35 results about "Hot strip rolling" patented technology

The invention relates to the technical field of hot continuous rolling material performance prediction, and discloses an efficient hot continuous rolling material performance prediction method and system, and the method comprises the steps: achieving the multi-source data cleaning through multi-dimensional outlier detection and cross-rack space-time interpolation, building a material component graph model, capturing the interaction of elements, and predicting the performance of a hot continuous rolling material. And fusing physical characteristics and gene coding characteristics by adopting a space-time attention mechanism. Cross-production-line model parameters are integrated based on a federated learning framework, model robustness is optimized in combination with physical conservation constraint and adversarial training, and finally, optimal process parameters are inverted through a sequential quadratic programming algorithm and PLC closed-loop control is realized. By adopting a multi-dimensional outlier detection algorithm and a cross-rack space-time interpolation technology, the problems of poor synchronism and abnormal missing detection of a traditional data cleaning method in a hot continuous rolling multi-source heterogeneous data scene are solved, and data quality enhancement in a high-noise environment is realized by joint distribution statistics and physical law constraints.

This invention relates to a high-precision, fast-response thickness control method for a hot strip rolling mill. The hot strip rolling mill includes N sets of roll mechanisms, a reduction system, a frequency conversion system, and a thickness control system. The thickness value of the strip after being rolled by the roll mechanisms is input to the thickness control system. The high-precision, fast-response thickness control method for the hot strip rolling mill includes the following steps performed by the thickness control system: receiving the thickness deviation through a feedforward predictive control regulator F, and calculating the intermediate value K. G And based on the intermediate quantity K G The thickness feedforward estimated adjustment amount is calculated and output. The thickness deviation is received by the thickness feedback proportional-integral controller M. The calculated thickness feedback proportional-integral adjustment amount is then output. The thickness feedforward estimated adjustment amount and the thickness feedback proportional-integral adjustment amount are superimposed by an overlay device to obtain the roll gap adjustment amount ΔG, which is input into the roll adjustment mechanism of the pressing system. This effectively solves the problem of thickness step fluctuation in strip steel caused by uncontrollable factors.

The utility model relates to the technical field of strip hot rolling mills, in particular to a smoke exhaust device for a strip hot rolling mill, which comprises a flue, at least one group of heat exchange component and a smoke suction component, the flue is provided with an air inlet and an air outlet, and the heat exchange component comprises a condenser which is arranged in the flue and is positioned between the air inlet and the air outlet; the smoke suction assembly comprises a fan and a smoke suction structure, an air inlet of the fan is fixedly connected to a smoke outlet of the strip hot mill, and an air outlet of the fan is fixedly connected with an air inlet of the flue through the smoke suction structure. According to the smoke exhaust device for the strip hot rolling mill, heat exchange can be conducted on high-temperature smoke exhausted from the hot rolling mill, the temperature of the high-temperature smoke is reduced, condensed smoke is obtained, and the content of liquid drops in the high-temperature smoke is effectively reduced; and after condensation, the smoke with reduced liquid drop content is discharged into the atmosphere, so that the environment is more environment-friendly, and serious pollution to the environment is avoided.

The invention discloses a hot continuous rolling laminar cooling control method and system, and belongs to the technical field of hot rolling process control, the method comprises the following steps: collecting multi-source process parameters in a hot continuous rolling laminar cooling process, and constructing a multi-source data input vector; inputting the multi-source data input vector into a preset prediction model to obtain a valve opening number prediction value; on the basis of the process parameters of the preorder strip steel, the valve opening number correction value is calculated in real time through a preset feedforward model; and the predicted value of the valve opening number and the correction value of the valve opening number are superposed to obtain the final valve opening number, and the final valve opening number is conveyed to a control execution mechanism of the hot continuous rolling laminar cooling process. By the adoption of the hot continuous rolling laminar cooling control method and system, the control precision and robustness of the laminar cooling system under the complex and changeable working conditions can be effectively improved, and the method and system have remarkable industrial value for improving the structure property uniformity of strip steel products.

