Method and system for control of steel manufacturing plants

Abstract

An aspect of the disclosure provides a method of controlling a steel manufacturing plant. The method comprising: determining, based on x ray data and / or penetrative neutron scanning data of a raw mate

Description

Field of Invention The present invention relates to a method and system for controlling a steel manufacturing plant. The present invention also relates to a method and system of detecting anomalies in a raw material feed for a steel manufacturing plant and providing verification for a steel manufacturing plant. Background In a steel manufacturing plant, the basic raw materials used include coal (and its derivatives), iron ore (and its derivatives), flux materials and scrap steel. These raw materials are sourced from various suppliers before being used in steel production. The quality of output steel, the efficiency of manufacture, and ultimate sustainability of steel depend heavily on the composition of input materials. In steel manufacturing, lacking detailed insights into the raw materials delivered by suppliers and leads to inconsistent product quality, process inefficiencies, increased costs, and environmental impact. Manufacturers struggle to control the steelmaking process because of this, resulting in quality deviations, inefficiencies, excessive waste, and supply chain challenges. This can ultimately disrupt production, raise operational costs, and affect the overall sustainability of the manufacturing process. The system and methods described below seek to address these problems. US 2023 / 0314077 describes methods and systems for determining a feed rate (unit mass / unit time) of metallic scrap material in real time being charged to an electric arc furnace (EAF). US 2023 / 0288142 describes methods and systems for determining a respective mass associated with respective portions of the respective layers of metallic scrap material deposited into a charging-bucket associated with a batchwise-charged electric arc furnace (EAF). Summary Aspects and examples of the invention are set out in the claims and aim to address at least a part of the above described technical problem, and other problems. An aspect of the invention relates to a method of controlling a steel manufacturing plant. The method comprises: determining, based on x-ray data and / or penetrative neutron scanning data of a raw material feed for a furnace of said steel manufacturing plant, at least one material parameter of a part of the raw material feed; and sending a control signal based on the determined at least one material parameter, wherein the control signal is configured to be used in the control operation of the steel manufacturing plant based on the at least one material parameter. The x-ray data may comprise x-ray image data, x-ray diffraction data, x-ray scattering data, x-ray spectroscopy data etc.. Other scanning and imaging devices can be used to provide further information (further material parameters) on the parts of the raw material feed for example an optical scanner such as a video camera can be used to record images of the part and a spectroscopic scanner can be used to provide information on the composition of the part on the raw material conveyor. This additional image and spectroscopic data can be used in a similar manner to the x-ray data and / or penetrative neutron scanning data. For example, it can be utilised to determine material parameters and a control signal configured to be used in the control operation of the steel manufacturing plant based on the at least one material parameter may be provided. The control signal may be configured to cause said steel manufacturing plant to select the disposition of the part of the raw material feed in the furnace of said steel manufacturing plant based on the at least one material parameter. In this way preferable compositions (for example preferable structural, chemical and / or mineralogical compositions) for the materials placed in the furnace may be selected. For example, the method may be performed on a number of parts of the raw material feed and the disposition on those parts selected based on at least one material parameter determined for each of those parts. These parts may include: scrap steel; coking coal; iron ore; iron ore derivatives; coal; coal derivatives; and flux. In particular, the control signal may be configured to cause at least one operational parameter of said furnace (for example an operational parameter that controls the internal environment of the furnace such as a temperature control and / or pressure control) to be controlled according to the selected dispositions. For example, the disposition may comprise a stacking of parts of the raw material feed in layers in the furnace based on the least one material parameter of the parts. The control signal may in these cases cause an operational / environmental parameter of the furnace to be controlled, such as temperature and / or pressure, for example temperature and / or pressure in at least one layer of the stacking. The control signal may cause a temperature and / or pressure gradient across at least part of the disposition to be controlled for example in at least part of the stacking for example a layer of the stacking. The control signal may cause at least one of: a heating of the furnace; and a cooling of the furnace, to be controlled, The control signal may be configured to cause a timed control of the operational parameters of the furnace. The material parameter may comprise a structural parameter. The structural parameter may comprise: size and / or shape data of the part of the raw material feed. For example, the determination of the material parameter may be based at least in part on the x-ray data and the structural parameter may be based at least in part on the x-ray data. The structural parameter may further comprise density data of the part of the raw material feed, for example wherein the determination is based at least in part on the x-ray data and the structural parameter is based at least in part on the x-ray data. The material parameter may comprise a chemical parameter. The chemical parameter comprising composition data of the part of the raw material feed. For example, wherein the determination is based at least in part on penetrative neutron scanning data and the composition data is based at least in part on the penetrative neutron scanning data. The method may further comprise: associating the determined material parameter with the part of the raw material feed, wherein associating comprises: image processing analysis of the x-ray data to identify the part of the raw material field feed associated with the determined material parameter, for example wherein the image processing analysis is based on at least one of: a machine learning model for example an AI-driven characterization model; pattern matching;; image transformation; image segmentation, edge detection, molecular depth estimation; filtering and convolution; and histogram equalization. The control signal may be configured to cause addition of material (for example a part) to and / or removal of material (for example a part) from the raw material feed based on the at least one material parameter. For example, wherein the control signal causes the addition of a part to and / or removal of a part from the raw material with a particular material parameter. In particular, the control signal may be configured to control addition of a part to and / or removal of a part of the raw material feed based on the at least one material parameter of the part and based on at least one material parameter associated with at least one another part of the raw material feed. For example, the control signal may cause the addition of parts to and / or removal of parts from the raw material feed to adjust for an abundance or shortfall of a particular material parameter in parts of the raw material feed. In this manner, the composition of the material