Method for determining in real time and continuously the particle rate of a given material

Abstract

The invention describes a method for determining in real time and continuously a particle rate of a given material in a sample, comprising steps of:E1: optical measurement of a signature of the sample using an optical sensor (10);E2: identification by a processing unit (20) of a type of the sample by means of a classification model trained on a learning database comprising a plurality of reference signatures, each reference signature being associated with a type of a reference sample; andE3: determination by the processing unit (20) of the particle rate of the given material in the sample from the type of the identified sample and a correspondence table associating with each of a plurality of types of reference samples a reference particle rate of the given material. Figure for the abstract: Fig. 3

Description

Title of the invention: Method for determining in real time and continuously a particle rate of a given material FIELD OF THE INVENTION

[0001] The present invention belongs to the field of air quality monitoring, and relates to a method for determining in real time and continuously a rate of particles of a given material in a sample, and a system for determining in real time and continuously a rate of particles of a given material in a sample. The present invention can more particularly be used to determine in real time and continuously the rate of respirable crystalline silica emitted by a construction site operation. STATE OF THE ART

[0002] Air quality is impacted by the type and number of particles suspended in the air. Air quality can have consequences on the health of people breathing this air, especially when certain potentially harmful particles are present in the air.

[0003] In particular, on construction sites, air quality is likely to be deteriorated due to the emission of dust containing particles of certain materials, which can present dangers for operators when they breathe them for a prolonged period. For example, respirable crystalline silica dust, ballast dust, lime, other hydraulic binders, polluted earth dust, chromium VI particles, or diesel particles, are likely to be emitted by various construction site operations.

[0004] Certain types of particles, such as respirable crystalline silica, present a particularly high health risk, with harmful effects on health. Crystalline silica is classified as respirable when the inhaled particles have a diameter of less than 10 pm, which allows them to reach the pulmonary alveoli and cause pathologies such as silicosis or cancer. Work involving exposure to respirable crystalline silica dust is classified as a carcinogenic activity as of January 1, 2021.

[0005] It is therefore important to monitor air quality, that is to say to identify and determine the particle rate of a given material, in order to put in place protective measures for operators working on construction sites which are adapted according to the type and quantity of particles emitted.

[0006] Current methods for monitoring air quality involve taking occasional samples from a construction site. These samples are then tested in the laboratory, their chemical analysis making it possible to determine the rate of particles of given materials, for example respirable crystalline silica, in the sample.

[0007] The collection and analysis of samples represents a complex and lengthy process, of the order of at least one working day. A device is thus worn all day by an operator, accumulating particles during the day, and is then analyzed the next day in a laboratory.

[0008] Consequently, these current methods do not allow the risk to be assessed, either continuously or in real time or for all operations carried out on construction sites, for operators present on the construction sites. The operator's protection and alert measures cannot therefore be adapted according to the actual particle rate in real time and continuously. As a result, the operator may be subjected to particle rates of materials that are potentially hazardous to health, such as respirable crystalline silica, ballast dust, etc., for a relatively long period corresponding to the time between two samples. The management of the health risk linked to the exposure of operators to particles of certain types of materials is therefore unsatisfactory. Statement of the invention

[0009] An objective of the invention is to propose a method for determining a particle rate of a given material in a sample which is more efficient than current methods, in particular which allows real-time and continuous determination of the particle rate of the given material in an air sample.

[0010] For this, the invention describes a method for determining in real time and continuously a rate of particles of a given material in a sample, comprising steps of: El: optical measurement of a sample signature; E2: identification by a processing unit of a type of the sample by means of a classification model trained on a training database comprising a plurality of reference signatures, each reference signature being associated with a type of a reference sample; and E3: determination by the processing unit of the particle rate of the given material in the sample from the type of sample identified and a correspondence table associating with each of a plurality of types of reference samples a reference particle rate of the given material.

