Industrial equipment intelligent monitoring and prediction maintenance system based on Internet of Things

Abstract

The invention discloses an industrial equipment intelligent monitoring and prediction maintenance system based on the Internet of Things, relates to the technical field of industrial equipment maintenance, and mainly aims to solve the problem of poor reliability of a generated prediction result caused by conventional prediction model training in the prior art. According to the method, a mode of executing secondary training on an existing trained prediction model is adopted to improve optimization of the prediction model, so that the accuracy of a finally generated control instruction is ensured, specifically, on the basis of existing historical data, the comprehensive health performance score and the like of the industrial equipment are obtained through calculation in a data analysis mode, and the accuracy of the control instruction is improved. According to the method, the multi-dimensional information is used as an additional feature during model training, so that the learning ability of the model is improved on the premise that the multi-dimensional information required during model training is further improved, the effect of improving the model prediction precision is effectively achieved, and the precision of a generated prediction result can be effectively guaranteed; and the accuracy of the control instruction can be guaranteed.

Description

Technical Field

[0001] The present invention relates to the technical field of industrial equipment maintenance, and in particular to an industrial equipment intelligent monitoring and predictive maintenance system based on the Internet of Things. Background Art

[0002] With the development of Internet of Things technology, intelligent monitoring and predictive maintenance of industrial equipment have gradually become a key means to improve production efficiency and reduce downtime. In this context, the intelligent monitoring and predictive maintenance method based on the Internet of Things allows real-time monitoring of equipment status and analysis based on the collected data to provide early warning of possible failures, thereby achieving preventive maintenance; the following are the implementation methods of existing technologies: First, it is necessary to connect industrial equipment to the Internet of Things platform, which usually involves installing sensors and other data acquisition devices on the equipment to monitor key performance indicators in real time, such as temperature, pressure, vibration, etc., and then transmit the collected data to the cloud or local server via wireless or wired networks for storage; then use big data analysis Technology and machine learning algorithms process and analyze the collected data, building predictive models to identify potential failure modes and predict when failures may occur. Finally, control strategies are formulated based on the analysis results, and control instructions are generated according to the control strategies. Based on the generated control instructions, the system can directly trigger actions such as automatically adjusting equipment operating parameters or notifying the maintenance team to take action. This immediate response mechanism significantly improves the reliability and efficiency of the system. Although the existing technology can effectively improve the reliability of industrial equipment, reduce operating costs, and ultimately promote the transformation of the manufacturing industry to intelligent manufacturing, the following defects still exist in the actual application process:

[0003] The existing training of prediction models is relatively conventional, resulting in the problem of poor reliability of the generated prediction results. Specifically, the features selected during the training of prediction models are relatively conventional, that is, conventional features are often directly obtained without certain data analysis and processing, such as extracting key events and operation information from the historical operation log of the equipment, which includes the equipment start time, stop time, operation mode, etc., and extracting information from the historical maintenance records of the equipment, which includes the last maintenance time, maintenance type, replacement parts, etc. Although these conventional features can help identify some simple failure modes to a certain extent, they fail to cover the multi-dimensional information in the operation of industrial equipment, resulting in limited learning ability of the prediction model, which can easily lead to the prediction model being unable to accurately predict possible problems and probabilities of the equipment in the future, that is, to a certain extent, it is easy to reduce the accuracy of the prediction results, and then it is easy to cause the generated control instructions to be inaccurate, making it difficult to effectively prevent the occurrence of equipment failures.

