Industrial equipment intelligent monitoring system and method based on multiple sensors

Abstract

The invention discloses an industrial equipment intelligent monitoring system and method based on multiple sensors, and relates to the technical field of data analysis, and the method specifically comprises the steps: obtaining the operation data of industrial equipment; establishing an industrial equipment operation state database; constructing an industrial equipment operation state curve model according to the operation time period of the industrial equipment; calculating a difference threshold range of the normal operation state of the industrial equipment and a difference value of the two curves in each time period, and performing real-time early warning and regulation on the industrial equipment exceeding the difference threshold range; and recording sensor operation state data of the industrial equipment in the monitoring process, and optimizing the operation state curve model of the industrial equipment. According to the method, curve analysis is carried out on real-time industrial equipment in different time stages through complete-cycle curve drawing of the mechanical equipment, real-time early warning can be carried out on abnormal conditions, manpower resources are reduced, and the real-time performance of fault processing is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data analysis, and in particular to a multi-sensor based industrial equipment intelligent monitoring system and method. Background Art

[0002] Data analysis is the core technology of modern industrial equipment monitoring and early warning systems. Their application has greatly improved the intelligent management level of equipment. Through the combination of AI and data analysis technology, in-depth insight into the operating status of industrial equipment, fault prediction, and automatic control can be achieved, thereby improving production efficiency and equipment reliability.

[0003] With the rapid development of industry, the intelligent and digital management of industrial equipment has become a key link in improving production efficiency and ensuring the safe operation of equipment. Through the Internet of Things technology and advanced sensor technology, the operating status data of industrial equipment can be collected and analyzed in real time, thereby realizing predictive maintenance, anomaly detection and automatic control; Although significant progress has been made in equipment status monitoring and fault warning technologies, there are still many challenges in practical applications. The operating data of industrial equipment is often affected by environmental conditions and equipment parameters, and the data generated by different types of equipment and process flows have high dimensionality and scale differences, which greatly increases the difficulty of data processing and analysis. In addition, the operating status of industrial equipment usually has complex nonlinear characteristics and dynamic time-varying characteristics. Traditional models have weak generalization capabilities when dealing with complex working conditions and are difficult to effectively adapt to the variability of different working conditions. Moreover, at this stage, industrial equipment generally lacks automated monitoring functions, which not only increases the workload of operators, but also may lead to potential faults that are not discovered and handled in a timely manner, thereby affecting the normal operation of the equipment. Summary of the invention

[0004] The object of the present invention is to provide an industrial equipment intelligent monitoring system and method based on multiple sensors to solve the problems raised in the prior art.

[0005] To achieve the above object, the present invention provides the following technical solution: an intelligent monitoring method for industrial equipment based on multiple sensors, the intelligent monitoring method comprising the following steps: Step S1, obtaining real-time operation status data of the equipment through sensors equipped on the surface of the industrial equipment, and obtaining historical operation status data of product manufacturing, industrial equipment operation parameters and industrial product production parameters through historical data of the industrial equipment; Step S2, establishing an industrial equipment operation status database based on the various industrial equipment data collected above, and updating the industrial equipment operation status database after each execution of step S6; Step S3, using various industrial equipment data in the industrial equipment operation status database as basic data, and constructing an industrial equipment operation status curve model according to the time period of industrial equipment operation; Step S4, generating a real-time operating status curve and a historical operating status curve through the operating status curve model according to the real-time operating status data of the industrial equipment, the operating parameters of the industrial equipment and the production parameters of the industrial products, as well as the historical industrial equipment data; Step S5, comparing and analyzing the historical operating status curve and the real-time operating status curve, calculating the difference threshold range of the normal operating status of the industrial equipment and the difference value of the two curves in each time period, judging whether the difference value exceeds the difference threshold range, and performing real-time early warning and regulation on the industrial equipment exceeding the difference threshold range; Step S6: record the sensor operating status data, equipment operating parameters, product production parameters and data analysis process of the industrial equipment during the monitoring process, input the data into the industrial equipment operating status database, and optimize the industrial equipment operating status curve model.

