Device energy efficiency recession early warning system and method based on multi-dimensional data fusion analysis

Abstract

The application discloses a device energy efficiency recession early warning system and method based on multi-dimensional data fusion analysis, relates to the technical field of device energy efficiency recession monitoring, and comprises the following steps: setting a device energy efficiency data analysis mechanism to analyze and obtain device energy efficiency evaluation values, and analyzing whether the device energy efficiency is abnormal; setting a unit output energy consumption analysis mechanism to further analyze the energy efficiency change abnormality of the device according to the change trend of unit output energy consumption; setting a threshold dynamic adjustment mechanism to dynamically adjust the threshold by using a device aging influence coefficient, and correcting the collected energy consumption data by using a working condition influence coefficient; setting a device energy consumption abnormality early warning mechanism to early warn the abnormal energy efficiency recession; and identifying and eliminating reasonable energy consumption disturbance caused by production load fluctuation, so that the misjudgment probability in the device energy consumption abnormality monitoring process is reduced, and the problems that the traditional energy efficiency analysis is easily disturbed by working conditions, cannot distinguish natural aging from fault deterioration, and has a high false alarm and missed alarm rate are solved.

Description

Technical Field

[0001] This invention relates to the field of equipment energy efficiency degradation monitoring technology, specifically to an equipment energy efficiency degradation early warning system and method based on multi-dimensional data fusion analysis. Background Technology

[0002] Industrial production equipment operates continuously for extended periods, and its energy efficiency exhibits a continuous and gradual decline due to factors such as load fluctuations, environmental changes, component wear, and aging drift. Traditional methods, which typically employ fixed threshold assessment models, have certain shortcomings. Traditional solutions often only statistically analyze total energy consumption data, failing to consider actual production output when evaluating equipment energy efficiency levels and struggling to distinguish between energy consumption changes caused by output fluctuations and those resulting from equipment performance degradation. Furthermore, current energy efficiency assessments generally use factory-fixed thresholds or manually applied static thresholds, failing to adapt to the aging patterns throughout the equipment's lifecycle and the mechanisms for eliminating operational disturbances, and lacking tiered adaptive correction capabilities. As service life increases, components wear out, and control parameters deviate, the accuracy of fixed threshold judgments continues to decline. Older equipment is prone to a large number of false alarms and missed alarms, making it impossible to distinguish between normal natural degradation and abnormal accelerated deterioration. Operating parameters such as equipment load, ambient temperature, and equipment speed fluctuate in real time, and existing technologies cannot effectively isolate operating condition disturbances. Temporary operating condition fluctuations are easily misjudged as equipment energy efficiency degradation. This leads to an inability to accurately distinguish between gradual degradation caused by normal aging and normal energy efficiency fluctuations caused by operating conditions and abnormal energy efficiency changes caused by equipment anomalies when identifying energy efficiency anomalies. As a result, the false alarm rate in the energy efficiency degradation monitoring and early warning process is relatively high. Summary of the Invention

[0003] The purpose of this invention is to provide an early warning system and method for equipment energy efficiency degradation based on multi-dimensional data fusion analysis, so as to solve the problems raised in the prior art.

[0004] To achieve the above objectives, the present invention provides the following technical solution: a method for early warning of equipment energy efficiency degradation based on multi-dimensional data fusion analysis, the method comprising the following: Set up an equipment energy efficiency data analysis mechanism to analyze and obtain equipment energy efficiency evaluation values, and set thresholds for comparative analysis to analyze whether there are any abnormalities in equipment energy efficiency; A unit output energy consumption analysis mechanism is set up to analyze the changing trend of unit output energy consumption of equipment, and further analyze the abnormal changes in energy efficiency of equipment based on the changing trend of unit output energy consumption. The threshold dynamic adjustment mechanism is set up to obtain the equipment aging impact coefficient by analyzing the equipment service life, obtain the operating condition impact coefficient by analyzing the actual operating conditions, dynamically adjust the threshold using the equipment aging impact coefficient, and correct the collected energy consumption data using the operating condition impact coefficient. The device energy consumption anomaly early warning mechanism is set up to determine the type of abnormal energy efficiency degradation that occurs in the device based on the type of instruction, and to issue an early warning for abnormal energy efficiency degradation.

[0005] Furthermore, the equipment energy efficiency data analysis mechanism is used to set an energy consumption data collection cycle, collect energy consumption data and output data in each data collection cycle, perform joint analysis on the collected energy consumption data and output data to obtain the equipment energy efficiency evaluation value, and set an equipment energy efficiency evaluation threshold. By comparing the equipment energy efficiency evaluation value with the set threshold, it is determined whether there is an abnormal increase in equipment energy consumption.