[0004] Therefore, existing technologies urgently need technical solutions for intelligent monitoring and predictive maintenance systems for industrial equipment based on the Internet of Things. Summary of the Invention

[0005] In order to solve the above technical problems, the present invention provides an intelligent monitoring and predictive maintenance system for industrial equipment based on the Internet of Things, which specifically includes the following modules:

[0006] Data acquisition and preprocessing module: used to connect industrial equipment with the IoT platform, collect real-time and historical data of industrial equipment through the IoT platform, and perform preprocessing on the collected real-time and historical data;

[0007] Pre-training module: connected to the data acquisition and pre-processing module, used to build a prediction model and train the prediction model based on the pre-processed historical data to obtain a pre-trained prediction model;

[0008] Final training module: connected to the pre-training module, used to perform optimization processing on the pre-trained prediction model to obtain the final trained prediction model;

[0009] Health index calculation unit: used to calculate the health index of industrial equipment based on historical data of industrial equipment;

[0010] The first data acquisition subunit is used to acquire the failure frequency, maintenance times and operation time data of the industrial equipment based on historical data;

[0011] The first data mean calculation subunit is used to calculate the mean of the failure frequency, maintenance times and operation time data of the industrial equipment using a statistical analysis method to obtain the average failure frequency, average maintenance times and average operation time data of the industrial equipment;

[0012] Health index calculation subunit: used to calculate the health index of industrial equipment based on the average failure frequency, average number of repairs and average operating time data of industrial equipment;

[0013] Among them, the calculation formula for the health index of industrial equipment is:

[0014]

[0015] Where HI represents the health index of industrial equipment; Represents the average failure frequency data of industrial equipment; Data on the average number of repairs on behalf of industrial equipment; represents the average operating time data of industrial equipment; α, β, and γ represent the adjustment coefficients of the average failure frequency data, the average number of maintenance times data, and the average operating time data, respectively;

[0016] Performance index calculation unit: used to calculate the performance index of industrial equipment based on historical data of industrial equipment;

[0017] The second data acquisition subunit is used to acquire energy consumption, production efficiency and output data of industrial equipment based on historical data;

[0018] The second data mean calculation subunit is used to calculate the mean of the energy consumption, production efficiency and output data of the industrial equipment using a statistical analysis method to obtain the average energy consumption, average production efficiency and average output data of the industrial equipment;

[0019] Performance index calculation subunit: used to calculate the performance index of industrial equipment based on the average energy consumption, average production efficiency and average output data of industrial equipment;

[0020] Among them, the calculation formula for the performance index of industrial equipment is:

[0021]

[0022] Where PI represents the performance index of industrial equipment; Represents the average production efficiency data of industrial equipment; Average production data representing industrial equipment; represents the average energy consumption data of industrial equipment; δ, ε, and ∈ represent the adjustment coefficients of average production efficiency data, average output data, and average energy consumption data, respectively;

[0023] Risk index calculation unit: used to calculate the risk index of industrial equipment based on the health index and performance index of industrial equipment;

[0024] Among them, the calculation formula for the risk index of industrial equipment is:

[0025]

[0026] In the formula, RI represents the risk index of industrial equipment; HI represents the health index of industrial equipment; PI represents the performance index of industrial equipment; θ, and μ represent the adjustment coefficients of health index, performance index and the sum of health index and performance index, respectively;

[0027] First and second weight calculation units: used to obtain a first weight of the health index and a second weight of the performance index according to a ratio of the health index to the risk index, and a ratio of the performance index to the risk index, respectively;

[0028] The calculation formula group for obtaining the first weight of the health index and the second weight of the performance index is:

[0029]

[0030] Wherein, Weight1 represents the first weight of the health index; Weight2 represents the second weight of the performance index; HI represents the health index of industrial equipment; PI represents the performance index of industrial equipment; RI represents the risk index of industrial equipment;

[0031] Comprehensive health performance score calculation unit: used to calculate the comprehensive health performance score of the industrial equipment based on the health index, performance index, risk index, first weight of the health index, and second weight of the performance index of the industrial equipment;

[0032] The calculation formula for the comprehensive health performance score of industrial equipment is:

[0033]

[0034] Where CHPS represents the comprehensive health performance score of industrial equipment; HI represents the health index of industrial equipment; PI represents the performance index of industrial equipment; RI represents the risk index of industrial equipment; Weight1 represents the first weight of the health index; Weight2 represents the second weight of the performance index;

[0035] Final training unit: used to input the comprehensive health performance score, health index, performance index, risk index of the industrial equipment, as well as the first weight of the health index and the second weight of the performance index into the pre-trained prediction model to obtain the final trained prediction model;

[0036] Control instruction execution module: connected to the final training module, used to input the pre-processed real-time data into the final trained prediction model to obtain the prediction results, formulate control strategies based on the prediction results, and generate control instructions according to the control strategies, and the control instructions execute the equipment maintenance operations.

