Control management system of mechanical electrical equipment

Abstract

The invention relates to the technical field of mechanical electrical equipment, in particular to a control management system of mechanical electrical equipment, which comprises a data acquisition module, a data processing module, an intelligent prediction and optimization module, a control and communication module and an early warning and maintenance management module, the data acquisition module acquires operation parameters of the mechanical electrical equipment; the data processing module analyzes and processes the operation parameters; the intelligent prediction and optimization module analyzes feature information and abnormal features in real time; the control and communication module controls the mechanical and electrical equipment in real time based on the collected operation parameters; and the early warning and maintenance management module sends out an early warning signal when an abnormality is detected, notifies a user to check and maintain, and manages the maintenance information and plan of the mechanical and electrical equipment. According to the invention, the operation efficiency and reliability of the equipment are improved, and the downtime and maintenance cost of the equipment are reduced.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mechanical and electrical equipment, and particularly relates to a control and management system of mechanical and electrical equipment. BACKGROUND

[0002] At present, mechanical and electrical equipment plays a vital role in industrial production and is widely used in manufacturing, energy, transportation and other fields. The efficient operation and reliable maintenance of these devices are directly related to production efficiency and safety. However, with the increasing complexity of equipment, traditional manual monitoring and maintenance methods have been difficult to meet the needs of modern industry. Modern industry requires more intelligent and automated management systems to realize real-time monitoring, fault prediction, performance optimization and maintenance management of equipment.

[0003] In the prior art, the monitoring system of mechanical and electrical equipment usually adopts simple processing of single sensor data and fixed period maintenance strategy, and lacks intelligent and comprehensive management ability. These systems have many deficiencies in data acquisition, processing and analysis, and are difficult to detect abnormal conditions and potential faults in equipment operation in real time. In addition, the existing optimization control method is relatively single and does not fully consider the multi-objective optimization requirements of equipment operation, resulting in that the performance of equipment cannot be fully utilized, and the maintenance management lacks systematicness and foresight, and can only be handled passively after the fault occurs, increasing downtime and maintenance cost.

[0004] The present application aims to provide a control and management system of mechanical and electrical equipment, which can collect and analyze equipment operation data in real time, detect and handle abnormal conditions in time, optimize equipment operation parameters, significantly improve equipment operation efficiency and reliability, and effectively prolong equipment life, reduce downtime and maintenance cost through systematic maintenance management, and meet the efficiency and intelligent requirements of modern industry for equipment management. SUMMARY

[0005] Based on the above purpose, the present application provides a control and management system of mechanical and electrical equipment.

[0006] A control and management system of mechanical and electrical equipment, comprising a data acquisition module, a data processing module, an intelligent prediction and optimization module, a control and communication module, and a warning and maintenance management module, wherein;

[0007] The data acquisition module acquires the operation parameters of the mechanical and electrical equipment, including temperature, pressure, vibration and energy consumption;

[0008] The data processing module analyzes and processes the operation parameters, extracts feature information and abnormal features;

[0009] The intelligent prediction and optimization module analyzes feature information and abnormal features in real time, predicts equipment failure and performance changes, and optimizes equipment operating parameters, specifically including:

[0010] Adaptive prediction model: Construct a prediction model and continuously update and optimize the prediction model using sliding window technology. The prediction model analyzes feature information and abnormal features to predict mechanical and electrical equipment failures and performance changes, and generates corresponding prediction results.

[0011] Multi-objective optimization: Define multiple optimization objectives, use a multi-objective optimization algorithm based on the Pareto frontier to find the best balance point between multiple performance indicators, and generate an optimization scheme.

[0012] Real-time optimization and feedback: Adjust the operating parameters of mechanical and electrical equipment in real time based on the results of the multi-objective optimization algorithm, and continuously monitor the optimization effect.

[0013] The control and communication module controls mechanical and electrical equipment in real time based on collected operating parameters, and realizes data transmission and communication with external units.

[0014] The early warning and maintenance management module issues a warning signal when an anomaly is detected, notifies the user to check and maintain, and manages the maintenance information and plan of mechanical and electrical equipment, including maintenance records, maintenance plan formulation and execution.

[0015] Further, the data acquisition module includes:

[0016] Temperature monitoring: Install temperature sensors on mechanical and electrical equipment to monitor temperature changes in real time.

[0017] Pressure measurement: Install pressure sensors in the hydraulic or pneumatic system of mechanical and electrical equipment to measure pressure values in real time.

[0018] Vibration monitoring: Install vibration sensors on rotating parts or machine bodies of mechanical and electrical equipment to monitor vibration conditions in real time.

[0019] Energy consumption monitoring: Install energy consumption sensors in the power supply system of mechanical and electrical equipment to monitor energy consumption, including voltage, current and power.

[0020] Further, the data processing module includes:

[0021] Data cleaning: Remove noise and outliers in operating parameters and use a moving average filter to smooth operating parameters.

[0022] Feature extraction: Extract feature information from operating parameters, convert time-domain signals to frequency domain using Fourier transform (FFT), analyze frequency components in the spectrum to extract characteristics of device vibration and energy consumption;

[0023] Anomaly detection: Use support vector machine (SVM) to classify and cluster extracted features, identify and label abnormal features;

[0024] Data fusion: Use Kalman filter to fuse operating parameters and analyze the correlation between different operating parameters.