This application provides a method for preparing hot-rolled wide coils of 60Si2Mn spring steel with anti-strip breakage properties, and the hot-rolled wide coils thereof. The method includes: heating a 60Si2Mn spring steel slab to obtain a heated slab; hot-rolling the heated slab to obtain a hot-rolled wide strip steel with a width of 900-1500 mm; subjecting the hot-rolled wide strip steel to laminar flow cooling to obtain laminar flow cooled hot-rolled wide strip steel, wherein the laminar flow cooling consists of a pre-stage non-water cooling treatment and a post-stage rapid cooling treatment, with a target temperature of 760-800℃ for the pre-stage non-water cooling treatment and a cooling rate of 10-20℃ / s for the rapid cooling treatment; and coiling and cooling the laminar flow cooled hot-rolled wide strip steel to obtain hot-rolled wide coils of 60Si2Mn spring steel with anti-strip breakage properties. Using the embodiments of this application, hot-rolled wide coils of 60Si2Mn spring steel with anti-strip breakage properties can be produced, and they will not break during subsequent processing steps.

This invention provides a hot-rolled strip quality prediction method and system based on PINN modeling and cross-modal graph learning, belonging to the fields of industrial intelligent manufacturing and hot-rolled strip quality monitoring. The method first acquires historical production process variable data, strip quality data, and sensor monitoring data; it then constructs a temperature field model of the hot-rolled strip water-cooling process based on PINN, and uses the trained temperature field model to solve the continuous temperature field during the laminar cooling stage, extracting temperature field features; it constructs modal subgraphs for both temperature field features and sensor features, building a cross-modal full graph structure; a preliminary prediction model is built based on GNN, using the cross-modal full graph structure as the model input layer structure, and N base learners based on a residual learning strategy are introduced into the output layer. The trained preliminary prediction model and the N base learners constitute the hot-rolled strip quality prediction model. This invention achieves a deep integration of physical mechanisms and deep learning, significantly improving the accuracy and robustness of hot-rolled strip quality prediction.

The present application belongs to the field of hot rolling, and particularly relates to a device and method for preventing hot-rolled strip from being scratched on an output roller way. The present application provides a device for preventing hot-rolled strip from being scratched on an output roller way. The device for preventing hot-rolled strip from being scratched on an output roller way is arranged on a strip hot rolling mill, and comprises a plurality of Hall current transformers, a first temperature sensor, a second temperature sensor and a control center. Wherein, one Hall current transformer is arranged on a power transmission line of a motor corresponding to each roller way of the strip hot rolling mill. One first temperature sensor is installed on a bearing end of each motor. One second temperature sensor is installed on a bearing end of each roller way. The control center is electrically connected with the plurality of Hall current transformers, the plurality of first temperature sensors and the second temperature sensors.

This document describes processes for forming malleable aluminum alloy products with excellent surface properties. The processes comprise a hot pre-rolling operation and a hot strip rolling operation, the latter performed at a lower exit temperature than the pre-rolling operation. The aluminum alloy product is not cooled between the first and hot strip rolling operations. The resulting aluminum alloy products can be used to form structural components for aerospace applications.

This invention provides a method and system for constructing a professional knowledge graph for the hot rolling process of strip steel, belonging to the field of industrial monitoring and intelligent manufacturing. The method first acquires multi-source heterogeneous data of the hot rolling process of strip steel, and transforms structured and semi-structured data into unstructured data before merging them into an unstructured dataset; constructs an ontology for the professional knowledge graph, including entity types and entity relationships; divides the unstructured data into training and testing sets; constructs a joint extraction model based on the CasRel framework and multi-hop attention mechanism, and performs training and testing; inputs all unstructured data into the model, identifies and extracts a set of structured triples, processes and stores them to obtain the basic knowledge graph; acquires hot rolling fault data and constructs a fault knowledge graph, and fuses them to obtain the professional knowledge graph for the hot rolling process of strip steel. This invention constructs a professional knowledge graph for the hot rolling process of strip steel, improving the systematic capture capability of hot rolling process data.

The application discloses a strip steel hot rolling process multi-performance index abnormality monitoring method and system, and belongs to the technical field of industrial process control and fault diagnosis, and the method comprises the following steps: collecting process variable data and performance index data in a historical strip steel hot rolling process and performing standardization pretreatment; dividing the strip steel hot rolling process into multiple different process subblocks; for each process subblock, performing space-time feature extraction on the corresponding process variable data to obtain a space-time feature representation; constructing a local statistic quantity of each performance index; fusing the local statistic quantities to obtain a global statistic quantity and a global control limit; and based on this, realizing multi-performance index abnormality monitoring and alarm. The application effectively solves the problems that cross-process time lag dependence is difficult to capture, space-time feature extraction is not comprehensive, and single performance index monitoring leads to abnormality missed reports in the strip steel hot rolling process, significantly improves the fault detection rate and reduces the false alarm rate.

