Copper-based material processing monitoring system based on multi-source heterogeneous data

Abstract

The invention discloses a copper-based material processing monitoring system based on multi-source heterogeneous data, relates to the technical field of copper-based material monitoring, and solves the problems that in the prior art, only parameters of a rolling mill are monitored, and many factors such as environmental factors and equipment aging actually influencing the hot rolling process of a copper-based material are not considered. The monitoring result is not comprehensive, and the overall condition of the hot rolling process cannot be accurately evaluated. According to the method, to-be-detected data in the hot rolling process are obtained in real time; calculating a first evaluation coefficient based on the rolling mill operation data; calculating a second evaluation coefficient based on the aging data; calculating a third evaluation coefficient based on the environment data; based on the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient, a hot rolling early warning evaluation coefficient is obtained through calculation; and whether the early warning information is sent or not is judged through the hot rolling early warning evaluation coefficient and a preset threshold value, and the technical problem is solved.

Description

Technical Field

[0001] The invention belongs to the field of copper-based material monitoring, and in particular is a copper-based material processing monitoring system based on multi-source heterogeneous data. Background Art

[0002] With the rapid development of materials science and information technology, copper-based materials have been widely used in aerospace, automobile manufacturing, electronic communications and other fields due to their excellent electrical conductivity, thermal conductivity, corrosion resistance and good processing performance. The processing of copper-based materials is a complex and sophisticated process, among which hot rolling is a key link in the processing of copper-based materials. It significantly improves the organizational properties of materials through the combined effects of high temperature and rolling force, including grain refinement, elimination of casting defects, and improvement of plasticity and deformation capacity of materials. These improvements directly improve the mechanical properties of copper materials, such as strength, toughness and processing properties, and provide a solid foundation for subsequent processing and the performance of the final product.

[0003] Hot rolling process monitoring is crucial for the copper-based material processing industry. It not only ensures the stability of product quality and the improvement of production efficiency, but also reduces energy consumption and costs by optimizing process parameters, while improving production safety and providing strong support for process improvement and innovation. The existing methods for monitoring the hot rolling process mainly monitor the operating parameters of the rolling mill, such as temperature, rolling pressure, and rolling speed; by real-time collection of key parameters such as temperature, rolling force, and speed during the hot rolling process, and using data analysis and processing technology, the hot rolling process is monitored and warned. However, there are many factors that actually affect the hot rolling process of copper-based materials, such as environmental factors and equipment aging. The existing technology only monitors the parameters of the rolling mill itself, and the monitoring results are obviously not comprehensive enough to accurately evaluate the overall status of the hot rolling process.

[0004] Therefore, the present invention solves the above-mentioned problems by proposing a copper-based material processing monitoring system based on multi-source heterogeneous data. Summary of the invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes a copper-based material processing monitoring system based on multi-source heterogeneous data, which is used to solve the technical problem that the prior art only monitors the parameters of the rolling mill itself, but does not take into account that there are many factors that actually affect the hot rolling process of copper-based materials, such as environmental factors and equipment aging, resulting in the monitoring results being not comprehensive enough and unable to accurately evaluate the overall condition of the hot rolling process.

[0006] To achieve the above-mentioned object, a first aspect of the present invention provides a copper-based material processing monitoring system based on multi-source heterogeneous data, comprising: a data acquisition module, a data analysis module, a data early warning module and an early warning processing module;

[0007] Data acquisition module: used to obtain the data to be tested in the hot rolling process in real time;

[0008] Data analysis module: calculates the hot rolling early warning evaluation coefficient based on the data to be tested;

[0009] Data warning module: determines whether to send warning information based on the hot rolling warning evaluation coefficient and the preset threshold; if yes, sends the warning information to the warning processing module; if no, continues to monitor and judge;

[0010] Early warning processing module: used to receive early warning information and process the hot rolling process based on the early warning information.

[0011] Preferably, the data analysis module communicates with and / or is electrically connected to the data acquisition module and the data early warning module respectively; the early warning processing module communicates with and / or is electrically connected to the data early warning module.

