WO2016098491A1 - Optimum rotation speed estimation device, optimum rotation speed estimation system, and rotation speed control device - Google Patents

Abstract

[Problem] To accurately estimate the optimum rotation speed of a propeller. [Solution] An optimum rotation speed estimation device (9b) is provided with: a speed through water prediction unit (34) for predicting a prediction value of the speed through water necessary for a ship to arrive at a destination by a target arrival time; a wind velocity prediction value output unit (36) for outputting a prediction value of wind velocity that is expected to act on the ship at a point of interest on a navigation route; a rotation speed candidate value output unit (35) for outputting multiple rotation speed candidate values as candidates for an optimum rotation speed; a speed through water candidate value calculation part (12) which receives input of the wind velocity estimation value at the point of interest and the multiple rotation speed candidate values and outputs, as speed through water candidate values of the ship at the point of interest, values that correspond to conditions specified by combinations of the wind velocity estimation value and the rotation speed candidate values; and an optimum rotation speed estimation part (15) that estimates that the optimum rotation speed is the rotation speed candidate value that is obtained when a speed through water candidate value at which the difference between the speed through water candidate value corresponding to the rotation speed candidate value and the speed through water prediction value is the smallest is output.

Description

Optimal rotational speed estimation device, optimal rotational speed estimation system, and rotational speed control device

The present invention includes an optimum rotational speed estimation device that estimates an optimal rotational speed of a propeller for generating a thrust of a ship, an optimal rotational speed estimation system that includes an optimal rotational speed estimation device, and an optimal rotational speed estimation device. The present invention relates to a rotation speed control device.

Conventionally, as disclosed in paragraph (0038) of Patent Document 1, for example, a navigation device that instructs an automatic steering device along a preset navigation route is known. This device is configured to notify the user of caution information such as a navigation prohibition area on the route created by the user.

JP 2013-217860 A

On the other hand, when trying to calculate the propeller rotation speed of a ship necessary for navigating a preset navigation route at a target time, the following methods are conceivable. Specifically, for example, by dividing the distance of the navigation route by the target time, the ground speed of the ship necessary to arrive at the destination at the target time can be obtained. Then, by calculating the rotation speed of the propeller necessary for the ship to navigate at the ground speed from the experimental data, etc., the rotation speed of the propeller (optimum rotation speed) required to arrive at the destination at the target time. Can be obtained. However, with this method, there is a possibility that the optimum rotational speed cannot be accurately calculated.

The present invention is for solving the above-mentioned problems, and the object thereof is to accurately estimate the optimum rotational speed of the propeller for generating the thrust of the ship.

(1) In order to solve the above-described problem, an optimal rotational speed estimation device according to an aspect of the present invention is an optimal rotational speed estimation device that estimates the optimal rotational speed of the propeller in a ship propelled by the rotation of the propeller. , The ground velocity vector of the ship necessary for the ship navigating along the preset navigation route to arrive at the destination by the target arrival time, and the surface current at the target point that is the point on the navigation route A water speed prediction unit that predicts a water speed prediction value that is a water speed vector at the target point required to arrive at the destination by the target arrival time based on the predicted speed value; and A wind speed prediction value output unit that outputs a wind speed prediction value that is a wind speed vector that is predicted to act on the ship at the target point, and a mutual value indicating the rotation speed of the propeller The rotational speed candidate value output unit that outputs different rotational speed candidate values that are different data and are candidates for the optimal rotational speed, the predicted wind speed value at the target point, and the multiple rotational speed candidate values. A value corresponding to each condition that is input and specified by a combination of the wind speed prediction value and the rotation speed candidate value is output as a water speed candidate value that is a candidate for the water speed vector of the ship at the target point. A target rotational speed value corresponding to a candidate water speed value having a smallest difference from the predicted water speed value among the plurality of water speed candidate values. And an optimum rotational speed estimation unit that estimates the optimum rotational speed at the point.

(2) Preferably, the water speed candidate value calculation unit is configured using a neural network, and at least one of the data related to the predicted wind speed value and the data related to the rotation speed candidate value is input to each. An output unit that outputs two candidates for water velocity, and outputs a value output from the unit on the input side in the neural network after being multiplied by a coupling coefficient; Is transmitted.

(3) More preferably, the optimum rotational speed estimation device includes a ground speed calculation unit that calculates a ground speed vector of the ship that sails at sea, a propeller rotational speed detection unit that detects the rotational speed of the propeller, A wind speed anemometer mounted on a ship and measuring a wind speed vector of wind force with respect to the ship, each input unit including data relating to the rotation speed of the propeller detected by the propeller rotation speed detector; and One of the data relating to the wind speed vector measured by the wind speed anemometer is input, and from the output unit, the rotation speed of the propeller detected by the propeller rotation speed detector and the wind speed anemometer are measured. The value corresponding to each condition specified by the combination of the wind speed vector is estimated as the water speed vector of the ship, and the water speed estimated value The optimum rotational speed estimation device compares the water speed estimated value with the ground speed vector as a teacher signal calculated by the ground speed calculating unit, and the water speed estimated value And an updating unit for updating the coupling coefficient so that an error between the teaching signal and the teacher signal is reduced.

(4) In order to solve the above-described problem, an optimal rotational speed estimation device according to an aspect of the present invention is an optimal rotational speed estimation device that estimates the optimal rotational speed of the propeller in a ship propelled by the rotation of the propeller. , The ground velocity vector of the ship necessary for the ship navigating along the preset navigation route to arrive at the destination by the target arrival time, and the surface current at the target point that is the point on the navigation route A water speed prediction unit that predicts a water speed prediction value that is a water speed vector at the target point required to arrive at the destination by the target arrival time based on the predicted speed value; and A wind speed prediction value output unit that outputs a wind speed prediction value that is a wind speed vector that is predicted to act on the ship at the target point, the rotation speed of the propeller, and the ship A plurality of cell units that store the ground speed vector of the ship for each condition specified by a combination of wind speed vectors of wind power for each of the plurality of conditions, and stored in each cell unit A storage unit that stores an average value of the ground speed vector as a water speed vector for each of the conditions corresponding to each cell unit, and the storage unit is specified by the wind speed predicted value and the water speed predicted value. And an optimal rotational speed estimation unit that estimates the rotational speed as the optimal rotational speed.

(5) Preferably, the optimum rotational speed estimation device includes a ground speed calculation unit that calculates a ground speed vector of the ship that sails at sea, a propeller rotational speed detection unit that detects the rotational speed of the propeller, and the ship And an anemometer for measuring the wind speed vector of the wind force with respect to the ship, and the storage unit calculates the ground speed vector calculated by the ground speed calculation unit to calculate the ground speed vector. An update unit for storing in the cell unit specified by a combination of the rotation number detected by the propeller rotation number detection unit and the wind speed vector measured by the wind speed and anemometer when necessary data is acquired. Are further provided.

(6) Preferably, the optimum rotational speed estimation device is a ground speed prediction which is a ground speed vector of the ship necessary for the ship navigating along the navigation route to arrive at the destination by a target arrival time. A ground speed prediction unit that predicts a value, and the water speed prediction unit predicts the water speed prediction value based on the ground speed vector predicted by the ground speed prediction unit.

(7) More preferably, the optimum rotational speed estimation device receives the navigation route, the departure time of the ship, and the target arrival time, and the input navigation route, the departure time, and the target. A navigation plan input unit that outputs the arrival time to the ground speed prediction unit;

(8) More preferably, the optimum rotational speed estimation device estimates the departure time based on at least one of a stop time of the main engine of the ship and a start time of the main engine of the ship. A departure time estimation unit that outputs the departure time to the navigation plan input unit as a predicted departure time.

