Risk management and control system based on model prediction control equipment

Abstract

The invention relates to the technical field of equipment risk management and control, and particularly discloses an equipment risk management and control system based on model prediction control, which comprises a data acquisition processing module, a data analysis module, a model construction prediction module and an analysis regulation and control module, obtaining an equipment health condition score through standardization processing and weighted calculation; the data analysis module is used for distinguishing linear and nonlinear characteristic signals according to the score change trend; the model construction and prediction module selects corresponding algorithms to establish a prediction model according to different types of signals, so as to predict the health state of the equipment in the future; the analysis regulation and control module formulates a reasonable equipment maintenance plan based on the prediction result, and dynamically adjusts the production arrangement, the equipment state is continuously monitored and intelligently analyzed, faults can be effectively prevented, the probability of occurrence of non-planned shutdown events is reduced, and finally the purpose of improving production safety and economic benefits is achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment risk management, and in particular to an equipment risk management and control system based on model prediction control. Background Art

[0002] With the continuous improvement of the level of industrial automation, the stable operation of production equipment has become one of the key factors for efficient production and sustainable development of enterprises. However, due to the wear and tear and potential failures caused by long-term operation of equipment, production interruptions and even economic losses may occur. Therefore, how to effectively manage the risks of equipment has become an urgent problem to be solved. Most of the existing equipment risk management technologies rely on post-repair or regular maintenance. This method is not only inefficient, but also often fails to detect potential failures in time, resulting in an increased probability of sudden equipment shutdown. Therefore, developing a method that can monitor the status of equipment in real time and perform risk assessment based on a predictive model is of great significance to improving equipment management efficiency and reducing unplanned downtime.

[0003] Existing equipment maintenance technologies mainly include post-maintenance, regular maintenance and condition-based maintenance. Post-maintenance is to repair the equipment after it fails. Although the method is simple and direct, due to the lack of preventive measures, it is easy to cause the equipment to be in an unstable state for a long time, thereby increasing the maintenance cost; regular maintenance is to inspect and repair the equipment according to the scheduled cycle. Although it can prevent some failures, it is easy to cause waste of resources due to the lack of pertinence; condition-based maintenance uses sensors to monitor the equipment operation data in real time, and combines data analysis methods to evaluate the equipment status to determine whether maintenance is needed. This method is relatively advanced, but in actual applications, it still faces the challenges of complex data processing, difficulty in building prediction models, and high implementation costs. Although these methods have their own advantages, such as real-time monitoring and prediction improve the ability to warn of faults and help preventive maintenance, they also have significant disadvantages, such as complex data processing, difficulty in building prediction models, and high implementation costs.

[0004] In view of the problems existing in the prior art, the present invention proposes an equipment risk management and control system based on model predictive control, which aims to achieve effective management of equipment risks through model predictive control technology. The core of the present invention is to monitor the vibration signal, temperature and current data of the equipment in real time, and conduct a comprehensive analysis to determine whether there are any abnormal conditions. If an abnormality is detected, the data is further analyzed to see if there is a regularity to follow (such as linear or nonlinear), and a suitable method is selected to construct an equipment risk prediction model. The risk trend is obtained based on the model, and the duration between the current time and the time to reach the risk is analyzed according to the trend. Finally, whether regulation is needed is determined based on whether the remaining use time of the equipment exceeds the time to reach the risk. Summary of the invention

[0005] The purpose of the present invention is to provide a risk management and control system for equipment based on model prediction control. The present invention mainly includes the following steps: by collecting equipment status data (such as vibration signals, temperature and current), integrating and standardizing these data, calculating the comprehensive score of the equipment through a preset weight coefficient, and then generating a data abnormality signal or a data normal signal; based on the data abnormality signal, further analyzing the change trend of the equipment status data over time, generating a linear trend signal or a nonlinear trend signal; constructing an equipment risk prediction model according to the nonlinear trend signal to predict the future state of the equipment; based on the prediction result, constructing an equipment risk trend curve chart, obtaining the expected use time of the equipment, and regulating the equipment accordingly according to the equipment status signal. In addition, the present invention also divides the monitoring cycle into multiple equal-length time sub-units and time small units, collects the equipment status data at the middle time point of each time small unit, and standardizes the data by calculating the mean and standard deviation of the equipment status data in each time sub-unit, and uses the weight coefficient to calculate the comprehensive score and compare it with the threshold value to determine whether the equipment state is abnormal. For data abnormality signals, further determine whether the vibration signal, temperature or current data show a linear trend, and select a suitable prediction model accordingly: when the data shows a linear trend, a linear regression model is used for prediction; when it shows a nonlinear trend, a random forest model is used to construct an equipment risk assessment model to predict future state changes of the equipment. Based on the prediction model, the present invention predicts the risk trend in the future by collecting the real-time status data of the equipment, and constructs a risk trend curve chart for the equipment. By comparing the expected use time and the remaining working time of the equipment, it is determined whether maintenance measures need to be taken in advance to ensure that the equipment can continue to operate without immediate intervention, or to perform maintenance in time to extend the life of the equipment and reduce risks. In summary, the present invention not only improves the efficiency of equipment management, but also effectively extends the service life of the equipment and reduces unplanned downtime through real-time monitoring of equipment status data, intelligent analysis and prediction, and dynamic control strategies, thereby improving the safety and economy of the production process.

