Workshop collaborative management method and device for industrial big data, electronic equipment and storage medium

Abstract

The invention discloses a workshop collaborative management method and device for industrial big data, electronic equipment and a storage medium, and the method comprises the steps: building a mineral aggregate data set through collection of mineral aggregate key data, determining standard mineral aggregate data, introducing a similarity threshold judgment mechanism, building similar mineral aggregates with balanced components, and carrying out the collaborative management of the industrial big data. The method effectively reduces the disturbance caused by the composition difference of the raw materials, enables various similar mineral aggregates to obtain the matched optimal smelting temperature and time interval based on the reduction rate-temperature change curve, achieves the precise control of the smelting reaction, and achieves the precise control of the smelting reaction through the mechanism of data driving and multi-region temperature control cooperation. And the composition difference between the similar mineral aggregate and the standard mineral aggregate is quantitatively analyzed and fed back to each temperature control area for dynamic adjustment of temperature and time, so that full-chain closed-loop control from raw material sensing to process regulation and control is realized, the stability and smelting efficiency of the mineral aggregate smelting process are effectively improved, and the production cost is reduced. And metal loss and product quality fluctuation caused by raw material component difference are reduced.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a workshop collaborative management method, device, electronic equipment, and storage medium for industrial big data. Background Art

[0002] With the development of industrial informatization and intelligent manufacturing, the traditional metallurgical and mineral processing industries are gradually transforming towards digitalization, automation, and intelligentization. In this process, workshop-level production scheduling and smelting process control have become one of the key bottlenecks hindering the advancement of intelligentization.

[0003] Traditional smelting workshop management relies heavily on manual experience and preset process parameters, lacking a mechanism to respond to variations in raw material composition. Faced with varying batches of ore, varying metal reduction characteristics, and fluctuating process windows, workshop systems struggle to adjust smelting parameters in a timely manner, leading to low smelting efficiency, high energy consumption, and poor product consistency. Furthermore, the lack of a unified data integration platform creates severe information silos between different workshop processes, resulting in insufficient collaboration and hindering the overall manufacturing system's responsiveness and resource utilization efficiency.

[0004] Therefore, it is necessary to design a workshop collaborative management method, device, electronic equipment, and storage medium for industrial big data to solve the above problems. Summary of the Invention

[0005] The present invention overcomes the deficiencies of the prior art and provides a workshop collaborative management method, device, electronic equipment, and storage medium for industrial big data.

[0006] To achieve the above objectives, the present invention adopts a technical solution: a workshop collaborative management method for industrial big data, which is executed by a control system and is used to perform data collection, data adjustment, temperature-time regulation and equipment collaborative control on the smelting process of multiple batches of mineral materials. The method includes the following steps:

[0007] Step S1: Using industrial IoT terminals deployed on mineral conveyor belts, key data on the types, metal element content, and impurity content of multiple batches of minerals in a mineral smelting workshop are collected in real time, and a data channel with the control system is established;

[0008] Step S2: The control system retrieves key mineral data, generates standard mineral material data, divides the minerals into piles, and controls the composition of each pile of mineral materials to be similar to form several piles of similar mineral materials;

[0009] Step S3: The control system retrieves standard ore data, automatically generates a standard smelting temperature-time control range based on the reduction rate-temperature dynamic response curve, and outputs it as a reference boundary of the smelting process control section;

[0010] Step S4: The control system retrieves the key data of each pile of similar ore and compares it with the standard ore data. Based on the temperature control and time control strategies, the temperature range and time range of different smelting areas are controlled and optimized based on the ore reduction rate-temperature change curve-zoning, forming a multivariable coordinated control of the smelting process.

[0011] Step S5: Upload the optimized control parameters generated by the control system to the workshop collaborative management platform and distribute them to the execution equipment of each smelting unit to form cross-regional and cross-batch smelting control instructions.

[0012] In a preferred embodiment of the present invention, in step S1,

[0013] Step S11: Configuring a laser-induced breakdown spectrometer on the mineral conveyor line to obtain in real time the mineral type and its proportion in the mineral smelting, as well as the content of metal elements and impurities in different mineral types in each batch of mineral smelting;

[0014] Step S12: Based on the key data obtained in step S11, a three-dimensional data set including mineral type identifier, element content matrix, and impurity feature vector is constructed. Among them, D k represents the kth batch of ore, M i represents the proportion of the i-th mineral in the k-th batch of ore, C in represents the content of metal elements in the nth mineral of the i-th mineral, Z in It represents the content of impurities in the nth mineral of the i-th mineral;

[0015] Step S13: Estimating theoretical product quantity based on total ore amount and metal content Among them, M i represents the proportion of the i-th mineral in the k-th batch of ore, C in represents the content of metal elements in the nth mineral of the i-th mineral, Y in It represents the estimated reduction rate of the metal element in the nth mineral of the i-th type.

