in a manufacturing factory. By introducing the intelligent detection and monitoring cloud service platform for industrial equipment, the intelligent level of equipment monitoring and management efficiency are improved.

[0029] First, according to the characteristics and requirements of different equipment, appropriate sensors are selected. For example, high-precision vibration sensors are installed on the stamping machine to monitor the vibration condition of the equipment during the stamping process. The vibration sensors are installed at key parts of the stamping machine, such as near the fuselage and the punch, to ensure that the vibration signals of the equipment can be accurately captured. Temperature sensors and energy consumption sensors are installed on the injection molding machine. The temperature sensors are installed at parts such as the barrel and nozzle of the injection molding machine to monitor the molten plastic temperature in real time. The energy consumption sensors are installed at the power inlet of the injection molding machine to measure the energy consumption of the equipment. And Wi-Fi wireless transmission technology is used to send the data collected by the sensors to the cloud service platform in real time. Multiple wireless access points are set up inside the factory to ensure a wide signal coverage range and stable transmission. To ensure the security of data transmission, the AES encryption algorithm is used to encrypt the data. At the data sending end, the collected data is encrypted before being sent. At the receiving end, the encrypted data is decrypted to ensure the confidentiality of the data. At the same time, the CRC checksum is used to check the transmitted data to timely detect and correct errors during the transmission process and ensure the integrity of the data.

[0030] Second, the Hadoop distributed file system is used to disperse and store a large amount of equipment operation data on multiple server nodes. This distributed storage architecture can effectively cope with the rapid growth of data volume and avoid data loss caused by single-point failures. For example, the data of different equipment is stored on different nodes, and data partitioning is performed according to factors such as equipment type and time to improve the efficiency and scalability of data storage. The MySQL database management system is used to classify and store the data. An equipment basic information table is established to record basic information such as the model, production date, and installation location of the equipment. An operation parameter table is established to store parameters such as temperature, pressure, energy consumption, and vibration frequency during the operation of the equipment. A fault record table is established to record information such as the time, type, and handling method of equipment failures. And index technology and partitioning technology are used to improve data query efficiency. For example, indexes are established for commonly queried fields such as equipment numbers and timestamps to speed up query speed; the data is partitioned and stored according to time or equipment type to facilitate querying and analyzing the data of a specific time period or specific type of equipment. At the same time, a full backup is performed once a day to back up all equipment operation data to an external storage device or cloud storage, and an incremental backup is performed once an hour to only back up the data that has changed since the last backup. This can quickly restore to the nearest backup point in case of data loss or damage, minimizing data loss.

[0031] Next, use algorithms to mine the association rules among temperature, energy consumption, and vibration frequency. First, preprocess the collected data, including operations such as data cleaning, normalization, and feature extraction, to remove noise data and outliers and improve the data quality. Then, use algorithms to mine frequent item sets and find the frequent patterns where temperature, energy consumption, and vibration frequency appear simultaneously. For example, by analyzing the operation data of an injection molding machine, it is found that when the temperature rises to a certain level and the energy consumption also increases accordingly, the vibration frequency will show abnormal changes. Based on these frequent patterns, the association strength among temperature, energy consumption, and vibration frequency can be calculated. The formula for calculating the association strength is: where C(T, E, V) represents the probability that temperature, energy consumption, and vibration frequency appear simultaneously, P(T), P(E), and P(V) represent the probabilities that temperature, energy consumption, and vibration frequency appear separately, T, E, and V are the means of temperature, energy consumption, and vibration frequency respectively, and ω is a regulation coefficient used to balance the contributions of the two parts. And use causal inference algorithms to analyze the causal relationships among different data, providing a basis for predicting the impacts of different data change trends on equipment performance and faults. Specifically, let the data item set be D = {X1, X2, …, X n}, for any two data items X i and X j , define the causal relationship strength as R ij , where I Xi→Xj and I Xj→Xi are the causal influence coefficients of X i on X j and X j on X i respectively, C(X i , X j ) represents the probability that X i and X j appear simultaneously, P(X i ), P(X j ) represent the probabilities that X i and X j appear separately, and μ is a regulation coefficient, and combine algorithms to verify and optimize the causal relationship.