[0006] In step S1, a temperature sensor and an air pressure sensor are installed on the surface of the industrial equipment; the operation status data of the equipment includes the surface temperature of the industrial equipment and the atmospheric pressure on the surface of the industrial equipment; The industrial equipment operating parameters are electrical parameters of the industrial equipment including voltage, current and power and mechanical performance parameters including rotation speed and torque; The industrial product production parameters include production rate, product quality parameters and product scrap rate.

[0007] In step S2, the specific steps of establishing the industrial equipment operation status database are: Step S2-1: Mark the collected sensor data, record the full cycle T of the industrial equipment operation time, and mark the specific time j in different cycle stages i of the equipment P, marked as T i j (P), where T i j (P) represents the full cycle slice of industrial equipment P at cycle stage i and specific time j; record time slice T i j (P) corresponds to the operating parameters of industrial equipment A i j (P) and industrial product production parameters B i j (P); Step S2-2: Summarize the collected data according to the tags to generate an industrial equipment operation status database, specifically: Among them, Ti j (P) represents the full cycle slice of industrial equipment P at cycle stage i and specific time j; A i j (P) represents the corresponding time full cycle slice T i j (P) industrial equipment operating parameters; B i j (P) represents the corresponding time full cycle slice T i j (P) industrial product production parameters.

[0008] In step S3, the specific steps are as follows: Step S3-1, using various industrial equipment data in the industrial equipment operation status database as basic data, constructing an industrial equipment operation status curve model according to a time period, and constructing different operation status curve models for different industrial equipment; Step S3-2: Analyze the correlation between the operating status data of industrial equipment, the operating parameters of industrial equipment and the production parameters of industrial products, and construct the formula of the operating status curve model of industrial equipment as follows: Among them, W cont (t) represents the calculated value of the operating status of the industrial equipment; t represents the operating time point of the industrial equipment, and t is a positive integer. ; f(A(t), B(t), K(t)) is the function representation of the operating status of industrial equipment at different time points t; Indicates the error compensation value of the operating status of industrial equipment; A(t)=[a1(t),a2(t),...,a m (t)], represents the set of operating parameters of industrial equipment; B(t)=[b1(t),b2(t),...,b n (t)], represents the set of industrial product production parameters; K(t) represents the environmental parameter value of the industrial equipment at the operating time point t; in, represents a constant term; and Respectively represent the operating parameters of industrial equipment a m (t) and industrial product production parameter b n (t); g and h represent the operating parameters of industrial equipment respectively. m (t) and industrial product production parameter b n (t), m and n are counting units, , .

[0009] In step S3-2, the specific steps of calculating the regression coefficient of the industrial equipment operation status curve model are: Step S3-2-1, construct the matrix U and the operating state observation matrix W of the industrial equipment, where each column of the matrix U represents an independent variable and each row represents a sample, and the industrial equipment operating parameter set A(t)=[a1(t),a2(t),...,a m (t)] and the industrial product production parameter set B(t)=[b1(t),b2(t),...,b n (t)] to form a matrix, and add a column of all 1s to the left of the matrix as the first column of the matrix U. The first column represents the regression coefficient constant term. ; The operating status observation value matrix W of the industrial equipment is obtained from the operating status database of the industrial equipment; Step S3-2-2, calculate U T U and U T W; among them, U T U represents the covariance matrix between independent variables, which is a (n+m+1)*(n+m+1) matrix; U T W represents the covariance matrix between each independent variable and the dependent variable, U T W is a (n+m+1)*1 matrix; Step S3-2-3, calculate the regression coefficient set V, V=(U T U) -1 U T W, where V = [ , ,..., , ,..., ], represents the set of regression coefficients; (U T U) -1 Denotes the matrix U T The inverse matrix of U.