[0006] Furthermore, the collected total energy consumption data and total output data are jointly analyzed to obtain the equipment energy efficiency evaluation coefficient. An energy consumption data collection period T is set, and n cumulative total energy consumption data E and cumulative total output data W are collected within each data collection period. The collected cumulative total energy consumption data are denoted as {E1, E2, ..., En}, and the collected cumulative total output data are denoted as {W1, W2, ..., Wn}. The equipment energy consumption change rate is calculated according to the following formula: Where g represents the rate of change of equipment energy consumption, and i represents the cumulative data number of total energy consumption, i=1,2,…n; the rate of change of equipment output is calculated according to the following formula: Where h represents the equipment output change rate, j represents the cumulative data number of total output, j=1, 2, ..., n; the ratio of the equipment energy consumption change rate to the equipment output change rate is denoted as s, and s represents the equipment energy efficiency assessment value; using the ratio of the equipment energy consumption change rate to the equipment output change rate as the equipment energy efficiency assessment value can directly reflect the magnitude of the energy consumption growth rate and the output growth rate based on the size and change of the equipment energy efficiency assessment value. For example, within the data collection period, if the energy consumption change rate g=0.08 and the output change rate h=0.08, then s=1, which means that within the same time period, the energy consumption growth rate and the output growth rate are the same, indicating that the increase in energy consumption is caused by the increase in output, and that there is no abnormal growth in equipment energy efficiency; set equipment energy efficiency assessment thresholds α and β, and compare and analyze the obtained equipment energy efficiency assessment values ​​with the set thresholds to determine whether the equipment energy efficiency has declined. The analysis results are as follows: If s < α, it means that the energy consumption growth rate of the equipment is lower than the output growth rate, indicating that the equipment has excellent energy efficiency and is in a reasonable operating condition. If α≤s≤β, it means that the energy consumption growth rate of the equipment is close to the output growth rate, and the equipment energy efficiency is normal. The energy consumption change is a reasonable fluctuation caused by the output change. If s>β, it means that the energy consumption growth rate of the equipment is higher than the output growth rate. The energy consumption of the equipment increases abnormally with the increase of output. If the energy efficiency of the equipment is abnormal, the unit output energy consumption analysis mechanism will be triggered. By using equipment energy efficiency assessment values ​​to conduct preliminary analysis of energy efficiency anomalies, reasonable energy consumption disturbances caused by production load fluctuations can be identified and eliminated. This eliminates the interference of production capacity changes on energy efficiency judgment from the source, reduces the probability of misjudgment in the process of monitoring equipment energy consumption anomalies, and improves the accuracy of equipment energy efficiency anomaly monitoring.

[0007] Furthermore, the unit output energy consumption analysis mechanism is used to perform collaborative analysis on the slope and rate of change of unit output energy consumption of the equipment, set a threshold for the slope and a threshold for the rate of change, and determine the cause of abnormal changes in the energy efficiency of the equipment by comparing with the thresholds.

[0008] Furthermore, analyze the unit energy consumption d of the equipment based on the changes in energy consumption and output; calculate the unit output energy consumption of the equipment using the following formula: ; where d v This represents the energy consumption per unit output of the equipment; v represents the number of the collected cumulative data on total equipment energy consumption and total equipment output, v=2,3,…,n; the acquired energy consumption per unit output of the equipment is recorded as {d1, d2,…,d…} n-1 The slope k of the energy consumption change per unit output of the equipment is calculated using the least squares method; and the rate of change r of the energy consumption per unit output is obtained by using the ratio of the difference in energy consumption per unit output of adjacent equipment to the energy consumption per unit output of the previous equipment. The calculated rate of change of energy consumption per unit output of the equipment is denoted as {r1, r2, ..., r...}. z Set the threshold for the slope of energy consumption change per unit output of the equipment, k0, and the threshold for the rate of change of energy consumption per unit output of the equipment, η; set the energy consumption change rate per unit output, r p A comparative analysis was performed with the set threshold, where p represents the number of the rate of change in energy consumption per unit output of the equipment, p=1, 2, ... z; the analysis results are as follows: If k≤k0 and r p If ≤η, it means that the energy consumption per unit output of the equipment fluctuates steadily with only normal small disturbances. If the equipment energy efficiency is normal, then no energy efficiency abnormality warning will be triggered. If k>k0 and r p If ≤η, it indicates that the energy consumption per unit output of the equipment is gradually increasing. If it is determined that the equipment has an inherent gradual energy efficiency decline, then an energy efficiency anomaly warning f1 is triggered. If k>k0 and there exists r p If η >, it indicates that the energy consumption per unit output of the equipment has increased dramatically. If it is determined that there is a permanent decrease in energy efficiency caused by component damage, then an energy efficiency abnormality warning f2 will be triggered. If k ≤ k0 and there exists r p If >η, it indicates a sudden jump in energy consumption per unit output of the equipment. If it is determined that the equipment has experienced an emergency abnormality caused by a sudden failure, then the energy efficiency abnormality warning f3 will be triggered. The unit output energy consumption anomaly analysis has achieved the effect of distinguishing between gradual energy efficiency decline caused by equipment aging and energy efficiency anomalies caused by equipment failure, and generates corresponding energy efficiency anomaly warnings, further improving the accuracy of energy efficiency anomaly identification.