[0032] Then, adopt the 3σ principle based on statistics and the isolation forest algorithm based on machine learning to conduct anomaly detection on equipment data. For data with a normal distribution, the 3σ principle can be used for anomaly detection. When the data exceeds the range of the mean plus or minus three standard deviations, it is regarded as abnormal data. For high-dimensional data, the isolation forest algorithm can be adopted for anomaly detection. This algorithm isolates abnormal data by randomly dividing the data space, thus realizing anomaly detection. When the data combination of the temperature, energy consumption, and vibration frequency of the injection molding machine exceeds the normal range, use the anomaly score calculation formula: Among them, A represents the anomaly scores of temperature (T), energy consumption (E), and vibration frequency (V). They respectively represent the average values of temperature, energy consumption, and vibration frequency. S(T, E, V) is the correlation strength obtained from the correlation mining and causal analysis module. If the anomaly score exceeds the threshold, an alarm will be immediately issued. The alarm can be notified to the equipment maintenance personnel by means of text messages and mobile APP push. At the same time, the detailed information of the abnormal situation is recorded, including the time of the abnormal data, the equipment number, the abnormal parameters, etc., providing a basis for subsequent analysis and processing. Combining the results of correlation mining and causal analysis, the root cause of the problem can be quickly located. For example, when it is found that the temperature of the injection molding machine rises abnormally, the energy consumption increases, and the vibration frequency is abnormal, according to the results of correlation mining and causal analysis, it is determined that the problem may be caused by a failure of the temperature control system. The maintenance personnel can quickly locate the problem based on this information and take corresponding measures for processing.

[0033] Finally, based on the results of correlation mining and causal analysis, an algorithm is used to predict the future operating state of the equipment. For example, by analyzing historical data, a time series model of the temperature, energy consumption, and vibration frequency of the injection molding machine is established. According to the current data and model parameters, the values of temperature, energy consumption, and vibration frequency in the future period are predicted. If it is predicted that the temperature may rise to a dangerous range, or the energy consumption will exceed the normal level, or the vibration frequency will change abnormally, an early warning can be issued in advance to remind the maintenance personnel to conduct inspections and maintenance. The algorithm formula is as follows: Among them, F(t + Δt) represents the predicted value of the equipment state at the future time t + Δt, F(t) represents the equipment state value at the current time t, n represents the number of factors affecting the equipment state, α i represents the weight coefficient of the i-th factor, I i→F represents the causal influence coefficient of the i-th factor on the equipment state, Δt represents the time interval, ∈ represents the random error term. This formula can predict the future operating state of the equipment based on the current equipment state and the causal influence coefficients of different factors, and display the analysis and processing results in the form of intuitive charts on the large screen of the factory monitoring center and the mobile APP. For example, a line chart is used to show the historical change trends and predicted values of temperature, energy consumption, and vibration frequency; a bar chart is used to show the operating states and abnormal situations of different equipment, facilitating managers and maintenance personnel to understand the equipment operating conditions at any time and formulating an advance maintenance plan according to the prediction results. For example, if it is predicted that a certain injection molding machine may malfunction in the next few days, maintenance personnel can be arranged in advance for inspection and repair to avoid production interruption caused by equipment failure. At the same time, by analyzing the equipment operation data, the production process is optimized and the production cost is reduced. For example, according to the relationship between temperature and energy consumption, the process parameters of the injection molding machine are adjusted to reduce energy consumption and improve production efficiency.

[0034] In summary, in this embodiment, the efficiency and accuracy of equipment monitoring are improved by introducing the industrial equipment intelligent detection and monitoring cloud service platform. Through multi-sensor data acquisition and advanced data mining and analysis algorithms, the operating status of the equipment can be accurately grasped in real time, potential problems can be discovered in a timely manner, the root cause of the problems can be quickly located, and a basis for precise maintenance can be provided.

[0035] Embodiment 2

[0036] This embodiment details the specific application of an industrial equipment intelligent detection and monitoring cloud service platform in power industry equipment. By introducing the industrial equipment intelligent detection and monitoring cloud service platform, it aims to improve the intelligent level of equipment monitoring and ensure the safe and reliable operation of power generation equipment.