in the furnace may be controlled. The raw material feed may comprise steel for example scrap steel. The control signal described above may be based on the determined at least one material parameter and an analysis of gas emissions from the furnace. For example, wherein the control signal is configured to cause said steel manufacturing plant to select the disposition of the part of the raw material feed in the furnace of said steel manufacturing plant based on the at least one material parameter and the analysis of gas emissions from the furnace, for example during operation of the furnace. Another aspect of the invention provides a controller for performing the above-described method. The controller comprising: an x-ray scanner and / or a penetrative neutron scanner configurable to scan a raw material feed of a steel manufacturing plant; and a computing system configurable to receive x-ray data and / or penetrative neutron scanner data from the x-ray scanner and / or the penetrative neutron scanner and configurable to provide the control signal to control operation of the steel manufacturing plant. The x-ray scanner may for example provide x-ray data such as x-ray image data, x-ray diffraction data, x-ray scattering data, x-ray spectroscopy data. A further aspect is directed to a steel manufacturing plant, comprising the controller described above. Also described is an aspect directed to a method of detecting anomalies in a raw material feed for a steel manufacturing plant. The method comprising: scanning vehicle carried loads of the raw material feed with an high-energy x-ray scanner prior to unloading of the vehicle carried load to produce high-energy x-ray data of the carried load; detecting the presence and / or absence of anomalous material in the carried load based on the high-energy x-ray data; and sending a detection signal based on the presence and / or absence of anomalous material. The high energy x-ray scanner may have an energy of between 3-9MeV, for example between 6 and 9 MeV, for example 9MeV. Detecting the presence and / or absence of anomalous material may comprise image processing analysis of the high-energy x-ray data. For example, wherein the image processing analysis is based on at least one of a machine learning model for example an Al-driven characterization model, pattern matching, edge detection, image transformation, image segmentation, molecular depth estimation, filtering and convolution, histogram equalizer. The anomalous material may comprise at least one of: explosive materials; toxic materials; and / or bulking materials. The carried load may comprise: at least one of: scrap steel; coking coal; iron ore; iron ore derivatives; coal; coal derivatives; and flux. The method further comprises removing the detected anomalous material based on the detection signal. Another aspect is directed to a method of manufacturing steel using the above-described methods. A further aspect is directed to a computer readable non-transitory storage medium comprising a program for a computer configured to cause a processor to perform the method of any of the previous method claims. Yet another aspect is directed to a steel manufacturing facility. The steel manufacturing facility comprising: a staging area for the delivery of vehicle carried loads of a raw material; at least one conveyor configured for moving raw material from the staging area to a furnace; and a high energy x-ray scanner configured for scanning vehicle carried loads of raw material. The steel manufacturing facility / plant may comprise a gantry, wherein the high-energy x-ray scanner is mounted on the gantry and for example wherein the gantry is positioned in or near to the staging area for example at an entrance of the staging area. An aspect of the disclosure is also a verification system for the above-described steel manufacturing facility. The verification system comprising: an imaging device configured to capture images of a vehicle carrying a vehicle carried load; and a controller that associates and stores captured images of the vehicle with scanned x-ray data of the vehicle carried load carried by said vehicle and captured by the high energy x-ray scanner. The controller may also be configured to associate at least a part of a prepared raw material feed from said vehicle with x-ray data and / or image data of said vehicle. For example, the control may be configured to associate at least a part of a prepared raw material feed from said vehicle conveyed by the conveyor with x-ray scan data and / or image data of said vehicle . The association may comprise a verifiable time stamp of the image data and / or x-ray data. Embodiments described herein advantageously detect unknown or hazardous materials or impurities that can disrupt the melting process, causing inefficiencies, increased energy consumption, and potential damage to equipment. A further advantage is in the determination of the quality of raw materials through determination of at least one material parameter, this advantageously identifies variability in the quality of the raw material delivered by suppliers which otherwise could result in higher operational costs due to the need for additional refining, rework, or disposal of non-conforming products. Furthermore, some of the embodiments described herein determine bulk rather than surface material properties. This provides a more representative analysis of the material properties than surface analysis. In some of the described embodiments, material properties are determined during transportation of the raw material through the steel manufacturing plant but before the raw material is introduced into a furnace. This allows the transportation of the raw material feed to be uninterrupted whilst analysis of the raw material feed is performed but also enables intervention if impurities in the raw materials are detected. Brief Description of Drawings Some practical implementations will now be described, by way of example only, with reference to the accompanying drawings in which: Figure 1 shows a system for detecting anomalies in a raw material feed for a steel manufacturing plant, verifying the raw material, and for controlling a steel manufacturing plant; Figure 2 shows a method flow diagram for detecting anomalies in a raw material feed for a steel manufacturing plant and for controlling a steel manufacturing plant; Figure 3 shows a method flow for detecting anomalies in a raw material feed for a steel manufacturing plant and verifying the raw material; and Figure 4 shows an overview data flow for the methods of Figure 2 and Figure 3 and the system of Figure 1. In the drawings and description below like reference numerals are used to indicate like elements. Specific Description System for controlling a steel manufacturing plant. Figure 1 shows a system 100 for controlling a steel manufacturing plant. The system 100 can also be used to detect anomalies in a raw material feed for the steel manufacturing plant and provide verification of vehicle carried loads used as raw material for steel manufacturing. Figure 1 shows the system 100 installed in a steel manufacturing plant. The system 100 comprises a gantry 124 mounted high energy x-ray scanner 126 and a surveillance system 128. The system 100 also comprises an x-ray scanner 132 and a penetrative neutron scanner 134 and a controller(s) 160 with database 162. The system 100 may also comprise a furnace gas emissions detector 155 for monitoring and analysing the gas emissions of the furnace 150. The gas emissions detector 155 may for example be a mass spectrometer or similar device. The steel manufacturing plant (shown in dashed lines) typically comprises a staging area 120 with entrance 122 in which vehicle carried loads 112 are delivered by vehicles 110. In addition, the steel manufacturing plant also comprises a raw material conveyor 130 connecting the staging area 120 to a storage area 140 and a furnace 150. Processes within the steel manufacturing plant are controlled