[0012] Preferably, the real-time acquisition of the data to be detected during the hot rolling process includes:

[0013] The data to be tested in the hot rolling process are collected in real time through data acquisition equipment; the data to be tested include: mill operation data, environmental data and mill aging data; the mill operation data include: the temperature of the copper-based material when it leaves the mill, the rolling pressure and the rolling speed; the environmental data include: the ambient temperature, the ambient humidity and the dust concentration in the environment; the aging data include: the vibration frequency of the motor housing and the sound pressure level of the sound.

[0014] It should be noted that in a rolling mill, the transmission system refers to the mechanical system used to drive and control the movement of the rolling mill spindle, rolls and other key components. The aging of the transmission system will lead to increased wear of gears, bearings and other components, and thus generate additional vibrations and abnormal noise.

[0015] The present invention collects the rolling mill operation data, environmental data and rolling mill aging data in real time during the hot rolling process, which is beneficial to comprehensively monitor the hot rolling process and more accurately reflect the overall state of the hot rolling process.

[0016] Preferably, the hot rolling early warning evaluation coefficient is calculated based on the data to be detected, including:

[0017] S1: Calculate and obtain a first evaluation coefficient based on rolling mill operation data;

[0018] S2: Calculate a second evaluation coefficient based on the aging data;

[0019] S3: Calculate a third evaluation coefficient based on environmental data;

[0020] S4: Calculate the hot rolling warning evaluation coefficient based on the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient.

[0021] Preferably, the first evaluation coefficient is calculated based on the rolling mill operation data, comprising:

[0022] The temperature of the copper-based material when it leaves the rolling mill is marked as T, the rolling pressure is marked as F, and the rolling speed is marked as V;

[0023] By formula:

[0024] P1=A×exp(|T-ZT| / ZT)+B×exp(|F-ZF| / ZF)+C×exp(|V-ZV| / ZV);

[0025] The first evaluation coefficient is calculated; wherein P1 is the first evaluation coefficient, A, B, and C are proportional coefficients, and 1>A>0, 1>B>0, 1>C>0, ZT is the standard temperature, ZF is the standard rolling pressure, and ZV is the standard rolling speed.

[0026] It should be noted that the standard temperature refers to the preset temperature when the copper-based material leaves the rolling mill under normal circumstances; the standard rolling pressure refers to the preset rolling pressure under normal circumstances; and the standard rolling speed refers to the preset rolling speed under normal circumstances.

[0027] Preferably, the calculating the second evaluation coefficient based on the aging data includes:

[0028] The vibration frequency of the motor housing is marked as M, and the sound pressure level of the sound is marked as Y;

[0029] By formula:

[0030] P2=D×exp[ln(M) / (ln(M)+1)]+E×tanh(Y)×ln(Y+1);

[0031] The second evaluation coefficient is calculated; wherein, P2 is the second evaluation coefficient, D and E are proportional coefficients, and 1>D>0, 1>E>0, tanh(*) is the hyperbolic tangent function, and ln(*) is the logarithmic function with the natural number e as the base.

[0032] It should be noted that as the use time increases, transmission parts such as gears and bearings will wear out, resulting in an increase in the clearance between parts, which will generate additional vibrations. The vibrations will affect the stability of the material when it passes through the rolling mill, causing defects such as ripples and scratches on the surface of the material. The vibrations may also cause fatigue damage to equipment parts, affecting the stability and service life of the equipment.

[0033] As transmission components wear, the clearance between gears and bearings increases, resulting in a reduction in contact area and abnormal noise. Abnormal noise is an early sign of transmission system aging. If not handled in time, it will lead to a decline in equipment performance.

[0034] Preferably, the calculating the third evaluation coefficient based on the environmental data includes:

[0035] The ambient temperature is marked as W, the ambient humidity is marked as S, and the dust concentration in the environment is marked as N;

[0036] By formula:

[0037] P3=[ln(W^J×S^K×N^L+1)] / exp(J+K+L);

[0038] The third evaluation coefficient is calculated; wherein P3 is the third evaluation coefficient, J, K, and L are proportional coefficients, and 1>J>0, 1>K>0, 1>L>0, and J+K+L>1.