The invention discloses a position adjusting method and device for loop rollers in a finishing mill group and electronic equipment, and belongs to the technical field of strip steel hot continuous rolling mill equipment maintenance. The position adjusting method comprises the steps that position information of a to-be-adjusted finishing mill loop roller in a working state is obtained, and the position information comprises horizontal height deviation information of the to-be-adjusted finishing mill loop roller and angle deviation information between the to-be-adjusted finishing mill loop roller in the working state and the horizontal direction; on the basis of the horizontal height deviation information and axial size information and angle deviation information of a bearing seat used for supporting the loop roller of the finishing mill to be adjusted, mechanical size deviation information of a positioning face where the bearing seat is located is determined; and on the basis of the mechanical size deviation information, size information of a bearing seat positioning gasket used for adjusting the height of the bearing seat is determined, so that horizontal adjustment of the to-be-adjusted loop roller of the finishing mill is achieved. The deviation of the loop roller in the horizontal direction is reduced, and the precision of the loop roller is improved.

The invention discloses a strip steel thickness prediction method and system based on data driving and a medium. The method comprises the following steps that process parameters in the strip steel hot rolling process are collected from a hot rolling production line based on a data driving strategy; analyzing the process parameters based on a random forest algorithm, and identifying key parameters influencing the thickness of the strip steel; and inputting the key parameters into a pre-established Nadam-ml p model to predict the thickness of the strip steel, and evaluating the performance of the model through various evaluation indexes. According to the method, a large amount of data in the hot rolling process is analyzed through the random forest algorithm so as to identify key parameters influencing the thickness of the strip steel, the thickness of the strip steel is predicted through the MLP model optimized by Nadam, the prediction precision of the thickness of the strip steel is improved, the product quality and the production benefit are improved, and the industrial high-precision requirement can be met.

This invention provides a method and device for monitoring energy consumption in the finishing rolling process based on nonlinear dynamic feature extraction, belonging to the field of intelligent monitoring technology for industrial production processes. The method includes: constructing a dataset based on a mutual information calculation method using a finishing rolling process energy consumption dataset to obtain a historical process dataset and energy consumption levels; extracting features from the historical process dataset using a feature extraction network to obtain a set of historical stand energy consumption features; calculating statistical quantities using a support vector data description algorithm based on the historical stand energy consumption feature set to obtain monitoring thresholds for each stand; and calculating statistical quantities based on actual stand energy consumption data to determine whether energy consumption exceeds the standard, and calculating the level of excessive energy consumption to obtain the level of excessive energy consumption. This invention is a precise and efficient distributed energy consumption monitoring method for the finishing rolling process of hot strip steel based on nonlinear dynamic feature extraction.

The invention relates to the technical field of mechanical automation control, in particular to a continuous annealing strip steel blocking early warning method based on full-process big data, which comprises the following steps: acquiring width data of each position in the full-length direction of a strip steel hot rolling outlet in the production process; based on the hot-state width and the thermal expansion coefficient, converting the hot-state width and the thermal expansion coefficient into cold-state data to obtain the cold-state width of each position in the full-length direction of the strip steel; calculating the actual rolling mill reduced scale and the continuous retraction reduced scale; constructing a BP neural network model to obtain a rolling mill reduced scale and a continuous retraction reduced scale; the opening degree of the continuous annealing circle shear is read, and the total edge reduction amount of the strip steel on the two sides of the continuous annealing circle shear is calculated; all the positions of the whole length of the strip steel are judged, when the edge reduction amount of the position of the strip steel is smaller than a danger threshold value, it is judged that the edge blocking risk exists in the position, and the system conducts early warning; according to the method, whether the strip steel has the edge blocking risk at the position of the circle shear or not is accurately predicted by accurately predicting the strip steel reduced scale, stable operation of equipment is guaranteed, and unnecessary shutdown is reduced.

The invention provides a rationality evaluation method and system based on a hot rolling strip steel rolling plan provided by the embodiment of the invention, and belongs to the field of metallurgical process formulation and evaluation. The method comprises the steps that a rolling simulation model is established based on an obtained rolling plan and corresponding product information, and a simulation production result is obtained through calculation of the simulation model and serves as a judgment basis of simulation production; a historical production result recorded in the past is obtained to serve as a judgment basis of historical production; respectively calculating a simulated production risk coefficient and a historical production risk coefficient, then carrying out weighted summation on the simulated production risk coefficient and the historical risk coefficient according to the plate shape consideration weight, and calculating a plate shape problem risk coefficient of the current steel coil; and after traversing all the steel coils, presetting an evaluation standard, arranging an evaluation result and an identifier according to the risk coefficient and the evaluation standard, and outputting the evaluation result as a risk evaluation result by adopting the identifier. According to the method, the reliability of a big data analysis result is improved, and the reliability of a rationality evaluation result is ensured.