from a process control interface 152. In particular, in the example shown in Figure 1 the process control interface 152 is in communication and can instruct a furnace control system 154, a furnace stacking entity 156, and an anomalous material removal entity 158. The vehicle carried loads 112 provide one or more of the basic raw materials used in the production of steel such as iron ore (and its derivatives), flux materials and scrap steel. In this example, the vehicle carried load 112 may be scrap steel. The vehicle carried load 112 might however contain anomalous material which is material that should not be used in the steel making process and which should not enter the furnace 150. This anomalous material might include hazardous material such as explosive materials for example batteries, gas cannisters, and toxic materials; and / or bulking materials such as soil or rubble. Thus, while the expected vehicle carried load might be raw material the actual load may comprise such anomalies, which system 100 seeks to identify and remove at the staging area 120 - preferably before the material is provided to the conveyor 130. To fit system 100 to the steel manufacturing plant the gantry mounted high energy x-ray scanner 126 is positioned in the staging area 120. The high-energy x-ray scanner 126 is configured to scan vehicle carried loads 112 at the staging area 120 - for example the staging area may comprise an access route for vehicles such as heavy goods vehicles (HGVs) and the gantry may be configured for scanning loads carried by such vehicles as they enter the staging area. The high-energy x-ray scanner has an energy of 9MeV allowing for penetration of generated x-rays through the exterior of the truck and through the carried load 112. Lower energy x-ray scanners could also be used for example x-ray scanners with a nominal energy of 2 to 9MeV. The surveillance system 128 is mounted in / or near to the staging area and is configured to capture vehicle identification images of vehicles 110 (in this case trucks) that enter the staging area 120 through entrance 122. The surveillance system 128 shown in the example system 100 is a video surveillance system. The x-ray scanner 132 and penetrative neutron scanner 134 are positioned for scanning material carried by the raw material conveyor 130 of the steel manufacturing plant. These scanners are configured to provide radioscopic inspection, x-ray diffraction data, and chemical analysis of material travelling on the raw material conveyor 130. The x-ray scanner is configured to provide x-ray data that may comprise x-ray image data, x-ray diffraction data, x-ray scattering data, x-ray spectroscopy data etc.. The x-ray scanner 132 in this example has two 300kV electron generators Other x-ray scanners may be used for example, 6-9MeV x-ray scanners, either gantry or conveyor based, or in free-flow mode. The penetrative neutron scanner 134 is configured to provide penetrative neutron scan data of material travelling on the raw material conveyor 130. Other scanning and imaging devices can be used to provide further information (further material parameters) on the parts travelling on the raw material conveyor for example an optical scanner such as a video camera can be used to record images of the part and a spectroscopic scanner can be used to provide information on the composition of the part on the raw material conveyor 130. The furnace gas emissions detector 155 is configured in the steel manufacturing plant to monitor and analyse the gas emissions of the furnace 150. The gas emissions detector 155 may for example be a mass spectrometer or similar device arranged to detect emitted gases in an exhaust of the furnace 150. The controller 160 is a computing system with a database 162 that is in communication with the gantry 124 mounted high energy x-ray scanner 126, surveillance system 128, x-ray scanner 132 and penetrative neutron scanner 134. The controller 160 is configured to control operation of and receive and store data from the gantry 124 mounted high energy x-ray scanner 126, surveillance system 128, x-ray scanner 132 and penetrative neutron scanner 134. Received data is stored in database 162. In addition, the controller 160 is configured to perform analysis / image processing analysis on data received from high energy x-ray scanner 126, surveillance system 128, furnace gas emission detector 155, x-ray scanner 132 and penetrative neutron scanner 134 and to provide a control signal and / or detection signal to the process control interface 152. Various image processing techniques such as image transformation, image segmentation, edge detection, molecular depth estimation, filtering and convolution, histogram equalizer can be used. In the example shown in Figure 1, the process control interface 152 is in communication with the furnace control system 154 and furnace stacking entity 156. The control signal may contain information that controls / instructs the process control interface 152 to control the furnace control system 154, and / or the furnace stacking entity 156. For example, the control signal may comprise a command and / or message data formatted to be read by the process control interface 152 and to cause the process control interface 152 to perform an action for example to control the furnace control system 154, and / or the furnace stacking entity 156. In this way, the control signal may be configured to control operation of the steel manufacturing plant based on the at least one material parameter. Other methods by which the control signal may be configured to control operation of the steel manufacturing plant may also be used. The control signal causes control of the operation of the steel manufacturing plant. The detection signal contains information that controls / instructs the process control interface 152 to control the anomalous material removal entity 158. Based on the detection signal the process control interface 152 controls the anomalous material removal entity 158 to remove anomalous material from the vehicle carried load 112 before the material leaves the staging area 120 on raw material conveyor 130. The system 100 is configured to perform the methods 200 and 300. Methods for controlling a steel manufacturing plant, detecting anomalies in a raw material feed, and providing verification of vehicle carried loads. Figure 2 shows a method 200 for controlling a steel manufacturing plant. The method 200 can also detect anomalies in a raw material feed for the steel manufacturing plant. Figure 3 shows a method 300 for providing verification of vehicle carried loads 112. The methods 200 and 300 with reference to system 100 will now be described. A heavy goods vehicle, such as truck 110 carrying a load 112 for delivery to the steel manufacturing plant enters 210 staging area 120 through entrance 122. As the vehicle 110 enters the staging area 120 the surveillance system 128 captures 312 identification images of the vehicle 110 which can be used to identify the vehicle. The surveillance system 128 is connected to the controller 160 and is configured to send these captured vehicle identification images 420 to the controller 160. Once the vehicle 110 is in the staging area 120 the high energy x-ray scanner scans 222 the vehicle carried load 112 and produces high energy x-ray image data 422 of the vehicle load 112. To capture this image data the gantry 124 moves the high-energy x-ray scanner 126 over / around the vehicle 110 so that a complete scan of the vehicle carried load 112 is obtained. Once the scan is complete, the high energy x-ray images 420 are analysed using image processing techniques to determine 224 the presence and / or absence of anomalous material in the vehicle carried load 112. The captured high energy x-ray image data of the vehicle carried load 112 is stored and the high energy x-ray image data and vehicle identification image data are associated with each other 314 and stored for example in a database, so that the