[0010] In step S3-2, the error compensation value calculation formula is: in, Indicates the error value of industrial equipment at different operating time points; Indicates the error compensation value of the operating status of industrial equipment; W cont W(t) represents the calculated value of the operating status of the industrial equipment; t represents the operating time point of the industrial equipment, and t is a positive integer; W(t) represents the observed value of the operating status of the industrial equipment, which is obtained from the operating status database of the industrial equipment.

[0011] In step S4, the real-time operation status data, the industrial equipment operation parameters, the industrial product production parameters and the historical data obtained from the operation status database of the industrial equipment are used to generate the state curve W about t through the industrial equipment operation status curve model constructed above. cont (t)_d and W cont (t)_s, where W cont (t)_d is the real-time operating status curve of industrial equipment at different time points; W cont (t)_s is the historical operating status curve of industrial equipment at different time points.

[0012] In step S5, the calculation of the difference threshold range of the normal operation status of the industrial equipment and the difference value of the two curves in each time period, judging whether the difference value exceeds the difference threshold range, and performing real-time early warning and regulation on the industrial equipment exceeding the difference threshold range specifically includes the following steps: Step S5-1: The real-time running status curve W generated above is cont (t)_d and historical operating status curve W cont (t)_s is placed at the same time coordinate and the discrete points of the curve are drawn; Step S5-2: Analyze the drawn curve and calculate the real-time running status curve W within the same time period. cont (t)_d and historical operating status curve W cont The difference value of (t)_s is: Wherein, ch_d(t) represents the slope of the real-time operation status curve at time point t; ch_s(t) represents the slope of the historical operation status curve at time point t; ch(t) represents the real-time operation status curve W cont (t)_d and historical operating status curve W cont (t)_s is the difference value at time point t; Step S5-3: Real-time operation status curve W cont (t)_d is judged by the difference value at time point t. When the difference value at time point t meets the difference threshold range When , the current device is judged to be operating normally and no warning is issued; if the difference value at time point t does not meet the difference threshold range, the system issues a real-time warning; Step S5-4: After receiving the system warning, intelligent regulation is performed to change the real-time operation status curve W cont(t)_d is modified by modifying the operating status data and industrial equipment operating parameters at time point t to become the historical operating status curve W cont (t)_sThe operating status data and operating parameters of industrial equipment at time point t are continuously monitored.

[0013] An industrial equipment intelligent monitoring system based on multiple sensors, the industrial equipment intelligent monitoring system comprising a data acquisition module, a database management module, an operation status modeling module, a status curve generation module, a difference analysis and early warning module and a model optimization module; The data acquisition module is used to collect and summarize real-time data and historical data of industrial equipment; supports multiple types of sensors and data interface protocols, and monitors the status of data transmission in real time; The database management module is used to provide data storage, retrieval, update and deletion operations; supports data classification and labeling management to facilitate subsequent data analysis and model building; The operation status modeling module is used to construct a curve model reflecting the normal operation status of industrial equipment by combining historical data with machine learning algorithms and statistical methods; The state curve generation module is used to call the operation state curve model in real time, and generate the current equipment operation state curve in combination with real-time data; it supports multi-dimensional data input and curve generation to meet the state monitoring requirements of different equipment; The difference analysis and early warning module is used to analyze the difference between the two curves according to the calculated difference threshold range; when the difference exceeds the threshold, the alarm system is triggered and the equipment is regulated by the intelligent algorithm; The model optimization module is used to continuously record the data and analysis results generated during the operation of the equipment to support subsequent model optimization; it provides data visualization functions to help operators understand the operating status and historical change trends of the equipment.