[0037] The embodiments of the present invention have the following technical effects:

[0038] The present invention mainly aims to address the problem that the existing conventional training of prediction models leads to poor reliability of the generated prediction results. The present invention adopts a method of performing secondary training on the existing trained prediction model to improve the optimization of the prediction model, thereby ensuring the accuracy of the control instructions finally generated. Specifically, the present invention calculates the comprehensive health performance score, health index, performance index, risk index of industrial equipment, as well as the first weight of the health index and the second weight of the performance index through data analysis on the basis of existing historical data, and uses them as additional features during model training, in order to seek to improve the learning ability of the model under the premise of further improving the multi-dimensional information required for model training, thereby effectively improving the model prediction accuracy, so that the accuracy of the generated prediction results can be effectively guaranteed, and thus the accuracy of the control instructions can be guaranteed. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0040] Figure 1 This is a framework diagram of an IoT-based intelligent monitoring and predictive maintenance system for industrial equipment provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0041] To make the objectives, technical solutions, and advantages of the present invention more clear, the technical solutions of the present invention are described clearly and completely below. Obviously, the embodiments described are only some of the embodiments of the present invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the present invention without inventive effort are also within the scope of protection of the present invention.

[0042] Example 1: Figure 1 As shown, the present invention provides an intelligent monitoring and predictive maintenance system for industrial equipment based on the Internet of Things, including the following modules:

[0043] Data acquisition and preprocessing module: used to connect industrial equipment with the IoT platform, collect real-time and historical data through the IoT platform, and perform preprocessing on the collected real-time and historical data;

[0044] It is worth noting that in the process of connecting industrial equipment to the Internet of Things platform, it is usually necessary to install sensors and other data acquisition devices for the industrial equipment, mainly to facilitate real-time monitoring of the key performance indicators of the industrial equipment, such as temperature, pressure, vibration, etc.; in addition, by connecting industrial equipment to the Internet of Things platform, real-time monitoring of the equipment's operating status can be achieved, which means that data on key performance indicators such as temperature, pressure, vibration, etc. can be obtained immediately. These real-time data are crucial for timely detection of equipment anomalies and help prevent small problems from turning into major failures; the real-time data collected include but are not limited to: temperature, pressure, vibration, power consumption, flow, etc.; the historical data collected include but are not limited to: maintenance records, operation logs, fault reports, energy consumption records, production efficiency records, etc.; in addition, preprocessing usually includes: data cleaning, that is, removing noise and erroneous data and filling missing values; standardization / normalization, that is, adjusting the data scale to make data from different sources comparable; time series processing, that is, sorting and segmenting time-related data for subsequent analysis.

[0045] Pre-training module: connected to the data acquisition and pre-processing module, used to build a prediction model and train the prediction model based on the pre-processed historical data to obtain a pre-trained prediction model;

[0046] It is worth noting that obtaining a pre-trained prediction model is a conventional technical means, which mainly includes the following steps: first, according to the specific needs of the problem, an appropriate machine learning or deep learning model is selected, such as regression analysis, decision tree, random forest, support vector machine, neural network, etc., and the present invention preferably selects a neural network model; then, the historical data pre-processed in step S1 is used as a training data set, and then based on domain knowledge and data analysis results, the necessary features for training the prediction model are selected, such as extracting key events and operation information from the operation log of the equipment, so the necessary features include equipment start time, stop time, operation mode, etc., and from the historical maintenance records of the equipment Information is extracted from it, so the necessary features include the last maintenance time, maintenance type, replacement parts, etc.; then the selected neural network model is trained according to the necessary features selected above and the training data set. During the training process, it is often necessary to iteratively adjust the model parameters multiple times to achieve the best prediction effect. Commonly used model training techniques include cross-validation, grid search, etc., which are not described one by one here. After continuous training, a pre-trained prediction model is obtained. It is worth further explaining that the present invention defines the existing trained prediction model as a pre-trained prediction model mainly to distinguish it from the subsequent final trained prediction model, that is, there is secondary training of the prediction model in the process.