truck 110 can be later identified. This is useful because if, for example, a large amount of anomalous material is detected in a particular carried load 112 it may be necessary to identify the vehicle that delivered the anomalous material. The vehicle carried load 112 is prepared for loading onto the raw material conveyor 130 by removing 228 the detected anomalous material. The prepared non-anomalous material is associated with the vehicle identification image data 420 and high energy x-ray scan image data 422 for the vehicle 110 from which the non-anomalous material originated, and this association is recorded 332 in for example database 162. Once the non-anomalous material has been prepared it is loaded 232 onto the raw material feed conveyor 130 as a raw material feed for transportation away from the staging area 120 to the furnace 150. The prepared non-anomalous material is a collection of different parts of scrap steel. Scrap steel for example might be a collection of steel from cars; buildings; etc. The parts being from various unknown sources differ in their material parameters such as shape, size, and chemistry. Aside from the classification as non-anomalous material the material parameters of the parts loaded onto the raw material conveyor 130 to form the raw material feed are unknown. These material parameters are however important to the steel manufacturing process and ultimately determine the quality of the steel produced in furnace 150. Knowledge of the material parameters of the parts of the raw material feed enables a preferable selection for and / or stacking of parts in the furnace 150 leading to an increased control of the quality of the steel that is produced by the steel manufacturing plant. To determine the material parameters of the parts of the raw material feed, the parts are scanned 234,236 by the x-ray scanner 132 and / or a penetrative neutron scanner 134 during transportation on the raw material conveyor 130 from the staging area 120 to the furnace 150. The material parameters include structural and chemical parameters of the part of the raw material feed. The structural parameters, are determined 234 from the x-ray data of the scanned raw material feed. The x-ray data may comprise x-ray image data, x-ray diffraction data, x-ray scattering data, x-ray spectroscopy data etc. The material parameters include the density, size and / or shape of the part. The chemical parameters of the raw material feed include the chemical composition of the part and are determined 236 from the penetrative neutron scan data of the raw material feed. The determined material parameters are associated 334 with the part of the raw material that was scanned. The association is stored for example in a database. This enables identification of the part later in the steel making process. This association can also be used, in combination with the vehicle identification image data, high energy x-ray image data and previous association steps, to determine the vehicle 110 and verify the vehicle carried load 112 from which the part originated. The determined material parameters for the raw material feed are used to generate 238 a control signal(s) for controlling the operation of the steel manufacturing plant. In addition to the determined material parameters, the control signal may also be based on analysis of the gas emissions of the furnace. Once generated the control signal(s) is sent to the process control interface 152. The control signal(s) are used in the control of a number of different aspects of the steel manufacturing process. In particular, in the steel making process parts of the raw material from the raw material feed are stacked in layers in furnace 150. These stacked parts are then processed (melted and exposed to pressure) to make molten steel. The properties of and order in which the parts of the raw material feed are stacked / layer in the furnace 150 is important for controlling the quality of steel that is produced. Based on the control signal, parts of the raw material feed to the furnace 150 with undesirable or particular material parameters are removed from the conveyor 130 to storage area 140. These stored parts may be discarded but may become useful in different stages of the steel making process and can be recalled, using the stored verification data or an identification tag for those parts, to the raw material feed from the storage area 140 to be used in the in the furnace 150, for example in a stacking of the furnace. In this way the parts with desirable material properties for a particular stage of the stacking process are selected 239 from the raw material feed or storage area 140 based on the control signal and are stacked 254 in layers in the furnace 150. The control signal is used in the control of the composition of the furnace. Based on the control signal 462, parts with desirable material parameters are added from storage area 140 to the raw material feed to the furnace - including addition of the parts directly in the furnace 150. The parts may be added to the furnace 150 to prepare the furnace 150 for steel manufacturing i.e. when the furnace 150 is not in operation. The parts can also be added whilst the furnace 150 is in operation and is manufacturing steel. The control signal 462 can additionally be based on real-time gas emission data from the furnace 150 and detected by furnace gas emission detector 155. The control signal 462 can be configured to cause the adjustment of the composition of the material in the furnace 150 in real-time in response to the received gas emission data from furnace gas emission detector 155. Based on this control signal, parts with desirable material parameters are added from storage area 140 to the raw material feed to the furnace 150 - including addition of the parts directly to the furnace 150 to achieve an adjusted composition in the furnace 150. The parts are added to the furnace 150 whilst the furnace 150 is in operation manufacturing steel. In this way, the control signal 462 causes real time control of the composition of the furnace 150 based on gas emission data from the furnace and the determined material parameters. The control signal is also used in the control 252 of the operational parameters of the furnace or for a particular layer or layers of the stacked material in the furnace. In particular, the optimal temperature / pressure experienced by the layers of the material stacked in the furnace 150 depends on the material parameters of the parts that make up the layer. The control signal (knowledge of the material parameters of the stacked parts) is used in the control of the operational parameters of each layer in the stack. Detailed examples on the control operation of the steel manufacturing plant based on the control signal are provided below. Dataflow in system 100 and methods 200 and 300 Figure 4 shows a data flow 400 for methods 200 and 300 of Figure 2 and Figure 3 and the system 100 of Figure 1. In more detail, a truck 110 with a vehicle carried load 112 enters the staging area 120. On entering the staging area 120, the surveillance system 128 captures vehicle identification image data 420 of the truck 110. This vehicle identification image data 420 is sent to controller 160. The vehicle carried load is scanned 222 using a high-energy x-ray scanner 126 to produce a high-energy x-ray image data 422 of the vehicle carried load 112. This high-energy x-ray image data 422 is sent the controller 160. The controller 160 associates the high-energy x-ray image data 422 and the vehicle identification image data 420 with each other and stores these associated images in database 162 so that the associated information can be accessed later. The high-energy x-ray image data 422 is also used by the controller 160 to detect 224 the presence of anomalous material in the vehicle carried load 112. The controller 160 sends 226 a detection signal 424 to the process control interface 152 based on the detected 224 presence or absence of