[0016] In a preferred embodiment of the present invention, step S2 includes the following steps:

[0017] Step S21: Determine the number of piles based on the key data of the minerals, and obtain the average data of each pile as the standard mineral data;

[0018] Step S22: Divide the minerals into several piles of similar mineral materials according to the required number of piles;

[0019] Step S23: Based on the standard mineral material data, a similarity threshold is set for several piles of similar mineral materials, and whether the several piles of similar mineral materials are within the similarity threshold range is determined according to the similarity threshold, and adjustments are made.

[0020] In a preferred embodiment of the present invention, in step S21, the determination of the standard ore data is specifically the proportion of the same mineral type in the mineral smelting, the content of metal elements and impurities in the same mineral type, and the average value in several piles of similar ore materials, that is, Where n represents the number of stacks.

[0021] In a preferred embodiment of the present invention, step S3 includes the following sub-steps:

[0022] Step S31: Establish a deep neural network model based on historical smelting data to determine the reduction rate of a certain mineral under temperature and time Y(T, t) = 1-e -ki(T)·t , where Y(T, t) represents the reduction rate of the i-th mineral at temperature T and time t, and ki(T) represents the reaction rate constant, which is obtained experimentally;

[0023] Step S32: Based on the reduction rate of a certain mineral under temperature and time, a reduction rate-temperature curve of similar minerals is constructed. Then determine the smelting temperature and time under different reduction rates, where p i represents the proportion of the i-th mineral in similar mineral materials, w i Indicates the iron content in the i-th mineral.

[0024] In a preferred embodiment of the present invention, in step S4, different smelting zones are obtained by the reduction rate of the smelted metal, and the different smelting zones include: a preheating zone, a primary reduction zone, a main reduction zone, a melting zone, and an iron-tapping slow cooling zone.

[0025] In a preferred embodiment of the present invention, in step S4, the key data of each pile of similar ore to be smelted is compared with the standard ore data, and the difference in mineral type proportion and metal element content is calculated. The offset of different temperature control zones is calculated based on the difference according to the reduction rate-temperature change curve, and the temperature range and time range are adjusted.

[0026] A workshop collaborative management device for industrial big data, comprising:

[0027] Mineral material data collection and standard modeling module, used to collect key data required for mineral smelting and build standard mineral material data for pile sorting and control reference;

[0028] The ore pile classification and similarity control module is used to reasonably classify different batches of ore according to their composition and structure, forming several piles of similar ore for unified control;

[0029] Temperature-reduction rate modeling and control strategy formulation module, which is used to build a functional relationship model between the ore reduction rate and temperature / time, and formulate standard smelting temperature and time ranges accordingly;

[0030] The temperature and time dynamic adjustment and coordinated control module is used to make differentiated adjustments to the temperature and time control range during the smelting process based on the difference between each pile of similar ore and the standard ore.

[0031] An electronic device includes a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the above-mentioned management method are executed.

[0032] A storage medium stores a computer program, which, when executed by a processor, executes the steps of the management method.

[0033] The present invention solves the defects existing in the background technology and has the following beneficial effects:

[0034] (1) The present invention provides a workshop collaborative management method for industrial big data. By collecting key data of mineral materials, a mineral material data set is constructed, standard mineral material data is determined, and a similarity threshold judgment mechanism is introduced to construct similar mineral materials with balanced composition, effectively reducing the disturbance caused by differences in raw material composition. A dynamic smelting parameter model is established based on the reduction rate-temperature change curve, so that all types of similar mineral materials can obtain matching optimal smelting temperature and time intervals, thereby achieving precise control of the smelting reaction. Through the "data-driven + multi-zone temperature control collaboration" mechanism, the composition differences between similar mineral materials and standard mineral materials are quantitatively analyzed, and feedback is given to each temperature control zone for dynamic adjustment of temperature and time, realizing full-chain closed-loop control from raw material perception to process regulation, effectively improving the stability and smelting efficiency of the mineral material smelting process, and reducing metal loss and product quality fluctuations caused by differences in raw material composition.