[0011] Some preferred but non-limiting features of the method for determining a particle rate of a given material described above are the following, taken individually or in combination:

[0012] - the identification of the type of the sample during step E2 comprises a comparison of the signature of the sample with the plurality of reference signatures stored in the training database, and the classification model is a k nearest neighbors type model; - the classification model is a neural network, support vector machine, stochastic gradient algorithm, or random forest algorithm type model; - the given material is at least one of respirable crystalline silica, ballast dust, lime, diesel particles, polluted earth dust, other hydraulic binders, Chromium VI particles, and / or other particles emitted by various construction site operations; - the signature of the sample measured at step E1 is a function of the size and number of particles present in the sample; - the signature of the sample measured in step E1 comprises a histogram of the distribution of a number of particles in the sample as a function of the size of the particles; - the type of sample identified in step E2 is defined by a nature of the sample and an activity of obtaining the sample; - the signature of the sample is measured periodically in step E1 at each measurement period, the type of the sample is identified periodically in step E2 at each calculation period and the particle rate is determined periodically in step E3 at each calculation period; - the calculation period is equal to or greater than the measurement period, the measurement period and the calculation period are between 1 second and 1 hour; - the method further comprises a step E4 of determining by the processing unit an exposure to the particles of the given material from the rate of particles of the given material determined in step E2 and a time of exposure to said particles of the given material; - the method further comprises a step E5 of alerting a user when exposure to particles of the given material exceeds a predetermined exposure threshold.

[0013] According to a second aspect, the invention also describes a system for determining in real time and continuously a rate of particles of a given material in a sample, comprising: - an optical sensor adapted to measure a signature of a sample; and - a processing unit configured to: - identifying a type of the sample by means of a classification model trained on a training database comprising a plurality of signatures of reference, each reference signature being associated with a type of a reference sample, and - determine the particle rate of the given material in the sample, from the type of sample identified and a correspondence table associating with each of a plurality of reference sample types a reference particle rate of the given material.

[0014] The optical sensor may be configured to perform particle counting.

[0015] The optical sensor may be portable.

[0016] The system for determining in real time and continuously a rate of particles of a given material in a sample described above may further comprise storage means configured to store the measurements carried out by the optical sensor and / or the learning database and / or the correspondence table. DESCRIPTION OF THE FIGURES

[0017] Other characteristics, aims and advantages of the present invention will appear on reading the detailed description which follows, given by way of non-limiting example, which will be illustrated by the following figures:

[0018] [Fig.l] [Fig.l] is a block diagram representing different steps of a method for determining a particle rate according to an embodiment of the invention.

[0019] [Fig.2] [Fig.2] is a block diagram representing different stages of a process of determination of a particle rate according to one embodiment of the invention.

[0020] [Fig.3] [Fig.3] is a block diagram representing different steps of a method for determining a particle rate according to an embodiment of the invention.

[0021] [Fig.4] [Fig.4] is an example of a distribution histogram of a number of particles according to their size.

[0022] [Fig.5] [Fig.5] is a diagram showing different elements of a system for determining a particle rate according to an embodiment of the invention. DETAILED DESCRIPTION OF THE INVENTION

[0023] A method for determining in real time and continuously a rate of particles of a given material in a sample, as illustrated by way of non-limiting example in [Fig.l], in [Fig.2] and in [Fig.3], comprises steps of: El: optical measurement of a sample signature; E2: identification by a processing unit 20 of a type of the sample by means of a classification model trained on a learning database comprising a plurality of reference signatures, each reference signature being associated with a type of a reference sample; and E3: determination by the processing unit 20 of the particle rate of the given material in the sample from the type of the identified sample and a table of cor correspondence associating with each of a plurality of types of reference samples a reference particle rate of the given material.

[0024] The method makes it possible to determine a rate of particles of a given material present in a sample, that is to say to differentiate, within the particles present in the sample, the particles of the given material compared to the particles of other materials.

[0025] By "sample", it will be understood that this is a sample of air likely to include suspended particles, for example particles of dust or given materials, and which may in particular be breathed by an individual working on a construction site.

[0026] Of course, several particle rates of several different given materials can be determined in step E3. Thus, the particles of one or more materials potentially harmful to health can be discriminated from the particles of other materials not presenting a danger to health.