(9) Preferably, the optimum rotation speed estimation device detects the departure time based on the rotation speed of the propeller and the ground speed of the ship, and sets the departure time as a departure time fixed value, the navigation plan input unit. And a departure time detection unit for outputting the information.

(10) Preferably, the optimum rotational speed estimation device is mounted on the ship as the ship.

(11) In order to solve the above-described problem, an optimal rotational speed estimation system according to an aspect of the present invention is provided with any of the above-described optimal rotational speed estimation devices mounted at a place different from the ship as a ship. , Arranged at a location different from the optimum rotational speed estimation device, and transmits data relating to the navigation route of the ship, the departure time of the own ship, and the target arrival time of the own ship to the optimum rotational speed estimation device And a receiving unit that is arranged at a location different from the optimum rotation speed estimation device and receives data related to the optimum rotation speed estimated by the optimum rotation speed estimation device.

(12) In order to solve the above-described problem, a rotational speed control device according to an aspect of the present invention includes any of the above-described optimal rotational speed estimation device and a ship propeller estimated by the optimal rotational speed estimation device. A rotation speed control unit that controls the rotation speed of the propeller of the ship based on the optimum rotation speed.

According to the present invention, it is possible to accurately estimate the optimum rotational speed of the propeller for generating the thrust of the ship.

It is a block diagram which shows the structure of the estimation apparatus which concerns on embodiment of this invention. It is a schematic diagram which shows an example of a structure of the water velocity output part shown in FIG. It is a vector diagram which shows the relationship between ground speed, water speed, and surface layer flow velocity. It is a figure for demonstrating the reason the water speed estimated value from the water speed output part shown in FIG. 1 converges on a water speed. It is a figure shown corresponding to FIG. 2, Comprising: The relationship between the rotation speed candidate value and wind speed prediction value which are input into a water speed output part, and the water speed candidate value output corresponding to these input values It is a figure shown about. It is a graph for demonstrating operation | movement of the optimal rotation speed estimation part shown in FIG. It is a block diagram which shows the structure of the estimation apparatus which concerns on a modification. It is a block diagram which shows the structure of the estimation apparatus which concerns on a modification. It is a block diagram which shows the structure of the estimation apparatus which concerns on a modification. FIG. 10 is a diagram for explaining in detail an optimum rotational speed estimation unit shown in FIG. 9. It is a block diagram which shows the structure of the estimation apparatus which concerns on a modification. It is a block diagram which shows the structure of the estimation apparatus which concerns on a modification. It is a block diagram which shows the structure of the learning coefficient setting process part shown in FIG. It is a figure which shows typically the table memorize | stored in a memory | storage part, and the self-organization map SOM memorize | stored corresponding to each cell of the table. It is a block diagram which shows the structure of the learning coefficient setting process part of the estimation apparatus which concerns on a modification. It is a figure which shows the table memorize | stored in a memory | storage part, and the learning data memorize | stored corresponding to each cell of the table. It is a block diagram which shows the structure of a rotation speed control apparatus. It is a block diagram which shows the structure of the estimation apparatus which concerns on a modification. It is a block diagram which shows the structure of the departure time automatic input part shown in FIG. It is a block diagram which shows the structure of the departure time automatic input part of the estimation apparatus which concerns on a modification. It is a block diagram which shows the structure of an optimal rotation speed estimation system. It is a schematic diagram for demonstrating complementation of learning data.

FIG. 1 is a block diagram showing a configuration of an estimation apparatus 1 according to an embodiment of the present invention. The estimation device 1 is mounted on a ship that sails on the sea by thrust generated by the rotation of a propeller. The estimation device 1 of the present embodiment is suitable for a ship (for example, a merchant ship) that navigates a predetermined route to a destination, and will be described later in detail, but does not arrive too early in time for a target arrival time (estimated arrival time). The rotation speed of the propeller is determined so as to estimate the rotation speed (that is, the optimum rotation speed from the viewpoint of fuel consumption).

The estimation device 1 includes a surface flow estimation device 8 and an optimum rotational speed estimation device 9 as shown in FIG. The surface layer flow estimation device 8 is configured to estimate the direction and magnitude of the surface layer flow at the ship position, that is, the velocity vector of the surface layer flow at the ship position. On the other hand, the optimal rotational speed estimation device 9 is configured to estimate the optimal rotational speed of the propeller. Below, the structure of the surface layer flow estimation apparatus 8 and the structure of the optimal rotation speed estimation apparatus 9 are demonstrated in order. The surface layer flow is a flow in a depth range of the range from the sea surface to the ship bottom.

[Configuration of surface flow estimation device]
In the surface layer flow estimation device 8, predetermined parameters (in this embodiment, the rotation speed of the propeller of the ship, the true wind speed in the bow direction, and the true wind speed on the starboard direction) are automatically obtained at each predetermined timing. For each condition specified by the combination of values, the surface flow velocity (surface flow velocity vector) at the ship position is calculated. The surface layer flow estimation device 8 includes a GPS signal receiving unit 2, a propeller rotational speed detection unit 3, an anemometer 4 and a part of the configuration requirements of the calculation unit 10 (details will be described later on the ground speed calculation unit 11, A velocity output unit 12, a surface flow calculation unit 13, a coupling coefficient update unit 14), and a display unit 5.

The GPS signal receiving unit 2 is provided as a GNSS signal receiving unit for receiving a GPS signal as a navigation signal (GNSS signal) transmitted from a navigation satellite (not shown). The GPS signal receiving unit 2 is configured by, for example, a GPS antenna. The GPS signal received by the GPS signal receiving unit 2 (that is, the position information of the ship) is notified to the calculation unit 10 together with the time when the GPS signal is received.

In this embodiment, the GPS signal receiving unit 2 is used as the GNSS signal receiving unit. However, the present invention is not limited to this, and a receiving unit used in other GNSS systems may be used. Here, GNSS is an abbreviation for Global Navigation Satellite System (GNSS). This GNSS is a collective term for “GPS” operated by the United States, “GALILEO” operated by Europe, “GLONASS” operated by Russia, and the like.

The propeller rotational speed detection unit 3 is for detecting the rotational speed per unit time of the propeller for generating the thrust of the ship, and is constituted by a sensor capable of detecting the rotational speed, for example. The rotation speed detected by the propeller rotation speed detection unit 3 is notified to the calculation unit 10.

The wind direction anemometer 4 is for measuring the true wind speed in the bow direction and the true wind speed in the starboard direction as information on the wind direction and the wind speed. The anemometer 4 is installed in a place where there are no obstacles that block the wind in the ship where the surface flow estimation device 8 according to the present embodiment is mounted. The bow direction true wind speed and starboard direction true wind speed measured by the anemometer 4 are notified to the calculation unit 10.

The calculation unit 10 estimates the surface layer flow at the ship position (target point) at each predetermined timing based on various information notified from the GPS signal reception unit 2, the propeller rotation number detection unit 3, and the wind direction anemometer 4. Is configured to do. The calculation unit 10 includes a ground speed calculation unit 11, a water speed output unit 12, a surface layer flow calculation unit 13, a coupling coefficient update unit 14, and an optimum rotation number estimation unit 15. Note that, among these structural requirements constituting the arithmetic unit 10, the optimal rotational speed estimation unit 15 is provided as a structural requirement of the optimal rotational speed estimation device 9.

The ground speed calculation unit 11 calculates the ground speed (ground speed vector) of the ship based on the position information of the ship notified from the GPS signal receiving unit 2 and the time when the ship position information is acquired. Specifically, the ground speed calculation unit 11 calculates the ground speed of the ship based on the ship position at at least two timings and the time when the position information of each ship position is acquired. The ground speed calculation unit 11 notifies the surface speed calculation unit 13 and the coupling coefficient update unit 14 of the ground speed calculated in this way.

