Classifications

• • B—PERFORMING OPERATIONS; TRANSPORTING
  • B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
  • B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
  • B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
  • B07C5/34—Sorting according to other particular properties
  • B07C5/342—Sorting according to other particular properties according to optical properties, e.g. colour
  • B07C5/3425—Sorting according to other particular properties according to optical properties, e.g. colour of granular material, e.g. ore particles, grain

Definitions

• the present invention relates to the field of recycling and recovery of spoil and rubble from public works sites, as well as quarry aggregates (non-secondary raw material).
• waste from construction represents a deposit of nearly 250 million tonnes per year, or 10 times more than household waste. IN 2015, only 40% of this waste was recycled and recovered while the programming of the law on energy and environmental transition sets a recovery rate of 70% by 2020.
• the RECYBETON project produced a report “Theme 1 Technology for selective sorting of crushed concrete aggregates” Author: C. DEBOFFE – NEO ECO R/15/RECY/027 LC/13/RECY/31 September 2015 presenting the general principles of sorting construction waste.
• a moving conveyor containing scrap particles is imaged using a vision system to create a vision image corresponding to a synchronized location of the conveyor, and is detected by using a detection system to create a detection matrix corresponding to the synchronized location.
• This prior art detection system comprises at least one network of analog proximity sensors.
• a control system analyzes the vision image as a vision matrix of cells, and generates a vision vector containing vision data from the vision matrix for the particle.
• This control system analyzes the detection matrix and generates a detection data vector containing detection data from the detection matrix for the particle.
• the control system classifies the particle into one of at least two classifications of a material based on the vision data vector and the sensing data vector.
• the solutions of the prior art are not suitable for automatic sorting of rubble at high throughput for the on-site recovery of rubble from construction sites. They are suitable for identifying the presence of one or more compounds based on re-emission generally by fluorescence in certain wavelengths for the purposes of analysis and overall classification of materials passing on the conveyor.
• the present invention relates, in its most general sense, to a process for the automatic treatment of spoil having the combination of technical characteristics set out in claim 1.
• the excavated material includes excavated material in the form of aggregates, construction waste, excavated soil, excavated soil and sediment, on a conveyor equipped with a hyperspectral imager. Their processing takes place on a conveyor equipped with a hyperspectral imager comprising means for comparing in real time the zone of the flow of cuttings imaged with a base of hyperspectral signatures characteristic of the undesirable constituents, said means controlling a means of deflecting the flow towards a secondary container in the event of detection of undesirable constituents in said imaged area (8) and/or means for deflecting the flow towards another secondary container in the event of detection of desirable constituents in said imaged area.
• said hyperspectral imager is made up of hyperspectral sensors having a sensitivity range of between 100 microns and 200 nanometers.
• said hyperspectral imager consists of a hyperspectral camera or a multispectral camera.
• said hyperspectral imager is made up of an assembly of sensors forming a composite multispectral sensor.
• said hyperspectral imager is made up of an assembly of sensors having a sensitivity range of between 100 microns and 200 nanometers and sensors having a sensitivity range of less than 200 nanometers, in particular X-ray.
• excavated material means mineral and/or organic elements removed from a work site, and including, depending on the site, bulk rubble coming for example from a demolition site, construction waste, spoil, excavated earth and sediments.
• It comprises a rubble belt conveyor (1) driving the recoverable inert rubble into a recovery bin (2), or, depending on the position of a trapdoor (4), to a waste bag or a bin (3) intended to recover non-inert or non-recoverable waste.
• This trapdoor (or any other form of switching the contents of the belt) is controlled by a computer (5) executing a program for using data coming from a characterization cell (6).
• This cell (6) is formed by a space surrounded by a tarpaulin (7) making it possible to reduce the light disturbances of an imaged portion (8) of the rubble transported by the belt (1).
• This cell (6) includes a hyperspectral imager (10) and optionally an excitation source (11).
• the goal is to detect in real time the presence of contaminants (sulfate, organic pollutant) and the nature (type of rock, hardness), and/or to classify plastic objects and possibly sort them qualitatively or quantitatively depending on the type. of micro-plastics and/or sorting materials in a qualitative or quantitative manner passing through the imaged portion (8) in order to control the position of the trapdoor (4).