The present invention relates to the field of hot-rolled strip technology, and in particular to a method for dynamically adjusting three-point differences during the hot-rolled strip rolling process. The method includes: S1, pre-rolling preparation and parameter initialization: roll profile matching and model parameter preloading; S2, dynamic control during the strip threading phase: thickness pre-compensation and temperature gradient suppression; S3, steady-state rolling control: real-time monitoring and compensation of three-point differences and dynamic compensation of thermal crown; and S4, tail swing and abnormality handling: tail stability control and intelligent transition material insertion. The present invention constructs a full-process control system encompassing dynamic roll gap control, temperature-stress coupling compensation, and intelligent decision support. By developing an asymmetric bending roll force distribution model and a roll profile matching strategy that adapts to the rolling rhythm, the system effectively addresses the difficulties faced by traditional single-point thickness control, such as the difficulty in suppressing head and tail thickness fluctuations and excessive edge thinning.

The invention discloses a strip steel cross section temperature uniformity control method. The method comprises the following steps: 1) data acquisition; 2) heating temperature control; 3) controlling the temperature and the surface quality of the strip steel in a rough rolling stage; 4) controlling the temperature and the surface quality of the strip steel in the finish rolling stage; 5) establishing a strip steel cross section temperature difference model; and 6) predicting the temperature difference according to the model and the real-time parameters, and when the predicted temperature difference exceeds a set threshold value, adjusting the parameters to control the predicted temperature difference within the set threshold value range, and using the adjusted parameters as the parameters of the next round of production control. The strip steel cross section temperature uniformity is controlled through the strip steel cross section temperature difference model, and the edge defect problem in the strip steel hot rolling process can be effectively solved.

The utility model provides a kind of shunting structure, laminar cooling equipment and strip steel hot rolling system, it is related to hot rolling technical field.Shunting structure includes shunting block, plunger, sealing ring, the shunting block includes main water hole and multiple shunt holes with the main water hole communication, one end of the main water hole is used to with main water pipe communication, multiple the shunt hole is spaced distribution along the axial direction of the main water hole, every the shunt hole is used to with corresponding gooseneck pipe communication;The plunger is inserted into the main water hole from the other end of the main water hole away from the main water pipe, and with the main water hole gap cooperation, and the plunger can be axially moved along the main water hole;The sealing ring is sleeved in the plunger, and the outer peripheral wall of the sealing ring is slidably connected with the inner wall of the main water hole.

This invention provides a method and system for diagnosing fault conditions in hot strip rolling mills, relating to the field of automated control technology for hot-rolled strip steel. The method includes: collecting a set of operating signals from the hot strip rolling mill to be diagnosed; selecting evaluation indicators from the set of operating signals; determining multiple fault condition types corresponding to the evaluation indicators; establishing a preset scoring system for the equipment fault conditions corresponding to each fault condition type; constructing an original decision matrix regarding the evaluation indicators and equipment fault conditions; performing cloud roughness number processing on the original decision matrix to generate a cloud roughness number decision matrix; calculating the importance ranking of the evaluation indicators using game theory and a comprehensive weighting method; using the grey relational analysis-TOPSIS algorithm to quantitatively score the equipment fault conditions; constructing a fault type evaluation formula; and diagnosing the equipment fault conditions based on the fault type evaluation formula.

The invention provides a self-adaptive dynamic setting method for cold continuous rolling additional tension under an unsteady rolling condition, and relates to the technical field of mechanical automation control. The method comprises the following steps: firstly, based on obtained strip steel hot rolling-cold rolling process information, constructing a cross-process cold continuous rolling unsteady state rolling force prediction model; and then an additional tension setting function in the cold continuous rolling unsteady-state speed increasing and decreasing rolling process is constructed with the minimum rolling force fluctuation as the target, finally, the optimal additional tension setting value of each rack is obtained through an artificial intelligence algorithm and is fitted into an additional tension curve, and collaborative setting of the tension of each rack is achieved. Compared with a traditional additional tension setting method, additional tension setting is dynamically adjusted according to the set and actually measured rolling force deviation, speed disturbance in the unstable rolling process can be responded in real time, the rolling stability of multiple low-speed and variable-speed stages is improved, the strip steel head thickness deviation and strip shape defects are effectively reduced, and the yield of the strip steel is improved. And the head quality consistency and the yield of the strip steel are guaranteed.