The water speed output unit 12 is configured to estimate the water speed of the ship and output the estimated water speed as an estimated water speed value. In this embodiment, the water speed output unit 12 includes the propeller rotation speed detected by the propeller rotation speed detection unit 3, the bow direction true wind speed and the starboard direction true wind speed measured by the wind direction anemometer, Is entered. The water speed output unit 12 sets a value corresponding to a condition specified by a combination of these input values (a condition specified by a combination of a certain rotation speed, a certain bow direction true wind speed, and a certain starboard direction true wind speed). It outputs to the surface layer flow calculation part 13 and the coupling coefficient update part 14 as a water velocity estimated value.

FIG. 2 is a diagram schematically illustrating an example of the configuration of the water velocity output unit 12. In this embodiment, the water velocity output unit 12 is configured using a generally known neural network. Specifically, the water velocity output unit 12 includes a plurality of input units U _{IN_1} , U _{IN_2} , U _{IN_3} constituting an input layer, and a plurality of intermediate units U _{MID_1} , U _{MID_2} , U _{MID_3} constituting a hidden layer. And output units U _{OUT — 1} and U _{OUT — 2} constituting the output layer. The configuration of the water velocity output unit 12 illustrated in FIG. 2 is merely an example, and the number of units in each layer and the number of hidden layers are not limited to those illustrated in FIG.

In-water velocity output section 12, the input unit _{U IN_1,} U _{IN_2,} when the input value _{U IN_3} (rotational speed of the propeller, etc.) is input, the coupling coefficient _{W I} for those input _{values, M} is Multiply and output to hidden layer intermediate units U _{MID — 1} , U _{MID — 2} , U _{MID — 3} . Each of the hidden layer intermediate units U _{MID — 1} , U _{MID — 2} and U _{MID — 3 sums} the input values and multiplies the values based on the total values by the coupling coefficients W _{M, O} to the output units U _{OUT — 1} and U _{OUT — 2} . Output. The output units U _{OUT — 1} and U _{OUT — 2 add up} the input values and output a value based on the total value to the surface flow calculation unit 13 and the coupling coefficient update unit 14 as an estimated water velocity value. Note that the value input to the water speed output unit 12 is not necessarily the parameter value itself such as the propeller rotation number, but is a numerical value that has a one-to-one relationship with these parameters (for example, rotation Or a voltage value that changes in proportion to the number).

In the water velocity output unit 12, an appropriate initial value is set for each coupling coefficient W in the initial state. Each coupling coefficient W is updated by the coupling coefficient updating unit 14 as needed. Specifically, each coupling coefficient W reduces an error between the estimated water speed output from the water speed output unit 12 and the ground speed (teacher signal) calculated by the ground speed calculation unit 11. The coupling coefficient update unit 14 updates the value. As a result, the estimated water speed value output from the water speed output unit 12 converges to the water speed of the ship every time the coupling coefficient W is updated.

The surface flow calculation unit 13 is based on the estimated water velocity output from the water velocity output unit 12 and the ground velocity calculated by the ground velocity calculation unit 11. Velocity vector). Specifically, the surface layer flow calculation unit 13 calculates the surface layer flow velocity by subtracting the water velocity from the ground velocity.

Figure 3 is a vector diagram illustrating the ground speed vector V _G, and to water velocity vector V _WT, the relationship between the surface layer flow velocity vector V _T. The ground speed V _G is a speed with respect to the ground surface, and the water speed V _WT is a speed with respect to the water surface (sea surface). A surface current is a flow of water in the surface layer of the sea. Therefore, the relationship between the ground speed vector V _G , the water speed vector V _WT , and the surface layer flow speed vector V _T can be expressed as shown in FIG. Therefore, surface current calculating unit 13, as described above, by subtracting the-water velocity V _WT from ground speed V _G, the surface velocity V _T is calculated.

The coupling coefficient updating unit 14 is configured to reduce the error between the estimated water speed output from the water speed output unit 12 and the ground speed (teacher signal) calculated by the ground speed calculation unit 11. The coupling coefficient W of the speed output unit 12 is updated. For example, the coupling coefficient updating unit 14 updates the coupling coefficient W by using back propagation (error back propagation method), for example.

The display unit 5 displays the direction and size of the surface flow calculated by the surface flow calculation unit 13. Thereby, the user can know the velocity of the surface layer flow at the ship position.

[About estimated water velocity output from the water velocity output unit]
FIG. 4 illustrates the reason why the estimated water speed output from the water speed output unit 12 converges to the water speed every time the coupling coefficient W of the water speed output unit 12 is updated. It is a figure for doing. As described above, each coupling coefficient W stored in the water speed output unit 12 includes the water speed estimation value output from the water speed output unit 12 as needed and the ground speed as a teacher signal calculated as needed. Is updated by the coupling coefficient updating unit 14 so as to reduce the error.

The surface current is different in size and direction due to the sea area, time, weather conditions, and the like. Therefore, the ground speed when the water speed is the same (that is, when the speed of the propeller, the true wind speed in the bow direction, and the true wind speed in the starboard direction are the same) includes components of surface flow velocity of any magnitude and direction. It is thought that. Therefore, when these are averaged (V _G1 to V _G6 in the case of FIG. 4 are averaged), the surface layer flow velocity components cancel each other, and the water velocity component remains. That is, when the coupling coefficient W of the water speed output unit 12 is updated so as to reduce the error between the water speed estimated value of the water speed output unit 12 and the ground speed as described above, the ground speed is increased. Since the influence of the surface layer flow velocity component included in is gradually reduced, the estimated water velocity value of the water velocity output unit 12 converges to the water velocity. Therefore, when the learning data (ground speed data) is sufficiently obtained and the learning is sufficiently advanced (that is, when the coupling coefficient is updated a sufficient number of times), the pair of data from the water speed output unit 12 is The estimated water velocity can be estimated as the water velocity.

In the surface flow estimator 8, the rotational speed is detected by the propeller rotational speed detection unit 3 at each predetermined timing during navigation of the ship, and the true wind speed in the bow direction and the true wind speed in the starboard direction are measured by the wind direction anemometer 4. These pieces of information are output to the water speed output unit 12 as needed. Based on these, the water speed output unit 12 generates the water speed estimation value using a coupling coefficient W that is updated as needed during the navigation of the ship.

[Configuration of optimal speed estimation device]
Based on the navigation plan (the navigation route, the departure time, and the target arrival time) input by the user or the like, the optimum rotational speed estimation device 9 is suitable for propellers that are in time for the destination by the target arrival time and do not arrive too early. Estimate the rotation speed (optimum rotation speed). At that time, as will be described later in detail, the optimum rotational speed estimation device 9 estimates the optimal rotational speed in consideration of the wind speed forecast value and the tidal current forecast value. Thereby, in the optimal rotation speed estimation apparatus 9 which concerns on this embodiment, an optimal rotation speed can be estimated more correctly.

As shown in FIG. 1, the optimum rotational speed estimation device 9 includes a GPS signal receiver 2, a propeller rotational speed detector 3, an anemometer 4, a navigation plan input unit 31, a ground speed predictor 32, The tidal current predicted value output unit 33, the water speed prediction unit 34, the rotation speed candidate value output unit 35, the wind speed predicted value output unit 36, and some of the configuration requirements of the calculation unit 10 (ground speed calculation unit 11, A water speed output unit 12, a coupling coefficient update unit 14, and an optimum rotational speed estimation unit 15). Since the GPS signal receiving unit 2, the propeller rotation number detecting unit 3, and the wind direction anemometer 4 have the same configuration and operation as those of the surface layer flow estimation device 8, the description thereof is omitted.