anomalous material in the vehicle carried load. The process control interface 152 controls the anomalous material removal entity 156 for example a grabber, vehicle, conveyor etc. to remove the detected anomalous material. Alternatively, or in addition, an alarm or warning is displayed on the process control interface 152, a computing system in staging area 120, indicating the detection of anomalous material and, based on the detection signal 424, anomalous material is removed 228 from the vehicle carried load 112. The process control interface 152 provides a location of the detected anomalous material in the vehicle carried load 112 based on the received detection signal 424. The remaining non-anomalous material forms the raw material feed for the furnace 150 and is loaded 232 onto the conveyor 130 to the furnace 150. The raw material feed on conveyor 130 is scanned 234,236 using x-ray scanner 132 and / or penetrative neutron scanner 134 to generate x-ray data and / or penetrative neutron scanning data 432. The x-ray data may comprise x-ray image data, x-ray diffraction data, x-ray scattering data, x-ray spectroscopy data etc.. The scanning data 432 is sent to controller 160 which determines 234,236 material parameter(s) of the part of the scanned raw material feed. The determined material parameters are associated and stored 334 in the database 162 with the image data 420,422 for that part of the raw material feed. The controller 160 may also assign an identification tag to that part and associate and store this with the other information for that part. The controller 160 also generates a control signal 462 based on the determined material parameter and sends the generated control signal 462 to the process control interface 152, which may be for example a computing system located in a control area of the steel manufacturing plant. The process control interface 152 displays an x-ray image of a part of the raw material along with the associated material parameters based on the control signal. The steel manufacturing plant may, based on the control signal and the displayed information on the process control interface, remove part of the material feed from the raw material conveyor 130 to the storage area 140. The steel manufacturing plant may also, based on the control signal 462, and the stored associated data in database 162 recall a part from the storage area 140 to be added to the raw material feed for furnace 150. The control signal 462 is used in the control operation of the steel manufacturing plant, for example it is used in the selection 239 of material for furnace 150, disposition / stacking 254 of selected material in furnace 150, and / or in the control of environmental parameters 252 of the furnace 150. Furnace stacking control In more detail, based on the data, and in particular the material parameters, stored in the database 162 and the scanned parts available either in storage area 140 or on conveyor 130 the controller 160 determines a stacking of the furnace 150 and sends a control signal 462 to process control interface 152 that causes parts to be retrieved from the storage area 140 or conveyor 130 for stacking in furnace 150 according to the determined stacking. The stacking determined by the controller 160 may be a function of several of the determined material parameters stored in database 162 and parts may be stacked according to these several material parameters. For example, the controller 160 may be configured to determine the melting properties of parts based on the size, shape and density of the parts. The determination of the stacking made by the controller 160 can then be based on the determined melting properties of the parts. The controller 160 may then send a control signal 462 based on the determined stacking to the process control interface 152. In this way embodiments described herein may be used to provide an improved stacking of the furnace 150. For example, it may be preferable to have larger, denser parts positioned at the bottom of the stacking, and having a chemical composition devoid of containments for example those commonly found in tramp metals . In this example, the process control interface 152 instructs the furnace stacking entity 156 to stack the furnace 150 based on the control signal 462. The furnace stacking entity 156 may then retrieve parts from the storage area 140 using the assigned identifier, the determined material property, and / or the x-ray data 432. The parts can be transferred from the storage area 140 to the furnace 150 by the furnace stacking entity 156 which might comprise for example mechanical grabbers, conveyors, vehicles for example automated vehicles such as automated forklift trucks. Similarly, the control signal 462 might cause parts to be transferred by the furnace stacking entity 156 directly from the raw material conveyor 130 to the furnace 150 using for example mechanical grabbers, conveyors, vehicles for example automated vehicles such as automated forklift trucks. In this way determined material parameters of parts of the raw material feed may be advantageously used to provide an improved stacking and / or composition in a furnace of a steel manufacturing plant and provide improved control of the steel produced by the steel manufacturing plant. Gas emission characterisation and feedback system During the manufacturing of the steel, gas emission data 452 ( for example a spectral analysis of the gases emitted by furnace 150) is collected 256 by gas emission detector 155. The gas emission data 452 is sent to the controller 160 and is analysed by controller 160. The controller 160 determines in real time, based on the gas emission data, an optimal stacking and / composition or an adjustment to an existing determined stacking and / or composition of the furnace 150. The controller 160 also determines based on the received gas emission data 452 adjustments to the control parameters of the furnace 150 such as the temperature and / pressure. The controller 160 sends a control signal 462 based on these determinations to the process control interface 152. The process control interface 152 then, based on the control signal 462 instructs furnace stacking entity 156 to adjust the stacking 462 as a real-time response to the gas emission data 452. For example, by adding parts with particular material parameters to the furnace 150 whilst the furnace 150 is in operation. In this manner, system 100 provides a feedback system for steel manufacturing in which real time information from furnace gas emissions in combination with material parameters determined using x-ray scanner 132 and / or penetrative neutron scanner 134 are used in the selection of material added to the furnace to achieve a particular grade of steel. Furthermore, the gas emission data 452 is also used by the controller 160, in combination with the material parameters determined using x-ray scanner 132 and / or penetrative neutron scanner 134 of selected parts used in the stacking, to determine control parameters for the furnace 160. A control signal 462 based on this determination is sent to the process control interface 152. The process control interface 152 instructs furnace control system 154 to adjust the furnace operational parameters based on the control signal 462. In this manner, system 100 provides a feedback system for steel manufacturing in which real time information from furnace gas emissions in combination with material parameters determined using x-ray scanner 132 and / or penetrative neutron scanner 134 are used in the control of the furnace 150 in particular in the adjustment of furnace operational parameters such as furnace temperature and pressure. The controller associates and stores the received gas emission data 452 with the part or parts that have been used in the stacking of the furnace 150. This provides an additional verification of the parts received in the vehicle carried load 112. Below are three examples of determining a particular material parameter