[0025] Further, the adaptive prediction model includes:

[0026] Prediction model construction: Based on historical operating parameters and feature information, use deep belief network (DBN) model for modeling;

[0027] Sliding window technology: During the operation of mechanical and electrical equipment, use sliding window technology to segment real-time operating parameters, the size of the sliding window is W, move one step S each time, get the latest operating parameter segment, the calculation formula is

[0028] X t ={x t ,x t+1 ,...,x t+W-1};

[0029] Where X t is the data in the current sliding window;

[0030] Model update and optimization: Use the data in the sliding window to continuously update and optimize the prediction model, adjust the weights of the prediction model through stochastic gradient descent (SGD) with adaptive learning rate, the calculation formula is:

[0031]

[0032] Where η0 is the initial learning rate, β1 and β2 are hyperparameters;

[0033] Prediction and result generation: The prediction model analyzes the extracted feature information and abnormal features in the sliding window to predict the failure and performance change of the mechanical and electrical equipment, outputs the prediction result, and generates the corresponding prediction report, including fault type, occurrence probability and recommended maintenance measures.

[0034] Further, the deep belief network (DBN) model includes:

[0035] Standardized data: Standardize the operating data so that the operating parameters have zero mean and unit variance, the calculation formula is:

[0036]

[0037] where x i is the original data, μ is the mean, and σ is the standard deviation;

[0038] Time series segmentation: segment the time series data with length T to capture the temporal dependence, the formula is:

[0039] X t = [x t , x t+1 ,..., x t+Y-1 ];

[0040] Multimodal data fusion: connect the operating parameters into a fusion vector, the formula is:

[0041] X fused = [X temp , X pressure , X vibration , X energy ];

[0042] where X temp , X pressure , X vibration , X energy are temperature, pressure, vibration and energy consumption data, respectively;

[0043] RBM energy function: the RBM energy function after introducing the time dependence and multimodal features, the formula is:

[0044] E(v, h) = -∑ i a i v i -∑ j b j h j -∑ i,j v i W ij h j -∑ t c t X t ;

[0045] where c t is the weight of time dependence;

[0046] Activation probability: calculate the activation probability considering time dependence, the formula is:

[0047] P(h j = 1 | v, X t ) = σ(b j +∑ i v i Wij +∑ t c t X t );

[0048] P(v i =1|h)=σ(a i +Σ j h j W ij );

[0049] Layer-by-layer training: The deep belief network model is trained layer by layer using RBM, learning the weights of each layer. The calculation formula is as follows:

[0050] h l =σ(W l ·h l-1 +b l );

[0051] Among them, h l W is the hidden unit of the l-th layer. l and b l The weights and biases of the l-th layer;

[0052] Fine-tuning: The entire network is fine-tuned using the backpropagation algorithm. The calculation formula is as follows:

[0053]

[0054] in, Let y be the loss function. i For the true value, This is a predicted value;

[0055] Predicted output: Predictions are made using a pre-trained deep belief network model, calculated using the following formula:

[0056]

[0057] Among them, W out and b out h represents the weights and biases of the output layer. L This is a hidden unit in the last layer;

[0058] Anomaly detection: Anomaly detection is performed based on the difference between the predicted results and the actual data. The calculation formula is as follows:

[0059]

[0060] Where δ is the set threshold.

[0061] Furthermore, the multi-objective optimization includes:

[0062] Define optimization objectives: Define multiple optimization objectives, including minimizing energy consumption, maximizing production efficiency, and prolonging equipment life;

[0063] The minimization of energy consumption is achieved by optimizing the operating parameters of mechanical and electrical equipment, reducing the consumption of electricity and energy, and the objective function is:

[0064]

[0065] Where E is the total energy consumption, P(t) is the power consumption at time t, and Δt is the time interval;

[0066] The maximization of production efficiency is achieved by optimizing the operating speed and workload of mechanical and electrical equipment, improving production output, and the objective function is:

[0067]

[0068] Where η is the production efficiency, Q output is the output, and Q input is the input;

[0069] The prolongation of equipment life is achieved by optimizing the operating conditions of mechanical and electrical equipment, reducing equipment wear and failure, and the objective function is:

[0070] max L = f(stress, temperature, vibration;

[0071] Where L is the equipment life, stress, temperature, and vibration are stress, temperature, and vibration parameters, respectively;

[0072] Pareto frontier: By comparing the compromise solutions between different optimization objectives, a Pareto frontier is constructed to find optimization solutions that are non-inferior in multiple objectives, and the calculation formula is:

[0073]

[0074] Where is the Pareto frontier solution set, X is the feasible solution space, and f i is the i-th objective function;

[0075] Optimization scheme generation: Select the optimal scheme on the Pareto frontier, balance each objective, and generate a comprehensive optimization scheme, and the calculation formula is:

[0076]

[0077] Where x * is the optimal scheme, and w i is the weight of the i-th objective.

[0078] Further, the real-time optimization and feedback includes:

[0079] Real-time adjustment of operating parameters: according to the optimization scheme generated by the multi-objective optimization algorithm, adjust the key operating parameters of the equipment, the calculation formula is:

[0080]

[0081] Wherein, u t is the optimization operating parameter at time t, w i is the weight of the i-th optimization objective, f i is the i-th optimization objective function, x t is the current state;

[0082] Continuous monitoring of optimization effect: in the running process, real-time acquisition of the running data of the equipment, monitoring the effect of each optimization index, including energy consumption, production efficiency and equipment life, the calculation formula is:

[0083]

[0084] Wherein, Effectiveeness is the comprehensive evaluation of optimization effect, u t-1 is the operating parameter at the previous moment;

[0085] Feedback mechanism: feedback the monitored optimization effect to the intelligent prediction and optimization module, adjust the parameters of the prediction model, optimize the control strategy, form a closed loop control, the calculation formula is:

[0086]

[0087] Wherein, θ t is the current model parameter, η is the learning rate, is the loss function, y t is the actual value, is the predicted value.