[0009] Furthermore, the threshold dynamic adjustment mechanism is used to analyze the aging impact coefficient and operating condition impact coefficient of the equipment. The aging impact coefficient of the equipment is obtained by using the service time, rated life and the proportion of time the equipment operates under overload. The temperature, load and speed of the equipment during real-time operation are coupled with the temperature, load and speed under standard operating conditions to obtain the operating condition impact coefficient. The threshold is dynamically adjusted using the equipment aging impact coefficient. The collected energy consumption data is corrected using the operating condition impact coefficient. The corrected threshold and energy consumption data are fed back to the equipment energy efficiency data analysis mechanism in real time.

[0010] Furthermore, the temperature collected under real-time operating conditions is denoted as 'a', the load as 'b', and the speed as 'c', while the temperature under standard operating conditions is denoted as 'a0', the load as 'b0', and the speed as 'c0'. A coupled analysis is performed between the real-time operating conditions (temperature, load, and speed) and the standard operating conditions (temperature, load, and speed) to obtain the operating condition influence coefficient 'q'. The operating condition influence coefficient is then calculated using the following formula: Where q represents the operating condition influence coefficient; in the calculation of the operating condition influence coefficient, when the actual operating condition meets the low load condition, that is, when When the operating condition influence coefficient q is set to 1, the operating condition influence coefficient does not actually adjust the collected energy consumption value. This is because when the actual operating condition load is less than the standard operating condition load, the operating condition will not have an additional impact on the equipment energy consumption. Therefore, the calculation method of the operating condition influence coefficient avoids incorrect adjustment of energy consumption data under low load conditions. The operating condition influence coefficient is used to correct the operating condition influence on the collected energy consumption data. The corrected energy consumption data is E' = E / q, where E' represents the corrected equipment energy consumption data. Let x be the service life of the equipment, x0 be the maximum service life of the equipment, and y be the time during which the equipment operates under high load conditions within the service life. The time during which the equipment operates under high load conditions refers to the time during which the equipment operates in a state where the operating condition influence coefficient is greater than 1, which is the operating condition coupling value. In cases where the equipment is naturally aging, the impact of high-load accelerated aging is analyzed and the equipment aging impact coefficient is calculated using the following formula: Where φ represents the equipment aging impact coefficient; when analyzing the equipment aging impact coefficient, the impact of equipment aging caused by increased service life and the impact of equipment overload operation on accelerated equipment deterioration are considered simultaneously. For example, if there are 200 days of high-load operation within a service life of x=300 days, the equipment components will experience accelerated aging due to high-load conditions such as high temperature, high load, or high speed. Furthermore, the degree of accelerated wear on equipment components differs depending on the proportion of high-load operation time, such as 200 days of high-load operation versus 20 days of high-load operation. Therefore, a high-load impact parameter is added when calculating the aging impact coefficient, further improving the accuracy of equipment energy efficiency anomaly judgment; the energy efficiency assessment threshold is dynamically adjusted using the obtained equipment aging impact coefficient, and the adjusted energy efficiency assessment threshold is α'=α×φ; β'=β×φ; the corrected threshold and energy consumption data are fed back to the equipment energy efficiency data analysis mechanism in real time.

[0011] Furthermore, the equipment energy efficiency degradation monitoring and early warning mechanism is used to issue corresponding abnormal warnings for different abnormal situations based on the analysis results of the rate of change of energy consumption per unit output and the slope of the rate of change of energy consumption per unit output. If the energy efficiency abnormality warning f1 is triggered, it is determined that the equipment has a gradual energy efficiency decline caused by component wear, scale buildup, and seal aging. In this case, a level one warning is triggered, prompting staff to carry out planned maintenance. If an energy efficiency anomaly warning f2 is triggered, it indicates that the equipment has suffered a permanent energy efficiency decline due to component damage, pipeline leakage, or seal failure. In this case, a level 2 warning is triggered, prompting staff to conduct special inspections and maintenance. If the energy efficiency abnormality warning f3 is triggered, it indicates that the equipment has experienced a sudden malfunction or that the parameters are inaccurate. This triggers a level 3 emergency warning, prompting staff to immediately conduct on-site investigation and handling.