[0027] The method can be implemented for example on construction sites, to improve the management of health risks for individuals working on construction sites, such as operators or inspectors.

[0028] The method makes it possible to determine the particle rate of the given material in the sample in real time and continuously. By "in real time", it will be understood that said determination is carried out simultaneously with the exposure of the individual to the particles of the given material, for example during the work of the operator or inspector on the site. By "continuously", it will be understood that said determination is carried out regularly over time, that is to say periodically, and at a period allowing the rapid adaptation of protective measures according to the determined particle rate of the given material, therefore the exposure of the individual to the particles of the given material. For example, the determination of the particle rate can be carried out during an entire working day of the individual, at a calculation period of between 1 second and 1 hour.

[0029] Thus, the risk resulting from the individual's exposure to particles of the given material can be assessed in real time and continuously. The individual's protection and alert measures can therefore be adapted in real time and continuously, which makes it possible to prevent the individual from being overexposed to materials potentially harmful to his or her health. The management of the health risk linked to the exposure of individuals to particles of certain materials is therefore improved.

[0030] The determination of the sample type is carried out by means of a classification model. This makes it possible to identify the sample type with good reliability, due to the training of the classification model on the basis of training data.

[0031] Furthermore, the assignment of a type to the sample can be carried out including in complex cases where the sample does not correspond to a reference sample type, but to a combination of several reference sample types, for example in the case of dust mixtures. The classification model thus makes it possible to isolate the different types of dust detected. Thus, depending on the signature of the sample measured in step E1, the identification of the sample type carried out in step E2 leads to the assignment to the sample of a sample type which can either correspond to a reference type or correspond to a combination of several reference types.

[0032] The given material may be respirable crystalline silica. Thus, the method makes it possible to determine in real time and continuously the rate of respirable crystalline silica emitted by construction site operations. Alternatively or in addition, the given material may be ballast dust, lime, other hydraulic binders, polluted earth dust or other types of dust, chromium VI particles, or diesel particles, and / or other particles emitted by different construction site operations.

[0033] Step El: Optical measurement of a sample signature

[0034] The optical measurement of the signature of the sample is carried out in step E1 in real time and continuously. Thus, the measurement data reflect the quality of the air actually breathed by the individual, in particular by the operator during his work on the site, and the evolution of this air quality over time.

[0035] The signature of the sample may be measured periodically at step E1 at each measurement period. Said measurement period may be between 0.1 seconds and 10 hours, for example between 1 second and 1 hour, for example between 1 minute and 30 minutes, for example be equal to 15 minutes. In the latter case, the signature of the sample is measured every 15 minutes.

[0036] The measurement of the signature of the sample can be carried out by means of an optical sensor 10, in particular an optical counter configured to carry out a particle count.

[0037] The signature of the sample measured in step E1 may be a function of a size and a number of particles present in the sample. The signature of the sample then depends on the size and the number of particles present in the sample.

[0038] The signature of the sample measured in step E1 may comprise a histogram of the distribution of a number of particles in the sample as a function of the size of the particles, i.e. a histogram of the size distribution of an alveolar fraction of particles in the sample.

[0039] A concentration of particles of the given material in the sample, expressed for example in ppm or pg / m3, can be deduced from the distribution histogram of the number of particles as a function of their size. For example, the concentration can be determined by considering all particles to be spherical in shape, and by considering known material density values.

[0040] The signature of the sample, in particular the histogram of the distribution of the number of particles in the sample as a function of their size, can be measured in a particle size range which corresponds to particles of a size less than 40 pm, for example of a size between 0.1 and 10 pm.

[0041] The size range may be divided into several slices, the number of particles being measured in each size slice. Each slice may correspond to a size interval of approximately 1 pm. The size range may be divided into a number of slices between 2 and 40, for example into 24 slices.

[0042] [Fig. 4] illustrates an example of a histogram of the distribution of a number of particles as a function of their size. The measurements are carried out for a particle size range of between 0.1 and 2 pm, the size range being divided into 6 slices, and for graphite and silica particles. The distribution of graphite particles as a function of their size is illustrated in black, and the distribution of silica particles as a function of their size is illustrated in gray.

