Method and system for the dynamic determination of the type of particles emitted in an industrial activity in a physical environment

Abstract

Method for dynamically determining a type (Te) of particles (1) emitted during the operation of an industrial activity (2) in a physical medium (3), the method comprising: • a sound measurement step (El) of the industrial activity (2) to determine a common sound signature (Sc), • a determination step (E2), by means of a first database (4), a first list of particle types (Ml) from the common sound signature (Sc), • a particle size measurement step (E3) of the particles (1) emitted in the physical medium (3) to determine a common particle size signature (Gc), • a determination step (E4), by means of a second database (5), a second list of particle types (NI) from the common particle size signature (Gc), • a determination step (E7) of the type (Te) of particles (1) by the intersection of the lists of particle types (Ml, NI).

Description

Domaine technique

[0001] The present invention relates to the field of particle identification during the implementation of an industrial activity in a physical environment.

[0002] It is well known that many industrial production activities generate airborne particles, called aerosols, the concentration of which must be monitored to protect the health of workers. For example, sawdust production, welding, drilling, and sanding are activities that produce aerosols, such as glass, wood, and metal particles.

[0003] To ensure monitoring, it is common practice to collect air samples which are then analyzed to determine aerosol concentrations and assess air quality. Analyzing such samples is costly and time-consuming. Furthermore, because sampling is carried out sporadically, regular monitoring is not possible.

[0004] It is also common practice to install or equip operators with analytical equipment to continuously monitor aerosol concentrations at industrial production sites. Such analytical equipment typically includes a sensor, specifically an optical particle counter. This sensor determines the quantity and statistical size distribution of aerosols, resulting in a particle size signature. This particle size signature can then be compared to one or more predetermined tolerance thresholds to detect potential hazards to the operator.

[0005] In practice, an operator is required to perform several different activities and is thus exposed to different types of particles, each with a different tolerance threshold. It is therefore necessary to identify the emitted particles to allow for comparison with a relevant tolerance threshold. Indeed, several different types of particles can have a similar particle size signature, making them difficult to distinguish reliably. Prior art analysis equipment is therefore insufficient to adequately meet the need for air quality monitoring.

[0006] To eliminate this drawback, an obvious solution would be to use a sensor for each type of particle or to ask the operator to manually enter the type of particles likely to be present and / or their tolerance threshold based on their current activity, thus enabling accurate measurement. However, such a solution is not feasible given that the same operator may frequently change tasks, which is cumbersome and prone to oversights.

[0007] The invention aims to determine, in a dynamic and reliable manner, the type of particles emitted during industrial activity in a physical environment. The invention is particularly applicable to airborne particles, but also to particles present in powders.

[0008] In the field of powder manufacturing, such as at flour milling plants, it is indeed necessary to control powder quality, namely to determine the particle size profile of the flour grains to verify powder homogeneity. In practice, different types of flour are milled at the same site and have different acceptance thresholds, which necessitates the ability to distinguish between them. The document Wangkanklang Ekkawit ET AL: "System for Monitoring Progress in a Mixing and Grinding Machine Using Sound Signal Processing", Micromachines, vol. 12, no. 9, August 29, 2021 (2021-08-29), page 1041 describes the use of acoustic signal processing to monitor particle size distribution during a mixing or grinding process. PRESENTATION OF THE INVENTION

[0009] The invention relates to a method for the dynamic determination of at least one type of particle, the particles being emitted during the implementation of an industrial activity in a physical environment, said method being implemented by means of at least: a first database comprising a plurality of reference sound signatures, each associated with a first list of particle types, each reference sound signature being characteristic of at least one industrial activity, and a second database comprising a plurality of reference particle size signatures, each associated with a second list of particle types, each reference particle size signature being characteristic of at least one particle type, said process comprising: a step of measuring the sound of the industrial activity in the physical environment, so as to determine a current sound signature, a step of determining, by means of the first database, a first list of particle types from the current sound signature, a step of measuring the particle size of the particles emitted in the physical environment, so as to determine a current particle size signature,a step of determining, using the second database, a second list of particle types from the current particle size signature, a step of determining at least one particle type by intersection of the first list of particle types and the second list of particle types.