[0014] Compared with the prior art, the beneficial effects of the present invention are: the present invention establishes a complete historical industrial equipment database, records the environmental data and equipment mechanical data of different equipment during normal operation in real time, draws curves of the entire cycle of mechanical equipment, performs curve analysis on real-time industrial equipment in time stages, calculates the slope of the curve in each stage and compares it with the history, can provide real-time warning for abnormal situations, and then automatically regulate and control, reducing human resources and improving the real-time performance of fault handling. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of the steps of a multi-sensor-based intelligent monitoring method for industrial equipment according to the present invention; Figure 2The present invention provides an industrial equipment operating status curve diagram of an industrial equipment intelligent monitoring system and method based on multiple sensors. DETAILED DESCRIPTION

[0016] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0017] Example: Figure 1-Figure 2 As shown, the present invention provides a technical solution, a multi-sensor based intelligent monitoring method for industrial equipment; industrial pump equipment is used to transport liquids on the production line to maintain system pressure; the equipment operation status is affected by the operating parameters such as temperature (T), pressure (P), flow (F) inside the equipment, and production parameters such as product quality (Q) on the production line. It is necessary to monitor these parameters in real time and compare them with the historical operation status to determine whether the equipment is operating normally and whether early warning and regulation are required.

[0018] like Figure 1 As shown, the intelligent monitoring method includes the following steps: Step S1, obtaining real-time operation status data of the equipment through sensors equipped on the surface of the industrial equipment, and obtaining historical operation status data of product manufacturing, industrial equipment operation parameters and industrial product production parameters through historical data of the industrial equipment; In step S1, a temperature sensor and an air pressure sensor are installed on the surface of the industrial equipment; the operation status data of the equipment includes the surface temperature of the industrial equipment and the atmospheric pressure on the surface of the industrial equipment; The industrial equipment operating parameters are electrical parameters of the industrial equipment including voltage, current and power and mechanical performance parameters including rotation speed and torque; The industrial product production parameters include production rate, product quality parameters and product scrap rate. The sensors on the industrial pump equipment collect the equipment's operating status data in real time, including: Equipment internal temperature T(t), equipment internal pressure P(t), flow rate F(t) and product quality Q(t) on the production line; Temperature T(t) (℃): [70,72,71,69,73]; Pressure P(t): [100,105,103,99,107]; Flow rate F(t) (L / min): [50,52,51,49,53]; Product quality Q(t)(g / min): [200,205,203,199,207]; These data will be continuously stored in the industrial equipment operation status database. At the same time, the operation status data of the corresponding time period is obtained from the historical data for model training and comparative analysis.

[0019] Step S2, establishing an industrial equipment operation status database based on the various industrial equipment data collected above, and updating the industrial equipment operation status database after each execution of step S6; In step S2, the specific steps of establishing the industrial equipment operation status database are: Step S2-1: Mark the collected sensor data, record the full cycle T of the industrial equipment operation time, and mark the specific time j in different cycle stages i of the equipment P, marked as T i j (P), where T i j (P) represents the full cycle slice of industrial equipment P at cycle stage i and specific time j; record time slice T i j (P) corresponds to the operating parameters of industrial equipment A i j (P) and industrial product production parameters B i j (P); Step S2-2: Summarize the collected data according to the tags to generate an industrial equipment operation status database, specifically: Among them, T i j (P) represents the full cycle slice of industrial equipment P at cycle stage i and specific time j; A i j (P) represents the corresponding time full cycle slice T i j (P) industrial equipment operating parameters; B i j (P) represents the corresponding time full cycle slice T i j (P) industrial product production parameters.

[0020] Step S3, using various industrial equipment data in the industrial equipment operation status database as basic data, and constructing an industrial equipment operation status curve model according to the time period of industrial equipment operation; In step S3, the specific steps are as follows: Step S3-1, using various industrial equipment data in the industrial equipment operation status database as basic data, constructing an industrial equipment operation status curve model according to a time period, and constructing different operation status curve models for different industrial equipment; Step S3-2: Analyze the correlation between the operating status data of industrial equipment, the operating parameters of industrial equipment and the production parameters of industrial products, and construct the formula of the operating status curve model of industrial equipment as follows: Among them, W cont (t) represents the calculated value of the operating status of the industrial equipment; t represents the operating time point of the industrial equipment, and t is a positive integer. ; f(A(t), B(t), K(t)) is the function representation of the operating status of industrial equipment at different time points t; Indicates the error compensation value of the operating status of industrial equipment; A(t)=[a1(t),a2(t),...,a m (t)], represents the set of operating parameters of industrial equipment; B(t)=[b1(t),b2(t),...,b n (t)], represents the set of industrial product production parameters; K(t) represents the environmental parameter value of the industrial equipment at the operating time point t; in, represents a constant term; and Respectively represent the operating parameters of industrial equipment a m (t) and industrial product production parameter b n (t); g and h represent the operating parameters of industrial equipment respectively. m (t) and industrial product production parameter b n (t), m and n are counting units, , .