[0037] First, install temperature sensors, pressure sensors, energy consumption sensors, and vibration sensors on key equipment such as generator sets and transformers. For example, install highly sensitive vibration sensors at the bearing parts of the generator set to monitor the vibration of the equipment in real time so as to discover potential mechanical failures in a timely manner. Install temperature sensors on the transformer to ensure that the transformer operates within the normal temperature range and prevent overheating damage. According to the structure and operating characteristics of the equipment, reasonably determine the installation positions of the sensors to ensure that key parameters can be accurately collected. For example, for the temperature sensors of the generator set, install them at parts where temperature anomalies are likely to occur, such as windings and cooling systems. Use ZigBee wireless transmission technology to send the data collected by the sensors to the cloud service platform. ZigBee technology has characteristics such as low power consumption and self-networking, and is suitable for data transmission in the complex environment of a power plant. Set up multiple ZigBee gateways in the power plant to ensure the stability and reliability of data transmission. To ensure the security of data transmission, adopt advanced data encryption technology to encrypt the transmitted data to prevent data from being stolen or tampered with. At the same time, use check codes to verify the data to ensure the integrity of the data.

[0038] Secondly, adopt the Ceph distributed storage technology to disperse a large amount of device operation data across multiple server nodes. The Ceph distributed storage system features high reliability, high scalability, and high performance, capable of meeting the large-scale data storage requirements of power plants. For example, store data of different types of devices in different storage pools, and perform hierarchical storage based on the importance and access frequency of the data to improve storage efficiency. Use the Oracle database management system to classify and manage the data. Establish a basic device information table to record basic information such as the model, specifications, and installation time of devices like generator sets and transformers; establish an operating parameter table to store real-time parameters such as temperature, pressure, energy consumption, and vibration frequency during device operation; establish a fault record table to record information such as the time, type, and handling method of device failures. Apply indexing technology and partitioning technology to improve data query efficiency. For example, create indexes for commonly queried fields such as device numbers and timestamps to speed up querying, and partition and store the data according to factors such as device type and time to facilitate quick querying and analysis of data for a specific time period or specific type of device. Regularly perform data backups to ensure rapid recovery in case of data loss or damage. For example, perform a full backup once a week to back up all device operation data to an external storage device or cloud storage, and perform an incremental backup once a day to only back up the data that has changed since the last backup. At the same time, establish a data recovery mechanism so that when data problems occur, it can quickly recover to the most recent backup point to minimize data loss.

[0039] Next, use the FP-Growth algorithm to mine the frequent item sets among temperature, energy consumption, and vibration frequency to determine their potential associations. The FP-Growth algorithm is an efficient association rule mining algorithm that can quickly mine frequent item sets from a large amount of data. For example, by analyzing the operation data of generator sets, it is found that when the temperature rises, energy consumption increases, and there are abnormal changes in vibration frequency, it may indicate potential device failures. Further analyze the mined frequent item sets and calculate the association strength between temperature, energy consumption, and vibration frequency. The association strength calculation formula is where C(T, E, V) represents the probability of the simultaneous occurrence of temperature, energy consumption, and vibration frequency, P(T), P(E), and P(V) respectively represent the probabilities of the individual occurrences of temperature, energy consumption, and vibration frequency, T, E, and V are the mean values of temperature, energy consumption, and vibration frequency respectively, and ω is a regulation coefficient used to balance the contributions of the two parts. And use the causal inference algorithm to analyze the causal relationships between different data, providing a basis for predicting the impacts of different data change trends on device performance and failures. Specifically, let the data item set be D = {X1, X2, …, X n}, for any two data items X i and X j, define the strength of the causal relationship as R ij , where I Xi→Xj and I Xj→Xi are the causal influence coefficients of X i on X j and X j on X i respectively, C(X i , X j ) represents the probability that X i and X j occur simultaneously, P(X i ), P(X j ) represent the probabilities that X i and X j appear alone respectively, μ is a regulation coefficient, and the causal relationship is verified and optimized by combining algorithms.

[0040] Then, the One-Class SVM algorithm based on machine learning is used to detect anomalies in device data. The One-Class SVM algorithm is suitable for anomaly detection problems, especially performing well in cases where the data distribution is uneven or there are a small number of abnormal data. For the device data of a power plant, the One-Class SVM algorithm can effectively detect abnormal changes in parameters such as temperature, energy consumption, and vibration frequency. When abnormal combinations of temperature, energy consumption, and vibration frequency data of a generator set occur, use the anomaly score calculation formula When the anomaly score exceeds a certain threshold, it is determined as an abnormal data combination. Among them, A represents the anomaly scores of temperature (T), energy consumption (E), and vibration frequency (V), T, E, and V represent the average values of temperature, energy consumption, and vibration frequency respectively, S(T, E, V) is the association strength obtained from the association mining and causal analysis module. If the score exceeds the threshold, an alarm is immediately issued. The alarm can be notified to relevant personnel by means of email and mobile APP push, ensuring that they can take measures in time. Combining the results of association mining and causal analysis, quickly locate the root cause of the problem. For example, when it is found that the temperature of the generator set rises abnormally and the energy consumption increases and the vibration frequency is abnormal, according to the results of association mining and causal analysis, it is determined that the problem may be caused by a cooling system failure or mechanical component wear. Maintenance personnel can quickly locate the problem and carry out repairs based on this information, reducing the equipment downtime.