[0088] Further, the control and communication module includes:

[0089] Real-time control: according to the obtained operating parameters, real-time control of the operating parameters of mechanical and electrical equipment, including voltage, current, speed and cooling parameter adjustment, the calculation formula is:

[0090]

[0091] Wherein, u t is the control signal at time t, r t is the reference value, y t is the actual value, K p , K iand K d Kp, Ki and Kd are the proportional, integral and derivative control coefficients, respectively;

[0092] Data transmission: real-time running parameters are transmitted to the data processing module and the intelligent prediction and optimization module through wired or wireless networks;

[0093] Communication with external units: communicate with external monitoring devices, cloud platforms or related devices through industrial communication protocols such as Modbus, Profibus or Ethernet.

[0094] Further, the early warning and maintenance management module includes:

[0095] Abnormality detection and early warning: real-time monitoring of mechanical and electrical equipment operation data, when abnormality is detected, triggering early warning through preset threshold;

[0096] Early warning signal: after detecting abnormality, send early warning signal to users through sound alarm, SMS, email or remote notification device, prompting to check and maintain;

[0097] Maintenance record management: record information of each maintenance, including maintenance date, maintenance content, maintenance personnel and mechanical and electrical equipment status;

[0098] Maintenance plan development: based on the operation data and historical maintenance records of mechanical and electrical equipment, develop regular and preventive maintenance plans;

[0099] Maintenance plan execution: according to the developed maintenance plan, generate maintenance tasks and track the execution of maintenance tasks.

[0100] Further, the maintenance plan development includes:

[0101] Device health assessment: based on the collected operation parameters and historical maintenance records, use health assessment algorithm to assess the current health status of the device, calculate health index HI, the calculation formula is:

[0102]

[0103] Where n is the number of monitoring parameters, w i is the weight of the i-th parameter, x i is the current value of the i-th monitoring parameter, μ i is the mean value of the i-th monitoring parameter, σ i is the standard deviation of the i-th monitoring parameter;

[0104] Regular maintenance plan: according to the recommendations of the equipment manufacturer and the use experience, develop regular maintenance plan to ensure maintenance within the specified time interval;

[0105] Preventive maintenance plan: based on the equipment health assessment results, combined with the trend analysis of operation parameters and historical failure modes, a preventive maintenance plan is formulated to prevent failures in advance.

[0106] Advantages of the present application:

[0107] The present application, through the combination of data acquisition module, data processing module, intelligent prediction and optimization module, control and communication module and early warning and maintenance management module, realizes efficient monitoring, fault prediction, performance optimization and maintenance management of mechanical and electrical equipment, the system can collect and analyze the running parameters of the equipment in real time, detect and handle abnormal situations in time, optimize the running parameters of the equipment, thereby significantly improving the running efficiency and reliability of the equipment, reducing the downtime and maintenance cost of the equipment.

[0108] The present application, by analyzing characteristic information and abnormal characteristics, predicts equipment failure and performance change, and finds the best balance point among multiple performance indicators, generates an optimization scheme, and a real-time optimization and feedback mechanism ensures dynamic adjustment and optimization of equipment operating parameters, forming a closed-loop control, improving the adaptability and response ability of the system in dynamic environment, helping to discover and prevent equipment failure in time, and ensuring the continuous and efficient operation of the equipment.

[0109] The present application, through the early warning and maintenance management module, can timely send early warning signals when detecting abnormalities, inform users to check and maintain, and systematically manage the maintenance information and plan of mechanical and electrical equipment, through equipment health assessment, formulate periodic maintenance plan including lubrication, cleaning, tightening and calibration tasks, and preventive maintenance plan including fault prediction, preventive maintenance and condition monitoring tasks, ensure the periodic and preventive maintenance work of the equipment, effectively prolong the service life of the equipment, and improve the overall operation efficiency and reliability of the equipment. BRIEF DESCRIPTION OF DRAWINGS

[0110] In order to more clearly illustrate the technical solutions in the present application or prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description only illustrate the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0111] Fig. 1 The system function module diagram of the embodiment of the present application is shown in the figure.

[0112] Fig. 2 The intelligent prediction and optimization module diagram of the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0113] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with specific examples.

[0114] It should be noted that, unless otherwise defined, technical terms or scientific terms used in the present application should be understood as their common meanings to those skilled in the art to which the present application pertains. The terms "first", "second" and similar terms used in the present application do not represent any order, number or importance, but are only used to distinguish different components. The terms "include" or "contain" and similar terms mean that the components or objects before the terms encompass the components or objects listed after the terms and their equivalents, without excluding other components or objects. The terms "connect" or "connected" and similar terms are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "upper", "lower", "left", "right" and the like are only used to represent relative positional relationships, which can change accordingly when the absolute positions of the described objects change.

[0115] As shown in Figs. 1-2 A control management system of mechanical and electrical equipment, comprising a data acquisition module, a data processing module, an intelligent prediction and optimization module, a control and communication module, and an early warning and maintenance management module, wherein:

[0116] The data acquisition module acquires operating parameters of the mechanical and electrical equipment, including temperature, pressure, vibration and energy consumption.