[0043] Alternatively or additionally, the signature of the sample measured in step E1 may be a function of a particle shape and a number of particles. The particles of a given material are then discriminated from the particles of other materials present in the sample according to their shape, for example spheroid, lenticular, etc. The signature of the sample then comprises a distribution of a number of particles in the sample according to their shape.

[0044] Step E2: Identification by a processing unit 20 of a type of the sample

[0045] In a first embodiment, illustrated by way of non-limiting example in [Fig.2], the identification of the type of the sample during step E2 comprises a comparison of the signature of the sample with a plurality of reference signatures stored in the learning database, each reference signature being associated with a type of reference sample.

[0046] The training database is consulted each time the sample type is identified.

[0047] To determine the type of the sample, the signature of the sample may be compared with one or more, in particular with each, of the reference signatures stored in the training database.

[0048] The classification model may in particular be a k nearest neighbors type model. The k types of reference samples whose reference signatures are closest to the signature of the measured sample, according to a determined distance, are taken into account to determine the type of the sample. The The value of k can be between 1 and N, where N is the number of samples in the classification database. For example, the value of k can be between 1 and 10, for example, it can be equal to 5.

[0049] In a first exemplary embodiment, the type of sample determined in step E2 corresponds to the type of reference sample most represented among the k reference samples whose reference signatures are closest to the signature measured in step E1.

[0050] In a second exemplary embodiment, the type of the sample determined in step E2 corresponds to a combination of the types of the k reference samples whose reference signatures are closest to the signature measured in step E1, for example by assigning to each reference sample among the k closest reference samples an identical weight, or a variable weight depending on the distance of their respective reference signatures to the signature of the sample measured in step E1.

[0051] The method may comprise a step of determining an unknown sample type when all the distances between the signatures of the reference samples and the signature measured in step E1 are greater than a certain threshold distance.

[0052] In a second embodiment, the classification model is a neural network, support vector machine, stochastic gradient algorithm, or random forest algorithm type model.

[0053] The method then comprises a preliminary step of learning the classification model from the learning database.

[0054] Once the learning has been carried out, the determination of the type of the sample can be carried out for a sample signature measured in step E1 by means of the classification model developed during the learning, without requiring consultation of the learning database.

[0055] The classification model may include alpha-beta pruning.

[0056] In the first embodiment and in the second embodiment, the training database may comprise a plurality of reference signatures, each reference signature corresponding to a type of a reference sample, which can be obtained during a specific operation.

[0057] Each reference signature may correspond to a reference histogram of distribution of a number of particles in the reference sample as a function of a particle size and / or a particle shape.

[0058] Each signature of a reference sample can correspond to a vector, in a multidimensional feature space constructed using the histogram of particle size or shape distribution in the reference sample, each vector corresponding to a type of the reference sample.

[0059] The signature of the sample measured in step E1 corresponds to an unlabeled vector, which is in the first embodiment compared to the vectors corresponding to the reference signatures of the reference samples of the training database.

[0060] A type of the reference sample can be defined by a nature of the reference sample and an activity of obtaining the reference sample. Indeed, the nature and / or the activity of obtaining a reference sample impacts its signature, in particular can impact the distribution in size and number of particles in the reference sample, and / or the rate of particles of a given material in the reference sample.

[0061] The nature of the reference sample may correspond to a material of the reference sample, such as brick, marble, concrete, quartz, the type of dust, etc., more particularly to a material from which the dust contained in the sample originates.

[0062] The activity of obtaining the reference sample may correspond to an activity following which the reference sample was obtained and / or to a tool corresponding to said activity, for example digging, sanding, cutting, demolition, etc., by means of a circular saw, a sander, a jackhammer, etc.

[0063] For example, a reference sample type may be a cement brick obtained by sawing using a circular saw, the resulting dust comprising a given mixture fraction of concrete and marble.

[0064] The type of sample identified in step E2 can be defined by a nature of the sample and an activity of obtaining the sample, the type of sample being determined according to the types (nature and activity of obtaining) of the reference samples.