[0035] (2) The present invention provides a workshop collaborative management method for industrial big data. Through the mechanism of "data-driven + multi-zone temperature control collaboration", the reduction rate of each metal at different temperatures and times is fitted, and different smelting areas are dynamically divided. The optimal temperature and reaction time range required for each smelting temperature zone is dynamically calculated and adjusted through the key data difference of similar ores, so as to realize the coordinated dynamic adjustment of smelting temperature and time in different smelting areas, ensure that the adjustment of metal smelting temperature and time is based on its reduction rate at different temperatures and times, reduce the loss of unreduced metal, and at the same time avoid energy waste or charge damage caused by excessively high temperature, and reduce metal loss and product quality fluctuation caused by differences in raw material composition.

[0036] (3) The present invention provides a workshop collaborative management method for industrial big data. By establishing "standard mineral material data", a unified comparison benchmark is set up for each pile of similar mineral materials, and the minerals are sorted into piles based on this. This not only makes the chemical composition of similar mineral materials more uniform and significantly reduces the process disturbance caused by raw material fluctuations, but also provides an accurate input basis for the subsequent establishment of a "reduction rate-temperature change curve-time" mechanism based on mineral material composition, so that the smelting temperature and time can be accurately matched and dynamically adjusted, reducing the smelting temperature fluctuations, local over-reduction or insufficient reduction caused by sudden changes in mineral material composition.

[0037] (4) The present invention models and obtains the reduction rate of metals under different temperature and time conditions, and then clarifies the optimal time range and temperature range of each metal in different reduction stages, thereby accurately matching the smelting process with the actual ore composition. This not only improves the accuracy of smelting parameters, but also provides a basic basis for the subsequent dynamic adjustment of temperature and time in the smelting area, avoiding the decline in metal recovery rate or fluctuation in product quality due to parameter offset, and realizing a more efficient, stable and intelligent smelting control process. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments described in the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive efforts.

[0039] Figure 1 This is a flow chart of a workshop collaborative management method for industrial big data according to a preferred embodiment of the present invention;

[0040] Figure 2 This is a regional temperature control adjustment logic diagram of a preferred embodiment of the present invention. DETAILED DESCRIPTION

[0041] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0042] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the scope of protection of the present invention is not limited to the specific embodiments disclosed below.

[0043] In the description of the present application, it should be understood that the terms "center", "longitudinal", "lateral", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the scope of protection of the present application. In addition, the terms "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, features defined as "first", "second", etc. may explicitly or implicitly include one or more of the features. In the description of the present invention, unless otherwise specified, "multiple" means two or more.

[0044] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "installed," "connected," and "connected" should be understood in a broad sense. For example, they can refer to fixed connections, detachable connections, or integral connections; they can refer to mechanical connections or electrical connections; they can refer to direct connections or indirect connections through an intermediate medium; and they can refer to internal connections between two components. Those skilled in the art will understand the specific meanings of the above terms in this application based on specific circumstances.

[0045] like Figure 1 As shown, a workshop collaborative management method for industrial big data is implemented by a control system and is used to collect data, adjust data, regulate temperature and time, and coordinate equipment control for the smelting process of multiple batches of mineral materials. The method includes the following steps:

[0046] Step S1: Using industrial IoT terminals deployed on mineral conveyor belts, key data on the types, metal element content, and impurity content of multiple batches of minerals in a mineral smelting workshop are collected in real time, and a data channel with the control system is established;

[0047] Step S2: The control system retrieves key mineral data, generates standard mineral material data, divides the minerals into piles, and controls the composition of each pile of mineral materials to be similar to form several piles of similar mineral materials;

[0048] Step S3: The control system retrieves standard ore data, automatically generates a standard smelting temperature-time control range based on the reduction rate-temperature dynamic response curve, and outputs it as a reference boundary of the smelting process control section;

[0049] Step S4: The control system retrieves the key data of each pile of similar ore and compares it with the standard ore data. Based on the temperature control and time control strategies, the temperature range and time range of different smelting areas are controlled and optimized based on the ore reduction rate-temperature change curve-zoning, forming a multivariable coordinated control of the smelting process.