The navigation plan input unit 31 includes, for example, a keyboard, a touch panel, and the like. The user appropriately operates the navigation plan input unit 31 to input a navigation plan (specifically, a navigation route, a departure time, and a target arrival time).

The ground speed prediction unit 32 predicts the ground speed of the ship necessary to arrive by the target arrival time based on the navigation plan input by the navigation plan input unit 31. Specifically, the ground speed prediction unit 32 divides the navigation distance obtained from the navigation route input from the navigation plan input unit 31 by the navigation time obtained from the departure time and the target arrival time, thereby obtaining the destination. Predict the optimal ground speed to arrive by the target arrival time. The ground speed prediction unit 32 outputs the predicted ground speed to the water speed prediction unit 34 as a ground speed prediction value.

The tidal current predicted value output unit 33 acquires data (direction and speed of the tidal current) related to the tidal current (surface flow) that is announced from a public organization as needed, and uses the acquired data as a tidal current predicted value to measure the water velocity. The prediction unit 34 is notified. The tidal current predicted value output unit 33 outputs the tidal current predicted value at each of a plurality of target points that are points on the navigation route of the ship to the water speed predicting unit 34 among information on tidal currents from public institutions and the like. To do.

The water speed prediction unit 34 is based on the ground speed prediction value output from the ground speed prediction unit 32 and the tidal current prediction value at each target point output from the tidal current prediction value output unit 33 until the target arrival time. Predict the ship's water speed required to arrive. Specifically, the water speed prediction unit 34 subtracts the tidal current predicted value at each target point expressed as a vector from the ground speed vector output from the ground speed prediction unit 32 to thereby automatically Predict ship water speed. The water speed prediction unit 34 notifies the optimum rotation speed estimation unit 15 of the predicted water speed prediction value at each target point.

The wind speed predicted value output unit 36 acquires information on wind speed (wind direction and wind speed) announced by a public institution or the like, and uses the acquired data as a bow direction true wind speed and a starboard direction true wind speed. 12 is notified. The predicted wind speed value output unit 36 outputs the predicted wind speed value at each target point among the information on the wind speed from a public organization or the like to the water speed output unit 12.

The rotational speed candidate value output unit 35 outputs a plurality of rotational speed candidate values (for example, values in increments of 1 rpm) that are different from each other and are candidates for the optimal rotational speed to the water speed output unit 12.

FIG. 5 is a diagram corresponding to FIG. 2, and the rotational speed candidate value and the wind speed prediction value input to the water speed output unit 12 and the water speed output corresponding to these input values. It is a figure shown about the relationship with a candidate value. In the optimum rotational speed estimation device 9, the water speed output unit 12 is provided as a water speed candidate value calculation unit. The water speed output unit 12 of the optimum rotational speed estimation device 9 includes a wind speed prediction value V _n (n = 1, 2,..., N is the number of target points) at a certain target point, and a plurality of rotational speed candidate values R. ₁ , R ₂ ,... Are input. The predicted wind speed value V _n can be expressed as a wind speed vector and can be divided into a bow direction true wind speed V _An and a starboard direction true wind speed V _Bn .

The water speed output unit 12 includes a plurality of input data (R ₁ ) in which a wind speed prediction value V _n at a certain target point and a plurality of rotation speed candidate values (R ₁ , R ₂ ,...) Are combined. And V _n , R ₂ and V _n , R ₃ and V _n ,...) Are sequentially input. The water speed output unit 12 estimates the optimum rotational speed using the water speeds V _WT1 , V _WT2 ,... Output from the output unit corresponding to each of the plurality of input data sequentially input as water speed candidate values. To the unit 15.

FIG. 6 is a graph for explaining the operation of the optimum rotational speed estimation unit 15. The optimum rotational speed estimation unit 15 is the target point predicted by the water speed prediction unit 34 from among a plurality of water speed candidate values V _WT1 , V _WT2 ,... Output from the water speed output unit 12. The water speed predicted value V _WTPn (n = 1, 2,..., N is the number of target points) closest to the water speed candidate value is selected, and the rotation speed candidate value at the time of the water speed candidate value is Estimated as the optimum rotational speed. More specifically, with reference to FIG. 6, the optimum rotation speed estimation unit 15 performs the water speed prediction value V _WTPn represented by a vector and the water speed candidate values V _WT1 , V represented by a vector. _WT2, taking the difference between _... and the rotational speed candidate value R _m that identifies the-water speed candidate value V _WTm when the difference is smallest, and outputs the optimum rotating speed.

As described above, the predicted water speed V _WTPn (n = 1, 2,...) Estimated at each target point is the optimum value at each target point for the ship to arrive at the destination at the target arrival time. This is the speed of the ship's water against water. Therefore, the rotation speed candidate value that identifies the water speed candidate value with the smallest difference from the water speed prediction value is the ship's own ship at each target point for the ship to arrive at the destination at the target arrival time. This is the optimum rotation speed of the propeller.

The display unit 5 displays the optimal rotational speed at each target point estimated by the optimal rotational speed estimation unit 15 as needed. The user adjusts the speed of the propeller of the ship based on the speed of the ship, so that the speed of the propeller can be adjusted so that the ship is in time for the target arrival time and does not arrive too early. At a high speed).

[effect]
As described above, in the optimum rotation speed estimation device 9 of the estimation device 1 according to the present embodiment, the ship arrives at the destination by the target arrival time based on the predicted tidal current speed at each target point on the navigation route. Predicting the water velocity vector of the ship necessary for this purpose. Thereby, since the water velocity vector can be predicted in consideration of the tidal velocity that has a great influence on the ground velocity of the ship, the water velocity can be predicted more accurately. In addition, the optimum rotational speed estimation device 9 estimates the optimal rotational speed of the ship based on the predicted wind speed at each target point. As a result, the optimum rotational speed can be estimated in consideration of the wind speed that greatly affects the ground speed of the ship, and thus the optimal rotational speed can be estimated more accurately.

Therefore, according to the optimum speed estimation device 9, the optimum speed of the propeller for generating the thrust of the ship can be accurately estimated.

Further, in the optimum rotation speed estimation device 9, the water speed output unit 12 is configured using a neural network. Thereby, the water speed output part 12 which can output a water speed can be comprised appropriately.

Further, in the optimum rotational speed estimation device 9, the water speed is adjusted so that an error between the water speed estimated value output from the water speed output unit 12 and the ground speed calculated by the ground speed calculation unit 11 is reduced. The output unit 12 is updated. Thereby, the water speed output part 12 provided with the learning function can be comprised. Moreover, the optimum rotational speed estimation device 9 can accumulate a large amount of data necessary for estimating an accurate water speed during navigation. Therefore, it is possible to save the trouble of preparing a large number of these learning data (ground speed data under certain conditions) in advance and setting an appropriate coupling coefficient based on these learning data.

Further, the optimum rotational speed estimation device 9 predicts the water speed prediction value based on the ground speed prediction value predicted by the ground speed prediction unit 32. Thereby, a predicted water velocity value can be appropriately predicted.

Further, in the optimum rotational speed estimation device 9, the navigation route, the ship departure time, and the target arrival time input by the user are input to the ground speed prediction unit 32. As a result, the ground speed prediction unit 32 can calculate the navigation distance from the navigation route and can calculate the navigation time from the departure time and the target arrival time. Therefore, the ground speed required to arrive at the destination by the target arrival time. Can be appropriately predicted.

Further, according to the optimum rotational speed estimation device 9, since the data on the tidal current and the wind speed announced from a public institution or the like can be used at any time, it is possible to save time and effort for predicting the tidal current and the wind speed.

Further, the optimum rotational speed estimation device 9 is mounted on the own ship. As a result, the user on the ship can appropriately operate the optimum rotation speed estimation device 9 and check the optimum rotation speed displayed on the display unit 5. A number estimation device can be provided.