[0021] Step S3-2-1, construct the matrix U and the operating state observation matrix W of the industrial equipment, where each column of the matrix U represents an independent variable and each row represents a sample, and the industrial equipment operating parameter set A(t)=[a1(t),a2(t),...,a m (t)] and the industrial product production parameter set B(t)=[b1(t),b2(t),...,b n (t)] to form a matrix, and add a column of all 1s to the left of the matrix as the first column of the matrix U. The first column represents the regression coefficient constant term. ; The operating status observation value matrix W of the industrial equipment is obtained from the operating status database of the industrial equipment; Step S3-2-2, calculate U T U and U T W; among them, U T U represents the covariance matrix between independent variables, which is a (n+m+1)*(n+m+1) matrix; U T W represents the covariance matrix between each independent variable and the dependent variable, U T W is a (n+m+1)*1 matrix; Step S3-2-3, calculate the regression coefficient set V, V=(U T U) -1 U T W, where V = [ , ,..., , ,..., ], represents the set of regression coefficients; (U T U) -1 Denotes the matrix U T The inverse matrix of U.

[0022] In step S3-2, the error compensation value calculation formula is: in, Indicates the error value of industrial equipment at different operating time points; Indicates the error compensation value of the operating status of industrial equipment; W cont (t) represents the calculated value of the operating status of the industrial equipment, which is calculated by step S3-2; t represents the operating time point of the industrial equipment, and t is a positive integer; W(t) represents the observed value of the operating status of the industrial equipment, which is obtained from the operating status database of the industrial equipment.

[0023] Step S4, generating a real-time operating status curve and a historical operating status curve through the operating status curve model according to the real-time operating status data of the industrial equipment, the operating parameters of the industrial equipment and the production parameters of the industrial products, as well as the historical industrial equipment data; In step S4, the real-time operation status data, the industrial equipment operation parameters, the industrial product production parameters and the historical data obtained from the operation status database of the industrial equipment are used to generate the state curve W about t through the industrial equipment operation status curve model constructed above. cont (t)_d and W cont (t)_s, where W cont (t)_d is the real-time operating status curve of industrial equipment at different time points; W cont (t)_s is the historical operating status curve of industrial equipment at different time points.

[0024] Step S5, comparing and analyzing the historical operating status curve and the real-time operating status curve, calculating the difference threshold range of the normal operating status of the industrial equipment and the difference value of the two curves in each time period, judging whether the difference value exceeds the difference threshold range, and performing real-time early warning and regulation on the industrial equipment exceeding the difference threshold range; like Figure 2 As shown, step S5-1, the real-time running status curve W generated above is cont (t)_d and historical operating status curve W cont (t)_s is placed at the same time coordinate and the discrete points of the curve are drawn; Step S5-2: Analyze the drawn curve and calculate the real-time running status curve W within the same time period. cont (t)_d and historical operating status curve W cont The difference value of (t)_s is: Wherein, ch_d(t) represents the slope of the real-time operation status curve at time point t; ch_s(t) represents the slope of the historical operation status curve at time point t; ch(t) represents the real-time operation status curve W cont (t)_d and historical operating status curve W cont (t)_s is the difference value at time point t; Step S5-3: Real-time operation status curve W cont (t)_d is judged by the difference value at time point t. When the difference value at time point t meets the difference threshold range When , the current device is judged to be operating normally and no warning is issued; if the difference value at time point t does not meet the difference threshold range, the system issues a real-time warning; Step S5-4: After receiving the system warning, intelligent regulation is performed to change the real-time operation status curve Wcont (t)_d is modified by modifying the operating status data and industrial equipment operating parameters at time point t to become the historical operating status curve W cont (t)_sThe operating status data and operating parameters of industrial equipment at time point t are continuously monitored.