The application provides a hot continuous rolling strip steel wedge control method and equipment, and relates to the field of metal material processing. The wedge value of the strip steel at the terminal outlet is judged to confirm the real-time condition of the wedge value at the terminal outlet. When the wedge value is greater than the preset wedge value, it indicates that the wedge value is too large and needs to be adjusted. Before the adjustment, the center line offset and the symmetric flatness of the strip steel are further judged. When the two values are within the normal range, the different rolling mill stands are automatically controlled according to the different thicknesses of the strip steel to adjust the wedge of the strip steel. The whole control process does not need human intervention. Only the corresponding control strategy needs to be formulated before production. According to the wedge value, the center line offset and the symmetric flatness at the terminal outlet monitored in the production process, the corresponding rolling mill stand is adjusted adaptively to ensure the production efficiency and the production precision of the whole production line and improve the qualified rate of the products.

This invention discloses a method, apparatus, equipment, and medium for controlling the coiling temperature of hot-rolled strip steel. The method includes: acquiring the measured temperature value of any strip steel control sample when it is detected that any strip steel control sample has arrived at the fine-tuning section; acquiring the measured coiling temperature value of the strip steel control sample after it is detected that any strip steel control sample has passed the coiling temperature detector, and determining the strip steel control sample to be adjusted currently at the entrance of the fine-tuning section, and performing the following adjustment steps: predicting the coiling temperature deviation of the strip steel control sample to be adjusted based on the measured temperature value corresponding to the strip steel control sample that has passed the coiling temperature detector, the measured coiling temperature value, the measured temperature value of the strip steel control sample to be adjusted when it arrives at the fine-tuning section, and the target coiling temperature value; and adjusting the number of manifolds opened in the fine-tuning section based on the coiling temperature deviation to control the coiling temperature of the strip steel control sample to be adjusted. This method improves the accuracy of coiling temperature control.

The present application relates to a kind of hot strip coiling temperature control method, belong to hot strip rolling technical field.The control method is based on the existing strip coiling before forecast temperature T pre, introduce the control temperature T control of strip coiling before with T pre same cycle and the compensation temperature T compensation of strip in laminar cooling section, further introduce the unit length temperature k of compensation temperature T compensation and fine tuning temperature t and in the each cycle of sampling constantly calculate and reassign, so that T compensation and T control The calculated value can be constantly updated with cycle and more accurate;Finally, by comparing the absolute value of the difference between T pre and T control of each cycle with the set limit deviation value and comparing T pre and T control, adjust the laminar cooling water injection amount set in the previous cycle and as the laminar cooling water injection amount newly set in the current cycle, make the laminar cooling water injection amount set in each cycle more accurate, so that the actual coiling temperature of strip can be more accurately controlled.

The invention relates to a thin-strip continuous casting silicon steel plate shape control technology, in particular to a method for controlling silicon steel edge drop. According to the invention, the roll shape of the double-roll cast-rolling crystallization roll is designed, and the roll shape of the crystallization roll is divided into an edge region and a middle region. The purpose of controlling the edge plate shape and the edge drop of the continuous casting thin strip steel is achieved by controlling the roll shape parameters of the edge area, and the edge drop of the hot-rolled silicon steel thin strip steel after one-pass hot rolling is effectively controlled. And meanwhile, the aim of coordinately controlling the edge drop of the thin strip steel of the hot-rolled silicon steel is achieved by controlling the thrust of a side sealing plate at the edge of a crystallization roller and the temperature of the thin strip steel before hot rolling. By means of the crystallization roller shape design, the edge drop of thin-strip continuous casting silicon steel thin strip steel, hot-rolled silicon steel thin strip steel and cold-rolled silicon steel thin strip steel is controlled, the rolling ability, the yield and the edge quality of cold rolling are improved, the value of the same-plate difference of cold-rolled silicon steel is reduced, and the plate shape quality of silicon steel is effectively improved.