[0050] Step S5: Upload the optimized control parameters generated by the control system to the workshop collaborative management platform and distribute them to the execution equipment of each smelting unit to form cross-regional and cross-batch smelting control instructions.

[0051] In the present invention, in step S1,

[0052] Step S11: Configuring a laser-induced breakdown spectrometer on the mineral conveyor line to obtain in real time the mineral type and its proportion in the mineral smelting, as well as the content of metal elements and impurities in different mineral types in each batch of mineral smelting;

[0053] Step S12: Based on the key data obtained in step S11, a three-dimensional data set including mineral type identifier, element content matrix, and impurity feature vector is constructed. Among them, D k represents the kth batch of ore, M i represents the proportion of the i-th mineral in the k-th batch of ore, C in represents the content of metal elements in the nth mineral of the i-th mineral, Z in It represents the content of impurities in the nth mineral of the i-th mineral;

[0054] Step S13: Estimating theoretical product quantity based on total ore amount and metal content Among them, M i represents the proportion of the i-th mineral in the k-th batch of ore, C in represents the content of metal elements in the nth mineral of the i-th mineral, Y in It represents the estimated reduction rate of the metal element in the nth mineral of the i-th type.

[0055] X-ray diffraction combined with laser-induced breakdown spectroscopy is used to detect the batch of minerals to be processed online, and the mineral type (such as hematite, siderite, magnetite, etc.) and its proportion are determined in real time. The proportion of mineral type = (the mass of this mineral type in this batch of ore / the total mass of this batch of ore) × 100%;

[0056] The content of iron and other metal elements in the mineral type was determined by X-ray fluorescence spectroscopy, and the content of impurity elements (such as silicon dioxide, aluminum oxide, sulfur, etc.) was determined by inductively coupled plasma emission spectroscopy. For example, the content of iron, copper, zinc, etc. in hematite, and the content of silicon dioxide, aluminum oxide, sulfur, etc. in hematite are shown in Table 1;

[0057] Table 1

[0058]

[0059]

[0060] Generate a unique identifier for each batch of minerals and collect key data for each batch of minerals, where the key data include the mineral type and its proportion in this batch of minerals, and the metal element content of this mineral type. Based on the key data obtained, a key data set is generated for each batch of minerals, providing basic input for calculating standard ore data, grouping similar ore materials, and adjusting smelting temperature and time in subsequent steps.

[0061] Based on the aforementioned key data set and the estimated theoretical reduction rate of the metal to be smelted (obtained through experiments), the theoretical product amount is estimated. This theoretical product amount provides an important reference for predictive process control and dynamic optimization. When the actual recovery rate deviates from the predicted value, the original data can be traced back in time to analyze the cause.

[0062] In the present invention, step S2 includes the following steps:

[0063] Step S21: Determine the number of piles based on the key data of the minerals, and obtain the average data of each pile as the standard mineral data;

[0064] Step S22: Divide the minerals into several piles of similar mineral materials according to the required number of piles;

[0065] Step S23: Based on the standard mineral material data, a similarity threshold is set for several piles of similar mineral materials, and whether the several piles of similar mineral materials are within the similarity threshold range is determined according to the similarity threshold, and adjustments are made.

[0066] In step S21, the determination of standard ore data is specifically the proportion of the same mineral type in mineral smelting, the content of metal elements and impurities in the same mineral type, and the average value in several piles of similar ore materials, that is, Where n represents the number of stacks.

[0067] By establishing standard ore data as a "reference system" for pile separation, the composition of each pile of ore can be more concentrated, homogeneous and controllable within the allowable fluctuation range, avoiding local over-reduction or under-reduction and improving metal recovery rate.

[0068] By dividing the minerals into piles, the key data of several piles of similar mineral materials formed by the piles are close to the standard mineral material data, which facilitates the subsequent regulation of the temperature range and time range.

[0069] Based on the standard mineral material data, similarity thresholds are set for several piles of similar mineral materials. The similarity threshold is based on the tolerance fluctuation range obtained from expert experience, with a threshold deviation of ±5%. The key data of the obtained similar mineral materials are compared with the standard mineral material data to quickly identify data that deviates from all piles (heterogeneous mineral materials).