[0006] The purpose of the present invention can be achieved through the following technical solutions:

[0007] A risk management and control system for equipment based on model prediction and control, comprising a data acquisition and processing module, a data analysis module, a model building and prediction module, and an analysis and control module;

[0008] The data acquisition and processing module is used to collect the status data of the equipment;

[0009] Integrate and standardize equipment status data;

[0010] Based on the standardized status data, the comprehensive score of the equipment is calculated to generate data abnormality signals and data normal signals;

[0011] The data analysis module further analyzes the change trend of the equipment status data over time based on the data anomaly signal, and generates linear trend signals and nonlinear trend signals;

[0012] The model building prediction module builds a risk prediction model based on linear trend signals and nonlinear trend signals;

[0013] The analysis and control module obtains the remaining working time of the equipment based on the risk prediction model, performs comparative analysis, and generates equipment operation signals, wherein the equipment operation signals include equipment normal working signals and equipment maintenance signals.

[0014] As a further technical solution of the present invention, the status data of the device includes a vibration intensity value, a temperature value and a current value;

[0015] Define the monitoring cycle and subdivide it into multiple equal-length time sub-units and smaller time sub-units, and collect device status data at the middle point of each time sub-unit;

[0016] The data collected in each time sub-unit is integrated and processed to calculate the average value of each state data in the time period, which is recorded as the state data value;

[0017] Based on the values ​​of various status data in each time subunit, the mean and standard deviation of various status data of the equipment within the monitoring period are calculated.

[0018] As a further technical solution of the present invention, based on the mean and standard deviation of each state data of the equipment in the monitoring period, the mean of each state data corresponding to the monitoring period is subtracted from each state data value in the time subunit, and then divided by the standard deviation of each state data corresponding to the monitoring period, to obtain the standard value of each state data in each time subunit;

[0019] Among them, the standard values ​​of various status data in the time sub-unit include the vibration intensity standard value, the temperature standard value and the current standard value.

[0020] As a further technical solution of the present invention, the standard values ​​of each state data of all time sub-units obtained within the monitoring period are integrated, and the formula DF i =w1×WD i +w2×ZD i +w3×DL i Calculate the comprehensive score DF based on equipment vibration, temperature and current in each time subunit i ;

[0021] Wherein, w1 is the weight coefficient assigned to the temperature standard value WD, w2 is the weight coefficient assigned to the vibration standard value ZD, w3 is the weight coefficient assigned to the current standard value DL, i is the number of time subunits, i = 1, 2, ..., n, WD i is the standard temperature value of the i-th time subunit, ZD i and DL i Same reason.

[0022] As a further technical solution of the present invention, based on the comprehensive score DF, the comprehensive score DF is compared with a score threshold;

[0023] If the comprehensive score is greater than the score threshold, a data anomaly signal is generated;

[0024] If the comprehensive score is less than or equal to the score threshold, a data normal signal is generated.

[0025] As a further technical solution of the present invention, the process of analyzing the changing trend of the equipment status data over time and generating the linear trend signal and the nonlinear trend signal is as follows:

[0026] Based on the data abnormality signal, the standard values ​​of all status data obtained during the monitoring period are integrated and processed in chronological order to obtain the time series of status data, including vibration intensity series, temperature series and current series;

[0027] Get the linear reference value XC and compare the linear reference value XC with the linear reference threshold:

[0028] If the linear reference value XC is greater than or equal to the linear reference threshold, the time series is marked as a linear series;

[0029] If the linear reference value XC is less than the linear reference threshold, the time series is marked as a nonlinear series;

[0030] Among all time series, count the number of linear sequences and compare them with the number of time series to get the linear quantity ratio, which is marked as XL.