[0041] Finally, according to the results of association mining and causal analysis, an algorithm is used to predict the future operating state of the device. For example, by analyzing historical data, a time series model of the temperature, energy consumption, and vibration frequency of the injection molding machine is established. According to the current data and model parameters, the temperature, energy consumption, and vibration frequency values for a period of time in the future are predicted. If it is predicted that the temperature may rise to a dangerous range, or the energy consumption will exceed the normal level, or the vibration frequency will change abnormally, a warning can be issued in advance to remind the maintenance personnel to conduct inspections and maintenance, and the analysis and processing results are displayed in the form of intuitive charts on the large screen of the factory monitoring center and the mobile phone APP. For example, a line chart is used to display the historical change trends and predicted values of temperature, energy consumption, and vibration frequency; a bar chart is used to display the operating states and abnormal conditions of different devices, which is convenient for management personnel and maintenance personnel to understand the device operating conditions at any time. At the same time, an advance maintenance plan is formulated according to the prediction results. For example, if it is predicted that a certain injection molding machine may malfunction in the next few days, the maintenance personnel can be arranged in advance to conduct inspections and repairs to avoid production interruptions caused by equipment failures. At the same time, by analyzing the device operation data, the production process is optimized and the production cost is reduced. For example, according to the relationship between temperature and energy consumption, the process parameters of the injection molding machine are adjusted to reduce energy consumption and improve production efficiency.

[0042] In summary, in this embodiment, by introducing the industrial equipment intelligent detection and monitoring cloud service platform, the efficiency and accuracy of equipment monitoring are improved. Through multi-sensor data collection and advanced data mining and analysis algorithms, the operating state of the equipment can be accurately grasped in real time, potential problems can be discovered in time, and the root cause of the problems can be quickly located, providing a basis for precise maintenance. At the same time, combined with the results of association mining and causal analysis, the cause of equipment failure can be accurately judged, and the pertinence and effectiveness of maintenance can be improved.

[0043] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic 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, it is intended to embrace all changes falling within the meaning and scope of the equivalent elements of the claims in the present invention, and any reference signs in the claims should not be regarded as limiting the claims involved.

Claims

1. An industrial equipment intelligent detection and monitoring cloud service platform, characterized in that: The platform includes the following components: data perception and transmission module, data storage and management module, association mining and causal analysis module, anomaly detection and early warning module, and prediction and decision support module; The data sensing and transmission module uses high-precision sensors to collect various operating parameters of industrial equipment in real time, determines the sensor installation location according to the characteristics and needs of different industrial equipment, and sends the data to the cloud service platform through wireless transmission technology. At the same time, data encryption and verification technology are used to verify the transmitted data; The data storage and management module uses distributed storage technology to store a large amount of equipment operation data in multiple nodes, uses the database management system to classify, store and manage the data, and uses indexing technology and partitioning technology to improve data query efficiency. It also uses a combination of regular backup and real-time backup to ensure data security. The association mining and causal analysis module analyzes the association between temperature changes and equipment energy consumption and vibration frequency under specific working conditions, and establishes a data association model. Specifically, the collected data is preprocessed to remove noise data and outliers, and a data mining algorithm is selected for association analysis. The causal inference algorithm is used to analyze the causal relationship between different data, providing a basis for predicting the impact of different data change trends on equipment performance and failures. The anomaly detection and early warning module uses an anomaly detection algorithm to monitor data changes in real time. When an abnormal situation is detected, it notifies relevant personnel through SMS, email and mobile APP push to handle it, and records detailed information of the abnormal situation to provide a basis for subsequent analysis and processing; The prediction and decision support module uses prediction algorithms to predict the future operating status of the equipment based on the results of data association mining and causal analysis, and presents the analysis and processing results to users in the form of intuitive charts and reports.