[0070] Among them, the key data of all similar mineral materials are kept within the set tolerance range, thereby achieving uniformity and controllability at the composition level. This not only provides a basis for the precise control of subsequent smelting temperature and time, but also effectively reduces the risk of process disturbances caused by raw material fluctuations. The smaller the difference between similar mineral materials, the more consistent the metal reduction behavior during the smelting process. As a result, the "reduction rate-temperature-time" control model constructed based on standard mineral material data can be efficiently adapted in actual production, ensuring that each batch of mineral materials can react stably within the optimal parameter range. As a result, the smelting process can be precisely controlled under dynamic regulation, which not only ensures the improvement of metal recovery rate, but also reduces energy consumption and resource waste, thereby improving the stability, controllability and economy of the entire smelting system.

[0071] It should be noted that by establishing "standard mineral material data" and setting up a unified comparison benchmark for each pile of similar mineral materials, and using this as the core to sort the minerals, not only can similar mineral materials be more uniform in chemical composition and significantly reduce process disturbances caused by raw material fluctuations, but it also provides an accurate input basis for the subsequent establishment of a "reduction rate-temperature change curve-time" mechanism based on mineral material composition, so that the smelting temperature and time can be accurately matched and dynamically adjusted, reducing smelting temperature fluctuations, local over-reduction or insufficient reduction caused by sudden changes in mineral material composition.

[0072] In the present invention, step S3 includes the following sub-steps:

[0073] Step S31: Establish a deep neural network model based on historical smelting data to determine the reduction rate of a certain mineral under temperature and time Y(T, t) = 1-e -ki(T)·t , where Y(T, t) represents the reduction rate of the i-th mineral at temperature T and time t, and ki(T) represents the reaction rate constant, which is obtained experimentally;

[0074] Step S32: Calculate the reduction rate-temperature curve of similar minerals based on the reduction rate of a certain mineral under temperature and time. Then determine the smelting temperature and time under different reduction rates, where p i represents the proportion of the i-th mineral in similar mineral materials, w i Indicates the iron content in the i-th mineral.

[0075] Considering that different similar ores have similar compositions, but different metal types, mineral structures and impurity components in different ores, their reduction behaviors at different temperatures and times are different. For example, ores with high iron content react faster at high temperatures, while ores with more impurities may require longer time or higher temperatures to complete effective reduction;

[0076] By constructing a reduction rate-temperature change curve, the reaction characteristics of each metal are quantitatively modeled, and temperature control settings can be "tailor-made" for different ores, thereby ensuring a more complete and accurate smelting process and avoiding insufficient reaction or excessive smelting.

[0077] The result outputted in step S3, namely the "optimal temperature-time interval at the target reduction rate", can be directly used to adjust the temperature and time of each smelting zone (such as the preheating zone, the primary reduction zone, the main reduction zone, etc.) in the subsequent step S4. By dynamically zoning and controlling different zones, the linkage and reaction coordination of the smelting process can be enhanced, thereby improving the overall process efficiency and resource utilization.

[0078] It should be noted that too high a temperature or too long a time during the smelting process will not only cause energy waste, but may also lead to secondary losses such as metal volatilization and impurity penetration; too low a temperature may lead to incomplete reduction and failure of metal precipitation. Therefore, step S3 accurately identifies the reaction conversion efficiency of the metal under different conditions, thereby setting the optimal energy consumption point and realizing a "just enough" smelting strategy, effectively reducing smelting energy consumption and metal loss, and improving product qualification rate.

[0079] like Figure 2 As shown, in the present invention, in the step S4, different smelting zones are obtained by the reduction rate of the smelted metal, and the different smelting zones include: a preheating zone, a primary reduction zone, a main reduction zone, a melting zone, and an iron-tapping slow cooling zone.

[0080] The following examples illustrate the preheating zone, primary reduction zone, main reduction zone, melting zone, and iron tapping and slow cooling zone:

[0081] Preheating zone: The corresponding reduction rate is less than 0.1, and the ore is preliminarily heated to reach the reaction starting temperature to prevent structural damage caused by violent reaction;

[0082] Initial reduction zone: The corresponding reduction rate is greater than or equal to 0.1 and less than 0.4, and the ore begins to undergo reduction reaction. The reaction rate at this stage is slow, and the temperature control accuracy requirement is high;

[0083] Main reduction zone: The corresponding reduction rate is greater than or equal to 0.4 and less than 0.85. It is the most intense reaction stage, the reduction rate increases fastest, and it is the key area for temperature control;

[0084] Melting zone: The corresponding reduction rate is greater than or equal to 0.85, the metal gradually melts and separates, and fully reacts with the charge;

[0085] Iron tapping slow cooling zone: controls the temperature drop to prevent metal oxidation and structural instability.