[0031] In all time series, the linear reference value corresponding to the nonlinear sequence is processed with the linear reference threshold, and the absolute value of the difference is taken to obtain the linear reference deviation value corresponding to the nonlinear sequence. The linear reference deviation values ​​corresponding to all nonlinear sequences are summed and averaged to obtain the linear reference deviation mean, and the linear reference threshold is compared to obtain the linear deviation ratio, which is marked as XP.

[0032] The obtained linear quantity ratio XL and linear deviation ratio XP are processed by the formula: A linear performance value XB is obtained, wherein z1 and z2 are both preset proportional coefficients;

[0033] comparing the linear performance value XB with a linear performance threshold;

[0034] If the linear performance value XB is greater than the linear performance threshold, a linear trend signal is generated;

[0035] If the linear performance value XB is less than or equal to the linear performance threshold, a nonlinear trend signal is generated.

[0036] As a further technical solution of the present invention, the linear reference value XC is obtained by: based on any time series, constructing a sequence change curve according to the time series, and dividing the sequence change curve into a plurality of change sub-curves;

[0037] Connect the two end points of the sequence change curve with straight lines to obtain the change reference line;

[0038] Measure the slope of the reference line and the slope of the change sub-curve, and compare the slope of the change sub-curve with the slope of the reference line for positive and negative values:

[0039] If the slope value of the change sub-curve is the same as the slope value of the reference line in terms of positive and negative, the change sub-curve is marked as a same-direction sub-curve;

[0040] If the slope value of the change sub-curve is different from the slope value of the reference line in terms of positive and negative, the change sub-curve is marked as a non-co-directional sub-curve;

[0041] Count the number of sub-curves in the same direction and perform ratio processing with the number of sub-curves in the changing direction to obtain the number ratio of sub-curves in the same direction and mark it as SL;

[0042] Obtain the slope values ​​of all the same-direction sub-curves and integrate them into a slope data group, calculate the variance value of the slope data group, and mark it as FC;

[0043] By formula: A linear reference value XC is obtained, wherein a1 and a2 are both preset proportional coefficients.

[0044] As a further technical solution of the present invention, a linear model is selected as a risk prediction model based on a linear trend signal;

[0045] Based on the nonlinear trend signal, the nonlinear model is selected as the risk prediction model.

[0046] As a further technical solution of the present invention, based on the risk prediction model, the risk threshold is input into the risk prediction model to obtain the time when the equipment status reaches the risk threshold, and the time when the equipment status reaches the risk threshold is subtracted from the current time to obtain the remaining working time of the equipment.

[0047] As a further technical solution of the present invention, the remaining working time of the device is obtained, and the expected use time of the device is compared with the remaining working time of the device;

[0048] If the expected usage time of the device is less than or equal to the remaining working time of the device, a normal working signal of the device is generated;

[0049] If the expected usage time of the equipment is greater than the remaining working time of the equipment, it is considered that the equipment needs maintenance measures in advance and an equipment maintenance signal is generated.

[0050] Beneficial effects of the present invention:

[0051] (1) The present invention collects equipment status data and calculates a comprehensive score through preset weight coefficients, thereby quickly and accurately identifying potential equipment failures, effectively reducing the frequency of manual inspections and the misjudgment rate, and significantly improving equipment management efficiency; secondly, an equipment risk prediction model is constructed based on nonlinear trend signals to accurately predict possible future failures, so that maintenance plans can be formulated in advance, avoiding unplanned downtime caused by sudden failures, and thus extending the overall service life of the equipment.

[0052] (2) The present invention constructs an equipment risk trend curve based on the prediction results. By real-time monitoring of the current and future health status of the equipment and taking preventive maintenance measures, the losses caused by unplanned downtime due to equipment failure are significantly reduced, and the safety and economy of the production process are enhanced. By calculating the mean and standard deviation of the equipment status data in each time sub-unit and comparing and analyzing it with the threshold, the present invention ensures the smooth operation of the production equipment, optimizes resource allocation under the premise of ensuring safety, and further improves the overall economic benefits of the production process.

[0053] (3) The present invention flexibly adapts to different types of equipment and their status data characteristics. By judging whether the vibration signal, temperature or current data show a linear trend, the most appropriate prediction model is selected to ensure the accuracy of the prediction results, thereby expanding the scope of application of the system. At the same time, through real-time status data collection and risk trend prediction, and comparing its expected usage time and remaining working time, the present invention can dynamically decide whether to take maintenance measures in advance to ensure that the equipment continues to operate without immediate intervention, or perform maintenance in a timely manner to extend the life of the equipment and reduce risks, thereby achieving a transition from passive response to active prevention and control, greatly improving the stability and economy of the production system, and having significant application value and social benefits. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] The present invention will be further described below in conjunction with the accompanying drawings.