[0065] The more reference sample types the training database contains, the more reliably and efficiently the classification model will be able to recognize a large number of sample types.

[0066] The correspondence table associates respective reference particle rates with a plurality of reference sample types.

[0067] Each type of reference sample is associated with at least one reference particle rate of at least one given material. Each type of reference sample may be associated with various reference particle rates of various given materials that may present a risk to the health of an individual who breathes it. For example, each type of reference sample may be associated with a respirable crystalline silica rate, a ballast dust rate, a chromium VI rate, a lime rate, a diesel rate, a polluted earth dust rate, a rate of other hydraulic binders, etc.

[0068] The training database and the correspondence table may correspond to a single database. The table below illustrates a non-limiting example of a single database grouping a training database associating a reference sample type with a reference signature, and a correspondence table associating particle rates of several given materials with each reference sample type.

[0069] [Tables 1] Signature of the reference sample Type of the reference sample Rate of particles in the reference sample Activity of acquisition Nature Rate of alveolar Si Rate of chromium VI Rate of particles X SI Excavation Al al bl cl S2 Sanding A2 a2 b2 c2 S3 Cutting A3 a3 b3 c3 S4 Demolition A4 a4 b4 c4

[0070] An example of a method for constituting the learning database and the correspondence table is described in the following paragraphs.

[0071] In order to constitute the training database, a plurality of reference samples having known reference types are taken on site. A reference signature corresponding to each reference sample is established, either directly on site, for example by means of an optical sensor adapted to carry out a particle count, or subsequently, for example by means of a laboratory analysis.

[0072] In order to constitute the correspondence table, particle rates of various given materials corresponding to the type of the reference sample are analyzed, for example by means of a chemical analysis carried out in the laboratory, in order to associate with each type of reference sample particle rates of the various given materials.

[0073] Step E3: Determination by the processing unit 20 of the particle rate of the material given in the sample

[0074] Once the type of sample has been identified, the processing unit 20 determines the particle rate of a given material in the sample, using the particle rate of the given material associated with each type of reference sample.

[0075] The type of the sample can be identified periodically in step E2 at each calculation period. The particle rate can be determined periodically in step E3 at each calculation period.

[0076] The calculation period may be equal to or greater than the measurement period. The identification of the sample type and / or the determination of the particle rate of the given material may therefore be carried out at each measurement carried out by the optical sensor 10, or at more spaced time intervals, so as to monitor in real time and continuously, therefore regularly over time, the evolution of the particle rate of the given material in the sample.

[0077] The calculation period may be equal to the measurement period. The calculation period may be between 0.1 seconds and 10 hours, for example between 1 second and 1 hour, for example between 1 minute and 30 minutes, for example be equal to 15 minutes.

[0078] In particular, when the measurement period and the calculation period are both equal to 15 minutes, the signature of the sample is measured every 15 minutes, and the particle rate of the given material is determined every 15 minutes, i.e. at each measurement of a signature of a sample.

[0079] When the calculation period is greater than the measurement period, the signature of the sample considered to determine the type of the sample can correspond to an average of the signatures of the samples obtained at each measurement period occurring during the calculation period. Thus, the autonomy of the device is improved, and potential measurement errors are smoothed.

[0080] E4: Determination of exposure to particles of the given material

[0081] The method may further comprise a step E4 of determination by the processing unit 20 of an exposure to the particles of the given material from the rate of particles of the given material determined in step E2 and a time of exposure to said particles of the given material, as illustrated by way of non-limiting example in [Fig.3].

[0082] The exposure to the given type of material during a calculation period can be calculated by integrating the particle rate of the given material determined in step E3 over a duration corresponding to the calculation period. The exposure to the given type of material during the exposure time determined in step E4 corresponds to the sum of the exposures during the calculation periods corresponding to this exposure time. Thus, the exposure calculated in step E4 takes into account the change over time in the particle rate of the given material determined in step E3.

[0083] The exposure time may be greater than or equal to the calculation period. The exposure time may be defined according to the type and harmfulness of the given material, and / or according to the desired speed of adaptation of the protective measures. Thus, the shorter the exposure time, the more quickly and accurately the exposure determination is carried out.