[0010] The invention enables the dynamic, simple, and reliable identification of a particle type at its emission site. The invention is of particular interest for air quality control at industrial production sites to verify that particles emitted by industrial activity do not exceed a predetermined acceptance threshold. The invention is also of particular interest for quality control of powders to verify their homogeneity.

[0011] The invention is advantageously based on the use of a sound signature of particle emission activity, which is combined with a particle size signature to identify the type of particle. This sound signature is advantageously simple to measure and highly discriminating. In particular, the sound signature reliably distinguishes between two types of particles with similar particle size signatures. Thus, each time an operator changes activities, they benefit from appropriate monitoring of the emitted particles, ensuring their safety and health.

[0012] According to one aspect of the invention, said method is also implemented using a threshold database comprising a plurality of particle types, each associated with an acceptance threshold, said method comprising: A step of determining, using the threshold database, an acceptance threshold from the determined type of particles, and a step of issuing an alarm if the current particle size signature exceeds the acceptance threshold.

[0013] The process is advantageously implemented directly at the particle emission site, without waiting, and in an automated manner, for example, periodically. The process thus enables autonomous monitoring of particle levels in a given physical environment, alerting the user if a tolerance threshold is exceeded. A suitable alarm can be triggered for each activity performed by the operator.

[0014] According to one aspect of the invention, each reference sound signature in the first database comprises at least one frequency characteristic of the associated industrial activity, and preferably a sound spectrum characteristic of the associated industrial activity. Advantageously, each industrial activity has a characteristic sound spectrum sufficiently different from the others to allow for easy identification.

[0015] According to one aspect of the invention, the particle size measurement step is implemented using an optical particle counter. An optical particle counter allows for a precise and reliable measurement of particle size distribution and concentration.

[0016] According to one aspect of the invention, the determination step is implemented by determining, among the reference sound signatures of the first database, the one closest to the current sound signature.

[0017] According to one aspect of the invention, the determination step is implemented by means of a statistical classification module, preferably of the support vector or neural network type.

[0018] According to one aspect of the invention, the method also includes a preliminary step of training the statistical classification module from a plurality of training sound signatures, the statistical classification module being configured to determine the closest reference sound signature in the first database.

[0019] According to a preferred aspect, the determination step is implemented by determining, among the reference particle size signatures of the second database, the one closest to the current particle size signature.

[0020] According to a preferred aspect, the determination step is implemented using a statistical classification module, preferably of the support vector or neural network type.

[0021] According to a preferred aspect, the process includes a preliminary step of training the statistical classification module from a plurality of training particle size signatures, the statistical classification module being configured to determine the closest reference particle size signature in the second database.

[0022] According to one aspect of the invention, the method is also implemented using a third database comprising a plurality of reference physical signatures, each associated with a third list of particle types, each reference physical signature being characteristic of the physical medium, said method comprising: a measurement step of a current physical signature of the physical medium, a determination step, using the third database, of a third list of particle types from the current physical signature, the determination step being further implemented by intersection with the third list of particle types.

[0023] The process combines three different types of measurements to identify the type of particles: particle size, sound emitted by industrial activity, and a physical environment parameter. This increases the method's accuracy and reliability.

[0024] According to one aspect of the invention, the current physical signature comprises one or more of the following elements: a temperature measurement, a humidity measurement, and an odor measurement of the physical medium. Such a physical signature, in combination with the sound signature and the particle size signature, increases the accuracy and reliability of the method.

[0025] According to a preferred aspect, the determination step is implemented by determining, among the reference physical signatures of the second database, the one closest to the current physical signature.

[0026] According to a preferred aspect, the determination step is implemented using a statistical classification module, preferably of the support vector or neural network type.

[0027] According to a preferred aspect, the process includes a preliminary step of training the statistical classification module from a plurality of physical training signatures, the statistical classification module being configured to determine the closest reference physical signature in the second database.

[0028] The invention also relates to a system for the dynamic determination of at least one type of particle for the implementation of the process as described above, the particles being emitted during the implementation of an industrial activity in a physical environment, said system comprising at least: a first database comprising a plurality of reference sound signatures, each associated with a first list of particle types, each reference sound signature being characteristic of at least one industrial activity, and a second database comprising a plurality of reference particle size signatures, each associated with a second list of particle types, each reference particle size signature being characteristic of at least one particle type, a first measuring device configured to measure a common sound signature of industrial activity in the physical environment, a second measuring device configured to measure a common particle size signature of particles in the physical environment, and a control device configured to determine: using the first database, a first list of particle types from the current sound signature,Using the second database, a second list of particle types is generated from the current particle size signature, with one particle type being the intersection of the first and second lists of particle types.