[0055] Figure 1It is a flowchart of specific steps of a risk management and control system of equipment based on model prediction control of the present invention;

[0056] Figure 2 It is a flow chart for generating a normal data signal and an abnormal data signal in the present invention. DETAILED DESCRIPTION

[0057] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0058] Example 1

[0059] See also Figure 1 As shown, the present invention is a risk management and control system for equipment based on model prediction and control, including a data acquisition and processing module, a data analysis module, a model building and prediction module, and an analysis and control module;

[0060] The data acquisition and processing module is used to collect the status data of the equipment;

[0061] Integrate and standardize equipment status data;

[0062] Based on the standardized status data, combined with the preset weight coefficient, the comprehensive score of the device is calculated to generate data abnormality signals and data normal signals;

[0063] The data analysis module further analyzes the change trend of the equipment status data over time based on the data anomaly signal, and generates linear trend signals and nonlinear trend signals;

[0064] The model building prediction module builds a risk prediction model based on linear trend signals and nonlinear trend signals;

[0065] The analysis and control module obtains the remaining working time of the equipment based on the risk prediction model, performs comparative analysis, and generates equipment operation signals, wherein the equipment operation signals include equipment normal working signals and equipment maintenance signals;

[0066] Data acquisition and processing module:

[0067] Function: Responsible for collecting equipment status data such as vibration intensity, temperature and current, and integrating and standardizing them.

[0068] Output: standard value of equipment status data, comprehensive score, data abnormality / normal signal.

[0069] Data Analysis Module:

[0070] Function: Based on data anomaly signals, analyze the changing trend of equipment status data over time and generate linear or nonlinear trend signals.

[0071] Output: Linear / non-linear trend signal.

[0072] Model building prediction module:

[0073] Function: Build risk prediction model based on linear trend signals and nonlinear trend signals.

[0074] Output: Risk prediction model.

[0075] Analysis and control module:

[0076] Function: Based on the risk prediction model, the remaining working time of the equipment is obtained, and comparative analysis is performed to generate equipment operation signals.

[0077] Output: Equipment operation signal.

[0078] Example 2

[0079] like Figure 2 As shown, this embodiment describes in detail how to collect and process device status data within a monitoring period:

[0080] Divide the monitoring cycle into a number of time sub-units of equal length, divide the time sub-unit into a number of time small units of equal length, and collect the status data of the device at the middle time point of each time small unit;

[0081] Wherein, the monitoring period is a preset time period, such as 1 hour, the equal-length time subunits are equal time periods obtained by dividing the equal time zone division method, the time length of each time subunit is a preset length, such as 1 minute, the time length of the time subunit is a preset length, such as 1 second, the middle time point of the time subunit is the time point when the time subunit is in the middle time, for example, if the time length of the time subunit is 1 second, the middle time point of the time subunit is 0.5 seconds, and the status data of the device includes the vibration intensity value, temperature value and current value of the device;

[0082] The device status data collected at the middle time point of each time sub-unit are respectively integrated and processed to obtain a vibration intensity value unit group, a temperature value unit group and a current value unit group in the time sub-unit;

[0083] According to the mean value calculation formula, the vibration intensity value unit group, the temperature value unit group and the current value unit group are processed respectively to obtain the vibration intensity unit mean value, the temperature unit mean value and the current unit mean value of the equipment in the time sub-unit, which are recorded as the unit vibration signal value, the unit temperature value and the unit current value respectively;

[0084] It should be noted that in the risk management and control analysis of equipment, the equipment may undergo instantaneous changes, that is, the collected equipment status data is instantaneous data, which cannot accurately represent the overall status of the equipment. The collection method of using the average value for the equipment will have higher accuracy;

[0085] Integrate all unit vibration signal values, unit temperature values ​​and unit current values ​​within the monitoring period to obtain a vibration intensity value group, a temperature value group and a current value group;

[0086] The vibration intensity value group, temperature value group and current value group are processed respectively according to the mean value calculation formula to obtain the vibration signal mean value, temperature mean value and current mean value of the equipment within the monitoring period;

[0087] The vibration intensity value group, temperature value group and current value group are processed according to the standard deviation calculation formula to obtain the vibration intensity standard deviation, temperature value standard deviation and current value standard deviation of the equipment within the monitoring period;

[0088] Based on the mean and standard deviation of the equipment status data, the values ​​in the vibration intensity value group, temperature value group and current value group are respectively subtracted from the corresponding mean and then divided by the standard value to obtain the standard value of the equipment status data;