[0012] The equipment energy efficiency degradation early warning system based on multi-dimensional data fusion analysis includes an equipment energy efficiency data analysis module, a unit output energy consumption analysis module, a threshold dynamic adjustment module, and an equipment energy consumption anomaly early warning module. The equipment energy efficiency data analysis module is used to analyze and obtain equipment energy efficiency evaluation values, and set thresholds for comparative analysis to analyze whether there are any abnormalities in equipment energy efficiency. The unit output energy consumption analysis module is used to analyze the changing trend of the unit output energy consumption of the equipment, and further analyze the abnormal changes in the energy efficiency of the equipment based on the changing trend of the unit output energy consumption. The threshold dynamic adjustment module obtains the equipment aging impact coefficient by analyzing the equipment service time, obtains the operating condition impact coefficient by analyzing the actual operating conditions, dynamically adjusts the threshold using the equipment aging impact coefficient, and corrects the collected energy consumption data using the operating condition impact coefficient. The device energy consumption anomaly early warning module is used to determine the type of abnormal energy efficiency degradation that has occurred in the device based on the type of instruction, and to issue an early warning for the abnormal energy efficiency degradation.

[0013] Compared with the prior art, the beneficial effects of the present invention are: This invention performs progressive energy efficiency analysis on equipment by setting up an equipment energy efficiency data analysis mechanism and a unit output energy consumption analysis mechanism. First, the equipment energy efficiency data analysis mechanism analyzes the rate of change in equipment energy consumption and the rate of change in output to obtain an equipment energy efficiency assessment value. This assessment value is then compared with a threshold to preliminarily determine if there are any energy efficiency anomalies. The assessment value is used to conduct a preliminary analysis of energy efficiency anomalies, identifying and eliminating reasonable energy consumption disturbances caused by production load fluctuations. This eliminates interference from production capacity changes on energy efficiency judgment at the source, reducing the probability of misjudgment during equipment energy consumption anomaly monitoring and improving the accuracy of anomaly monitoring. When an abnormal increase in equipment energy consumption with increasing output is detected, the unit output energy consumption analysis mechanism is triggered to conduct a collaborative analysis of the slope and rate of change of unit output energy consumption. Based on the comparative analysis results, the type of energy efficiency anomaly in the equipment is further determined, and further unit output energy consumption anomaly analysis is performed. This invention achieves the effect of distinguishing between gradual energy efficiency degradation caused by equipment aging and energy efficiency anomalies caused by equipment failure, and generates corresponding energy efficiency anomaly warnings, further improving the accuracy of identifying energy efficiency anomalies. Furthermore, the invention sets up a dynamic threshold adjustment mechanism to dynamically adjust the threshold using the equipment aging influence coefficient, and uses the operating condition influence coefficient to correct the collected energy consumption data. The adjusted data is then used for energy efficiency change analysis, taking into account both natural energy efficiency degradation caused by equipment aging and excess energy consumption caused by operating condition changes, further improving the accuracy of identifying normal energy efficiency degradation and abnormal energy efficiency changes. Moreover, when performing equipment aging influence coefficient analysis, the invention also considers the impact of increased equipment service life on equipment aging and the impact of equipment overload operation on accelerated equipment degradation, further improving the accuracy of equipment energy efficiency anomaly judgment. This invention solves the problems of traditional energy efficiency analysis being susceptible to operating condition disturbances, unable to distinguish between natural aging and fault degradation, and having a high false alarm and false negative rate. Attached Figure Description

[0014] Figure 1 This is a schematic diagram of the method flow for the device energy efficiency degradation early warning method based on multi-dimensional data fusion analysis according to the present invention. Detailed Implementation

[0015] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0016] like Figure 1 As shown, the present invention provides a technical solution: a method for early warning of equipment energy efficiency degradation based on multi-dimensional data fusion analysis, the method comprising the following: Set up an equipment energy efficiency data analysis mechanism to analyze and obtain equipment energy efficiency evaluation values, and set thresholds for comparative analysis to analyze whether there are any abnormalities in equipment energy efficiency; A unit output energy consumption analysis mechanism is set up to analyze the changing trend of unit output energy consumption of equipment, and further analyze the abnormal changes in energy efficiency of equipment based on the changing trend of unit output energy consumption. The threshold dynamic adjustment mechanism is set up to obtain the equipment aging impact coefficient by analyzing the equipment service life, obtain the operating condition impact coefficient by analyzing the actual operating conditions, dynamically adjust the threshold using the equipment aging impact coefficient, and correct the collected energy consumption data using the operating condition impact coefficient. The device energy consumption anomaly early warning mechanism is set up to determine the type of abnormal energy efficiency degradation that occurs in the device based on the type of instruction, and to issue an early warning for abnormal energy efficiency degradation.

[0017] The equipment energy efficiency data analysis mechanism is used to set the energy consumption data collection cycle. In each data collection cycle, energy consumption data and output data are collected. The collected energy consumption data and output data are jointly analyzed to obtain the equipment energy efficiency assessment value. The equipment energy efficiency assessment threshold is set. By comparing the equipment energy efficiency assessment value with the set threshold, it is determined whether there is an abnormal increase in equipment energy consumption.