[0029] According to a preferred aspect, the second measuring device includes an optical particle counter sensor.

[0030] According to a preferred aspect, the control unit includes a statistical classification module, preferably of the support vector or neural network type.

[0031] Preferably, the system also includes: a threshold database comprising a plurality of particle types, each associated with an acceptance threshold, said control body being configured to determine, by means of the threshold database, the acceptance threshold from the determined particle type, and to issue an alarm if the current particle size signature exceeds the acceptance threshold.

[0032] Preferably, the system also includes: a third database comprising a plurality of reference physical signatures, each associated with a third list of particle types, each reference physical signature being characteristic of the physical medium, a third measuring device configured to measure a current physical signature of the physical medium, said control device being configured to determine: by means of the third database, a third list of particle types from the current physical signature, a particle type by intersection with the third list of particle types. PRESENTATION OF THE FIGURES

[0033] The invention will be better understood upon reading the following description, given by way of example, and referring to the following figures, given by way of non-limiting examples, in which identical references are given to similar objects. There [ Fig.1 ] is a schematic representation of the steps in a process for the dynamic determination of a type of particle according to an embodiment of the invention. The [ Fig.2 ] is a schematic representation of a drilling activity on an oak panel carried out near a dynamic particle type determination system according to one embodiment of the invention. The [ Fig.3 ] is a schematic structural representation of the dynamic particle type determination system of the [ Fig.2 ]. There [ Fig.4 ] is a schematic representation of the steps involved in determining lists of particle types from databases, and their intersection to determine the particle type according to the [ Fig.1 ]. There [ Fig.5 ] is a schematic representation of a method for dynamically determining the type of particles according to another embodiment of the invention. The [ Fig.6 ] is a schematic representation of a dynamic particle type determination system to implement the process of the [ Fig.5 ]. There [ Fig.7 ] is a schematic representation of a method for the dynamic determination of a type of particle according to another embodiment of the invention. The [ Fig.8 ] is a schematic representation of a dynamic particle type determination system to implement the process of the [ Fig.7 ]. There [ Fig.9 ] is a schematic representation of a method for dynamically determining a type of particle according to another embodiment of the invention.

[0034] It should be noted that the figures explain the invention in detail for implementing the invention, said figures being of course able to serve to better define the invention where appropriate. DETAILED DESCRIPTION OF THE INVENTION

[0035] The invention relates to a method (see [ Fig.1 ]) and a system 12 (see [ Fig.3 ]) for determining one or more types Tc of particles 1 emitted into a physical medium 3 during an industrial activity 2. The invention allows for dynamic and reliable identification. In particular, the invention aims to warn an operator when one or more types of particles exceed a predetermined acceptance threshold.

[0036] As illustrated on the [ Fig.2 The invention is particularly intended for use at industrial production sites to monitor the concentration of airborne particles, known as aerosols, generated by site activities and thus protect the health of operators. Drilling, welding, sawdust, sanding, building demolition, and roadworks are examples of industrial activities that emit particles during their execution, such as wood, metal, or glass particles.

[0037] Another example of an application of the invention is quality control at powder manufacturing sites, for example, at flour milling plants. The invention makes it possible, in particular, to verify the homogeneity of the powder by identifying and comparing it with acceptance thresholds.

[0038] Other examples of applications of the invention include monitoring the concentration of suspended pollen during agricultural, pruning, gardening, etc. activities. Other examples of applications of the invention include monitoring the level of toxic particles in an enclosed environment, such as cigarette smoke or the outbreak of a fire.

[0039] Hereafter, "industrial activity" refers to any manual and / or automated work or action whose implementation tends to emit particles, the emission of particles being either the intended goal of the activity (for example, flour grinding) or an induced consequence (for example, drilling, welding, sawdust, and sanding). Hereafter, the term "particles" includes, in particular, particles suspended in the air, known as aerosols, and those present in a powder.