[0086] In the present invention, in step S4, the key data of each pile of similar ore to be smelted is compared with the standard ore data, and the difference in mineral type proportion and metal element content is calculated. The offset of different temperature control zones is calculated based on the reduction rate-temperature change curve through the difference, and the temperature range and time range are adjusted according to the offset.

[0087] Through the "data-driven + multi-zone temperature control coordination" mechanism, fitting is performed according to the reduction rate of each metal at different temperatures and times, and different smelting areas are dynamically divided. The optimal temperature and reaction time range required for each smelting temperature zone is dynamically calculated and adjusted through the key data differences of similar ores, so as to achieve coordinated dynamic adjustment of smelting temperature and time in different smelting areas, ensure that the adjustment of metal smelting temperature and time is based on its reduction rate at different temperatures and times, reduce the loss of unreduced metal, avoid energy waste or charge damage caused by excessively high temperatures, and reduce metal loss and product quality fluctuations caused by differences in raw material composition.

[0088] A workshop collaborative management device for industrial big data, comprising:

[0089] Mineral material data collection and standard modeling module, used to collect key data required for mineral smelting and build standard mineral material data for pile sorting and control reference;

[0090] The ore pile classification and similarity control module is used to reasonably classify different batches of ore according to their composition and structure, forming several piles of similar ore for unified control;

[0091] Temperature-reduction rate modeling and control strategy formulation module, which is used to build a functional relationship model between the ore reduction rate and temperature / time, and formulate standard smelting temperature and time ranges accordingly;

[0092] The temperature and time dynamic adjustment and coordinated control module is used to make differentiated adjustments to the temperature and time control range during the smelting process based on the difference between each pile of similar ore and the standard ore.

[0093] An electronic device includes a processor and a memory, wherein the memory stores computer-readable instructions. When the computer-readable instructions are executed by the processor, the steps in the above-mentioned management method are executed.

[0094] A storage medium stores a computer program, which, when executed by a processor, executes the steps of the management method.

[0095] In summary, the present invention constructs a mineral material data set by collecting key mineral material data, determines standard mineral material data, and introduces a similarity threshold judgment mechanism to construct similar mineral materials with balanced composition, effectively reducing the disturbance caused by differences in raw material composition, and establishing a dynamic smelting parameter model based on the reduction rate-temperature change curve, so that all types of similar mineral materials can obtain matching optimal smelting temperature and time range, thereby realizing precise control of the smelting reaction. Through the "data-driven + multi-zone temperature control coordination" mechanism, the composition differences between similar mineral materials and standard mineral materials are quantitatively analyzed, and feedback is given to each temperature control zone for dynamic adjustment of temperature and time, realizing full-chain closed-loop control from raw material perception to process regulation, effectively improving the stability and smelting efficiency of the mineral material smelting process, and reducing metal loss and product quality fluctuations caused by differences in raw material composition.

[0096] The above description is based on the ideal embodiment of the present invention. Based on the above description, relevant personnel can make various changes and modifications without departing from the technical scope of this invention. The technical scope of this invention is not limited to the content of the specification and must be determined according to the scope of the claims.

Claims

1. A workshop collaborative management method for industrial big data, characterized by: The method is executed by a control system and is used to collect data, adjust data, regulate temperature and time, and coordinate equipment control during the smelting process of multiple batches of ore materials. The method includes the following steps: Step S1: Using industrial IoT terminals deployed on mineral conveyor belts, key data on the types, metal element content, and impurity content of multiple batches of minerals in a mineral smelting workshop are collected in real time, and a data channel with the control system is established; Step S2: The control system retrieves key mineral data, generates standard mineral material data, divides the minerals into piles, and controls the composition of each pile of mineral materials to be similar to form several piles of similar mineral materials; Step S3: The control system retrieves standard ore data, automatically generates a standard smelting temperature-time control range based on the reduction rate-temperature dynamic response curve, and outputs it as a reference boundary of the smelting process control section; Step S4: The control system retrieves the key data of each pile of similar ore and compares it with the standard ore data. Based on the temperature control and time control strategies, the temperature range and time range of different smelting areas are controlled and optimized based on the ore reduction rate-temperature change curve-zoning, forming a multivariable coordinated control of the smelting process. Step S5: Upload the optimized control parameters generated by the control system to the workshop collaborative management platform and distribute them to the execution equipment of each smelting unit to form cross-regional and cross-batch smelting control instructions.