2. According to claim 1, an industrial equipment intelligent detection and monitoring cloud service platform is characterized in that: The sensors in the data perception and transmission module include temperature sensors, pressure sensors, flow sensors, energy consumption sensors and vibration sensors. The sensor installation positions are reasonably determined according to the characteristics and needs of different industrial equipment so that key parameters can be accurately collected.

3. The industrial equipment intelligent detection and monitoring cloud service platform according to claim 1 is characterized in that: The data encryption and verification technology adopted by the data perception and transmission module includes using the AES encryption algorithm to encrypt the data and using the CRC check code to verify the transmitted data.

4. The industrial equipment intelligent detection and monitoring cloud service platform according to claim 1 is characterized in that: The data storage and management module adopts distributed storage technology, including Hadoop distributed file system and Ceph, to store a large amount of device operation data in multiple nodes, so as to effectively cope with the rapid growth of data volume and avoid data loss caused by single point failure.

5. The industrial equipment intelligent detection and monitoring cloud service platform according to claim 1 is characterized in that: The data storage and management module utilizes database management systems, including MySQL and Oracle, to classify, store and manage data, and establishes different database tables according to the type and purpose of the data. At the same time, it uses indexing technology and partitioning technology to partition and store data according to time or device type, so that it can query and analyze data in a specific time period and for a specific type of device. In addition, in order to prevent data loss, a combination of regular backup and real-time backup is used to back up data to different storage media, and a data recovery mechanism is established to quickly restore data when it is damaged or lost.

6. The industrial equipment intelligent detection and monitoring cloud service platform according to claim 1 is characterized in that: The association mining and causal analysis module preprocesses the collected data, removes noise data and outliers, and selects a data mining algorithm for association analysis. The calculation formula is: Where C(T,E,V) represents the probability of temperature, energy consumption and vibration frequency occurring simultaneously, P(T), P(E) and P(V) represent the probability of temperature, energy consumption and vibration frequency occurring separately, respectively. are the mean values ​​of temperature, energy consumption, and vibration frequency, respectively. ω is the adjustment coefficient, which is used to balance the contribution of the two parts. The causal inference algorithm is used to analyze the causal relationship between different data, providing a basis for predicting the impact of different data change trends on equipment performance and failure. Specifically, let the data item set be D = {X1, X2, …, X n }, for any two data items X i and X j , define the causal relationship strength as R ij , in and X i X j and X j X i The causal influence coefficient, C(X i ,X j ) indicates X i and X j The probability of simultaneous occurrence, P(X i )、P(X j ) represent X i and X j The probability of a single occurrence, μ is the adjustment coefficient.

7. The industrial equipment intelligent detection and monitoring cloud service platform according to claim 1 is characterized in that: The anomaly detection and early warning module uses an anomaly detection algorithm to monitor data changes in real time. When an abnormal data combination occurs, it can issue an alarm in time, quickly locate the root cause of the problem, and notify relevant personnel to handle it through SMS, email and mobile phone APP push. At the same time, it records detailed information of the abnormal situation to provide a basis for subsequent analysis and processing. In order to improve the accuracy of problem location, combined with the results of data association mining and causal analysis, the correlation between abnormal data and other data is determined, thereby judging the cause of the problem.

8. The industrial equipment intelligent detection and monitoring cloud service platform according to claim 1 is characterized in that: The anomaly detection and warning module uses the anomaly score calculation formula When the abnormal score exceeds a certain threshold, it is determined to be an abnormal data combination, where A represents the abnormal scores of temperature (T), energy consumption (E) and vibration frequency (V). They represent the average values ​​of temperature, energy consumption and vibration frequency respectively, and S(T,E,V) is the association strength obtained in the association mining and causal analysis module.

9. The industrial equipment intelligent detection and monitoring cloud service platform according to claim 1 is characterized in that ,The prediction and decision support module uses a prediction algorithm to predict the future ,operation status of the equipment based on the results of data association ,mining and causal analysis. The algorithm formula is as follows: Where F(t+Δt) represents the predicted value of the device's state at the future time t+Δt, F(t) represents the state value of the device at the current time t, n represents the number of factors that affect the device state, and α i Represents the weight coefficient of the i-th factor, I i→F represents the causal influence coefficient of the i-th factor on the equipment state, Δt represents the time interval, and ∈ represents the random error term. This formula predicts the future operating state of the equipment based on the current equipment state and the causal influence coefficients of different factors.

Images