[0018] The collected total energy consumption data and total output data are jointly analyzed to obtain the equipment energy efficiency evaluation coefficient. An energy consumption data collection period T is set, and n cumulative total energy consumption data E and cumulative total output data W are collected within each data collection period. The collected cumulative total energy consumption data are denoted as {E1, E2, ..., En}, and the collected cumulative total output data are denoted as {W1, W2, ..., Wn}. The equipment energy consumption change rate is calculated using the following formula: Where g represents the rate of change of equipment energy consumption, and i represents the cumulative data number of total energy consumption, i=1,2,…n; the rate of change of equipment output is calculated according to the following formula: Where h represents the equipment output change rate, j represents the cumulative data number of total output, j=1, 2, ..., n; the ratio of equipment energy consumption change rate to equipment output change rate is denoted as s, s represents the equipment energy efficiency assessment value, equipment energy efficiency assessment thresholds α and β are set, and the obtained equipment energy efficiency assessment value is compared with the set thresholds to determine whether the equipment energy efficiency has declined. The analysis results are as follows: If s < α, it means that the energy consumption growth rate of the equipment is lower than the output growth rate, indicating that the equipment has excellent energy efficiency and is in a reasonable operating condition. If α≤s≤β, it means that the energy consumption growth rate of the equipment is close to the output growth rate, and the equipment energy efficiency is normal. The energy consumption change is a reasonable fluctuation caused by the output change. If s>β, it means that the energy consumption growth rate of the equipment is higher than the output growth rate. The energy consumption of the equipment increases abnormally with the increase of output. If the energy efficiency of the equipment is abnormal, the unit output energy consumption analysis mechanism will be triggered.

[0019] The unit output energy consumption analysis mechanism is used to perform collaborative analysis on the slope and rate of change of unit output energy consumption of equipment. It sets thresholds for the slope and rate of change, and determines the cause of abnormal changes in equipment energy efficiency by comparing the results with the thresholds.

[0020] Analyze the unit energy consumption (d) of the equipment based on the changes in energy consumption and output; calculate the unit output energy consumption of the equipment using the following formula: ; where d v This represents the energy consumption per unit output of the equipment; v represents the number of the collected cumulative data on total equipment energy consumption and total equipment output, v=2,3,…,n; the acquired energy consumption per unit output of the equipment is recorded as {d1, d2,…,d…} n-1 The slope k of the energy consumption change per unit output of the equipment is calculated using the least squares method; and the rate of change r of the energy consumption per unit output is obtained by using the ratio of the difference in energy consumption per unit output of adjacent equipment to the energy consumption per unit output of the previous equipment. The calculated rate of change of energy consumption per unit output of the equipment is denoted as {r1, r2, ..., r...}. z Set the threshold for the slope of energy consumption change per unit output of the equipment, k0, and the threshold for the rate of change of energy consumption per unit output of the equipment, η; set the energy consumption change rate per unit output, r p A comparative analysis was performed with the set threshold, where p represents the number of the rate of change in energy consumption per unit output of the equipment, p=1, 2, ... z; the analysis results are as follows: If k≤k0 and r p If ≤η, it means that the energy consumption per unit output of the equipment fluctuates steadily with only normal small disturbances. If the equipment energy efficiency is normal, then no energy efficiency abnormality warning will be triggered. If k>k0 and r pIf ≤η, it indicates that the energy consumption per unit output of the equipment is gradually increasing. If it is determined that the equipment has an inherent gradual energy efficiency decline, then an energy efficiency anomaly warning f1 is triggered. If k>k0 and there exists r p If η >, it indicates that the energy consumption per unit output of the equipment has increased dramatically. If it is determined that there is a permanent decrease in energy efficiency caused by component damage, then an energy efficiency abnormality warning f2 will be triggered. If k ≤ k0 and there exists r p If >η, it indicates a sudden jump in energy consumption per unit output of the equipment. If it is determined that the equipment has experienced an emergency abnormality caused by a sudden failure, then the energy efficiency abnormality warning f3 is triggered.

[0021] The threshold dynamic adjustment mechanism is used to analyze the aging impact coefficient and operating condition impact coefficient of equipment. It obtains the aging impact coefficient of equipment by using the service time, rated life and the proportion of time the equipment operates under overload. It couples the temperature, load and speed of the equipment under real-time operating conditions with the temperature, load and speed under standard operating conditions to obtain the operating condition impact coefficient. The threshold is dynamically adjusted using the equipment aging impact coefficient. The collected energy consumption data is corrected using the operating condition impact coefficient. The corrected threshold and energy consumption data are fed back to the equipment energy efficiency data analysis mechanism in real time.