[0089] Among them, the standard values ​​of the equipment status data include the standard value of vibration intensity, the standard value of temperature and the standard value of current;

[0090] It should be noted that the purpose of data standardization is to make data of different dimensions in the same order of magnitude to prevent data inconsistency, thereby preventing certain features from having too great an impact on the model;

[0091] By formula DF i =w1×WD i +w2×ZD i +w3×DL i Calculate the comprehensive score DF based on equipment vibration, temperature and current i ;

[0092] Wherein, w1 is the weight coefficient assigned to the temperature standard value WD, w2 is the weight coefficient assigned to the vibration standard value ZD, w3 is the weight coefficient assigned to the current standard value DL, i is the number of time subunits, i = 1, 2, ..., n, WD i is the standard temperature value of the i-th time subunit, ZD i and DLi Similarly;

[0093] Compare the comprehensive score DF with the score threshold;

[0094] If the comprehensive score is greater than the score threshold, it is considered that the data of the device in this time sub-unit is abnormal, and a data abnormality signal is generated;

[0095] If the comprehensive score is less than or equal to the score threshold, the data of the device in this time subunit is considered to be in a normal state, and a data normal signal is generated;

[0096] It should be noted that this embodiment first divides the monitoring period (such as 1 hour) into several equal-length time sub-units (such as 1 minute), and then subdivides each time sub-unit into shorter time units (such as 1 second), and collects equipment status data at the middle time point of each time unit (such as 0.5 seconds), and then integrates the status data in each time sub-unit, calculates the mean and standard deviation of vibration intensity, temperature and current to eliminate the influence of dimension, and finally, uses preset weight coefficients (w1, w2, w3) to calculate the comprehensive score DF, compares it with the threshold, and generates data abnormality / normal signal.

[0097] Example 3

[0098] This embodiment further describes how to analyze the trend of device status data based on data anomaly signals and select a suitable prediction model:

[0099] In a specific embodiment:

[0100] All the standard values ​​of the status data obtained during the monitoring period are integrated and processed in chronological order to obtain the time series of the status data, including the vibration intensity series, the temperature series and the current series;

[0101] Based on any time series, a sequence change curve is constructed according to the time series, and the sequence change curve is divided into several change sub-curves;

[0102] Connect the two end points of the sequence change curve with straight lines to obtain the change reference line;

[0103] Measure the slope of the reference line and the slope of the change sub-curve, and compare the slope of the change sub-curve with the slope of the reference line for positive and negative values:

[0104] If the slope value of the change sub-curve is the same as the slope value of the reference line in terms of positive and negative, the change sub-curve is marked as a same-direction sub-curve;

[0105] If the slope value of the change sub-curve is different from the slope value of the reference line in terms of positive and negative, the change sub-curve is marked as a non-co-directional sub-curve;

[0106] It should be noted that the same positive and negative means that the slope value of the change sub-curve and the slope value of the reference line are of the same positive or negative;

[0107] Count the number of sub-curves in the same direction and perform ratio processing with the number of sub-curves in the changing direction to obtain the number ratio of sub-curves in the same direction and mark it as SL;

[0108] Obtain the slope values ​​of all the same-direction sub-curves and integrate them into a slope data group, calculate the variance value of the slope data group, and mark it as FC;

[0109] By formula: A linear reference value XC is obtained, wherein a1 and a2 are both preset proportional coefficients;

[0110] In some embodiments, the linear reference value XC is compared to a linear reference threshold:

[0111] If the linear reference value XC is greater than or equal to the linear reference threshold, the time series is marked as a linear series;

[0112] If the linear reference value XC is less than the linear reference threshold, the time series is marked as a nonlinear series;

[0113] Among all time series, count the number of linear sequences and compare them with the number of time series to get the linear quantity ratio, which is marked as XL.

[0114] In all time series, the linear reference value corresponding to the nonlinear sequence is processed with the linear reference threshold, and the absolute value of the difference is taken to obtain the linear reference deviation value corresponding to the nonlinear sequence. The linear reference deviation values ​​corresponding to all nonlinear sequences are summed and averaged to obtain the linear reference deviation mean, and the linear reference threshold is compared to obtain the linear deviation ratio, which is marked as XP.