[0025] Step S6: record the sensor operating status data, equipment operating parameters, product production parameters and data analysis process of the industrial equipment during the monitoring process, input the data into the industrial equipment operating status database, and optimize the industrial equipment operating status curve model.

[0026] An industrial equipment intelligent monitoring system based on multiple sensors, the industrial equipment intelligent monitoring system comprising a data acquisition module, a database management module, an operation status modeling module, a status curve generation module, a difference analysis and early warning module and a model optimization module; The data acquisition module is used to collect and summarize the real-time data and historical data of industrial equipment; it supports various types of sensors and data interface protocols, and monitors the status of data transmission in real time; the database management module is used to provide data storage, retrieval, update and deletion operations; it supports data classification and labeling management to facilitate subsequent data analysis and model building; the operation status modeling module is used to build a curve model reflecting the normal operation status of industrial equipment through historical data, combined with machine learning algorithms and statistical methods; the status curve generation module is used to call the operation status curve model in real time, and generate the current equipment operation status curve in combination with real-time data; it supports multi-dimensional data input and curve generation to meet the status monitoring needs of different equipment; the difference analysis and early warning module is used to analyze the difference between two curves according to the calculated difference threshold range; when the difference exceeds the threshold, the alarm system is triggered, and the equipment is regulated by intelligent algorithms; The model optimization module is used to continuously record the data and analysis results generated during the operation of the equipment to support subsequent model optimization; it provides data visualization functions to help operators understand the operating status and historical change trends of the equipment.

[0027] It will be apparent to those skilled in the art that the invention is not limited to the details of the exemplary embodiments described above and that the invention can be implemented in other specific forms without departing from the spirit or essential features of the invention. Therefore, the embodiments should be considered exemplary and non-limiting in all respects, and the scope of the invention is defined by the appended claims rather than the foregoing description, and it is intended that all variations falling within the meaning and scope of the equivalent elements of the claims be included in the invention. Any reference numeral in a claim should not be considered as limiting the claim to which it relates.

Claims

1. A multi-sensor based intelligent monitoring method for industrial equipment, characterized in that: The intelligent monitoring method comprises the following steps: Step S1, obtaining real-time operation status data of the equipment through sensors equipped on the surface of the industrial equipment, and obtaining historical operation status data of product manufacturing, industrial equipment operation parameters and industrial product production parameters through historical data of the industrial equipment; Step S2, establishing an industrial equipment operation status database based on the various industrial equipment data collected above, and updating the industrial equipment operation status database after each execution of step S6; Step S3, using various industrial equipment data in the industrial equipment operation status database as basic data, and constructing an industrial equipment operation status curve model according to the time period of industrial equipment operation; Step S4, generating a real-time operating status curve and a historical operating status curve through the operating status curve model according to the real-time operating status data of the industrial equipment, the operating parameters of the industrial equipment and the production parameters of the industrial products, as well as the historical industrial equipment data; Step S5, comparing and analyzing the historical operating status curve and the real-time operating status curve, calculating the difference threshold range of the normal operating status of the industrial equipment and the difference value of the two curves in each time period, judging whether the difference value exceeds the difference threshold range, and performing real-time early warning and regulation on the industrial equipment exceeding the difference threshold range; Step S6, recording the sensor operating status data, equipment operating parameters, product production parameters and data analysis process of the industrial equipment during the monitoring process, inputting the data into the industrial equipment operating status database, and optimizing the industrial equipment operating status curve model.