[0117] The data processing module analyzes and processes the operating parameters, extracts feature information and abnormal features.

[0118] The intelligent prediction and optimization module analyzes the feature information and abnormal features in real time, predicts equipment failures and performance changes, and optimizes equipment operating parameters to improve overall equipment performance and energy efficiency, specifically including:

[0119] Adaptive prediction model: build a prediction model and continuously update and optimize the prediction model using sliding window technology. The prediction model analyzes feature information and abnormal features to predict mechanical and electrical equipment failures and performance changes, and generates corresponding prediction results.

[0120] Multi-objective optimization: define multiple optimization objectives, use a multi-objective optimization algorithm based on the Pareto frontier to find the best balance point between multiple performance indicators, and generate an optimization scheme.

[0121] Real-time optimization and feedback: based on the results of the multi-objective optimization algorithm, real-time adjust the operating parameters of the mechanical and electrical equipment, and continuously monitor the optimization effect, and use the feedback to improve the prediction model to form a closed-loop control.

[0122] The control and communication module controls the mechanical and electrical equipment in real time based on the collected operating parameters, and realizes data transmission and communication with external units, supporting the overall collaborative work of the system.

[0123] The early warning and maintenance management module sends an early warning signal when an anomaly is detected, notifying the user to check and maintain, and manages the maintenance information and plan of the mechanical and electrical equipment, including maintenance records, maintenance plan formulation and execution.

[0124] Through the above, efficient monitoring, fault prediction, performance optimization and maintenance management of mechanical and electrical equipment are realized, significantly improving the operation efficiency, reliability and life of the equipment, reducing downtime and maintenance costs.

[0125] The data acquisition module includes:

[0126] Temperature monitoring: Install temperature sensors on mechanical and electrical equipment to monitor temperature changes in real time;

[0127] Pressure measurement: Install pressure sensors in the hydraulic or pneumatic system of the mechanical and electrical equipment to measure pressure values in real time;

[0128] Vibration monitoring: Install vibration sensors on rotating parts or the body of the mechanical and electrical equipment to monitor vibration conditions in real time;

[0129] Energy consumption monitoring: Install energy consumption sensors in the power supply system of the mechanical and electrical equipment to monitor energy consumption, including voltage, current and power;

[0130] Through the above, comprehensive monitoring and timely feedback of equipment status are ensured, which helps early fault detection and optimization of equipment performance, improving the operation efficiency and reliability of the system.

[0131] The data processing module includes:

[0132] Data cleaning: Remove noise and outliers in operating parameters to ensure data quality, and use a moving average filter to smooth the operating parameters;

[0133] The calculation formula of the moving average filter is:

[0134]

[0135] where, is the smoothed data, x(t) is the original data, and N is the size of the moving window;

[0136] Feature extraction: Extract feature information from operating parameters, convert time domain signals to frequency domain using Fourier transform (FFT), and extract features of equipment vibration and energy consumption by analyzing frequency components in the frequency spectrum;

[0137] The calculation formula of Fourier transform (FFT) is:

[0138]

[0139] Where X(f) is the frequency domain signal, x(n) is the time domain signal, and N is the signal length;

[0140] Anomaly detection: Use support vector machine (SVM) to classify and cluster the extracted features, identify and label abnormal features;

[0141] The calculation formula of support vector machine (SVM) is:

[0142]

[0143] Where w is the weight vector, b is the bias, ξ i is the slack variable, and C is the penalty parameter;

[0144] Data fusion: Use Kalman filter to fuse operating parameters, analyze the correlation between different operating parameters, and enhance the accuracy and reliability of anomaly detection;

[0145] The calculation formula of Kalman filter is:

[0146]

[0147] P k|k-1 =AP k-1|k-1 A T +Q;

[0148] K k =P k|k-1 H T (HP k|k-1 H T +R) -1 ;

[0149]

[0150] P k|k =(I-K k H)P k|k-1 ;

[0151] Where, is the prior state estimate, P k|k-1 is the prior estimation error covariance, K k is the Kalman gain, and z kY = {y1, y2,..., yn} for observations, A, B, H, Q, R are system parameter matrices;

[0152] Through the above steps, the overall monitoring of the equipment operating state and the accurate extraction of abnormal features are ensured, and high-quality data support is provided for the intelligent prediction and optimization module.

[0153] The adaptive prediction model includes:

[0154] Prediction model construction: based on historical operating parameters and feature information, a deep belief network (DBN) model is used for modeling;

[0155] Sliding window technology: in the process of mechanical and electrical equipment operation, sliding window technology is used for segmented processing of real-time operating parameters, the size of the sliding window is set to W, and each time it moves a step S to obtain the latest operating parameter segment, the calculation formula is

[0156] X t = {x t ,x t+1 ,...,x t+W-1};

[0157] Where X t is the data in the current sliding window;

[0158] Model updating and optimization: use the data in the sliding window to continuously update and optimize the prediction model, adjust the weights of the prediction model through the stochastic gradient descent (SGD) of the adaptive learning rate, to adapt to the latest data changes, the calculation formula is:

[0159]

[0160] Where η0 is the initial learning rate, β1 and β2 are hyperparameters;

[0161] Prediction and result generation: the prediction model analyzes the feature information and abnormal features extracted in the sliding window to predict the mechanical and electrical equipment faults and performance changes, outputs the prediction results, and generates the corresponding prediction report, including fault type, occurrence probability and recommended maintenance measures;

[0162] Through the above content, real-time processing and optimization of equipment operating data can be realized, accurate prediction of equipment faults and performance changes can be realized, and detailed prediction reports can be generated. This method not only improves the accuracy and reliability of prediction, but also enhances the adaptability of the system in dynamic environment, helps to discover and prevent equipment faults in time, and improves the overall operation efficiency and safety of the equipment.