[0022] Let the temperature collected under real-time operating conditions be denoted as 'a', the load as 'b', and the speed as 'c', and let the temperature under standard operating conditions be denoted as 'a0', the load as 'b0', and the speed as 'c0'. A coupled analysis is performed between the real-time operating conditions (temperature, load, and speed) and the standard operating conditions (temperature, load, and speed) to obtain the operating condition influence coefficient 'q'. The operating condition influence coefficient is then calculated using the following formula: Where q represents the operating condition influence coefficient; the collected energy consumption data is corrected for operating condition influence using the operating condition influence coefficient, and the corrected energy consumption data is E'=E / q; where E' represents the corrected equipment energy consumption data; Let x be the equipment's service life, x0 be the equipment's maximum service life, and y be the time the equipment operates under high load conditions within its service life. Then, we will analyze and calculate the equipment aging impact coefficient using the following formula: (Analysis of the impact of natural aging and the impact of accelerated aging under high load are then set up.) Where φ represents the equipment aging impact coefficient; the energy efficiency assessment threshold is dynamically adjusted using the obtained equipment aging impact coefficient, and the adjusted energy efficiency assessment threshold is α'=α×φ; β'=β×φ; the corrected threshold and energy consumption data are fed back to the equipment energy efficiency data analysis mechanism in real time.

[0023] The equipment energy efficiency degradation monitoring and early warning mechanism is used to issue corresponding abnormal warnings for different abnormal situations based on the analysis results of the rate of change of energy consumption per unit output and the slope of the rate of change of energy consumption per unit output. If the energy efficiency abnormality warning f1 is triggered, it is determined that the equipment has a gradual energy efficiency decline caused by component wear, scale buildup, and seal aging. In this case, a level one warning is triggered, prompting staff to carry out planned maintenance. If an energy efficiency anomaly warning f2 is triggered, it indicates that the equipment has suffered a permanent energy efficiency decline due to component damage, pipeline leakage, or seal failure. In this case, a level 2 warning is triggered, prompting staff to conduct special inspections and maintenance. If the energy efficiency abnormality warning f3 is triggered, it indicates that the equipment has experienced a sudden malfunction or that the parameters are inaccurate. This triggers a level 3 emergency warning, prompting staff to immediately conduct on-site investigation and handling.

[0024] The equipment energy efficiency degradation early warning system based on multi-dimensional data fusion analysis includes an equipment energy efficiency data analysis module, a unit output energy consumption analysis module, a threshold dynamic adjustment module, and an equipment energy consumption anomaly early warning module. The equipment energy efficiency data analysis module is used to analyze and obtain equipment energy efficiency evaluation values, and set thresholds for comparative analysis to analyze whether there are any abnormalities in equipment energy efficiency. The unit output energy consumption analysis module is used to analyze the changing trend of the unit output energy consumption of the equipment, and further analyze the abnormal changes in the energy efficiency of the equipment based on the changing trend of the unit output energy consumption. The threshold dynamic adjustment module obtains the equipment aging impact coefficient by analyzing the equipment service time, obtains the operating condition impact coefficient by analyzing the actual operating conditions, dynamically adjusts the threshold using the equipment aging impact coefficient, and corrects the collected energy consumption data using the operating condition impact coefficient. The equipment energy consumption anomaly early warning module is used to determine the type of abnormal energy efficiency degradation that has occurred in the equipment based on the type of instruction, and to issue an early warning for the abnormal energy efficiency degradation.

[0025] Example 1: The collected total energy consumption data and total output data are jointly analyzed to obtain the equipment energy efficiency evaluation coefficient. An energy consumption data collection period T is set, and five cumulative total energy consumption data points E and cumulative total output data points W are collected within each data collection period. The collected cumulative total energy consumption data is denoted as {1100, 1115, 1128, 1142, 1155}, and the collected cumulative total output data is denoted as {8600, 8720, 8810, 8900, 8990}. The equipment energy consumption change rate g = 0.049 is calculated, and the equipment output change rate h = 0.044 is calculated. The ratio of the equipment energy consumption change rate to the equipment output change rate is denoted as s, s = 1.11. Equipment energy efficiency evaluation thresholds α = 0.9 and β = 1.1 are set. The obtained equipment energy efficiency evaluation values ​​are compared with the set thresholds to determine whether equipment energy efficiency has declined. The analysis results are as follows: If s > β, it means that the energy consumption growth rate of the equipment is higher than the output growth rate. The energy consumption of the equipment increases abnormally with the increase of output. If the energy efficiency of the equipment is judged to be abnormal, the unit output energy consumption analysis mechanism will be triggered.

[0026] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A method for early warning of equipment energy efficiency degradation based on multi-dimensional data fusion analysis, characterized in that: The method includes the following: Set up an equipment energy efficiency data analysis mechanism to analyze and obtain equipment energy efficiency evaluation values, and set thresholds for comparative analysis to analyze whether there are any abnormalities in equipment energy efficiency; A unit output energy consumption analysis mechanism is set up to analyze the changing trend of unit output energy consumption of equipment, and further analyze the abnormal changes in energy efficiency of equipment based on the changing trend of unit output energy consumption. The threshold dynamic adjustment mechanism is set up to obtain the equipment aging impact coefficient by analyzing the equipment service life, obtain the operating condition impact coefficient by analyzing the actual operating conditions, dynamically adjust the threshold using the equipment aging impact coefficient, and correct the collected energy consumption data using the operating condition impact coefficient. The device energy consumption anomaly early warning mechanism is set up to determine the type of abnormal energy efficiency degradation that occurs in the device based on the type of instruction, and to issue an early warning for abnormal energy efficiency degradation.