to control stacking and / or composition of the furnace 150. Determining size and shape of a part of the raw material feed to control stacking of the furnace. The system 100 and methods 200, 300, described above can be used to determine size and shape of raw material on conveyor 130 to control the stacking of the furnace 150. As outlined above, parts of the raw material feed are transported along the raw material conveyor 130. The parts on the raw material conveyor are scanned 234 using an x-ray scanner to produce x-ray data 432 of the part. The x-ray data 432 is sent to the controller 162, which in this example, processes the x-ray data (in particular the x-ray image data) to determine 234 the size and shape of the part. The x-ray data is processed using various image processing techniques such as image transformation, image segmentation, edge detection, molecular depth estimation, filtering and convolution, histogram equalizer. The determined size and shape material parameters are associated 334 with the x-ray data 432 and, if available, the penetrative neutron scanning data 432 of the part and this association along with the size and shape material parameters are stored in database 162. The part may be given an identifier (for example an identification tag), which is stored in database 162. The part is then transferred to storage area 140. The part may be stored in the storage area 140 based on the identifier, and / or determined material property (size and shape). This process is repeated for other parts of the raw material feed. Based on the data stored in the database 162 and the scanned parts available either in storage area 140 or on conveyor 130 the controller 160 determines a stacking and / or composition of the furnace 150 and sends a control signal 238 to process control interface 152 that causes parts to be retrieved from the storage area 140 or conveyor 130 and stacked in furnace 150 according to the determined stacking. In this example, the process control interface 152 instructs the furnace stacking entity 156 to stack the furnace 150 based on the received control signal 462. The furnace stacking entity 156 may then retrieve parts from the storage area 140 using the assigned identifier, the determined material property, and / or the x-ray data 432. The retrieved parts are transferred from the storage area 140 to the furnace 150 using for example mechanical grabbers, conveyors, vehicles for example automated vehicles such as automated forklift trucks. Similarly, the control signal 462 might cause the process control interface 152 to transfer parts directly from the raw material conveyor 130 to the furnace 150 using the furnace stacking entity 156 for example using mechanical grabbers, conveyors, vehicles for example automated vehicles such as automated forklift trucks. Once in the furnace 150 the parts can be stacked by the furnace stacking entity 156 according to the control signal 462. The parts may be stacked by the furnace stacking entity 156 using a crane for example an automated crane, vehicles for example automated forklift trucks etc.. Determining density of a part of the raw material feed to control stacking of the furnace. The system 100 and methods 200, 300, described above can be used to determine density of raw material on conveyor 150 to control the stacking of the furnace 150. As outlined above, parts of the raw material feed are transported along the raw material conveyor 130. The parts on the raw material conveyor are scanned 234 using an x-ray scanner 132 to produce x-ray data 432 of the part. The x-ray data 432 is sent to the controller 162, which in this example, processes the x-ray data 462 to determine the density of the part. The determined density material parameter is associated with the x-ray data 432 and if available the penetrative neutron scanning data of the part and this association along with the density material parameter is stored in database 162. The part may be given an identifier (for example and identification tag) and is then transferred to storage area 140. The part may be stored in the storage area 140 based on the identifier and / or determined material property (density). This process is then repeated for other parts of the raw material feed. Based on the data stored in the database 162 and the scanned parts available, either in the storage area 140 or on conveyor 130, the controller 160 determines a stacking and / or composition of the furnace 150 and sends a control signal 462 to process control interface 152 that causes parts to be retrieved from the storage area 140 or conveyor 130 and stacked in furnace 150 according to the determined stacking and / or composition. In this example, the process control interface 152 instructs the furnace stacking entity 156 to stack the furnace based on the received control signal 462. The furnace stacking entity 156 retrieves parts from the storage area 140 using the assigned identifier, the determined material property (density), and / or the x-ray data 432. The retrieved parts are transferred from the storage area 140 to the furnace 150 by the furnace stacking entity 156 using for example mechanical grabbers, conveyors, vehicles for example automated vehicles such as automated forklift trucks. Similarly, the control signal 462 might cause parts to be transferred directly from the raw material conveyor 130 to the furnace 150 by the furnace stacking entity 156 using for example mechanical grabbers, conveyors, vehicles for example automated vehicles such as automated forklift trucks. Once in the furnace 150 the parts can be stacked by the furnace stacking entity 156 according to the control signal 462 based on the determined stacking. The parts may be stacked by the furnace stacking entity 156 using: a crane for example an automated crane; vehicles for example automated vehicles, and conveyors. Determining elemental composition of a part of the raw material feed to control stacking of the furnace. The system 100 and methods 200, 300, described above can be used to determine the chemical composition of raw material on conveyor 130 to control the stacking of the furnace 150. As outlined above, parts of the raw material feed are transported along the raw material conveyor 130. The parts on the raw material conveyor are scanned 234 using a penetrative neutron scanner to produce penetrative neutron scanning data 432 of the part. The penetrative neutron scanning data 432 is sent to the controller 162, which in this example, processes the penetrative neutron scanning data 432 to determine the chemical composition of the part. The determined chemical composition material parameter is associated with the penetrative neutron scanning data 432 and if available the x-ray data of the part and this association along with the chemical composition material parameter is stored in database 162. The part may be given an identifier (for example an identification tag) and is then transferred to storage area 140. The part may be stored in the storage area 140 based on the identifier and / or determined material property (chemical composition). This process is then repeated for other parts of the raw material feed. Based on the chemical composition data stored in the database 162 and the scanned parts available, either in the storage area or on conveyor 130, the controller 160 determines a stacking of the furnace 150 and sends a control signal 462 to process control interface 152 that causes parts to be retrieved from the storage area 140 or conveyor 150 and stacked in furnace 150 according to the determined stacking. In this example, the process control interface 152 instructs the furnace stacking entity 156 to stack the furnace based on the control signal 462. The furnace stacking entity 156 retrieves parts from the storage area 140 using the assigned identifier, the determined material property (chemical composition), and / or the x-ray data 432. The retrieved parts are transferred from the storage area 140 to the furnace 