[0163] The deep belief network (DBN) model includes:

[0164] Standardization: Standardize the operational data to make the operational parameters have zero mean and unit variance, the calculation formula is:

[0165]

[0166] where x i is the original data, μ is the mean, and σ is the standard deviation;

[0167] Time series segmentation: Segment the time series data, each segment length is T, to capture the time dependence, the calculation formula is:

[0168] X t = [x t , x t+1 ,..., x t+T-1 ];

[0169] Multimodal data fusion: Connect the operational parameters into a fusion vector, the calculation formula is:

[0170] X fused = [X temp , X pressure , X vibration , X energy ];

[0171] where X temp , X pressure , X vibration , X energy are temperature, pressure, vibration and energy consumption data, respectively;

[0172] RBM energy function: The RBM energy function after introducing time dependence and multimodal features, the calculation formula is:

[0173] E(v, h) = -∑ i a i v i -∑ j b j h j -∑ i,j v i W ij h j -∑ t c t X t ;

[0174] where c t is the weight of time dependence;

[0175] Activation probability: Calculate the activation probability considering time dependence, the calculation formula is:

[0176] P(h j = 1 | v, Xt ) = σ(b j +∑ i v i W ij +∑ t c t X t );

[0177] P(v i =1|h) = σ(a i +∑ j h j W ij );

[0178] Layer-wise training: Use RBM to train deep belief network model layer by layer, learn the weight of each layer, the formula is:

[0179] h l = σ(W l ·h l-1 +b l );

[0180] Where h l is the hidden unit of the l-th layer, W l and b l are the weight and bias of the l-th layer;

[0181] Fine-tuning: Use backpropagation algorithm to fine-tune the entire network, improve the prediction accuracy, the formula is:

[0182]

[0183] Where, is the loss function, y i is the true value, is the predicted value;

[0184] Prediction output: Use the trained deep belief network model for prediction, the formula is:

[0185]

[0186] Where W out and b out are the weight and bias of the output layer, h L is the hidden unit of the last layer;

[0187] Anomaly detection: Based on the difference between the prediction result and the actual data for anomaly detection, the formula is:

[0188]

[0189] Where δ is the set threshold;

[0190] In the present application, the DBN model can better capture the complex characteristics and dynamic changes in the equipment operation data, improve the accuracy and robustness of the prediction, ensure the hierarchical feature learning ability of the model, and ultimately realize efficient fault prediction and performance optimization.

[0191] Multi-objective optimization includes:

[0192] Define optimization objectives: define multiple optimization objectives, including minimizing energy consumption, maximizing production efficiency, and extending equipment life;

[0193] Minimize energy consumption by optimizing the operating parameters of mechanical and electrical equipment to reduce power and energy consumption, the objective function is:

[0194]

[0195] Where E is the total energy consumption, P(t) is the power consumption at time t, and Δt is the time interval;

[0196] Maximize production efficiency by optimizing the operating speed and workload of mechanical and electrical equipment to improve production output, the objective function is:

[0197]

[0198] Where η is the production efficiency, Q output is the output, and Q input is the input;

[0199] Extend equipment life by optimizing the operating conditions of mechanical and electrical equipment to reduce equipment wear and failure, the objective function is:

[0200] max L=f(stress, temperature, vibration);

[0201] Where L is the equipment life, stress, temperature, and vibration are stress, temperature, and vibration parameters, respectively;

[0202] Pareto frontier: by comparing the compromise solutions between different optimization objectives, construct the Pareto frontier, find the optimization solution that is not inferior in multiple objectives, the calculation formula is:

[0203]

[0204] Where, is the Pareto frontier solution set, X is the feasible solution space, and f i is the i-th objective function;

[0205] Optimization scheme generation: select the optimal scheme on the Pareto frontier, generate a comprehensive optimization scheme by balancing each target, the calculation formula is:

[0206]

[0207] Where x * is the optimal scheme, w i is the weight of the i-th target;

[0208] Through the above steps, the best balance point between multiple performance indicators can be found, and a comprehensive optimization scheme can be generated, which can consider the energy consumption, production efficiency and life of the equipment at the same time, improve the overall operation efficiency and reliability of the equipment, and realize intelligent optimization control.

[0209] Real-time optimization and feedback includes:

[0210] Real-time adjustment of operating parameters: according to the optimization scheme generated by the multi-objective optimization algorithm, adjust the key operating parameters of the equipment, the calculation formula is:

[0211]

[0212] Where u t is the optimization operating parameter at time t, w i is the weight of the i-th optimization target, f i is the i-th optimization objective function, x t is the current state;

[0213] Continuous monitoring of optimization effect: in the running process, real-time collection of equipment operation data, monitoring of the effect of each optimization index, including energy consumption, production efficiency and equipment life, to ensure the effectiveness of the optimization result, the calculation formula is:

[0214]

[0215] Where Effectiveness is the comprehensive evaluation of the optimization effect, u t-1 is the operating parameter at the previous time;

[0216] Feedback mechanism: feedback the monitored optimization effect to the intelligent prediction and optimization module, adjust the parameters of the prediction model, optimize the control strategy, form a closed-loop control, the calculation formula is:

[0217]

[0218] Where θ t is the current model parameter, η is the learning rate, is the loss function, y t is the actual value, is the predicted value;

[0219] Through the above, the running state of the equipment can be dynamically optimized according to the results of the multi-objective optimization algorithm, ensuring the realization of various optimization objectives. The introduction of the feedback mechanism enables the system to adaptively adjust and optimize the control strategy, forming an efficient closed-loop control, and improving the overall performance and operation reliability of the equipment.