[0040] According to the invention, as illustrated in the [ Fig.1 ], the process is implemented by means of: a first database 4 comprising several reference sound signatures S1, S2, S3, each associated with a first list of particle types M1, M2, M3, each reference sound signature S1, S2, S3 being characteristic of one or more industrial activities 2, and a second database 5 comprising several reference particle size signatures G1, G2, G3, each associated with a second list of particle types N1, N2, N3, each reference particle size signature being characteristic of at least one particle type 1.

[0041] According to the invention and as illustrated in the [ Fig.1 ], the process includes: a sound measurement step E1 of the industrial activity 2 in the physical medium 3, so as to determine a current sound signature Sc, a determination step E2, using the first database 4, of a first list of particle types M1 from the current sound signature Sc, a particle size measurement step E3 of the particles 1 emitted in the physical medium 3, so as to determine a current particle size signature Gc, a determination step E4, using the second database 5 of a second list of particle types N1 from the current particle size signature Gc, and a determination step E7 of the type(s) Tc of particles 1 by intersection of the first list of particle types M1 and the second list of particle types N1.

[0042] As illustrated on the [ Fig.2 The process is implemented in the physical environment 3 of particles 1, near the industrial activity 2. The system 12 is configured to implement the process during the industrial activity 2 and is permanently installed in the physical environment 3 near the industrial activity 2. In other embodiments, the system 12 is portable, specifically configured to be worn by an operator. This allows for reliable and relevant sound and particle size measurements to identify the industrial activity and suspended particles. Preferably, the system 12 has a battery so as to be autonomous.

[0043] With reference to the [ Fig.3 ], system 12 includes, in addition to the first database 4 and the second database 5 described previously: a first measuring device 9 configured to measure a current sound signature Sc of industrial activity 2 in the physical medium 3, a second measuring device 10 configured to measure a current particle size signature Gc of particles 1 in the physical medium 3, and a control device 11 configured to determine: using the first database 4, a first list of particle types M1 from the current sound signature Sc, using the second database 5, a second list of particle types N1 from the current particle size signature Gc, a type Tc of particles 1 by intersection of the lists of particle types M1, N1.

[0044] We then describe each of the steps of the process in more detail using the example of drilling an oak panel.

[0045] With reference to figures 1 And 3The sound measurement step E1 is implemented by the first measuring device 9 during industrial activity 2. The sound measurement step E1 makes it possible to determine a current sound signature Sc of industrial activity 2. The first measuring device 9 is preferably in the form of a microphone configured to record the sound emitted during the implementation of industrial activity 2.

[0046] Preferably, the current sound signature Sc is determined from at least one time-domain sound recording to be representative of industrial activity. Preferably, the current sound signature Sc is determined from a Fourier transform of the time-domain sound recording. Such a sound signature can be practically compared with the sound signatures S1, S2, and S3 of the first database.

[0047] With reference to figures 1 And 4The step E2 for determining a first list of particles M1 is implemented after the measurement step E1 of the current sound signature Sc. The first list of particle types M1 is selected from the first database 4 from among all the lists of particle types M1, M2, M3. The first list of particles M1 chosen corresponds to the one whose reference sound signature S1, S2, S3 is closest to the current sound signature Sc.

[0048] With reference to the [ Fig.4 In this example, we consider the first database 4 to be the following: S1 is a reference sound signature of a drilling activity associated with a first list of particles M1 comprising oak α, chipboard β and plastic γ. S2 is a reference sound signature of a welding activity associated with a first list of particles M2 comprising aluminum δ and titanium ε. S3 is a reference sound signature of a grinding activity associated with a first list of particles M3 comprising T45 θ flour, T55 λ flour and T65 ϕ flour.

[0049] Note that the size of the databases 4, 5, 6, 8 used in the invention, restricted in the example presented here, is preferably extended and depends in practice on the field of application.

[0050] As illustrated on the figures 1 , 3 et 4 The determination step E2 is implemented by the control unit 11, and preferably by a statistical classification module 7 of the control unit 11. The statistical classification module 7, of the neural network or support vector type, is configured to compare the current sound signature Sc to the reference sound signatures S1, S2, S3 of the first database 4 and to determine the closest one, S1 in this example. The control unit 11 is then configured to select the first list of particles M1 associated with the chosen reference sound signature S1, namely oak α, chipboard β, and plastic γ in this example. Preferably, the control unit 11 is in the form of a computer or similar system.