As mentioned above, although embodiment of this invention was described, this invention is not limited to these, A various change is possible unless it deviates from the meaning of this invention.

[Modification]
(1) FIG. 7 is a block diagram illustrating a configuration of an estimation apparatus 1a according to a modification. Unlike the calculation unit 10 of the above-described embodiment, the calculation unit 10a of the estimation device 1a according to the present modification has a configuration in which the surface layer flow calculation unit 13 is omitted. That is, the estimation device 1 a according to this modification does not have a function as the surface layer flow estimation device 8, and is provided as the optimum rotational speed estimation device 9. Therefore, according to the estimation apparatus 1a according to the present modification, unlike the case of the above embodiment, the surface layer flow near the ship cannot be estimated, but the optimum rotation speed of the propeller is set in the same manner as in the above embodiment. Can be estimated.

(2) FIG. 8 is a block diagram showing a configuration of the estimation apparatus 1b according to the modification. Unlike the estimation apparatus 1a shown in FIG. 8, the estimation apparatus 1b according to this modification has a configuration in which the coupling coefficient update unit 14 is omitted. That is, the estimation device 1b according to this modification does not have a learning function. In addition, the estimation device 1b according to this modification has a configuration in which the GPS signal receiving unit 2, the ground speed calculation unit 11, the propeller rotation number detection unit 3, and the wind direction anemometer 4 are also omitted.

In the estimation apparatus 1b according to the present modification, the water-to-water output from the water-speed output unit 12 in which the coupling coefficient W is determined based on a lot of learning data (ground speed data at a certain condition) acquired in advance. Based on the speed candidate value, the optimum rotational speed is estimated. Even with such a configuration, the optimum rotational speed of the propeller can be estimated as in the case of the estimation device 1a shown in FIG.

(3) FIG. 9 is a block diagram showing a configuration of the estimation apparatus 1c according to the modification. The estimation apparatus 1c according to the present modification is different from the estimation apparatus 1a illustrated in FIG. 7 in that the water speed output unit, the coupling coefficient update unit, and the rotation number candidate value output unit are omitted, and the optimum rotation number estimation unit The configuration is very different. The optimum rotation speed estimation unit 15c of the present modification includes a detection value output from the propeller rotation speed detection unit 3, a measurement value output from the anemometer 4 and a wind speed prediction value output from the wind speed prediction value output unit 36. , And a predicted water speed value output from the water speed prediction unit 34.

FIG. 10 is a diagram for explaining the optimum rotational speed estimation unit 15c in detail. As shown in FIGS. 9 and 10, the optimum rotation speed estimation unit 15 c includes a storage unit 16 and an update unit 17.

In the storage unit 16, a matrix table is stored as shown in FIG. In this table, each condition (in each cell portion 16a of the table) specified by a combination of each value (X1, X2, X3,...) Of the wind speed and wind direction and each value (R1, R2, R3,. The ground speed calculated at the time of (corresponding) is stored. In FIG. 10, one ground speed value is indicated by one circle. That is, the storage unit 16 stores, for example, five ground speed values calculated when the wind speed and the wind direction value are X1 and the rotation speed value is R1.

As described above with reference to FIG. 4, when the ground speed under a certain condition (a condition specified by a combination of a certain rotation speed and a certain wind direction and wind speed) is averaged, the surface flow velocity components included in the ground speed cancel each other. Therefore, the average value is close to the water velocity. Therefore, when the average value of the ground speeds included in each cell unit 16a of the optimum rotational speed estimation unit 15c according to this modification is taken, the value is close to the water speed.

The update unit 17 calculates the ground speed calculated at the timing when the rotational speed from the propeller rotational speed detection unit 3 input to the optimal rotational speed estimation unit 15c and the wind direction and wind speed measured by the anemometer 4 are detected. Is used to update the table stored in the storage unit 16. Specifically, the ground speed calculated when a predetermined rotation speed (for example, R3) and a predetermined wind direction and wind speed (for example, X2) are detected or measured is added to the cell specified by R3 and X2. By performing this operation as needed, learning data is accumulated even during navigation, and the water speed can be estimated more accurately. That is, the optimum rotational speed estimation unit 15c according to this modification also has a learning function. As a result, the water speed can be calculated more accurately.

When the wind speed prediction value and the water speed prediction value at a certain target point are input to the optimum rotation speed estimation unit 15c, the optimum rotation speed estimation unit 15c, based on the wind speed prediction value and the water speed prediction value, Estimate the optimum number of revolutions at the target point. Specifically, referring to FIG. 10, the optimum rotational speed estimation unit 15 c includes a plurality of cell units 16 a (in the same column as X <b> 2 in the case of FIG. 10) identified by the input wind speed prediction value (for example, X <b> 2). A value obtained by averaging the ground speeds included in each of the cell parts) for each cell part 16a is compared with the predicted water speed. And the rotation speed of the propeller specified by the cell section 16a having the average value closest to the predicted water speed among the plurality of cell sections 16a is estimated as the optimum rotation speed. Even with such a method, as in the case of the above-described embodiment, the optimum rotational speed can be estimated more accurately.

In addition, by setting it as the structure which abbreviate | omitted the update part 17 in this modification, the estimation apparatus 1d which does not have a learning function can be comprised (refer FIG. 11). In this case, it is necessary to store a plurality of previously acquired learning data (data corresponding to one circle in FIG. 10) in the storage unit 16.

(4) FIG. 12 is a block diagram showing a configuration of the estimation apparatus 1e according to the modification. The estimation apparatus 1e according to the present modification has a configuration in which a learning coefficient setting processing unit 20 is further provided with respect to the estimation apparatus 1a shown in FIG.

The water velocity output unit 12e is configured using a neural network, as in the above embodiment, and is configured so that the coupling coefficient is updated as needed by so-called supervised learning. In the estimation device 1e, an error between the output value from the water speed output unit 12e and the teacher signal (ground speed) is calculated. Then, the estimating apparatus 1e updates the coupling coefficient W while propagating the error as a learning signal from the unit on the output layer side to the unit on the input layer side. The correction amount of the coupling coefficient is given by the following equation (1).

[Equation 1]
ΔW _{i, j} ^{n, n−1} (t) = ηδ _i ⁿ X _j ⁿ⁻¹ + αΔW _{i, j} ^{n, n−1} (t−1) (1)

In Equation (1), ΔW _{i, j} ^{n, n−1} (t) is a correction amount for the weight of the coupling between the unit j of the n−1 layer and the unit i of the n layer, η is a learning coefficient, δ _i ⁿ is a learning signal returned from the unit i of the nth layer to each unit of the n−1 layer, X _j ⁿ⁻¹ is an output value of the unit j of the n−1 layer, α is a stabilization coefficient, ΔW _{i, j} ^{n , n-1} (t-1) indicates the previous correction amount. Note that the n-1th layer is one layer on the input side than the nth layer.

FIG. 13 is a block diagram illustrating a configuration of the learning coefficient setting processing unit 20. The learning coefficient setting processing unit 20 is for setting the learning coefficient in Expression (1) as needed. As illustrated in FIG. 13, the learning coefficient setting processing unit 20 includes a storage unit 21, an SOM update unit 22, a count unit 23, a learning coefficient calculation unit 24, and a learning coefficient setting unit 25. .

FIG. 14 is a diagram schematically showing a table stored in the storage unit 21 and a self-organizing map SOM stored corresponding to each cell of the table. As shown in FIG. 14, the storage unit 21 stores a table cut in a mesh shape for each predetermined propeller rotational speed and for each predetermined wind speed and wind direction. A corresponding self-organizing map SOM is stored in each cell of this table. Each self-organizing map SOM of this modification is a two-dimensional SOM composed of n × n units. Each unit stores a reference vector having the same dimension as the input vector. In an initial state (a state in which learning is not performed), an appropriate reference vector is set for each unit.