[0084] The exposure time may be between 0.1 seconds and 10 hours, for example between 1 second and 1 hour, for example between 1 minute and 30 minutes, for example be equal to 15 minutes.

[0085] For example, if the exposure time is equal to 1 hour and the calculation period is equal to 15 minutes, the exposure is determined by summing, for each of the 4 calculation periods included in the exposure time, the particle rates determined at each of these 4 calculation periods.

[0086] Alternatively or additionally, a predicted exposure to the given material particle type may be determined by multiplying the particle rate of the given material determined during the calculation period by a predicted exposure time corresponding to several calculation periods. Thus, a predicted exposure to the given material particle type may be calculated in advance of the actual exposure. E5: User alert

[0087] The method may further comprise a step E5 of alerting a user when exposure to particles of the given material exceeds a predetermined exposure threshold, as illustrated by way of non-limiting example in [Fig.3].

[0088] The exposure threshold can be defined according to the given material, its potential impact on the health of the individual likely to breathe it, specific safety standards, etc.

[0089] Alternatively or additionally, the method may comprise a step E5' of alerting a user when the particle rate determined in step E3 during a calculation period exceeds a predetermined rate threshold.

[0090] Thus, a temporary but significant exceedance of a particle rate of the given material, regardless of when the exceedance occurs and the duration of the exceedance, is identified and the user is alerted, in order to be able to take adequate protective measures in real time and continuously.

[0091] Alternatively or additionally, the method may comprise a step E5” of alerting a user when the predicted exposure to the given material particle type exceeds a predetermined exposure threshold. Thus, protective measures can be taken before the operator is actually subjected to the exposure threshold. E6: Transmission of alert data

[0092] The method may further comprise a step E6 of transmitting alert data. The alert data may comprise the exposure determined in step E5, E5', or E5” and / or the particle rate determined in step E3 for each period calculation and / or the signatures measured at step El for each calculation period.

[0093] The alert data may be transmitted when the exposure to particles of the given material exceeds a predetermined exposure threshold, and / or when the particle rate determined in step E3 during a calculation period exceeds a predetermined rate threshold.

[0094] The alert data may be transmitted to a remote server via a wireless connection.

[0095] System for real-time and continuous determination of a particle rate of a given material in a sample

[0096] A system for determining in real time and continuously a rate of particles of a given material in a sample comprises, as illustrated by way of non-limiting example in [Fig.5]: - an optical sensor 10 adapted to measure a signature of a sample; and - a processing unit 20 configured to: - identifying a type of the sample by means of a classification model trained on a training database comprising a plurality of reference signatures, each reference signature being associated with a type of a reference sample, and - determine the particle rate of the given material in the sample, from the type of sample identified and a correspondence table associating with each of a plurality of reference sample types a reference particle rate of the given material.

[0097] The system is suitable for implementing the method described above. The system may be a system for identifying and determining a rate of respirable crystalline silica particles emitted by different construction site operations. Alternatively or in addition, the system may be a system for identifying and determining a rate of ballast dust, a rate of lime, a rate of diesel, a rate of polluted earth dust, a rate of other hydraulic binders, a rate of Chromium VI, and / or a rate of other particles, emitted by different construction site operations.

[0098] By "processing unit 20", it will be understood that it can be any system allowing the desired treatments to be carried out, for example a single processing unit 20, or several processing units 20 which can be controlled by a parent unit. The processing unit 20 can comprise one or more microprocessors) adapted to process the measurement data from the optical sensor 10 in order to determine the rate of particles of the given material in the sample.

[0099] The classification model, the training database, and the correspondence table may correspond to those described above concerning the method of de termination of a particle rate of the given material in a sample.

[0100] The processing unit 20 may further be configured to determine an exposure to particles of the given material from the determined rate of particles of the given material and a time of exposure to said particles of the given material.