2. The equipment energy efficiency degradation early warning method based on multi-dimensional data fusion analysis according to claim 1, characterized in that: The equipment energy efficiency data analysis mechanism is used to set the energy consumption data collection cycle, collect energy consumption data and output data in each data collection cycle, perform joint analysis on the collected energy consumption data and output data to obtain the equipment energy efficiency evaluation value, and set the equipment energy efficiency evaluation threshold. By comparing the equipment energy efficiency evaluation value with the set threshold, it is determined whether there is an abnormal increase in equipment energy consumption.

3. The equipment energy efficiency degradation early warning method based on multi-dimensional data fusion analysis according to claim 2, characterized in that: The total energy consumption data and total output data collected are jointly analyzed to obtain the equipment energy efficiency evaluation coefficient. The energy consumption data collection cycle T is set, and n total energy consumption cumulative data E and total output cumulative data W are collected in each data collection cycle. The total energy consumption data collected is recorded as {E1, E2, ..., En}, and the total output data collected is recorded as {W1, W2, ..., Wn}. Calculate the equipment energy consumption change rate using the following formula: ; Where g represents the rate of change of equipment energy consumption, and i represents the cumulative data number of total energy consumption, i=1,2,…n; Calculate the rate of change in equipment output using the following formula: Where h represents the equipment output change rate, j represents the cumulative data number of total output, j=1, 2, ..., n; the ratio of equipment energy consumption change rate to equipment output change rate is denoted as s, s represents the equipment energy efficiency assessment value, equipment energy efficiency assessment thresholds α and β are set, and the obtained equipment energy efficiency assessment value is compared with the set thresholds to determine whether the equipment energy efficiency has declined. The analysis results are as follows: If s < α, it means that the energy consumption growth rate of the equipment is lower than the output growth rate, indicating that the equipment has excellent energy efficiency and is in a reasonable operating condition. If α≤s≤β, it means that the energy consumption growth rate of the equipment is close to the output growth rate, and the equipment energy efficiency is normal. The energy consumption change is a reasonable fluctuation caused by the output change. If s>β, it means that the energy consumption growth rate of the equipment is higher than the output growth rate. The energy consumption of the equipment increases abnormally with the increase of output. If the energy efficiency of the equipment is abnormal, the unit output energy consumption analysis mechanism will be triggered.

4. The equipment energy efficiency degradation early warning method based on multi-dimensional data fusion analysis according to claim 1, characterized in that: The unit output energy consumption analysis mechanism is used to perform collaborative analysis on the slope and rate of change of unit output energy consumption of equipment. It sets thresholds for the slope and rate of change, and determines the cause of abnormal changes in equipment energy efficiency by comparing the results with the thresholds.

5. The equipment energy efficiency degradation early warning method based on multi-dimensional data fusion analysis according to claim 4, characterized in that: Analyze the unit energy consumption (d) of the equipment based on changes in energy consumption and output; Calculate the energy consumption per unit output of the equipment using the following formula: ; where d v This represents the energy consumption per unit output of the equipment; v represents the number of the collected cumulative data on total equipment energy consumption and total equipment output, v=2,3,…,n; the acquired energy consumption per unit output of the equipment is recorded as {d1, d2,…,d…} n-1 The slope k of the energy consumption change per unit output of the equipment is calculated using the least squares method; and the rate of change r of the energy consumption per unit output is obtained by using the ratio of the difference in energy consumption per unit output of adjacent equipment to the energy consumption per unit output of the previous equipment. The calculated rate of change of energy consumption per unit output of the equipment is denoted as {r1, r2, ..., r...}. z Set the threshold for the slope of energy consumption change per unit output of the equipment, k0, and the threshold for the rate of change of energy consumption per unit output of the equipment, η; set the energy consumption change rate per unit output, r p A comparative analysis was performed with the set threshold, where p represents the number of the rate of change in energy consumption per unit output of the equipment, p=1, 2, ... z; the analysis results are as follows: If k≤k0 and r p If ≤η, it means that the energy consumption per unit output of the equipment fluctuates steadily with only normal small disturbances. If the equipment energy efficiency is normal, then no energy efficiency abnormality warning will be triggered. If k>k0 and r p If ≤η, it indicates that the energy consumption per unit output of the equipment is gradually increasing. If it is determined that the equipment has an inherent gradual energy efficiency decline, then an energy efficiency anomaly warning f1 is triggered. If k>k0 and there exists r p If η >, it indicates that the energy consumption per unit output of the equipment has increased dramatically. If it is determined that there is a permanent decrease in energy efficiency caused by component damage, then an energy efficiency abnormality warning f2 will be triggered. If k ≤ k0 and there exists r p If >η, it indicates a sudden jump in energy consumption per unit output of the equipment. If it is determined that the equipment has experienced an emergency abnormality caused by a sudden failure, then the energy efficiency abnormality warning f3 is triggered.