[0047] Final training module: connected to the pre-training module, used to perform optimization processing on the pre-trained prediction model to obtain the final trained prediction model;

[0048] Health index calculation unit: used to calculate the health index of industrial equipment based on historical data of industrial equipment;

[0049] It is worth noting that by comprehensively considering the failure frequency, number of maintenance times and operating hours, the health index can more comprehensively reflect the overall health status of the equipment, rather than just a single-dimensional data. By inputting the health index into the prediction model as an additional feature, the model not only relies on conventional features, but can also learn the changing trends of the equipment health status, thereby improving the accuracy and reliability of the prediction results.

[0050] The first data acquisition subunit is used to acquire the failure frequency, maintenance times and operation time data of the industrial equipment based on historical data;

[0051] The first data mean calculation subunit is used to calculate the mean of the failure frequency, maintenance times and operation time data of the industrial equipment using a statistical analysis method to obtain the average failure frequency, average maintenance times and average operation time data of the industrial equipment;

[0052] Health index calculation subunit: used to calculate the health index of industrial equipment based on the average failure frequency, average number of repairs and average operating time data of industrial equipment;

[0053] Among them, the calculation formula for the health index of industrial equipment is:

[0054]

[0055] Where HI represents the health index of industrial equipment; Represents the average failure frequency data of industrial equipment; Data on the average number of repairs on behalf of industrial equipment; represents the average operating time data of industrial equipment; α, β, and γ represent the adjustment coefficients of the average failure frequency data, the average number of maintenance times data, and the average operating time data, respectively;

[0056] Performance index calculation unit: used to calculate the performance index of industrial equipment based on historical data of industrial equipment;

[0057] It is worth noting that by comprehensively considering energy consumption, production efficiency and output, the performance index can comprehensively evaluate the operating efficiency of the equipment, help identify the performance differences of the equipment under different working conditions, and input the performance index as an additional feature into the prediction model, which can enable the model to better understand the performance of the equipment under different working conditions and improve its generalization ability and adaptability.

[0058] The second data acquisition subunit is used to acquire energy consumption, production efficiency and output data of industrial equipment based on historical data;

[0059] The second data mean calculation subunit is used to calculate the mean of the energy consumption, production efficiency and output data of the industrial equipment using a statistical analysis method to obtain the average energy consumption, average production efficiency and average output data of the industrial equipment;

[0060] Performance index calculation subunit: used to calculate the performance index of industrial equipment based on the average energy consumption, average production efficiency and average output data of industrial equipment;

[0061] Among them, the calculation formula for the performance index of industrial equipment is:

[0062]

[0063] Where PI represents the performance index of industrial equipment; Represents the average production efficiency data of industrial equipment; Average production data representing industrial equipment; represents the average energy consumption data of industrial equipment; δ, ε, and ∈ represent the adjustment coefficients of average production efficiency data, average output data, and average energy consumption data, respectively;

[0064] Risk index calculation unit: used to calculate the risk index of industrial equipment based on the health index and performance index of industrial equipment;

[0065] Among them, the calculation formula for the risk index of industrial equipment is:

[0066]

[0067] In the formula, RI represents the risk index of industrial equipment; HI represents the health index of industrial equipment; PI represents the performance index of industrial equipment; θ, and μ represent the adjustment coefficients of health index, performance index and the sum of health index and performance index, respectively;

[0068] It is worth noting that by comprehensively considering the health index and performance index, the risk index can quantify the overall risk level of the equipment, helping managers better understand the current status of the equipment. Inputting the risk index as an additional feature into the prediction model can enable the model to better capture the overall risk change trend of the equipment and improve its robustness and stability.