• the imager (10) consists of a sensor or a set of hyperspectral sensors having a sensitivity range of between 100 microns and 200 nanometers. It may be a hyperspectral camera, or a multispectral camera, or an assembly of sensors forming a composite multispectral sensor.
• a laser or X-ray source and corresponding sensors can be coupled with hyperspectral imaging to reinforce or complete the characterization of certain materials or pollutants.
• a robotic probe (104) coupled to an optical fiber can be introduced into the load to obtain multispectral information at the heart of the load.
• the probe (104) can also consist of a physicochemical sensor; for example a thermal probe, or a pH meter, or even a sound sensor to characterize sound signatures, or even a pressure sensor.
• it further comprises at least one three-dimensional image sensor and means for processing the signals provided by said sensor for estimating the volume of said conveyor.
• the characterization of the materials present in the content passing through the imaged area (8) can be carried out by algorithmic processing or by a neural network after a supervised learning step.
• the training of the predictive model is carried out using a database and reference samples.
• a first processing model consists of converting raw data from the sensor into reflection. This normalization step refers to the method that uses raw data measured on >99% reflectance reference hardware (Spectralon(R)) and electronic noise data measured without an illuminant (source) to normalize the sample data between these two spectra (i.e. 0 and 100% reflection).
• a model is generated from the prior recording of these raw reference data.
• Raw data measured on 8 reference materials (from 2% to 99% reflection) and electronic noise are used, a model can be trained for each combination of parameters of a device.
• a second level of processing predicts the variables of interest (soil composition, presence of pollutants and quantity of pollutant) from the reflection of a sample.
• published training databases pure compound spectral library, e.g. USGS Spectral Library
• data produced on artificial samples produced in the laboratory or data produced on samples analyzed in the laboratory. In the case where a batch of analyzed samples comes from a particular site, a model can be trained on this batch only or this batch can be used to improve a pre-trained model on an existing base by learning method by transfer.
• Data processing applies to imaging data, the data from analyzed subsamples makes it possible to interpret or refine an initial interpretation of the core samples.
• the model generated with the spectrometer data makes it possible to produce analyzes in real time, including analyzes referenced against data from COFRAC certified laboratories.
• the coupling of on-site imaging then spectrometry responds to the diagnosis phase of a site, then to the works phase. Selective sorting of excavated soil according to their waste class is possible.
• Learning can be shared from laboratory analyses, with equipment, equipped with a high-performance hyperspectral camera, to record the spectral signatures of a large number of reference samples, and provide a database accessible to a plurality of field equipment equipped with less efficient and less expensive sensors.
• each field equipment is calibrated using reference samples whose spectral signature has previously been recorded in the database.
• We calculate a correction function allowing the content of the database to be used with equipment different from that used for the initial analysis.
• the samples are distinguished on the one hand by the nature of the substrate, and on the other hand by the nature of the pollutants present.
• the reference substrate can be characterized by physicochemical analyses. It can also be prepared from predetermined components to prepare substrates by assembly.
• the loads consist of deconstruction materials coming from a demolition site.
• the sensors make it possible to check the nature of waste and excavated material and their qualification in relation to landfill, reuse or recycling standards (sulphate content, bituminous coating, etc.).
• This variant also concerns the verification of loads presented at the entrance to a recovery site, for compliance of the load with the nature of the authorized excavated material. Rubble, secondary raw materials, sediments and excavated soil can be checked and sorted after transport in truck or barge bodies.

Landscapes

• Processing Of Solid Wastes (AREA)
• Investigating Or Analysing Materials By Optical Means (AREA)
• Image Processing (AREA)

Applications Claiming Priority (2)

Publications (3)

Family

ID=83690537

Family Applications (1)

Country Status (3)

Families Citing this family (1)

Family Cites Families (5)

• 2022
  • 2022-07-26 FR FR2207694A patent/FR3138331A1/fr active Pending
• 2023
  • 2023-07-25 EP EP23748489.4A patent/EP4561764B1/de active Active
  • 2023-07-25 WO PCT/EP2023/070629 patent/WO2024023110A1/fr not_active Ceased

Also Published As

Similar Documents

Legal Events