[0220] The control and communication module includes:

[0221] Real-time control: According to the obtained running parameters, the running parameters of the mechanical and electrical equipment are controlled in real time, including the adjustment of voltage, current, speed and cooling parameters, and the calculation formula is:

[0222]

[0223] Where, u t is the control signal at time t, r t is the reference value, y t is the actual value, K p , K i and K d are the proportional, integral and differential control coefficients, respectively;

[0224] Voltage control adjusts the power supply voltage of the equipment in real time to ensure stable operation of the equipment, and the calculation formula is:

[0225] V t = V ref + u t ;

[0226] Where, V t is the adjusted voltage value, and V ref is the reference voltage value;

[0227] Current control adjusts the current to meet the load demand of the equipment, and the calculation formula is:

[0228] I t = I ref + u t ;

[0229] Where, I t is the adjusted current value, and I ref is the reference current value;

[0230] Speed control adjusts the running speed of the equipment in real time according to the production requirements, and the calculation formula is:

[0231] S t = S ref + u t ;

[0232] Where, S tFor the adjusted speed value, S ref For the reference speed value;

[0233] Cooling control adjusts the cooling system according to the data of the temperature sensor to keep the equipment within the optimal working temperature range, the calculation formula is:

[0234] C t = C ref + u t ;

[0235] Where C t is the adjusted cooling parameter, C ref is the reference cooling parameter;

[0236] Data transmission: Real-time running parameters are transmitted to the data processing module and intelligent prediction and optimization module through wired or wireless networks, realizing data sharing and coordination between modules;

[0237] Communication with external units: Through industrial communication protocols (such as Modbus, Profibus or Ethernet), communicate with external monitoring devices, cloud platforms or related devices to ensure the integration and collaborative work of the system;

[0238] Through real-time control of voltage, current, speed and cooling parameters, the control and communication module can ensure the stable and efficient operation of mechanical and electrical equipment. At the same time, through the realization of data transmission and communication with external units, the system can share real-time running data, realize integrated management and control, and improve the overall performance and reliability of the system.

[0239] The early warning and maintenance management module includes:

[0240] Abnormality detection and early warning: Real-time monitoring of mechanical and electrical equipment running data, when abnormality is detected, triggering early warning through preset threshold;

[0241] Early warning signal: After detecting abnormality, send early warning signal to users through sound alarm, SMS, email or remote notification device, prompting to check and maintain;

[0242] Maintenance record management: Record information of each maintenance, including maintenance date, maintenance content, maintenance personnel and mechanical and electrical equipment status;

[0243] Maintenance plan development: Based on the running data and historical maintenance records of mechanical and electrical equipment, develop regular and preventive maintenance plan;

[0244] Maintenance plan execution: According to the developed maintenance plan, generate maintenance tasks and track the execution of maintenance tasks to ensure the completion of maintenance work according to the plan;

[0245] Through the above, when the device operation is abnormal, the system can timely notify the user for inspection and maintenance, prevent the fault from further expanding, at the same time, can systematize the management of maintenance information, formulate and execute the maintenance plan, ensure the regular and preventive maintenance work of the device, improve the overall operation efficiency and reliability of the device.

[0246] The maintenance plan includes:

[0247] Device health assessment: based on the collected operation parameters and historical maintenance records, the current health status of the device is evaluated using a health assessment algorithm, and a health index HI is calculated, the calculation formula is:

[0248]

[0249] Where n is the number of monitoring parameters, w i is the weight of the i-th parameter, x i is the current value of the i-th monitoring parameter, μ i is the mean of the i-th monitoring parameter, σ i is the standard deviation of the i-th monitoring parameter;

[0250] Regular maintenance plan: according to the suggestions of the device manufacturer and the use experience, the regular maintenance plan is made, and the maintenance is ensured within the specified time interval;

[0251] The regular maintenance plan specifically includes:

[0252] Lubrication: regular inspection and addition of lubricating oil to reduce the wear of mechanical parts;

[0253] Cleaning: regular cleaning of the device to prevent dust and impurities from affecting the operation of the device;

[0254] Fastening: check and tighten loose bolts and connectors to ensure the stability of the device;

[0255] Calibration: regular calibration of sensors and instruments to ensure the accuracy of measurement;

[0256] Preventive maintenance plan: based on the results of device health assessment, combined with trend analysis of operation parameters and historical failure modes, a preventive maintenance plan is made to prevent faults in advance;

[0257] The preventive maintenance plan specifically includes:

[0258] Fault prediction: by analyzing the device operation data, the type and time of possible faults are predicted;

[0259] Preventive repair: repair and replace the vulnerable parts before the fault occurs to prevent the fault from occurring;

[0260] State monitoring: increase the monitoring frequency of key parts to find potential problems in time

[0261] Through the maintenance planning method based on equipment operation data and historical maintenance records, the health status of the equipment can be effectively evaluated, the periodic maintenance plan including tasks such as lubrication, cleaning, fastening and calibration, and the preventive maintenance plan including tasks such as fault prediction, preventive maintenance and state monitoring can be formulated, and the continuous and efficient operation of the equipment can be ensured.