150 using for example mechanical grabbers, conveyors, vehicles for example automated vehicles such as automated forklift trucks. Similarly, the control signal 462 might cause parts to be transferred directly from the raw material conveyor 130 to the furnace 150 using for example the furnace stacking entity 156 using for example mechanical grabbers, conveyors, vehicles for example automated vehicles such as automated forklift trucks. Once in the furnace 150 the parts can be stacked by the furnace stacking entity 156 according to the control signal. The parts may be stacked by the furnace stacking entity using: a crane for example an automated crane; vehicles for example automated vehicles, and conveyors. The system 100 and methods 200,300 can be implemented in a steel manufacturing plant to perform any one of or all of the above described: determining size and shape of part of the raw material feed to control stacking of the furnace; determining density of a part of the raw material feed to control stacking of the furnace; and determining elemental composition of a part of the raw material feed to control stacking and / or composition of material in the furnace 150. These determinations may all be made on the same part of the raw material feed as it is transported by conveyor 150. Further material parameters may also determined. Furnace operational control Furthermore, based on the determined stacking and / or composition, the controller 160 determines operational parameters to be maintained in the furnace 150 for the steel making process and sends a control signal 462 to the process control interface 152 based on this. The process control interface 152 then instructs furnace control system 154 to adjust the operational parameters of the furnace 150 based on the control signal 464. The operational parameters may include: a temperature and / pressure regimes for a layer or layers in the stacking. These regimes may include temperature parameters including heating and cooling information, pressure parameters, timing information and temperature / pressure ramp parameters that should be applied to a layer or layers of the stack. For example, it may be that a first layer of parts of the determined stacking requires a particular temperature at a particular pressure for a period of time because of the material parameters of the parts in that particular layer or the stack as a whole. For example, the determined stack may have a greater proportion of scrap steel than virgin ore which affected the operational parameters needed to produce a particular quality of steel. Based on the known material parameters of the stack the controller determines the operational parameters needed to achieve the particular quality of steel. Inventory management The stored information in database 162 may also be used to provide an inventory of the material parameters of the parts in the raw material feed and in the storage area 140 and based on this information the steel manufacturing plant adjust the parts present in the raw material feed to optimise the stacking of the furnace 150. Further examples The above system 100 and methods 200, 300 have been described in the context of a scrap steel raw material feed for a steel manufacturing plant. The same system and methods may be used in other raw material feed for steel manufacturing plants. For example, steel manufacturing plants also have a raw material feed associated with coal and coal derivatives. There is also a raw material feed associated with iron ore, iron ore derivatives and flux. Material parameters of the raw material feed of these other raw material feeds may also be determined using system 100 and methods 200,300. Material parameters that are particularly important for ores and coal may include elemental content, mineralogical content and moisture content. The above methods 200,300 may be adjusted and applied to these other raw material feeds for example by identifying coal and coal derivatives to be non-anomalous materials instead of scrap steel as above. The controller 160 may control several different raw material feeds and collate the data from these. This collated data can be used together in the determination of the stacking described above where parts, and their associated material parameters, from different material feeds are used in the determination of the stacking and / or composition of material / parts in furnace 150 and then in the creation of the stacking in the furnace 150. For example, the collated information may be used to determine a preferable composition of a charging bucket to be deposited in a furnace 150. The above system 100 and methods 200, 300 have been described with reference to truck carried loads. However, the methods 200,300 and system 100 may be applied to other vehicles delivering carried loads to a steel manufacturing plant. The other vehicles or delivery mechanisms may include but are not limited to: trains, boats, other automobiles, delivery conveyors, and planes. The raw material conveyor 130 described above may be a belt conveyor, a charging bucket or other means of transporting raw material out of the staging area 120, storage area 140 and / or furnace 150 and / or transporting material into the staging area 120, storage area 140, and / or furnace 150. The furnace 150 may for example be a blast furnace or an electric arc furnace. The high energy x-ray scanner 126 may have an energy of between 2MeV and 9Mev for example at least 2MeV, for example at least 4MeV, for example at least 6MeV, for example at least 9 MeV. For example, the x-ray scanner may have an energy between 6MeV and 9MeV.In the example described above the high energy x-ray scanner is mounted on a movable gantry. However, other non-gantry mounted high-energy x-ray scanners can be used and may be selected based on the type of vehicle 110 that is to be scanned. For example, a "side mounted" x-ray scanner may be placed on either side of a railway line so that a carried load delivered by train may be scanned. The other x-ray scanner 132 may have configurations other than the two 300kV electron generators in the example system 100 described above. For example, 6-9MeV x-ray scanners, either gantry or conveyor based, or in free-flow mode may be used. The x-ray scanner is selected to provide radioscopic images of the material on the raw material conveyor 130. The x-ray scanner may be configured to perform an x-ray diffraction analysis of a part of the raw material. This enables further material parameters of parts to be determined such as the mineralogical structure. The x-ray scanner may be configured to provide x-ray data comprising: any one of x-ray image data, x-ray diffraction data, x-ray scattering data, x-ray spectroscopy data etc. The penetrative neutron scanner 134 may have configurations other than that described above. The penetrative neutron scanner is selected to provide composition data on the material on the raw material feed conveyor. For example, conveyor based neutron scanners that use a californium source may be used. In another embodiment, a slag valorisation method is provided. Slag as a byproduct of the steel making process is scanned in bulk using penetrative, optical and spectroscopic means in real-time to determine the chemical and physical properties. The scanned slag is then graded based on the determined chemical and physical properties into valorisable and non-valorisable fractions. The above examples are to be understood as illustrative examples. Further examples are envisaged. It is to be understood that any feature described in relation to any one example may be used alone, or in combination with other 5 features described, and may also be used in combination with one or more features of any other of the examples, or any combination of any other of the examples. Furthermore, equivalents and modifications not described above may also be employed without departing from the scope of the invention, 10 which is defined in the accompanying claims.