[0039] It should be noted that excessively high ambient temperature will lead to poor heat dissipation of the equipment, causing the equipment to overheat, thereby affecting the stability and service life of the equipment; in a high humidity environment, the surface of copper-based materials is easily adsorbed with moisture, causing surface oxidation, affecting the surface quality of the material and the lubrication effect during subsequent processing. At the same time, high humidity may cause the electrical part of the equipment to become damp, affecting the stability and safety of the equipment; dust will adhere to the surface of the material, affecting the surface quality, causing defects such as scratches or spots during processing, and dust may enter the interior of the equipment, causing accelerated wear of the equipment and even clogging the filtration system, affecting the normal operation of the equipment.

[0040] Preferably, the hot rolling early warning evaluation coefficient is calculated based on the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient, including:

[0041] The hot rolling early warning assessment coefficient is calculated by weighted average method, which is:

[0042] P = Q × P1 + R × P2 + G × P3;

[0043] Among them, P is the hot rolling early warning evaluation coefficient, Q, R, and G are weight coefficients, and Q+R+G=1.

[0044] Preferably, the determining whether to send warning information based on the hot rolling warning evaluation coefficient and a preset threshold value includes:

[0045] Determine whether the hot rolling warning evaluation coefficient is greater than the preset threshold; if yes, generate warning information and send it to the warning processing module; if no, continue to monitor and judge; wherein the preset threshold is set by experience based on the actual scenario.

[0046] The present invention obtains the data to be detected in the hot rolling process in real time; calculates a first evaluation coefficient based on the rolling mill operation data; calculates a second evaluation coefficient based on the aging data; calculates a third evaluation coefficient based on the environmental data; and calculates a hot rolling early warning evaluation coefficient based on the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient; determines whether to send an early warning message based on the hot rolling early warning evaluation coefficient and a preset threshold value, thereby solving the problem that the prior art does not take into account the factors that actually affect the hot rolling process of copper-based materials, as well as environmental factors and equipment aging, resulting in an incomplete monitoring result and an inability to accurately evaluate the overall condition of the hot rolling process.

[0047] Preferably, the processing of the hot rolling process based on the early warning information includes:

[0048] The warning levels are classified into different levels, and the hot rolling process is processed based on the warning levels;

[0049] S1: After receiving the warning information, extract the hot rolling warning evaluation coefficient corresponding to the warning information;

[0050] S2: Determine whether the hot rolling warning evaluation coefficient is greater than the preset advanced warning threshold; if yes, the warning level is advanced warning; if not, the warning level is ordinary warning; wherein, the preset advanced warning threshold is set according to the actual mill fault maintenance requirements.

[0051] The present invention divides the warning degrees into levels and processes the hot rolling process based on the warning levels, which is beneficial to reducing the safety risks and equipment damage risks in the production process.

[0052] Compared with the prior art, the present invention has the following beneficial effects:

[0053] 1. The prior art only monitors the parameters of the rolling mill itself, without taking into account that there are many factors that actually affect the hot rolling process of copper-based materials, such as environmental factors and equipment aging, resulting in incomplete monitoring results and inability to accurately evaluate the overall status of the hot rolling process. The present invention obtains the data to be detected in the hot rolling process in real time; calculates a first evaluation coefficient based on the rolling mill operation data; calculates a second evaluation coefficient based on aging data; calculates a third evaluation coefficient based on environmental data; and calculates a hot rolling early warning evaluation coefficient based on the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient; determines whether to send an early warning message based on the hot rolling early warning evaluation coefficient and a preset threshold, thereby solving the problem of incomplete monitoring and low accuracy of the hot rolling process in the prior art.

[0054] 2. The present invention classifies the warning degree into levels and processes the hot rolling process based on the warning level; determines whether the hot rolling warning evaluation coefficient is greater than a preset advanced warning threshold; if so, the warning level is a high-level warning; if not, the warning level is a common warning; by determining the warning level, the corresponding emergency response procedure is quickly initiated, and measures are taken in time to avoid or mitigate possible failures; and through a graded response mechanism, the safety risks and equipment damage risks in the production process can be effectively reduced, and the continuity and stability of production can be guaranteed, while helping to reduce unnecessary downtime and maintenance costs, and also avoiding the waste of resources caused by excessive maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0056] Figure 1 A schematic diagram of a system module according to an embodiment of the present invention;

[0057] Figure 2 A schematic diagram of a specific process of an embodiment of the present invention;

[0058] Figure 3 Schematic diagram of a method for calculating a hot rolling early warning evaluation coefficient according to an embodiment of the present invention. DETAILED DESCRIPTION

[0059] The technical solution of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than 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.