2. The workshop collaborative management method of industrial big data according to claim 1, characterized in that: In the step S1, Step S11: Configuring a laser-induced breakdown spectrometer on the mineral conveyor line to obtain in real time the mineral type and its proportion in the mineral smelting, as well as the content of metal elements and impurities in different mineral types in each batch of mineral smelting; Step S12: Based on the key data obtained in step S11, a three-dimensional data set including mineral type identifier, element content matrix, and impurity feature vector is constructed. Among them, D k represents the kth batch of ore, M i represents the proportion of the i-th mineral in the k-th batch of ore, C in represents the content of metal elements in the nth mineral of the i-th mineral, Z in It represents the content of impurities in the nth mineral of the i-th mineral; Step S13: Estimating theoretical product quantity based on total ore amount and metal content Among them, M i represents the proportion of the i-th mineral in the k-th batch of ore, C in represents the content of metal elements in the nth mineral of the i-th mineral, Y in It represents the estimated reduction rate of the metal element in the nth mineral of the i-th type.

3. The workshop collaborative management method of industrial big data according to claim 1, characterized in that: In the step S2, the following steps are included: Step S21: Determine the number of piles based on the key data of the minerals, and obtain the average data of each pile as the standard mineral data; Step S22: Divide the minerals into several piles of similar mineral materials according to the required number of piles; Step S23: Based on the standard mineral material data, a similarity threshold is set for several piles of similar mineral materials, and whether the several piles of similar mineral materials are within the similarity threshold range is determined according to the similarity threshold, and adjustments are made.

4. The workshop collaborative management method of industrial big data according to claim 1, characterized in that: In step S21, the determination of standard ore data is specifically the proportion of the same mineral type in mineral smelting, the content of metal elements and impurities in the same mineral type, and the average value in several piles of similar ore materials, that is, Where n represents the number of stacks.

5. The workshop collaborative management method of industrial big data according to claim 1, characterized in that: In step S3, the following sub-steps are included: Step S31: Establish a deep neural network model based on historical smelting data to determine the reduction rate of a certain mineral under temperature and time Y(T, t) = 1-e -ki(T)·t , where Y(T, t) represents the reduction rate of the i-th mineral at temperature T and time t, and ki(T) represents the reaction rate constant, which is obtained experimentally; Step S32: Based on the reduction rate of a certain mineral under temperature and time, a reduction rate-temperature curve of similar minerals is constructed. Then determine the smelting temperature and time under different reduction rates, where p i represents the proportion of the i-th mineral in similar mineral materials, w i Indicates the iron content in the i-th mineral.

6. The workshop collaborative management method of industrial big data according to claim 1, characterized in that: In step S4, different smelting zones are obtained by the reduction rate of the smelted metal, and the different smelting zones include: a preheating zone, a primary reduction zone, a main reduction zone, a melting zone, and a tapping and slow cooling zone.

7. The workshop collaborative management method of industrial big data according to claim 6, characterized in that: In step S4, the key data of each pile of similar ore to be smelted is compared with the standard ore data, and the difference in mineral type proportion and metal element content is calculated. The offset of different temperature control zones is calculated based on the reduction rate-temperature change curve through the difference, and the temperature range and time range are adjusted.

8. A workshop collaborative management device for industrial big data, characterized in that: include: Mineral material data collection and standard modeling module, used to collect key data required for mineral smelting and build standard mineral material data for pile sorting and control reference; The ore pile classification and similarity control module is used to reasonably classify different batches of ore according to their composition and structure, forming several piles of similar ore for unified control; Temperature-reduction rate modeling and control strategy formulation module, which is used to build a functional relationship model between the ore reduction rate and temperature / time, and formulate standard smelting temperature and time ranges accordingly; The temperature and time dynamic adjustment and coordinated control module is used to make differentiated adjustments to the temperature and time control range during the smelting process based on the difference between each pile of similar ore and the standard ore.

9. An electronic device, characterized in that: The invention comprises a processor and a memory, wherein the memory stores computer-readable instructions, and when the computer-readable instructions are executed by the processor, the steps in the method according to any one of claims 1 to 7 are executed.

10. A storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are executed.

Images