[0069] First and second weight calculation units: used to obtain a first weight of the health index and a second weight of the performance index according to a ratio of the health index to the risk index, and a ratio of the performance index to the risk index, respectively;

[0070] The calculation formula group for obtaining the first weight of the health index and the second weight of the performance index is:

[0071]

[0072] Wherein, Weight1 represents the first weight of the health index; Weight2 represents the second weight of the performance index; HI represents the health index of industrial equipment; PI represents the performance index of industrial equipment; RI represents the risk index of industrial equipment;

[0073] It is worth noting that by calculating the weights of the health index and performance index, the importance of each indicator in the model can be dynamically adjusted according to the actual status of the equipment, making the model more flexible and adaptive. The introduction of weights makes the results of the model more interpretable, making it easier for managers to understand and apply the prediction results.

[0074] Comprehensive health performance score calculation unit: used to calculate the comprehensive health performance score of the industrial equipment based on the health index, performance index, risk index, first weight of the health index, and second weight of the performance index of the industrial equipment;

[0075] The calculation formula for the comprehensive health performance score of industrial equipment is:

[0076]

[0077] Where CHPS represents the comprehensive health performance score of industrial equipment; HI represents the health index of industrial equipment; PI represents the performance index of industrial equipment; RI represents the risk index of industrial equipment; Weight1 represents the first weight of the health index; Weight2 represents the second weight of the performance index;

[0078] It is worth noting that the comprehensive health performance score can comprehensively evaluate the health status, operating efficiency and overall risk level of the equipment, providing a comprehensive evaluation indicator. The comprehensive health performance score can provide a scientific basis for the formulation of equipment control strategies, helping managers decide when to perform preventive maintenance or replace parts, etc. By introducing the comprehensive health performance score, the reliability and efficiency of the system can be further improved to ensure that the equipment is always in the best operating condition.

[0079] Final training unit: used to input the comprehensive health performance score, health index, performance index, risk index of the industrial equipment, as well as the first weight of the health index and the second weight of the performance index into the pre-trained prediction model to obtain the final trained prediction model;

[0080] It is worth noting that in the process of obtaining the final trained prediction model, the comprehensive health performance score, health index, performance index, risk index of industrial equipment, as well as the first weight of the health index and the second weight of the performance index obtained through data analysis and calculation should be input as additional features into the pre-trained prediction model. The specific steps are as follows: First, the additional features are combined with the conventional features to form a new feature vector. For example, when the feature vector of the conventional feature is represented as X, the combined feature vector can be expressed as:

[0081] X new =[X, HI, PI, RI, CHPS, Weight1, Weight2];

[0082] Then, add terms related to the additional features to the model's loss function to ensure that the model can fully account for the influence of these features. For example, you can add a regularization term to the loss function:

[0083] Loss=OriginalLoss+(HI-TargetHI) 2 +(PI-TargetPI) 2 ;

[0084] Among them, Loss represents the total loss function value, that is, the total loss function value after combining the regularization term of the additional features and the original loss function value, OriginalLoss represents the standard loss function value based on conventional features, that is, the original loss function value, TargetHI and TargetPI represent the target health index and target performance index; (HI-TargetHI) 2 and (PI-TargetPI) 2 denote the regularization terms of health index and performance index respectively.

[0085] Finally, the pre-trained prediction model is retrained using the expanded feature vector. This process can adopt an incremental learning approach, that is, training can be continued based on the original pre-trained prediction model, or a new model can be trained from scratch to obtain the final trained prediction model. The training process is consistent with the training method of the existing model and will not be described in detail here.