[0060] See also Figure 1-Figure 2 , the first aspect of the present invention provides a copper-based material processing monitoring system based on multi-source heterogeneous data, including: a data acquisition module, a data analysis module, a data early warning module and an early warning processing module;

[0061] Data acquisition module: used to obtain the data to be tested in the hot rolling process in real time;

[0062] Data analysis module: calculates the hot rolling early warning evaluation coefficient based on the data to be tested;

[0063] Real-time acquisition of data to be tested during hot rolling, including:

[0064] The data to be tested in the hot rolling process are collected in real time through data acquisition equipment; the data to be tested include: mill operation data, environmental data and mill aging data; the mill operation data include: the temperature of the copper-based material when it leaves the mill, the rolling pressure and the rolling speed; the environmental data include: the ambient temperature, the ambient humidity and the dust concentration in the environment; the aging data include: the vibration frequency of the motor housing and the sound pressure level of the sound.

[0065] See also Figure 3 , the hot rolling early warning evaluation coefficient is calculated based on the data to be tested, including:

[0066] S1: Calculate and obtain a first evaluation coefficient based on rolling mill operation data;

[0067] S2: Calculate a second evaluation coefficient based on the aging data;

[0068] S3: Calculate a third evaluation coefficient based on environmental data;

[0069] S4: Calculate the hot rolling warning evaluation coefficient based on the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient.

[0070] The first evaluation coefficient is calculated based on the rolling mill operation data, including:

[0071] The temperature of the copper-based material when it leaves the rolling mill is marked as T, the rolling pressure is marked as F, and the rolling speed is marked as V;

[0072] By formula:

[0073] P1=A×exp(|T-ZT| / ZT)+B×exp(|F-ZF| / ZF)+C×exp(|V-ZV| / ZV);

[0074] The first evaluation coefficient is calculated; wherein P1 is the first evaluation coefficient, A, B, and C are proportional coefficients, and 1>A>0, 1>B>0, 1>C>0, ZT is the standard temperature, ZF is the standard rolling pressure, and ZV is the standard rolling speed.

[0075] The second evaluation coefficient is calculated based on the aging data, including:

[0076] The vibration frequency of the motor housing is marked as M, and the sound pressure level of the sound is marked as Y;

[0077] By formula:

[0078] P2=D×exp[ln(M) / (ln(M)+1)]+E×tanh(Y)×ln(Y+1);

[0079] The second evaluation coefficient is calculated; wherein, P2 is the second evaluation coefficient, D and E are proportional coefficients, and 1>D>0, 1>E>0, tanh(*) is the hyperbolic tangent function, and ln(*) is the logarithmic function with the natural number e as the base.

[0080] The third evaluation coefficient is calculated based on the environmental data, including:

[0081] The ambient temperature is marked as W, the ambient humidity is marked as S, and the dust concentration in the environment is marked as N;

[0082] By formula:

[0083] P3=[ln(W^J×S^K×N^L+1)] / exp(J+K+L);

[0084] The third evaluation coefficient is calculated; wherein P3 is the third evaluation coefficient, J, K, and L are proportional coefficients, and 1>J>0, 1>K>0, 1>L>0, and J+K+L>1.

[0085] The hot rolling early warning evaluation coefficient is calculated based on the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient, including:

[0086] The hot rolling early warning assessment coefficient is calculated by weighted average method, which is:

[0087] P = Q × P1 + R × P2 + G × P3;

[0088] Among them, P is the hot rolling early warning evaluation coefficient, Q, R, and G are weight coefficients, and Q+R+G=1.