[0101] The optical sensor 10 may be an optical particle counter configured to perform particle counting. More particularly, the optical sensor 10 may be configured to generate a distribution histogram of a number of particles in the sample as a function of particle size. A concentration of particles of the given material in the sample, expressed for example in ppm or pg / m3, may be deduced from the distribution histogram measured by the optical sensor 10. For example, the concentration may be determined by considering that all particles are spherical, and by considering known material density values.

[0102] The optical sensor 10 can be adapted to accurately measure the signature of the sample, more particularly the distribution of the number of particles as a function of their size, in a particle size range which can correspond to particles of a size less than 40 pm, for example between 0.1 and 10 pm.

[0103] The optical sensor 10 may be a micro-sensor. The optical sensor 10 may be an optical sensor 10 of the nephelometer and laser diffraction type. Such optical particle counters are robust, precise and inexpensive, and allow reliable measurements to be carried out on a wide variety of sample types, whether they come from natural rocks (granite, sand, etc.) or processed materials (concrete, cement, mortar).

[0104] The optical sensor 10 may be portable. By portable, it will be understood that the optical sensor 10 is not permanently fixed to the ground, can be transported, the optical sensor 10 having a moderate weight and size. In particular, the optical sensor 10 can be carried by a user such as an individual working on a construction site, such as an operator or an inspector, without representing a significant inconvenience for the individual during his work.

[0105] The measurements made by the optical sensor 10 can be transmitted to the processing unit 20 which can be a remote server. Alternatively, the processing unit 20 and the optical sensor 10 can be integrated into a portable module. The exposure can then be assessed on a personal scale.

[0106] Alternatively, the optical sensor 10 may be stationary, i.e. be posted at a given location on the construction site. The processing unit 20 may be a remote server to which the measurement data are sent for processing. The system then comprises means for transmitting the measurement data to the processing unit 20. The exposure can then be evaluated at the construction site scale, the optical sensor 10 being implemented in a stationary manner.

[0107] The system may further comprise storage means 30 configured to store the measurements made by the optical sensor 10. The storage means 30 may, alternatively or additionally, be configured to store the correspondence table and / or the learning database. The storage means 30 may further be adapted to store the alert data, for a determined storage duration.

[0108] The storage means 30 may comprise a dedicated electronic card, such as an SD storage card. A dedicated electronic card consumes little energy, which makes it possible to preserve the autonomy of the system.

[0109] The system may further comprise an alert unit 40 adapted to alert a user when exposure to particles of the given material exceeds a predetermined exposure threshold. The alert unit 40 may correspond to the processing unit 20.

[0110] The user alerted by the alert unit may correspond to the user wearing the system, for example an operator or inspector working on a construction site, or another user, for example an operator manager or a construction site control center.

[0111] The system may further comprise a transmission unit 50 adapted to transmit alert data. The transmission unit 50 may be configured to transmit via a wireless connection.

[0112] The transmission unit 50 may in particular comprise a transmitter module enabling transmission via LPWAN technologies, in order to limit the energy consumed by the transmission and thus increase the autonomy of the system.

[0113] The system may further comprise a battery 60 adapted to provide energy to the processing unit 20 and / or the alert unit 40 and / or the transmission unit 50.

[0114] The battery 60 may comprise one or more non-rechargeable batteries connected in series, or be rechargeable by a charger, the nature of the battery being able to be chosen according to the desired autonomy for the system.

[0115] The system may further comprise a housing 100. The optical sensor 10 and the processing unit 20 are integrated into the housing 100. Where appropriate, the storage means 30, the alert unit 40, the transmission unit 50 and / or the battery 60 may also be integrated into the housing 100.

[0116] The housing 100 may be made of a waterproof material, in order to protect the electronics of the system from external disturbances common on construction sites, such as water and dust. The reliability of the measurements is increased and the service life of the components of the device is improved.

[0117] The housing 100 may be portable, so that it can be carried by a user without to bother him, the 100 case having a moderate weight and size.

[0118] Other embodiments may be envisaged and a person skilled in the art may easily modify the embodiments or examples set forth above or envisage others while remaining within the scope of the invention.