6. The equipment energy efficiency degradation early warning method based on multi-dimensional data fusion analysis according to claim 1, characterized in that: The threshold dynamic adjustment mechanism is used to analyze the aging impact coefficient and operating condition impact coefficient of the equipment. It obtains the aging impact coefficient of the equipment by using the equipment's service time, rated life, and the proportion of time the equipment operates under overload. It couples the temperature, load, and speed of the equipment during real-time operation with the temperature, load, and speed under standard operating conditions to obtain the operating condition impact coefficient. It uses the equipment aging impact coefficient to dynamically adjust the threshold and uses the operating condition impact coefficient to correct the collected energy consumption data. The corrected threshold and energy consumption data are fed back to the equipment energy efficiency data analysis mechanism in real time.

7. The equipment energy efficiency degradation early warning method based on multi-dimensional data fusion analysis according to claim 6, characterized in that: Let the temperature collected under real-time operating conditions be denoted as 'a', the load as 'b', and the speed as 'c', and let the temperature under standard operating conditions be denoted as 'a0', the load as 'b0', and the speed as 'c0'. A coupled analysis is performed between the real-time operating conditions (temperature, load, and speed) and the standard operating conditions (temperature, load, and speed) to obtain the operating condition influence coefficient 'q'. The operating condition influence coefficient is then calculated using the following formula: Where q represents the operating condition influence coefficient; the collected energy consumption data is corrected for operating condition influence using the operating condition influence coefficient, and the corrected energy consumption data is E'=E / q; where E' represents the corrected equipment energy consumption data; Let x be the equipment's service life, x0 be the equipment's maximum service life, and y be the time the equipment operates under high load conditions within its service life. Then, we will analyze and calculate the equipment aging impact coefficient using the following formula: (Analysis of the impact of natural aging and the impact of accelerated aging under high load are then set up.) Where φ represents the equipment aging impact coefficient; the energy efficiency assessment threshold is dynamically adjusted using the obtained equipment aging impact coefficient, and the adjusted energy efficiency assessment threshold is α'=α×φ; β'=β×φ; the corrected threshold and energy consumption data are fed back to the equipment energy efficiency data analysis mechanism in real time.

8. The equipment energy efficiency degradation early warning method based on multi-dimensional data fusion analysis according to claim 5, characterized in that: The equipment energy efficiency degradation monitoring and early warning mechanism is used to issue corresponding abnormal warnings for different abnormal situations based on the analysis results of the change rate and slope of the change rate of energy consumption per unit output of the equipment. If the energy efficiency abnormality warning f1 is triggered, it is determined that the equipment has a gradual energy efficiency decline caused by component wear, scale buildup, and seal aging. In this case, a level one warning is triggered, prompting staff to carry out planned maintenance. If an energy efficiency anomaly warning f2 is triggered, it indicates that the equipment has suffered a permanent energy efficiency decline due to component damage, pipeline leakage, or seal failure. In this case, a level 2 warning is triggered, prompting staff to conduct special inspections and maintenance. If the energy efficiency abnormality warning f3 is triggered, it indicates that the equipment has experienced a sudden malfunction or that the parameters are inaccurate. This triggers a level 3 emergency warning, prompting staff to immediately conduct on-site investigation and handling.

9. A device energy efficiency degradation early warning system based on multidimensional data fusion analysis, applied to the device energy efficiency degradation early warning method based on multidimensional data fusion analysis as described in claims 1-8, characterized in that: The system includes an equipment energy efficiency data analysis module, a unit output energy consumption analysis module, a threshold dynamic adjustment module, and an equipment energy consumption anomaly early warning module; The equipment energy efficiency data analysis module is used to analyze and obtain equipment energy efficiency evaluation values, and set thresholds for comparative analysis to analyze whether there are any abnormalities in equipment energy efficiency. The unit output energy consumption analysis module is used to analyze the changing trend of the unit output energy consumption of the equipment, and further analyze the abnormal changes in the energy efficiency of the equipment based on the changing trend of the unit output energy consumption. The threshold dynamic adjustment module obtains the equipment aging impact coefficient by analyzing the equipment service time, obtains the operating condition impact coefficient by analyzing the actual operating conditions, dynamically adjusts the threshold using the equipment aging impact coefficient, and corrects the collected energy consumption data using the operating condition impact coefficient. The device energy consumption anomaly early warning module is used to determine the type of abnormal energy efficiency degradation that has occurred in the device based on the type of instruction, and to issue an early warning for the abnormal energy efficiency degradation.

Images