[0089] For example, suppose you are monitoring data from a copper-based material hot rolling process, as follows:

[0090] Data acquisition module;

[0091] 1. Rolling mill operation data:

[0092] The temperature T of the copper-based material when it leaves the rolling mill: The temperature of the copper-based material when it leaves the rolling mill is collected by a temperature sensor, which is assumed to be 450°C;

[0093] Rolling pressure F: The rolling pressure is collected by the pressure sensor, assuming it is 1200N;

[0094] Rolling speed V: The rolling speed is collected by the photoelectric encoder, assuming it is 0.5m / s;

[0095] 2. Environmental data:

[0096] Ambient temperature W: The ambient temperature is collected by the temperature and humidity sensor, assuming it is 25°C;

[0097] Ambient humidity S: The ambient humidity is collected by the temperature and humidity sensor, assuming it is 60%;

[0098] Dust concentration N in the environment: The dust concentration in the environment is collected by the dust concentration sensor, assuming it is 0.05 mg / m^3;

[0099] 3. Aging data:

[0100] Vibration frequency M of the motor housing: The vibration frequency of the motor housing is collected by a vibration sensor, assuming it is 15 Hz;

[0101] Sound pressure level Y of the motor housing sound: The sound pressure level of the motor housing sound is collected by an acoustic sensor, assuming it is 80 dB;

[0102] Data analysis;

[0103] Assume that the standard temperature ZT = 400°C, the standard rolling pressure ZF = 1000N, and the standard rolling speed ZV = 0.4m / s. The proportional coefficients are A = 0.7, B = 0.6, and C = 0.5.

[0104] 1. Calculation of the first evaluation coefficient P1:

[0105] By formula:

[0106] P1=A×exp(|T-ZT| / ZT)+B×exp(|F-ZF| / ZF)+C×exp(|V-ZV| / ZV);

[0107] Calculating a first evaluation coefficient;

[0108] P1=0.7×exp(|450-400| / 400)+0.6×exp(|1200-1000| / 1000)+0.5×exp(|0.5-0.4| / 0.4)≈2.17;

[0109] 2. Calculation of the second evaluation coefficient P2:

[0110] Assume proportionality coefficient: D = 0.8, E = 0.7;

[0111] By formula:

[0112] P2=D×exp[ln(M) / (ln(M)+1)]+E×tanh(Y)×ln(Y+1);

[0113] calculating a second evaluation coefficient;

[0114] P2=0.8×exp[ln(15) / (ln(15)+1)]+0.7×tanh(80)×ln(81)≈4.74;

[0115] 3. Calculation of the third evaluation coefficient P3:

[0116] Assume proportionality coefficients: J = 0.8, K = 0.7, L = 0.6;

[0117] By formula:

[0118] P3=[ln(W^J×S^K×N^L+1)] / exp(J+K+L);

[0119] Calculating a third evaluation coefficient;

[0120] P3=[ln(25^0.6×60^0.4×0.05^0.5+1)] / exp(0.6+0.4+0.5)≈0.44;

[0121] 4. Calculation of hot rolling early warning assessment coefficient P:

[0122] Assume that weight coefficients Q=0.5, R=0.3, G=0.2.

[0123] P=0.5×2.17+0.3×4.74+0.2×0.44=2.595;

[0124] Data warning module: determines whether to send warning information based on the hot rolling warning evaluation coefficient and the preset threshold; if yes, sends the warning information to the warning processing module; if no, continues to monitor and judge;

[0125] Early warning processing module: used to receive early warning information and process the hot rolling process based on the early warning information.

[0126] Based on the hot rolling early warning evaluation coefficient and the preset threshold, it is determined whether to send early warning information, including:

[0127] Determine whether the hot rolling warning evaluation coefficient is greater than the preset threshold; if yes, generate warning information and send it to the warning processing module; if no, continue to monitor and judge; wherein the preset threshold is set by experience based on the actual scenario.

[0128] The hot rolling process is processed based on the early warning information, including:

[0129] The warning levels are classified into different levels, and the hot rolling process is processed based on the warning levels;

[0130] S1: After receiving the warning information, extract the hot rolling warning evaluation coefficient corresponding to the warning information;

[0131] S2: Determine whether the hot rolling warning evaluation coefficient is greater than the preset advanced warning threshold; if yes, the warning level is advanced warning; if not, the warning level is ordinary warning; wherein, the preset advanced warning threshold is set according to the actual mill fault maintenance requirements.

[0132] For example, assuming that the calculated hot rolling warning evaluation coefficient is 4 and the preset threshold is 2.5, the specific warning processing is as follows:

[0133] 1. Early warning judgment;

[0134] Since the hot rolling warning evaluation coefficient (4) is greater than the preset threshold (2.5), the system sends the warning information to the warning processing module.