The SOM update unit 22 updates the SOM according to an input vector (a vector composed of a propeller rotation speed, a wind direction, a wind speed, a ground speed, and the like input at every predetermined timing). Specifically, the SOM update unit 22 updates the SOM stored in the cell including the input rotation speed and wind direction and wind speed as follows.

Specifically, the SOM update unit 22 sets the unit having the shortest Euclidean distance from the input vector as the winner unit, the reference vector stored in the winner unit, and the reference vector stored in units around the winner unit. Is updated based on the following equation (2).

[Equation 2]
m _i (t + 1) = m _i (t) + h _i (t) [x (t) −m _i (t)] (2)

Here, m _i is a reference vector, x (t) is an input vector, and h _i is a neighborhood function represented by c · exp (−dis ² / α ² ). In the neighborhood function, c is a learning rate coefficient, and dis = | x−m _c |. Here, _mc is a reference vector that minimizes the Euclidean distance from x (t).

The SOM update unit 22 updates the self-organizing map SOM at any time using the above-described equation (2) according to the input vector input at any time.

The counting unit 23 counts the number of units having a reference vector whose difference from the input vector (Euclidean distance) is a threshold value or less.

The learning coefficient calculation unit 24 takes the reciprocal of the value counted by the counting unit 23 and calculates the value as a learning coefficient. That is, the learning coefficient is small when the count value is large (when there are many similar input data), and the learning coefficient is large when the count value is small (when there are few similar input data).

The learning coefficient setting unit 25 notifies the water speed output unit 12e of the value calculated by the learning coefficient calculation unit 24, and sets it as the learning coefficient η in the equation (1). The water speed output unit 12e uses the learning coefficient η to update the coupling coefficient based on the equation (1), and then calculates the water speed vector based on the updated coupling coefficient.

According to this modification, when a large number of similar learning data (input vectors) are accumulated, the learning coefficient becomes small. In this case, as is clear from the above-described expression (1), the correction amount ΔW _{i, j} ^{n, n−1} (t) of the coupling coefficient becomes small. On the other hand, when similar learning data is not accumulated or only a little is accumulated, the learning coefficient is increased. In this case, as is clear from the equation (1), the correction amount of the coupling coefficient becomes large. Thereby, according to this modification, the bias | inclination of the output value from a water speed output part resulting from accumulating many similar learning data can be suppressed.

(5) FIG. 15 is a block diagram illustrating a configuration of the learning coefficient setting processing unit 26 of the estimation apparatus according to the modification. As in the case of the learning coefficient setting processing unit 20 of the modification described above, the learning coefficient setting processing unit 26 according to the present modification is expressed by the equation (1) used in the water velocity output unit configured using a neural network. This is for setting the learning coefficient η. However, the learning coefficient setting processing unit 26 according to the present modification is different in configuration from the learning coefficient setting processing unit 20 of the above-described modification. As illustrated in FIG. 15, the learning coefficient setting processing unit 26 according to the present modification includes a storage unit 27, a learning coefficient calculation unit 28, and a learning coefficient setting unit 29.

FIG. 16 is a diagram showing a table stored in the storage unit 27 and learning data stored corresponding to each cell (each area) of the table. As illustrated in FIG. 16, the storage unit 27 stores a table cut in a mesh shape for each predetermined propeller rotational speed and each predetermined wind speed and wind direction, as in the case of the above-described modification. In this modification, the learning data stored in each area is mapped according to the ground speed of each learning data. Specifically, as shown in FIG. 17, in a map having a plurality of subareas cut in a mesh shape for each predetermined bow direction ground speed and each predetermined starboard direction ground speed, each learning data is It is mapped according to the speed.

The learning coefficient calculation unit 28 calculates the number of learning data (4 in the case of FIG. 16) stored in the subarea including the most recently input learning data among all the subareas of the area including the subarea. A value obtained by normalizing the reciprocal of the value divided by the number of learning data stored in the subarea with the largest number of learning data (10 in subarea A in the case of FIG. 16) is set as the learning coefficient. Then, the learning coefficient setting unit 29 notifies the estimator of the learning coefficient set by the learning coefficient calculation unit 28 and sets it as the learning coefficient η in the equation (1), similarly to the learning coefficient setting unit 25 of the modified example. . Even with such a configuration, the learning coefficient can be set appropriately.

(6) FIG. 17 is a block diagram showing a configuration of a rotational speed control device 1f provided with the optimal rotational speed estimation device 9 shown in FIG. In the example shown in FIG. 7, the rotational speed estimated by the optimal rotational speed estimation device 9 is displayed on the display unit 5, but is not limited thereto. Specifically, as shown in FIG. 17, instead of the display unit 5, a propeller rotational speed control unit 6 that rotates the propeller of the ship at the optimal rotational speed estimated by the optimal rotational speed estimation device 9 may be provided. . Thereby, it can control automatically so that the rotation speed of the propeller of a ship may become the optimal rotation speed.

(7) In the above embodiment, the optimum rotation speed of the propeller is estimated at each target point, and each optimum rotation speed is displayed on the display unit 5 as needed. However, the present invention is not limited to this. Specifically, the optimal rotational speed of the propeller estimated at each target point may be averaged, and the averaged optimal rotational speed may be displayed on the display unit 5.

(8) FIG. 18 is a block diagram showing a configuration of an estimation apparatus 1g according to a modification. In the embodiment and the modification described above, the user appropriately operates the navigation plan input unit 31 and inputs the navigation plan (specifically, the navigation route, the departure time, and the target arrival time). Absent. Specifically, the estimation device 1g according to this modification includes a departure time automatic input unit 40. The departure time automatic input unit 40 estimates or detects the departure time of the ship, and automatically inputs the departure time to the navigation plan input unit 31 as needed.

In the ship, the operation of the end of the navigation (stop of the main engine), the start of the main engine, and the departure of the ship is repeated for each navigation. Then, in the departure time automatic input unit 40 of the estimation device 1g according to the present modification, as will be described in detail later, until the main aircraft (mechanism portion for generating thrust in the ship) is stopped in the past until the next departure. (Hereinafter also referred to as ship stop time). The departure time automatic input unit 40 stores a time from when the main engine is activated in the past until the departure (hereinafter also referred to as warm-up operation time). Based on these data, the departure time automatic input unit 40 estimates the time at which the ship departs before the ship actually departs. Therefore, the estimation device 1g according to the present modification is suitable for a ship (for example, a regular ship) in which the time until the next departure after the main engine is stopped is generally determined.

FIG. 19 is a block diagram illustrating a configuration of the departure time automatic input unit 40. The departure time automatic input unit 40 includes a main engine stop time detection unit 41, a main machine activation time detection unit 42, a departure time detection unit 43, a first storage unit 44, a second storage unit 45, and a first departure time estimation. Unit 46 and a second departure time estimating unit 47.

The main machine stop time detection unit 41 detects the time (main machine stop time) every time the operation of the main machine is stopped. The main machine stop time detection unit 41 outputs the detected main machine stop time to the first storage unit 44 and the first departure time estimation unit 46 each time.

The main machine activation time detector 42 detects the time (main machine activation time) each time the main machine is activated. The main machine activation time detection unit 42 outputs the detected main machine activation time to the second storage unit 45 and the second departure time estimation unit 47 each time.

The departure time detection unit 43 detects the time (departure time) every time the ship departs. Specifically, the departure time detector 43 detects the rotation speed and ground speed of the propeller of the ship, and detects the departure time of the ship based on the detected rotation speed and ground speed. The departure time detection unit 43 outputs the detected departure time to the first storage unit 44, the second storage unit 45, and the navigation plan input unit 31 each time as a departure time fixed value.