Claims

1. A method of controlling a steel manufacturing plant, the method comprising:determining, based on x-ray data and / or penetrative neutron scanning data of a raw material feed for a furnace of said steel manufacturing plant, at least one material parameter of a part of the raw material feed; andsending a control signal based on the determined at least one material parameter,wherein the control signal is configured to be used in the control of the operation of the steel manufacturing plant based on the at least one material parameter.

2. The method of claim 1, wherein the control signal is configured to cause said steel manufacturing plant to select the disposition of the part of the raw material feed in the furnace of said steel manufacturing plant based on the at least one material parameter.

3. The method of claim 2, wherein the control signal is configured to cause at least one operational parameter of said furnace to be controlled according to the selected dispositions,for example wherein the disposition comprises a stacking of parts of the raw material feed based on the least one material parameter of the part, for example wherein the control signal causes an operational parameter to be controlled such as temperature and / or pressure in at least one region of said stacking, for example the control signal causes a temperature and / or pressure gradient across at least part of the disposition to be controlled for example in at least part of the stacking,for example the control signal may cause at least one of a heating of the furnace and a cooling of the furnace to be controlled,for example the control signal may be configured to cause a timed operational control of the furnace.

4. The method of any preceding claim, wherein the material parameter comprises a structural parameter.

5. The method of claim 4, wherein the structural parameter comprises: at least one of: size; shape; and / or density data of the part of the raw material feed, for example wherein the determination is based at least in part on the x-ray image data and the structural parameter is based at least in part on the x-ray image data.

6. The method of any preceding claim, wherein the material parameter comprises a chemical parameter, for example wherein the chemical parameter comprises composition data of the part of the raw material feed, for example wherein the determination is based at least in part on penetrative neutron scanning data and the composition data is based at least in part on the penetrative neutron scanning data.

7. The method of any preceding claim, comprising:associating the determined material parameter with the part of the raw material feed,for example, wherein associating comprises: image processing analysis of the x-ray data to identify the part of the raw material field feed associated with the determined material parameter for example wherein the image processing analysis is based on at least one of: a machine learning model for example an Al-driven characterization model; image transformation; image segmentation, edge detection, molecular depth estimation; filtering and convolution; and / or histogram equalization.

8. The method of any preceding claim, wherein the control signal is configured to cause addition of a part to and / or removal of a part from the raw material feed based on the at least one material parameter, for example wherein the control signal causes the addition of a part to and / or removal of a part with a particular material parameter from the raw material feed.

9. The method of claim 8, wherein the control signal is configured to control addition of a part to and / or removal of a part of the raw material feed based on the at least one material parameter of the part and based on at least one material parameter associated with at least one another part of the raw material feed, for example wherein the control signal causes the addition of a part to and / or removal of a part from the raw material feed to adjust for an abundance or shortfall of a particular material parameter in parts of the raw material feed.

10. The method of any preceding claim wherein the raw material feedcomprises steel for example scrap steel.

11. The method of any preceding claim, wherein the control signal isbased on the determined at least one material parameter and an analysisof gas emissions from the furnace.

12. A controller for performing the method of any one of claims 1to 11, the controller comprising:an x-ray scanner and / or a penetrative neutron scanner configurable to scan a raw material feed of a steel manufacturing plant; anda computing system configurable to receive x-ray data and / or penetrative neutron scanner data from the x-ray scanner and / or the penetrative neutron scanner and configurable to provide the control signal to control operation of the steel manufacturing plant.

13. A steel manufacturing plant, comprising the apparatus of claim12 .

14. A method of detecting anomalies in a raw material feed for a steel manufacturing plant comprising:scanning vehicle carried loads of the raw material feed with a high-energy x-ray scanner prior to unloading of the vehicle carried load to produce high-energy x-ray data of the carried load;detecting the presence and / or absence of anomalous material in the carried load based on the high-energy x-ray data; andsending a detection signal based on the presence and / or absence of anomalous material.

15. The method of claim 14, wherein the high energy x-ray scannerhas an energy of at least 6MeV for example between 6MeV and 9MeV.

16. The method of claim 14 or 15, wherein detecting comprises image processing analysis of the x-ray data wherein the image processing analysis is based on at least one of: a machine learning model for example an Al-driven characterization model; image transformation; image segmentation; edge detection; molecular depth estimation; filtering and convolution; and / or histogram equalization.

17. The method of any one of claims 13 to 16, wherein the anomalousmaterial comprises: at least one of: explosive materials; toxicmaterials; and / or bulking materials.

18. The method of claims 13 to 17, wherein the load comprises: at least one of: scrap steel; coking coal; iron ore; iron ore derivatives; coal; coal derivatives; and flux.

19. The method of claim 13 to 18 comprising: removing the detectedanomalous material based on the detection signal.

20. A method of manufacturing steel comprising any one of thepreceding method claims.

21. A computer readable non-transitory storage medium comprising aprogram for a computer configured to cause a processor to perform themethod of any of the previous method claims.

22. A steel manufacturing facility, comprising:a staging area for the delivery of vehicle carried loads of araw material;at least one conveyor configured for moving raw material from the staging area to a furnace; anda high energy x-ray scanner configured for scanning vehicle carried loads of raw material.

23. The steel manufacturing facility of claim 22, comprising a gantry, wherein the high-energy x-ray scanner is mounted on the gantry and for example wherein the gantry is positioned in or near to the staging area for example at an entrance of the staging area.

24. A verification system for the steel manufacturing facility ofclaim 22 or 23, comprising:an imaging device configured to capture images of a vehiclecarrying a vehicle carried load; anda controller that associates and stores captured images of the vehicle with x-ray data of the vehicle carried load carried by said vehicle and captured by the high energy x-ray scanner.5 25. The verification system of claim 24, comprising:associating at least a part of a prepared raw material feed from said vehicle with x-ray data and / or image data of said vehicle for example associating at least a part of a prepared raw material feed from said vehicle conveyed by the conveyor with x-ray data and / or10 image data of said vehicle for example wherein the associating comprises a verifiable time stamp of the image data and / or x-ray data on the association.

Images