[0115] The obtained linear quantity ratio XL and linear deviation ratio XP are processed by the formula: A linear performance value XB is obtained, wherein z1 and z2 are both preset proportional coefficients;

[0116] In some embodiments, the linearity performance value XB is compared to a linearity performance threshold value;

[0117] If the linear performance value XB is greater than the linear performance threshold, a linear trend signal is generated;

[0118] If the linear performance value XB is less than or equal to the linear performance threshold, a nonlinear trend signal is generated;

[0119] Based on the linear trend signal, a linear model is selected to predict the future state of the equipment, such as a linear regression model or an autoregressive moving average model;

[0120] Based on the nonlinear trend signal, a nonlinear model is selected to predict the future state of the equipment, such as a random forest model;

[0121] It should be noted that the random forest model is suitable for dealing with situations with multiple input variables and can automatically screen important features;

[0122] In another specific embodiment, if the standard value of the equipment status data presents a nonlinear trend, a nonlinear trend signal is generated, and a risk assessment model for the equipment is constructed by a random forest model, specifically:

[0123] Based on nonlinear trend signals, the time series of equipment status data within the monitoring period is obtained;

[0124] Based on the time series of the equipment status data, a sliding window of a fixed size is added to the vibration intensity series, temperature series or current series;

[0125] Perform sliding average processing on the standard value of the state data in the sliding window to obtain the time series characteristics of the state data in the sliding window, including the mean, standard deviation, maximum value and minimum value of the state data in the sliding window;

[0126] Performing statistical feature extraction processing on the vibration intensity sequence, temperature sequence or current sequence to obtain statistical features of the state data standard values ​​of the equipment in the vibration intensity sequence, temperature sequence or current sequence, including the mean, median, standard deviation, maximum value and minimum value of the state data standard values;

[0127] By formula: The temperature series and the vibration intensity series are jointly analyzed to obtain the combined characteristics of the joint distribution of temperature and vibration;

[0128] Where Ti is the standard value of temperature, Vi is the standard value of vibration intensity, T, is the average value of the standard value of temperature, V, is the average value of the standard value of vibration intensity, and WZL is the correlation coefficient between temperature and vibration, that is, the joint distribution characteristics of temperature and vibration, that is, the combined characteristics;

[0129] The time series characteristics, statistical characteristics and combined characteristics of the standard value of the equipment status data are integrated to obtain the characteristic matrix X of the standard value of the equipment status data;

[0130] Add a corresponding label y to each data point in the feature matrix;

[0131] Integrate the feature matrix X and label y into the dataset D;

[0132] Use random forest regression to build a prediction model, divide the data set D into training set, validation set and test set for training the model, and obtain a mature equipment risk prediction model;

[0133] The characteristic matrix X is simulated and predicted through the equipment risk prediction model to obtain the state changes of the equipment in the future period;

[0134] It should be noted that this embodiment provides a risk prediction model based on nonlinear trends, which simulates and predicts the risk trend of equipment in a certain period of time in the future through a nonlinear model. By simulating and predicting the health status of equipment in a certain period of time in the future, specific risk indicators are provided to help decision makers understand the impact of the current equipment status on production safety and provide a basis for subsequent decisions.

[0135] Example 4

[0136] This example describes how to perform real-time status monitoring and future risk trend prediction based on a risk prediction model:

[0137] In a specific embodiment:

[0138] Based on the risk prediction model, the risk threshold is input into the risk prediction model to obtain the time when the equipment status reaches the risk threshold. The time when the equipment status reaches the risk threshold is subtracted from the current time to obtain the remaining working time of the equipment.

[0139] Obtain the remaining working time of the device and compare the expected usage time of the device with the remaining working time of the device;

[0140] If the expected usage time of the equipment is less than or equal to the remaining working time of the equipment, it is considered that the equipment can continue to operate without immediate intervention, and a normal working signal of the equipment is generated;

[0141] If the expected use time of the equipment is greater than the remaining working time of the equipment, it is considered that the equipment needs to take maintenance measures in advance, and an equipment maintenance signal is generated;

[0142] It should be noted that the expected usage time indicates the length of time the equipment needs to continue to be used according to usage requirements;

[0143] Based on the normal working signal of the equipment, the current operation mode is maintained without adjusting the equipment;

[0144] Based on equipment maintenance signals, take measures such as planned maintenance of the equipment, replace parts, adjust operating parameters to reduce load or increase monitoring frequency.