[0086] Control instruction execution module: This module is connected to the final training module and is used to input the pre-processed real-time data into the final trained prediction model to obtain the prediction results. The control strategy is formulated based on the prediction results, and control instructions are generated according to the control strategy. The control instructions are used to execute the equipment maintenance operations.

[0087] It is worth noting that the prediction results of the finally trained prediction model will output possible problems and their probabilities that may occur in the future of the equipment. For example, a certain component has a high probability of failure in the next few days. Based on the prediction results, it is determined whether immediate action is needed. For example, if a certain device is predicted to fail, a corresponding control strategy needs to be formulated, which can include the following: 1. Preventive maintenance, that is, scheduling maintenance work orders in advance and notifying relevant personnel to conduct inspections or repairs; 2. Alarm notification, that is, sending alarm information to equipment managers or maintenance teams to remind them to pay attention to the status of specific equipment; 3. If the prediction results show that the operating parameters of certain equipment are close to critical values, it is necessary to prioritize adjusting the operating parameters of these devices to avoid equipment overload or damage;

[0088] Based on the above control strategy, control instructions are automatically generated, including: 1. Maintenance work order: Detailed description of the equipment requiring maintenance, estimated time and required materials; 2. Alarm notification: Send early warning information to relevant personnel to remind them to pay attention to the equipment status; 3. Automatic parameter adjustment: If the prediction results show that certain parameters need to be adjusted, the system will issue instructions to directly modify the equipment settings;

[0089] Finally, based on the above control instructions, the system performs equipment maintenance operations, which usually include automatic adjustment maintenance operations, that is, for some parameters that can be controlled by software, such as temperature, pressure, etc., the system can directly send instructions to adjust them; and manual intervention maintenance operations, that is, for maintenance work that requires manual operation, such as replacing parts, checking mechanical components, etc., the system will generate a maintenance work order and notify the relevant personnel. After receiving the notification, the relevant personnel will perform maintenance operations according to the instructions.

[0090] It should be noted that the terms used in the present invention are only for describing specific embodiments and are not intended to limit the scope of this application. As shown in the present specification, unless the context clearly indicates an exception, the words "one", "a", "a kind of" and / or "the" do not specifically refer to the singular and may also include the plural. The terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that the process, method or device comprising a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method or device. In the absence of further restrictions, the elements defined by the sentence "comprise a..." do not exclude the presence of other identical elements in the process, method or device comprising the elements.

[0091] It should also be noted that the terms "center", "up", "down", "left", "right", "vertical", "horizontal", "inside", "outside", etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings. They are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, they cannot be understood as limitations on the present invention. Unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", etc. should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or an indirect connection through an intermediate medium, or it can be a communication between the internal parts of two elements. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0092] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.

Claims

1. The intelligent monitoring and predictive maintenance system for industrial equipment based on the Internet of Things is characterized by: Includes the following modules: Data acquisition and preprocessing module: used to connect industrial equipment with the IoT platform, collect real-time and historical data of industrial equipment through the IoT platform, and perform preprocessing on the collected real-time and historical data; Pre-training module: connected to the data acquisition and pre-processing module, used to build a prediction model and train the prediction model based on the pre-processed historical data to obtain a pre-trained prediction model; Final training module: connected to the pre-training module, used to perform optimization processing on the pre-trained prediction model to obtain the final trained prediction model; Control instruction execution module: connected to the final training module, used to input the pre-processed real-time data into the final trained prediction model to obtain the prediction results, formulate control strategies based on the prediction results, and generate control instructions according to the control strategies, and the control instructions execute the equipment maintenance operations.