Claims

Claims

1. A method for determining a rate of particles of a given material in a sample, wherein said determination is performed in real time, the determination being performed simultaneously with an exposure of the individual to the particles of the given material, and continuously, the determination being performed periodically over time, wherein the sample is an air sample likely to comprise suspended particles, wherein the method comprises steps of: E1: optical measurement of a signature of the sample; E2: identification by a processing unit (20) of a type of the sample by means of the measured signature of the sample and a classification model trained on a learning database comprising a plurality of reference signatures, each reference signature being associated with a type of a reference sample;and E3: determination by the processing unit (20) of the particle rate of the given material in the sample from the type of the identified sample and a correspondence table associating with each of a plurality of types of reference samples a reference particle rate of the given material, in which the signature of the sample measured in step E1 is a function of a size and a number of the particles present in the sample and / or a shape and a number of the particles present in the sample, and in which the signature of the sample measured in step E1 comprises a histogram of the distribution of a number of particles in the sample as a function of the size of the particles and / or as a function of the shape of the particles.;

2. A method for determining a particle rate of a given material according to claim 1, wherein the identification of the type of the sample during step E2 comprises a comparison of the signature of the sample with the plurality of reference signatures stored in the training database, and wherein the classification model is a k-nearest neighbor type model.

3. Method for determining a particle rate of a given material according to claim 1, wherein the classification model is a neural network, support vector machine, stochastic gradient algorithm, or random forest algorithm type model.

4. A method for determining a particle rate according to one of the preceding claims, wherein the given material is at least one of respirable crystalline silica, ballast dust, lime, diesel particles, polluted earth dust, other hydraulic binders, Chromium VI particles, and / or other particles emitted by different construction site operations.

5. Method for determining a particle rate according to one of the preceding claims, in which the type of the sample identified in step E2 is defined by a nature of the sample, corresponding to a material of the reference sample, and an activity of obtaining the sample, corresponding to an activity following which the reference sample was obtained and / or to a tool corresponding to said activity.

6. Method for determining a particle rate according to one of the preceding claims, in which the signature of the sample is measured periodically in step E1 at each measurement period, the type of the sample is identified periodically in step E2 at each calculation period and the particle rate is determined periodically in step E3 at each calculation period, in which the calculation period is equal to or greater than the measurement period, in which the measurement period and the calculation period are between 1 second and 1 hour.

7. Method for determining a particle rate according to one of the preceding claims, further comprising a step E4 of determining by the processing unit (20) an exposure to the particles of the given material from the particle rate of the given material determined in step E3 and a time of exposure to said particles of the given material.

8. Method for determining a particle rate according to claim 7, further comprising a step E5 of alerting a user when exposure to particles of the given material exceeds a predetermined exposure threshold.

9. System for determining a rate of particles of a given material in a sample, said determination system being adapted to carry out a determination in real time, the determination being carried out simultaneously with an exposure of the individual to the particles of the given material, and continuously, the determination being carried out perio- specifically over time, wherein the sample is an air sample likely to comprise suspended particles, and wherein said system comprises: - an optical sensor (10) adapted to measure a signature of a sample; and - a processing unit (20) configured to: - identify a type of the sample by means of the measured sample signature and a classification model trained on a learning database comprising a plurality of reference signatures, each reference signature being associated with a type of a reference sample, and - determine the rate of particles of the given material in the sample, from the type of the identified sample and a correspondence table associating with each of a plurality of types of reference samples a rate of reference particles of the given material,wherein the signature of the sample measured in step E1 is a function of a size and a number of particles present in the sample and / or a shape and a number of particles present in the sample, and wherein the signature of the sample measured in step E1 comprises a histogram of the distribution of a number of particles in the sample as a function of the size of the particles and / or as a function of the shape of the particles.,

10. A system for identifying and determining a particle rate according to claim 9, wherein the optical sensor (10) is configured to perform a particle count.

11. A system for identifying and determining a particle rate according to claim 9 or claim 10, wherein the optical sensor (10) is portable.

12. System for identifying and determining a particle rate according to one of claims 9 to 11, further comprising storage means (30) configured to store the measurements carried out by the optical sensor (10) and / or the learning database and / or the correspondence table.

Images