[0145] The technical solution of the present invention is as follows: first, by simulating and predicting the health status of the equipment in a certain period of time in the future, specific risk indicators are provided to help understand the impact of the current equipment status on production safety and provide a basis for subsequent decision-making; then, by determining the time required for the equipment to develop from the current state to the high-risk state, a time window is provided, during which it is determined whether measures are taken to avoid or reduce risks, ensuring that there is enough time to arrange necessary maintenance activities to prevent sudden failures from affecting production; then, by estimating how long the equipment can operate normally without failure, a scientific basis is provided for the maintenance and replacement plan of the equipment, asset management is optimized, unnecessary maintenance expenses are reduced, and failures caused by excessive aging of the equipment are avoided; next, by comparing the remaining use time of the equipment with the estimated length of time required to reach the high-risk state, it can be determined whether actions need to be taken to extend the life of the equipment or reduce risks, ensure the economy and effectiveness of maintenance activities, and avoid excessive or insufficient maintenance; finally, based on the results of the comparative analysis, it is determined whether and how to adjust the operating conditions of the equipment, and through appropriate maintenance strategies, the service life of the equipment is extended, the failure rate is reduced, the continuity and stability of production are guaranteed, the overall efficiency of the equipment is improved, and the production cost is reduced.

[0146] The working principle of the present invention is as follows: by collecting the status data of the equipment (such as vibration signals, temperature and current), integrating and standardizing these data, calculating the comprehensive score of the equipment through the preset weight coefficient, and then generating a data abnormality signal or a data normal signal; based on the data abnormality signal, further analyzing the change trend of the equipment status data over time, generating a linear trend signal or a nonlinear trend signal; constructing an equipment risk prediction model according to the nonlinear trend signal to predict the future status of the equipment; based on the prediction results, constructing an equipment risk trend curve chart to obtain the expected use time of the equipment, and adjusting the equipment accordingly according to the status signal of the equipment. In addition, the present invention also divides the monitoring cycle into multiple equal-length time sub-units and time small units, collects the status data of the equipment at the middle time point of each time small unit, and standardizes the data by calculating the mean and standard deviation of the equipment status data in each time sub-unit, and uses the weight coefficient to calculate the comprehensive score and compare it with the threshold value to determine whether the equipment status is abnormal. For data abnormality signals, further determine whether the vibration signal, temperature or current data show a linear trend, and select a suitable prediction model accordingly: when the data shows a linear trend, a linear regression model is used for prediction; when it shows a nonlinear trend, a random forest model is used to construct an equipment risk assessment model to predict future state changes of the equipment. Based on the prediction model, the present invention predicts the risk trend in the future by collecting the real-time status data of the equipment, and constructs a risk trend curve chart for the equipment. By comparing the expected use time and the remaining working time of the equipment, it is determined whether maintenance measures need to be taken in advance to ensure that the equipment can continue to operate without immediate intervention, or to perform maintenance in time to extend the life of the equipment and reduce risks. In summary, the present invention not only improves the efficiency of equipment management, but also effectively extends the service life of the equipment and reduces unplanned downtime through real-time monitoring of equipment status data, intelligent analysis and prediction, and dynamic control strategies, thereby improving the safety and economy of the production process.

[0147] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A risk management and control system for equipment based on model prediction and control, characterized in that: It includes data acquisition and processing module, data analysis module, model building and prediction module and analysis and control module; The data acquisition and processing module is used to collect the status data of the equipment; Integrate and standardize equipment status data; Based on the standardized status data, the comprehensive score of the equipment is calculated to generate data abnormality signals and data normal signals; The data analysis module further analyzes the change trend of the equipment status data over time based on the data anomaly signal, and generates linear trend signals and nonlinear trend signals; The model building prediction module builds a risk prediction model based on linear trend signals and nonlinear trend signals; The analysis and control module obtains the remaining working time of the equipment based on the risk prediction model, performs comparative analysis, and generates equipment operation signals, wherein the equipment operation signals include equipment normal working signals and equipment maintenance signals.

2. A risk management and control system for equipment based on model predictive control according to claim 1, characterized in that: The equipment status data includes vibration intensity value, temperature value and current value; Define the monitoring cycle and subdivide it into multiple equal-length time sub-units and smaller time sub-units, and collect device status data at the middle point of each time sub-unit; The data collected in each time sub-unit is integrated and processed to calculate the average value of each state data in the time period, which is recorded as the state data value; Based on the values ​​of various status data in each time subunit, the mean and standard deviation of various status data of the equipment within the monitoring period are calculated.

3. The risk management and control system of equipment based on model predictive control according to claim 2, characterized in that: Based on the mean and standard deviation of each state data of the equipment within the monitoring period, the values ​​of each state data in the time subunit are respectively subtracted from the mean of each state data corresponding to the monitoring period and then divided by the standard deviation of each state data corresponding to the monitoring period to obtain the standard value of each state data in each time subunit; Among them, the standard values ​​of various status data in the time sub-unit include the vibration intensity standard value, the temperature standard value and the current standard value.