[0262] Those skilled in the art should understand that the above discussion of any embodiment is only exemplary and is not intended to imply that the scope of the present application is limited to these examples; under the idea of the present application, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other changes of different aspects of the present application as described above, which are not provided in details for the sake of brevity.

[0263] The present application is intended to cover all such alternatives, modifications and variations as fall within the broad scope of the claims. Therefore, any omission, modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the protection scope of the present application.

Claims

1. A control management system for a mechanical electrical plant, characterized by The system includes a data acquisition module, a data processing module, an intelligent prediction and optimization module, a control and communication module, and an early warning and maintenance management module. The data acquisition module collects the operating parameters of mechanical and electrical equipment, including temperature, pressure, vibration, and energy consumption. The data processing module analyzes and processes the operating parameters, extracting characteristic information and abnormal characteristics. The intelligent prediction and optimization module analyzes the characteristic information and abnormal characteristics in real time, predicts equipment failures and performance changes, and optimizes equipment operating parameters, including: Adaptive prediction model: Construct a prediction model and continuously update and optimize it using sliding window technology. The prediction model analyzes the characteristic information and abnormal characteristics to predict the failure and performance changes of mechanical and electrical equipment and generates corresponding prediction results. Multi-objective optimization: Define multiple optimization objectives and use a multi-objective optimization algorithm based on the Pareto frontier to find the best balance point among multiple performance indicators and generate an optimization scheme. Real-time optimization and feedback: Adjust the operating parameters of mechanical and electrical equipment in real time based on the results of the multi-objective optimization algorithm and continuously monitor the optimization effect. The control and communication module controls mechanical and electrical equipment in real time based on the collected operating parameters and realizes data transmission and communication with external units. The early warning and maintenance management module issues a warning signal when an anomaly is detected, notifies the user to check and maintain, and manages the maintenance information and plan of mechanical and electrical equipment, including maintenance records, maintenance plan formulation and execution.

2. A control management system for a mechanical and electrical plant according to claim 1, characterized in that, The data acquisition module includes: Temperature monitoring: Install temperature sensors on mechanical and electrical equipment to monitor temperature changes in real time. Pressure measurement: Install pressure sensors in the hydraulic or pneumatic systems of mechanical and electrical equipment to measure pressure values in real time. Vibration monitoring: Install vibration sensors on rotating parts or the body of mechanical and electrical equipment to monitor vibration in real time. Energy consumption monitoring: Install energy consumption sensors in the power supply system of mechanical and electrical equipment to monitor energy consumption, including voltage, current, and power.

3. A control management system for mechanical and electrical equipment as claimed in claim 1, wherein, The data processing module includes: Data cleaning: Remove noise and outliers from operating parameters and use a moving average filter to smooth the operating parameters. Feature extraction: Extract characteristic information from operating parameters, convert time-domain signals to frequency domain using Fourier transform, and extract device vibration and energy consumption characteristics by analyzing frequency components in the frequency spectrum. Anomaly detection: Use a support vector machine to classify and cluster the extracted features, identify and label abnormal characteristics. Data fusion: Use a Kalman filter to fuse operating parameters and analyze the correlation between different operating parameters.

4. A control management system for mechanical and electrical equipment according to claim 1, characterized in that, The adaptive prediction model includes: Prediction model construction: Based on historical operating parameters and characteristic information, use a deep belief network model to build a model. Sliding window technology: Use sliding window technology to segment real-time operating parameters during the operation of mechanical and electrical equipment. The size of the sliding window is W, and it moves one step S at a time to obtain the latest operating parameter segment. The formula is X t = {x t ,x t+1 ,...,x t+W-1} ; wherein X t is data within the current sliding window; Model updating and optimization: continuously update and optimize the prediction model using data within the sliding window, adjust the weights of the prediction model through stochastic gradient descent with adaptive learning rate, the calculation formula is: Where η0 is the initial learning rate, β1 and β2 are hyperparameters; Prediction and generation of results: the prediction model analyzes the extracted feature information and abnormal features within the sliding window, predicts the mechanical and electrical equipment failure and performance changes, outputs the prediction results, and generates the corresponding prediction report, including fault type, occurrence probability and recommended maintenance measures.

5. A control management system for a mechanical and electrical installation according to claim 4, characterized in that The deep belief network model includes: Standardized data: standardize the operation data, so that the operation parameters have zero mean and unit variance, the calculation formula is: where x i is the original data, μ is the mean, and σ is the standard deviation. Time series segmentation: segment the time series data, each segment length is T, to capture the time dependence, the calculation formula is: X t = [x t ,x t+1 ,...,x t+T-1 ] ; Multi-modal data fusion: connect the operation parameters into a fusion vector, the calculation formula is: X fused = [X temp , X pressure , X vibration , X energy ] ; wherein X temp , X pressure , X vibration , X energy are temperature, pressure, vibration and energy consumption data, respectively; RBM energy function: the RBM energy function after introducing time dependence and multi-modal features, the calculation formula is: E(v, h) = -∑ i a i v i -∑ j b j h j -∑ i,j v i W ij h j -∑ t c t X t ; where c t is a time-dependent weight; Activation probability: calculate the activation probability considering time dependence, the calculation formula is: P(h j |v,X t ) = σ(b j +∑ i v i W ij +∑ t c t X t ) P(v i =1|h) = σ(a i +∑ j h j W ij ); Layer-by-layer training: use RBM to train the deep belief network model layer by layer, learn the weights of each layer, the calculation formula is: h l = σ(W l · h l-1 + b l ); where h l is the hidden unit of the lth layer, W l and b l are the weights and bias of the lth layer; Fine-tuning: use the back propagation algorithm to fine-tune the entire network, the calculation formula is: wherein, is a loss function, y i is a true value, is a predicted value; Prediction output: use the trained deep belief network model for prediction, the calculation formula is: where W out and b out are the weights and biases of the output layer, and h L is the hidden unit of the last layer. Anomaly detection: based on the difference between the prediction results and the actual data, the calculation formula is: Where δ is the set threshold.