The invention provides a data-driven hot-rolled strip steel performance comprehensive evaluation method and device, and relates to the technical field of performance evaluation of industrial processes. The method comprises the steps that multi-dimensional data of the strip steel hot rolling production process are obtained and preprocessed; constructing a random forest prediction model to complete performance-related data missing values to obtain multi-dimensional complete data; a hot-rolled strip steel performance comprehensive rating scheme is designed according to the strip steel quality standard; a strip steel performance comprehensive evaluation model based on multi-task learning and a performance-related stacked auto-encoder is constructed, and multi-dimensional complete data is used for training; and according to the strip steel performance comprehensive evaluation model, a multi-level performance rating result of the hot-rolled strip steel is obtained. According to the method, scientific, accurate and multi-level real-time evaluation on the performance of the hot-rolled strip steel can be realized by mining the incidence relation between the process data and the performance related data.

The present invention belongs to the technical field of metallurgical rolling in metallurgical science and technology, and specifically relates to a finish rolling method for high-speed steel rolls, including: adjusting the load distribution of the rolling mill according to the rolling pressure; adding a roll correction coefficient in the calculation of the rolling pressure according to the roll type. The finish rolling method for high-speed steel rolls of the present invention reduces the rolling pressure deviation from a maximum of 40% to within ±10%, and no stainless steel overcurrent phenomenon occurs, realizing the stable rolling of high-speed steel rolls in the hot strip rolling production line and achieving remarkable economic benefits.

The invention provides hot-rolled ultrahigh-strength strip steel with high formability, the yield strength of the hot-rolled strip steel is greater than or equal to 900 MPa, and the hot-rolled strip steel comprises the following chemical elements in percentage by mass: 0.07 to 0.2 percent of C, 0.02 to 0.20 percent of Si, 1.2 to 2.5 percent of Mn, 0.3 to 1.0 percent of Cr, 0.13 to 0.2 percent of Ti and 0.01 to 0.06 percent of Al. The invention also provides a manufacturing method of the hot-rolled strip steel, which comprises the following steps of: heating a plate blank, roughly rolling and finely rolling to obtain the strip steel, and then carrying out staged online quenching treatment, coiling, water blowing treatment and tempering heat treatment. The cost of the hot-rolled strip steel alloy with the 900MPa yield strength grade is remarkably reduced, and on the basis of reducing the cost, the preparation process is combined, and on the basis of ensuring the yield strength of the strip steel, high plasticity and cold forming performance are achieved.

The invention belongs to the technical field of strip steel hot rolling, and relates to a method and system for improving the tail stability of hot-rolled thin strip steel. The method comprises the following steps: S1, controlling the width of a side guide plate; s2, the side guide plate is subjected to steel throwing and quick opening; s3, the roll gaps of the rack are lifted in sequence; s4, a side guide plate is matched and quickly opened; step S5, rolling force protection is carried out; according to the technical scheme, intelligent and automatic control in the strip steel hot rolling production line is achieved through key operation, the drifting problem during hot rolling thin-gauge production is solved, the stability of thin-gauge strip steel hot rolling is improved, and the large promotion effect on product development and control research of hot rolling strip steel is achieved.

The utility model discloses a hot-rolled strip rolling mill finish rolling inlet guide table segmented roller device which comprises a base, the base is installed on a small vertical roller memorial archway rack through bolts, segmented rollers are installed on the base through bolts in a combined mode, and the number of the segmented rollers is multiple. The sectional roller body is provided with a core shaft through a bearing, and each two sections of sectional roller body are supported by a shaft seat. The utility model relates to the field of design of guide table segmented rollers, in particular to a segmented roller device of a finish rolling inlet guide table of a hot rolling strip rolling mill.

The invention provides a finish rolling process energy consumption monitoring method and device based on nonlinear dynamic feature extraction, and relates to the technical field of industrial production process intelligent monitoring. The method comprises the steps of performing data set construction according to a finish rolling process energy consumption data set based on a mutual information calculation method, and obtaining a historical process data set and an energy consumption level; performing feature extraction through a feature extraction network according to the historical process data set to obtain a historical rack energy consumption feature set; according to the historical rack energy consumption feature set, using a support vector data description algorithm to carry out statistic calculation to obtain each rack monitoring threshold; and performing statistic calculation according to the actual rack energy consumption data, judging whether the energy consumption exceeds the standard or not, and performing grade calculation on the standard-exceeding energy consumption to obtain a standard-exceeding energy consumption grade. The distributed energy consumption monitoring method for the hot rolling and finish rolling process of the strip steel is accurate and efficient based on nonlinear dynamic feature extraction.