4. The risk management and control system of equipment based on model predictive control according to claim 3, characterized in that: The standard values ​​of each state data of all time sub-units obtained during the monitoring period are integrated, and the formula DF i =w1×WD i +w2×ZD i +w3×DL i Calculate the comprehensive score DF based on equipment vibration, temperature and current in each time subunit i ; Wherein, w1 is the weight coefficient assigned to the temperature standard value WD, w2 is the weight coefficient assigned to the vibration standard value ZD, w3 is the weight coefficient assigned to the current standard value DL, i is the number of time subunits, i = 1, 2, ..., n, WD i is the temperature standard value of the i-th time subunit, ZD i and DL i Same reason.

5. The risk management and control system of equipment based on model predictive control according to claim 4, characterized in that: Based on the comprehensive score DF, the comprehensive score DF is compared with the score threshold; If the comprehensive score is greater than the score threshold, a data anomaly signal is generated; If the comprehensive score is less than or equal to the score threshold, a data normal signal is generated.

6. The risk management and control system of equipment based on model predictive control according to claim 1, characterized in that: The process of analyzing the changing trend of equipment status data over time and generating linear trend signals and nonlinear trend signals is as follows: Based on the data abnormality signal, the standard values ​​of all status data obtained during the monitoring period are integrated and processed in chronological order to obtain the time series of status data, including vibration intensity series, temperature series and current series; Get the linear reference value XC and compare the linear reference value XC with the linear reference threshold: If the linear reference value XC is greater than or equal to the linear reference threshold, the time series is marked as a linear series; If the linear reference value XC is less than the linear reference threshold, the time series is marked as a nonlinear series; Among all time series, count the number of linear sequences and compare them with the number of time series to get the linear quantity ratio, which is marked as XL. In all time series, the linear reference value corresponding to the nonlinear sequence is processed with the linear reference threshold, and the absolute value of the difference is taken to obtain the linear reference deviation value corresponding to the nonlinear sequence. The linear reference deviation values ​​corresponding to all nonlinear sequences are summed and averaged to obtain the linear reference deviation mean, and the linear reference threshold is processed to obtain the linear deviation ratio, which is marked as XP; The obtained linear quantity ratio XL and linear deviation ratio XP are processed by the formula: A linear performance value XB is obtained, wherein z1 and z2 are both preset proportional coefficients; comparing the linear performance value XB with a linear performance threshold; If the linear performance value XB is greater than the linear performance threshold, a linear trend signal is generated; If the linear performance value XB is less than or equal to the linear performance threshold, a nonlinear trend signal is generated.

7. The risk management and control system of equipment based on model predictive control according to claim 6, characterized in that: The linear reference value XC is obtained by: based on any time series, constructing a sequence change curve according to the time series, and dividing the sequence change curve into several change sub-curves; Connect the two end points of the sequence change curve with straight lines to obtain the change reference line; Measure the slope of the reference line and the slope of the variation sub-curve, and compare the slope of the variation sub-curve with the slope of the reference line for positive and negative values: If the slope value of the change sub-curve is the same as the slope value of the reference line in terms of positive and negative, the change sub-curve is marked as a same-direction sub-curve; If the slope value of the change sub-curve is different from the slope value of the reference line in terms of positive and negative, the change sub-curve is marked as a non-co-directional sub-curve; Count the number of sub-curves in the same direction and perform ratio processing with the number of sub-curves in the changing direction to obtain the number ratio of sub-curves in the same direction and mark it as SL; Obtain the slope values ​​of all the same-direction sub-curves and integrate them into a slope data group, calculate the variance value of the slope data group, and mark it as FC; By formula: A linear reference value XC is obtained, wherein a1 and a2 are both preset proportional coefficients.

8. The risk management and control system of equipment based on model predictive control according to claim 6, characterized in that: Based on the linear trend signal, the linear model was selected as the risk prediction model; Based on the nonlinear trend signal, the nonlinear model is selected as the risk prediction model.

9. The risk management and control system of equipment based on model predictive control according to claim 8, characterized in that: Based on the risk prediction model, the risk threshold is input into the risk prediction model to obtain the time when the equipment status reaches the risk threshold. The time when the equipment status reaches the risk threshold is subtracted from the current time to obtain the remaining working time of the equipment.

10. A risk management and control system for equipment based on model predictive control according to claim 9, characterized in that: Obtain the remaining working time of the device and compare the expected usage time of the device with the remaining working time of the device; If the expected usage time of the device is less than or equal to the remaining working time of the device, a normal working signal of the device is generated; If the expected usage time of the equipment is greater than the remaining working time of the equipment, it is considered that the equipment needs maintenance measures in advance and an equipment maintenance signal is generated.

Images