[0051] Preferably, each reference sound signature S1, S2, S3 includes at least one frequency characteristic of the industrial activity 2 with which it is associated. Preferably, each reference sound signature S1, S2, S3 includes a sound spectrum characteristic of the industrial activity. During the determination step E2, the statistical classification module 7 compares the sound spectrum of the current sound signature Sc to the sound spectra of the reference sound signatures S1, S2, S3. The reference sound signature S1 is chosen because its characteristic sound spectrum is the least different from that of the current sound signature Sc.

[0052] Preferably, the process includes a preliminary training step E0 of the statistical classification module 7 from training sound signatures Se.

[0053] As illustrated on the [ Fig.1 ], the particle size measurement steps E3 and determination E4 of a second list of particle types M2 are implemented independently of the sound measurement steps E1 and determination E2 of the first list of particle types M1, preferably in parallel for a faster process.

[0054] With reference to figures 1 And 3The particle size measurement step E3 is implemented by the second measuring element 10, preferably incorporating an optical particle counter sensor. During the particle size measurement step E3, the optical particle counter sensor is configured to measure a common particle size signature Gc of particles 1 in the physical medium 3, in this example, the aerosols emitted by drilling the oak panel. Such a particle size signature Gc includes a concentration and a histogram of the size distribution of the aerosols measured in the physical medium 3. The measurement using an optical particle counter sensor is known to those skilled in the art and is therefore not described further.

[0055] With reference to figures 1 And 3The step E4 for determining a second list of N1 particles is implemented after the measurement step E3 of the current particle size signature Gc. The second list of N1 particle types is selected from the second database 5 from among all the lists of N1, N2, and N3 particle types. The second N1 particle list chosen corresponds to the one whose reference particle size signature G1, G2, or G3 is closest to the current particle size signature Gc.

[0056] As illustrated on the [ Fig.4 In this example, we consider the second database 5 to be the following: G1 is a reference particle size signature associated with a second list of particles N1 comprising α oak and µ glass. G2 is a reference particle size signature associated with a second list of particles N2 comprising T45 θ flour and β agglomerate. G3 is a reference particle size signature associated with a second list of particles N3 comprising γ plastic and T65 ϕ flour.

[0057] As illustrated on the figures 1 , 3 et 4 The determination step E4 is implemented by the control unit 11, and preferably by the statistical classification module 7. The statistical classification module 7 is configured to compare the histogram of the current particle size signature Gc with that of the reference particle size signatures G1, G2, G3 from the second database 5 and to determine the closest one, G1 in this example. The control unit 11 is then configured to select the second list of particles N1 associated with the closest reference sound signature G1, namely α oak and µ glass in this example.

[0058] With reference to figures 1 , 3 et 4 The particle type determination step E7, Tc, is implemented after the determination steps E2 and E4 of the particle type lists M1 and N1. During the determination step E7, the control element 11 performs an intersection operation between the first particle type list M1 and the second particle type list N1: Tc = M1 ∩ N1. In other words, the particle type Tc determined by the control element 11 corresponds to the element(s) common to the first and second particle type lists M1 and N1, in this example, oak α.

[0059] Thus, the type of Tc particles is determined using two different measurements to allow for reliable and relevant identification. Advantageously, the combination of a sound signature and a particle size signature forms a discriminating set for the type of Tc particles. Indeed, two different types of particles with similar particle size signatures can be distinguished by their sound signatures, and vice versa.

[0060] According to a preferred aspect of the invention illustrated on the figures 5 And 6 , the process is also implemented using a threshold database 6 comprising several types T1, T2, T3 of particles 1, each associated with an acceptance threshold A1, A2, A3.

[0061] As illustrated on the [ Fig.5 The process includes a determination step E8, during which the control device 11 determines, using the threshold database 6, the acceptance threshold A1 associated with the determined particle type Tc 1, in this example oak. The acceptance threshold A1 corresponds to the maximum concentration of airborne oak particles permitted to protect the health of the operator performing the drilling operation on the oak panel α.

[0062] As illustrated on the [ Fig.5 ], after the implementation of the determination step E8, the process includes an alarm emission step E9 if the current particle size signature Gc exceeds the acceptance threshold A1. The emission step E9 allows the operator to be warned of a potential exceedance, for example by means of an audible, computer or visual signal.