The first storage unit 44 calculates the ship stop time based on the main engine stop time output from the main engine stop time detection unit 41 as needed and the departure time output from the departure time detection unit 43 as needed, The ship stop time is stored. In the present modification, the first storage unit 44 stores a plurality of ship stop times that occur for each navigation.

The second storage unit 45 calculates the warm-up operation time based on the main unit start time output from the main unit start time detection unit 42 as needed and the departure time output from the departure time detection unit 43 as needed, The warm-up operation time is stored. In the present modification, the second storage unit 45 stores a plurality of warm-up operation times that occur for each navigation.

The first departure time estimation unit 46 estimates the departure time of the ship based on the main engine stop time detected by the main engine stop time detection unit 41 and the ship stop time stored in the first storage unit 44. Specifically, for example, as an example, the first departure time estimation unit 46 estimates the time when the average value of the plurality of ship stop times stored in the first storage unit 44 has elapsed from the main engine stop time as the departure time. This is output to the navigation plan input unit 31 as the first departure time predicted value.

The second departure time estimation unit 47 estimates the departure time of the ship based on the main unit start time detected by the main unit start time detection unit 42 and the warm-up operation time stored in the second storage unit 45. Specifically, for example, as an example, the second departure time estimation unit 47 estimates the time when the average value of a plurality of warm-up operation times stored in the second storage unit 45 has elapsed from the main engine start time as the departure time. This is output to the navigation plan input unit 31 as the second departure time predicted value.

The navigation plan input unit 31 outputs the first departure time prediction value, the second departure time prediction value, and the departure time fixed value that are input as needed together with the navigation route and the target arrival time that are input in advance. Thereby, the optimal rotation speed estimation device 9g of the present modification updates the optimal rotation speed every time the first departure time predicted value, the second departure time predicted value, and the departure time fixed value are calculated.

Specifically, the navigation plan input unit 31 outputs a first estimated departure time estimated value that is estimated earliest before the departure, together with the navigation route and the target arrival time. Then, the optimum rotational speed estimation device 9g estimates the optimal rotational speed after the predicted first departure time is calculated. In this way, in this modification, the optimum rotation speed can be known at a relatively early stage before departure, so that the ship's operation plan can be planned at an early stage based on the optimum rotation speed.

In addition, the navigation plan input unit 31 outputs the second departure time predicted value estimated next to the first departure time predicted value together with the navigation route and the target arrival time in the stage before departure. Then, after the second departure time predicted value is calculated, the optimal rotation speed estimation device 9g estimates and updates the optimal rotation speed.

As described above, the first departure time predicted value is predicted based on the time from when the main engine of the ship stops until the next departure (ship stop time). However, the ship stop time is likely to vary greatly depending on the operation status of the ship, and there is a risk that the error from the actual departure time will increase.

On the other hand, in this modification, since the second departure time predicted value is predicted based on the warm-up operation time, there is a high possibility that it is closer to the actual departure time than the first departure time predicted value. Therefore, although the estimated time is later than the predicted value of the first departure time, the departure time of the ship can be predicted relatively accurately, and as a result, the accurate optimum rotational speed can be estimated.

Further, the navigation plan input unit 31 outputs the departure time fixed value detected by the departure time detection unit 43 together with the navigation route and the target arrival time. Then, the optimum rotational speed estimation device 9g estimates and updates the optimal rotational speed after the departure time fixed value is detected. As described above, in the present modification, the optimum rotational speed is estimated based on the actual departure time, so that the optimal rotational speed can be predicted more accurately. Moreover, in this modified example, since the departure time fixed value is automatically input, it is possible to save the user from inputting the departure time.

In this modification, statistics may be taken for each day of the week, and the first departure time may be estimated based on the statistical results.

(9) FIG. 20 is a block diagram illustrating a configuration of the departure time automatic input unit 40a of the estimation apparatus according to the modification. Unlike the departure time automatic input unit 40 shown in FIG. 19, the departure time automatic input unit 40 a of the estimation apparatus according to the present modification further includes an external environment detection unit 48.

In this modification, the second storage unit 45 stores the external environment (for example, temperature and humidity) detected by the external environment detection unit 48 when the warm-up operation has been performed in the past, for a plurality of warm-up operation times. Is stored in association with each of the above. And in this modification, the 2nd departure time estimation part 47 estimates the 2nd departure time based also on the external environment memorize | stored corresponding to each warming-up operation time.

The time (ie, warm-up operation time) from when the main engine is started until it is ready to sail varies depending on the season, for example. Specifically, since it takes more time for the engine to warm in cold weather than in hot weather, it is necessary to extend the warm-up time.

On the other hand, as in this modification, it is possible to estimate the optimum rotational speed more accurately by estimating the second departure time in consideration of the external environment such as temperature.

(10) FIG. 21 is a block diagram showing a configuration of an optimal rotational speed estimation system 1h provided with an optimal rotational speed estimation apparatus 9h configured by removing the display unit 5 from the optimal rotational speed estimation apparatus 9b shown in FIG. is there. The optimal rotational speed estimation system 1h includes an optimal rotational speed estimation device 9h, a transmission unit 18a, and a reception unit 18b.

The optimum rotation speed estimation device 9h is provided at a position different from the own ship (for example, the data center 19 provided on land as an example). As described above, the optimum rotational speed estimation device 9h is configured by removing the display unit 5 from the optimal rotational speed estimation device 9b shown in FIG. Since this is the same, the description thereof is omitted.

Both the transmission unit 18a and the reception unit 18b are provided at a position different from the data center 19 described above (for example, the ship). The transmission unit 18a transmits data relating to the navigation plan of the ship (the navigation route, the departure time, and the estimated arrival time) input by the user to the optimum rotational speed estimation device 9h of the data center 19. The receiving unit 18b receives data related to the optimum rotational speed estimated by the optimum rotational speed estimation device 9h. Data relating to the optimum rotational speed received by the receiving unit 18 b is displayed on the display unit 5.

As described above, in the optimal rotational speed estimation system 1h, the optimal rotational speed estimation device 9h having a relatively large calculation load can be provided in a place different from the own ship. As a result, the optimum number of revolutions can be obtained without providing the optimum number of revolutions estimation device 9h on the own ship, so that the number of devices mounted on the own ship can be reduced.

In FIG. 21, the optimum rotation speed estimation device 9b illustrated in FIG. 8 is described as an example of the optimum rotation speed estimation device provided in the optimum rotation speed estimation system 1h. An estimation device may be provided. For example, the optimal rotational speed estimation system may include the optimal rotational speed estimation device described in the above-described embodiments and modifications.

Moreover, although the optimal rotational speed estimation device 9h of the optimal rotational speed estimation system 1h according to the present modified example estimates the optimal rotational speed based on the tidal current predicted value and the wind speed predicted value, the present invention is not limited to this. Specifically, it is not a predicted value announced by a public institution, but the surface flow velocity actually measured by a tidal meter, wind propulsion speed (propulsion speed of own ship caused by wind force), the influence of waves, The optimum rotational speed may be estimated based on the propulsion performance of the ship, the deterioration state of the main engine of the ship, and the like.

(11) In the above-described embodiment and each modification, the learning data can be supplemented when the learning data is not sufficiently accumulated.