2. The multi-sensor based intelligent monitoring method for industrial equipment according to claim 1, characterized in that: In step S1, a temperature sensor and an air pressure sensor are installed on the surface of the industrial equipment; the operation status data of the equipment includes the surface temperature of the industrial equipment and the atmospheric pressure on the surface of the industrial equipment; The industrial equipment operating parameters are electrical parameters of the industrial equipment including voltage, current and power and mechanical performance parameters including rotation speed and torque; The industrial product production parameters include production rate, product quality parameters and product scrap rate.

3. The multi-sensor based intelligent monitoring method for industrial equipment according to claim 2, characterized in that: In step S2, the specific steps of establishing the industrial equipment operation status database are: Step S2-1: Mark the collected sensor data, record the full cycle T of the industrial equipment operation time, and mark the specific time j in different cycle stages i of the industrial equipment P, marked as T i j (P), where T i j (P) represents the full cycle slice of industrial equipment P at cycle stage i and specific time j; record time slice T i j (P) corresponds to the operating parameters of industrial equipment A i j (P) and industrial product production parameters B i j (P); Step S2-2: Summarize the collected data according to the tags to generate an industrial equipment operation status database, specifically: Among them, T i j (P) represents the full cycle slice of industrial equipment P at cycle stage i and specific time j; A i j (P) represents the corresponding time full cycle slice T i j (P) industrial equipment operating parameters; B i j (P) represents the corresponding time full cycle slice T i j (P) industrial product production parameters.

4. The multi-sensor based intelligent monitoring method for industrial equipment according to claim 3, characterized in that: In step S3, the specific steps of constructing the industrial equipment operation status curve model according to the time period of industrial equipment operation are: Step S3-1, using various industrial equipment data in the industrial equipment operation status database as basic data, constructing an industrial equipment operation status curve model according to a time period, and constructing different operation status curve models for different industrial equipment; Step S3-2: Analyze the correlation between the operating status data of industrial equipment, the operating parameters of industrial equipment and the production parameters of industrial products, and construct the formula of the operating status curve model of industrial equipment as follows: Among them, W cont (t) represents the calculated value of the operating status of the industrial equipment; t represents the operating time point of the industrial equipment, and t is a positive integer. ; f(A(t), B(t), K(t)) is the function representation of the operating status of industrial equipment at different time points t; Indicates the error compensation value of the operating status of industrial equipment; A(t)=[a1(t),a2(t),...,a m (t)], represents the set of operating parameters of industrial equipment; B(t)=[b1(t),b2(t),...,b n (t)], represents the set of industrial product production parameters; K(t) represents the environmental parameter value of the industrial equipment at the operating time point t; in, represents a constant term; and Respectively represent the operating parameters of industrial equipment a m (t) and industrial product production parameter b n (t); g and h represent the operating parameters of industrial equipment respectively. m (t) and industrial product production parameter b n (t), m and n are counting units, , .

5. The multi-sensor based intelligent monitoring method for industrial equipment according to claim 4, characterized in that: In step S3-2, the specific steps of calculating the regression coefficient of the industrial equipment operation status curve model are: Step S3-2-1, construct the matrix U and the operating state observation value matrix W of the industrial equipment, where each column of the matrix U represents an independent variable and each row represents a sample, and the industrial equipment operating parameter set A(t)=[a1(t),a2(t),...,a m (t)] and the industrial product production parameter set B(t)=[b1(t),b2(t),...,b n (t)] to form a matrix, and add a column of all 1s to the left of the matrix as the first column of the matrix U. The first column represents the regression coefficient constant term. ; The operating status observation value matrix W of the industrial equipment is obtained from the operating status database of the industrial equipment; Step S3-2-2, calculate U T U and U T W; among them, U T U represents the covariance matrix between independent variables, which is a (n+m+1)*(n+m+1) matrix; U T W represents the covariance matrix between each independent variable and the dependent variable, U T W is a (n+m+1)*1 matrix; Step S3-2-3, calculate the regression coefficient set V, V=(U T U) -1 U T W, where V = [ , ,..., , ,..., ], represents the set of regression coefficients; (U T U) -1 Denotes the matrix U T The inverse matrix of U.