2. The IoT-based industrial equipment intelligent monitoring and predictive maintenance system according to claim 1 is characterized in that: The optimization process is performed on the pre-trained prediction model to obtain a final trained prediction model, including: Health index calculation unit: used to calculate the health index of industrial equipment based on historical data of industrial equipment; Performance index calculation unit: used to calculate the performance index of industrial equipment based on historical data of industrial equipment; Risk index calculation unit: used to calculate the risk index of industrial equipment based on the health index and performance index of industrial equipment; First and second weight calculation units: used to obtain a first weight of the health index and a second weight of the performance index according to a ratio of the health index to the risk index, and a ratio of the performance index to the risk index, respectively; Comprehensive health performance score calculation unit: used to calculate the comprehensive health performance score of the industrial equipment based on the health index, performance index, risk index, first weight of the health index, and second weight of the performance index of the industrial equipment; Final training unit: used to input the comprehensive health performance score, health index, performance index, risk index of industrial equipment, as well as the first weight of the health index and the second weight of the performance index into the pre-trained prediction model to obtain the final trained prediction model.

3. The IoT-based industrial equipment intelligent monitoring and predictive maintenance system according to claim 2 is characterized in that: The health index of the industrial equipment is calculated based on the historical data of the industrial equipment, including: The first data acquisition subunit is used to acquire the failure frequency, maintenance times and operation time data of the industrial equipment based on historical data; The first data mean calculation subunit is used to calculate the mean of the failure frequency, maintenance times and operation time data of the industrial equipment using a statistical analysis method to obtain the average failure frequency, average maintenance times and average operation time data of the industrial equipment; Health index calculation subunit: used to calculate the health index of industrial equipment based on the average failure frequency, average number of repairs and average operating time data of industrial equipment; Among them, the calculation formula for the health index of industrial equipment is: Where HI represents the health index of industrial equipment; Represents the average failure frequency data of industrial equipment; Data on the average number of repairs on behalf of industrial equipment; represents the average operating time data of industrial equipment; α, β and γ represent the adjustment coefficients of average failure frequency data, average maintenance times data and average operating time data respectively.

4. The IoT-based industrial equipment intelligent monitoring and predictive maintenance system according to claim 3 is characterized in that: The performance index of the industrial equipment is calculated based on the historical data of the industrial equipment, including: The second data acquisition subunit is used to acquire energy consumption, production efficiency and output data of industrial equipment based on historical data; The second data mean calculation subunit is used to calculate the mean of the energy consumption, production efficiency and output data of the industrial equipment using a statistical analysis method to obtain the average energy consumption, average production efficiency and average output data of the industrial equipment; Performance index calculation subunit: used to calculate the performance index of industrial equipment based on the average energy consumption, average production efficiency and average output data of industrial equipment; Among them, the calculation formula for the performance index of industrial equipment is: Where PI represents the performance index of industrial equipment; Represents the average production efficiency data of industrial equipment; Average production data representing industrial equipment; represents the average energy consumption data of industrial equipment; δ, ε and ∈ represent the adjustment coefficients of average production efficiency data, average output data and average energy consumption data respectively.

5. The IoT-based industrial equipment intelligent monitoring and predictive maintenance system according to claim 4 is characterized in that: The calculation formula of the risk index of the industrial equipment is: Where RI represents the risk index of industrial equipment; HI stands for the health index of industrial equipment; PI stands for the performance index of industrial equipment; θ、 and μ represent the adjustment coefficients of the health index, performance index, and the sum of the health index and performance index, respectively.

6. The IoT-based industrial equipment intelligent monitoring and predictive maintenance system according to claim 5, characterized in that: The calculation formula group of the first weight of the health index and the second weight of the performance index is: Wherein, Weight1 represents the first weight of the health index; Weight2 represents the second weight of the performance index; HI stands for the health index of industrial equipment; PI stands for the performance index of industrial equipment; and RI stands for the risk index of industrial equipment.

7. The IoT-based industrial equipment intelligent monitoring and predictive maintenance system according to claim 6, characterized in that: The calculation formula for the comprehensive health performance score of the industrial equipment is: Where CHPS represents the comprehensive health performance score of industrial equipment; HI represents the health index of industrial equipment; PI represents the performance index of industrial equipment; RI represents the risk index of industrial equipment; Weight1 represents the first weight of the health index; Weight2 represents the second weight of the performance index.

Images