FIG. 22 is a schematic diagram for explaining learning data complementation. Since the shape of the ship is generally bilaterally symmetric, it is expected that the wind power characteristics (the traveling speed of the ship due to the wind direction and wind speed) are also bilaterally symmetric. Specifically, for example, a ship that is sailing under certain conditions receives 45 degrees of wind behind the starboard and 45 degrees of wind behind the starboard (the wind speed is the same). Then, the traveling direction is expected to be symmetrical. Thus, with reference to FIG. 22, for example, when the propeller speed is a predetermined speed, wind direction port backward 45 degrees, when the wind speed is a predetermined magnitude, of the ground speed was V _G, the learned Based on the data, the data can be supplemented as follows. Specifically, the size of the propeller speed and the wind speed is the same as the learning data, it is possible to wind direction starboard aft 45 degrees, as learning data when the complements the vector V _'G obtained by mirror-inverting . By supplementing the learning data in this way, it is possible to accurately estimate the optimum rotational speed even at an initial stage where the learning data is not sufficiently accumulated, for example.

1f Rotational speed controller 1h Optimal rotational speed estimation system 9, 9b, 9c, 9d, 9e, 9g, 9h Optimal rotational speed estimator 12, 12e Water speed output part (water speed candidate value calculation part)
15, 15c, 15d Optimal rotation speed estimation unit 34 Water speed prediction unit 35 Speed candidate value output unit 36 Wind speed prediction value output unit

Claims (12)

1. An optimal rotational speed estimation device for estimating an optimal rotational speed of the propeller in a ship propelled by rotation of a propeller,
   The ground velocity vector of the ship necessary for the ship navigating along the preset navigation route to arrive at the destination by the target arrival time, and the surface layer flow velocity at the target point that is a point on the navigation route A water speed prediction unit that predicts a water speed prediction value that is a water speed vector at the target point required to arrive at the destination by the target arrival time based on the predicted value of
   A wind speed predicted value output unit that outputs a wind speed predicted value that is a wind speed vector predicted to act on the ship at the target point;
   A rotation number candidate value output unit that outputs a plurality of rotation number candidate values that are candidates for the optimum rotation number, and are data having different values indicating the rotation number of the propeller,
   The wind speed prediction value at the target point and the plurality of rotation number candidate values are input, and values corresponding to the respective conditions specified by the combination of the wind speed prediction value and the rotation number candidate value are determined at the target point. A water speed candidate value calculation unit that outputs a water speed candidate value that is a candidate for the water speed vector of the ship;
   The optimum rotational speed value corresponding to the water speed candidate value having the smallest difference from the water speed predicted value among the plurality of water speed candidate values is estimated as the optimum rotational speed at the target point. A rotation speed estimation unit;
   An optimum rotational speed estimation device comprising:
2. In the optimal rotation speed estimation device according to claim 1,
   The water speed candidate value calculation unit is configured using a neural network,
   Each of at least two input units to which any one of the data regarding the wind speed prediction value and the data regarding the rotation speed candidate value is input,
   An output unit that outputs the water speed candidate value,
   The optimum rotational speed estimation apparatus, wherein a value output from an input side unit in the neural network is multiplied by a coupling coefficient and then transmitted to an output side unit.
3. In the optimal rotation speed estimation device according to claim 2,
   A ground speed calculation unit for calculating a ground speed vector of the ship navigating at sea;
   A propeller rotational speed detector for detecting the rotational speed of the propeller;
   An anemometer mounted on the vessel and measuring a wind velocity vector of wind force with respect to the vessel;
   Further comprising
   Each of the input units receives one of data relating to the rotation speed of the propeller detected by the propeller rotation speed detector and data relating to the wind speed vector measured by the wind speed and anemometer.
   From the output unit, a value corresponding to each condition specified by a combination of the rotation speed of the propeller detected by the propeller rotation speed detection unit and the wind speed vector measured by the wind speed anemometer, Estimated as the water velocity vector of the ship and output as the water velocity estimate,
   While comparing the water speed estimated value and the ground speed vector as the teacher signal calculated by the ground speed calculator, so that the error between the water speed estimated value and the teacher signal is reduced, An optimum rotational speed estimation apparatus, further comprising: an update unit that updates the coupling coefficient.
4. An optimal rotational speed estimation device for estimating an optimal rotational speed of the propeller in a ship propelled by rotation of a propeller,
   The ground velocity vector of the ship necessary for the ship navigating along the preset navigation route to arrive at the destination by the target arrival time, and the surface layer flow velocity at the target point that is a point on the navigation route A water speed prediction unit that predicts a water speed prediction value that is a water speed vector at the target point required to arrive at the destination by the target arrival time based on the predicted value of
   A wind speed predicted value output unit that outputs a wind speed predicted value that is a wind speed vector predicted to act on the ship at the target point;
   A plurality of cell units for storing, for each of the plurality of conditions, a ground speed vector of the ship at each condition specified by a combination of the rotation speed of the propeller and the wind speed vector of the wind force with respect to the ship; A storage unit that stores an average value of the ground speed vectors stored in each cell unit as a water speed vector for each of the conditions corresponding to each cell unit;
   In the storage unit, an optimal rotational speed estimation unit that estimates the rotational speed specified by the predicted wind speed value and the predicted water speed value as the optimal rotational speed;
   An optimum rotational speed estimation device comprising:
5. In the optimal rotation speed estimation device according to claim 4,
   A ground speed calculation unit for calculating a ground speed vector of the ship navigating at sea;
   A propeller rotational speed detector for detecting the rotational speed of the propeller;
   An anemometer mounted on the vessel and measuring a wind velocity vector of wind force with respect to the vessel;
   Further comprising
   The storage unit is configured to detect the rotation speed detected by the propeller rotation speed detection unit when the data necessary for calculation of the ground speed vector is acquired from the ground speed vector calculated by the ground speed calculation unit, And an update unit for storing in the cell unit specified by a combination of the wind velocity vector measured by the wind velocity and anemometer.
6. In the optimal rotation speed estimation device according to any one of claims 1 to 5,
   A ground speed prediction unit that predicts a ground speed prediction value that is a ground speed vector of the ship necessary for the ship navigating along the navigation route to reach a destination by a target arrival time;
   The said water speed prediction part predicts the said water speed prediction value based on the said ground speed vector estimated in the said ground speed prediction part, The optimal rotation speed estimation apparatus characterized by the above-mentioned.
7. In the optimum rotational speed estimation device according to claim 6,
   A navigation plan input unit that inputs the navigation route, the departure time of the ship, and the target arrival time, and outputs the input navigation route, the departure time, and the target arrival time to the ground speed prediction unit And an optimum rotational speed estimation device.
8. In the optimum rotational speed estimation device according to claim 7,
   The departure time is estimated based on at least one of the stop time of the main engine of the ship and the start time of the main engine of the ship, and the estimated departure time is output to the navigation plan input unit as a predicted departure time An optimum rotational speed estimation device, further comprising a departure time estimation unit.
9. In the optimum rotational speed estimation device according to claim 7 or 8,
   A departure time detection unit that detects the departure time based on the rotation speed of the propeller and the ground speed of the ship, and outputs the departure time to the navigation plan input unit as a departure time fixed value. An optimum rotational speed estimation device.
10. In the optimal rotation speed estimation device according to any one of claims 1 to 9,
    An optimum rotational speed estimation device mounted on the ship as the ship.
11. The optimal rotation speed estimation device according to any one of claims 1 to 9, which is mounted in a place different from the ship as a ship,
    It is arranged at a location different from the optimum rotational speed estimation device, and transmits data relating to the navigation route of the own ship, the departure time of the own ship, and the target arrival time of the own ship to the optimum rotational speed estimation device. A transmission unit;
    A receiving unit that is arranged at a different location from the optimal rotational speed estimation device and receives data relating to the optimal rotational speed estimated by the optimal rotational speed estimation device;
    An optimum rotational speed estimation system comprising:
12. The optimal rotation speed estimation device according to any one of claims 1 to 10,
    A rotational speed control unit that controls the rotational speed of the propeller of the ship based on the optimal rotational speed of the propeller of the ship estimated by the optimal rotational speed estimation device;
    A rotation speed control device comprising:

Images