[0063] Alternatively, the acceptance threshold corresponds to the maximum permissible level of heterogeneity between the particles of the powder to be identified, for example, T55 flour. The E9 emission step then alerts the operator to the insufficient quality of the powder.

[0064] According to a preferred aspect of the invention illustrated on the figures 7 And 8 , the process is also implemented using a third database 8 comprising a plurality of reference physical signatures P1, P2, P3, each associated with a third list of particle types L1, L2, L3, each reference physical signature P1, P2, P3 being characteristic of the physical medium 3.

[0065] As illustrated on the [ Fig.7 ], the process includes: a measurement step E5 of a current physical signature Pc of the physical medium 3, a determination step E6, using the third database 8, of a third list of particle types L1 from the current physical signature Pc, the determination step E7 being further implemented by intersection with the third list of particle types L1.

[0066] According to a preferred aspect of the invention, the current physical signature Pc comprises a measurement of the temperature, humidity, and / or odor of the physical medium 3, namely the surrounding air, in the example of an activity involving drilling an oak panel. The particle type Tc is advantageously determined by means of three different measurements to allow for more reliable and relevant identification. Such a current physical signature increases the discriminating power of the combination of the sound signature and the particle size signature.

[0067] As illustrated on the [ Fig.7 ], the measurement steps E8 and determination E9 are implemented independently of the sound measurement steps E1, particle size measurement E3 and determination E2, E4 of the other lists of particle types M1, N1, preferably in parallel for a faster process.

[0068] With reference to figures 7 And 8The measurement step E8 is implemented by a third measuring device 10, such as a temperature sensor, humidity sensor, electrochemical sensor, or metal oxide sensor (MOX sensor). The determination step E9 of a third particle list L1 is implemented after the measurement step E8. The third particle list L1 chosen corresponds to the one whose reference physical signature P1, P2, P3 is closest to the current physical signature Pc, namely P1 in this example. The determination step E4 is implemented by the control device 11, and preferably by the statistical classification module 7.

[0069] With reference to figures 7 And 8 , during the determination step E7, the control unit 11 performs an intersection operation between the first list of particle types M1, the second list of particle types and the third list of particle types L1: Tc = M1 ∩ N1 ∩ L1.

[0070] According to a preferred embodiment of the invention illustrated in the [ Fig.9 The second database 5 and the third database 8 are combined and contain several combinations of reference activities C1-C4. Each combination of reference activities C1-C4: It includes on the one hand a reference sound signature S1, S2, S3 and on the other hand a reference physical signature P1, P2, P3, and is associated with a combined list of particle types D1-D4.

[0071] Each combined list of particle types D1-D4 is the intersection of a second list of particle types N1, N2, N3 and a third list of particle types L1, L2, L3, namely those associated with the reference sound signature S1, S2, S3 and the reference physical signature P1, P2, P3. For example, the reference activity combination C2 = (S1; P2) is associated with a combined list of particle types D2 = N1 ∩ L2. The reference physical signature P1, P2, P3 is thus an auxiliary measure of the reference sound signature S1, S2, S3, which allows for the precise and reliable determination of the industrial activity implemented.As an auxiliary measure, it could also be envisaged to mount an electronic chip, for example of the NFC or Bluetooth type, on the systems implementing the industrial activity, such as a saw or a drill, and to determine the industrial activity implemented by reading the electronic chips located nearby.

[0072] With reference to the [ Fig.9The determination steps E4 and E6 form a single step, implemented after the measurement steps E3 and E5, in which a combined list of particle types D1-D4 is determined from the current sound signature Sc and the current physical signature Pc. Specifically, the statistical processing module 7 determines the reference activity combination C1-C4 that most closely matches the current sound signature Sc and the current physical signature Pc. The control unit 11 then selects the associated combined list of particle types D1-D4, which is used for the determination step E7 of particle type Tc 1.