[0135] 2. Determination of warning level;

[0136] Once the warning information is received, the warning processing module starts working:

[0137] S1: Extract the hot rolling warning evaluation coefficient corresponding to the warning information.

[0138] S2: Assuming the preset advanced warning threshold is 3.5, then:

[0139] Since the hot rolling warning evaluation coefficient (4) is greater than the preset advanced warning threshold (3.5), the warning level is advanced warning.

[0140] 3. Process the hot rolling process;

[0141] For advanced warnings, more proactive preventive maintenance measures can be taken, such as emergency shutdown inspections and replacement of key components, to prevent major accidents; for ordinary warnings, inspections and maintenance can be arranged during production breaks.

[0142] The present invention can effectively predict and prevent problems that may occur during the hot rolling process by performing multi-dimensional evaluation on the data collected in real time. The system first obtains the data to be detected, including the mill operation data, environmental data and aging data, through the data acquisition module; then, in the data analysis module, a specific mathematical model is used to calculate the first evaluation coefficient (based on the mill operation data), the second evaluation coefficient (based on the aging data) and the third evaluation coefficient (based on the environmental data). Finally, these evaluation coefficients are calculated by weighted average to obtain the hot rolling early warning evaluation coefficient. When this evaluation coefficient exceeds the preset threshold, the system will issue an early warning message and take corresponding treatment measures according to the different early warning levels, such as emergency shutdown inspection or arranging maintenance during production intervals, which will help improve the safety and efficiency of the hot rolling process, reduce unplanned downtime, and also extend the life of the equipment and reduce maintenance costs.

[0143] Part of the data in the above formula is calculated by removing the dimension and taking its numerical value. The formula is a formula closest to the actual situation obtained by software simulation of a large amount of collected data; the preset parameters and preset thresholds in the formula are set by technical personnel in this field according to actual conditions or obtained through simulation of a large amount of data.

[0144] Working principle of the present invention:

[0145] The present invention collects the data to be detected in the hot rolling process in real time through the data collection equipment; calculates the first evaluation coefficient based on the rolling mill operation data; calculates the second evaluation coefficient based on the aging data; calculates the third evaluation coefficient based on the environmental data; and calculates the hot rolling early warning evaluation coefficient based on the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient; judges whether to send an early warning message through the hot rolling early warning evaluation coefficient and a preset threshold; after receiving the early warning message, extracts the hot rolling early warning evaluation coefficient corresponding to the early warning message; judges whether the hot rolling early warning evaluation coefficient is greater than the preset high-level early warning threshold; if yes, the early warning level is a high-level early warning; if not, the early warning level is a common early warning, which solves the technical problem that the prior art only monitors the parameters of the rolling mill itself, but does not take into account that there are many factors that actually affect the hot rolling process of copper-based materials, such as environmental factors and equipment aging, resulting in the monitoring results being not comprehensive enough and the overall condition of the hot rolling process cannot be accurately evaluated.

[0146] The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A copper-based material processing monitoring system based on multi-source heterogeneous data, characterized in that: include: Data collection module, data analysis module, data warning module and warning processing module; Data acquisition module: used to obtain the data to be tested in the hot rolling process in real time; Data analysis module: calculates the hot rolling early warning evaluation coefficient based on the data to be tested; Data warning module: determines whether to send warning information based on the hot rolling warning evaluation coefficient and the preset threshold; If yes, the warning information is sent to the warning processing module; If not, continue to monitor and judge; Early warning processing module: used to receive early warning information and process the hot rolling process based on the early warning information.

2. A copper-based material processing monitoring system based on multi-source heterogeneous data according to claim 1, characterized in that: The data analysis module communicates with and / or is electrically connected to the data acquisition module and the data early warning module respectively; the early warning processing module communicates with and / or is electrically connected to the data early warning module.

3. The copper-based material processing monitoring system based on multi-source heterogeneous data according to claim 1 is characterized in that: The real-time acquisition of the data to be detected during the hot rolling process includes: The data to be tested in the hot rolling process are collected in real time through data acquisition equipment; the data to be tested include: mill operation data, environmental data and mill aging data; the mill operation data include: the temperature of the copper-based material when it leaves the mill, the rolling pressure and the rolling speed; the environmental data include: the ambient temperature, the ambient humidity and the dust concentration in the environment; the aging data include: the vibration frequency of the motor housing and the sound pressure level of the sound.