6. The multi-sensor based intelligent monitoring method for industrial equipment according to claim 5, characterized in that: In step S3-2, the error compensation value calculation formula is: in, Indicates the error value of industrial equipment at different operating time points; Indicates the error compensation value of the operating status of industrial equipment; W cont (t) represents the calculated value of the operating status of the industrial equipment; t represents the operating time point of the industrial equipment, and t is a positive integer; W(t) represents the observed value of the operating status of the industrial equipment, which is obtained from the operating status database of the industrial equipment.

7. The multi-sensor based intelligent monitoring method for industrial equipment according to claim 6, characterized in that: In step S4, the real-time operation status data, the industrial equipment operation parameters, the industrial product production parameters and the historical data obtained from the operation status database of the industrial equipment are used to generate the state curve W about t through the industrial equipment operation status curve model constructed above. cont (t)_d and W cont (t)_s, where W cont (t)_d is the real-time operating status curve of industrial equipment at different time points; W cont (t)_s is the historical operating status curve of industrial equipment at different time points.

8. The multi-sensor based intelligent monitoring method for industrial equipment according to claim 7, characterized in that: In step S5, the calculation of the difference threshold range of the normal operation status of the industrial equipment and the difference value of the two curves in each time period, judging whether the difference value exceeds the difference threshold range, and performing real-time early warning and regulation on the industrial equipment exceeding the difference threshold range specifically includes the following steps: Step S5-1: The real-time running status curve W generated above is cont (t)_d and historical operating status curve W cont (t)_s is placed at the same time coordinate and the discrete points of the curve are drawn; Step S5-2: Analyze the drawn curve and calculate the real-time running status curve W within the same time period. cont (t)_d and historical operating status curve W cont The difference value of (t)_s is: Wherein, ch_d(t) represents the slope of the real-time operation status curve at time point t; ch_s(t) represents the slope of the historical operation status curve at time point t; ch(t) represents the real-time operation status curve W cont (t)_d and historical operating status curve W cont (t)_s is the difference value at time point t; Step S5-3: Real-time operation status curve W cont (t)_d is judged by the difference value at time point t. When the difference value at time point t meets the difference threshold range When , the current device is judged to be operating normally and no warning is issued; if the difference value at time point t does not meet the difference threshold range, the system issues a real-time warning; Step S5-4: After receiving the system warning, intelligent regulation is performed to change the real-time operation status curve W cont (t)_d is modified by modifying the operating status data and industrial equipment operating parameters at time point t to become the historical operating status curve W cont (t)_sThe operating status data and operating parameters of industrial equipment at time point t are continuously monitored.

9. An intelligent monitoring system for industrial equipment based on multiple sensors, characterized in that: The industrial equipment intelligent monitoring system includes a data acquisition module, a database management module, an operation status modeling module, a status curve generation module, a difference analysis and early warning module and a model optimization module; The data acquisition module is used to collect and summarize real-time data and historical data of industrial equipment; supports multiple types of sensors and data interface protocols, and monitors the status of data transmission in real time; The database management module is used to provide data storage, retrieval, update and deletion operations; supports data classification and labeling management to facilitate subsequent data analysis and model building; The operation status modeling module is used to construct a curve model reflecting the normal operation status of industrial equipment by combining historical data with machine learning algorithms and statistical methods; The state curve generation module is used to call the operation state curve model in real time, and generate the current equipment operation state curve in combination with real-time data; it supports multi-dimensional data input and curve generation to meet the state monitoring requirements of different equipment; The difference analysis and early warning module is used to analyze the difference between the two curves according to the calculated difference threshold range; When the difference exceeds the threshold, the alarm system is triggered and the equipment is regulated through intelligent algorithms; The model optimization module is used to continuously record the data and analysis results generated during the operation of the equipment to support subsequent model optimization; it provides data visualization functions to help operators understand the operating status and historical change trends of the equipment.

Images