Claims

1. A method for dynamically determining at least one type (Tc) of particles (1), the particles (1) being emitted during the operation of an industrial activity (2) in a physical medium (3), said method being implemented by means of at least: • a first database (4) comprising a plurality of reference sound signatures (S1, S2, S3), each associated with a first list of particle types (M1, M2, M3), each reference sound signature (S1, S2, S3) being characteristic of at least one industrial activity (2), and • a second database (5) comprising a plurality of reference particle size signatures (G1, G2, G3), each associated with a second list of particle types (N1, N2, N3), each reference particle size signature (G1, G2, G3) being characteristic of at least one particle type (1), • said method comprising: • a step of measuring the sound (E1) of the industrial activity (2) in the physical medium (3), so as to determine a common sound signature (Sc), • a step of determining (E2), using the first database (4), a first list of particle types (M1) from the common sound signature (Sc), • a step of measuring the particle size (E3) of the particles (1) emitted into the physical medium (3) in order to determine a common particle size signature (Gc), • a step of determining (E4), using the second database (5), a second list of particle types (N1) from the common particle size signature (Gc), • a step of determining (E7) of at least one type (Tc) of particles (1) by intersection of the first list of particle types (M1) and the second list of particle types (N1).

2. The method according to claim 1, said method also being implemented by means of a threshold database (6) comprising a plurality of types (T1, T2, T3) of particles (1), each being associated with an acceptance threshold (A1, A2, A3), said method comprising: • a determination step (E8), by means of the threshold database (6), an acceptance threshold (A1) from the determined type (Tc) of particles (1), and • a step of issuing an alarm (E9) if the common particle size signature (Gc) exceeds the acceptance threshold (A1).

3. The method according to one of claims 1 and 2, wherein each reference sound signature (S1, S2, S3) in the first database (4) comprises at least one frequency characteristic of the associated industrial activity (2), and preferably a sound spectrum characteristic of the associated industrial activity (2).

4. The method according to one of claims 1 to 3, wherein the particle size measurement step (E3) is implemented using an optical particle counter.

5. The method according to one of claims 1 to 4, wherein the determination step (E2) is implemented by determining, among the reference sound signatures (S1, S2, S3) of the first database (4), the one closest to the common sound signature (Sc).

6. The method according to one of claims 1 to 5, wherein the determination step (E2) is implemented by means of a statistical classification module (7), preferably of the support vector or neural network type.

7. The method according to claim 6, also comprising a preliminary training step (E0) of the statistical classification module (7) based on a plurality of training sound signatures (Se), the statistical classification module (7) being configured to determine the closest reference sound signature (S1) in the first database (4).

8. The method according to one of claims 1 to 7, said method also being implemented by means of a third database (8) comprising a plurality of reference physical signatures (P1, P2, P3), each being associated with a third list of particle types (L1, L2, L3), each reference physical signature (P1, P2, P3) being characteristic of the physical medium (3), said method comprising: • a step of measuring (E5) a common physical signature (Pc) of the physical medium (3), • a determination step (E6), by means of the third database (8), a third list of particle types (L1) from the common physical signature (Pc), • the determination step (E7) being further implemented by intersection with the third list of particle types (L1).

9. The method according to claim 8, wherein the common physical signature (Pc) comprises one or more of the following: a temperature measurement, a humidity measurement, and an odor measurement of the physical medium (3).

10. A system (12) for dynamically determining at least one type (Tc) of particles (1) for implementing the method according to one of claims 1 to 9, the particles (1) being emitted during the operation of an industrial activity (2) in a physical medium (3), said system (12) comprising at least: • a first database (4) comprising a plurality of reference sound signatures (S1, S2, S3), each associated with a first list of particle types (M1, M2, M3), each reference sound signature (S1, S2, S3) being characteristic of at least one industrial activity (2), and • a second database (5) comprising a plurality of reference particle size signatures (G1, G2, G3), each associated with a second list of particle types (N1, N2, N3), each reference particle size signature (G1, G2, G3) being characteristic of at least one particle type (1), • a first measuring device (9) configured to measure a common sound signature (Sc) of the industrial activity (2) in the physical medium (3), • a second measuring device (10) configured to measure a common particle size signature (Gc) of the particles (1) in the physical medium (3), and • a control device (11) configured to determine: • by means of the first database (4), a first list of particle types (M1) from the common sound signature (Sc), • by means of the second database (5), a second list of particle types (N1) from the common particle size signature (Gc), • a type (Tc) of particles (1) by intersection of the first list of particle types (M1) and the second list of particle types (N1).

Images