4. The copper-based material processing monitoring system based on multi-source heterogeneous data according to claim 1 is characterized in that: The hot rolling early warning evaluation coefficient is calculated based on the data to be detected, including: S1: Calculate and obtain a first evaluation coefficient based on rolling mill operation data; S2: Calculate a second evaluation coefficient based on the aging data; S3: Calculate a third evaluation coefficient based on environmental data; S4: Calculate the hot rolling warning evaluation coefficient based on the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient.

5. The copper-based material processing monitoring system based on multi-source heterogeneous data according to claim 4 is characterized in that: The step of calculating the first evaluation coefficient based on the rolling mill operation data includes: The temperature of the copper-based material when it leaves the rolling mill is marked as T, the rolling pressure is marked as F, and the rolling speed is marked as V; By formula: P1=A×exp(|T-ZT| / ZT)+B×exp(|F-ZF| / ZF)+C×exp(|V-ZV| / ZV); The first evaluation coefficient is calculated; wherein P1 is the first evaluation coefficient, A, B, and C are proportional coefficients, and 1>A>0, 1>B>0, 1>C>0, ZT is the standard temperature, ZF is the standard rolling pressure, and ZV is the standard rolling speed.

6. The copper-based material processing monitoring system based on multi-source heterogeneous data according to claim 4 is characterized in that: The step of calculating the second evaluation coefficient based on the aging data includes: The vibration frequency of the motor housing is marked as M, and the sound pressure level of the sound is marked as Y; By formula: P2=D×exp[ln(M) / (ln(M)+1)]+E×tanh(Y)×ln(Y+1); The second evaluation coefficient is calculated; wherein, P2 is the second evaluation coefficient, D and E are proportional coefficients, and 1>D>0, 1>E>0, tanh(*) is the hyperbolic tangent function, and ln(*) is the logarithmic function with the natural number e as the base.

7. The copper-based material processing monitoring system based on multi-source heterogeneous data according to claim 4 is characterized in that: The step of calculating the third evaluation coefficient based on the environmental data includes: The ambient temperature is marked as W, the ambient humidity is marked as S, and the dust concentration in the environment is marked as N; By formula: P3=[ln(W^J×S^K×N^L+1)] / exp(J+K+L); The third evaluation coefficient is calculated; wherein P3 is the third evaluation coefficient, J, K, and L are proportional coefficients, and 1>J>0, 1>K>0, 1>L>0, and J+K+L>1.

8. The copper-based material processing monitoring system based on multi-source heterogeneous data according to claim 4 is characterized in that: The hot rolling early warning evaluation coefficient is calculated based on the first evaluation coefficient, the second evaluation coefficient and the third evaluation coefficient, including: The hot rolling early warning assessment coefficient is calculated by weighted average method, which is: P = Q × P1 + R × P2 + G × P3; Among them, P is the hot rolling early warning evaluation coefficient, Q, R, and G are weight coefficients, and Q+R+G=1.

9. The copper-based material processing monitoring system based on multi-source heterogeneous data according to claim 1, characterized in that: The determining whether to send warning information based on the hot rolling warning evaluation coefficient and the preset threshold value includes: Determine whether the hot rolling warning evaluation coefficient is greater than the preset threshold; if yes, generate warning information and send it to the warning processing module; if no, continue to monitor and judge; wherein the preset threshold is set by experience based on the actual scenario.

10. The copper-based material processing monitoring system based on multi-source heterogeneous data according to claim 1, characterized in that: The processing of the hot rolling process based on the early warning information includes: The warning levels are classified into different levels, and the hot rolling process is processed based on the warning levels; S1: After receiving the warning information, extract the hot rolling warning evaluation coefficient corresponding to the warning information; S2: Determine whether the hot rolling warning evaluation coefficient is greater than the preset advanced warning threshold; if yes, the warning level is advanced warning; if not, the warning level is ordinary warning; wherein, the preset advanced warning threshold is set according to the actual mill fault maintenance requirements.

Images