6. A control management system for a mechanical and electrical installation according to claim 5, characterized in that The multi-objective optimization includes: Define optimization objectives: define multiple optimization objectives, including minimizing energy consumption, maximizing production efficiency and prolonging equipment life; The minimum energy consumption is achieved by optimizing the operation parameters of mechanical and electrical equipment to reduce power and energy consumption, the objective function is: Where E is the total energy consumption, P(t) is the power consumption at time t, and Δt is the time interval; The maximum production efficiency is achieved by optimizing the running speed and workload of mechanical and electrical equipment to improve production output, the objective function is: wherein η is the production efficiency, Q output is the output, Q input is the input; The prolongation of equipment life is achieved by optimizing the operating conditions of mechanical and electrical equipment to reduce equipment wear and failure, the objective function is: maxL=f(stress, temperature, vibration); Where L is the equipment life, stress, temperature and vibration are stress, temperature and vibration parameters respectively; Pareto frontier: by comparing the compromise solutions between different optimization objectives, construct the Pareto frontier, find the optimization scheme that is not worse on multiple objectives, the calculation formula is: wherein, is the Pareto front solution set, X is the feasible solution space, f i is the i-th objective function; Optimization scheme generation: select the optimal scheme on the Pareto frontier, balance each target to generate a comprehensive optimization scheme, the calculation formula is: where x * is the optimal solution, w i is the weight of the i-th objective.

7. A control management system for a mechanical and electrical installation according to claim 6, characterized in that The real-time optimization and feedback includes: Real-time adjustment of operation parameters: adjust the key operation parameters of the equipment according to the optimization scheme generated by the multi-objective optimization algorithm, the calculation formula is: wherein u t is the optimized operating parameter at time t, w i is the weight of the i-th optimization objective, f i is the i-th optimization objective function, x t is the current state; Continuous monitoring of optimization effect: During operation, real-time collection of equipment operation data, monitoring of the effect of various optimization indicators, including energy consumption, production efficiency and equipment life, calculation formula: wherein Effectiveness is the comprehensive evaluation of the optimization effect, u t-1 is the operating parameter at the previous moment; Feedback mechanism: Feedback the monitored optimization effect to the intelligent prediction and optimization module, adjust the parameters of the prediction model, optimize the control strategy, form a closed-loop control, calculation formula: where θ t is the current model parameter, η is the learning rate, is the loss function, y t is the actual value, is the predicted value.

8. A control management system for mechanical and electrical equipment according to claim 1, characterized in that, The control and communication module includes: Real-time control: According to the obtained operation parameters, the operation parameters of mechanical and electrical equipment are controlled in real time, including voltage, current, speed and cooling parameter adjustment, calculation formula: wherein u t is the control signal at time t, r t is the reference value, y t is the actual value, K p , K i and K d are the proportional, integral and derivative control coefficients, respectively. Data transmission: Real-time operation parameters are transmitted to the data processing module and the intelligent prediction and optimization module through wired or wireless networks; Communication with external units: Communicate with external monitoring devices, cloud platforms or related devices through industrial communication protocols.

9. A control management system for a mechanical and electrical installation according to claim 8, characterized in that The early warning and maintenance management module includes: Abnormality detection and early warning: Real-time monitoring of mechanical and electrical equipment operation data, when abnormality is detected, triggering early warning through preset threshold; Early warning signal: After detecting the abnormality, send early warning signals to the user through sound alarm, SMS, email or remote notification device, prompt to check and maintain; Maintenance record management: Record the information of each maintenance, including maintenance date, maintenance content, maintenance personnel and mechanical and electrical equipment state; Maintenance plan development: Based on the operation data and historical maintenance records of mechanical and electrical equipment, develop regular and preventive maintenance plans; Maintenance plan execution: According to the developed maintenance plan, generate maintenance tasks and track the execution of maintenance tasks.

10. A control management system for a mechanical and electrical installation according to claim 9, characterized in that The maintenance plan development includes: Equipment health assessment: Based on the collected operation parameters and historical maintenance records, use the health assessment algorithm to assess the current health status of the equipment, calculate the health index HI, calculation formula: where n is the number of monitoring parameters, w i is the weight of the i-th parameter, x i is the current value of the i-th monitoring parameter, μ i is the mean value of the i-th monitoring parameter, σ i is the standard deviation of the i-th monitoring parameter; Regular maintenance plan: According to the recommendations of equipment manufacturers and use experience, develop regular maintenance plan to ensure maintenance within specified time interval; Preventive maintenance plan: Based on the results of equipment health assessment, combined with trend analysis of operation parameters and historical failure modes, develop preventive maintenance plan to prevent failure in advance.

Images